Merge branch 'development'

README.md

@@ -30,6 +30,8 @@ If the annotation is not made beforehand make sure that the necessary database r
 The HPO resources needed for the prioritization step can be found in the `data` folder. The path to the files is specified in the configuration file make sure that it leads to the correct location.
 In the data folder there is also a standalone python script to generate these files (inside the script in the comments you can find the download links to the files that are used to generate the resources). For compatibility reasons the HPO graph resources were generated using networkx v1. Version 2 can still import these resources, but the graph generated with version 2 is not compatible with version 1.
 
+Last update of HPO resources: 30th July, 2021
+
 
 ## Pathogenicity prediction
 There are two random forest models that are used in AIdiva to predict the pathogenicity of a given variant. One for SNP variants and the other for inframe InDel variants. The training data of the two models consists of variants from Clinvar combined with additional variants from HGMD that are not present in Clinvar.

data/makefiles/Makefile_ABB-SCORE → data/makefiles/Makefile_ABB-SCORE.mk

@@ -1,5 +1,5 @@
 help:
-	@cat Makefile_ABB-SCORE
+	@cat Makefile_ABB-SCORE.mk
 
 download:
 	wget -c https://public_docs.crg.es/sossowski/publication_data/ABB/ABB_SCORE.txt

data/makefiles/Makefile_Condel → data/makefiles/Makefile_Condel.mk

@@ -1,5 +1,5 @@
 help:
-	@cat Makefile_Condel
+	@cat Makefile_Condel.mk
 
 download:
 	wget -c https://bbglab.irbbarcelona.org/fannsdb/downloads/fannsdb.tsv.gz

data/makefiles/Makefile_Eigen-phred → data/makefiles/Makefile_Eigen-phred.mk

@@ -1,5 +1,5 @@
 help:
-	@cat Makefile_Eigen-phred
+	@cat Makefile_Eigen-phred.mk
 
 download:
 	wget -c http://web.corral.tacc.utexas.edu/WGSAdownload/resources/Eigen/Eigen_hg19_combined.tab.chr1.gz

data/makefiles/Makefile_FATHMM-XF → data/makefiles/Makefile_FATHMM-XF.mk

@@ -1,5 +1,5 @@
 help:
-	@cat Makefile_FATHMM-XF
+	@cat Makefile_FATHMM-XF.mk
 
 download:
 	wget -c http://fathmm.biocompute.org.uk/fathmm-xf/fathmm_xf_coding.vcf.gz

data/makefiles/Makefile_HPO.mk

@@ -0,0 +1,30 @@
+SHELL:=/bin/bash
+
+help:
+	@cat Makefile_HPO.mk
+
+download:
+	wget -c http://purl.obolibrary.org/obo/hp/hpoa/phenotype_to_genes.txt
+	wget -c http://purl.obolibrary.org/obo/hp.obo
+	wget -c http://purl.obolibrary.org/obo/hp/hpoa/phenotype_annotation.tab
+	wget -c http://ftp.ebi.ac.uk/pub/databases/genenames/hgnc/tsv/hgnc_complete_set.txt
+	wget -c https://stringdb-static.org/download/protein.links.detailed.v11.0/9606.protein.links.detailed.v11.0.txt.gz
+	wget -c https://string-db.org/mapping_files/STRING_display_names/human.name_2_string.tsv.gz
+
+convert:
+	awk -F '	'  '{print $$5}' < phenotype_annotation.tab | sort  | uniq -c | awk '{print $$2 "	" $$1}' > HPO_counts.txt
+	python3 generate_HPO_resources.py --hpo_ontology hp.obo --gene_phenotype phenotype_to_genes.txt --gene_hpo gene2hpo.pkl --hpo_edges hpo_edges.pkl --hpo_counts HPO_counts.txt --hpo_graph hpo_graph.pkl --hgnc_symbols hgnc_complete_set.txt --hgnc_gene hgnc2gene.pkl --string_links 9606.protein.links.detailed.v11.0.txt.gz --string_mapping human.name_2_string.tsv.gz --gene_interacting gene2interacting.pkl
+
+	rm phenotype_to_genes.txt
+	rm hp.obo
+	rm phenotype_annotation.tab
+	rm hgnc_complete_set.txt
+	rm 9606.protein.links.detailed.v11.0.txt.gz
+	rm human.name_2_string.tsv.gz
+	rm hpo_edges.pkl
+	rm HPO_counts.txt
+
+	mv gene2hpo.pkl ../hpo_resources/
+	mv gene2interacting.pkl ../hpo_resources/
+	mv hgnc2gene.pkl ../hpo_resources/
+	mv hpo_graph.pkl ../hpo_resources/

