Autogenous - LDna combined analysis

Population label key: The code labels used in the analysis below correspond to the following manuscript labels: AUT = AUTO, MAN = NON-AUTO, NEW = NON-AUTO-FIELD.

# Load tidyverse FIRST to avoid rlang version conflict
library(tidyverse)
library(here)
library(scales)
library(ggrepel)

# Then add LDna v.2.15 library path and load
.libPaths(c("/workspace/lib/ldna_v215", .libPaths()))
library(LDna)
library(reshape2)
library(writexl)

6. Combine the chromosomal data

Clean env and memory

# Remove all objects from the environment
rm(list = ls())

# Run the garbage collector to free up memory
gc()

##           used (Mb) gc trigger  (Mb) max used  (Mb)
## Ncells 1176646 62.9    2232931 119.3  2232931 119.3
## Vcells 1972919 15.1    8388608  64.0  3453300  26.4

Read the plotting data for NEW and AUT

# NEW
NEW1 <- readRDS(here("output", "ldna", "pop", "chr1", "NEW_plot2.rds")) |> mutate(Population = "NEW")
NEW2 <- readRDS(here("output", "ldna", "pop", "chr2", "NEW_plot2.rds")) |> mutate(Population = "NEW")
NEW3 <- readRDS(here("output", "ldna", "pop", "chr3", "NEW_plot2.rds")) |> mutate(Population = "NEW")

# AUT
AUT1 <- readRDS(here("output", "ldna", "pop", "chr1", "AUT_plot2.rds")) |> mutate(Population = "AUT")
AUT2 <- readRDS(here("output", "ldna", "pop", "chr2", "AUT_plot2.rds")) |> mutate(Population = "AUT")
AUT3 <- readRDS(here("output", "ldna", "pop", "chr3", "AUT_plot2.rds")) |> mutate(Population = "AUT")

Bind the objects

albo <- rbind(NEW1, NEW2, NEW3, AUT1, AUT2, AUT3)

head(albo)

##   Chromosome   Cluster   r2    Start      End nSegments nSNPs Population
## 1          1 2098_0.81 0.81  1671072 16303506       225  3339        NEW
## 2          1 2098_0.81 0.81 16308219 16458676       225  3339        NEW
## 3          1 2098_0.81 0.81 16560013 16688706       225  3339        NEW
## 4          1 2098_0.81 0.81 16723593 17338376       225  3339        NEW
## 5          1 2098_0.81 0.81 17376443 17614762       225  3339        NEW
## 6          1 2098_0.81 0.81 17763447 19491473       225  3339        NEW

We can create a table

table1 <- albo |>
  mutate(Size = End - Start) |>
  dplyr::select(
    Population, Chromosome, Cluster, r2, nSegments, nSNPs, Start, End, Size
  ) |>
  arrange(Population, Chromosome, Start)
head(table1)

##   Population Chromosome   Cluster   r2 nSegments nSNPs    Start      End
## 1        AUT          1 1927_0.68 0.68        18    43  1619834  2269308
## 2        AUT          1 1877_0.71 0.71        21    46  3766945  4238554
## 3        AUT          1 1946_0.66 0.66        23    30  4981859  5217622
## 4        AUT          1 1877_0.71 0.71        21    46  5443736 10957198
## 5        AUT          1 1980_0.63 0.63        20    31 11125830 11276238
## 6        AUT          1 1559_0.84 0.84        33    42 11638599 12192074
##      Size
## 1  649474
## 2  471609
## 3  235763
## 4 5513462
## 5  150408
## 6  553475

We can focus on LD blocks equal or bigger than 1Mb

table1 <- table1 %>%
  dplyr::filter(Size >= 1000000) %>%
  dplyr::mutate(`Size (Mb)` = round(Size / 1000000, 2)) # %>%
  # dplyr::select(Size)
head(table1)

##   Population Chromosome   Cluster   r2 nSegments nSNPs     Start       End
## 1        AUT          1 1877_0.71 0.71        21    46   5443736  10957198
## 2        AUT          1 1763_0.77 0.77        30    61  87157392  88199259
## 3        AUT          1 1763_0.77 0.77        30    61  88919855  90254445
## 4        AUT          1 1628_0.82 0.82        26    50 119130691 120305920
## 5        AUT          1 1971_0.64 0.64        29    90 138373561 140570398
## 6        AUT          1 1651_0.81 0.81       519   679 151544898 152551833
##      Size Size (Mb)
## 1 5513462      5.51
## 2 1041867      1.04
## 3 1334590      1.33
## 4 1175229      1.18
## 5 2196837      2.20
## 6 1006935      1.01

Create table

knitr::kable(table1)

Population	Chromosome	Cluster	r2	nSegments	nSNPs	Start	End	Size	Size (Mb)
AUT	1	1877_0.71	0.71	21	46	5443736	10957198	5513462	5.51
AUT	1	1763_0.77	0.77	30	61	87157392	88199259	1041867	1.04
AUT	1	1763_0.77	0.77	30	61	88919855	90254445	1334590	1.33
AUT	1	1628_0.82	0.82	26	50	119130691	120305920	1175229	1.18
AUT	1	1971_0.64	0.64	29	90	138373561	140570398	2196837	2.20
AUT	1	1651_0.81	0.81	519	679	151544898	152551833	1006935	1.01
AUT	1	1673_0.8	0.8	395	486	179031717	180129204	1097487	1.10
AUT	1	1656_0.81	0.81	536	691	242081344	243905804	1824460	1.82
AUT	1	1656_0.81	0.81	536	691	247353243	249207733	1854490	1.85
AUT	1	1673_0.8	0.8	395	486	260581858	262016624	1434766	1.43
AUT	1	1976_0.63	0.63	18	90	266160984	270116064	3955080	3.96
AUT	1	1934_0.67	0.67	19	40	282087582	284546412	2458830	2.46
AUT	2	3065_0.81	0.81	1933	4652	49798927	52237467	2438540	2.44
AUT	2	3065_0.81	0.81	1933	4652	101467688	102825816	1358128	1.36
AUT	2	3065_0.81	0.81	1933	4652	103572137	106204056	2631919	2.63
AUT	2	3065_0.81	0.81	1933	4652	124168259	126538488	2370229	2.37
AUT	2	3065_0.81	0.81	1933	4652	130361623	131660157	1298534	1.30
AUT	2	3065_0.81	0.81	1933	4652	137777373	138981409	1204036	1.20
AUT	2	3065_0.81	0.81	1933	4652	141440521	142703746	1263225	1.26
AUT	2	3065_0.81	0.81	1933	4652	149078628	153093408	4014780	4.01
AUT	2	3065_0.81	0.81	1933	4652	153767456	155771880	2004424	2.00
AUT	2	3066_0.81	0.81	797	989	156275046	158102348	1827302	1.83
AUT	2	3533_0.6	0.6	33	72	328800255	329979871	1179616	1.18
AUT	2	3531_0.61	0.61	21	31	333084727	334205193	1120466	1.12
AUT	2	3215_0.78	0.78	97	324	390518548	391668996	1150448	1.15
AUT	2	3215_0.78	0.78	97	324	391711273	392777580	1066307	1.07
AUT	2	3215_0.78	0.78	97	324	397107735	401367529	4259794	4.26
AUT	2	3215_0.78	0.78	97	324	405893739	407224834	1331095	1.33
AUT	2	3138_0.8	0.8	26	61	407321663	411100836	3779173	3.78
AUT	2	3138_0.8	0.8	26	61	411409101	412997990	1588889	1.59
AUT	2	3065_0.81	0.81	1933	4652	445201256	447678524	2477268	2.48
AUT	2	3065_0.81	0.81	1933	4652	447843218	448906645	1063427	1.06
AUT	2	3065_0.81	0.81	1933	4652	466090283	467282916	1192633	1.19
AUT	2	3065_0.81	0.81	1933	4652	495634845	497303862	1669017	1.67
AUT	2	3065_0.81	0.81	1933	4652	502247398	503278166	1030768	1.03
AUT	2	3065_0.81	0.81	1933	4652	504551083	505702718	1151635	1.15
AUT	2	3065_0.81	0.81	1933	4652	520825136	523110071	2284935	2.28
AUT	3	2950_0.81	0.81	1634	6373	15260009	16679033	1419024	1.42
AUT	3	2950_0.81	0.81	1634	6373	22221783	24876231	2654448	2.65
AUT	3	2950_0.81	0.81	1634	6373	57597040	60996345	3399305	3.40
AUT	3	2950_0.81	0.81	1634	6373	64323643	66464901	2141258	2.14
AUT	3	2950_0.81	0.81	1634	6373	67025564	68305791	1280227	1.28
AUT	3	2950_0.81	0.81	1634	6373	69348616	70416221	1067605	1.07
AUT	3	3292_0.56	0.56	10	37	75010838	76064737	1053899	1.05
AUT	3	2950_0.81	0.81	1634	6373	110079720	112277286	2197566	2.20
AUT	3	2950_0.81	0.81	1634	6373	112497013	113712759	1215746	1.22
AUT	3	2950_0.81	0.81	1634	6373	116172157	117763299	1591142	1.59
AUT	3	3129_0.76	0.76	105	311	197419987	198725960	1305973	1.31
AUT	3	3129_0.76	0.76	105	311	199372953	200641223	1268270	1.27
AUT	3	3195_0.73	0.73	47	94	213789681	215749074	1959393	1.96
AUT	3	2809_0.84	0.84	17	30	217392863	218946788	1553925	1.55
AUT	3	2950_0.81	0.81	1634	6373	223089294	224371815	1282521	1.28
AUT	3	2950_0.81	0.81	1634	6373	252429715	257705872	5276157	5.28
AUT	3	2950_0.81	0.81	1634	6373	261367232	263434740	2067508	2.07
AUT	3	2950_0.81	0.81	1634	6373	263696140	264901249	1205109	1.21
AUT	3	2950_0.81	0.81	1634	6373	267045795	268729206	1683411	1.68
AUT	3	2950_0.81	0.81	1634	6373	269707578	272924524	3216946	3.22
AUT	3	2950_0.81	0.81	1634	6373	284309274	285864116	1554842	1.55
AUT	3	2950_0.81	0.81	1634	6373	296354064	297430287	1076223	1.08
AUT	3	2950_0.81	0.81	1634	6373	314111993	315235784	1123791	1.12
AUT	3	2950_0.81	0.81	1634	6373	340649572	342828725	2179153	2.18
AUT	3	2950_0.81	0.81	1634	6373	345522786	349025972	3503186	3.50
AUT	3	2950_0.81	0.81	1634	6373	378164815	379392861	1228046	1.23
AUT	3	2950_0.81	0.81	1634	6373	380732751	381773127	1040376	1.04
AUT	3	2950_0.81	0.81	1634	6373	437388093	438768367	1380274	1.38
NEW	1	2098_0.81	0.81	225	3339	1671072	16303506	14632434	14.63
NEW	1	2098_0.81	0.81	225	3339	17763447	19491473	1728026	1.73
NEW	1	2098_0.81	0.81	225	3339	31462771	33110064	1647293	1.65
NEW	1	2098_0.81	0.81	225	3339	33812253	39535721	5723468	5.72
NEW	1	2098_0.81	0.81	225	3339	42912079	45617370	2705291	2.71
NEW	1	2098_0.81	0.81	225	3339	45813378	46852266	1038888	1.04
NEW	1	2098_0.81	0.81	225	3339	49058652	52982032	3923380	3.92
NEW	1	2098_0.81	0.81	225	3339	53104692	57458477	4353785	4.35
NEW	1	2098_0.81	0.81	225	3339	57603304	81674467	24071163	24.07
NEW	1	2098_0.81	0.81	225	3339	84125006	85286331	1161325	1.16
NEW	1	2257_0.78	0.78	21	49	88409052	90437664	2028612	2.03
NEW	1	2257_0.78	0.78	21	49	92128407	93161109	1032702	1.03
NEW	1	2098_0.81	0.81	225	3339	96662783	99757810	3095027	3.10
NEW	1	2098_0.81	0.81	225	3339	109454635	110939058	1484423	1.48
NEW	1	2098_0.81	0.81	225	3339	111088239	115093306	4005067	4.01
NEW	1	2098_0.81	0.81	225	3339	116539985	117786853	1246868	1.25
NEW	1	2098_0.81	0.81	225	3339	118382563	133808459	15425896	15.43
NEW	1	2098_0.81	0.81	225	3339	134311499	152641345	18329846	18.33
NEW	1	2098_0.81	0.81	225	3339	155511543	168919506	13407963	13.41
NEW	1	2098_0.81	0.81	225	3339	169035292	173049491	4014199	4.01
NEW	1	2098_0.81	0.81	225	3339	175562655	184285228	8722573	8.72
NEW	1	2098_0.81	0.81	225	3339	184822512	191340592	6518080	6.52
NEW	1	2098_0.81	0.81	225	3339	191491743	192497058	1005315	1.01
NEW	1	2098_0.81	0.81	225	3339	193238959	195536041	2297082	2.30
NEW	1	2098_0.81	0.81	225	3339	196644737	199686032	3041295	3.04
NEW	1	2098_0.81	0.81	225	3339	199758742	207076243	7317501	7.32
NEW	1	2098_0.81	0.81	225	3339	210193969	212041495	1847526	1.85
NEW	1	2098_0.81	0.81	225	3339	217126621	230413950	13287329	13.29
NEW	1	2098_0.81	0.81	225	3339	230429247	241512774	11083527	11.08
NEW	1	2098_0.81	0.81	225	3339	241581708	245964256	4382548	4.38
NEW	1	2098_0.81	0.81	225	3339	246194066	250559827	4365761	4.37
NEW	1	2098_0.81	0.81	225	3339	250638063	252000239	1362176	1.36
NEW	1	2098_0.81	0.81	225	3339	252144386	255284772	3140386	3.14
NEW	1	2098_0.81	0.81	225	3339	255471960	260032529	4560569	4.56
NEW	1	2098_0.81	0.81	225	3339	262169514	263823952	1654438	1.65
NEW	1	2098_0.81	0.81	225	3339	263937222	271417059	7479837	7.48
NEW	1	2098_0.81	0.81	225	3339	274018327	291005909	16987582	16.99
NEW	1	2098_0.81	0.81	225	3339	291128858	294274102	3145244	3.15
NEW	1	2098_0.81	0.81	225	3339	294683970	297498464	2814494	2.81
NEW	1	2098_0.81	0.81	225	3339	299222427	302129356	2906929	2.91
NEW	1	2098_0.81	0.81	225	3339	302199736	305506598	3306862	3.31
NEW	1	2098_0.81	0.81	225	3339	305564825	308828617	3263792	3.26
NEW	1	2098_0.81	0.81	225	3339	308845316	310046723	1201407	1.20
NEW	1	2098_0.81	0.81	225	3339	310436955	312893712	2456757	2.46
NEW	1	2098_0.81	0.81	225	3339	313386794	321651633	8264839	8.26
NEW	1	2098_0.81	0.81	225	3339	329288148	330792056	1503908	1.50
NEW	1	2098_0.81	0.81	225	3339	331903843	334134626	2230783	2.23
NEW	1	2098_0.81	0.81	225	3339	349747385	350752606	1005221	1.01
NEW	1	2098_0.81	0.81	225	3339	350759454	352036196	1276742	1.28
NEW	1	2098_0.81	0.81	225	3339	352250603	353457242	1206639	1.21
NEW	1	2098_0.81	0.81	225	3339	355814525	356832851	1018326	1.02
NEW	1	2098_0.81	0.81	225	3339	357649351	360432526	2783175	2.78
NEW	1	2098_0.81	0.81	225	3339	361376691	362625358	1248667	1.25
NEW	1	2098_0.81	0.81	225	3339	363346050	365490174	2144124	2.14
NEW	1	2098_0.81	0.81	225	3339	365516884	367009263	1492379	1.49
NEW	1	2098_0.81	0.81	225	3339	367076124	368115714	1039590	1.04
NEW	1	2098_0.81	0.81	225	3339	368209240	370940654	2731414	2.73
NEW	2	3393_0.8	0.8	1027	3235	224747	2320220	2095473	2.10
NEW	2	3393_0.8	0.8	1027	3235	3767940	5516504	1748564	1.75
NEW	2	3404_0.8	0.8	905	1502	20865308	23384980	2519672	2.52
NEW	2	3393_0.8	0.8	1027	3235	32333986	33684664	1350678	1.35
NEW	2	3393_0.8	0.8	1027	3235	37484773	39477392	1992619	1.99
NEW	2	3404_0.8	0.8	905	1502	47841211	49223392	1382181	1.38
NEW	2	3393_0.8	0.8	1027	3235	60198806	63385698	3186892	3.19
NEW	2	3404_0.8	0.8	905	1502	63957749	65028705	1070956	1.07
NEW	2	3393_0.8	0.8	1027	3235	71334985	75185080	3850095	3.85
NEW	2	3404_0.8	0.8	905	1502	75680372	77722092	2041720	2.04
NEW	2	3404_0.8	0.8	905	1502	79048197	81335266	2287069	2.29
NEW	2	3393_0.8	0.8	1027	3235	86262808	87274287	1011479	1.01
NEW	2	3393_0.8	0.8	1027	3235	89422203	90648941	1226738	1.23
NEW	2	3393_0.8	0.8	1027	3235	92717918	93748781	1030863	1.03
NEW	2	3393_0.8	0.8	1027	3235	100600773	102052192	1451419	1.45
NEW	2	3393_0.8	0.8	1027	3235	107385063	111397305	4012242	4.01
NEW	2	3393_0.8	0.8	1027	3235	112239445	113398794	1159349	1.16
NEW	2	3404_0.8	0.8	905	1502	115171624	117422202	2250578	2.25
NEW	2	3393_0.8	0.8	1027	3235	120642568	121789169	1146601	1.15
NEW	2	3404_0.8	0.8	905	1502	129752494	132084935	2332441	2.33
NEW	2	3404_0.8	0.8	905	1502	134691453	136254657	1563204	1.56
NEW	2	3393_0.8	0.8	1027	3235	137286537	138732635	1446098	1.45
NEW	2	3404_0.8	0.8	905	1502	141517826	144428065	2910239	2.91
NEW	2	3404_0.8	0.8	905	1502	145519669	147610899	2091230	2.09
NEW	2	3393_0.8	0.8	1027	3235	147686588	148800994	1114406	1.11
NEW	2	3404_0.8	0.8	905	1502	149738780	153093408	3354628	3.35
NEW	2	3404_0.8	0.8	905	1502	159957622	162105222	2147600	2.15
NEW	2	3404_0.8	0.8	905	1502	164942040	166163633	1221593	1.22
NEW	2	3404_0.8	0.8	905	1502	176121303	178566001	2444698	2.44
NEW	2	3393_0.8	0.8	1027	3235	184599662	185697190	1097528	1.10
NEW	2	3404_0.8	0.8	905	1502	187872447	189338359	1465912	1.47
NEW	2	3393_0.8	0.8	1027	3235	196919065	198241184	1322119	1.32
NEW	2	3393_0.8	0.8	1027	3235	198399859	199866764	1466905	1.47
NEW	2	3393_0.8	0.8	1027	3235	200640262	201766366	1126104	1.13
NEW	2	3393_0.8	0.8	1027	3235	211336217	214704214	3367997	3.37
NEW	2	3393_0.8	0.8	1027	3235	221458739	227293746	5835007	5.84
NEW	2	3404_0.8	0.8	905	1502	231449434	232560068	1110634	1.11
NEW	2	3404_0.8	0.8	905	1502	234706206	236580351	1874145	1.87
NEW	2	3393_0.8	0.8	1027	3235	250661099	251754487	1093388	1.09
NEW	2	3393_0.8	0.8	1027	3235	269725161	271001058	1275897	1.28
NEW	2	3393_0.8	0.8	1027	3235	272699658	274730588	2030930	2.03
NEW	2	3393_0.8	0.8	1027	3235	281488259	282754807	1266548	1.27
NEW	2	3393_0.8	0.8	1027	3235	298229333	300182152	1952819	1.95
NEW	2	3404_0.8	0.8	905	1502	301661105	304313204	2652099	2.65
NEW	2	3404_0.8	0.8	905	1502	304515783	306218388	1702605	1.70
NEW	2	3393_0.8	0.8	1027	3235	309917339	318159364	8242025	8.24
NEW	2	3393_0.8	0.8	1027	3235	322231858	323875574	1643716	1.64
NEW	2	3404_0.8	0.8	905	1502	331446801	335080127	3633326	3.63
NEW	2	3393_0.8	0.8	1027	3235	338547271	341098241	2550970	2.55
NEW	2	3404_0.8	0.8	905	1502	343930528	345470965	1540437	1.54
NEW	2	3404_0.8	0.8	905	1502	345633769	354870721	9236952	9.24
NEW	2	3404_0.8	0.8	905	1502	363676430	365753357	2076927	2.08
NEW	2	3393_0.8	0.8	1027	3235	371505037	373052338	1547301	1.55
NEW	2	3393_0.8	0.8	1027	3235	373133669	376347397	3213728	3.21
NEW	2	3393_0.8	0.8	1027	3235	379361111	381543575	2182464	2.18
NEW	2	3393_0.8	0.8	1027	3235	382522637	383782785	1260148	1.26
NEW	2	3393_0.8	0.8	1027	3235	394747517	395926654	1179137	1.18
NEW	2	3404_0.8	0.8	905	1502	407185045	409429909	2244864	2.24
NEW	2	3393_0.8	0.8	1027	3235	423413849	425459834	2045985	2.05
NEW	2	3393_0.8	0.8	1027	3235	426632333	428968851	2336518	2.34
NEW	2	3393_0.8	0.8	1027	3235	434926662	436108135	1181473	1.18
NEW	2	3404_0.8	0.8	905	1502	445321096	447678524	2357428	2.36
NEW	2	3393_0.8	0.8	1027	3235	450997412	452946043	1948631	1.95
NEW	2	3393_0.8	0.8	1027	3235	489711160	491614193	1903033	1.90
NEW	2	3393_0.8	0.8	1027	3235	505908537	507012127	1103590	1.10
NEW	2	3393_0.8	0.8	1027	3235	518565796	519621236	1055440	1.06
NEW	2	3393_0.8	0.8	1027	3235	522038684	523113152	1074468	1.07
NEW	2	3393_0.8	0.8	1027	3235	533383712	534904257	1520545	1.52
NEW	2	3393_0.8	0.8	1027	3235	546386096	547694728	1308632	1.31
NEW	2	3393_0.8	0.8	1027	3235	559442893	561613146	2170253	2.17
NEW	2	3393_0.8	0.8	1027	3235	584590398	585804603	1214205	1.21
NEW	3	2836_0.81	0.81	567	1122	138261	1143824	1005563	1.01
NEW	3	2836_0.81	0.81	567	1122	6888798	8280336	1391538	1.39
NEW	3	2837_0.81	0.81	602	1668	8741873	16401719	7659846	7.66
NEW	3	2837_0.81	0.81	602	1668	30868364	32084271	1215907	1.22
NEW	3	2837_0.81	0.81	602	1668	33607382	34770651	1163269	1.16
NEW	3	2837_0.81	0.81	602	1668	38220097	39497877	1277780	1.28
NEW	3	2837_0.81	0.81	602	1668	41999164	43351711	1352547	1.35
NEW	3	2837_0.81	0.81	602	1668	45971148	49553360	3582212	3.58
NEW	3	2837_0.81	0.81	602	1668	53278835	54796696	1517861	1.52
NEW	3	2837_0.81	0.81	602	1668	57016980	58476637	1459657	1.46
NEW	3	2844_0.81	0.81	94	142	62431035	64197177	1766142	1.77
NEW	3	2837_0.81	0.81	602	1668	66551211	68843398	2292187	2.29
NEW	3	2837_0.81	0.81	602	1668	70979233	76622043	5642810	5.64
NEW	3	2837_0.81	0.81	602	1668	79033650	80149798	1116148	1.12
NEW	3	2837_0.81	0.81	602	1668	82956837	84368104	1411267	1.41
NEW	3	2836_0.81	0.81	567	1122	87052596	88327934	1275338	1.28
NEW	3	2837_0.81	0.81	602	1668	96649526	97704550	1055024	1.06
NEW	3	2837_0.81	0.81	602	1668	103304460	105510232	2205772	2.21
NEW	3	2837_0.81	0.81	602	1668	106246872	108915149	2668277	2.67
NEW	3	2837_0.81	0.81	602	1668	110248778	112627576	2378798	2.38
NEW	3	2837_0.81	0.81	602	1668	117801583	119196324	1394741	1.39
NEW	3	2837_0.81	0.81	602	1668	122688806	125806099	3117293	3.12
NEW	3	2837_0.81	0.81	602	1668	126000611	132461516	6460905	6.46
NEW	3	2837_0.81	0.81	602	1668	134726992	142770788	8043796	8.04
NEW	3	2837_0.81	0.81	602	1668	143504855	146770743	3265888	3.27
NEW	3	2837_0.81	0.81	602	1668	149536509	156001191	6464682	6.46
NEW	3	2837_0.81	0.81	602	1668	158530473	159797863	1267390	1.27
NEW	3	2837_0.81	0.81	602	1668	161308720	163859867	2551147	2.55
NEW	3	2837_0.81	0.81	602	1668	164412695	165638650	1225955	1.23
NEW	3	2837_0.81	0.81	602	1668	165745584	169750947	4005363	4.01
NEW	3	2837_0.81	0.81	602	1668	173459259	182850273	9391014	9.39
NEW	3	2837_0.81	0.81	602	1668	183591308	191456216	7864908	7.86
NEW	3	2837_0.81	0.81	602	1668	191547834	194909609	3361775	3.36
NEW	3	2837_0.81	0.81	602	1668	197419987	208785670	11365683	11.37
NEW	3	2837_0.81	0.81	602	1668	209544043	212578519	3034476	3.03
NEW	3	2837_0.81	0.81	602	1668	212882391	219711403	6829012	6.83
NEW	3	2837_0.81	0.81	602	1668	220295952	223586999	3291047	3.29
NEW	3	2837_0.81	0.81	602	1668	224412047	226630195	2218148	2.22
NEW	3	2837_0.81	0.81	602	1668	227290780	229701667	2410887	2.41
NEW	3	2837_0.81	0.81	602	1668	238924438	243184338	4259900	4.26
NEW	3	2837_0.81	0.81	602	1668	244529416	246058521	1529105	1.53
NEW	3	4066_0.72	0.72	7	42	248606503	250684517	2078014	2.08
NEW	3	2837_0.81	0.81	602	1668	252765819	258190930	5425111	5.43
NEW	3	2837_0.81	0.81	602	1668	260250588	261292851	1042263	1.04
NEW	3	2836_0.81	0.81	567	1122	266966314	268898469	1932155	1.93
NEW	3	2837_0.81	0.81	602	1668	269155423	274126769	4971346	4.97
NEW	3	2837_0.81	0.81	602	1668	274697733	276432605	1734872	1.73
NEW	3	2836_0.81	0.81	567	1122	276462623	279021064	2558441	2.56
NEW	3	2837_0.81	0.81	602	1668	280594192	282048225	1454033	1.45
NEW	3	2837_0.81	0.81	602	1668	286337276	287471025	1133749	1.13
NEW	3	2836_0.81	0.81	567	1122	288896346	290130685	1234339	1.23
NEW	3	2837_0.81	0.81	602	1668	291357677	293293846	1936169	1.94
NEW	3	2837_0.81	0.81	602	1668	296354064	298088579	1734515	1.73
NEW	3	2837_0.81	0.81	602	1668	299533420	301080582	1547162	1.55
NEW	3	2837_0.81	0.81	602	1668	302091398	303360496	1269098	1.27
NEW	3	2837_0.81	0.81	602	1668	303715842	306464838	2748996	2.75
NEW	3	2837_0.81	0.81	602	1668	311114136	313584547	2470411	2.47
NEW	3	2837_0.81	0.81	602	1668	315936740	317289268	1352528	1.35
NEW	3	2836_0.81	0.81	567	1122	320805786	322094119	1288333	1.29
NEW	3	2837_0.81	0.81	602	1668	330738652	332126201	1387549	1.39
NEW	3	2837_0.81	0.81	602	1668	339919173	342105404	2186231	2.19
NEW	3	2836_0.81	0.81	567	1122	344380481	345522786	1142305	1.14
NEW	3	2837_0.81	0.81	602	1668	370379158	371501078	1121920	1.12
NEW	3	2837_0.81	0.81	602	1668	380236644	381564291	1327647	1.33
NEW	3	2837_0.81	0.81	602	1668	382176532	383384925	1208393	1.21
NEW	3	2837_0.81	0.81	602	1668	404173993	405714900	1540907	1.54
NEW	3	2836_0.81	0.81	567	1122	428481578	430261142	1779564	1.78
NEW	3	2836_0.81	0.81	567	1122	437336558	438485871	1149313	1.15
NEW	3	2837_0.81	0.81	602	1668	438979662	440553449	1573787	1.57
NEW	3	2836_0.81	0.81	567	1122	447077906	448164929	1087023	1.09
NEW	3	2837_0.81	0.81	602	1668	459111122	461437206	2326084	2.33
NEW	3	2836_0.81	0.81	567	1122	463741283	464793077	1051794	1.05
NEW	3	2836_0.81	0.81	567	1122	466877065	470726943	3849878	3.85
NEW	3	2837_0.81	0.81	602	1668	470834558	472278174	1443616	1.44
NEW	3	2837_0.81	0.81	602	1668	477874059	479070412	1196353	1.20
NEW	3	2837_0.81	0.81	602	1668	482358967	483846198	1487231	1.49
NEW	3	2837_0.81	0.81	602	1668	483851021	485203479	1352458	1.35

