def __main__():
#check aruguments
if len(sys.argv) == 1:
details()
sys.exit()
if len(sys.argv) < 3:
usage()
f = "first_introns.sites"
n = "nonfirst_introns.sites"
try:
opts, args = getopt.getopt(sys.argv[3:], "f:n:")
except getopt.GetoptError:
usage()
for opt, arg in opts:
if opt == "-f":
f = arg
elif opt == "-n":
n = arg
else:
print("Unrecognized option: " + opt + "\n")
usage()
first = open(f, "w")
nonfirst = open(n, "w")
annot = annotation.Reader(open(sys.argv[1], "rb"))
divergence = pickle.load(open(sys.argv[2], "rb"))
print("Gene\tIntronNum\tIntronLen\tSitesTot\tDiverged")
for gene in annot:
#print gene_name intron_number intron_length site_count divergence_count
#sys.stderr.write(gene)
introns = gene.makeIntrons()
for j, intron in enumerate(introns):
#sys.stderr.write(intron)
siteCount = 0
divCount = 0
for i in range(intron[0], intron[1] + 1):
div = divergence[i][2] #get the flag indicating divergence
if div == None:
sys.stderr.write("NO DATA: " + str(i) + "\n")
continue
siteCount += 1
if not div:
divCount += 1
if j == 0: #a first intron
first.write(gene.scaf + "\t" + str(i) + "\n")
else:
nonfirst.write(gene.scaf + "\t" + str(i) + "\n")
print(gene.name + "\t" + str(j) + "\t" +
str(intron[1] - intron[0] + 1) + "\t" + str(siteCount) +
"\t" + str(divCount))
def processAnnotation(con):
reader = annotation.Reader(open(sys.argv[2], 'rb'))
genes = []
for gene in reader:
gene.sortExons()
vals = "\'%s\', \'%s\',\'%\s\', %s, %s, 0" % (
gene.name, gene.scaf, gene.direction, gene.start, gene.end)
genes.append(vals)
con.executemany(
"INSERT INTO genes (name, scaffold, direction, start, stop, expression) VALUES (?, ?, ?, ?, ?, ?)",
genes)
def __main__():
if len(sys.argv) == 1:
details()
sys.exit()
processArgs(3)
#initialize my parsers
annotation_reader = annotation.Reader(open(sys.argv[1], 'rb'))
if not _r:
reader = vcf.Reader(open(sys.argv[2], 'rb'))
names = reader.samples
else:
reader = pileup.Reader(open(sys.argv[2], 'rb'))
names = ["outgroup"]
annotation_iter = annotation_reader.__iter__()
#pull my first gene
next_gene = getNextGene(annotation_iter)
if next_gene == None: #No genes = done
sys.stderr.write("No valid genes in annotation. Exiting.\n")
sys.exit(0)
exons = next_gene.exons
last_site = -1
myFasta = Fasta(names)
for record in reader:
indel = 0
#if we're out of exons get the next gene
if len(exons) == 0:
myFasta.writeFasta(next_gene.name, next_gene.start, next_gene.end,
next_gene.direction)
next_gene = getNextGene(annotation_iter)
while next_gene != None and next_gene.start < record.POS:
sys.stderr.write("Gene missed, read in gene at POS = " +
str(record.POS) + "\n\t" + str(next_gene) +
"\n")
next_gene = getNextGene(annotation_iter)
if next_gene == None: #no more genes
break
exons = next_gene.exons
myFasta = Fasta(names) #reset our fasta data
if not _r and 'Dels' in record.INFO.keys() and record.INFO[
'Dels'] > _i: #if this site has some probability of having an INDEL
indel = 1
#TODO check reference for deletions
if record.POS < next_gene.start: #if we haven't reached the next gene yet
continue
if record.POS >= exons[0][
0]: #if we're past the beginning of the next exon
if (last_site != -1 and last_site != record.POS - 1) or (
last_site == -1 and exons[0][0] != record.POS):
#if we missed some sites in the middle
#OR
