def processSummary(con):
myReader = summary.Reader(open(sys.argv[2], 'rb'))
gene = None
ffold = 0
snps = 0
introns = []
exons = []
exon = []
intron = []
for site in myReader:
if isCoding(myReader, site):
if gene == None: #get the gene ID
try:
res = con.execute(
"SELECT gene_id FROM genes WHERE scaf=%s AND (start=%s OR stop=%s)"
% (site.CHROM, site.POS, site.POS))
gene = res[0]
except sqlite3.Error, e:
sys.stderr.write(
"Database Error: %s\nCould not get gene ID for gene at %s %s."
% (e.args[0], site.CHROM, site.POS))
if site.ALT_NUM > 0:
snps += 1
if myReader.TypeToCode['4fold'] in site.Types:
ffold += 1
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"))
div = pickle.load(open(sys.argv[2], "rb"))
print(summaryReader.Header)
#read the infile file...
for site in summaryReader:
if div.has_key(site.CHROM):
try:
site.DIVERGENCE = div[site.CHROM][site.POS]
except IndexError:
sys.stderr.write(
"No divergence for site %s %s in divergence file. Assigning a -1.\n"
% (site.CHROM, site.POS))
site.DIVERGENCE = -1
else:
sys.stderr.write(
"No divergence for site %s %s in divergence file (Missing CHROM in divergence). Assigning a -1.\n"
% (site.CHROM, site.POS))
site.DIVERGENCE = -1
print(site)
def __main__():
processArgs()
hapcutReader = hapcut.Reader(open(_args.hapcut))
summaryReader = summary.Reader(open(_args.summary))
myGenerator = getNextBlock(hapcutReader)
block = myGenerator.next()
pSite = None
#print(summaryReader.Genotypes)
for site in summaryReader:
if site.CHROM != block.chrom:
sys.stderr.write(
"Not on the correct chromosome. Skipping ahead. (Summary: %s Haplotype: %s)\n"
% (site.CHROM, block.chrom))
continue
if site.POS >= block.start and site.POS <= block.end and _args.name in site.Genotypes.keys(
): #within the block
#add the site to the haplotypes
#sys.stderr.write("WITHIN BLOCK %s %s.\n" % (site.CHROM, site.POS))
#sys.stderr.write("%s %s\n" % (block.start, block.end))
#sys.stderr.write("%s %s %s\n" % (site.CHROM, site.POS ,"".join(block.haplotype1)))
#sys.stderr.write("%s\n" % summaryReader.Genotypes[site.Genotypes[_args.name]])
if site.POS in block.SNPs:
#site already phased NOTE the same qual cutoffs may NOT have happened here
continue
if len(site.REF) > 1 or len(site.ALT) > 1:
block.addSNP(site.CHROM, site.POS, "N", "N", 1, 0, 0)
if summaryReader.Genotypes[site.Genotypes[
_args.name]] == "heterozygote":
block.addSNP(site.CHROM, site.POS, "N", "N", 1, 0, 0)
elif summaryReader.Genotypes[site.Genotypes[
_args.name]] == "homozygote reference":
block.addSNP(site.CHROM, site.POS, site.REF, site.ALT, 0, 0, 0)
elif summaryReader.Genotypes[site.Genotypes[
_args.name]] == "homozygote alternate":
block.addSNP(site.CHROM, site.POS, site.REF, site.ALT, 1, 1, 0)
else: #N
continue
#sys.stderr.write("%s %s %s\n" % (site.CHROM, site.POS, "".join(block.haplotype1)))
if site.POS == block.end: #output this block
outputBlock(block)
block = myGenerator.next()
if block == None:
break
if site.POS > block.end: #we missed something
#add N's to fill it out
fillN(block, pSite, site.POS)
outputBlock(block)
block = myGenerator.next()
if block == None:
break
pSite = site.POS
def __main__():
#check aruguments
if len(sys.argv) == 1:
details()
sys.exit()
if len(sys.argv) < 2:
usage()
processArgs(2)
reader = summary.Reader(open(sys.argv[1], "rb"))
afs = [0] * (_N + 1)
div = [0, 0] #checked, diverged
start = 0
pSite = 0
header = "chrom\tstart\tstop\tlen\tdivergenceSites\tdivergence\tafs_"
for i in range(_N + 1):
header += str(i) + "\tafs_"
header = header[:-4]
print(header)
for record in reader:
if _v: sys.stderr.write("On line:\t%s\n" % record.prettyStr())
if 'intron' in record.typeNames():
if start == 0:
if _v:
sys.stderr.write("Start intron: %s.\n" %
record.prettyStr())
start = record.POS
pSite = record.POS
if record.TOTAL != _N:
continue
afs[record.ALT_NUM] += 1
if record.DIVERGENCE != -1:
div[0] += 1
if record.DIVERGENCE:
div[1] += 1
elif pSite != 0:
if _v:
sys.stderr.write("End of intron at %s.\n" %
(record.prettyStr()))
#scaf, start, stop, length, divergenceChecked, divergence, afs
afsStr = "\t".join(map(str, afs))
print("%s\t%s\t%s\t%s\t%s\t%s\t%s" %