We can create a facet plot now for all chromosomes

# To plot only clusters equal or bigger than 1Mb
albo2 <- table1 |> dplyr::filter(Size >= 1000000)

# Function to format numbers as Mb
label_mb <- function(x) {
  sprintf("%.0fMb", x / 1e6)
}

# Plot it
ggplot(albo2, aes(xmin = Start, xmax = End, ymin = 0, ymax = Size)) +
  geom_rect(aes(fill = as.factor(Cluster)), color = "black", linewidth = 0.2) +
  scale_x_continuous(labels = label_mb, breaks = pretty_breaks(n = 3)) +
  scale_y_continuous(labels = label_mb, breaks = pretty_breaks(n = 5)) +
  labs(x = "Position", y = "Cluster Size") +
  theme_minimal() +
  theme(
    axis.text.y = element_text(margin = margin(t = 0, r = 5, b = 0, l = 5)),
    axis.ticks.y = element_blank(),
    panel.grid.major.x = element_line(color = "gray", linetype = "dotted"),
    strip.background = element_rect(fill = "#e8e8e8", colour = NA),
    panel.grid.minor.x = element_blank(),
    legend.position = "none",
    panel.spacing.x = unit(1, "lines")  # Adjust the unit and number to increase space as needed
  ) +
  facet_grid(Population ~ Chromosome, scales = "fixed", space = "fixed") +
  guides(fill = "none")

# Use ggsave to save the plot as a PDF
# ggsave(
#   filename = here("output", "ldna", "AUT_NEW_fixed.pdf"),
#   device = "pdf",
#   width = 10,
#   height = 5,
#   units = "in"
# )

Make each plot with different scales

# Plot it
ggplot(albo2, aes(xmin = Start, xmax = End, ymin = 0, ymax = Size)) +
  geom_rect(aes(fill = as.factor(Cluster)), color = "black", linewidth = 0.2) +
  scale_x_continuous(labels = label_mb, breaks = pretty_breaks(n = 3)) +
  scale_y_continuous(labels = label_mb, breaks = pretty_breaks(n = 5)) +
  labs(x = "Position", y = "Cluster Size") +
  theme_minimal() +
  theme(
    axis.text.y = element_text(margin = margin(t = 0, r = 5, b = 0, l = 5)),
    axis.ticks.y = element_blank(),
    panel.grid.major.x = element_line(color = "gray", linetype = "dotted"),
    panel.grid.minor.x = element_blank(),
    # strip.background = element_rect(fill = "#e8e8e8", colour = NA),
    legend.position = "none",
    panel.spacing.x = unit(1, "lines")
  ) +
  facet_wrap(~ Population + Chromosome, scales = "free_y", ncol = 3) +  # Free y scale, and each chromosome gets its own row
  guides(fill = "none")

# Use ggsave to save the plot as a PDF
# ggsave(
#   filename = here("output", "ldna", "AUT_NEW_free.pdf"),
#   device = "pdf",
#   width = 8,
#   height = 5,
#   units = "in"
# )

We can also remove the large clusters and plot with fixed scale to look at the cluster between 1 and 10Mb

# To plot only clusters equal or bigger than 1Mb but less that 10Mb
albo3 <- albo2 |> dplyr::filter(Size >= 1000000, Size <= 10000000)


# Plot it
ggplot(albo3, aes(xmin = Start, xmax = End, ymin = 0, ymax = Size)) +
  geom_rect(aes(fill = as.factor(Cluster)), color = "black", linewidth = 0.2) +
  scale_x_continuous(labels = label_mb, breaks = pretty_breaks(n = 3)) +
  scale_y_continuous(labels = label_mb, breaks = pretty_breaks(n = 5)) +
  labs(x = "Position", y = "Cluster Size") +
  theme_minimal() +
  theme(
    axis.text.y = element_text(margin = margin(t = 0, r = 5, b = 0, l = 5)),
    axis.ticks.y = element_blank(),
    panel.grid.major.x = element_line(color = "gray", linetype = "dotted"),
    strip.background = element_rect(fill = "#e8e8e8", colour = NA),
    panel.grid.minor.x = element_blank(),
    legend.position = "none",
    panel.spacing.x = unit(1, "lines")  # Adjust the unit and number to increase space as needed
  ) +
  facet_grid(Population ~ Chromosome, scales = "fixed", space = "fixed") +
  guides(fill = "none")

# Use ggsave to save the plot as a PDF
# ggsave(
#   filename = here("output", "ldna", "AUT_NEW_fixed_1_to_10Mb.pdf"),
#   device = "pdf",
#   width = 8,
#   height = 5,
#   units = "in"
# )

It seems that the linkage patters are quite different from AUT to the wild population. I am not sure why we are seeing clusters at such long distance the wild population for chromosome 2 and 3

We could do the analysis by sex, but we only have 13 females and 15 males in AUT. Perhaps we could use the same number of samples for each. However, the sample size will be too small still.

7. Plot SNPs on DE genes with LD blocks

snps_scan <-
  read.table(
    # here("output", "pcadapt", "man_aut_common_SNPs_pcadapt_outflank.txt"),
    here("output", "snpeff", "SNPs_79_DE.txt"),
    stringsAsFactors = FALSE
  ) |>
  dplyr::rename(
    SNP = V1
  )

head(snps_scan)

##            SNP
## 1 AX-583054970
## 2 AX-583055828
## 3 AX-583093532
## 4 AX-583142560
## 5 AX-583237406
## 6 AX-583279927

Import bim file

# Import the function
source(
  here(
    "notebooks", "helpers", "import_bim.R")
)

# Import the data
snps <- import_bim(here("output", "ldna", "files", "file1.bim"))

# Check it
head(snps)

## # A tibble: 6 x 6
##   Scaffold SNP             Cm Position Allele1 Allele2
##   <chr>    <chr>        <int>    <dbl> <chr>   <chr>  
## 1 1        AX-581444870     0    97856 C       T      
## 2 1        AX-583035083     0   305518 A       G      
## 3 1        AX-583035102     0   308124 A       G      
## 4 1        AX-583033342     0   315059 C       G      
## 5 1        AX-583035163     0   315386 A       G      
## 6 1        AX-583033356     0   315674 C       T

Merge the objects

merged_snps <- inner_join(snps_scan, snps, by = "SNP") |>
  dplyr::rename(
    Chromosome = Scaffold
  )
head(merged_snps)

##            SNP Chromosome Cm Position Allele1 Allele2
## 1 AX-583054970          1  0  5342242       G       A
## 2 AX-583055828          1  0  6260504       A       G
## 3 AX-583093532          1  0 18373267       C       T
## 4 AX-583142560          1  0 33012482       T       C
## 5 AX-583237406          1  0 66299838       T       C
## 6 AX-583279927          1  0 80133483       A       G

We can add them as lines in the plot

# First, create a new data frame with 1Mb windows and count SNPs in each window
merged_snps$Window <- floor(merged_snps$Position / 20e6) * 20e6 # 20mb
snp_counts <- merged_snps %>%
  group_by(Chromosome, Window) %>%
  summarize(SNP_count = n(), .groups = 'drop')

# Now, add this SNP information to the plot
snp_plot <- ggplot() +
  geom_rect(data = albo2, aes(xmin = Start, xmax = End, ymin = 0, ymax = Size, fill = as.factor(Cluster)),
            color = "black", linewidth = 0.2) +
  geom_vline(data = snp_counts, aes(xintercept = Window + 0.5e6), color = "pink", linetype = "dotted", linewidth = 0.5) +
  geom_text(data = snp_counts, aes(x = Window + 0.5e6, y = 8e6, label = SNP_count), vjust = -0.5, color = "blue", size = 2) +
  scale_x_continuous(labels = label_mb, breaks = pretty_breaks(n = 3)) +
  scale_y_continuous(labels = label_mb, breaks = pretty_breaks(n = 5)) +
  labs(x = "Position (Mb)", y = "Cluster Size (Mb)") +
  theme_minimal() +
  theme(
    axis.text.y = element_text(margin = margin(t = 0, r = 5, b = 0, l = 5)),
    axis.ticks.y = element_blank(),
    panel.grid.major.x = element_line(color = "gray", linetype = "dotdash"),
    strip.background = element_rect(fill = "#e8e8e8", colour = NA),
    panel.grid.minor.x = element_blank(),
    legend.position = "none",
    panel.spacing.x = unit(1, "lines")
  ) +
  facet_grid(Population ~ Chromosome, scales = "fixed", space = "fixed")

# Display the plot
print(snp_plot)

## Warning: Combining variables of class <numeric> and <character> was deprecated in
## ggplot2 3.4.0.
## i Please ensure your variables are compatible before plotting (location:
##   `combine_vars()`)
## This warning is displayed once every 8 hours.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.

#
# # Use ggsave to save the plot as a PDF
# ggsave(
#   filename = here("output", "ldna", "linkage_snps_genes_de.pdf"),
#   device = "pdf",
#   width = 8,
#   height = 5,
#   units = "in"
# )

Find the non-overlapping clusters

# Split the data into two subsets based on Population
albo_NEW <- subset(albo2, Population == "NEW")
albo_AUT <- subset(albo2, Population == "AUT")

# Function to find non-overlapping clusters
find_non_overlapping_clusters <- function(new_clusters, aut_clusters) {
  non_overlapping <- vector("list", length(new_clusters$Chromosome))
  names(non_overlapping) <- unique(new_clusters$Chromosome)

  for (chr in unique(new_clusters$Chromosome)) {
    new_chrom_clusters <- new_clusters[new_clusters$Chromosome == chr, ]
    aut_chrom_clusters <- aut_clusters[aut_clusters$Chromosome == chr, ]

    non_overlap <- vector("list", nrow(new_chrom_clusters))

    for (i in 1:nrow(new_chrom_clusters)) {
      overlaps <- any(aut_chrom_clusters$Start <= new_chrom_clusters$End[i] & aut_chrom_clusters$End >= new_chrom_clusters$Start[i])
      if (!overlaps) {
        non_overlap[[i]] <- new_chrom_clusters[i, ]
      }
    }

