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.

1. Load libraries

library(tidyverse)
library(here)

2. Variant annotation with SnpEff

Functional annotation was performed with SnpEff using a custom AalbF3 database built from the AalbF3 GFF annotation file (data/files/genes.gff). The publicly available SnpEff database for Aedes albopictus targets AalbF1 and is not compatible with the genome assembly used here.

head -n 2 data/files/genes.gff
## chr3.9   Gnomon  gene    10376   142706  .   -   .   ID=gene-LOC109400916;Dbxref=GeneID:109400916;Name=LOC109400916;gbkey=Gene;gene=LOC109400916;gene_biotype=protein_coding;partial=true;start_range=.,10376
## chr3.9   Gnomon  mRNA    10376   142706  .   -   .   ID=rna-XM_029851713.1;Parent=gene-LOC109400916;Dbxref=GeneID:109400916,Genbank:XM_029851713.1;Name=XM_029851713.1;gbkey=mRNA;gene=LOC109400916;model_evidence=Supporting evidence includes similarity to: 1 Protein%2C and 97%25 coverage of the annotated genomic feature by RNAseq alignments%2C including 57 samples with support for all annotated introns;partial=true;product=UPF0565 protein C2orf69 homolog;start_range=.,10376;transcript_id=XM_029851713.1

2. Build snpEff database and annotate

A custom snpEff database was built from the AalbF3 GTF annotation and reference genome. The GTF uses scaffold names matching the FASTA (e.g., 1.1, 3.9).

DBDIR=output/snpeff/database
mkdir -p $DBDIR/data/albo_v3

# GTF annotation (scaffold names match FASTA)
zcat data/genome/AalbF3_annotation.gtf.gz > $DBDIR/data/albo_v3/genes.gtf
zcat data/genome/albo.fasta.gz > $DBDIR/data/albo_v3/sequences.fa
cp data/genome/AalbF3_protein.fasta $DBDIR/data/albo_v3/protein.fa

# Use container's default config + add custom genome
SNPEFF_CONFIG=/workspace/.pixi/envs/default/share/snpeff-5.4.0c-0/snpEff.config
cp $SNPEFF_CONFIG $DBDIR/snpEff.config
echo "albo_v3.genome : Aedes_albopictus_AalbF3" >> $DBDIR/snpEff.config
sed -i "s|^data.dir.*|data.dir = $DBDIR/data/|" $DBDIR/snpEff.config

# Build database
cd $DBDIR && snpEff build -gtf22 -v -noCheckProtein -noCheckCds albo_v3 -config $DBDIR/snpEff.config

# Annotate all SNPs
cd $DBDIR && snpEff ann albo_v3 -config $DBDIR/snpEff.config /project/output/snpeff/albo.vcf > /project/output/snpeff/albo_ann.vcf
mv $DBDIR/snpEff_* /project/output/snpeff/ 2>/dev/null || true

echo "Annotated VCF lines: $(grep -v '^#' /project/output/snpeff/albo_ann.vcf | wc -l)"
## 00:00:00 SnpEff version SnpEff 5.4c (build 2026-02-23 07:25), by Pablo Cingolani
## 00:00:00 Command: 'build'
## 00:00:00 Building database for 'albo_v3'
## 00:00:00 Reading configuration file 'output/snpeff/database/snpEff.config'. Genome: 'albo_v3'
## 00:00:00 Looking for config file: '/project/output/snpeff/database/output/snpeff/database/snpEff.config'
## java.lang.RuntimeException: Cannot find config file 'output/snpeff/database/snpEff.config'
## 
##  at org.snpeff.snpEffect.Config.findConfigFile(Config.java:281)
##  at org.snpeff.snpEffect.Config.init(Config.java:599)
##  at org.snpeff.snpEffect.Config.<init>(Config.java:130)
##  at org.snpeff.SnpEff.loadConfig(SnpEff.java:451)
##  at org.snpeff.snpEffect.commandLine.SnpEffCmdBuild.run(SnpEffCmdBuild.java:409)
##  at org.snpeff.SnpEff.run(SnpEff.java:1175)
##  at org.snpeff.SnpEff.main(SnpEff.java:164)
## 00:00:00 Done.
## bash: line 19: cd: output/snpeff/database: No such file or directory
## Annotated VCF lines: 129381

3. Identify genes near selection-scan SNPs

Four SNPs from the selection scans fall within the coding regions of differentially expressed genes. This section locates all genes within proximity of the full set of selection-scan SNPs.

3.1 Extract annotated SNP records

grep -f output/snpeff/SNPs_158.txt output/snpeff/albo_ann.vcf > output/snpeff/genes_158_SNPs.txt;
echo "Lines: $(wc -l < output/snpeff/genes_158_SNPs.txt)"
## Lines: 161

Reformat the annotated VCF into a tab-delimited table.

sed -e 's/|/\t/g' -e 's/,/\t/g' -e 's/;/\t/g' -e 's/\t\+/\t/g' output/snpeff/genes_158_SNPs.txt | awk -F"\t" '{
    for(i = 1; i <= NF; ++i) {
        if ($i == "GT") {
            break
        } else {
            if ($i !~ /\//) {
                printf "%s\t", $i
            }
        }
    }
    printf "\n"
}' | awk -F '\t' '{print $1, $2, $3, $10, $11, $12, $13, $17, $18, $19, $20}' > output/snpeff/snps_autogenous.txt;
echo "Lines: $(wc -l < output/snpeff/snps_autogenous.txt)"
## Lines: 161
snps_autogenous <- read_delim(here("output", "snpeff", "snps_autogenous.txt"), delim = " ", col_names = FALSE, show_col_types = FALSE)
head(snps_autogenous)
## # A tibble: 6 x 11
##      X1      X2 X3           X4        X5    X6    X7    X8    X9    X10   X11  
##   <dbl>   <dbl> <chr>        <chr>     <chr> <chr> <chr> <chr> <chr> <chr> <chr>
## 1  1.1  4991044 AX-583054970 synonymo~ LOW   exon~ GENE~ c.97~ p.Gl~ G     upst~
## 2  1.10  311276 AX-583095890 synonymo~ LOW   exon~ GENE~ c.31~ p.Gl~ T     syno~
## 3  1.14 7256914 AX-583324654 intergen~ MODI~ exon~ GENE~ <NA>  <NA>  <NA>  <NA> 
## 4  1.14  118038 AX-583355868 intron_v~ MODI~ exon~ GENE~ c.-1~ A     non_~ MODI~
## 5  1.15 4673825 AX-583423493 intron_v~ MODI~ exon~ GENE~ c.32~ C     non_~ MODI~
## 6  1.15 4968460 AX-583426050 synonymo~ LOW   exon~ GENE~ c.67~ p.Cy~ A     syno~

