changeset 7:a5233fbfc603 draft

Uploaded
author davidvanzessen
date Wed, 12 Aug 2015 05:09:59 -0400
parents 752528a5934d
children 38f0e68d1bac
files OMT_coding.txt Phenotypic_groups.txt phenotype_gene_relations.r phenotype_gene_relations.sh phenotype_gene_relations.xml
diffstat 5 files changed, 30 insertions(+), 528 deletions(-) [+]
line wrap: on
line diff
--- a/OMT_coding.txt	Thu Aug 06 03:34:49 2015 -0400
+++ b/OMT_coding.txt	Wed Aug 12 05:09:59 2015 -0400
@@ -1,523 +1,1 @@
-ID	OMT.name
-1	1. Malformation
-2	2. Deformation
-3	3. Dysplasia
-11	1A. Entire limb malformations
-12	1B. Handplate malformations
-21	Constriction ring sequence
-22	Trigger digits
-31	3A. Hypertrophy
-32	3B. Tumorous conditions
-110	1A. NOS entire limb malformation
-111	1A1. Proximal-distal axis (entire limb)
-112	1A2. Radio-ulnar axis (entire limb)
-113	1A4. Unspecified axis (entire limb)
-114	1A3. Dorso-ventral axis (entire limb)
-120	1B. NOS handplate malformation
-121	1B1. Proximal-distal axis (hand)
-122	1B2. Radio-ulnar axis (hand)
-123	1B3. Dorso-ventral axis (hand)
-124	1B4. Unspecified axis (hand)
-210	Constriction ring sequence
-220	Trigger digits
-311	3A1. Whole limb hypertrophy
-312	3A2. Partial Limb hypertrophy
-321	3B1. Vascular tumors
-324	3B4. Skeletal tumors
-1100	1A. NOS malformation (entire limb)
-1110	1A1. NOS prox-distal axis (entire limb)
-1111	1A1i. Brachymelia
-1112	1A1ii. Symbrachydactyly
-1113	1A1iii. Transverse deficiency
-1114	1A1iv. Intersegmental deficiency
-1115	1A1v. Limb duplication
-1120	1A2. NOS rad-uln axis (entire limb)
-1121	1A2i. Radial longitudinal deficiency
-1122	1A2ii. Ulnar longitudinal deficiency
-1124	1A2iv. Radioulnar synostosis
-1125	1A2v. Congenital radial head dislocation
-1126	1A2vi. Humeroradial synostosis
-1127	1A2vii. Madelung deformity
-1131	1A3i. Dorsal dimelia (palmar nail)
-1132	1A3ii. Ventral dimelia 
-1141	1A4i. Abberant shoulder (incl Sprengel deformity)
-1142	1A4ii. Arthrogryposis
-1200	1B. NOS malformation (hand)
-1211	1B1i. Brachydactyly
-1213	1B1iii. Transverse deficiency (no arm involvement)
-1220	1B2. NOS rad-uln axis malformation (hand)
-1221	1B2i. Radial deficiency of the hand
-1222	1B2ii. Ulnar deficiency of the hand
-1223	1B2iii. Radial polydactyly
-1224	1B2iv. Triphalangeal thumb
-1225	1B2v. Ulnar dimelia
-1226	1B2vi. Ulnar polydactyly
-1232	1B3ii. Ventral dimelia (incl hypoplastic/aplastic nail)
-1241	1B4i. Softi tissue malformations
-1242	1B4ii. Sekeltal deficiencies
-1243	1B4iii. Complex anomalies of unspecified axis (hand)
-2100	Constriction ring sequence
-2200	Trigger digits
-3111	3A1i. Hemihypertrophy
-3121	3A2i. Macrodactyly
-3211	3B1i. Hemangioma
-3212	3B1ii. Vascular malformation
-3241	3B4i. Osteochondromatosis
-3242	3B4ii. Echondromatosis
-3244	3B4iv. Epiphyseal abnormalities
-11000	1A. NOS entire limb malformation
-11100	1A1. NOS proximal-distal axis malformation
-11110	1A1i. Brachymelia
-11121	1A1iia. Poland Syndrome
-11130	1A1iii. Transverse deficiency
-11140	1A1iv. Intersegmental deficiency
-11150	1A1v. Limb duplication
-11200	1A2. NOS rad-uln axis (entire limb)
-11210	1A2i. Radial longitudinal deficiency