    non_overlapping[[chr]] <- do.call(rbind, non_overlap)
  }

  do.call(rbind, non_overlapping)
}

# Find non-overlapping clusters
non_overlapping_clusters <- find_non_overlapping_clusters(albo_NEW, albo_AUT)

# View the non-overlapping clusters
non_overlapping_clusters

##       Population Chromosome   Cluster   r2 nSegments nSNPs     Start       End
## 1.67         NEW          1 2098_0.81 0.81       225  3339  17763447  19491473
## 1.68         NEW          1 2098_0.81 0.81       225  3339  31462771  33110064
## 1.69         NEW          1 2098_0.81 0.81       225  3339  33812253  39535721
## 1.70         NEW          1 2098_0.81 0.81       225  3339  42912079  45617370
## 1.71         NEW          1 2098_0.81 0.81       225  3339  45813378  46852266
## 1.72         NEW          1 2098_0.81 0.81       225  3339  49058652  52982032
## 1.73         NEW          1 2098_0.81 0.81       225  3339  53104692  57458477
## 1.74         NEW          1 2098_0.81 0.81       225  3339  57603304  81674467
## 1.75         NEW          1 2098_0.81 0.81       225  3339  84125006  85286331
## 1.77         NEW          1 2257_0.78 0.78        21    49  92128407  93161109
## 1.78         NEW          1 2098_0.81 0.81       225  3339  96662783  99757810
## 1.79         NEW          1 2098_0.81 0.81       225  3339 109454635 110939058
## 1.80         NEW          1 2098_0.81 0.81       225  3339 111088239 115093306
## 1.81         NEW          1 2098_0.81 0.81       225  3339 116539985 117786853
## 1.84         NEW          1 2098_0.81 0.81       225  3339 155511543 168919506
## 1.85         NEW          1 2098_0.81 0.81       225  3339 169035292 173049491
## 1.87         NEW          1 2098_0.81 0.81       225  3339 184822512 191340592
## 1.88         NEW          1 2098_0.81 0.81       225  3339 191491743 192497058
## 1.89         NEW          1 2098_0.81 0.81       225  3339 193238959 195536041
## 1.90         NEW          1 2098_0.81 0.81       225  3339 196644737 199686032
## 1.91         NEW          1 2098_0.81 0.81       225  3339 199758742 207076243
## 1.92         NEW          1 2098_0.81 0.81       225  3339 210193969 212041495
## 1.93         NEW          1 2098_0.81 0.81       225  3339 217126621 230413950
## 1.94         NEW          1 2098_0.81 0.81       225  3339 230429247 241512774
## 1.97         NEW          1 2098_0.81 0.81       225  3339 250638063 252000239
## 1.98         NEW          1 2098_0.81 0.81       225  3339 252144386 255284772
## 1.99         NEW          1 2098_0.81 0.81       225  3339 255471960 260032529
## 1.100        NEW          1 2098_0.81 0.81       225  3339 262169514 263823952
## 1.103        NEW          1 2098_0.81 0.81       225  3339 291128858 294274102
## 1.104        NEW          1 2098_0.81 0.81       225  3339 294683970 297498464
## 1.105        NEW          1 2098_0.81 0.81       225  3339 299222427 302129356
## 1.106        NEW          1 2098_0.81 0.81       225  3339 302199736 305506598
## 1.107        NEW          1 2098_0.81 0.81       225  3339 305564825 308828617
## 1.108        NEW          1 2098_0.81 0.81       225  3339 308845316 310046723
## 1.109        NEW          1 2098_0.81 0.81       225  3339 310436955 312893712
## 1.110        NEW          1 2098_0.81 0.81       225  3339 313386794 321651633
## 1.111        NEW          1 2098_0.81 0.81       225  3339 329288148 330792056
## 1.112        NEW          1 2098_0.81 0.81       225  3339 331903843 334134626
## 1.113        NEW          1 2098_0.81 0.81       225  3339 349747385 350752606
## 1.114        NEW          1 2098_0.81 0.81       225  3339 350759454 352036196
## 1.115        NEW          1 2098_0.81 0.81       225  3339 352250603 353457242
## 1.116        NEW          1 2098_0.81 0.81       225  3339 355814525 356832851
## 1.117        NEW          1 2098_0.81 0.81       225  3339 357649351 360432526
## 1.118        NEW          1 2098_0.81 0.81       225  3339 361376691 362625358
## 1.119        NEW          1 2098_0.81 0.81       225  3339 363346050 365490174
## 1.120        NEW          1 2098_0.81 0.81       225  3339 365516884 367009263
## 1.121        NEW          1 2098_0.81 0.81       225  3339 367076124 368115714
## 1.122        NEW          1 2098_0.81 0.81       225  3339 368209240 370940654
## 2.123        NEW          2  3393_0.8  0.8      1027  3235    224747   2320220
## 2.124        NEW          2  3393_0.8  0.8      1027  3235   3767940   5516504
## 2.125        NEW          2  3404_0.8  0.8       905  1502  20865308  23384980
## 2.126        NEW          2  3393_0.8  0.8      1027  3235  32333986  33684664
## 2.127        NEW          2  3393_0.8  0.8      1027  3235  37484773  39477392
## 2.128        NEW          2  3404_0.8  0.8       905  1502  47841211  49223392
## 2.129        NEW          2  3393_0.8  0.8      1027  3235  60198806  63385698
## 2.130        NEW          2  3404_0.8  0.8       905  1502  63957749  65028705
## 2.131        NEW          2  3393_0.8  0.8      1027  3235  71334985  75185080
## 2.132        NEW          2  3404_0.8  0.8       905  1502  75680372  77722092
## 2.133        NEW          2  3404_0.8  0.8       905  1502  79048197  81335266
## 2.134        NEW          2  3393_0.8  0.8      1027  3235  86262808  87274287
## 2.135        NEW          2  3393_0.8  0.8      1027  3235  89422203  90648941
## 2.136        NEW          2  3393_0.8  0.8      1027  3235  92717918  93748781
## 2.138        NEW          2  3393_0.8  0.8      1027  3235 107385063 111397305
## 2.139        NEW          2  3393_0.8  0.8      1027  3235 112239445 113398794
## 2.140        NEW          2  3404_0.8  0.8       905  1502 115171624 117422202
## 2.141        NEW          2  3393_0.8  0.8      1027  3235 120642568 121789169
## 2.143        NEW          2  3404_0.8  0.8       905  1502 134691453 136254657
## 2.146        NEW          2  3404_0.8  0.8       905  1502 145519669 147610899
## 2.147        NEW          2  3393_0.8  0.8      1027  3235 147686588 148800994
## 2.149        NEW          2  3404_0.8  0.8       905  1502 159957622 162105222
## 2.150        NEW          2  3404_0.8  0.8       905  1502 164942040 166163633
## 2.151        NEW          2  3404_0.8  0.8       905  1502 176121303 178566001
## 2.152        NEW          2  3393_0.8  0.8      1027  3235 184599662 185697190
## 2.153        NEW          2  3404_0.8  0.8       905  1502 187872447 189338359
## 2.154        NEW          2  3393_0.8  0.8      1027  3235 196919065 198241184
## 2.155        NEW          2  3393_0.8  0.8      1027  3235 198399859 199866764
## 2.156        NEW          2  3393_0.8  0.8      1027  3235 200640262 201766366
## 2.157        NEW          2  3393_0.8  0.8      1027  3235 211336217 214704214
## 2.158        NEW          2  3393_0.8  0.8      1027  3235 221458739 227293746
## 2.159        NEW          2  3404_0.8  0.8       905  1502 231449434 232560068
## 2.160        NEW          2  3404_0.8  0.8       905  1502 234706206 236580351
## 2.161        NEW          2  3393_0.8  0.8      1027  3235 250661099 251754487
## 2.162        NEW          2  3393_0.8  0.8      1027  3235 269725161 271001058
## 2.163        NEW          2  3393_0.8  0.8      1027  3235 272699658 274730588
## 2.164        NEW          2  3393_0.8  0.8      1027  3235 281488259 282754807
## 2.165        NEW          2  3393_0.8  0.8      1027  3235 298229333 300182152
## 2.166        NEW          2  3404_0.8  0.8       905  1502 301661105 304313204
## 2.167        NEW          2  3404_0.8  0.8       905  1502 304515783 306218388
## 2.168        NEW          2  3393_0.8  0.8      1027  3235 309917339 318159364
## 2.169        NEW          2  3393_0.8  0.8      1027  3235 322231858 323875574
## 2.171        NEW          2  3393_0.8  0.8      1027  3235 338547271 341098241
## 2.172        NEW          2  3404_0.8  0.8       905  1502 343930528 345470965
## 2.173        NEW          2  3404_0.8  0.8       905  1502 345633769 354870721
## 2.174        NEW          2  3404_0.8  0.8       905  1502 363676430 365753357
## 2.175        NEW          2  3393_0.8  0.8      1027  3235 371505037 373052338
## 2.176        NEW          2  3393_0.8  0.8      1027  3235 373133669 376347397
## 2.177        NEW          2  3393_0.8  0.8      1027  3235 379361111 381543575
## 2.178        NEW          2  3393_0.8  0.8      1027  3235 382522637 383782785
## 2.179        NEW          2  3393_0.8  0.8      1027  3235 394747517 395926654
## 2.181        NEW          2  3393_0.8  0.8      1027  3235 423413849 425459834
## 2.182        NEW          2  3393_0.8  0.8      1027  3235 426632333 428968851
## 2.183        NEW          2  3393_0.8  0.8      1027  3235 434926662 436108135
## 2.185        NEW          2  3393_0.8  0.8      1027  3235 450997412 452946043
## 2.186        NEW          2  3393_0.8  0.8      1027  3235 489711160 491614193
## 2.187        NEW          2  3393_0.8  0.8      1027  3235 505908537 507012127
## 2.188        NEW          2  3393_0.8  0.8      1027  3235 518565796 519621236
## 2.190        NEW          2  3393_0.8  0.8      1027  3235 533383712 534904257
## 2.191        NEW          2  3393_0.8  0.8      1027  3235 546386096 547694728
## 2.192        NEW          2  3393_0.8  0.8      1027  3235 559442893 561613146
## 2.193        NEW          2  3393_0.8  0.8      1027  3235 584590398 585804603
## 3.194        NEW          3 2836_0.81 0.81       567  1122    138261   1143824
## 3.195        NEW          3 2836_0.81 0.81       567  1122   6888798   8280336
## 3.197        NEW          3 2837_0.81 0.81       602  1668  30868364  32084271
## 3.198        NEW          3 2837_0.81 0.81       602  1668  33607382  34770651
## 3.199        NEW          3 2837_0.81 0.81       602  1668  38220097  39497877
## 3.200        NEW          3 2837_0.81 0.81       602  1668  41999164  43351711
## 3.201        NEW          3 2837_0.81 0.81       602  1668  45971148  49553360
## 3.202        NEW          3 2837_0.81 0.81       602  1668  53278835  54796696
## 3.204        NEW          3 2844_0.81 0.81        94   142  62431035  64197177
## 3.207        NEW          3 2837_0.81 0.81       602  1668  79033650  80149798
## 3.208        NEW          3 2837_0.81 0.81       602  1668  82956837  84368104
## 3.209        NEW          3 2836_0.81 0.81       567  1122  87052596  88327934
## 3.210        NEW          3 2837_0.81 0.81       602  1668  96649526  97704550
## 3.211        NEW          3 2837_0.81 0.81       602  1668 103304460 105510232
## 3.212        NEW          3 2837_0.81 0.81       602  1668 106246872 108915149
## 3.214        NEW          3 2837_0.81 0.81       602  1668 117801583 119196324
## 3.215        NEW          3 2837_0.81 0.81       602  1668 122688806 125806099
## 3.216        NEW          3 2837_0.81 0.81       602  1668 126000611 132461516
## 3.217        NEW          3 2837_0.81 0.81       602  1668 134726992 142770788
## 3.218        NEW          3 2837_0.81 0.81       602  1668 143504855 146770743
## 3.219        NEW          3 2837_0.81 0.81       602  1668 149536509 156001191
## 3.220        NEW          3 2837_0.81 0.81       602  1668 158530473 159797863
## 3.221        NEW          3 2837_0.81 0.81       602  1668 161308720 163859867
## 3.222        NEW          3 2837_0.81 0.81       602  1668 164412695 165638650
## 3.223        NEW          3 2837_0.81 0.81       602  1668 165745584 169750947
## 3.224        NEW          3 2837_0.81 0.81       602  1668 173459259 182850273
## 3.225        NEW          3 2837_0.81 0.81       602  1668 183591308 191456216
## 3.226        NEW          3 2837_0.81 0.81       602  1668 191547834 194909609
## 3.228        NEW          3 2837_0.81 0.81       602  1668 209544043 212578519
## 3.231        NEW          3 2837_0.81 0.81       602  1668 224412047 226630195
## 3.232        NEW          3 2837_0.81 0.81       602  1668 227290780 229701667
## 3.233        NEW          3 2837_0.81 0.81       602  1668 238924438 243184338
## 3.234        NEW          3 2837_0.81 0.81       602  1668 244529416 246058521
## 3.235        NEW          3 4066_0.72 0.72         7    42 248606503 250684517
## 3.237        NEW          3 2837_0.81 0.81       602  1668 260250588 261292851
## 3.240        NEW          3 2837_0.81 0.81       602  1668 274697733 276432605
## 3.241        NEW          3 2836_0.81 0.81       567  1122 276462623 279021064
## 3.242        NEW          3 2837_0.81 0.81       602  1668 280594192 282048225
## 3.243        NEW          3 2837_0.81 0.81       602  1668 286337276 287471025
## 3.244        NEW          3 2836_0.81 0.81       567  1122 288896346 290130685
## 3.245        NEW          3 2837_0.81 0.81       602  1668 291357677 293293846
## 3.247        NEW          3 2837_0.81 0.81       602  1668 299533420 301080582
## 3.248        NEW          3 2837_0.81 0.81       602  1668 302091398 303360496
## 3.249        NEW          3 2837_0.81 0.81       602  1668 303715842 306464838
## 3.250        NEW          3 2837_0.81 0.81       602  1668 311114136 313584547
## 3.251        NEW          3 2837_0.81 0.81       602  1668 315936740 317289268
## 3.252        NEW          3 2836_0.81 0.81       567  1122 320805786 322094119
## 3.253        NEW          3 2837_0.81 0.81       602  1668 330738652 332126201
## 3.256        NEW          3 2837_0.81 0.81       602  1668 370379158 371501078
## 3.258        NEW          3 2837_0.81 0.81       602  1668 382176532 383384925
## 3.259        NEW          3 2837_0.81 0.81       602  1668 404173993 405714900
## 3.260        NEW          3 2836_0.81 0.81       567  1122 428481578 430261142
## 3.262        NEW          3 2837_0.81 0.81       602  1668 438979662 440553449
## 3.263        NEW          3 2836_0.81 0.81       567  1122 447077906 448164929
## 3.264        NEW          3 2837_0.81 0.81       602  1668 459111122 461437206
## 3.265        NEW          3 2836_0.81 0.81       567  1122 463741283 464793077
## 3.266        NEW          3 2836_0.81 0.81       567  1122 466877065 470726943
## 3.267        NEW          3 2837_0.81 0.81       602  1668 470834558 472278174
## 3.268        NEW          3 2837_0.81 0.81       602  1668 477874059 479070412
## 3.269        NEW          3 2837_0.81 0.81       602  1668 482358967 483846198
## 3.270        NEW          3 2837_0.81 0.81       602  1668 483851021 485203479
##           Size Size (Mb)
## 1.67   1728026      1.73
## 1.68   1647293      1.65
## 1.69   5723468      5.72
## 1.70   2705291      2.71
## 1.71   1038888      1.04
## 1.72   3923380      3.92
## 1.73   4353785      4.35
## 1.74  24071163     24.07
## 1.75   1161325      1.16
## 1.77   1032702      1.03
## 1.78   3095027      3.10
## 1.79   1484423      1.48
## 1.80   4005067      4.01
## 1.81   1246868      1.25
## 1.84  13407963     13.41
## 1.85   4014199      4.01
## 1.87   6518080      6.52
## 1.88   1005315      1.01
## 1.89   2297082      2.30
## 1.90   3041295      3.04
## 1.91   7317501      7.32
## 1.92   1847526      1.85
## 1.93  13287329     13.29
## 1.94  11083527     11.08
## 1.97   1362176      1.36
## 1.98   3140386      3.14
## 1.99   4560569      4.56
## 1.100  1654438      1.65
## 1.103  3145244      3.15
## 1.104  2814494      2.81
## 1.105  2906929      2.91
## 1.106  3306862      3.31
## 1.107  3263792      3.26
## 1.108  1201407      1.20
## 1.109  2456757      2.46
## 1.110  8264839      8.26
## 1.111  1503908      1.50
## 1.112  2230783      2.23
## 1.113  1005221      1.01
## 1.114  1276742      1.28
## 1.115  1206639      1.21
## 1.116  1018326      1.02
## 1.117  2783175      2.78
## 1.118  1248667      1.25
## 1.119  2144124      2.14
## 1.120  1492379      1.49
## 1.121  1039590      1.04
## 1.122  2731414      2.73
## 2.123  2095473      2.10
## 2.124  1748564      1.75
## 2.125  2519672      2.52
## 2.126  1350678      1.35
## 2.127  1992619      1.99
## 2.128  1382181      1.38
## 2.129  3186892      3.19
## 2.130  1070956      1.07
## 2.131  3850095      3.85
## 2.132  2041720      2.04
## 2.133  2287069      2.29
## 2.134  1011479      1.01
## 2.135  1226738      1.23
## 2.136  1030863      1.03
## 2.138  4012242      4.01
## 2.139  1159349      1.16
## 2.140  2250578      2.25
## 2.141  1146601      1.15
## 2.143  1563204      1.56
## 2.146  2091230      2.09
## 2.147  1114406      1.11
## 2.149  2147600      2.15
## 2.150  1221593      1.22
## 2.151  2444698      2.44
## 2.152  1097528      1.10
## 2.153  1465912      1.47
## 2.154  1322119      1.32
## 2.155  1466905      1.47
## 2.156  1126104      1.13
## 2.157  3367997      3.37
## 2.158  5835007      5.84
## 2.159  1110634      1.11
## 2.160  1874145      1.87
## 2.161  1093388      1.09
## 2.162  1275897      1.28
## 2.163  2030930      2.03
## 2.164  1266548      1.27
## 2.165  1952819      1.95
## 2.166  2652099      2.65
## 2.167  1702605      1.70
## 2.168  8242025      8.24
## 2.169  1643716      1.64
## 2.171  2550970      2.55
## 2.172  1540437      1.54
## 2.173  9236952      9.24
## 2.174  2076927      2.08
## 2.175  1547301      1.55
## 2.176  3213728      3.21
## 2.177  2182464      2.18
## 2.178  1260148      1.26
## 2.179  1179137      1.18
## 2.181  2045985      2.05
## 2.182  2336518      2.34
## 2.183  1181473      1.18
## 2.185  1948631      1.95
## 2.186  1903033      1.90
## 2.187  1103590      1.10
## 2.188  1055440      1.06
## 2.190  1520545      1.52
## 2.191  1308632      1.31
## 2.192  2170253      2.17
## 2.193  1214205      1.21
## 3.194  1005563      1.01
## 3.195  1391538      1.39
## 3.197  1215907      1.22
## 3.198  1163269      1.16
## 3.199  1277780      1.28
## 3.200  1352547      1.35
## 3.201  3582212      3.58
## 3.202  1517861      1.52
## 3.204  1766142      1.77
## 3.207  1116148      1.12
## 3.208  1411267      1.41
## 3.209  1275338      1.28
## 3.210  1055024      1.06
## 3.211  2205772      2.21
## 3.212  2668277      2.67
## 3.214  1394741      1.39
## 3.215  3117293      3.12
## 3.216  6460905      6.46
## 3.217  8043796      8.04
## 3.218  3265888      3.27
## 3.219  6464682      6.46
## 3.220  1267390      1.27
## 3.221  2551147      2.55
## 3.222  1225955      1.23
## 3.223  4005363      4.01
## 3.224  9391014      9.39
## 3.225  7864908      7.86
## 3.226  3361775      3.36
## 3.228  3034476      3.03
## 3.231  2218148      2.22
## 3.232  2410887      2.41
## 3.233  4259900      4.26
## 3.234  1529105      1.53
## 3.235  2078014      2.08
## 3.237  1042263      1.04
## 3.240  1734872      1.73
## 3.241  2558441      2.56
## 3.242  1454033      1.45
## 3.243  1133749      1.13
## 3.244  1234339      1.23
## 3.245  1936169      1.94
## 3.247  1547162      1.55
## 3.248  1269098      1.27
## 3.249  2748996      2.75
## 3.250  2470411      2.47
## 3.251  1352528      1.35
## 3.252  1288333      1.29
## 3.253  1387549      1.39
## 3.256  1121920      1.12
## 3.258  1208393      1.21
## 3.259  1540907      1.54
## 3.260  1779564      1.78
## 3.262  1573787      1.57
## 3.263  1087023      1.09
## 3.264  2326084      2.33
## 3.265  1051794      1.05
## 3.266  3849878      3.85
## 3.267  1443616      1.44
## 3.268  1196353      1.20
## 3.269  1487231      1.49
## 3.270  1352458      1.35

Sanity check: Second way to get it

# Function to find non-overlapping segments
find_non_overlapping_segments <- function(new_clusters, aut_clusters) {
  non_overlapping <- list()

  for (chr in unique(new_clusters$Chromosome)) {
    new_chrom_segments <- new_clusters[new_clusters$Chromosome == chr, ]
    aut_chrom_segments <- aut_clusters[aut_clusters$Chromosome == chr, ]

    non_overlap <- list()

    for (i in 1:nrow(new_chrom_segments)) {
      overlaps <- FALSE
      for (j in 1:nrow(aut_chrom_segments)) {
        if (new_chrom_segments$Start[i] <= aut_chrom_segments$End[j] && new_chrom_segments$End[i] >= aut_chrom_segments$Start[j]) {
          overlaps <- TRUE
          break
        }
      }

      if (!overlaps) {
        non_overlap <- c(non_overlap, list(new_chrom_segments[i, ]))
      }
    }