Retain only non-coding and splice-site variants.

snps_autogenous <- snps_autogenous |>
  filter(!X4 %in% c("synonymous_variant", "intron_variant", "missense_variant", "splice_region_variant&intron_variant"))
head(snps_autogenous)
## # A tibble: 6 x 11
##      X1       X2 X3           X4       X5    X6    X7    X8    X9    X10   X11  
##   <dbl>    <dbl> <chr>        <chr>    <chr> <chr> <chr> <chr> <chr> <chr> <chr>
## 1  1.14  7256914 AX-583324654 interge~ MODI~ exon~ GENE~ <NA>  <NA>  <NA>  <NA> 
## 2  1.15  3966380 AX-583518586 downstr~ MODI~ exon~ GENE~ n.*3~ 3600  T     intr~
## 3  1.15  5078954 AX-583521326 3_prime~ MODI~ exon~ GENE~ c.*7~ 73    C     down~
## 4  1.15  6216642 AX-583531703 5_prime~ LOW   exon~ GENE~ c.-5~ A     5_pr~ MODI~
## 5  1.7   9233887 AX-583905588 5_prime~ MODI~ exon~ GENE~ c.-4~ 12963 C     5_pr~
## 6  1.7  13556856 AX-583924978 5_prime~ MODI~ exon~ GENE~ c.-2~ 227   C     non_~

Some transcripts lack a LOC identifier in the SnpEff output; these can be resolved by querying the GFF file directly.

grep "exon-XM_029870196.1-1" data/files/genes.gff
## chr2.17  Gnomon  exon    3870597 3870840 .   -   .   ID=exon-XM_029870196.1-1;Parent=rna-XM_029870196.1;Dbxref=GeneID:109411464,Genbank:XM_029870196.1;gbkey=mRNA;gene=LOC109411464;product=rho GTPase-activating protein 68F%2C transcript variant X1;transcript_id=XM_029870196.1

3.2 Proximity analysis with bedtools

Gene coordinates are extracted from the GFF file and a 10 kb window search is used to identify genes proximal to each selection-scan SNP.

awk 'BEGIN {OFS="\t"} $3=="gene" {print $1, $4-1, $5, $9}' data/files/genes.gff > output/snpeff/genes.bed
awk 'BEGIN {OFS="\t"} {print $2, $3, $4, $1}' output/snpeff/snps_functional.bed > output/snpeff/snps_functional_rearranged.bed;
sort -k1,1 -k2,2n output/snpeff/snps_functional_rearranged.bed > output/snpeff/snps_functional_sorted.bed;
head output/snpeff/snps_functional_sorted.bed
## 1.10 91677   91678   AX-583035257
## 1.10 958271  958272  AX-583035671
## 1.10 976678  976679  AX-583037587
## 1.10 1143681 1143682 AX-583039330
## 1.10 1462572 1462573 AX-583040214
## 1.10 1649719 1649720 AX-583043295
## 1.10 1890345 1890346 AX-583044718
## 1.10 2585730 2585731 AX-583046569
## 1.10 3198232 3198233 AX-583051721
## 1.10 4991044 4991045 AX-583054970
sort -k1,1 -k2,2n output/snpeff/genes.bed > output/snpeff/genes_sorted.bed;
awk 'BEGIN {OFS="\t"} {gsub(/^chr/, "", $1); print $0}' output/snpeff/genes_sorted.bed > output/snpeff/genes_sorted_no_chr.bed;
head output/snpeff/genes_sorted_no_chr.bed
## 1.1  63834   63906   ID=gene-Trnaa-cgc-11;Dbxref=GeneID:109622996;Name=Trnaa-cgc;gbkey=Gene;gene=Trnaa-cgc;gene_biotype=tRNA
## 1.1  64507   102530  ID=gene-LOC109398996;Dbxref=GeneID:109398996;Name=LOC109398996;gbkey=Gene;gene=LOC109398996;gene_biotype=protein_coding
## 1.1  251542  251614  ID=gene-Trnaa-cgc-3;Dbxref=GeneID:109622998;Name=Trnaa-cgc;gbkey=Gene;gene=Trnaa-cgc;gene_biotype=tRNA
## 1.1  261057  261129  ID=gene-Trnap-cgg-7;Dbxref=GeneID:109399016;Name=Trnap-cgg;gbkey=Gene;gene=Trnap-cgg;gene_biotype=tRNA
## 1.1  262948  263021  ID=gene-Trnar-ucg-2;Dbxref=GeneID:115263563;Name=Trnar-ucg;gbkey=Gene;gene=Trnar-ucg;gene_biotype=tRNA
## 1.1  300964  303187  ID=gene-LOC109431818;Dbxref=GeneID:109431818;Name=LOC109431818;gbkey=Gene;gene=LOC109431818;gene_biotype=protein_coding
## 1.1  310593  316608  ID=gene-LOC109431831;Dbxref=GeneID:109431831;Name=LOC109431831;gbkey=Gene;gene=LOC109431831;gene_biotype=protein_coding
## 1.1  346346  346851  ID=gene-LOC115263560;Dbxref=GeneID:115263560;Name=LOC115263560;gbkey=Gene;gene=LOC115263560;gene_biotype=lncRNA
## 1.1  347368  347774  ID=gene-LOC115263561;Dbxref=GeneID:115263561;Name=LOC115263561;gbkey=Gene;gene=LOC115263561;gene_biotype=lncRNA
## 1.10 66917   192829  ID=gene-LOC109408922;Dbxref=GeneID:109408922;Name=LOC109408922;gbkey=Gene;gene=LOC109408922;gene_biotype=protein_coding
bedtools closest -a output/snpeff/snps_functional_sorted.bed -b output/snpeff/genes_sorted_no_chr.bed -D "ref" > output/snpeff/closest_genes.bed;
head output/snpeff/closest_genes.bed
## 1.10 91677   91678   AX-583035257    1.10    66917   192829  ID=gene-LOC109408922;Dbxref=GeneID:109408922;Name=LOC109408922;gbkey=Gene;gene=LOC109408922;gene_biotype=protein_coding 0
## 1.10 958271  958272  AX-583035671    1.10    957973  960080  ID=gene-LOC109405110;Dbxref=GeneID:109405110;Name=LOC109405110;gbkey=Gene;gene=LOC109405110;gene_biotype=protein_coding 0
## 1.10 976678  976679  AX-583037587    1.10    975821  994846  ID=gene-LOC115256850;Dbxref=GeneID:115256850;Name=LOC115256850;gbkey=Gene;gene=LOC115256850;gene_biotype=protein_coding 0
## 1.10 1143681 1143682 AX-583039330    1.10    1028225 1151387 ID=gene-LOC109415242;Dbxref=GeneID:109415242;Name=LOC109415242;gbkey=Gene;gene=LOC109415242;gene_biotype=protein_coding 0
## 1.10 1462572 1462573 AX-583040214    1.10    1328360 1489570 ID=gene-LOC109428360;Dbxref=GeneID:109428360;Name=LOC109428360;gbkey=Gene;gene=LOC109428360;gene_biotype=protein_coding 0
## 1.10 1649719 1649720 AX-583043295    1.10    1649234 1754966 ID=gene-LOC109428368;Dbxref=GeneID:109428368;Name=LOC109428368;gbkey=Gene;gene=LOC109428368;gene_biotype=protein_coding 0
## 1.10 1890345 1890346 AX-583044718    1.10    1795444 1893443 ID=gene-LOC109415254;Dbxref=GeneID:109415254;Name=LOC109415254;gbkey=Gene;gene=LOC109415254;gene_biotype=protein_coding 0
## 1.10 2585730 2585731 AX-583046569    1.10    2574856 2587370 ID=gene-LOC109428399;Dbxref=GeneID:109428399;Name=LOC109428399;gbkey=Gene;gene=LOC109428399;gene_biotype=protein_coding 0
## 1.10 3198232 3198233 AX-583051721    1.10    3125047 3324406 ID=gene-LOC109415184;Dbxref=GeneID:109415184;Name=LOC109415184;gbkey=Gene;gene=LOC109415184;gene_biotype=protein_coding 0
## 1.10 4991044 4991045 AX-583054970    1.10    4906873 5020951 ID=gene-LOC109428426;Dbxref=GeneID:109428426;Name=LOC109428426;gbkey=Gene;gene=LOC109428426;gene_biotype=protein_coding 0