data/makefiles/Makefile_MutationAssessor → data/makefiles/Makefile_MutationAssessor.mk

@@ -1,5 +1,5 @@
 help:
-	@cat Makefile_MutationAssessor
+	@cat Makefile_MutationAssessor.mk
 
 download:
 	wget -c http://mutationassessor.org/r3/MA_scores_rel3_hg19_full.tar.gz

data/makefiles/Makefile_gnomAD_OE → data/makefiles/Makefile_gnomAD_OE.mk

@@ -1,5 +1,5 @@
 help:
-	@cat Makefile_gnomAD_OE
+	@cat Makefile_gnomAD_OE.mk
 
 download:
 	wget -c https://storage.googleapis.com/gnomad-public/release/2.1.1/constraint/gnomad.v2.1.1.lof_metrics.by_gene.txt.bgz

data/makefiles/Makefile_phastCons46mammal → data/makefiles/Makefile_phastCons46mammal.mk

@@ -1,5 +1,5 @@
 help:
-	@cat Makefile_phastCons46mammal
+	@cat Makefile_phastCons46mammal.mk
 
 download_hg19:
 	wget -c http://hgdownload.cse.ucsc.edu/goldenpath/hg19/phastCons46way/placentalMammals/chr1.phastCons46way.placental.wigFix.gz

data/makefiles/Makefile_phastCons46primate → data/makefiles/Makefile_phastCons46primate.mk

@@ -1,5 +1,5 @@
 help:
-	@cat Makefile_phastCons46primate
+	@cat Makefile_phastCons46primate.mk
 
 download_hg19:
 	wget -c http://hgdownload.cse.ucsc.edu/goldenpath/hg19/phastCons46way/primates/chr1.phastCons46way.primates.wigFix.gz

data/makefiles/Makefile_phastCons46vertebrate → data/makefiles/Makefile_phastCons46vertebrate.mk

@@ -1,5 +1,5 @@
 help:
-	@cat Makefile_phastCons46vertebrate
+	@cat Makefile_phastCons46vertebrate.mk
 
 download_hg19:
 	wget -c http://hgdownload.cse.ucsc.edu/goldenpath/hg19/phastCons46way/vertebrate/chr1.phastCons46way.wigFix.gz

data/makefiles/Makefile_phyloP46mammal → data/makefiles/Makefile_phyloP46mammal.mk

@@ -1,5 +1,5 @@
 help:
-	@cat Makefile_phyloP46mammal
+	@cat Makefile_phyloP46mammal.mk
 
 download_hg19:
 	wget -c http://hgdownload.cse.ucsc.edu/goldenpath/hg19/phyloP46way/placentalMammals/chr1.phyloP46way.placental.wigFix.gz

data/makefiles/Makefile_phyloP46primate → data/makefiles/Makefile_phyloP46primate.mk

@@ -1,5 +1,5 @@
 help:
-	@cat Makefile_phyloP46primate
+	@cat Makefile_phyloP46primate.mk
 
 download_hg19:
 	wget -c http://hgdownload.cse.ucsc.edu/goldenpath/hg19/phyloP46way/primates/chr1.phyloP46way.primate.wigFix.gz

data/makefiles/Makefile_phyloP46vertebrate → data/makefiles/Makefile_phyloP46vertebrate.mk

