X-Git-Url: http://woldlab.caltech.edu/gitweb/?p=erange.git;a=blobdiff_plain;f=cistematic%2Fgenomes%2Fhsapiens.py;fp=cistematic%2Fgenomes%2Fhsapiens.py;h=e9c677cace13c0e556d0c2234029d3ce42e8c98d;hp=0000000000000000000000000000000000000000;hb=bc30aca13e5ec397c92e67002fbf7a103130b828;hpb=0d3e3112fd04c2e6b44a25cacef1d591658ad181

diff --git a/cistematic/genomes/hsapiens.py b/cistematic/genomes/hsapiens.py
new file mode 100644
index 0000000..e9c677c
--- /dev/null
+++ b/cistematic/genomes/hsapiens.py
@@ -0,0 +1,264 @@
+###########################################################################
+#                                                                         #
+# C O P Y R I G H T   N O T I C E                                         #
+#  Copyright (c) 2003-10 by:                                              #
+#    * California Institute of Technology                                 #
+#                                                                         #
+#    All Rights Reserved.                                                 #
+#                                                                         #
+# Permission is hereby granted, free of charge, to any person             #
+# obtaining a copy of this software and associated documentation files    #
+# (the "Software"), to deal in the Software without restriction,          #
+# including without limitation the rights to use, copy, modify, merge,    #
+# publish, distribute, sublicense, and/or sell copies of the Software,    #
+# and to permit persons to whom the Software is furnished to do so,       #
+# subject to the following conditions:                                    #
+#                                                                         #
+# The above copyright notice and this permission notice shall be          #
+# included in all copies or substantial portions of the Software.         #
+#                                                                         #
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,         #
+# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF      #
+# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND                   #
+# NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS     #
+# BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN      #
+# ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN       #
+# CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE        #
+# SOFTWARE.                                                               #
+###########################################################################
+#
+# data for Homo sapiens
+import string
+from cistematic.genomes import Genome
+from cistematic.core.geneinfo import geneinfoDB
+from os import environ
+
+if environ.get("CISTEMATIC_ROOT"):
+    cisRoot = environ.get("CISTEMATIC_ROOT") 
+else:
+    cisRoot = "/proj/genome"
+
+geneDB = "%s/H_sapiens/hsapiens.genedb" % cisRoot
+
+def loadChromosome(db, chromID, chromPath, chromOut):
+    seqArray = []
+    hsGenome = Genome("hsapiens", dbFile=db)
+    inFile = open(chromPath, "r")
+    line = inFile.readline()
+    for line in inFile:
+        seqArray.append(line.strip())
+
+    seq = string.join(seqArray, "")
+    seqLen = len(seq)
+    if seqLen < 1:
+        print "Problems reading sequence from file"
+    print "writing to file %s" % chromOut
+    outFile = open("%s%s" % (cisRoot, chromOut), "w")
+    outFile.write(seq)
+    outFile.close()
+    hsGenome.addChromosomeEntry(chromID, chromOut, "file")
+
+
+def loadGeneEntries(db, gFile, cDict):
+    """ FIXME - NEED TO DEAL WITH ALTERNATIVE SPLICING ENTRIES
+    """
+    geneEntries = []
+    hsGenome = Genome("hsapiens", dbFile=db)
+    geneFile = open(gFile, "r")
+    for line in geneFile:
+        cols = line.split("\t")
+        if cols[11] != "GENE":
+            continue
+
+        if cols[12] == "Celera":
+            continue
+
+        chrom = cols[1].strip()
+        if chrom not in cDict:
+            continue
+  
+        name = cols[10].split(":")
+        gid = name[1]
+        start = int(cols[2])
+        stop = int(cols[3])
+        sense = cols[4]
+        if sense == "+":
+            sense = "F"
+        else:
+            sense = "R"
+
+        geneID = ("hsapiens", gid)
+        gidVersion = 1
+        geneEntries.append((geneID, chrom, start, stop, sense, "gene", gidVersion))
+
+    print "Adding %d gene entries" % len(geneEntries)
+    hsGenome.addGeneEntryBatch(geneEntries)
+
+
+def loadGeneFeatures(db, gFile, cDict):
+    """ Load gene features such as CDS, UTR, and PSEUDO from the gene file.