Each SNP region is extended by 10 kb on both sides and intersected with the gene annotation to retrieve proximal genes.

bedtools slop -i output/snpeff/snps_functional_sorted.bed -g data/genome/scaffold_sizes.txt -b 10000 > output/snpeff/snps_10k.bed;
head output/snpeff/snps_10k.bed
## 1.10 81677   101678  AX-583035257
## 1.10 948271  968272  AX-583035671
## 1.10 966678  986679  AX-583037587
## 1.10 1133681 1153682 AX-583039330
## 1.10 1452572 1472573 AX-583040214
## 1.10 1639719 1659720 AX-583043295
## 1.10 1880345 1900346 AX-583044718
## 1.10 2575730 2595731 AX-583046569
## 1.10 3188232 3208233 AX-583051721
## 1.10 4981044 5001045 AX-583054970
bedtools closest -a output/snpeff/snps_10k.bed -b output/snpeff/genes_sorted_no_chr.bed -D "ref" -d > output/snpeff/closest_genes_within_10kb.bed;
head output/snpeff/closest_genes_within_10kb.bed
## 1.10 81677   101678  AX-583035257    1.10    66917   192829  ID=gene-LOC109408922;Dbxref=GeneID:109408922;Name=LOC109408922;gbkey=Gene;gene=LOC109408922;gene_biotype=protein_coding 0
## 1.10 948271  968272  AX-583035671    1.10    949791  950655  ID=gene-LOC115256807;Dbxref=GeneID:115256807;Name=LOC115256807;gbkey=Gene;gene=LOC115256807;gene_biotype=protein_coding 0
## 1.10 948271  968272  AX-583035671    1.10    957973  960080  ID=gene-LOC109405110;Dbxref=GeneID:109405110;Name=LOC109405110;gbkey=Gene;gene=LOC109405110;gene_biotype=protein_coding 0
## 1.10 966678  986679  AX-583037587    1.10    975821  994846  ID=gene-LOC115256850;Dbxref=GeneID:115256850;Name=LOC115256850;gbkey=Gene;gene=LOC115256850;gene_biotype=protein_coding 0
## 1.10 1133681 1153682 AX-583039330    1.10    1028225 1151387 ID=gene-LOC109415242;Dbxref=GeneID:109415242;Name=LOC109415242;gbkey=Gene;gene=LOC109415242;gene_biotype=protein_coding 0
## 1.10 1452572 1472573 AX-583040214    1.10    1328360 1489570 ID=gene-LOC109428360;Dbxref=GeneID:109428360;Name=LOC109428360;gbkey=Gene;gene=LOC109428360;gene_biotype=protein_coding 0
## 1.10 1639719 1659720 AX-583043295    1.10    1649234 1754966 ID=gene-LOC109428368;Dbxref=GeneID:109428368;Name=LOC109428368;gbkey=Gene;gene=LOC109428368;gene_biotype=protein_coding 0
## 1.10 1880345 1900346 AX-583044718    1.10    1795444 1893443 ID=gene-LOC109415254;Dbxref=GeneID:109415254;Name=LOC109415254;gbkey=Gene;gene=LOC109415254;gene_biotype=protein_coding 0
## 1.10 2575730 2595731 AX-583046569    1.10    2574856 2587370 ID=gene-LOC109428399;Dbxref=GeneID:109428399;Name=LOC109428399;gbkey=Gene;gene=LOC109428399;gene_biotype=protein_coding 0
## 1.10 2575730 2595731 AX-583046569    1.10    2594311 2594976 ID=gene-LOC109415197;Dbxref=GeneID:109415197;Name=LOC109415197;gbkey=Gene;gene=LOC109415197;gene_biotype=protein_coding 0
awk 'match($4, /AX-[0-9]+/) {snp=substr($4, RSTART, RLENGTH)} match($8, /LOC[0-9]+/) {gene=substr($8, RSTART, RLENGTH)} {if(snp && gene) print snp, gene; snp=""; gene=""}' output/snpeff/closest_genes_within_10kb.bed > output/snpeff/genes_10kb_snps.txt;
head output/snpeff/genes_10kb_snps.txt
## AX-583035257 LOC109408922
## AX-583035671 LOC115256807
## AX-583035671 LOC109405110
## AX-583037587 LOC115256850
## AX-583039330 LOC109415242
## AX-583040214 LOC109428360
## AX-583043295 LOC109428368
## AX-583044718 LOC109415254
## AX-583046569 LOC109428399
## AX-583046569 LOC109415197