#if we missed sites at the beginning of a gene
num = myFasta.fillRemainder(
max(last_site, exons[0][0]),
record.POS) #fill in any missing sites with N
#WARNING: if an exon starts right after another ended then this will N the first base in the new exon
if _v and num > 0:
sys.stderr.write(
"'N'ed " + str(num) +
" sites because we missed the beginning of an exon, or something in the middle\n\t"
+ str(record))
if record.POS <= exons[0][1]: #if we're within the current exon
processSite(record, myFasta, indel, next_gene.direction)
last_site = record.POS
else: #this exon is done
num = myFasta.fillRemainder(
max(last_site, exons[0][0]),
exons[0][1]) #fill in any missing sites with N
if _v and num > 0:
sys.stderr.write(
"'N'ed " + str(num) +
" sites because we have passed the end of the exon\n\t"
+ str(record))
last_site = -1 #we finished this exon
exons.pop(0)
if next_gene != None: #finish the last gene with N's
for exon in exons:
myFasta.fillRemainder(last_site, exon)
myFasta.writeFasta(next_gene.name, next_gene.start, next_gene.end,
next_gene.direction)
def __main__():
#check aruguments
if len(sys.argv) == 1:
details()
sys.exit()
if len(sys.argv) < 3:
usage()
processArgs(3)
summaryReader = summary.Reader(open(sys.argv[1], "rb"))
annotationReader = annotation.Reader(open(sys.argv[2], "rb"))
annotIter = annotationReader.__iter__()
myGene = getNextGene(annotIter)
if myGene == None:
sys.stderr.write("No genes listed in annotation. Exiting.\n")
sys.exit(0)
if len(summaryReader.summary.Samples) == 0:
sys.stderr.write(
"No individual genotype info in this Summary file. Cannot make fastas.\n"
)
sys.exit(0)
seqs = {}
for samp in summaryReader.summary.Samples:
seqs[samp] = [[], []]
doneScafs = []
genoDict = {v: k for k, v in summaryReader.summary.Genotypes.items()}
pScaf = ""
pSite = 0
#read the infile file...
for site in summaryReader:
#sys.stderr.write("Processing site %s\n" % site.prettyStr())
if site.CHROM != myGene.scaf:
while myGene.scaf in doneScafs:
sys.stderr.write(
"Missed gene %s on scaf %s. Make sure file is sorted correctly.\n"
% (myGene.name, myGene.scaf))
myGene = getNextGene(annotIter)
for samp in summaryReader.summary.Samples:
seqs[samp] = [[], []]
if site.CHROM != myGene.scaf: #haven't reached this scaf yet, skip along in the summary
continue
if pScaf == "" or pScaf != site.CHROM:
doneScafs.append(pScaf)
pScaf = site.CHROM
pSite = 0
myGene = addNs(seqs, pSite, site.POS, myGene, annotIter)
if myGene == None:
#sys.stderr.write("main 71: ran out of genes. Exiting.\n")
break
if site.POS < myGene.exons[0][0]:
pass
elif site.POS <= myGene.exons[0][1]:
for samp, geno in site.Genotypes.items():
if geno == genoDict['heterozygote']:
seqs[samp][0].append(site.REF)
seqs[samp][1].append(site.ALT)
elif geno == genoDict['homozygote reference']:
seqs[samp][0].append(site.REF)
seqs[samp][1].append(site.REF)
elif geno == genoDict['homozygote alternate']:
seqs[samp][0].append(site.ALT)
seqs[samp][1].append(site.ALT)
else:
seqs[samp][0].append("N")
seqs[samp][1].append("N")
if site.POS >= myGene.exons[0][1]:
myGene.exons.pop(0)
if not myGene.exons:
#print the seqs to a file
outputFasta(myGene, seqs)
#grab new gene
myGene = getNextGene(annotIter)
#check it
if myGene == None:
break
#reset seqs
for samp in summaryReader.summary.Samples:
seqs[samp] = [[], []]
pSite = site.POS