@@ -1,5 +1,5 @@
 help:
-	@cat Makefile_phyloP46vertebrate
+	@cat Makefile_phyloP46vertebrate.mk
 
 download_hg19:
 	wget -c http://hgdownload.cse.ucsc.edu/goldenpath/hg19/phyloP46way/vertebrate/chr1.phyloP46way.wigFix.gz

data/makefiles/Makefile_segmentDuplication → data/makefiles/Makefile_segmentDuplication.mk

@@ -1,5 +1,5 @@
 help:
-	@cat Makefile_segmentDuplication
+	@cat Makefile_segmentDuplication.mk
 
 download_hg19:
 	wget -O hg19.genomicSuperDups.txt.gz ftp://hgdownload.soe.ucsc.edu/goldenPath/hg19/database/genomicSuperDups.txt.gz

data/makefiles/Makefile_simpleRepeat → data/makefiles/Makefile_simpleRepeat.mk

@@ -1,5 +1,5 @@
 help:
-	@cat Makefile_simpleRepeat
+	@cat Makefile_simpleRepeat.mk
 
 download_hg19:
 	wget -O hg19.simpleRepeat.txt.gz ftp://hgdownload.soe.ucsc.edu/goldenPath/hg19/database/simpleRepeat.txt.gz

aidiva/helper_modules/generate_HPO_resources.py → data/makefiles/generate_HPO_resources.py

@@ -7,7 +7,7 @@
 
 # get mapping gene -> HPOs
 # download from HPO charite phenotype to gene
-# wget http://compbio.charite.de/jenkins/job/hpo.annotations/lastStableBuild/artifact/util/annotation/phenotype_to_genes.txt
+# wget http://purl.obolibrary.org/obo/hp/hpoa/phenotype_to_genes.txt
 def generate_gene2hpo_dict(gene2phenotype_list, gene2hpo_dict):
     print("Generate gene to HPO mapping...")
     gene_2_HPO = dict()
@@ -31,7 +31,7 @@ def generate_gene2hpo_dict(gene2phenotype_list, gene2hpo_dict):
 
 
 # download data
-# wget https://raw.githubusercontent.com/obophenotype/human-phenotype-ontology/master/hp.obo
+# wget http://purl.obolibrary.org/obo/hp.obo
 def extract_hpo_graph_edges(hpo_ontology, hpo_edges_file):
     print("Extract HPO edges...")
     out_HPO = dict()
@@ -87,7 +87,7 @@ def extract_hpo_graph_edges(hpo_ontology, hpo_edges_file):
     print("HPO edges successfully extracted and saved as %s" % (hpo_edges_file))
 
 
-# counts as wget http://compbio.charite.de/jenkins/job/hpo.annotations/lastStableBuild/artifact/misc/phenotype_annotation.tab
+# counts as wget http://purl.obolibrary.org/obo/hp/hpoa/phenotype_annotation.tab
 # awk -F '\t'  '{print $5}' < phenotype_annotation.tab | sort  | uniq -c | awk '{print $2 "\t" $1}' > HPO_counts.txt
 def generate_hpo_graph(hpo_counts, hpo_edges_file, hpo_graph_file):
     print("Generate HPO graph...")
@@ -98,8 +98,10 @@ def generate_hpo_graph(hpo_counts, hpo_edges_file, hpo_graph_file):
     # generate graph with counts:
     counts_dict = dict()
     tot = 0
-    with open(hpo_counts) as count_file:
+    with open(hpo_counts, "r") as count_file:
         for line in count_file:
+            if line.startswith("HPO-ID"):
+                continue
             splitted_line = line.strip().split("\t")
             counts_dict[splitted_line[0]] = int(splitted_line[1])
             tot += int(splitted_line[1])