3.3 Intersect with differentially expressed genes

closest_genes <- read_delim(
  here("output", "snpeff", "genes_10kb_snps.txt"),
  delim     = " ",
  col_names = c("SNP", "Gene_ID"),
  show_col_types = FALSE
)
head(closest_genes)
## # A tibble: 6 x 2
##   SNP          Gene_ID     
##   <chr>        <chr>       
## 1 AX-583035257 LOC109408922
## 2 AX-583035671 LOC115256807
## 3 AX-583035671 LOC109405110
## 4 AX-583037587 LOC115256850
## 5 AX-583039330 LOC109415242
## 6 AX-583040214 LOC109428360
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
gene_snps_exp <- inner_join(gene_expression, closest_genes, by = "Gene_ID")
head(gene_snps_exp)
## # A tibble: 6 x 3
##   Gene_ID      log2FoldChange SNP         
##   <chr>                 <dbl> <chr>       
## 1 LOC109422059           6.58 AX-583709904
## 2 LOC115269882          -6.28 AX-580214745
## 3 LOC109419115           6.10 AX-581434035
## 4 LOC109417645          -5.49 AX-584629321
## 5 LOC115259897          -5.46 AX-584949353
## 6 LOC109421750          -5.28 AX-580385664
unique(gene_snps_exp$SNP)
##   [1] "AX-583709904" "AX-580214745" "AX-581434035" "AX-584629321" "AX-584949353"
##   [6] "AX-580385664" "AX-585072210" "AX-584792883" "AX-585132993" "AX-584255242"
##  [11] "AX-584253349" "AX-582772850" "AX-580932801" "AX-582569592" "AX-584085828"
##  [16] "AX-585167663" "AX-584659072" "AX-584659195" "AX-583143703" "AX-579719337"
##  [21] "AX-579719427" "AX-581432700" "AX-581014751" "AX-583462099" "AX-582486287"
##  [26] "AX-583237406" "AX-583299009" "AX-584697422" "AX-580363853" "AX-581302901"
##  [31] "AX-581303138" "AX-583548107" "AX-582287268" "AX-585047348" "AX-584538667"
##  [36] "AX-580037979" "AX-582458673" "AX-582481614" "AX-582481773" "AX-582481882"
##  [41] "AX-583320377" "AX-581298758" "AX-583431590" "AX-583696963" "AX-584348874"
##  [46] "AX-581798715" "AX-585191554" "AX-579838845" "AX-582580299" "AX-583055828"
##  [51] "AX-584188695" "AX-580546704" "AX-581504020" "AX-581505925" "AX-581506313"
##  [56] "AX-581504582" "AX-581506954" "AX-581225967" "AX-583054970" "AX-579486733"
##  [61] "AX-579485773" "AX-582812598" "AX-582813926" "AX-582740296" "AX-582743046"
##  [66] "AX-580506679" "AX-584275783" "AX-585454571" "AX-581230116" "AX-582276088"
##  [71] "AX-579602820" "AX-580790145" "AX-583972796" "AX-582375521" "AX-582293283"
##  [76] "AX-579551827" "AX-581307031" "AX-580820490" "AX-583918543" "AX-582683159"
##  [81] "AX-580726735" "AX-580706309" "AX-582039669" "AX-580713461" "AX-583865570"
##  [86] "AX-583869891" "AX-584506677" "AX-583483657" "AX-583778551" "AX-583142560"
##  [91] "AX-583683199" "AX-583687374" "AX-584275318" "AX-579528676" "AX-579530323"
##  [96] "AX-581839987" "AX-584644050" "AX-580734190" "AX-583279927" "AX-579587308"
## [101] "AX-579589045" "AX-584653374" "AX-584653471" "AX-585162248" "AX-585162361"
## [106] "AX-579518040" "AX-579519594" "AX-581487305" "AX-580966528" "AX-580878016"
## [111] "AX-583093532" "AX-583093598" "AX-584813246" "AX-584222538"

This confirms the four SNPs identified by direct SnpEff annotation.

3.4 Annotate candidate SNPs

grep "AX-581302901" output/snpeff/albo_ann.vcf | cut -f1-8
## 3.170    12036013    AX-581302901    A   C   .   .   PR;ANN=C|missense_variant|MODERATE|exon-XM_029875736.1-1|GENE_exon-XM_029875736.1-1|transcript|rna-XM_029875736.1|protein_coding|3/6|c.468A>C|p.Leu156Phe|543/3001|468/2880|156/959||,C|non_coding_transcript_variant|MODIFIER|LOC109403353|gene-LOC109403353|transcript|XM_029875736.1|protein_coding||||||||WARNING_TRANSCRIPT_NO_START_CODON
grep "AX-581504582" output/snpeff/albo_ann.vcf | cut -f1-8
## 3.19 1649039 AX-581504582    C   T   .   .   PR;ANN=T|intron_variant|MODIFIER|exon-XM_029870293.1-1|GENE_exon-XM_029870293.1-1|transcript|rna-XM_029870293.1|protein_coding|3/5|c.964-3896C>T||||||,T|non_coding_transcript_variant|MODIFIER|LOC109405833|gene-LOC109405833|transcript|XM_029870293.1|protein_coding||||||||WARNING_TRANSCRIPT_NO_START_CODON
grep "AX-583054970" output/snpeff/albo_ann.vcf | cut -f1-8
## 1.10 4991044 AX-583054970    A   G   .   .   PR;ANN=G|synonymous_variant|LOW|exon-XM_029855844.1-1|GENE_exon-XM_029855844.1-1|transcript|rna-XM_029855844.1|protein_coding|6/8|c.975A>G|p.Glu325Glu|1687/2862|975/2067|325/688||,G|upstream_gene_variant|MODIFIER|exon-XM_029855847.1-1|GENE_exon-XM_029855847.1-1|transcript|rna-XM_029855847.1|protein_coding||c.-4343T>C|||||3988|,G|upstream_gene_variant|MODIFIER|LOC109428424|gene-LOC109428424|transcript|XM_019704177.2|protein_coding||c.-2247A>G|||||2248|WARNING_TRANSCRIPT_NO_START_CODON,G|downstream_gene_variant|MODIFIER|LOC115256836|gene-LOC115256836|transcript|XM_029855847.1|protein_coding||c.*3988A>G|||||3988|WARNING_TRANSCRIPT_NO_START_CODON,G|downstream_gene_variant|MODIFIER|exon-XM_019704177.2-1|GENE_exon-XM_019704177.2-1|transcript|rna-XM_019704177.2|protein_coding||c.*2252T>C|||||2248|,G|non_coding_transcript_variant|MODIFIER|LOC109428426|gene-LOC109428426|transcript|XM_029855844.1|protein_coding||||||||WARNING_TRANSCRIPT_NO_START_CODON
grep "AX-583972796" output/snpeff/albo_ann.vcf | cut -f1-8
## 1.8  315751  AX-583972796    G   A   .   .   PR;ANN=A|intragenic_variant|MODIFIER|LOC109408954|gene-LOC109408954|gene_variant|gene-LOC109408954|||n.315751G>A||||||,A|non_coding_transcript_exon_variant|MODIFIER|exon-XR_003894428.1-1|GENE_exon-XR_003894428.1-1|transcript|rna-XR_003894428.1|pseudogene|2/2|n.1711G>A||||||