    non_overlapping[[chr]] <- do.call(rbind, non_overlap)
  }

  do.call(rbind, non_overlapping)
}

# Find non-overlapping segments
non_overlapping_segments <- find_non_overlapping_segments(albo_NEW, albo_AUT)

# View the non-overlapping segments
non_overlapping_segments

##     Population Chromosome   Cluster   r2 nSegments nSNPs     Start       End
## 67         NEW          1 2098_0.81 0.81       225  3339  17763447  19491473
## 68         NEW          1 2098_0.81 0.81       225  3339  31462771  33110064
## 69         NEW          1 2098_0.81 0.81       225  3339  33812253  39535721
## 70         NEW          1 2098_0.81 0.81       225  3339  42912079  45617370
## 71         NEW          1 2098_0.81 0.81       225  3339  45813378  46852266
## 72         NEW          1 2098_0.81 0.81       225  3339  49058652  52982032
## 73         NEW          1 2098_0.81 0.81       225  3339  53104692  57458477
## 74         NEW          1 2098_0.81 0.81       225  3339  57603304  81674467
## 75         NEW          1 2098_0.81 0.81       225  3339  84125006  85286331
## 77         NEW          1 2257_0.78 0.78        21    49  92128407  93161109
## 78         NEW          1 2098_0.81 0.81       225  3339  96662783  99757810
## 79         NEW          1 2098_0.81 0.81       225  3339 109454635 110939058
## 80         NEW          1 2098_0.81 0.81       225  3339 111088239 115093306
## 81         NEW          1 2098_0.81 0.81       225  3339 116539985 117786853
## 84         NEW          1 2098_0.81 0.81       225  3339 155511543 168919506
## 85         NEW          1 2098_0.81 0.81       225  3339 169035292 173049491
## 87         NEW          1 2098_0.81 0.81       225  3339 184822512 191340592
## 88         NEW          1 2098_0.81 0.81       225  3339 191491743 192497058
## 89         NEW          1 2098_0.81 0.81       225  3339 193238959 195536041
## 90         NEW          1 2098_0.81 0.81       225  3339 196644737 199686032
## 91         NEW          1 2098_0.81 0.81       225  3339 199758742 207076243
## 92         NEW          1 2098_0.81 0.81       225  3339 210193969 212041495
## 93         NEW          1 2098_0.81 0.81       225  3339 217126621 230413950
## 94         NEW          1 2098_0.81 0.81       225  3339 230429247 241512774
## 97         NEW          1 2098_0.81 0.81       225  3339 250638063 252000239
## 98         NEW          1 2098_0.81 0.81       225  3339 252144386 255284772
## 99         NEW          1 2098_0.81 0.81       225  3339 255471960 260032529
## 100        NEW          1 2098_0.81 0.81       225  3339 262169514 263823952
## 103        NEW          1 2098_0.81 0.81       225  3339 291128858 294274102
## 104        NEW          1 2098_0.81 0.81       225  3339 294683970 297498464
## 105        NEW          1 2098_0.81 0.81       225  3339 299222427 302129356
## 106        NEW          1 2098_0.81 0.81       225  3339 302199736 305506598
## 107        NEW          1 2098_0.81 0.81       225  3339 305564825 308828617
## 108        NEW          1 2098_0.81 0.81       225  3339 308845316 310046723
## 109        NEW          1 2098_0.81 0.81       225  3339 310436955 312893712
## 110        NEW          1 2098_0.81 0.81       225  3339 313386794 321651633
## 111        NEW          1 2098_0.81 0.81       225  3339 329288148 330792056
## 112        NEW          1 2098_0.81 0.81       225  3339 331903843 334134626
## 113        NEW          1 2098_0.81 0.81       225  3339 349747385 350752606
## 114        NEW          1 2098_0.81 0.81       225  3339 350759454 352036196
## 115        NEW          1 2098_0.81 0.81       225  3339 352250603 353457242
## 116        NEW          1 2098_0.81 0.81       225  3339 355814525 356832851
## 117        NEW          1 2098_0.81 0.81       225  3339 357649351 360432526
## 118        NEW          1 2098_0.81 0.81       225  3339 361376691 362625358
## 119        NEW          1 2098_0.81 0.81       225  3339 363346050 365490174
## 120        NEW          1 2098_0.81 0.81       225  3339 365516884 367009263
## 121        NEW          1 2098_0.81 0.81       225  3339 367076124 368115714
## 122        NEW          1 2098_0.81 0.81       225  3339 368209240 370940654
## 123        NEW          2  3393_0.8  0.8      1027  3235    224747   2320220
## 124        NEW          2  3393_0.8  0.8      1027  3235   3767940   5516504
## 125        NEW          2  3404_0.8  0.8       905  1502  20865308  23384980
## 126        NEW          2  3393_0.8  0.8      1027  3235  32333986  33684664
## 127        NEW          2  3393_0.8  0.8      1027  3235  37484773  39477392
## 128        NEW          2  3404_0.8  0.8       905  1502  47841211  49223392
## 129        NEW          2  3393_0.8  0.8      1027  3235  60198806  63385698
## 130        NEW          2  3404_0.8  0.8       905  1502  63957749  65028705
## 131        NEW          2  3393_0.8  0.8      1027  3235  71334985  75185080
## 132        NEW          2  3404_0.8  0.8       905  1502  75680372  77722092
## 133        NEW          2  3404_0.8  0.8       905  1502  79048197  81335266
## 134        NEW          2  3393_0.8  0.8      1027  3235  86262808  87274287
## 135        NEW          2  3393_0.8  0.8      1027  3235  89422203  90648941
## 136        NEW          2  3393_0.8  0.8      1027  3235  92717918  93748781
## 138        NEW          2  3393_0.8  0.8      1027  3235 107385063 111397305
## 139        NEW          2  3393_0.8  0.8      1027  3235 112239445 113398794
## 140        NEW          2  3404_0.8  0.8       905  1502 115171624 117422202
## 141        NEW          2  3393_0.8  0.8      1027  3235 120642568 121789169
## 143        NEW          2  3404_0.8  0.8       905  1502 134691453 136254657
## 146        NEW          2  3404_0.8  0.8       905  1502 145519669 147610899
## 147        NEW          2  3393_0.8  0.8      1027  3235 147686588 148800994
## 149        NEW          2  3404_0.8  0.8       905  1502 159957622 162105222
## 150        NEW          2  3404_0.8  0.8       905  1502 164942040 166163633
## 151        NEW          2  3404_0.8  0.8       905  1502 176121303 178566001
## 152        NEW          2  3393_0.8  0.8      1027  3235 184599662 185697190
## 153        NEW          2  3404_0.8  0.8       905  1502 187872447 189338359
## 154        NEW          2  3393_0.8  0.8      1027  3235 196919065 198241184
## 155        NEW          2  3393_0.8  0.8      1027  3235 198399859 199866764
## 156        NEW          2  3393_0.8  0.8      1027  3235 200640262 201766366
## 157        NEW          2  3393_0.8  0.8      1027  3235 211336217 214704214
## 158        NEW          2  3393_0.8  0.8      1027  3235 221458739 227293746
## 159        NEW          2  3404_0.8  0.8       905  1502 231449434 232560068
## 160        NEW          2  3404_0.8  0.8       905  1502 234706206 236580351
## 161        NEW          2  3393_0.8  0.8      1027  3235 250661099 251754487
## 162        NEW          2  3393_0.8  0.8      1027  3235 269725161 271001058
## 163        NEW          2  3393_0.8  0.8      1027  3235 272699658 274730588
## 164        NEW          2  3393_0.8  0.8      1027  3235 281488259 282754807
## 165        NEW          2  3393_0.8  0.8      1027  3235 298229333 300182152
## 166        NEW          2  3404_0.8  0.8       905  1502 301661105 304313204
## 167        NEW          2  3404_0.8  0.8       905  1502 304515783 306218388
## 168        NEW          2  3393_0.8  0.8      1027  3235 309917339 318159364
## 169        NEW          2  3393_0.8  0.8      1027  3235 322231858 323875574
## 171        NEW          2  3393_0.8  0.8      1027  3235 338547271 341098241
## 172        NEW          2  3404_0.8  0.8       905  1502 343930528 345470965
## 173        NEW          2  3404_0.8  0.8       905  1502 345633769 354870721
## 174        NEW          2  3404_0.8  0.8       905  1502 363676430 365753357
## 175        NEW          2  3393_0.8  0.8      1027  3235 371505037 373052338
## 176        NEW          2  3393_0.8  0.8      1027  3235 373133669 376347397
## 177        NEW          2  3393_0.8  0.8      1027  3235 379361111 381543575
## 178        NEW          2  3393_0.8  0.8      1027  3235 382522637 383782785
## 179        NEW          2  3393_0.8  0.8      1027  3235 394747517 395926654
## 181        NEW          2  3393_0.8  0.8      1027  3235 423413849 425459834
## 182        NEW          2  3393_0.8  0.8      1027  3235 426632333 428968851
## 183        NEW          2  3393_0.8  0.8      1027  3235 434926662 436108135
## 185        NEW          2  3393_0.8  0.8      1027  3235 450997412 452946043
## 186        NEW          2  3393_0.8  0.8      1027  3235 489711160 491614193
## 187        NEW          2  3393_0.8  0.8      1027  3235 505908537 507012127
## 188        NEW          2  3393_0.8  0.8      1027  3235 518565796 519621236
## 190        NEW          2  3393_0.8  0.8      1027  3235 533383712 534904257
## 191        NEW          2  3393_0.8  0.8      1027  3235 546386096 547694728
## 192        NEW          2  3393_0.8  0.8      1027  3235 559442893 561613146
## 193        NEW          2  3393_0.8  0.8      1027  3235 584590398 585804603
## 194        NEW          3 2836_0.81 0.81       567  1122    138261   1143824
## 195        NEW          3 2836_0.81 0.81       567  1122   6888798   8280336
## 197        NEW          3 2837_0.81 0.81       602  1668  30868364  32084271
## 198        NEW          3 2837_0.81 0.81       602  1668  33607382  34770651
## 199        NEW          3 2837_0.81 0.81       602  1668  38220097  39497877
## 200        NEW          3 2837_0.81 0.81       602  1668  41999164  43351711
## 201        NEW          3 2837_0.81 0.81       602  1668  45971148  49553360
## 202        NEW          3 2837_0.81 0.81       602  1668  53278835  54796696
## 204        NEW          3 2844_0.81 0.81        94   142  62431035  64197177
## 207        NEW          3 2837_0.81 0.81       602  1668  79033650  80149798
## 208        NEW          3 2837_0.81 0.81       602  1668  82956837  84368104
## 209        NEW          3 2836_0.81 0.81       567  1122  87052596  88327934
## 210        NEW          3 2837_0.81 0.81       602  1668  96649526  97704550
## 211        NEW          3 2837_0.81 0.81       602  1668 103304460 105510232
## 212        NEW          3 2837_0.81 0.81       602  1668 106246872 108915149
## 214        NEW          3 2837_0.81 0.81       602  1668 117801583 119196324
## 215        NEW          3 2837_0.81 0.81       602  1668 122688806 125806099
## 216        NEW          3 2837_0.81 0.81       602  1668 126000611 132461516
## 217        NEW          3 2837_0.81 0.81       602  1668 134726992 142770788
## 218        NEW          3 2837_0.81 0.81       602  1668 143504855 146770743
## 219        NEW          3 2837_0.81 0.81       602  1668 149536509 156001191
## 220        NEW          3 2837_0.81 0.81       602  1668 158530473 159797863
## 221        NEW          3 2837_0.81 0.81       602  1668 161308720 163859867
## 222        NEW          3 2837_0.81 0.81       602  1668 164412695 165638650
## 223        NEW          3 2837_0.81 0.81       602  1668 165745584 169750947
## 224        NEW          3 2837_0.81 0.81       602  1668 173459259 182850273
## 225        NEW          3 2837_0.81 0.81       602  1668 183591308 191456216
## 226        NEW          3 2837_0.81 0.81       602  1668 191547834 194909609
## 228        NEW          3 2837_0.81 0.81       602  1668 209544043 212578519
## 231        NEW          3 2837_0.81 0.81       602  1668 224412047 226630195
## 232        NEW          3 2837_0.81 0.81       602  1668 227290780 229701667
## 233        NEW          3 2837_0.81 0.81       602  1668 238924438 243184338
## 234        NEW          3 2837_0.81 0.81       602  1668 244529416 246058521
## 235        NEW          3 4066_0.72 0.72         7    42 248606503 250684517
## 237        NEW          3 2837_0.81 0.81       602  1668 260250588 261292851
## 240        NEW          3 2837_0.81 0.81       602  1668 274697733 276432605
## 241        NEW          3 2836_0.81 0.81       567  1122 276462623 279021064
## 242        NEW          3 2837_0.81 0.81       602  1668 280594192 282048225
## 243        NEW          3 2837_0.81 0.81       602  1668 286337276 287471025
## 244        NEW          3 2836_0.81 0.81       567  1122 288896346 290130685
## 245        NEW          3 2837_0.81 0.81       602  1668 291357677 293293846
## 247        NEW          3 2837_0.81 0.81       602  1668 299533420 301080582
## 248        NEW          3 2837_0.81 0.81       602  1668 302091398 303360496
## 249        NEW          3 2837_0.81 0.81       602  1668 303715842 306464838
## 250        NEW          3 2837_0.81 0.81       602  1668 311114136 313584547
## 251        NEW          3 2837_0.81 0.81       602  1668 315936740 317289268
## 252        NEW          3 2836_0.81 0.81       567  1122 320805786 322094119
## 253        NEW          3 2837_0.81 0.81       602  1668 330738652 332126201
## 256        NEW          3 2837_0.81 0.81       602  1668 370379158 371501078
## 258        NEW          3 2837_0.81 0.81       602  1668 382176532 383384925
## 259        NEW          3 2837_0.81 0.81       602  1668 404173993 405714900
## 260        NEW          3 2836_0.81 0.81       567  1122 428481578 430261142
## 262        NEW          3 2837_0.81 0.81       602  1668 438979662 440553449
## 263        NEW          3 2836_0.81 0.81       567  1122 447077906 448164929
## 264        NEW          3 2837_0.81 0.81       602  1668 459111122 461437206
## 265        NEW          3 2836_0.81 0.81       567  1122 463741283 464793077
## 266        NEW          3 2836_0.81 0.81       567  1122 466877065 470726943
## 267        NEW          3 2837_0.81 0.81       602  1668 470834558 472278174
## 268        NEW          3 2837_0.81 0.81       602  1668 477874059 479070412
## 269        NEW          3 2837_0.81 0.81       602  1668 482358967 483846198
## 270        NEW          3 2837_0.81 0.81       602  1668 483851021 485203479
##         Size Size (Mb)
## 67   1728026      1.73
## 68   1647293      1.65
## 69   5723468      5.72
## 70   2705291      2.71
## 71   1038888      1.04
## 72   3923380      3.92
## 73   4353785      4.35
## 74  24071163     24.07
## 75   1161325      1.16
## 77   1032702      1.03
## 78   3095027      3.10
## 79   1484423      1.48
## 80   4005067      4.01
## 81   1246868      1.25
## 84  13407963     13.41
## 85   4014199      4.01
## 87   6518080      6.52
## 88   1005315      1.01
## 89   2297082      2.30
## 90   3041295      3.04
## 91   7317501      7.32
## 92   1847526      1.85
## 93  13287329     13.29
## 94  11083527     11.08
## 97   1362176      1.36
## 98   3140386      3.14
## 99   4560569      4.56
## 100  1654438      1.65
## 103  3145244      3.15
## 104  2814494      2.81
## 105  2906929      2.91
## 106  3306862      3.31
## 107  3263792      3.26
## 108  1201407      1.20
## 109  2456757      2.46
## 110  8264839      8.26
## 111  1503908      1.50
## 112  2230783      2.23
## 113  1005221      1.01
## 114  1276742      1.28
## 115  1206639      1.21
## 116  1018326      1.02
## 117  2783175      2.78
## 118  1248667      1.25
## 119  2144124      2.14
## 120  1492379      1.49
## 121  1039590      1.04
## 122  2731414      2.73
## 123  2095473      2.10
## 124  1748564      1.75
## 125  2519672      2.52
## 126  1350678      1.35
## 127  1992619      1.99
## 128  1382181      1.38
## 129  3186892      3.19
## 130  1070956      1.07
## 131  3850095      3.85
## 132  2041720      2.04
## 133  2287069      2.29
## 134  1011479      1.01
## 135  1226738      1.23
## 136  1030863      1.03
## 138  4012242      4.01
## 139  1159349      1.16
## 140  2250578      2.25
## 141  1146601      1.15
## 143  1563204      1.56
## 146  2091230      2.09
## 147  1114406      1.11
## 149  2147600      2.15
## 150  1221593      1.22
## 151  2444698      2.44
## 152  1097528      1.10
## 153  1465912      1.47
## 154  1322119      1.32
## 155  1466905      1.47
## 156  1126104      1.13
## 157  3367997      3.37
## 158  5835007      5.84
## 159  1110634      1.11
## 160  1874145      1.87
## 161  1093388      1.09
## 162  1275897      1.28
## 163  2030930      2.03
## 164  1266548      1.27
## 165  1952819      1.95
## 166  2652099      2.65
## 167  1702605      1.70
## 168  8242025      8.24
## 169  1643716      1.64
## 171  2550970      2.55
## 172  1540437      1.54
## 173  9236952      9.24
## 174  2076927      2.08
## 175  1547301      1.55
## 176  3213728      3.21
## 177  2182464      2.18
## 178  1260148      1.26
## 179  1179137      1.18
## 181  2045985      2.05
## 182  2336518      2.34
## 183  1181473      1.18
## 185  1948631      1.95
## 186  1903033      1.90
## 187  1103590      1.10
## 188  1055440      1.06
## 190  1520545      1.52
## 191  1308632      1.31
## 192  2170253      2.17
## 193  1214205      1.21
## 194  1005563      1.01
## 195  1391538      1.39
## 197  1215907      1.22
## 198  1163269      1.16
## 199  1277780      1.28
## 200  1352547      1.35
## 201  3582212      3.58
## 202  1517861      1.52
## 204  1766142      1.77
## 207  1116148      1.12
## 208  1411267      1.41
## 209  1275338      1.28
## 210  1055024      1.06
## 211  2205772      2.21
## 212  2668277      2.67
## 214  1394741      1.39
## 215  3117293      3.12
## 216  6460905      6.46
## 217  8043796      8.04
## 218  3265888      3.27
## 219  6464682      6.46
## 220  1267390      1.27
## 221  2551147      2.55
## 222  1225955      1.23
## 223  4005363      4.01
## 224  9391014      9.39
## 225  7864908      7.86
## 226  3361775      3.36
## 228  3034476      3.03
## 231  2218148      2.22
## 232  2410887      2.41
## 233  4259900      4.26
## 234  1529105      1.53
## 235  2078014      2.08
## 237  1042263      1.04
## 240  1734872      1.73
## 241  2558441      2.56
## 242  1454033      1.45
## 243  1133749      1.13
## 244  1234339      1.23
## 245  1936169      1.94
## 247  1547162      1.55
## 248  1269098      1.27
## 249  2748996      2.75
## 250  2470411      2.47
## 251  1352528      1.35
## 252  1288333      1.29
## 253  1387549      1.39
## 256  1121920      1.12
## 258  1208393      1.21
## 259  1540907      1.54
## 260  1779564      1.78
## 262  1573787      1.57
## 263  1087023      1.09
## 264  2326084      2.33
## 265  1051794      1.05
## 266  3849878      3.85
## 267  1443616      1.44
## 268  1196353      1.20
## 269  1487231      1.49
## 270  1352458      1.35

# Function to find unique non-overlapping clusters for each population
find_unique_clusters <- function(population1, population2) {
  unique_clusters <- list()

  for (chr in unique(population1$Chromosome)) {
    pop1_chrom_clusters <- population1[population1$Chromosome == chr, ]
    pop2_chrom_clusters <- population2[population2$Chromosome == chr, ]

    unique_clusters_chr <- list()

    for (i in 1:nrow(pop1_chrom_clusters)) {
      overlaps <- any(
        pop2_chrom_clusters$Start <= pop1_chrom_clusters$End[i] &
        pop2_chrom_clusters$End >= pop1_chrom_clusters$Start[i]
      )

      if (!overlaps) {
        unique_clusters_chr <- c(unique_clusters_chr, list(pop1_chrom_clusters[i, ]))
      }
    }

    if (length(unique_clusters_chr) > 0) {
      unique_clusters[[chr]] <- do.call(rbind, unique_clusters_chr)
    }
  }

  do.call(rbind, unique_clusters)
}

# Find unique non-overlapping clusters for NEW and AUT populations
unique_clusters_NEW <- find_unique_clusters(albo2[albo2$Population == "NEW",], albo2[albo2$Population == "AUT",])
unique_clusters_AUT <- find_unique_clusters(albo2[albo2$Population == "AUT",], albo2[albo2$Population == "NEW",])

# View the unique non-overlapping clusters for each population
unique_clusters_NEW

##     Population Chromosome   Cluster   r2 nSegments nSNPs     Start       End
## 67         NEW          1 2098_0.81 0.81       225  3339  17763447  19491473
## 68         NEW          1 2098_0.81 0.81       225  3339  31462771  33110064
## 69         NEW          1 2098_0.81 0.81       225  3339  33812253  39535721
## 70         NEW          1 2098_0.81 0.81       225  3339  42912079  45617370
## 71         NEW          1 2098_0.81 0.81       225  3339  45813378  46852266
## 72         NEW          1 2098_0.81 0.81       225  3339  49058652  52982032
## 73         NEW          1 2098_0.81 0.81       225  3339  53104692  57458477
## 74         NEW          1 2098_0.81 0.81       225  3339  57603304  81674467
## 75         NEW          1 2098_0.81 0.81       225  3339  84125006  85286331
## 77         NEW          1 2257_0.78 0.78        21    49  92128407  93161109
## 78         NEW          1 2098_0.81 0.81       225  3339  96662783  99757810
## 79         NEW          1 2098_0.81 0.81       225  3339 109454635 110939058
## 80         NEW          1 2098_0.81 0.81       225  3339 111088239 115093306
## 81         NEW          1 2098_0.81 0.81       225  3339 116539985 117786853
## 84         NEW          1 2098_0.81 0.81       225  3339 155511543 168919506
## 85         NEW          1 2098_0.81 0.81       225  3339 169035292 173049491
## 87         NEW          1 2098_0.81 0.81       225  3339 184822512 191340592
## 88         NEW          1 2098_0.81 0.81       225  3339 191491743 192497058
## 89         NEW          1 2098_0.81 0.81       225  3339 193238959 195536041
## 90         NEW          1 2098_0.81 0.81       225  3339 196644737 199686032
## 91         NEW          1 2098_0.81 0.81       225  3339 199758742 207076243
## 92         NEW          1 2098_0.81 0.81       225  3339 210193969 212041495
## 93         NEW          1 2098_0.81 0.81       225  3339 217126621 230413950
## 94         NEW          1 2098_0.81 0.81       225  3339 230429247 241512774
## 97         NEW          1 2098_0.81 0.81       225  3339 250638063 252000239
## 98         NEW          1 2098_0.81 0.81       225  3339 252144386 255284772
## 99         NEW          1 2098_0.81 0.81       225  3339 255471960 260032529
## 100        NEW          1 2098_0.81 0.81       225  3339 262169514 263823952
## 103        NEW          1 2098_0.81 0.81       225  3339 291128858 294274102
## 104        NEW          1 2098_0.81 0.81       225  3339 294683970 297498464
## 105        NEW          1 2098_0.81 0.81       225  3339 299222427 302129356
## 106        NEW          1 2098_0.81 0.81       225  3339 302199736 305506598
## 107        NEW          1 2098_0.81 0.81       225  3339 305564825 308828617
## 108        NEW          1 2098_0.81 0.81       225  3339 308845316 310046723
## 109        NEW          1 2098_0.81 0.81       225  3339 310436955 312893712
## 110        NEW          1 2098_0.81 0.81       225  3339 313386794 321651633
## 111        NEW          1 2098_0.81 0.81       225  3339 329288148 330792056
## 112        NEW          1 2098_0.81 0.81       225  3339 331903843 334134626
## 113        NEW          1 2098_0.81 0.81       225  3339 349747385 350752606
## 114        NEW          1 2098_0.81 0.81       225  3339 350759454 352036196
## 115        NEW          1 2098_0.81 0.81       225  3339 352250603 353457242
## 116        NEW          1 2098_0.81 0.81       225  3339 355814525 356832851
## 117        NEW          1 2098_0.81 0.81       225  3339 357649351 360432526
## 118        NEW          1 2098_0.81 0.81       225  3339 361376691 362625358
## 119        NEW          1 2098_0.81 0.81       225  3339 363346050 365490174
## 120        NEW          1 2098_0.81 0.81       225  3339 365516884 367009263
## 121        NEW          1 2098_0.81 0.81       225  3339 367076124 368115714
## 122        NEW          1 2098_0.81 0.81       225  3339 368209240 370940654
## 123        NEW          2  3393_0.8  0.8      1027  3235    224747   2320220
## 124        NEW          2  3393_0.8  0.8      1027  3235   3767940   5516504
## 125        NEW          2  3404_0.8  0.8       905  1502  20865308  23384980
## 126        NEW          2  3393_0.8  0.8      1027  3235  32333986  33684664
## 127        NEW          2  3393_0.8  0.8      1027  3235  37484773  39477392
## 128        NEW          2  3404_0.8  0.8       905  1502  47841211  49223392
## 129        NEW          2  3393_0.8  0.8      1027  3235  60198806  63385698
## 130        NEW          2  3404_0.8  0.8       905  1502  63957749  65028705
## 131        NEW          2  3393_0.8  0.8      1027  3235  71334985  75185080
## 132        NEW          2  3404_0.8  0.8       905  1502  75680372  77722092
## 133        NEW          2  3404_0.8  0.8       905  1502  79048197  81335266
## 134        NEW          2  3393_0.8  0.8      1027  3235  86262808  87274287
## 135        NEW          2  3393_0.8  0.8      1027  3235  89422203  90648941
## 136        NEW          2  3393_0.8  0.8      1027  3235  92717918  93748781
## 138        NEW          2  3393_0.8  0.8      1027  3235 107385063 111397305
## 139        NEW          2  3393_0.8  0.8      1027  3235 112239445 113398794
## 140        NEW          2  3404_0.8  0.8       905  1502 115171624 117422202
## 141        NEW          2  3393_0.8  0.8      1027  3235 120642568 121789169
## 143        NEW          2  3404_0.8  0.8       905  1502 134691453 136254657
## 146        NEW          2  3404_0.8  0.8       905  1502 145519669 147610899
## 147        NEW          2  3393_0.8  0.8      1027  3235 147686588 148800994
## 149        NEW          2  3404_0.8  0.8       905  1502 159957622 162105222
## 150        NEW          2  3404_0.8  0.8       905  1502 164942040 166163633
## 151        NEW          2  3404_0.8  0.8       905  1502 176121303 178566001
## 152        NEW          2  3393_0.8  0.8      1027  3235 184599662 185697190
## 153        NEW          2  3404_0.8  0.8       905  1502 187872447 189338359
## 154        NEW          2  3393_0.8  0.8      1027  3235 196919065 198241184
## 155        NEW          2  3393_0.8  0.8      1027  3235 198399859 199866764
## 156        NEW          2  3393_0.8  0.8      1027  3235 200640262 201766366
## 157        NEW          2  3393_0.8  0.8      1027  3235 211336217 214704214
## 158        NEW          2  3393_0.8  0.8      1027  3235 221458739 227293746
## 159        NEW          2  3404_0.8  0.8       905  1502 231449434 232560068
## 160        NEW          2  3404_0.8  0.8       905  1502 234706206 236580351
## 161        NEW          2  3393_0.8  0.8      1027  3235 250661099 251754487
## 162        NEW          2  3393_0.8  0.8      1027  3235 269725161 271001058
## 163        NEW          2  3393_0.8  0.8      1027  3235 272699658 274730588
## 164        NEW          2  3393_0.8  0.8      1027  3235 281488259 282754807
## 165        NEW          2  3393_0.8  0.8      1027  3235 298229333 300182152
## 166        NEW          2  3404_0.8  0.8       905  1502 301661105 304313204
## 167        NEW          2  3404_0.8  0.8       905  1502 304515783 306218388
## 168        NEW          2  3393_0.8  0.8      1027  3235 309917339 318159364
## 169        NEW          2  3393_0.8  0.8      1027  3235 322231858 323875574
## 171        NEW          2  3393_0.8  0.8      1027  3235 338547271 341098241
## 172        NEW          2  3404_0.8  0.8       905  1502 343930528 345470965
## 173        NEW          2  3404_0.8  0.8       905  1502 345633769 354870721
## 174        NEW          2  3404_0.8  0.8       905  1502 363676430 365753357
## 175        NEW          2  3393_0.8  0.8      1027  3235 371505037 373052338
## 176        NEW          2  3393_0.8  0.8      1027  3235 373133669 376347397
## 177        NEW          2  3393_0.8  0.8      1027  3235 379361111 381543575
## 178        NEW          2  3393_0.8  0.8      1027  3235 382522637 383782785
## 179        NEW          2  3393_0.8  0.8      1027  3235 394747517 395926654
## 181        NEW          2  3393_0.8  0.8      1027  3235 423413849 425459834
## 182        NEW          2  3393_0.8  0.8      1027  3235 426632333 428968851
## 183        NEW          2  3393_0.8  0.8      1027  3235 434926662 436108135
## 185        NEW          2  3393_0.8  0.8      1027  3235 450997412 452946043
## 186        NEW          2  3393_0.8  0.8      1027  3235 489711160 491614193
## 187        NEW          2  3393_0.8  0.8      1027  3235 505908537 507012127
## 188        NEW          2  3393_0.8  0.8      1027  3235 518565796 519621236
## 190        NEW          2  3393_0.8  0.8      1027  3235 533383712 534904257
## 191        NEW          2  3393_0.8  0.8      1027  3235 546386096 547694728
## 192        NEW          2  3393_0.8  0.8      1027  3235 559442893 561613146
## 193        NEW          2  3393_0.8  0.8      1027  3235 584590398 585804603
## 194        NEW          3 2836_0.81 0.81       567  1122    138261   1143824
## 195        NEW          3 2836_0.81 0.81       567  1122   6888798   8280336
## 197        NEW          3 2837_0.81 0.81       602  1668  30868364  32084271
## 198        NEW          3 2837_0.81 0.81       602  1668  33607382  34770651
## 199        NEW          3 2837_0.81 0.81       602  1668  38220097  39497877
## 200        NEW          3 2837_0.81 0.81       602  1668  41999164  43351711
## 201        NEW          3 2837_0.81 0.81       602  1668  45971148  49553360
## 202        NEW          3 2837_0.81 0.81       602  1668  53278835  54796696
## 204        NEW          3 2844_0.81 0.81        94   142  62431035  64197177
## 207        NEW          3 2837_0.81 0.81       602  1668  79033650  80149798
## 208        NEW          3 2837_0.81 0.81       602  1668  82956837  84368104
## 209        NEW          3 2836_0.81 0.81       567  1122  87052596  88327934
## 210        NEW          3 2837_0.81 0.81       602  1668  96649526  97704550
## 211        NEW          3 2837_0.81 0.81       602  1668 103304460 105510232
## 212        NEW          3 2837_0.81 0.81       602  1668 106246872 108915149
## 214        NEW          3 2837_0.81 0.81       602  1668 117801583 119196324
## 215        NEW          3 2837_0.81 0.81       602  1668 122688806 125806099
## 216        NEW          3 2837_0.81 0.81       602  1668 126000611 132461516
## 217        NEW          3 2837_0.81 0.81       602  1668 134726992 142770788
## 218        NEW          3 2837_0.81 0.81       602  1668 143504855 146770743
## 219        NEW          3 2837_0.81 0.81       602  1668 149536509 156001191
## 220        NEW          3 2837_0.81 0.81       602  1668 158530473 159797863
## 221        NEW          3 2837_0.81 0.81       602  1668 161308720 163859867
## 222        NEW          3 2837_0.81 0.81       602  1668 164412695 165638650
## 223        NEW          3 2837_0.81 0.81       602  1668 165745584 169750947
## 224        NEW          3 2837_0.81 0.81       602  1668 173459259 182850273
## 225        NEW          3 2837_0.81 0.81       602  1668 183591308 191456216
## 226        NEW          3 2837_0.81 0.81       602  1668 191547834 194909609
## 228        NEW          3 2837_0.81 0.81       602  1668 209544043 212578519
## 231        NEW          3 2837_0.81 0.81       602  1668 224412047 226630195
## 232        NEW          3 2837_0.81 0.81       602  1668 227290780 229701667
## 233        NEW          3 2837_0.81 0.81       602  1668 238924438 243184338
## 234        NEW          3 2837_0.81 0.81       602  1668 244529416 246058521
## 235        NEW          3 4066_0.72 0.72         7    42 248606503 250684517
## 237        NEW          3 2837_0.81 0.81       602  1668 260250588 261292851
## 240        NEW          3 2837_0.81 0.81       602  1668 274697733 276432605
## 241        NEW          3 2836_0.81 0.81       567  1122 276462623 279021064
## 242        NEW          3 2837_0.81 0.81       602  1668 280594192 282048225
## 243        NEW          3 2837_0.81 0.81       602  1668 286337276 287471025
## 244        NEW          3 2836_0.81 0.81       567  1122 288896346 290130685
## 245        NEW          3 2837_0.81 0.81       602  1668 291357677 293293846
## 247        NEW          3 2837_0.81 0.81       602  1668 299533420 301080582
## 248        NEW          3 2837_0.81 0.81       602  1668 302091398 303360496
## 249        NEW          3 2837_0.81 0.81       602  1668 303715842 306464838
## 250        NEW          3 2837_0.81 0.81       602  1668 311114136 313584547
## 251        NEW          3 2837_0.81 0.81       602  1668 315936740 317289268
## 252        NEW          3 2836_0.81 0.81       567  1122 320805786 322094119
## 253        NEW          3 2837_0.81 0.81       602  1668 330738652 332126201
## 256        NEW          3 2837_0.81 0.81       602  1668 370379158 371501078
## 258        NEW          3 2837_0.81 0.81       602  1668 382176532 383384925
## 259        NEW          3 2837_0.81 0.81       602  1668 404173993 405714900
## 260        NEW          3 2836_0.81 0.81       567  1122 428481578 430261142
## 262        NEW          3 2837_0.81 0.81       602  1668 438979662 440553449
## 263        NEW          3 2836_0.81 0.81       567  1122 447077906 448164929
## 264        NEW          3 2837_0.81 0.81       602  1668 459111122 461437206
## 265        NEW          3 2836_0.81 0.81       567  1122 463741283 464793077
## 266        NEW          3 2836_0.81 0.81       567  1122 466877065 470726943
## 267        NEW          3 2837_0.81 0.81       602  1668 470834558 472278174
## 268        NEW          3 2837_0.81 0.81       602  1668 477874059 479070412
## 269        NEW          3 2837_0.81 0.81       602  1668 482358967 483846198
## 270        NEW          3 2837_0.81 0.81       602  1668 483851021 485203479
##         Size Size (Mb)
## 67   1728026      1.73
## 68   1647293      1.65
## 69   5723468      5.72
## 70   2705291      2.71
## 71   1038888      1.04
## 72   3923380      3.92
## 73   4353785      4.35
## 74  24071163     24.07
## 75   1161325      1.16
## 77   1032702      1.03
## 78   3095027      3.10
## 79   1484423      1.48
## 80   4005067      4.01
## 81   1246868      1.25
## 84  13407963     13.41
## 85   4014199      4.01
## 87   6518080      6.52
## 88   1005315      1.01
## 89   2297082      2.30
## 90   3041295      3.04
## 91   7317501      7.32
## 92   1847526      1.85
## 93  13287329     13.29
## 94  11083527     11.08
## 97   1362176      1.36
## 98   3140386      3.14
## 99   4560569      4.56
## 100  1654438      1.65
## 103  3145244      3.15
## 104  2814494      2.81
## 105  2906929      2.91
## 106  3306862      3.31
## 107  3263792      3.26
## 108  1201407      1.20
## 109  2456757      2.46
## 110  8264839      8.26
## 111  1503908      1.50
## 112  2230783      2.23
## 113  1005221      1.01
## 114  1276742      1.28
## 115  1206639      1.21
## 116  1018326      1.02
## 117  2783175      2.78
## 118  1248667      1.25
## 119  2144124      2.14
## 120  1492379      1.49
## 121  1039590      1.04
## 122  2731414      2.73
## 123  2095473      2.10
## 124  1748564      1.75
## 125  2519672      2.52
## 126  1350678      1.35
## 127  1992619      1.99
## 128  1382181      1.38
## 129  3186892      3.19
## 130  1070956      1.07
## 131  3850095      3.85
## 132  2041720      2.04
## 133  2287069      2.29
## 134  1011479      1.01
## 135  1226738      1.23
## 136  1030863      1.03
## 138  4012242      4.01
## 139  1159349      1.16
## 140  2250578      2.25
## 141  1146601      1.15
## 143  1563204      1.56
## 146  2091230      2.09
## 147  1114406      1.11
## 149  2147600      2.15
## 150  1221593      1.22
## 151  2444698      2.44
## 152  1097528      1.10
## 153  1465912      1.47
## 154  1322119      1.32
## 155  1466905      1.47
## 156  1126104      1.13
## 157  3367997      3.37
## 158  5835007      5.84
## 159  1110634      1.11
## 160  1874145      1.87
## 161  1093388      1.09
## 162  1275897      1.28
## 163  2030930      2.03
## 164  1266548      1.27
## 165  1952819      1.95
## 166  2652099      2.65
## 167  1702605      1.70
## 168  8242025      8.24
## 169  1643716      1.64
## 171  2550970      2.55
## 172  1540437      1.54
## 173  9236952      9.24
## 174  2076927      2.08
## 175  1547301      1.55
## 176  3213728      3.21
## 177  2182464      2.18
## 178  1260148      1.26
## 179  1179137      1.18
## 181  2045985      2.05
## 182  2336518      2.34
## 183  1181473      1.18
## 185  1948631      1.95
## 186  1903033      1.90
## 187  1103590      1.10
## 188  1055440      1.06
## 190  1520545      1.52
## 191  1308632      1.31
## 192  2170253      2.17
## 193  1214205      1.21
## 194  1005563      1.01
## 195  1391538      1.39
## 197  1215907      1.22
## 198  1163269      1.16
## 199  1277780      1.28
## 200  1352547      1.35
## 201  3582212      3.58
## 202  1517861      1.52
## 204  1766142      1.77
## 207  1116148      1.12
## 208  1411267      1.41
## 209  1275338      1.28
## 210  1055024      1.06
## 211  2205772      2.21
## 212  2668277      2.67
## 214  1394741      1.39
## 215  3117293      3.12
## 216  6460905      6.46
## 217  8043796      8.04
## 218  3265888      3.27
## 219  6464682      6.46
## 220  1267390      1.27
## 221  2551147      2.55
## 222  1225955      1.23
## 223  4005363      4.01
## 224  9391014      9.39
## 225  7864908      7.86
## 226  3361775      3.36
## 228  3034476      3.03
## 231  2218148      2.22
## 232  2410887      2.41
## 233  4259900      4.26
## 234  1529105      1.53
## 235  2078014      2.08
## 237  1042263      1.04
## 240  1734872      1.73
## 241  2558441      2.56
## 242  1454033      1.45
## 243  1133749      1.13
## 244  1234339      1.23
## 245  1936169      1.94
## 247  1547162      1.55
## 248  1269098      1.27
## 249  2748996      2.75
## 250  2470411      2.47
## 251  1352528      1.35
## 252  1288333      1.29
## 253  1387549      1.39
## 256  1121920      1.12
## 258  1208393      1.21
## 259  1540907      1.54
## 260  1779564      1.78
## 262  1573787      1.57
## 263  1087023      1.09
## 264  2326084      2.33
## 265  1051794      1.05
## 266  3849878      3.85
## 267  1443616      1.44
## 268  1196353      1.20
## 269  1487231      1.49
## 270  1352458      1.35