+    """
+    featureEntries = []
+    hsGenome = Genome("hsapiens", dbFile=db)
+    featureFile = open(gFile, "r")
+    for line in featureFile:
+        cols = line.split("\t")
+        if cols[11] not in ["CDS", "UTR", "PSEUDO"]:
+            continue
+        if cols[12] == "Celera":
+            continue
+        chrom = cols[1].strip()
+        if chrom not in cDict:
+            continue
+
+        fType = cols[11]
+        name = cols[10].split(":")
+        gid = name[1]
+        start = int(cols[2])
+        stop = int(cols[3])
+        sense = cols[4]
+        if sense == "+":
+            sense = "F"
+        else:
+            sense = "R"
+
+        geneID = ("hsapiens", gid)
+        gidVersion = 1
+        featureEntries.append((geneID, gidVersion, chrom, start, stop, sense, fType))
+
+    print "Adding %d feature entries" % len(featureEntries)
+    hsGenome.addFeatureEntryBatch(featureEntries)
+
+
+def loadGeneAnnotations(db):
+    geneAnnotations = []
+    idb = geneinfoDB()
+    hsGenome = Genome("hsapiens", dbFile=db)
+    gidList = hsGenome.allGIDs()
+    for locID in gidList:
+        gID = ("hsapiens", locID)
+        geneDescArray = idb.getDescription(gID)
+        geneDesc = ""
+        for entry in geneDescArray:
+            geneDesc += ","
+            geneDesc += entry.strip()
+
+        if len(geneDescArray) > 0:
+            geneAnnotations.append((gID, string.replace(geneDesc[1:], "'", "p")))
+
+    print "Adding %d annotations" % len(geneAnnotations)
+    hsGenome.addAnnotationBatch(geneAnnotations)
+
+
+def loadGeneOntology(db, goPath, goDefPath):
+    hsGenome = Genome("hsapiens", dbFile=db)
+    goDefFile = open(goDefPath, "r")
+    goFile = open(goPath, "r")
+    idb = geneinfoDB()
+    goDefs = {}
+    goArray = []
+    for goDefEntry in goDefFile:
+        if goDefEntry[0] != "!":
+            cols = goDefEntry.split("\t")
+            goDefs[cols[0]] = (cols[1], cols[2].strip())
+
+    prevGID = ""
+    index = 0
+    for entry in goFile:
+        try:
+            fields = entry.split("\t")
+            if fields[0] != "9606":
+                continue
+
+            index += 1
+            if index % 1000 == 0:
+                print "adding 1000 go entries"
+                hsGenome.addGoInfoBatch(goArray)
+                goArray = []
+
+            locID = fields[1].strip()
+            gID = ("hsapiens", locID)
+            if prevGID != gID:
+                prevGID = gID
+                gene_name = ""
+                synonyms = idb.geneIDSynonyms(gID)
+                if len(synonyms) >0:
+                    for entry in synonyms:
+                        gene_name += ","    
+                        gene_name += entry
+                else:
+                    gene_name = " "
+
+            goArray.append((gID, fields[2], "", gene_name[1:], "", string.replace(goDefs[fields[2]][0], "'", "p"), goDefs[fields[2]][1], ""))
+        except:
+            print "locus ID %s could not be added" % locID
+            pass
+
+    print "adding %d go entries" % len(goArray)
+    hsGenome.addGoInfoBatch(goArray)
+
+
+def createDBFile(db):
+    hsGenome = Genome("hsapiens",  dbFile=db)
+    hsGenome.createGeneDB(db)
+
+
+def createDBindices(db):
+    hsGenome = Genome("hsapiens", dbFile=db)
+    hsGenome.createIndices()
+
+
+def buildHsapiensDB(db=geneDB, downloadDir="%s/download" % cisRoot):
+    genePath = "%s/seq_gene.md" % downloadDir # ftp://ftp.ncbi.nih.gov/genomes/H_sapiens/mapview/seq_gene.md.gz
+    goDefPath = "%s/GO.terms_and_ids" % downloadDir # ftp://ftp.geneontology.org/go/doc/GO.terms_and_ids
+    goPath = "%s/gene2go" % downloadDir # ftp://ftp.ncbi.nih.gov/gene/gene2go.gz
+    # chromosomes are from UCSC - will ignore all the alternative haplotypes, chrUn, and random chromosomes
+    chromDict = {"1": "%s/chr1.fa" % downloadDir,
+                 "2": "%s/chr2.fa" % downloadDir,
+                 "3": "%s/chr3.fa" % downloadDir,
+                 "4": "%s/chr4.fa" % downloadDir,
+                 "5": "%s/chr5.fa" % downloadDir,
+                 "6": "%s/chr6.fa" % downloadDir,
+                 "7": "%s/chr7.fa" % downloadDir,
+                 "8": "%s/chr8.fa" % downloadDir,
+                 "9": "%s/chr9.fa" % downloadDir,
+                 "10": "%s/chr10.fa" % downloadDir,
+                 "11": "%s/chr11.fa" % downloadDir,
+                 "12": "%s/chr12.fa" % downloadDir,
+                 "13": "%s/chr13.fa" % downloadDir,
+                 "14": "%s/chr14.fa" % downloadDir,
+                 "15": "%s/chr15.fa" % downloadDir,
+                 "16": "%s/chr16.fa" % downloadDir,
+                 "17": "%s/chr17.fa" % downloadDir,
+                 "18": "%s/chr18.fa" % downloadDir,
+                 "19": "%s/chr19.fa" % downloadDir,
+                 "20": "%s/chr20.fa" % downloadDir,
+                 "21": "%s/chr21.fa" % downloadDir,
+                 "22": "%s/chr22.fa" % downloadDir,
+                 "X": "%s/chrX.fa" % downloadDir,
+                 "Y": "%s/chrY.fa" % downloadDir
+    }
+    
+    print "Creating database %s" % db
+    createDBFile(db)
+    
+    print "Adding gene entries"
+    loadGeneEntries(db, genePath, chromDict)
+    
+    print "Adding gene features"
+    loadGeneFeatures(db, genePath, chromDict)
+    
+    print "Adding gene annotations"
+    loadGeneAnnotations(db)
+    
+    print "Adding gene ontology"
+    loadGeneOntology(db, goPath, goDefPath)
+    
+    for chromID in chromDict.keys():
+        print "Loading chromosome %s" % chromID
+        loadChromosome(db, chromID, chromDict[chromID], "/H_sapiens/chromo%s.bin" % chromID)
+    
+    print "Creating Indices"
+    createDBindices(db)
+    
+    print "Finished creating database %s" % db