3.5 Annotate cluster 14 SNPs on chromosome 2

grep -E "AX-579474142|AX-579474650|AX-579509845|AX-579556477|AX-579560686|AX-579564292|AX-579565469|AX-579580051|AX-579584369|AX-579583040|AX-579584883|AX-579596233|AX-579602153|AX-579603553|AX-579604213|AX-579607140|AX-579618571|AX-579619995|AX-579620627" output/snpeff/albo_ann.vcf | cut -f1-8
## 2.22 6075268 AX-579474142    C   T   .   .   PR;ANN=T|synonymous_variant|LOW|exon-XM_019693167.2-1|GENE_exon-XM_019693167.2-1|transcript|rna-XM_019693167.2|protein_coding|2/4|c.337C>T|p.Leu113Leu|473/2196|337/1800|113/599||,T|non_coding_transcript_variant|MODIFIER|LOC109418947|gene-LOC109418947|transcript|XM_019693167.2|protein_coding||||||||WARNING_TRANSCRIPT_NO_START_CODON
## 2.22 6122430 AX-579474650    G   A   .   .   PR;ANN=A|3_prime_UTR_variant|MODIFIER|exon-XM_029877733.1-1|GENE_exon-XM_029877733.1-1|transcript|rna-XM_029877733.1|protein_coding|5/5|c.*2336C>T|||||2336|,A|upstream_gene_variant|MODIFIER|exon-XR_003898678.1-1|GENE_exon-XR_003898678.1-1|transcript|rna-XR_003898678.1|pseudogene||n.-2807C>T|||||2807|,A|non_coding_transcript_variant|MODIFIER|LOC109418949|gene-LOC109418949|transcript|XM_029877733.1|protein_coding||||||||WARNING_TRANSCRIPT_NO_START_CODON
## 2.22 13142038    AX-579509845    T   A   .   .   PR;ANN=A|3_prime_UTR_variant|MODIFIER|exon-XM_029877630.1-1|GENE_exon-XM_029877630.1-1|transcript|rna-XM_029877630.1|protein_coding|21/21|c.*683T>A|||||683|,A|3_prime_UTR_variant|MODIFIER|exon-XM_029877629.1-1|GENE_exon-XM_029877629.1-1|transcript|rna-XM_029877629.1|protein_coding|20/20|c.*683T>A|||||683|,A|3_prime_UTR_variant|MODIFIER|exon-XM_029877628.1-1|GENE_exon-XM_029877628.1-1|transcript|rna-XM_029877628.1|protein_coding|18/18|c.*683T>A|||||683|,A|3_prime_UTR_variant|MODIFIER|exon-XM_029877621.1-1|GENE_exon-XM_029877621.1-1|transcript|rna-XM_029877621.1|protein_coding|22/22|c.*683T>A|||||683|,A|3_prime_UTR_variant|MODIFIER|exon-XM_029877623.1-1|GENE_exon-XM_029877623.1-1|transcript|rna-XM_029877623.1|protein_coding|21/21|c.*683T>A|||||683|,A|3_prime_UTR_variant|MODIFIER|exon-XM_029877624.1-1|GENE_exon-XM_029877624.1-1|transcript|rna-XM_029877624.1|protein_coding|21/21|c.*683T>A|||||683|,A|3_prime_UTR_variant|MODIFIER|exon-XM_029877625.1-1|GENE_exon-XM_029877625.1-1|transcript|rna-XM_029877625.1|protein_coding|21/21|c.*683T>A|||||683|,A|3_prime_UTR_variant|MODIFIER|exon-XM_029877626.1-1|GENE_exon-XM_029877626.1-1|transcript|rna-XM_029877626.1|protein_coding|21/21|c.*683T>A|||||683|,A|3_prime_UTR_variant|MODIFIER|exon-XM_029877627.1-1|GENE_exon-XM_029877627.1-1|transcript|rna-XM_029877627.1|protein_coding|21/21|c.*683T>A|||||683|,A|3_prime_UTR_variant|MODIFIER|exon-XM_029877636.1-1|GENE_exon-XM_029877636.1-1|transcript|rna-XM_029877636.1|protein_coding|22/22|c.*683T>A|||||683|,A|3_prime_UTR_variant|MODIFIER|exon-XM_029877634.1-1|GENE_exon-XM_029877634.1-1|transcript|rna-XM_029877634.1|protein_coding|20/20|c.*683T>A|||||683|,A|3_prime_UTR_variant|MODIFIER|exon-XM_029877635.1-1|GENE_exon-XM_029877635.1-1|transcript|rna-XM_029877635.1|protein_coding|19/19|c.*683T>A|||||683|,A|3_prime_UTR_variant|MODIFIER|exon-XM_029877622.1-1|GENE_exon-XM_029877622.1-1|transcript|rna-XM_029877622.1|protein_coding|21/21|c.*683T>A|||||683|,A|3_prime_UTR_variant|MODIFIER|exon-XM_029877632.1-1|GENE_exon-XM_029877632.1-1|transcript|rna-XM_029877632.1|protein_coding|20/20|c.*683T>A|||||683|,A|3_prime_UTR_variant|MODIFIER|exon-XM_029877633.1-1|GENE_exon-XM_029877633.1-1|transcript|rna-XM_029877633.1|protein_coding|20/20|c.*683T>A|||||683|,A|3_prime_UTR_variant|MODIFIER|exon-XM_019670866.2-1|GENE_exon-XM_019670866.2-1|transcript|rna-XM_019670866.2|protein_coding|6/6|c.