unique_clusters_AUT

##    Population Chromosome   Cluster   r2 nSegments nSNPs     Start       End
## 2         AUT          1 1763_0.77 0.77        30    61  87157392  88199259
## 10        AUT          1  1673_0.8  0.8       395   486 260581858 262016624
## 13        AUT          2 3065_0.81 0.81      1933  4652  49798927  52237467
## 15        AUT          2 3065_0.81 0.81      1933  4652 103572137 106204056
## 16        AUT          2 3065_0.81 0.81      1933  4652 124168259 126538488
## 21        AUT          2 3065_0.81 0.81      1933  4652 153767456 155771880
## 22        AUT          2 3066_0.81 0.81       797   989 156275046 158102348
## 23        AUT          2  3533_0.6  0.6        33    72 328800255 329979871
## 25        AUT          2 3215_0.78 0.78        97   324 390518548 391668996
## 26        AUT          2 3215_0.78 0.78        97   324 391711273 392777580
## 27        AUT          2 3215_0.78 0.78        97   324 397107735 401367529
## 30        AUT          2  3138_0.8  0.8        26    61 411409101 412997990
## 32        AUT          2 3065_0.81 0.81      1933  4652 447843218 448906645
## 33        AUT          2 3065_0.81 0.81      1933  4652 466090283 467282916
## 34        AUT          2 3065_0.81 0.81      1933  4652 495634845 497303862
## 35        AUT          2 3065_0.81 0.81      1933  4652 502247398 503278166
## 36        AUT          2 3065_0.81 0.81      1933  4652 504551083 505702718
## 39        AUT          3 2950_0.81 0.81      1634  6373  22221783  24876231
## 41        AUT          3 2950_0.81 0.81      1634  6373  64323643  66464901
## 43        AUT          3 2950_0.81 0.81      1634  6373  69348616  70416221
## 47        AUT          3 2950_0.81 0.81      1634  6373 116172157 117763299
## 54        AUT          3 2950_0.81 0.81      1634  6373 261367232 263434740
## 55        AUT          3 2950_0.81 0.81      1634  6373 263696140 264901249
## 58        AUT          3 2950_0.81 0.81      1634  6373 284309274 285864116
## 60        AUT          3 2950_0.81 0.81      1634  6373 314111993 315235784
## 63        AUT          3 2950_0.81 0.81      1634  6373 378164815 379392861
##       Size Size (Mb)
## 2  1041867      1.04
## 10 1434766      1.43
## 13 2438540      2.44
## 15 2631919      2.63
## 16 2370229      2.37
## 21 2004424      2.00
## 22 1827302      1.83
## 23 1179616      1.18
## 25 1150448      1.15
## 26 1066307      1.07
## 27 4259794      4.26
## 30 1588889      1.59
## 32 1063427      1.06
## 33 1192633      1.19
## 34 1669017      1.67
## 35 1030768      1.03
## 36 1151635      1.15
## 39 2654448      2.65
## 41 2141258      2.14
## 43 1067605      1.07
## 47 1591142      1.59
## 54 2067508      2.07
## 55 1205109      1.21
## 58 1554842      1.55
## 60 1123791      1.12
## 63 1228046      1.23

Plot it

# Combine the two data frames
combined_clusters <- rbind(unique_clusters_NEW, unique_clusters_AUT)


# Function to format numbers as Mb
label_mb <- function(x) {
  sprintf("%.0fMb", x / 1e6)
}

# Plot it
ggplot(combined_clusters, aes(xmin = Start, xmax = End, ymin = 0, ymax = Size)) +
  geom_rect(aes(fill = as.factor(Cluster)), color = "black", linewidth = 0.2) +
  scale_x_continuous(labels = label_mb, breaks = pretty_breaks(n = 3)) +
  scale_y_continuous(labels = label_mb, breaks = pretty_breaks(n = 5)) +
  labs(x = "Position", y = "Cluster Size") +
  theme_minimal() +
  theme(
    axis.text.y = element_text(margin = margin(t = 0, r = 5, b = 0, l = 5)),
    axis.ticks.y = element_blank(),
    panel.grid.major.x = element_line(color = "gray", linetype = "dotted"),
    strip.background = element_rect(fill = "#e8e8e8", colour = NA),
    panel.grid.minor.x = element_blank(),
    legend.position = "none",
    panel.spacing.x = unit(1, "lines")  # Adjust the unit and number to increase space as needed
  ) +
  facet_grid(Population ~ Chromosome, scales = "fixed", space = "fixed") +
  guides(fill = "none")

# Use ggsave to save the plot as a PDF
# ggsave(
#   filename = here("output", "ldna", "AUT_NEW_fixed_non_overlapping.pdf"),
#   device = "pdf",
#   width = 10,
#   height = 5,
#   units = "in"
# )

snps_DEgenes<- read_delim(here("output", "snpeff", "SNPs_on_DE_genes.txt"), delim = "\t", col_names = TRUE, show_col_types = FALSE)
head(snps_DEgenes)

## # A tibble: 6 x 3
##   SNP          Chromosome Position_chr
##   <chr>             <dbl>        <dbl>
## 1 AX-583050970          1      3777633
## 2 AX-583052853          1      3777864
## 3 AX-583051011          1      3779183
## 4 AX-583052887          1      3793314
## 5 AX-583051025          1      3793653
## 6 AX-583052920          1      3794185

Check if any SNP fall within the clusters

# Initialize an empty data frame to store the results
results <- data.frame(Population = character(), Chromosome = integer(),
                      Cluster = character(), r2 = numeric(),
                      nSegments = integer(), nSNPs = integer(),
                      Start = integer(), End = integer(), Size = integer(),
                      SizeMb = numeric(), SNP = character(), Position_chr = integer(),
                      stringsAsFactors = FALSE)

for (i in 1:nrow(snps_DEgenes)) {
    for (j in 1:nrow(combined_clusters)) {
        if (snps_DEgenes$Chromosome[i] == combined_clusters$Chromosome[j] &&
            snps_DEgenes$Position_chr[i] >= combined_clusters$Start[j] &&
            snps_DEgenes$Position_chr[i] <= combined_clusters$End[j]) {

            # Create a new row as a data frame with the same column names
            new_row <- data.frame(Population = combined_clusters$Population[j],
                                  Chromosome = combined_clusters$Chromosome[j],
                                  Cluster = combined_clusters$Cluster[j],
                                  r2 = combined_clusters$r2[j],
                                  nSegments = combined_clusters$nSegments[j],
                                  nSNPs = combined_clusters$nSNPs[j],
                                  Start = combined_clusters$Start[j],
                                  End = combined_clusters$End[j],
                                  Size = combined_clusters$Size[j],
                                  SizeMb = combined_clusters$Size[j],
                                  SNP = snps_DEgenes$SNP[i],
                                  Position_chr = snps_DEgenes$Position_chr[i],
                                  stringsAsFactors = FALSE)

            # Append the new row to the results data frame
            results <- rbind(results, new_row)
        }
    }
}


head(results)

##   Population Chromosome   Cluster   r2 nSegments nSNPs    Start      End
## 1        NEW          1 2098_0.81 0.81       225  3339 17763447 19491473
## 2        NEW          1 2098_0.81 0.81       225  3339 17763447 19491473
## 3        NEW          1 2098_0.81 0.81       225  3339 17763447 19491473
## 4        NEW          1 2098_0.81 0.81       225  3339 17763447 19491473
## 5        NEW          1 2098_0.81 0.81       225  3339 17763447 19491473
## 6        NEW          1 2098_0.81 0.81       225  3339 17763447 19491473
##      Size  SizeMb          SNP Position_chr
## 1 1728026 1728026 AX-583091405     18352792
## 2 1728026 1728026 AX-583091423     18353091
## 3 1728026 1728026 AX-583093509     18354233
## 4 1728026 1728026 AX-583091460     18354996
## 5 1728026 1728026 AX-583093519     18355386
## 6 1728026 1728026 AX-583093532     18373267

We can count how many SNPs we have per cluster per population

snp_counts <- results %>%
  select(Population, Chromosome, Cluster, nSNPs) %>%
  distinct() %>%
  rename(SNP_Count = nSNPs)


head(snp_counts)

##   Population Chromosome   Cluster SNP_Count
## 1        NEW          1 2098_0.81      3339
## 2        NEW          2  3404_0.8      1502
## 3        NEW          2  3393_0.8      3235
## 4        AUT          2 3215_0.78       324
## 5        NEW          3 2837_0.81      1668
## 6        AUT          3 2950_0.81      6373

Plot the clusters for which we have SNPs on the DE genes

# Merge SNP counts into results
results_with_counts <- merge(results, snp_counts, by = c("Population", "Chromosome", "Cluster"))

ggplot(results_with_counts, aes(xmin = Start, xmax = End, ymin = 0, ymax = Size)) +
  geom_rect(aes(fill = as.factor(Cluster)), color = "black", linewidth = 0.2) +
  geom_text(aes(x = (Start + End) / 2, y = Size + 0.5, label = SNP_Count), size = 3, vjust = -0.2) + # Annotate SNP counts on top
  scale_x_continuous(labels = label_mb, breaks = pretty_breaks(n = 3)) +
  scale_y_continuous(labels = label_mb, breaks = pretty_breaks(n = 5)) +
  labs(x = "Position", y = "Cluster Size") +
  theme_minimal() +
  theme(
    axis.text.y = element_text(margin = margin(t = 0, r = 5, b = 0, l = 5)),
    axis.ticks.y = element_blank(),
    panel.grid.major.x = element_line(color = "gray", linetype = "dotted"),
    strip.background = element_rect(fill = "#e8e8e8", colour = NA),
    panel.grid.minor.x = element_blank(),
    legend.position = "none",
    panel.spacing.x = unit(1, "lines")
  ) +
  facet_grid(Population ~ Chromosome, scales = "fixed", space = "fixed") +
  guides(fill = "none")

# 1. Generate integer IDs for each cluster in plotting order
cluster_ids <- data.frame(
  Cluster     = sort(unique(results$Cluster)),
  Cluster_ID  = seq_along(unique(results$Cluster))
)

# 2. Merge IDs into your results
results_with_ids <- merge(results, cluster_ids, by = "Cluster")

# 3. Plot, labeling by your original 1,2,3,… IDs
ggplot(results_with_ids, aes(xmin = Start, xmax = End, ymin = 0, ymax = Size)) +
  geom_rect(aes(fill = factor(Cluster_ID)), color = "black", linewidth = 0.2) +
  geom_text(aes(x = (Start + End) / 2,
                y = Size + 0.5,
                label = Cluster_ID),
            size = 3, vjust = -0.2) +
  scale_x_continuous(labels = label_mb, breaks = pretty_breaks(n = 3)) +
  scale_y_continuous(labels = label_mb, breaks = pretty_breaks(n = 5)) +
  labs(x = "Position", y = "Cluster Size") +
  theme_minimal() +
  theme(
    axis.text.y        = element_text(margin = margin(t = 0, r = 5)),
    axis.ticks.y       = element_blank(),
    panel.grid.major.x = element_line(color = "gray", linetype = "dotted"),
    strip.background   = element_rect(fill = "#e8e8e8", colour = NA),
    panel.grid.minor.x = element_blank(),
    legend.position    = "none",
    panel.spacing.x    = unit(1, "lines")
  ) +
  facet_grid(Population ~ Chromosome, scales = "fixed", space = "fixed") +
  guides(fill = "none")

# 1. Merge integer IDs into your SNP‐counted data
cluster_ids <- data.frame(
  Cluster    = sort(unique(results_with_counts$Cluster)),
  Cluster_ID = seq_along(unique(results_with_counts$Cluster))
)
results_with_counts <- merge(results_with_counts, cluster_ids, by = "Cluster")

# 2. Build the fill label
results_with_counts$Cluster_SNP <- with(
  results_with_counts,
  paste0(Cluster, " (", SNP_Count, " SNPs)")
)

# 3. Plot with fill by SNP count label and text by cluster ID
ggplot(results_with_counts, aes(xmin = Start, xmax = End, ymin = 0, ymax = Size)) +
  geom_rect(aes(fill = Cluster_SNP), color = "black", linewidth = 0.2) +
  geom_text(
    aes(x = (Start + End) / 2, y = Size + 0.5, label = Cluster_ID),
    size = 3, vjust = -0.2
  ) +
  scale_fill_discrete(name = "Cluster and SNP Count") +
  scale_x_continuous(labels = label_mb, breaks = pretty_breaks(n = 3)) +
  scale_y_continuous(labels = label_mb, breaks = pretty_breaks(n = 5)) +
  labs(x = "Position", y = "Cluster Size") +
  theme_minimal() +
  theme(
    axis.text.y        = element_text(margin = margin(t = 0, r = 5)),
    axis.ticks.y       = element_blank(),
    panel.grid.major.x = element_line(color = "gray", linetype = "dotted"),
    strip.background   = element_rect(fill = "#e8e8e8", colour = NA),
    panel.grid.minor.x = element_blank(),
    legend.position    = "right",
    panel.spacing.x    = unit(1, "lines")
  ) +
  facet_grid(Population ~ Chromosome, scales = "fixed", space = "fixed")

Save

saveRDS(results_with_counts, file = here("output", "ldna", "results_with_counts.rds"))

Read the data

results_with_counts <- readRDS(file = here("output", "ldna", "results_with_counts.rds"))

# Rebuild the fill label: add ID before Cluster and drop “ SNPs”
results_with_counts$Cluster_SNP <- with(
  results_with_counts,
  paste0(Cluster_ID, ": ", Cluster, " (", SNP_Count, ")")
)

