hpo

.gitignore

@@ -0,0 +1 @@
+HPO

Makefile

@@ -1,2 +1,6 @@
 md5:
 	Rscript -e 'source("generate-md5.R")'
+
+
+hpo:
+	Rscript -e 'source("create-HPO.R")'

create-HPO.R

@@ -0,0 +1,22 @@
+## Human Phenotype Ontology
+## repo: https://github.com/obophenotype/human-phenotype-ontology
+## release: https://github.com/obophenotype/human-phenotype-ontology/releases
+
+
+pg <- read.delim("HPO/phenotype_to_genes.txt")
+hpo2gene <- pg[, c("hpo_id", "ncbi_gene_id")]
+hpo2gene <- na.omit(unique(hpo2gene)) |> setNames(c("id", "gene"))
+
+# updated date
+date <- 20240813
+
+
+library(obolite)
+create_sqlite("HPO/hp.obo", "HPO.sqlite", 
+    name = "Human Phenotype Ontology",
+    date = date,
+    url = 'https://github.com/obophenotype/human-phenotype-ontology/releases/download/v2024-08-13/hp.obo', 
+    ont2gene = hpo2gene
+    )
+
+

create-sqlite.R

@@ -7,3 +7,4 @@ url <- "https://github.com/DiseaseOntology/HumanDiseaseOntology/blob/main/src/on
 
 create_sqlite("Downloads/HumanDO.obo", "HDO.sqlite", name, date, url)
 
+

generate-md5.R

@@ -1,4 +1,14 @@
 ff <- list.files(pattern = ".sqlite$")
 md5 <- vapply(ff, function(f) digest::digest(f, algo='md5', file=TRUE), character(1))
+
+if (file.exists("md5.txt")) {
+    x <- read.delim("md5.txt", header=F)
+    oldmd5 <- setNames(x[,2], x[,1])
+    md5 <- c(md5, oldmd5[!names(oldmd5) %in% names(md5)])
+}
+
+
 cat(sprintf("%s\t%s\n", ff, md5), file="md5.txt", sep="")
 
+sapply(ff, R.utils::gzip, overwrite = TRUE)
+

md5.txt

@@ -1 +1,2 @@
 HDO.sqlite	41c0d4dc996b5bb4df194fc7d3c3f5b7
+HPO.sqlite	1722ff49c2eb7162c77d1d48b055df1c