A catalog of single nucleotide polymorphisms (SNPs) in voltage gated sodium channel subunits

library("biomaRt")

Genomic coorinates of voltage gated sodium channel subunit genes (SCN)

We will use the genomic assembly GRCh38.p12 for this exercise. We can obtain the necessary information about SCN genes from part 1 of this series.

However, we will use the following information (i.e., gene name, ENTREZ ID, chromosome number and coordinates) obtained from ENTREZ/NCBI:

“6323” = SCN1A Chromosome 2, NC_000002.12 (165989160..166149216, complement); “6326” = SCN2A Chromosome 2, NC_000002.12 (165208056..165392310); “6328” = SCN3A Chromosome 2, NC_000002.12 (165087520..165204295, complement); “6329” = SCN4A Chromosome 17, NC_000017.11 (63938554..63972918, complement); “6331” = SCN5A Chromosome 3, NC_000003.12 (38548061..38649673, complement); “6332” = SCN7A Chromosome 2, NC_000002.12 (166403573..166494264, complement); “6334” = SCN8A Chromosome 12, NC_000012.12 (51589958..51812864); “6335” = SCN9A Chromosome 2, NC_000002.12 (166195185..166375987, complement); “6336” = SCN10A Chromosome 3, NC_000003.12 (38697110..38794010, complement); “11280” = SCN11A Chromosome 3, NC_000003.12 (38845764..39051945, complement); “6324” = SCN1B Chromosome 19, NC_000019.10 (35030688..35040449); “6327” = SCN2B Chromosome 11, NC_000011.10 (118162804..118176622, complement); “55800” = SCN3B Chromosome 11, NC_000011.10 (123629187..123654607, complement); “6330” = SCN4B Chromosome 11, NC_000011.10 (118133377..118152915, complement)

Retrieve SNPs for SCN genes

hssnpmart = useMart(biomart = "ENSEMBL_MART_SNP", dataset="hsapiens_snp") # see listMarts() function
hssnpmart

Object of class 'Mart':
  Using the ENSEMBL_MART_SNP BioMart database
  Using the hsapiens_snp dataset

SCN1A SNPs

scn1a_snps_ncbi= getBM(attributes = c('refsnp_id','allele','chrom_start','chrom_strand'),
                       filters = c('chr_name','start','end'),
                       values = list(2, 165989160, 166149216),
                       mart = hssnpmart)
head(scn1a_snps_ncbi) 

nrow(scn1a_snps_ncbi)

[1] 34896

SCN2A SNPs

nrow(scn2a_snps_ncbi)

[1] 38544

SCN3A SNPs

nrow(scn3a_snps_ncbi)

[1] 23674

SCN4A SNPs

nrow(scn4a_snps_ncbi)

[1] 9146

SCN5A SNPs

nrow(scn5a_snps_ncbi)

[1] 23278

SCN7A SNPs

nrow(scn7a_snps_ncbi)

[1] 20782

SCN8A SNPs

nrow(scn8a_snps_ncbi)

[1] 45703

SCN9A SNPs

nrow(scn9a_snps_ncbi)

[1] 40382

SCN10A SNPs

nrow(scn10a_snps_ncbi)

[1] 22914

SCN11A SNPs

nrow(scn11a_snps_ncbi)

[1] 43321

SCN1B SNPs

nrow(scn1b_snps_ncbi)

[1] 2343

SCN2B SNPs

nrow(scn2b_snps_ncbi)

[1] 3287

SCN3B SNPs

nrow(scn3b_snps_ncbi)

[1] 5624

SCN4B SNPs

nrow(scn4b_snps_ncbi)

[1] 4678

elementNROWS(scn4b_snps_ncbi) 

   refsnp_id       allele  chrom_start chrom_strand 
        4678         4678         4678         4678 

A dataframe of the SCN reference SNPs

SCNsnps <- as.data.frame(cbind(scn1a_snps_ncbi$refsnp_id, scn2a_snps_ncbi$refsnp_id,
                               scn3a_snps_ncbi$refsnp_id, scn4a_snps_ncbi$refsnp_id,
                               scn5a_snps_ncbi$refsnp_id, scn7a_snps_ncbi$refsnp_id,
                               scn8a_snps_ncbi$refsnp_id, scn9a_snps_ncbi$refsnp_id,
                               scn10a_snps_ncbi$refsnp_id, scn11a_snps_ncbi$refsnp_id,
                               scn1b_snps_ncbi$refsnp_id, scn2b_snps_ncbi$refsnp_id,
                               scn3b_snps_ncbi$refsnp_id, scn4b_snps_ncbi$refsnp_id))

number of rows of result is not a multiple of vector length (arg 1)

head(SCNsnps)

dim(SCNsnps)

[1] 45703    14

Barplotting

scn_snp_counts

 [1] 34896 38544 23674  9146 23278 20782 45703 40382 22914 43321  2343  3287  5624  4678

barplot(scn_snp_counts)