# 1. Reorder Cluster_SNP factor by Cluster_ID so the legend follows numeric order
results_with_counts$Cluster_SNP <- factor(
  results_with_counts$Cluster_SNP,
  levels = results_with_counts %>%
    distinct(Cluster_ID, Cluster_SNP) %>%
    arrange(Cluster_ID) %>%
    pull(Cluster_SNP)
)

# 2. Plot with sorted legend
ggplot(results_with_counts, aes(xmin = Start, xmax = End, ymin = 0, ymax = Size)) +
  geom_rect(aes(fill = Cluster_SNP), color = "black", linewidth = 0.2) +
  geom_text(
    aes(x = (Start + End) / 2, y = Size + 0.5, label = Cluster_ID),
    size = 3, vjust = -0.2
  ) +
  scale_fill_discrete(name = "Cluster and SNP Count") +
  scale_x_continuous(labels = label_mb, breaks = pretty_breaks(n = 3)) +
  scale_y_continuous(labels = label_mb, breaks = pretty_breaks(n = 5)) +
  labs(x = "Position", y = "Cluster Size") +
  theme_minimal() +
  theme(
    axis.text.y        = element_text(margin = margin(t = 0, r = 5)),
    axis.ticks.y       = element_blank(),
    panel.grid.major.x = element_line(color = "gray", linetype = "dotted"),
    strip.background   = element_rect(fill = "#e8e8e8", colour = NA),
    panel.grid.minor.x = element_blank(),
    legend.position    = "right",
    panel.spacing.x    = unit(1, "lines")
  ) +
  facet_grid(Population ~ Chromosome, scales = "fixed", space = "fixed")

# Use ggsave to save the plot as a PDF
ggsave(
  filename = here("output", "ldna", "AUT_NEW_non_overlapping_clusters_with_SNPs_on_DE_genes.pdf"),
  device = "pdf",
  width = 10,
  height = 5,
  units = "in"
)

Save it

library(writexl)

# 1. Drop Cluster_ID column(s)
cleaned_results <- results_with_counts %>%
  select(-starts_with("Cluster_ID")) %>%
  mutate(
    Start        = formatC(Start,        format = "f", digits = 0),
    End          = formatC(End,          format = "f", digits = 0),
    Position_chr = formatC(Position_chr, format = "f", digits = 0)
  )


# 2. Export cleaned results_with_counts to Excel
write_xlsx(
  list(Results = cleaned_results),
  here("output/ldna/results_with_counts.xlsx")
)

Now we can get the SNPs on the DE genes

snps79_DE_genes<- read_delim(here("output", "snpeff","SNPs_79_DE.txt"), delim = "\t", col_names = FALSE, show_col_types = FALSE)
head(snps79_DE_genes)

## # A tibble: 6 x 1
##   X1          
##   <chr>       
## 1 AX-583054970
## 2 AX-583055828
## 3 AX-583093532
## 4 AX-583142560
## 5 AX-583237406
## 6 AX-583279927

Or the SNPs from the selection scan

snps_selection <- read_delim(here("output", "pcadapt","outlier_157_SNPs.txt"), delim = "\t", col_names = FALSE, show_col_types = FALSE)
head(snps_selection)

## # A tibble: 6 x 1
##   X1          
##   <chr>       
## 1 AX-583054970
## 2 AX-583095890
## 3 AX-583324654
## 4 AX-583423493
## 5 AX-583426050
## 6 AX-583467551

Filter

# Create a logical vector to filter rows based on SNP IDs
filter_vector <- results_with_counts$SNP %in% snps79_DE_genes$X1
# filter_vector <- results_with_counts$SNP %in% snps_selection$X1  # we do not have any

# Subset results_with_counts to keep only rows where SNP matches
filtered_results <- results_with_counts[filter_vector, ]

head(filtered_results)

##      Cluster Population Chromosome   r2 nSegments nSNPs     Start       End
## 6  2098_0.81        NEW          1 0.81       225  3339  17763447  19491473
## 16 2098_0.81        NEW          1 0.81       225  3339  31462771  33110064
## 19 2098_0.81        NEW          1 0.81       225  3339  57603304  81674467
## 23 2098_0.81        NEW          1 0.81       225  3339  57603304  81674467
## 52 2098_0.81        NEW          1 0.81       225  3339 199758742 207076243
## 57 2098_0.81        NEW          1 0.81       225  3339 199758742 207076243
##        Size   SizeMb          SNP Position_chr SNP_Count Cluster_ID
## 6   1728026  1728026 AX-583093532     18373267      3339          1
## 16  1647293  1647293 AX-583142560     33012482      3339          1
## 19 24071163 24071163 AX-583237406     66299838      3339          1
## 23 24071163 24071163 AX-583279927     80133483      3339          1
## 52  7317501  7317501 AX-583696963    199917250      3339          1
## 57  7317501  7317501 AX-583709904    206309664      3339          1
##            Cluster_SNP
## 6  1: 2098_0.81 (3339)
## 16 1: 2098_0.81 (3339)
## 19 1: 2098_0.81 (3339)
## 23 1: 2098_0.81 (3339)
## 52 1: 2098_0.81 (3339)
## 57 1: 2098_0.81 (3339)

# length(filtered_results)

We have 16 SNPs

# Assign unique numbers to each cluster and create labels
filtered_results <- filtered_results %>%
  mutate(Cluster_Number = as.numeric(as.factor(Cluster))) %>%
  arrange(Cluster_Number) %>%
  mutate(Cluster_Label = paste(Cluster_Number, "_", Cluster, " (", SNP_Count, ")", sep=""))

# Reorder the factor levels of Cluster_Label based on Cluster_Number
filtered_results$Cluster_Label <- factor(filtered_results$Cluster_Label,
                                            levels = unique(filtered_results$Cluster_Label[order(filtered_results$Cluster_Number)]))

# Plotting
ggplot(filtered_results, aes(xmin = Start, xmax = End, ymin = 0, ymax = Size)) +
  geom_rect(aes(fill = Cluster_Label), color = "black", linewidth = 0.2) +
  geom_text(aes(x = (Start + End) / 2, y = Size + 0.5, label = Cluster_Number), size = 3, vjust = -0.2) +
  scale_fill_discrete(name = "Cluster ID") +
  scale_x_continuous(labels = label_mb, breaks = pretty_breaks(n = 3)) +
  scale_y_continuous(labels = label_mb, breaks = pretty_breaks(n = 5)) +
  labs(x = "Position", y = "Cluster Size") +
  theme_minimal() +
  theme(
    axis.text.y = element_text(margin = margin(t = 0, r = 5, b = 0, l = 5)),
    axis.ticks.y = element_blank(),
    panel.grid.major.x = element_line(color = "gray", linetype = "dotted"),
    strip.background = element_rect(fill = "#e8e8e8", colour = NA),
    panel.grid.minor.x = element_blank(),
    legend.position = "right",
    panel.spacing.x = unit(1, "lines")
  ) +
  facet_grid(Population ~ Chromosome, scales = "fixed", space = "fixed")

# Use ggsave to save the plot as a PDF
ggsave(
  filename = here("output", "ldna", "AUT_NEW_overlapping_clusters_with_SNPs_on_DE_genes_intersect.pdf"),
  device = "pdf",
  width = 10,
  height = 5,
  units = "in"
)

This are the clusters for which we found the SNP as outlier and the gene the SNP in on is DE

Get the overlapping clusters

# Function to find overlapping clusters
find_overlapping_clusters <- function(population1, population2) {
  overlapping_clusters <- list()

  for (chr in unique(population1$Chromosome)) {
    pop1_chrom_clusters <- population1[population1$Chromosome == chr, ]
    pop2_chrom_clusters <- population2[population2$Chromosome == chr, ]

    overlapping_clusters_chr <- list()

    for (i in 1:nrow(pop1_chrom_clusters)) {
      for (j in 1:nrow(pop2_chrom_clusters)) {
        if (pop1_chrom_clusters$Start[i] <= pop2_chrom_clusters$End[j] &&
            pop1_chrom_clusters$End[i] >= pop2_chrom_clusters$Start[j]) {
          overlapping_clusters_chr <- c(overlapping_clusters_chr, list(pop1_chrom_clusters[i, ]))
          break
        }
      }
    }

    if (length(overlapping_clusters_chr) > 0) {
      overlapping_clusters[[chr]] <- do.call(rbind, overlapping_clusters_chr)
    }
  }

  do.call(rbind, overlapping_clusters)
}

# Subset data for NEW and AUT populations
albo_NEW <- subset(albo2, Population == "NEW")
albo_AUT <- subset(albo2, Population == "AUT")

# Find overlapping clusters between NEW and AUT
overlapping_clusters <- find_overlapping_clusters(albo_NEW, albo_AUT)

# View the overlapping clusters
overlapping_clusters

##     Population Chromosome   Cluster   r2 nSegments nSNPs     Start       End
## 66         NEW          1 2098_0.81 0.81       225  3339   1671072  16303506
## 76         NEW          1 2257_0.78 0.78        21    49  88409052  90437664
## 82         NEW          1 2098_0.81 0.81       225  3339 118382563 133808459
## 83         NEW          1 2098_0.81 0.81       225  3339 134311499 152641345
## 86         NEW          1 2098_0.81 0.81       225  3339 175562655 184285228
## 95         NEW          1 2098_0.81 0.81       225  3339 241581708 245964256
## 96         NEW          1 2098_0.81 0.81       225  3339 246194066 250559827
## 101        NEW          1 2098_0.81 0.81       225  3339 263937222 271417059
## 102        NEW          1 2098_0.81 0.81       225  3339 274018327 291005909
## 137        NEW          2  3393_0.8  0.8      1027  3235 100600773 102052192
## 142        NEW          2  3404_0.8  0.8       905  1502 129752494 132084935
## 144        NEW          2  3393_0.8  0.8      1027  3235 137286537 138732635
## 145        NEW          2  3404_0.8  0.8       905  1502 141517826 144428065
## 148        NEW          2  3404_0.8  0.8       905  1502 149738780 153093408
## 170        NEW          2  3404_0.8  0.8       905  1502 331446801 335080127
## 180        NEW          2  3404_0.8  0.8       905  1502 407185045 409429909
## 184        NEW          2  3404_0.8  0.8       905  1502 445321096 447678524
## 189        NEW          2  3393_0.8  0.8      1027  3235 522038684 523113152
## 196        NEW          3 2837_0.81 0.81       602  1668   8741873  16401719
## 203        NEW          3 2837_0.81 0.81       602  1668  57016980  58476637
## 205        NEW          3 2837_0.81 0.81       602  1668  66551211  68843398
## 206        NEW          3 2837_0.81 0.81       602  1668  70979233  76622043
## 213        NEW          3 2837_0.81 0.81       602  1668 110248778 112627576
## 227        NEW          3 2837_0.81 0.81       602  1668 197419987 208785670
## 229        NEW          3 2837_0.81 0.81       602  1668 212882391 219711403
## 230        NEW          3 2837_0.81 0.81       602  1668 220295952 223586999
## 236        NEW          3 2837_0.81 0.81       602  1668 252765819 258190930
## 238        NEW          3 2836_0.81 0.81       567  1122 266966314 268898469
## 239        NEW          3 2837_0.81 0.81       602  1668 269155423 274126769
## 246        NEW          3 2837_0.81 0.81       602  1668 296354064 298088579
## 254        NEW          3 2837_0.81 0.81       602  1668 339919173 342105404
## 255        NEW          3 2836_0.81 0.81       567  1122 344380481 345522786
## 257        NEW          3 2837_0.81 0.81       602  1668 380236644 381564291
## 261        NEW          3 2836_0.81 0.81       567  1122 437336558 438485871
##         Size Size (Mb)
## 66  14632434     14.63
## 76   2028612      2.03
## 82  15425896     15.43
## 83  18329846     18.33
## 86   8722573      8.72
## 95   4382548      4.38
## 96   4365761      4.37
## 101  7479837      7.48
## 102 16987582     16.99
## 137  1451419      1.45
## 142  2332441      2.33
## 144  1446098      1.45
## 145  2910239      2.91
## 148  3354628      3.35
## 170  3633326      3.63
## 180  2244864      2.24
## 184  2357428      2.36
## 189  1074468      1.07
## 196  7659846      7.66
## 203  1459657      1.46
## 205  2292187      2.29
## 206  5642810      5.64
## 213  2378798      2.38
## 227 11365683     11.37
## 229  6829012      6.83
## 230  3291047      3.29
## 236  5425111      5.43
## 238  1932155      1.93
## 239  4971346      4.97
## 246  1734515      1.73
## 254  2186231      2.19
## 255  1142305      1.14
## 257  1327647      1.33
## 261  1149313      1.15

Plot it

# Function to format numbers as Mb
label_mb <- function(x) {
  sprintf("%.0fMb", x / 1e6)
}

# Plot it
ggplot(overlapping_clusters, aes(xmin = Start, xmax = End, ymin = 0, ymax = Size)) +
  geom_rect(aes(fill = as.factor(Cluster)), color = "black", linewidth = 0.2) +
  scale_x_continuous(labels = label_mb, breaks = pretty_breaks(n = 3)) +
  scale_y_continuous(labels = label_mb, breaks = pretty_breaks(n = 5)) +
  labs(x = "Position", y = "Cluster Size") +
  theme_minimal() +
  theme(
    axis.text.y = element_text(margin = margin(t = 0, r = 5, b = 0, l = 5)),
    axis.ticks.y = element_blank(),
    panel.grid.major.x = element_line(color = "gray", linetype = "dotted"),
    strip.background = element_rect(fill = "#e8e8e8", colour = NA),
    panel.grid.minor.x = element_blank(),
    legend.position = "none",
    panel.spacing.x = unit(1, "lines")  # Adjust the unit and number to increase space as needed
  ) +
  facet_grid(Population ~ Chromosome, scales = "fixed", space = "fixed") +
  guides(fill = "none")

# Use ggsave to save the plot as a PDF
ggsave(
  filename = here("output", "ldna", "AUT_NEW_fixed_overlapping.pdf"),
  device = "pdf",
  width = 10,
  height = 5,
  units = "in"
)

8. Mapping back SNP clusters to scaffolds

Clean env and memory

# Remove all objects from the environment
rm(list = ls())

# Run the garbage collector to free up memory
gc()

##           used (Mb) gc trigger  (Mb) max used  (Mb)
## Ncells 1540503 82.3    3147227 168.1  3147227 168.1
## Vcells 2771221 21.2    8388608  64.0  5863028  44.8

I created the chromosomal scale for the linkage networks analysis, now we have to map back the SNPs from clusters of interest to the scaffold scale, then we can check the gene annotation file to find what genes are in the linkage group.

Cluster 14 is on chromosome 2 and only in the AUT line. I create files with the SNP ids, we can import it (on the legend is the cluster 14_3215_0.78 (18))

aut_ch2 <- readRDS(here("output", "ldna", "pop", "chr2", "AUT_clusters_snps.rds"))
str(aut_ch2$`3215_0.78`)

##  chr [1:4652] "AX-579450486" "AX-579456609" "AX-579459157" "AX-579459504" ...

# We have 566 SNPs on this cluster

Now we can import the bim file with the scaffolds. We can use the backup file we created when we created the chromosomal scale.

head output/quality_control/file7_backup.bim

## 1.1  AX-581444870    0   97856   C   T
## 1.1  AX-583035083    0   305518  A   G
## 1.1  AX-583035102    0   308124  A   G
## 1.1  AX-583033342    0   315059  C   G
## 1.1  AX-583035163    0   315386  A   G
## 1.1  AX-583033356    0   315674  C   T
## 1.1  AX-583033370    0   330057  G   A
## 1.1  AX-583035194    0   330265  A   G
## 1.1  AX-583035198    0   330908  G   T
## 1.1  AX-583033387    0   331288  C   T

Import it

# Import the function
source(
  here(
    "notebooks", "helpers", "import_bim.R")
)

# Import the data
snps <- import_bim(here("output", "quality_control", "file7_backup.bim"))

# Check it
head(snps)

## # A tibble: 6 x 6
##   Scaffold SNP             Cm Position Allele1 Allele2
##   <chr>    <chr>        <int>    <dbl> <chr>   <chr>  
## 1 1.1      AX-581444870     0    97856 C       T      
## 2 1.1      AX-583035083     0   305518 A       G      
## 3 1.1      AX-583035102     0   308124 A       G      
## 4 1.1      AX-583033342     0   315059 C       G      
## 5 1.1      AX-583035163     0   315386 A       G      
## 6 1.1      AX-583033356     0   315674 C       T

Now we can filter the 566 SNPs that are in the cluster and see what scaffolds there are located

cluster_14 <- snps[snps$SNP %in% aut_ch2$`3215_0.78`, ]
head(cluster_14) # 316 SNPs

## # A tibble: 6 x 6
##   Scaffold SNP             Cm Position Allele1 Allele2
##   <chr>    <chr>        <int>    <dbl> <chr>   <chr>  
## 1 2.22     AX-579450486     0  1538827 G       A      
## 2 2.22     AX-579456609     0  2793553 T       G      
## 3 2.22     AX-579459157     0  3278309 C       T      
## 4 2.22     AX-579459504     0  3384885 C       A      
## 5 2.22     AX-579459790     0  3448373 T       C      
## 6 2.22     AX-579461404     0  3490196 C       T

# Save it
saveRDS(
  cluster_14, here(
    "output", "ldna", "cluster_14.rds"
    )
  )

Create table

knitr::kable(cluster_14)