-11220	1A2ii. Ulnar longitudinal deficiency
-11240	1A2iv. Radioulnar synostosis
-11250	1A2v. Congenital radial head dislocation
-11260	1A2vi. Humeroradial synostosis
-11270	1A2vii. Madelung deformity
-11310	1A3i. Dorsal dimelia (palmar nail)
-11320	1A3ii. Ventral dimelia 
-11411	1A4ia. Sprengel deformity
-11412	1A4ib. Abnormal shoulder muscles
-11413	1A4ic. NOS shoulder malformation
-11420	1A4ii. Arthrogryposis
-12000	1B. NOS handplate malformation
-12110	1B1i. Brachydactyly
-12130	1B1iii. Transverse deficiency (no arm involvement)
-12200	1B2. NOS rad-uln axis malformation (hand)
-12210	1B2i. Radial deficiency of the hand
-12220	1B2ii. Ulnar deficiency of the hand
-12230	1B2iii. Radial polydactyly
-12240	1B2iv. Triphalangeal thumb
-12250	1B2v. Ulnar dimelia
-12260	1B2vi. Ulnar polydactyly
-12320	1B3ii. Ventral dimelia (incl hypoplastic/aplastic nail)
-12411	1B4ia. Syndactyly
-12412	1B4ib. Camptodactyly
-12413	1B4ic. Thumb in palm deformity
-12414	1B4id. Distal arthrogryposis
-12421	1B4iia. Clinodactyly
-12423	1B4iib. Synostosis/symphalangism
-12431	1B4iiia. Complex syndactyly
-12432	1B4iiib. Synpolydactyly
-12433	1B4iiic. Cleft Hand
-12434	1B4iiid. Apert Hand
-21000	Constriction ring sequence
-22000	Trigger digits
-31110	3A1i. Hemihypertrophy
-31210	3A2i. Macrodactyly
-32110	3B1i. Hemangioma
-32120	3B1ii. Vascular malformation
-32410	3B4i. Osteochondromatosis
-32420	3B4ii. Echondromatosis
-32440	3B4iv. Epiphyseal abnormalities
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
-	
+1	1. Malformation
2	2. Deformation
3	3. Dysplasia
11	1A. Entire limb malformations
12	1B. Handplate malformations
21	Constriction ring sequence
22	Trigger digits
31	3A. Hypertrophy
32	3B. Tumorous conditions
110	1A. NOS entire limb malformation
111	1A1. Proximal-distal axis (entire limb)
112	1A2. Radio-ulnar axis (entire limb) 
113	1A3. Dorso-ventral axis (entire limb)
114	1A4. Unspecified axis (entire limb)
120	1B. NOS handplate malformation
121	1B1. Proximal-distal axis (hand)
122	1B2. Radio-ulnar axis (hand)
123	1B3. Dorso-ventral axis (hand)
124	1B4. Unspecified axis (hand)
210	Constriction ring sequence
220	Trigger digits
311	3A1. Whole limb hypertrophy
312	3A2. Partial Limb hypertrophy
321	3B1. Vascular tumors
324	3B4. Skeletal tumors
1100	1A. NOS malformation (entire limb)
1110	1A1. NOS prox-distal axis (entire limb)
1111	1A1i. Brachymelia
1112	1A1ii. Symbrachydactyly
1113	1A1iii. Transverse deficiency
1114	1A1iv. Intersegmental deficiency
1115	1A1v. Limb duplication
1120	1A2. NOS rad-uln axis (entire limb)
1121	1A2i. Radial longitudinal deficiency
1122	1A2ii. Ulnar longitudinal deficiency
1124	1A2iv. Radioulnar synostosis
1125	1A2v. Congenital radial head dislocation
1126	1A2vi. Humeroradial synostosis
1127	1A2vii. Madelung deformity
1131	1A3i. Dorsal dimelia (palmar nail)
1132	1A3ii. Ventral dimelia 
1141	1A4i. Abberant shoulder (incl Sprengel deformity)
1142	1A4ii. Arthrogryposis
1200	1B. NOS malformation (hand)
1211	1B1i. Brachydactyly
1213	1B1iii. Transverse deficiency (no arm involvement)
1220	1B2. NOS rad-uln axis malformation (hand)
