Seeding comprehensive analysis in their named directories (e.g., BMI), the repository links to technical issues documented in physalia, Mixed-Models, software-notes and other sister repositories: SUMSTATS, FM-pipeline, PW-pipeline, hess-pipeline, TWAS-pipeline, EWAS-fusion. for fine-mapping, pathway analysis, TWAS, Mendelian randomisation, predictive analytics and other topics as highlighted in the wiki page.
Earlier or broader aspects have been reflected in the following repositories: Haplotype-Analysis, misc, R.
The figure below was generated with eQTL.R.
The Ensembl public MySQL Servers
The following script gives information on genes from ENSEMBL as well as attributes (columns) that contains gene.
library(biomaRt)
listMarts()
mart <- useMart("ENSEMBL_MART_FUNCGEN")
listDatasets(mart)
mart <- useMart("ensembl")
listDatasets(mart)
ensembl <- useMart("ensembl", dataset="hsapiens_gene_ensembl", host="grch37.ensembl.org", path="/biomart/martservice")
attr <- listAttributes(ensembl)
attr_select <- c('ensembl_gene_id', 'chromosome_name', 'start_position', 'end_position', 'description', 'hgnc_symbol', 'transcription_start_site')
gene <- getBM(attributes = attr_select, mart = ensembl)
filter <- listFilters(ensembl)
searchFilters(mart = ensembl, pattern = "gene")See also https://sites.google.com/site/jpopgen/wgsa for precompiled annotation. Alternatively,
# GENCODE v19
url <- "ftp://ftp.ebi.ac.uk/pub/databases/gencode/Gencode_human/release_19/gencode.v19.chr_patch_hapl_scaff.annotation.gtf.gz"
gtf <- rtracklayer::import(url)
gencode <- as.data.frame(gtf)LDlink: https://ldlink.nci.nih.gov/?tab=home.
NyuWa Chinese Population Variant Database (NCVD): http://bigdata.ibp.ac.cn/NyuWa_variants/
Example code,
library(ontologyIndex)
id <- function(ontology)
{
inflammatory <- grep(ontology$name,pattern="inflammatory")
immune <- grep(ontology$name,pattern="immune")
inf <- union(inflammatory,immune)
list(id=ontology$id[inf],name=ontology$name[inf])
}
# GO
data(go)
goidname <- id(go)
# EFO
file <- "efo.obo"
get_relation_names(file)
efo <- get_ontology(file, extract_tags="everything")
length(efo) # 89
length(efo$id) # 27962
efoidname <- id(efo)
diseases <- get_descendants(efo,"EFO:0000408")
efo_0000540 <- get_descendants(efo,"EFO:0000540")
efo_0000540name <- efo$name[efo_0000540]
isd <- data.frame(efo_0000540,efo_0000540name)
save(efo,diseases,isd,efoidname,goidname, file="work/efo.rda")
write.table(isd,file="efo_0000540.csv",col.names=FALSE,row.names=FALSE,sep=",")
pdf("efo_0000540.pdf",height=15,width=15)
library(ontologyPlot)
onto_plot(efo,efo_0000540)
dev.off()https://fuma.ctglab.nl/ (https://github.com/Kyoko-wtnb/FUMA-webapp/)
https://ftp.1000genomes.ebi.ac.uk/vol1/ftp/technical/reference/GRCh38_reference_genome/
https://metamap.nlm.nih.gov/MetaMapLite.shtml
- https://hupo.org/human-proteome-project (Resources, https://hupo.org/HPP-Resources)
- https://www.topdownproteomics.org/
http://www.roadmapepigenomics.org/
https://snakemake.github.io/snakemake-workflow-catalog/
https://github.com/hakyimlab/MetaXcan
http://gusevlab.org/projects/fusion/
The relevant URLs are as follows,
- https://cran.r-project.org/web/packages/rentrez/vignettes/rentrez_tutorial.html
- https://pubmed.ncbi.nlm.nih.gov/
- https://www.ncbi.nlm.nih.gov/pmc/pmctopmid/
with example code,
library(rentrez)
entrez_dbs()
entrez_db_links("pubmed")
pubmed_fields <- entrez_db_searchable("pubmed")
# set_entrez_key("")
Sys.getenv("ENTREZ_KEY")
term <- "pQTLs OR (protein AND quantitative AND trait AND loci) AND human [MH] AND (plasma OR Serum)"
r <- entrez_search(db="pubmed",term=term,use_history=TRUE)
class(r)
names(r)
with(r,web_history)
unlink(paste("pubmed",c("fetch","summary"),sep="."))
fields <- c("uid", "pubdate", "sortfirstauthor", "title", "source", "volume", "pages")
for(i in seq(1,with(r,count),50))
{
cat(i+49, "records downloaded\r")
f <- entrez_fetch(db="pubmed", web_history=with(r,web_history), rettype="text", retmax=50, retstart=i)
write.table(f, col.names=FALSE, row.names=FALSE, file="pubmed.fetch", append=TRUE)
s <- entrez_summary(db="pubmed", web_history=with(r,web_history), rettype="text", retmax=50, retstart=i)
e <- extract_from_esummary(s, fields)
write.table(t(e), col.names=FALSE, row.names=FALSE, file="pubmed.summary", append=TRUE, sep="\t")
}
id <- 600807
upload <- entrez_post(db="omim", id=id)
asthma_variants <- entrez_link(dbfrom="omim", db="clinvar", cmd="neighbor_history", web_history=upload)
asthma_variants
snp_links <- entrez_link(dbfrom="clinvar", db="snp", web_history=asthma_variants$web_histories$omim_clinvar, cmd="neighbor_history")
all_links <- entrez_link(dbfrom='pubmed', id=id, db='all')http://www.sequenceontology.org/
- China Kadoorie Biobank
- Estonian Biobank
- FinGenn
- Japan Biobank
- UK Biobank
- AMS (mailto:[email protected]), Access_019-Access-Management-System-User-Guide-V4.0.pdf, messages.
- Accessing data guide, http://biobank.ctsu.ox.ac.uk/crystal/exinfo.cgi?src=AccessingData.
- AstraZeneca PheWAS Portal, https://azphewas.com/ (CGR Proteogenomics Portal)
- Data access guide 3.2, https://biobank.ndph.ox.ac.uk/~bbdatan/Data_Access_Guide_v3.2.pdf
- DNAnexus, landing, partnerships
- Imputation, http://biobank.ctsu.ox.ac.uk/crystal/crystal/docs/impute_ukb_v1.pdf.
- Gene ATLAS, http://geneatlas.roslin.ed.ac.uk/.
- genebass
- PHESANT.
- Online showcase, https://biobank.ndph.ox.ac.uk/ukb/ (Showcase User Guide).
- Pan-UK Biobank, GWAS sumstats and GitHub.
- COVID-19 data, format and field.