Scaffold	SNP	Cm	Position	Allele1	Allele2
2.22	AX-579450486	0	1538827	G	A
2.22	AX-579456609	0	2793553	T	G
2.22	AX-579459157	0	3278309	C	T
2.22	AX-579459504	0	3384885	C	A
2.22	AX-579459790	0	3448373	T	C
2.22	AX-579461404	0	3490196	C	T
2.22	AX-579461838	0	3576474	G	A
2.22	AX-579461056	0	3629081	C	T
2.22	AX-579461271	0	3653077	C	T
2.22	AX-579462558	0	3681870	G	A
2.22	AX-579463030	0	3776496	A	G
2.22	AX-579463068	0	3777765	A	T
2.22	AX-579463086	0	3791971	A	C
2.22	AX-579463269	0	3848058	C	T
2.22	AX-579462195	0	3852455	T	C
2.22	AX-579463347	0	3852798	T	G
2.22	AX-579462236	0	3859113	A	G
2.22	AX-579463414	0	3861124	A	G
2.22	AX-579463494	0	3881563	T	C
2.22	AX-579463498	0	3882589	C	T
2.22	AX-579463587	0	3895702	A	G
2.22	AX-579462440	0	3895907	T	C
2.22	AX-579463874	0	3956685	T	C
2.22	AX-579462720	0	3966733	C	T
2.22	AX-579463888	0	3975909	C	T
2.22	AX-579464091	0	4020869	G	T
2.22	AX-579463106	0	4064758	T	C
2.22	AX-579463231	0	4094036	T	C
2.22	AX-579464583	0	4107741	C	G
2.22	AX-579464787	0	4212179	T	C
2.22	AX-579464795	0	4226874	C	T
2.22	AX-579463642	0	4262471	A	G
2.22	AX-579465027	0	4314848	G	A
2.22	AX-579463851	0	4326276	A	G
2.22	AX-579463996	0	4330431	C	T
2.22	AX-579465698	0	4393351	C	T
2.22	AX-579465949	0	4467885	C	G
2.22	AX-579466055	0	4480968	G	C
2.22	AX-579466082	0	4489343	A	C
2.22	AX-579465216	0	4574326	T	C
2.22	AX-579465235	0	4574813	A	G
2.22	AX-579466528	0	4587884	C	G
2.22	AX-579466629	0	4598725	T	C
2.22	AX-579465413	0	4599659	G	T
2.22	AX-579465498	0	4629289	T	A
2.22	AX-579465649	0	4656488	T	A
2.22	AX-579466030	0	4689200	C	T
2.22	AX-579468753	0	5318173	T	C
2.22	AX-579469407	0	5510490	A	G
2.22	AX-579469600	0	5515347	T	C
2.22	AX-579471414	0	5609135	A	G
2.22	AX-579471641	0	5644918	T	A
2.22	AX-579471677	0	5645846	T	C
2.22	AX-579471008	0	5770455	A	G
2.22	AX-579471253	0	5803284	C	T
2.22	AX-579471334	0	5819884	C	G
2.22	AX-579471617	0	5832805	A	G
2.22	AX-579471746	0	5843378	A	G
2.22	AX-579472640	0	6037441	G	T
2.22	AX-579474681	0	6123654	C	T
2.22	AX-579474277	0	6162084	T	C
2.22	AX-579475628	0	6170338	A	G
2.22	AX-579475675	0	6171699	T	C
2.22	AX-579474609	0	6173500	T	A
2.22	AX-579475863	0	6177554	T	C
2.22	AX-579477079	0	6337539	T	C
2.22	AX-579477559	0	6419058	C	T
2.22	AX-579480488	0	7113284	C	T
2.22	AX-579480540	0	7114693	C	T
2.22	AX-579481793	0	7166834	T	C
2.22	AX-579481954	0	7473323	T	C
2.22	AX-579483482	0	7806720	G	A
2.22	AX-579486420	0	8074399	C	T
2.22	AX-579486555	0	8186532	T	C
2.22	AX-579486568	0	8187000	T	G
2.22	AX-579490366	0	8853756	C	T
2.22	AX-579489177	0	8870912	C	G
2.22	AX-579489211	0	8871496	A	T
2.22	AX-579489422	0	8894417	A	C
2.22	AX-579492297	0	9511379	C	T
2.22	AX-579491302	0	9574144	G	C
2.22	AX-579493621	0	9747187	A	C
2.22	AX-579493195	0	9878211	G	A
2.22	AX-579494546	0	9881500	G	A
2.22	AX-579497824	0	10502539	T	C
2.22	AX-579498357	0	10769457	A	C
2.22	AX-579498441	0	10771570	A	G
2.22	AX-579499981	0	10805036	T	C
2.22	AX-579500777	0	11005339	A	G
2.22	AX-579499823	0	11078281	A	G
2.22	AX-579501488	0	11165465	A	C
2.22	AX-579501509	0	11486922	T	C
2.22	AX-579501594	0	11500114	T	A
2.22	AX-579501695	0	11518427	C	T
2.22	AX-579503052	0	11521815	T	C
2.22	AX-579503167	0	11811918	A	G
2.22	AX-579504531	0	11812599	A	G
2.22	AX-579505825	0	12322037	C	T
2.22	AX-579506213	0	12415362	C	G
2.27	AX-579514764	0	3143	A	T
2.27	AX-579514780	0	3924	A	T
2.27	AX-579514832	0	19391	T	C
2.27	AX-579513447	0	19620	T	C
2.27	AX-579515086	0	93803	G	A
2.27	AX-579515106	0	94019	A	G
2.27	AX-579516800	0	99017	A	G
2.27	AX-579521449	0	1313549	C	G
2.27	AX-579522956	0	1325963	C	T
2.27	AX-579521736	0	1345366	G	A
2.27	AX-579525293	0	1561644	C	T
2.27	AX-579524022	0	1563849	T	C
2.27	AX-579525501	0	1574245	A	G
2.27	AX-579528877	0	2083014	A	G
2.27	AX-579530612	0	2656493	A	G
2.27	AX-579531606	0	3939052	T	C
2.27	AX-579533372	0	4626751	T	C
2.27	AX-579533771	0	5190811	T	C
2.27	AX-579534229	0	5300874	A	T
2.27	AX-579533798	0	5480935	A	G
2.27	AX-579536022	0	5626846	T	C
2.27	AX-579536107	0	5639527	C	T
2.27	AX-579535050	0	5653677	G	A
2.27	AX-579535085	0	5654174	G	A
2.27	AX-579535400	0	5695991	T	G
2.27	AX-579537686	0	6005191	G	C
2.27	AX-579536482	0	6021051	C	G
2.27	AX-579537999	0	6037155	T	C
2.27	AX-579536746	0	6037770	G	A
2.27	AX-579538092	0	6266645	G	A
2.27	AX-579539919	0	6627914	A	C
2.27	AX-579544247	0	7482829	T	C
2.27	AX-579545575	0	7483880	T	G
2.27	AX-579546394	0	7837393	A	G
2.27	AX-579548165	0	7946950	T	C
2.27	AX-579548233	0	7958035	A	C
2.27	AX-579547370	0	8017758	C	T
2.27	AX-579547376	0	8017979	G	C
2.32	AX-579553752	0	2293932	T	C
2.36	AX-579554924	0	122073	T	C
2.36	AX-579555022	0	122978	A	G
2.36	AX-579554313	0	177712	G	A
2.36	AX-579554700	0	233093	G	A
2.36	AX-579555223	0	316293	G	C
2.36	AX-579556352	0	966741	A	G
2.36	AX-579556686	0	1233251	A	G
2.36	AX-579558663	0	1923334	G	A
2.36	AX-579560288	0	1988456	G	A
2.36	AX-579560662	0	2006981	C	T
2.36	AX-579559480	0	2010914	A	C
2.36	AX-579560965	0	2023214	A	G
2.36	AX-579559703	0	2024629	A	G
2.36	AX-579561712	0	2103073	A	G
2.36	AX-579560506	0	2117189	G	T
2.36	AX-579560776	0	2159466	C	T
2.36	AX-579561033	0	2360547	T	G
2.36	AX-579561118	0	2375602	A	C
2.36	AX-579561629	0	2476040	T	C
2.36	AX-579562408	0	2742031	C	T
2.36	AX-579564629	0	2977222	C	T
2.36	AX-579563611	0	3039586	G	A
2.36	AX-579564982	0	3063901	G	A
2.36	AX-579565814	0	3225773	A	G
2.36	AX-579566111	0	3499011	G	A
2.36	AX-579566130	0	3499260	T	G
2.36	AX-579566954	0	3775104	A	G
2.36	AX-579568657	0	3855224	G	T
2.36	AX-579568951	0	3924403	T	G
2.36	AX-579571176	0	4429492	C	T
2.36	AX-579571698	0	4506577	G	A
2.36	AX-579570501	0	4525604	A	G
2.36	AX-579571897	0	4525871	A	G
2.36	AX-579571606	0	4722263	G	T
2.36	AX-579573008	0	4722473	G	A
2.36	AX-579571640	0	4722920	T	G
2.36	AX-579571741	0	4732500	T	C
2.36	AX-579571778	0	4733288	C	A
2.36	AX-579571885	0	4735900	T	G
2.36	AX-579572182	0	4771453	T	C
2.36	AX-579572348	0	4773049	A	G
2.36	AX-579575218	0	4954626	T	C
2.36	AX-579574417	0	5093568	A	C
2.36	AX-579576372	0	5174565	G	C
2.36	AX-579575014	0	5182212	G	A
2.36	AX-579576494	0	5195710	A	G
2.36	AX-579576620	0	5220518	C	T
2.36	AX-579575264	0	5221019	T	C
2.36	AX-579576700	0	5232144	T	A
2.36	AX-579578676	0	5871547	C	A
2.36	AX-579578960	0	5905142	A	C
2.36	AX-579579230	0	5977765	C	T
2.36	AX-579580763	0	6013782	A	T
2.36	AX-579579387	0	6044877	A	G
2.36	AX-579579808	0	6131092	C	T
2.36	AX-579580108	0	6183757	G	A
2.36	AX-579580428	0	6264997	T	G
2.36	AX-579582210	0	6366093	C	T
2.36	AX-579580737	0	6374847	C	T
2.36	AX-579580782	0	6399348	G	C
2.36	AX-579582325	0	6409036	C	T
2.36	AX-579582344	0	6424187	G	T
2.36	AX-579582396	0	6451287	A	G
2.36	AX-579581051	0	6471713	G	A
2.36	AX-579582591	0	6471983	T	C
2.36	AX-579581085	0	6472487	G	A
2.36	AX-579582777	0	6484066	T	A
2.36	AX-579581842	0	6601224	T	C
2.36	AX-579582896	0	6815052	T	C
2.36	AX-579584795	0	6840596	T	G
2.36	AX-579585088	0	6864648	G	A
2.36	AX-579585247	0	6884462	A	G
2.36	AX-579585413	0	6913172	G	A
2.36	AX-579585547	0	6979869	A	G
2.36	AX-579584631	0	7310698	G	A
2.36	AX-579586817	0	7524611	C	T
2.36	AX-579587054	0	7555928	A	T
2.36	AX-579587132	0	7558468	A	G
2.36	AX-579585816	0	7598150	T	C
2.36	AX-579586639	0	7738695	A	G
2.36	AX-579588150	0	7739652	G	A
2.36	AX-579588280	0	7769335	C	T
2.36	AX-579588443	0	7785936	G	T
2.36	AX-579588768	0	7842421	C	A
2.36	AX-579588851	0	7847327	C	T
2.36	AX-579589139	0	7863252	C	T
2.36	AX-579589153	0	7863471	A	G
2.36	AX-579589060	0	8163406	G	A
2.36	AX-579591399	0	8368205	T	C
2.38	AX-579592977	0	33173	T	C
2.38	AX-579591594	0	105906	T	G
2.38	AX-579591718	0	138430	C	T
2.38	AX-579593540	0	225032	T	G
2.38	AX-579593773	0	307640	A	G
2.38	AX-579592307	0	307963	T	C
2.38	AX-579593876	0	332935	A	C
2.38	AX-579592773	0	808486	T	C
2.38	AX-579594255	0	808711	C	T
2.38	AX-579593116	0	904947	A	G
2.38	AX-579593401	0	1012549	C	T
2.38	AX-579595097	0	1068943	A	G
2.38	AX-579593808	0	1253358	C	T
2.38	AX-579595377	0	1435426	A	G
2.38	AX-579595568	0	1546396	C	T
2.38	AX-579594123	0	1555916	G	A
2.38	AX-579595641	0	1582105	A	G
2.38	AX-579595929	0	1745456	T	G
2.38	AX-579595131	0	1890450	C	G
2.38	AX-579596432	0	2092493	T	C
2.38	AX-579596460	0	2093042	A	C
2.38	AX-579596587	0	2133235	A	G
2.38	AX-579597760	0	2412837	G	A
2.38	AX-579600249	0	2643323	G	C
2.38	AX-579598791	0	2679893	C	A
2.38	AX-579598805	0	2680377	A	G
2.38	AX-579600802	0	2768268	A	G
2.38	AX-579599348	0	2769292	A	G
2.38	AX-579601954	0	3420287	C	T
2.38	AX-579603787	0	3855171	T	C
2.38	AX-579605417	0	3866591	C	T
2.38	AX-579605652	0	3869671	G	A
2.38	AX-579604364	0	3875395	A	G
2.38	AX-579605090	0	4025293	T	C
2.38	AX-579605155	0	4034581	T	C
2.38	AX-579605258	0	4059911	G	C
2.38	AX-579605997	0	4217138	T	C
2.38	AX-579606037	0	4233102	T	C
2.38	AX-579606082	0	4261878	A	C
2.38	AX-579606324	0	4321442	C	T
2.38	AX-579606484	0	4362367	T	C
2.38	AX-579607967	0	4365528	A	G
2.40	AX-579609322	0	7757	T	G
2.40	AX-579607994	0	22781	C	T
2.40	AX-579608017	0	23519	A	C
2.40	AX-579608372	0	63601	T	C
2.40	AX-579609853	0	63812	A	G
2.40	AX-579608454	0	66117	A	G
2.40	AX-579610235	0	117199	C	T
2.40	AX-579610308	0	269848	A	G
2.40	AX-579610990	0	314487	T	C
2.40	AX-579610992	0	314726	G	A
2.40	AX-579609938	0	391207	A	G
2.40	AX-579611740	0	476232	G	A
2.40	AX-579611969	0	535273	G	A
2.40	AX-579610498	0	542557	C	A
2.40	AX-579612052	0	555521	C	A
2.40	AX-579610585	0	556029	T	C
2.40	AX-579612219	0	589415	T	C
2.40	AX-579610845	0	611373	T	C
2.40	AX-579611070	0	637163	A	T
2.40	AX-579612655	0	659602	C	A
2.40	AX-579611192	0	668647	T	G
2.40	AX-579613074	0	747694	A	G
2.40	AX-579613337	0	825033	T	G
2.40	AX-579613453	0	836220	G	C
2.40	AX-579612387	0	894866	A	G
2.40	AX-579612453	0	896032	G	A
2.40	AX-579614469	0	1027270	C	T
2.40	AX-579612967	0	1027987	A	G
2.40	AX-579613089	0	1031879	G	A
2.40	AX-579614661	0	1032599	G	A
2.40	AX-579614672	0	1032875	A	G
2.40	AX-579613249	0	1035703	G	A
2.40	AX-579615168	0	1075172	G	C
2.40	AX-579615300	0	1086477	A	G
2.40	AX-579615327	0	1087851	A	G
2.40	AX-579615710	0	1164681	G	A
2.40	AX-579616152	0	1273262	C	A
2.40	AX-579616931	0	1384904	C	T
2.40	AX-579615476	0	1387460	T	C
2.40	AX-579615529	0	1407741	T	C
2.40	AX-579617096	0	1410210	T	A
2.40	AX-579617194	0	1412279	A	G
2.40	AX-579615703	0	1412642	A	G
2.40	AX-579617599	0	1468946	A	C
2.40	AX-579617368	0	1651660	T	C
2.40	AX-579619072	0	1665441	T	C
2.40	AX-579617534	0	1665651	A	C
2.40	AX-579618424	0	1904505	G	T
2.40	AX-579619997	0	1910958	T	C
2.40	AX-579620126	0	1955336	T	C
2.40	AX-579618630	0	1972960	C	T
2.40	AX-579618760	0	1995445	A	G
2.40	AX-579620866	0	2124643	G	A
2.40	AX-579619588	0	2186172	A	G
2.40	AX-579619840	0	2225961	T	C

Let’s check cluster 6_19_42 on AUT chr1

aut_ch1 <- readRDS(here("output", "ldna", "pop", "chr1", "AUT_clusters_snps.rds"))
str(aut_ch1$`1971_0.64`)

##  chr [1:1579] "AX-583500511" "AX-583500520" "AX-583503153" "AX-583500379" ...

# We have 566 SNPs on this cluster

cluster_6 <- snps[snps$SNP %in% aut_ch1$`1971_0.64`, ]
head(cluster_6) # 316 SNPs

## # A tibble: 6 x 6
##   Scaffold SNP             Cm Position Allele1 Allele2
##   <chr>    <chr>        <int>    <dbl> <chr>   <chr>  
## 1 1.152    AX-583500511     0   339500 G       C      
## 2 1.152    AX-583500520     0   345870 A       G      
## 3 1.152    AX-583503153     0   977944 T       G      
## 4 1.152    AX-583500379     0   978467 G       T      
## 5 1.152    AX-583503258     0   987625 C       T      
## 6 1.152    AX-583504302     0  1149628 A       G

# Save it
saveRDS(
  cluster_6, here(
    "output", "ldna", "cluster_6.rds"
    )
  )

Create table

knitr::kable(cluster_6)

Scaffold	SNP	Cm	Position	Allele1	Allele2
1.152	AX-583500511	0	339500	G	C
1.152	AX-583500520	0	345870	A	G
1.152	AX-583503153	0	977944	T	G
1.152	AX-583500379	0	978467	G	T
1.152	AX-583503258	0	987625	C	T
1.152	AX-583504302	0	1149628	A	G
1.152	AX-583503279	0	1491640	G	C
1.152	AX-583503440	0	1535179	A	G
1.152	AX-583503906	0	1564958	T	C
1.152	AX-583506777	0	1565216	C	G
1.152	AX-583504295	0	1602992	G	A
1.152	AX-583507197	0	1603711	G	T
1.152	AX-583507425	0	1627574	G	C
1.152	AX-583507639	0	1644594	T	C
1.152	AX-583507878	0	1664015	G	A
1.152	AX-583505073	0	1664826	T	C
1.152	AX-583508045	0	1665840	C	A
1.152	AX-583508498	0	1669803	T	C
1.152	AX-583508594	0	1670439	G	A
1.152	AX-583508771	0	1673676	T	C
1.152	AX-583505971	0	1673937	C	T
1.152	AX-583506892	0	1803316	G	C
1.152	AX-583511182	0	1955809	A	G
1.152	AX-583508519	0	1966895	C	T
1.152	AX-583508573	0	1971684	T	C
1.152	AX-583509292	0	2556372	T	C
1.152	AX-583509391	0	2580817	T	C
1.152	AX-583509412	0	2581274	A	G
1.152	AX-583509733	0	2598090	G	T
1.152	AX-583512511	0	2598734	A	G
1.152	AX-583510076	0	2619288	C	A
1.152	AX-583512897	0	2625567	G	C
1.152	AX-583513248	0	2655189	T	G
1.152	AX-583513308	0	2666934	T	G
1.152	AX-583513359	0	2668625	A	G
1.152	AX-583513377	0	2668892	A	G
1.152	AX-583510794	0	2701081	A	G
1.152	AX-583510903	0	2706078	C	T
1.152	AX-583513648	0	2725250	C	T
1.152	AX-583511483	0	2848038	G	A
1.152	AX-583514235	0	2848259	T	G
1.152	AX-583514359	0	2888182	A	G
1.152	AX-583514397	0	2900388	A	G
1.152	AX-583511792	0	2913109	T	C
1.152	AX-583512377	0	3056913	G	A
1.152	AX-583512666	0	3117848	C	A
1.152	AX-583515819	0	3174781	A	G
1.152	AX-583513555	0	3382178	T	C
1.152	AX-583513773	0	3464938	G	A
1.152	AX-583517814	0	3775044	T	C
1.152	AX-583519450	0	4112020	T	C
1.152	AX-583516942	0	4210175	A	G
1.152	AX-583517794	0	4432697	G	T
1.152	AX-583521326	0	5078954	C	A
1.152	AX-583521530	0	5098043	T	C
1.152	AX-583525764	0	5184643	T	C
1.152	AX-583527475	0	5423719	G	T
1.152	AX-583527695	0	5449431	G	A
1.152	AX-583526378	0	5567513	G	A
1.152	AX-583529290	0	5577967	C	T
1.152	AX-583530453	0	5927434	T	C
1.152	AX-583528261	0	6093153	A	G
1.152	AX-583531073	0	6102875	T	C
1.152	AX-583528689	0	6128044	T	C
1.152	AX-583530679	0	6478224	G	A
1.152	AX-583533848	0	6554566	A	G
1.152	AX-583532801	0	6856535	T	A
1.152	AX-583533673	0	7055034	T	C
1.152	AX-583536382	0	7055500	A	G
1.152	AX-583536435	0	7055779	C	T
1.152	AX-583534984	0	7166546	A	C
1.152	AX-583535005	0	7166793	G	C
1.152	AX-583537871	0	7168782	T	C
1.152	AX-583538179	0	7190150	A	G
1.152	AX-583536224	0	7313002	A	G
1.152	AX-583538596	0	7562522	C	T
1.152	AX-583539329	0	7641844	T	C
1.152	AX-583539476	0	7657914	T	G
1.152	AX-583542283	0	7660371	C	T
1.152	AX-583542500	0	7716798	G	A
1.152	AX-583542697	0	7766866	T	C
1.154	AX-583542132	0	533422	G	A
1.156	AX-583547648	0	11722	C	G
1.156	AX-583544949	0	74115	C	T
1.170	AX-583556250	0	197780	A	C
1.170	AX-583560886	0	919858	C	T
1.170	AX-583571044	0	1622696	T	C
1.170	AX-583571065	0	1623404	T	G
1.170	AX-583571174	0	1631928	A	G
1.170	AX-583571507	0	2091806	A	C

cluster_6_all <- snps[snps$Scaffold %in% cluster_6$Scaffold, ]
head(cluster_6_all)

## # A tibble: 6 x 6
##   Scaffold SNP             Cm Position Allele1 Allele2
##   <chr>    <chr>        <int>    <dbl> <chr>   <chr>  
## 1 1.152    AX-583496546     0    28493 T       C      
## 2 1.152    AX-583496607     0    43318 A       G      
## 3 1.152    AX-583499574     0    96763 G       A      
## 4 1.152    AX-583499672     0   132155 T       G      
## 5 1.152    AX-583499700     0   136348 A       G      
## 6 1.152    AX-583499977     0   188640 T       A

However we need the other SNPs to know if the blocks are connected or not. Now we know what scaffolds the SNPs are located and we can check it

cluster_14_all <- snps[snps$Scaffold %in% cluster_14$Scaffold, ]
head(cluster_14_all)

## # A tibble: 6 x 6
##   Scaffold SNP             Cm Position Allele1 Allele2
##   <chr>    <chr>        <int>    <dbl> <chr>   <chr>  
## 1 2.22     AX-579445128     0    49751 G       A      
## 2 2.22     AX-579445195     0    64564 A       T      
## 3 2.22     AX-579443938     0   100572 A       G      
## 4 2.22     AX-579445430     0   157266 G       T      
## 5 2.22     AX-579445592     0   202795 T       A      
## 6 2.22     AX-579444301     0   212193 C       T

Now we can create a new column and tag the SNPs that are linked

# Creating the new column 'linked'
cluster_14_all <- cluster_14_all %>%
  mutate(linked = SNP %in% aut_ch2$`3215_0.78`)
head(cluster_14_all)

## # A tibble: 6 x 7
##   Scaffold SNP             Cm Position Allele1 Allele2 linked
##   <chr>    <chr>        <int>    <dbl> <chr>   <chr>   <lgl> 
## 1 2.22     AX-579445128     0    49751 G       A       FALSE 
## 2 2.22     AX-579445195     0    64564 A       T       FALSE 
## 3 2.22     AX-579443938     0   100572 A       G       FALSE 
## 4 2.22     AX-579445430     0   157266 G       T       FALSE 
## 5 2.22     AX-579445592     0   202795 T       A       FALSE 
## 6 2.22     AX-579444301     0   212193 C       T       FALSE

# Creating the new column 'linked'
cluster_6_all <- cluster_6_all %>%
  mutate(linked = SNP %in% aut_ch1$`1971_0.64`)
head(cluster_6_all)

## # A tibble: 6 x 7
##   Scaffold SNP             Cm Position Allele1 Allele2 linked
##   <chr>    <chr>        <int>    <dbl> <chr>   <chr>   <lgl> 
## 1 1.152    AX-583496546     0    28493 T       C       FALSE 
## 2 1.152    AX-583496607     0    43318 A       G       FALSE 
## 3 1.152    AX-583499574     0    96763 G       A       FALSE 
## 4 1.152    AX-583499672     0   132155 T       G       FALSE 
## 5 1.152    AX-583499700     0   136348 A       G       FALSE 
## 6 1.152    AX-583499977     0   188640 T       A       FALSE

Lets check how many linked SNPs we have and how many aren’t

count_linked <- cluster_14_all %>%
  group_by(linked) %>%
  summarise(count = n())
count_linked

## # A tibble: 2 x 2
##   linked count
##   <lgl>  <int>
## 1 FALSE   2649
## 2 TRUE     324

count_linked <- cluster_6_all %>%
  group_by(linked) %>%
  summarise(count = n())
count_linked

## # A tibble: 2 x 2
##   linked count
##   <lgl>  <int>
## 1 FALSE   1268
## 2 TRUE      90

Get the 157 outliers

snps_157 <-
  read.table(
    here("output", "pcadapt", "outlier_157_SNPs.txt"),
    stringsAsFactors = FALSE
    )

# Get the 157 SNPs
snps_157b <- cluster_14_all |>
  filter(SNP %in% snps_157$V1)

head(snps_157b)

## # A tibble: 6 x 7
##   Scaffold SNP             Cm Position Allele1 Allele2 linked
##   <chr>    <chr>        <int>    <dbl> <chr>   <chr>   <lgl> 
## 1 2.22     AX-579474142     0  6075268 T       C       FALSE 
## 2 2.22     AX-579474650     0  6122430 A       G       FALSE 
## 3 2.22     AX-579509845     0 13142038 A       T       FALSE 
## 4 2.36     AX-579556477     0  1062758 T       C       FALSE 
## 5 2.36     AX-579560686     0  2139679 C       T       FALSE 
## 6 2.36     AX-579564292     0  2894537 A       G       FALSE

# Get the 157 SNPs
snps_157c <- cluster_6_all |>
  filter(SNP %in% snps_157$V1)

head(snps_157c)

## # A tibble: 6 x 7
##   Scaffold SNP             Cm Position Allele1 Allele2 linked
##   <chr>    <chr>        <int>    <dbl> <chr>   <chr>   <lgl> 
## 1 1.152    AX-583504302     0  1149628 A       G       TRUE  
## 2 1.152    AX-583514148     0  2847295 T       C       FALSE 
## 3 1.152    AX-583515734     0  3903190 A       G       FALSE 
## 4 1.152    AX-583518586     0  3966380 T       C       FALSE 
## 5 1.152    AX-583518994     0  4024772 A       G       FALSE 
## 6 1.152    AX-583516491     0  4057192 T       C       FALSE

Plot it

# Function to format numbers as Mb
label_mb <- function(x) {
  sprintf("%.0fMb", x / 1e6)
}


# Calculate the start and end positions for each stretch of TRUE or FALSE
rect_data <- cluster_14_all %>%
  arrange(Scaffold, Position) %>%
  mutate(change = linked != lag(linked, default = first(linked))) %>%
  group_by(Scaffold) %>%
  mutate(group_id = cumsum(change)) %>%
  group_by(Scaffold, group_id, linked) %>%
  summarize(start = min(Position), end = max(Position), .groups = 'drop') %>%
  ungroup()