*683T>A|||||683|,A|non_coding_transcript_variant|MODIFIER|LOC109398403|gene-LOC109398403|transcript|XM_019670866.2|protein_coding||||||||WARNING_TRANSCRIPT_NO_START_CODON,A|non_coding_transcript_variant|MODIFIER|LOC109398403|gene-LOC109398403|transcript|XM_029877630.1|protein_coding||||||||WARNING_TRANSCRIPT_NO_START_CODON,A|non_coding_transcript_variant|MODIFIER|LOC109398403|gene-LOC109398403|transcript|XM_029877629.1|protein_coding||||||||WARNING_TRANSCRIPT_NO_START_CODON,A|non_coding_transcript_variant|MODIFIER|LOC109398403|gene-LOC109398403|transcript|XM_029877628.1|protein_coding||||||||WARNING_TRANSCRIPT_NO_START_CODON,A|non_coding_transcript_variant|MODIFIER|LOC109398403|gene-LOC109398403|transcript|XM_029877621.1|protein_coding||||||||WARNING_TRANSCRIPT_NO_START_CODON,A|non_coding_transcript_variant|MODIFIER|LOC109398403|gene-LOC109398403|transcript|XM_029877623.1|protein_coding||||||||WARNING_TRANSCRIPT_NO_START_CODON,A|non_coding_transcript_variant|MODIFIER|LOC109398403|gene-LOC109398403|transcript|XM_029877624.1|protein_coding||||||||WARNING_TRANSCRIPT_NO_START_CODON,A|non_coding_transcript_variant|MODIFIER|LOC109398403|gene-LOC109398403|transcript|XM_029877625.1|protein_coding||||||||WARNING_TRANSCRIPT_NO_START_CODON,A|non_coding_transcript_variant|MODIFIER|LOC109398403|gene-LOC109398403|transcript|XM_029877626.1|protein_coding||||||||WARNING_TRANSCRIPT_NO_START_CODON,A|non_coding_transcript_variant|MODIFIER|LOC109398403|gene-LOC109398403|transcript|XM_029877627.1|protein_coding||||||||WARNING_TRANSCRIPT_NO_START_CODON,A|non_coding_transcript_variant|MODIFIER|LOC109398403|gene-LOC109398403|transcript|XM_029877636.1|protein_coding||||||||WARNING_TRANSCRIPT_NO_START_CODON,A|non_coding_transcript_variant|MODIFIER|LOC109398403|gene-LOC109398403|transcript|XM_029877634.1|protein_coding||||||||WARNING_TRANSCRIPT_NO_START_CODON,A|non_coding_transcript_variant|MODIFIER|LOC109398403|gene-LOC109398403|transcript|XM_029877635.1|protein_coding||||||||WARNING_TRANSCRIPT_NO_START_CODON,A|non_coding_transcript_variant|MODIFIER|LOC109398403|gene-LOC109398403|transcript|XM_029877622.1|protein_coding||||||||WARNING_TRANSCRIPT_NO_START_CODON,A|non_coding_transcript_variant|MODIFIER|LOC109398403|gene-LOC109398403|transcript|XM_029877632.1|protein_coding||||||||WARNING_TRANSCRIPT_NO_START_CODON,A|non_coding_transcript_variant|MODIFIER|LOC109398403|gene-LOC109398403|transcript|XM_029877633.1|protein_coding||||||||WARNING_TRANSCRIPT_NO_START_CODON
## 2.36 1062758 AX-579556477    C   T   .   .   PR;ANN=T|5_prime_UTR_variant|MODIFIER|exon-XM_029869906.1-1|GENE_exon-XM_029869906.1-1|transcript|rna-XM_029869906.1|protein_coding|1/6|c.-693G>A|||||75259|,T|5_prime_UTR_variant|MODIFIER|exon-XM_029869907.1-1|GENE_exon-XM_029869907.1-1|transcript|rna-XM_029869907.1|protein_coding|1/6|c.-690G>A|||||75259|,T|non_coding_transcript_variant|MODIFIER|LOC109397339|gene-LOC109397339|transcript|XM_029869906.1|protein_coding||||||||WARNING_TRANSCRIPT_NO_START_CODON,T|non_coding_transcript_variant|MODIFIER|LOC109397339|gene-LOC109397339|transcript|XM_029869907.1|protein_coding||||||||WARNING_TRANSCRIPT_NO_START_CODON
## 2.36 2139679 AX-579560686    T   C   .   .   PR;ANN=C|intergenic_region|MODIFIER|exon-XM_029869376.1-1-exon-XR_003896591.1-1|GENE_exon-XM_029869376.1-1-GENE_exon-XR_003896591.1-1|intergenic_region|GENE_exon-XM_029869376.1-1-GENE_exon-XR_003896591.1-1|||n.2139679T>C||||||
## 2.36 2894537 AX-579564292    G   A   .   .   PR;ANN=A|intergenic_region|MODIFIER|exon-XR_003896876.1-1-exon-XR_003896852.1-1|GENE_exon-XR_003896876.1-1-GENE_exon-XR_003896852.1-1|intergenic_region|GENE_exon-XR_003896876.1-1-GENE_exon-XR_003896852.1-1|||n.2894537G>A||||||
## 2.36 3152089 AX-579565469    T   A   .   .   PR;ANN=A|intergenic_region|MODIFIER|exon-XR_003896852.1-1-exon-XR_003896853.1-1|GENE_exon-XR_003896852.1-1-GENE_exon-XR_003896853.1-1|intergenic_region|GENE_exon-XR_003896852.1-1-GENE_exon-XR_003896853.1-1|||n.3152089T>A||||||
## 2.36 5870984 AX-579580051    T   C   .   .   