1221	1B2i. Radial deficiency of the hand
1222	1B2ii. Ulnar deficiency of the hand
1223	1B2iii. Radial polydactyly
1224	1B2iv. Triphalangeal thumb
1225	1B2v. Ulnar dimelia
1226	1B2vi. Ulnar polydactyly
1232	1B3ii. Ventral dimelia (incl hypoplastic/aplastic nail)
1241	1B4i. Softi tissue malformations
1242	1B4ii. Sekeltal deficiencies
1243	1B4iii. Complex anomalies of unspecified axis (hand)
2100	Constriction ring sequence
2200	Trigger digits
3111	3A1i. Hemihypertrophy
3121	3A2i. Macrodactyly
3211	3B1i. Hemangioma
3212	3B1ii. Vascular malformation
3241	3B4i. Osteochondromatosis
3242	3B4ii. Echondromatosis
3244	3B4iv. Epiphyseal abnormalities
11000	1A. NOS entire limb malformation
11100	1A1. NOS proximal-distal axis malformation
11110	1A1i. Brachymelia
11121	1A1iia. Poland Syndrome
11130	1A1iii. Transverse deficiency
11140	1A1iv. Intersegmental deficiency
11150	1A1v. Limb duplication
11200	1A2. NOS rad-uln axis (entire limb)
11210	1A2i. Radial longitudinal deficiency
11220	1A2ii. Ulnar longitudinal deficiency
11240	1A2iv. Radioulnar synostosis
11250	1A2v. Congenital radial head dislocation
11260	1A2vi. Humeroradial synostosis
11270	1A2vii. Madelung deformity
11310	1A3i. Dorsal dimelia (palmar nail)
11320	1A3ii. Ventral dimelia 
11411	1A4ia. Sprengel deformity
11412	1A4ib. Abnormal shoulder muscles
11413	1A4ic. NOS shoulder malformation
11420	1A4ii. Arthrogryposis
12000	1B. NOS handplate malformation
12110	1B1i. Brachydactyly
12130	1B1iii. Transverse deficiency (no arm involvement)
12200	1B2. NOS rad-uln axis malformation (hand)
12210	1B2i. Radial deficiency of the hand
12220	1B2ii. Ulnar deficiency of the hand
12230	1B2iii. Radial polydactyly
12240	1B2iv. Triphalangeal thumb
12250	1B2v. Ulnar dimelia
12260	1B2vi. Ulnar polydactyly
12320	1B3ii. Ventral dimelia (incl hypoplastic/aplastic nail)
12411	1B4ia. Syndactyly
12412	1B4ib. Camptodactyly
12413	1B4ic. Thumb in palm deformity
12414	1B4id. Distal arthrogryposis
12421	1B4iia. Clinodactyly
12423	1B4iib. Synostosis/symphalangism
12431	1B4iiia. Complex syndactyly
12432	1B4iiib. Synpolydactyly
12433	1B4iiic. Cleft Hand
12434	1B4iiid. Apert Hand
21000	Constriction ring sequence
22000	Trigger digits
31110	3A1i. Hemihypertrophy
31210	3A2i. Macrodactyly
32110	3B1i. Hemangioma
32120	3B1ii. Vascular malformation
32410	3B4i. Osteochondromatosis
32420	3B4ii. Echondromatosis
32440	3B4iv. Epiphyseal abnormalities
\ No newline at end of file
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/Phenotypic_groups.txt	Wed Aug 12 05:09:59 2015 -0400
@@ -0,0 +1,12 @@
+1	CULA
+2	Circulatory
+3	Respiratory
+4	Digestive
+5	Urogenital
+6	Nervous system
+7	Vertebral column
+8	Musculoskeletal
+9	Head/Neck
+10	Lower limb
+11	Skin 
+12	Others
--- a/phenotype_gene_relations.r	Thu Aug 06 03:34:49 2015 -0400
+++ b/phenotype_gene_relations.r	Wed Aug 12 05:09:59 2015 -0400
@@ -16,7 +16,8 @@
 hpo.to.omt.file = args[3]
 inheritance.from.group.0.file = args[4]
 omt.coding.file = args[5]
-final.file = args[6]
+phenotypic.names.file = args[6]
+final.file = args[7]
 
 #get ALL_SOURCES_ALL_FREQUENCIES.TXT
 all.sources = read.table(all.sources.file, header=T, sep="\t", comment.char="#", quote = "")