# Plotting using geom_rect
ggplot(rect_data, aes(xmin = start, xmax = end, ymin = as.numeric(Scaffold) - 0.1, ymax = as.numeric(Scaffold) + 0.1)) +
  # Add a background layer for each scaffold with gray color
  geom_rect(data = rect_data %>% group_by(Scaffold) %>%
            summarize(start = min(start), end = max(end), .groups = 'drop'),
            aes(xmin = start, xmax = end, ymin = as.numeric(Scaffold) - 0.1, ymax = as.numeric(Scaffold) + 0.1),
            fill = "gray", inherit.aes = FALSE) +
  # Add the TRUE stretches
  geom_rect(aes(fill = linked), data = rect_data %>% filter(linked == TRUE)) +
  scale_fill_manual(values = c("TRUE" = "green")) +
  facet_wrap(~ Scaffold, scales = "fixed", ncol = 1) +
  geom_vline(data = snps_157b, aes(xintercept = Position, color = SNP), linetype = "solid", color = "red") +
  geom_text(data = snps_157b, aes(x = Position, y = as.numeric(Scaffold) + 0.2, label = SNP), inherit.aes = FALSE, angle = 90, vjust = 0, size = 2, check_overlap = TRUE) +
  theme_minimal() +
  theme(
    axis.title.y = element_blank(),
    axis.text.y = element_blank(),
    axis.ticks.y = element_blank(),
    panel.spacing = unit(0.1, "lines"),
    panel.grid.major = element_blank(),
    panel.grid.minor = element_blank(),
    strip.text = element_text(size = 12, face = "bold", hjust = 0.5, margin = margin(t = 1, b = 5))
  ) +
  scale_x_continuous(labels = label_mb, breaks = scales::pretty_breaks(n = 6)) +
  labs(x = "Position", title = "Continuous Stretches of Linked SNPs by Scaffold - Cluster 14 AUT", fill = "Linked") +
  guides(fill = "none")

# Save Venn diagram to PDF
output_path <- here("output", "ldna", "figures", "cluster_14_aut_scaffolds.pdf")
ggsave(output_path, height = 5, width = 8, units = "in")

To make sure the windows appear even if they are small

# Set a minimum width for the windows
min_width <- 1e4  # for example, 1 million base pairs

# Adjust the rect_data calculation
rect_data <- cluster_14_all %>%
  arrange(Scaffold, Position) %>%
  mutate(change = linked != lag(linked, default = first(linked))) %>%
  group_by(Scaffold) %>%
  mutate(group_id = cumsum(change)) %>%
  group_by(Scaffold, group_id, linked) %>%
  summarize(start = min(Position), end = max(Position), .groups = 'drop') %>%
  ungroup() %>%
  mutate(width = end - start,
         adjusted_end = ifelse(width < min_width, start + min_width, end))

# Plotting using geom_rect with adjusted ends
ggplot(rect_data, aes(xmin = start, xmax = adjusted_end, ymin = as.numeric(Scaffold) - 0.1, ymax = as.numeric(Scaffold) + 0.1)) +
  geom_rect(data = rect_data %>% group_by(Scaffold) %>%
            summarize(start = min(start), end = max(adjusted_end), .groups = 'drop'),
            aes(xmin = start, xmax = end, ymin = as.numeric(Scaffold) - 0.1, ymax = as.numeric(Scaffold) + 0.1),
            fill = "gray", inherit.aes = FALSE) +
  geom_rect(aes(fill = linked), data = rect_data %>% filter(linked == TRUE)) +
  scale_fill_manual(values = c("TRUE" = "green")) +
  facet_wrap(~ Scaffold, scales = "fixed", ncol = 1) +
  theme_minimal() +
  geom_vline(data = snps_157b, aes(xintercept = Position, color = SNP), linetype = "solid", color = "red") +
  geom_text_repel(data = snps_157b, aes(x = Position, y = as.numeric(Scaffold) + 0.2, label = SNP),
                  inherit.aes = FALSE, angle = 45, size = 2,
                  nudge_y = 0.1,   # Adjust this value as needed
                  direction = "y") +
  theme(axis.title.y = element_blank(), axis.text.y = element_blank(), axis.ticks.y = element_blank(), panel.spacing = unit(0.1, "lines"),
        panel.grid.major = element_blank(), panel.grid.minor = element_blank(),
        strip.text = element_text(size = 12, face = "bold", hjust = 0.5)) +
  scale_x_continuous(labels = label_mb, breaks = scales::pretty_breaks(n = 6)) +
  labs(x = "Position", title = "Continuous Stretches of Linked SNPs by Scaffold - Cluster 14 AUT", fill = "Linked") +
  guides(fill = "none")

## Warning: ggrepel: Repulsion works correctly only for rotation angles multiple of 90 degrees
## ggrepel: Repulsion works correctly only for rotation angles multiple of 90 degrees
## ggrepel: Repulsion works correctly only for rotation angles multiple of 90 degrees
## ggrepel: Repulsion works correctly only for rotation angles multiple of 90 degrees

# Save Venn diagram to PDF
output_path <- here("output", "ldna", "figures", "cluster_14_aut_scaffolds_with_small_windows.pdf")
ggsave(output_path, height = 5, width = 8, units = "in")

## Warning: ggrepel: Repulsion works correctly only for rotation angles multiple of 90 degrees
## ggrepel: Repulsion works correctly only for rotation angles multiple of 90 degrees
## ggrepel: Repulsion works correctly only for rotation angles multiple of 90 degrees
## ggrepel: Repulsion works correctly only for rotation angles multiple of 90 degrees

Cluster 6

# Function to format numbers as Mb
label_mb <- function(x) {
  sprintf("%.0fMb", x / 1e6)
}


# Calculate the start and end positions for each stretch of TRUE or FALSE
rect_data <- cluster_6_all %>%
  arrange(Scaffold, Position) %>%
  mutate(change = linked != lag(linked, default = first(linked))) %>%
  group_by(Scaffold) %>%
  mutate(group_id = cumsum(change)) %>%
  group_by(Scaffold, group_id, linked) %>%
  summarize(start = min(Position), end = max(Position), .groups = 'drop') %>%
  ungroup()

# Plotting using geom_rect
ggplot(rect_data, aes(xmin = start, xmax = end, ymin = as.numeric(Scaffold) - 0.1, ymax = as.numeric(Scaffold) + 0.1)) +
  # Add a background layer for each scaffold with gray color
  geom_rect(data = rect_data %>% group_by(Scaffold) %>%
            summarize(start = min(start), end = max(end), .groups = 'drop'),
            aes(xmin = start, xmax = end, ymin = as.numeric(Scaffold) - 0.1, ymax = as.numeric(Scaffold) + 0.1),
            fill = "gray", inherit.aes = FALSE) +
  # Add the TRUE stretches
  geom_rect(aes(fill = linked), data = rect_data %>% filter(linked == TRUE)) +
  scale_fill_manual(values = c("TRUE" = "green")) +
  facet_wrap(~ Scaffold, scales = "fixed", ncol = 1) +
  geom_vline(data = snps_157c, aes(xintercept = Position, color = SNP), linetype = "solid", color = "red") +
  geom_text(data = snps_157c, aes(x = Position, y = as.numeric(Scaffold) + 0.2, label = SNP), inherit.aes = FALSE, angle = 90, vjust = 0, size = 2, check_overlap = TRUE) +
  theme_minimal() +
  theme(
    axis.title.y = element_blank(),
    axis.text.y = element_blank(),
    axis.ticks.y = element_blank(),
    panel.spacing = unit(0.1, "lines"),
    panel.grid.major = element_blank(),
    panel.grid.minor = element_blank(),
    strip.text = element_text(size = 12, face = "bold", hjust = 0.5, margin = margin(t = 1, b = 5))
  ) +
  scale_x_continuous(labels = label_mb, breaks = scales::pretty_breaks(n = 6)) +
  labs(x = "Position", title = "Continuous Stretches of Linked SNPs by Scaffold - Cluster 6 AUT", fill = "Linked") +
  guides(fill = "none")

# Save Venn diagram to PDF
output_path <- here("output", "ldna", "figures", "cluster_6_aut_scaffolds.pdf")
ggsave(output_path, height = 5, width = 8, units = "in")

To make sure the windows appear even if they are small

# Set a minimum width for the windows
min_width <- 1e4  # for example, 1 million base pairs

# Adjust the rect_data calculation
rect_data <- cluster_6_all %>%
  arrange(Scaffold, Position) %>%
  mutate(change = linked != lag(linked, default = first(linked))) %>%
  group_by(Scaffold) %>%
  mutate(group_id = cumsum(change)) %>%
  group_by(Scaffold, group_id, linked) %>%
  summarize(start = min(Position), end = max(Position), .groups = 'drop') %>%
  ungroup() %>%
  mutate(width = end - start,
         adjusted_end = ifelse(width < min_width, start + min_width, end))

# Plotting using geom_rect with adjusted ends
ggplot(rect_data, aes(xmin = start, xmax = adjusted_end, ymin = as.numeric(Scaffold) - 0.1, ymax = as.numeric(Scaffold) + 0.1)) +
  geom_rect(data = rect_data %>% group_by(Scaffold) %>%
            summarize(start = min(start), end = max(adjusted_end), .groups = 'drop'),
            aes(xmin = start, xmax = end, ymin = as.numeric(Scaffold) - 0.1, ymax = as.numeric(Scaffold) + 0.1),
            fill = "gray", inherit.aes = FALSE) +
  geom_rect(aes(fill = linked), data = rect_data %>% filter(linked == TRUE)) +
  scale_fill_manual(values = c("TRUE" = "green")) +
  facet_wrap(~ Scaffold, scales = "fixed", ncol = 1) +
  theme_minimal() +
  geom_vline(data = snps_157c, aes(xintercept = Position, color = SNP), linetype = "solid", color = "red") +
  geom_text_repel(data = snps_157c, aes(x = Position, y = as.numeric(Scaffold) + 0.2, label = SNP),
                  inherit.aes = FALSE, angle = 45, size = 2,
                  nudge_y = 0.1,   # Adjust this value as needed
                  direction = "y") +
  theme(axis.title.y = element_blank(), axis.text.y = element_blank(), axis.ticks.y = element_blank(), panel.spacing = unit(0.1, "lines"),
        panel.grid.major = element_blank(), panel.grid.minor = element_blank(),
        strip.text = element_text(size = 12, face = "bold", hjust = 0.5)) +
  scale_x_continuous(labels = label_mb, breaks = scales::pretty_breaks(n = 6)) +
  labs(x = "Position", title = "Continuous Stretches of Linked SNPs by Scaffold - Cluster 6 AUT", fill = "Linked") +
  guides(fill = "none")

## Warning: ggrepel: Repulsion works correctly only for rotation angles multiple
## of 90 degrees

# Save Venn diagram to PDF
output_path <- here("output", "ldna", "figures", "cluster_6_aut_scaffolds_with_small_windows.pdf")
ggsave(output_path, height = 5, width = 8, units = "in")

## Warning: ggrepel: Repulsion works correctly only for rotation angles multiple
## of 90 degrees

Calculate size

# Calculate the length of each stretch
rect_data <- rect_data %>%
  mutate(length = end - start + 1)

# Calculate average sizes for TRUE and FALSE stretches
average_sizes <- rect_data %>%
  group_by(linked) %>%
  summarize(average_size = mean(length))

# Display the average sizes
print(average_sizes)

## # A tibble: 2 x 2
##   linked average_size
##   <lgl>         <dbl>
## 1 FALSE       132584.
## 2 TRUE          1015.

We can also check what genes are in these scaffolds.

Import the data

snps_genes_chr <- readRDS(here("output", "ldna", "snps_genes_chr.rds"))

The expression data

gene_expression <- read_delim(here("data", "files","MANvsAUTO_sig_mRNAs.csv"), delim = ",", col_names = TRUE, show_col_types = FALSE) |>
  dplyr::select(
    gene,log2FoldChange
  ) |>
  dplyr::rename(
    Gene_ID = gene
  )
head(gene_expression)

## # A tibble: 6 x 2
##   Gene_ID      log2FoldChange
##   <chr>                 <dbl>
## 1 LOC115262812         -10.5 
## 2 LOC109401291          -9.19
## 3 LOC109397830           8.73
## 4 LOC115264022           8.56
## 5 LOC115260314           8.51
## 6 LOC115258723           8.39

For example, what genes are in the cluster 14, so we can check what genes are in these scaffolds or more specifically what SNPs are in the genes

First, what genes are in these scaffolds?

cluster_14_genes <- snps_genes_chr[snps_genes_chr$Scaffold %in% cluster_14_all$Scaffold, ]

# How many genes in the scaffolds
length(unique(cluster_14_genes$Gene_ID))

## [1] 321

Now lets check what genes have the linked SNPs

cluster_14_snps2 <- snps_genes_chr[snps_genes_chr$SNP %in% aut_ch2$`3215_0.78`, ]

# How many genes with SNPs from the ld block
length(unique(cluster_14_snps2$Gene_ID))

## [1] 109

Save as Excel file

# Save the data frame to an Excel file
write_xlsx(cluster_14_snps2, here("output", "ldna", "cluster_14_snps2.xlsx"))

We can count how many linked SNPs per gene

# Count the number of SNPs for each Gene_ID
snp_count_per_gene <- cluster_14_snps2 %>%
  group_by(Gene_ID) %>%
  summarise(SNP_count = n())

# View the first few rows of the result
head(snp_count_per_gene)

## # A tibble: 6 x 2
##   Gene_ID      SNP_count
##   <chr>            <int>
## 1 LOC109397326         1
## 2 LOC109397337         1
## 3 LOC109397339         1
## 4 LOC109397340         1
## 5 LOC109397344         2
## 6 LOC109397369         4

Save as Excel file

# Save the data frame to an Excel file
write_xlsx(snp_count_per_gene, here("output", "ldna", "snp_count_per_gene.xlsx"))

Now we can check how many DE genes are among the 109 genes that have SNPs on the cluster 14

cluster_14_snps3 <- cluster_14_snps2[cluster_14_snps2$Gene_ID %in% gene_expression$Gene_ID, ]

# How many genes in the scaffolds
length(unique(cluster_14_snps3$Gene_ID))

## [1] 3

unique(cluster_14_snps3$Gene_ID)

## [1] "LOC109415738" "LOC109415743" "LOC109414739"

Get the 17 SNPs position

# Get the 17 SNPs
genes_17_snps <- snps_genes_chr |>
  dplyr::filter(SNP %in% snps_157b$SNP)

genes_17_snps <- snps_genes_chr[snps_genes_chr$SNP %in% snps_157b$SNP, ]

head(genes_17_snps)

## # A tibble: 6 x 8
##   SNP          Chromosome Position_chr Scaffold Position Gene_ID    Start    End
##   <chr>        <chr>             <dbl> <chr>       <dbl> <chr>      <dbl>  <dbl>
## 1 AX-579474142 2             368006161 2.22      6075268 LOC10941~ 6.07e6 6.08e6
## 2 AX-579474650 2             368053323 2.22      6122430 LOC10941~ 6.12e6 6.19e6
## 3 AX-579509845 2             375072931 2.22     13142038 LOC10939~ 1.25e7 1.31e7
## 4 AX-579556477 2             390614565 2.36      1062758 LOC10939~ 9.66e5 1.06e6
## 5 AX-579580051 2             395422791 2.36      5870984 LOC10940~ 5.87e6 5.90e6
## 6 AX-579584369 2             396355776 2.36      6803969 LOC10941~ 6.71e6 6.82e6

Save as Excel file

# Save the data frame to an Excel file
write_xlsx(genes_17_snps, here("output", "ldna", "cluster_14_17_snps.xlsx"))

Get the SNPs for which we do not have genes

genes_17_snps2 <- snps_157b |>
  dplyr::filter(!(SNP %in% genes_17_snps$SNP))
head(genes_17_snps2)

## # A tibble: 6 x 7
##   Scaffold SNP             Cm Position Allele1 Allele2 linked
##   <chr>    <chr>        <int>    <dbl> <chr>   <chr>   <lgl> 
## 1 2.36     AX-579560686     0  2139679 C       T       FALSE 
## 2 2.36     AX-579564292     0  2894537 A       G       FALSE 
## 3 2.36     AX-579565469     0  3152089 A       T       FALSE 
## 4 2.38     AX-579596233     0  2030415 A       G       FALSE 
## 5 2.38     AX-579602153     0  3099174 G       A       FALSE 
## 6 2.38     AX-579604213     0  3599115 T       C       FALSE

Save it (17 genes)

write.table(
  snps_157b,
  file      = here(
    "output", "ldna", "snps_157b.txt"
  ),
  sep       = "\t",
  row.names = FALSE,
  col.names = FALSE,
  quote     = FALSE
)

8. Cluster gene intersection with differentially expressed genes

This section identifies genes within the two major LD clusters (cluster 14 on chromosome 2 and cluster 6 on chromosome 1) and checks whether any overlap with differentially expressed genes from the NON-AUTO vs AUTO comparison.

The gene coordinate data (snps_genes_chr.rds) and expression data (snps_expression.rds) were generated in File S5.

8.1 Cluster 14 genes

snps_genes_chr <-
  readRDS(
    file = here(
      "output", "ldna", "snps_genes_chr.rds"
      )
    )
head(snps_genes_chr)

## # A tibble: 6 x 8
##   SNP          Chromosome Position_chr Scaffold Position Gene_ID    Start    End
##   <chr>        <chr>             <dbl> <chr>       <dbl> <chr>      <dbl>  <dbl>
## 1 AX-581444870 1                 97856 1.1         97856 LOC10939~  64508 102530
## 2 AX-583033342 1                315059 1.1        315059 LOC10943~ 310594 316608
## 3 AX-583035163 1                315386 1.1        315386 LOC10943~ 310594 316608
## 4 AX-583033356 1                315674 1.1        315674 LOC10943~ 310594 316608
## 5 AX-583035257 1                442875 1.10        91677 LOC10940~  66918 192829
## 6 AX-583035268 1                462944 1.10       111746 LOC10940~  66918 192829

snps_expression <-
  readRDS(
    here(
      "output", "ldna", "snps_expression.rds"
      )
    )
head(snps_expression)

## # A tibble: 6 x 9
##   SNP          Chromosome Position_chr Scaffold Position Gene_ID    Start    End
##   <chr>        <chr>             <dbl> <chr>       <dbl> <chr>      <dbl>  <dbl>
## 1 AX-583050970 1               3777633 1.10      3426435 LOC10942~ 3.42e6 3.43e6
## 2 AX-583052853 1               3777864 1.10      3426666 LOC10942~ 3.42e6 3.43e6
## 3 AX-583051011 1               3779183 1.10      3427985 LOC10942~ 3.42e6 3.43e6
## 4 AX-583052887 1               3793314 1.10      3442116 LOC10942~ 3.44e6 3.47e6
## 5 AX-583051025 1               3793653 1.10      3442455 LOC10942~ 3.44e6 3.47e6
## 6 AX-583052920 1               3794185 1.10      3442987 LOC10942~ 3.44e6 3.47e6
## # i 1 more variable: log2FoldChange <dbl>

cluster_14_SNPs <-
  cluster_14 |>
  select(
    SNP
  )

head(cluster_14_SNPs)

## # A tibble: 6 x 1
##   SNP         
##   <chr>       
## 1 AX-579450486
## 2 AX-579456609
## 3 AX-579459157
## 4 AX-579459504
## 5 AX-579459790
## 6 AX-579461404

8.1.1 Genes from coding regions

genes_cluster_14 <- inner_join(cluster_14_SNPs, snps_genes_chr, by = "SNP", suffix = c("", ""))

head(genes_cluster_14)

## # A tibble: 6 x 8
##   SNP          Chromosome Position_chr Scaffold Position Gene_ID    Start    End
##   <chr>        <chr>             <dbl> <chr>       <dbl> <chr>      <dbl>  <dbl>
## 1 AX-579450486 2             363469720 2.22      1538827 LOC10941~ 1.54e6 1.55e6
## 2 AX-579459504 2             365315778 2.22      3384885 LOC11525~ 3.37e6 4.60e6
## 3 AX-579459790 2             365379266 2.22      3448373 LOC11525~ 3.37e6 4.60e6
## 4 AX-579459790 2             365379266 2.22      3448373 LOC11526~ 3.45e6 3.45e6
## 5 AX-579461404 2             365421089 2.22      3490196 LOC11525~ 3.37e6 4.60e6
## 6 AX-579461838 2             365507367 2.22      3576474 LOC11525~ 3.37e6 4.60e6

write_xlsx(
  genes_cluster_14,
  here(
    "output", "ldna","genes_cluster_14.xlsx"
    )
  )

8.1.2 Genes with differential expression

DE_genes_cluster_14 <- inner_join(cluster_14_SNPs, snps_expression, by = "SNP", suffix = c("", ""))

head(DE_genes_cluster_14)

## # A tibble: 4 x 9
##   SNP          Chromosome Position_chr Scaffold Position Gene_ID    Start    End
##   <chr>        <chr>             <dbl> <chr>       <dbl> <chr>      <dbl>  <dbl>
## 1 AX-579585547 2             396531676 2.36      6979869 LOC10941~ 6.98e6 7.19e6
## 2 AX-579588768 2             397394228 2.36      7842421 LOC10941~ 7.84e6 7.84e6
## 3 AX-579598791 2             401278130 2.38      2679893 LOC10941~ 2.67e6 2.68e6
## 4 AX-579598805 2             401278614 2.38      2680377 LOC10941~ 2.67e6 2.68e6
## # i 1 more variable: log2FoldChange <dbl>

write_xlsx(
  DE_genes_cluster_14,
  here(
    "output", "ldna","DE_genes_cluster_14.xlsx"
    )
  )

8.2 Cluster 6 genes

cluster_6_SNPs <-
  cluster_6 |>
  select(
    SNP
  )

head(cluster_6_SNPs)

## # A tibble: 6 x 1
##   SNP         
##   <chr>       
## 1 AX-583500511
## 2 AX-583500520
## 3 AX-583503153
## 4 AX-583500379
## 5 AX-583503258
## 6 AX-583504302

8.2.1 Genes from coding regions

genes_cluster_6 <- inner_join(cluster_6_SNPs, snps_genes_chr, by = "SNP", suffix = c("", ""))

head(genes_cluster_6)

## # A tibble: 6 x 8
##   SNP          Chromosome Position_chr Scaffold Position Gene_ID    Start    End
##   <chr>        <chr>             <dbl> <chr>       <dbl> <chr>      <dbl>  <dbl>
## 1 AX-583503153 1             138373561 1.152      977944 LOC11526~ 9.77e5 9.79e5
## 2 AX-583500379 1             138374084 1.152      978467 LOC11526~ 9.77e5 9.79e5
## 3 AX-583503258 1             138383242 1.152      987625 LOC11525~ 9.79e5 9.89e5
## 4 AX-583503279 1             138887257 1.152     1491640 LOC10941~ 1.43e6 1.49e6
## 5 AX-583503440 1             138930796 1.152     1535179 LOC10941~ 1.51e6 1.54e6
## 6 AX-583503906 1             138960575 1.152     1564958 LOC10941~ 1.56e6 1.57e6

write_xlsx(
  genes_cluster_6,
  here(
    "output", "ldna","genes_cluster_6.xlsx"
    )
  )

8.2.2 Genes with differential expression

DE_genes_cluster_6 <- inner_join(cluster_6_SNPs, snps_expression, by = "SNP", suffix = c("", ""))

head(DE_genes_cluster_6)

## # A tibble: 0 x 9
## # i 9 variables: SNP <chr>, Chromosome <chr>, Position_chr <dbl>,
## #   Scaffold <chr>, Position <dbl>, Gene_ID <chr>, Start <dbl>, End <dbl>,
## #   log2FoldChange <dbl>

write_xlsx(
  DE_genes_cluster_6,
  here(
    "output", "ldna","DE_genes_cluster_6.xlsx"
    )
  )