PR;ANN=C|synonymous_variant|LOW|exon-XM_029869860.1-1|GENE_exon-XM_029869860.1-1|transcript|rna-XM_029869860.1|protein_coding|6/7|c.1359A>G|p.Leu453Leu|2073/2844|1359/1785|453/594||,C|synonymous_variant|LOW|exon-XM_029869858.1-1|GENE_exon-XM_029869858.1-1|transcript|rna-XM_029869858.1|protein_coding|7/8|c.1413A>G|p.Leu471Leu|2129/2900|1413/1839|471/612||,C|synonymous_variant|LOW|exon-XM_029869859.1-1|GENE_exon-XM_029869859.1-1|transcript|rna-XM_029869859.1|protein_coding|7/8|c.1413A>G|p.Leu471Leu|1527/2298|1413/1839|471/612||,C|non_coding_transcript_variant|MODIFIER|LOC109406424|gene-LOC109406424|transcript|XM_029869858.1|protein_coding||||||||WARNING_TRANSCRIPT_NO_START_CODON,C|non_coding_transcript_variant|MODIFIER|LOC109406424|gene-LOC109406424|transcript|XM_029869860.1|protein_coding||||||||WARNING_TRANSCRIPT_NO_START_CODON,C|non_coding_transcript_variant|MODIFIER|LOC109406424|gene-LOC109406424|transcript|XM_029869859.1|protein_coding||||||||WARNING_TRANSCRIPT_NO_START_CODON
## 2.36 6803969 AX-579584369    A   G   .   .   PR;ANN=G|synonymous_variant|LOW|exon-XM_029869867.1-1|GENE_exon-XM_029869867.1-1|transcript|rna-XM_029869867.1|protein_coding|3/8|c.1263A>G|p.Lys421Lys|3006/5907|1263/3042|421/1013||,G|synonymous_variant|LOW|exon-XM_029869868.1-1|GENE_exon-XM_029869868.1-1|transcript|rna-XM_029869868.1|protein_coding|3/8|c.1263A>G|p.Lys421Lys|3006/5838|1263/2973|421/990||,G|non_coding_transcript_variant|MODIFIER|LOC109417065|gene-LOC109417065|transcript|XM_029869867.1|protein_coding||||||||WARNING_TRANSCRIPT_NO_START_CODON,G|non_coding_transcript_variant|MODIFIER|LOC109417065|gene-LOC109417065|transcript|XM_029869868.1|protein_coding||||||||WARNING_TRANSCRIPT_NO_START_CODON
## 2.36 6838018 AX-579583040    A   T   .   .   PR;ANN=T|3_prime_UTR_variant|MODIFIER|exon-XM_019691182.2-1|GENE_exon-XM_019691182.2-1|transcript|rna-XM_019691182.2|protein_coding|2/2|c.*429T>A|||||429|,T|non_coding_transcript_variant|MODIFIER|LOC109417063|gene-LOC109417063|transcript|XM_019691182.2|protein_coding||||||||WARNING_TRANSCRIPT_NO_START_CODON
## 2.36 6844853 AX-579584883    G   A   .   .   PR;ANN=A|synonymous_variant|LOW|exon-XM_019689662.2-1|GENE_exon-XM_019689662.2-1|transcript|rna-XM_019689662.2|protein_coding|2/2|c.795G>A|p.Leu265Leu|892/1971|795/1578|265/525||,A|upstream_gene_variant|MODIFIER|exon-XM_019691182.2-1|GENE_exon-XM_019691182.2-1|transcript|rna-XM_019691182.2|protein_coding||c.-4218C>T|||||3809|,A|downstream_gene_variant|MODIFIER|LOC109417063|gene-LOC109417063|transcript|XM_019691182.2|protein_coding||c.*3809G>A|||||3809|WARNING_TRANSCRIPT_NO_START_CODON,A|non_coding_transcript_variant|MODIFIER|LOC109415735|gene-LOC109415735|transcript|XM_019689662.2|protein_coding||||||||WARNING_TRANSCRIPT_NO_START_CODON
## 2.38 2030415 AX-579596233    G   A   .   .   PR;ANN=A|intergenic_region|MODIFIER|exon-XM_029869787.1-1-exon-XM_029869785.1-1|GENE_exon-XM_029869787.1-1-GENE_exon-XM_029869785.1-1|intergenic_region|GENE_exon-XM_029869787.1-1-GENE_exon-XM_029869785.1-1|||n.2030415G>A||||||
## 2.38 3099174 AX-579602153    A   G   .   .   PR;ANN=G|intron_variant|MODIFIER|exon-XM_029869783.1-1|GENE_exon-XM_029869783.1-1|transcript|rna-XM_029869783.1|protein_coding|2/8|c.-840-58725A>G||||||
## 2.38 3599115 AX-579604213    C   T   .   .   PR;ANN=T|3_prime_UTR_variant|MODIFIER|exon-XM_029869783.1-1|GENE_exon-XM_029869783.1-1|transcript|rna-XM_029869783.1|protein_coding|9/9|c.*179C>T|||||179|
## 2.38 3809839 AX-579603553    T   C   .   .   PR;ANN=C|intergenic_region|MODIFIER|Trnah-gug-exon-XM_029869778.1-1|gene-Trnah-gug-28-GENE_exon-XM_029869778.1-1|intergenic_region|gene-Trnah-gug-28-GENE_exon-XM_029869778.1-1|||n.3809839T>C||||||
## 2.38 4184034 AX-579607140    A   T   .   .   PR;ANN=T|intron_variant|MODIFIER|exon-XM_029871638.1-1|GENE_exon-XM_029871638.1-1|transcript|rna-XM_029871638.1|protein_coding|1/5|c.50-1804A>T||||||,T|non_coding_transcript_variant|MODIFIER|LOC109406563|gene-LOC109406563|transcript|XM_029871638.1|protein_coding||||||||WARNING_TRANSCRIPT_NO_START_CODON
## 2.40 1592853 AX-579618571    C   T   .   .   