@@ -92,8 +93,19 @@
 final$HPO.term.name.y = as.character(final$HPO.term.name.y)
 final$HPO.term.name.y[is.na(final$HPO.term.name.y)] = "No inheritance pattern available"
 
-final = final[,c("diseaseId", "gene.symbol", "gene.id.entrez.", "HPO.term.name.x", "variable", "value", "OMT.1", "OMT.1.name", "OMT.2", "OMT.2.name", "OMT.3", "OMT.3.name", "OMT.4", "OMT.4.name", "OMT.5", "OMT.5.name", "HPO.term.name.y")]
-names(final) = c("diseaseId", "gene.symbol", "gene.id.entrez.", "HPO.term.name", "GROUP.CODE", "ratio", "OMT.1", "OMT.1.name", "OMT.2", "OMT.2.name", "OMT.3", "OMT.3.name", "OMT.4", "OMT.4.name", "OMT.5", "OMT.5.name", "inheritance")
+phenotypic.names = read.table(phenotypic.names.file, header=F, sep="\t", comment.char="#", quote = "")
+names(phenotypic.names) = c("GROUP.CODE", "GROUP.NAME")
+final = merge(final, phenotypic.names, by.x="variable", by.y="GROUP.CODE")
+
+
+final$url = ""
+final$db = gsub(":.*", "", final$diseaseId)
+final$id = gsub(".*:", "", final$diseaseId)
+final$url = paste("http://www.omim.org/entry/", final$id, sep="")
+final[final$db == "ORPHANET",]$url = paste("http://www.orpha.net/consor/cgi-bin/Disease_Search_Simple.php?lng=EN&lng=EN&Disease_Disease_Search_diseaseGroup=", final[final$db == "ORPHANET",]$id, "&Disease_Disease_Search_diseaseType=ORPHA", sep="")
+
+final = final[,c("diseaseId", "gene.symbol", "gene.id.entrez.", "HPO.term.name.x", "variable", "GROUP.NAME", "value", "OMT.1", "OMT.1.name", "OMT.2", "OMT.2.name", "OMT.3", "OMT.3.name", "OMT.4", "OMT.4.name", "OMT.5", "OMT.5.name", "HPO.term.name.y", "url")]
+names(final) = c("diseaseId", "gene.symbol", "gene.id.entrez.", "HPO.term.name", "GROUP.CODE", "GROUP.NAME", "ratio", "OMT.1", "OMT.1.name", "OMT.2", "OMT.2.name", "OMT.3", "OMT.3.name", "OMT.4", "OMT.4.name", "OMT.5", "OMT.5.name", "inheritance", "url")
 write.table(final, file=final.file, quote=F, sep="\t", row.names=F, col.names=T)
 
 
--- a/phenotype_gene_relations.sh	Thu Aug 06 03:34:49 2015 -0400
+++ b/phenotype_gene_relations.sh	Wed Aug 12 05:09:59 2015 -0400
@@ -8,4 +8,4 @@
 inheritence_from_group_0=$4
 output=$5
 
-Rscript --verbose $dir/phenotype_gene_relations.r "$all_sources" "$phenotypic_groups" "$hpo_to_omt" "$inheritence_from_group_0" "$dir/OMT_coding.txt" "$output" 2>&1
+Rscript --verbose $dir/phenotype_gene_relations.r "$all_sources" "$phenotypic_groups" "$hpo_to_omt" "$inheritence_from_group_0" "$dir/OMT_coding.txt" "$dir/Phenotypic_groups.txt" "$output" 2>&1
--- a/phenotype_gene_relations.xml	Thu Aug 06 03:34:49 2015 -0400
+++ b/phenotype_gene_relations.xml	Wed Aug 12 05:09:59 2015 -0400
@@ -10,7 +10,7 @@
         <param name="inheritence_from_group_0" format="tabular" type="data" label="Inheritance from group 0" />
 	</inputs>
 	<outputs>
-		<data format="tabular" name="output" label="Phenotype Gene Rel on: ${all_sources.name},${phenotypic_groups.name},${hpo_to_omt.name} "/>
+		<data format="csv" name="output" label="Phenotype Gene Rel on: ${all_sources.name},${phenotypic_groups.name},${hpo_to_omt.name} "/>
 	</outputs>
 	<help>
 stuff, words, things