PR;ANN=T|synonymous_variant|LOW|exon-XM_029869762.1-1|GENE_exon-XM_029869762.1-1|transcript|rna-XM_029869762.1|protein_coding|12/13|c.5973C>T|p.Thr1991Thr|6944/7955|5973/6276|1991/2091||,T|synonymous_variant|LOW|exon-XM_029869761.1-1|GENE_exon-XM_029869761.1-1|transcript|rna-XM_029869761.1|protein_coding|12/13|c.5973C>T|p.Thr1991Thr|6383/7394|5973/6276|1991/2091||,T|synonymous_variant|LOW|exon-XM_029869764.1-1|GENE_exon-XM_029869764.1-1|transcript|rna-XM_029869764.1|protein_coding|11/12|c.5970C>T|p.Thr1990Thr|6380/7391|5970/6273|1990/2090||,T|synonymous_variant|LOW|exon-XM_029869763.1-1|GENE_exon-XM_029869763.1-1|transcript|rna-XM_029869763.1|protein_coding|12/13|c.5973C>T|p.Thr1991Thr|6352/7363|5973/6276|1991/2091||,T|intron_variant|MODIFIER|exon-XM_029869727.1-1|GENE_exon-XM_029869727.1-1|transcript|rna-XM_029869727.1|protein_coding|5/7|c.1936-1166870C>T||||||WARNING_TRANSCRIPT_MULTIPLE_STOP_CODONS,T|intron_variant|MODIFIER|exon-XM_029869728.1-1|GENE_exon-XM_029869728.1-1|transcript|rna-XM_029869728.1|protein_coding|5/7|c.1921-1166870C>T||||||WARNING_TRANSCRIPT_MULTIPLE_STOP_CODONS,T|intron_variant|MODIFIER|exon-XM_029869729.1-1|GENE_exon-XM_029869729.1-1|transcript|rna-XM_029869729.1|protein_coding|5/7|c.1936-1166870C>T||||||WARNING_TRANSCRIPT_MULTIPLE_STOP_CODONS,T|intron_variant|MODIFIER|exon-XM_029869730.1-1|GENE_exon-XM_029869730.1-1|transcript|rna-XM_029869730.1|protein_coding|4/6|c.1795-1166872C>T||||||WARNING_TRANSCRIPT_MULTIPLE_STOP_CODONS,T|non_coding_transcript_variant|MODIFIER|LOC109410517|gene-LOC109410517|transcript|XM_029869761.1|protein_coding||||||||WARNING_TRANSCRIPT_NO_START_CODON,T|non_coding_transcript_variant|MODIFIER|LOC109410517|gene-LOC109410517|transcript|XM_029869762.1|protein_coding||||||||WARNING_TRANSCRIPT_NO_START_CODON,T|non_coding_transcript_variant|MODIFIER|LOC109410517|gene-LOC109410517|transcript|XM_029869764.1|protein_coding||||||||WARNING_TRANSCRIPT_NO_START_CODON,T|non_coding_transcript_variant|MODIFIER|LOC109410517|gene-LOC109410517|transcript|XM_029869763.1|protein_coding||||||||WARNING_TRANSCRIPT_NO_START_CODON
## 2.40 1910214 AX-579619995    A   G   .   .   PR;ANN=G|intron_variant|MODIFIER|exon-XM_029869727.1-1|GENE_exon-XM_029869727.1-1|transcript|rna-XM_029869727.1|protein_coding|5/7|c.1936-849509A>G||||||WARNING_TRANSCRIPT_MULTIPLE_STOP_CODONS,G|intron_variant|MODIFIER|exon-XM_029869728.1-1|GENE_exon-XM_029869728.1-1|transcript|rna-XM_029869728.1|protein_coding|5/7|c.1921-849509A>G||||||WARNING_TRANSCRIPT_MULTIPLE_STOP_CODONS,G|intron_variant|MODIFIER|exon-XM_029869729.1-1|GENE_exon-XM_029869729.1-1|transcript|rna-XM_029869729.1|protein_coding|5/7|c.1936-849509A>G||||||WARNING_TRANSCRIPT_MULTIPLE_STOP_CODONS,G|intron_variant|MODIFIER|exon-XM_029869730.1-1|GENE_exon-XM_029869730.1-1|transcript|rna-XM_029869730.1|protein_coding|4/6|c.1795-849511A>G||||||WARNING_TRANSCRIPT_MULTIPLE_STOP_CODONS,G|intron_variant|MODIFIER|exon-XM_019702173.2-1|GENE_exon-XM_019702173.2-1|transcript|rna-XM_019702173.2|protein_coding|2/4|c.39+35305T>C||||||,G|non_coding_transcript_variant|MODIFIER|LOC109426648|gene-LOC109426648|transcript|XM_019702173.2|protein_coding||||||||WARNING_TRANSCRIPT_NO_START_CODON
## 2.40 2335429 AX-579620627    A   G   .   .   PR;ANN=G|synonymous_variant|LOW|exon-XM_029871669.1-1|GENE_exon-XM_029871669.1-1|transcript|rna-XM_029871669.1|protein_coding|2/2|c.843T>C|p.Tyr281Tyr|1054/1270|843/855|281/284||,G|intron_variant|MODIFIER|exon-XM_029869727.1-1|GENE_exon-XM_029869727.1-1|transcript|rna-XM_029869727.1|protein_coding|5/7|c.1936-424294A>G||||||WARNING_TRANSCRIPT_MULTIPLE_STOP_CODONS,G|intron_variant|MODIFIER|exon-XM_029869728.1-1|GENE_exon-XM_029869728.1-1|transcript|rna-XM_029869728.1|protein_coding|5/7|c.1921-424294A>G||||||WARNING_TRANSCRIPT_MULTIPLE_STOP_CODONS,G|intron_variant|MODIFIER|exon-XM_029869729.1-1|GENE_exon-XM_029869729.1-1|transcript|rna-XM_029869729.1|protein_coding|5/7|c.1936-424294A>G||||||WARNING_TRANSCRIPT_MULTIPLE_STOP_CODONS,G|intron_variant|MODIFIER|exon-XM_029869730.1-1|GENE_exon-XM_029869730.1-1|transcript|rna-XM_029869730.1|protein_coding|4/6|c.1795-424296A>G||||||WARNING_TRANSCRIPT_MULTIPLE_STOP_CODONS,G|non_coding_transcript_variant|MODIFIER|LOC115265709|gene-LOC115265709|transcript|XM_029871669.1|protein_coding||||||||WARNING_TRANSCRIPT_NO_START_CODON