(record.CHROM, start, pSite, pSite - start, div[0], div[1],
afsStr))
pSite = 0
start = 0
afs = [0] * (_N + 1)
div = [0, 0]
def __main__():
mySum = summary.Reader(open(sys.argv[1],'rb'))
out = open(sys.argv[2],'w')
#out.write("pac piS piN Ssite# Nsite#\n")
myTest = sys.argv[3]
processArgs(4)
count = _d
siteDic = mySum.summary.typesAsInt()
if myTest == "sfs":
sfs(mySum, out, count, siteDic)
elif myTest == "dfealpha":
dfealpha(mySum, out, count, siteDic)
elif myTest == "diversity":
diversity(mySum, out, count, siteDic)
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], "r"))
regions = open(sys.argv[2], "r")
#read the regions
#regions{IND{SCAF{(start, end)}}}
regionsList = {}
for ind in summaryReader.summary.Samples:
regionsList[ind] = {}
for line in regions:
line = line.rstrip()
sline = line.split()
if line.startswith("CHROM"):
continue
if len(sline) != 4:
sys.stderr.write("Weird line:\n\t%s\n" % line)
continue
chrom = sline[0]
start = int(sline[1])
end = int(sline[2])
ind = sline[3]
if chrom in regionsList[ind].keys():
regionsList[ind][chrom].append((start, end))
else:
regionsList[ind][chrom] = [(start, end)]
header = summaryReader.summary.prettyHeader()
header = header[0:header.index("DIVERGENCE") + 10]
print(header)
genoReverse = {v: k for k, v in summaryReader.summary.Genotypes.items()}
#read the infile file...
for site in summaryReader:
ibdInds = getUnsafeInds(site, regionsList)
#print("%s %s" % (site.POS, ibdInds))
alleles = []
for ind in site.Genotypes.keys():
if ind in ibdInds:
if site.Genotypes[ind] == genoReverse["homozygote reference"]:
alleles.append(site.REF)
elif site.Genotypes[ind] == genoReverse[
"homozygote alternate"]:
alleles.append(site.ALT)
elif site.Genotypes[ind] == genoReverse[
"heterozygote"]: #assume ref for all IBD individuals with data
alleles.append(site.REF)
elif site.Genotypes[ind] == genoReverse["unknown"]:
alleles.append(genoReverse["unknown"])
else:
if site.Genotypes[ind] == genoReverse["homozygote reference"]:
alleles.append(site.REF)
alleles.append(site.REF)
elif site.Genotypes[ind] == genoReverse[
"homozygote alternate"]:
alleles.append(site.ALT)
alleles.append(site.ALT)
elif site.Genotypes[ind] == genoReverse["heterozygote"]:
alleles.append(site.REF)
alleles.append(site.ALT)
elif site.Genotypes[ind] == genoReverse["unknown"]:
alleles.append(genoReverse["unknown"])
alleles.append(genoReverse["unknown"])
newAlleles = random.sample(alleles, _N)
ref = newAlleles.count(site.REF)
alt = newAlleles.count(site.ALT)
site.REF_NUM = ref
site.ALT_NUM = alt
if site.TOTAL != 0: #if total was 0 for some reason, like being filtered, keep it that way
site.TOTAL = ref + alt
site.Genos = []
print(site)
def __main__():
#check aruguments
if len(sys.argv) == 1:
details()
sys.exit()
if len(sys.argv) < 2:
usage()
processArgs(2)
args = {
"fraction coding": _c,
"window size": _w,
"sample size": _N,
"region output file": _o
}
argStr = ""
for arg in args.keys():
argStr += ("#%s\t%s\n" % (arg, args[arg]))
sys.stderr.write(argStr)
myReader = summary.Reader(open(sys.argv[1], "rb"))
codingN = []
for t in _coding:
if t in myReader.TypeToCode.keys():
codingN.append(myReader.TypeToCode[t])
codingN = set(codingN)
ncodingN = []
for t in _ncoding:
if t in myReader.TypeToCode.keys():
ncodingN.append(myReader.TypeToCode[t])
ncodingN = set(ncodingN)
if _o:
filteredRegions = open(_o, "w")
else:
filteredRegions = None
window = []
safe_sites = 0.0
print(myReader.Header)
pScaf = ""
#read the infile file...
for site in myReader:
if pScaf == "":
site.CHROM
if (len(window) == _w or pScaf != site.CHROM) and window:
processWindow(window, safe_sites, filteredRegions)
window = []
safe_sites = 0.0
#check if all individuals are represented
if site.TOTAL == _N:
safe_sites += 1
#check if a site is both a coding site and a noncoding site
#if it is, make the site not safe, set type to unknown
safe = True
if len(set(site.Types) & codingN) and len(set(site.Types) & ncodingN):
safe = False
if not safe:
site.Types = [myReader.TypeToCode['unknown']]
window.append(site)
pScaf = site.CHROM
processWindow(window, safe_sites, filteredRegions) #get the last window
if _o: filteredRegions.close()
def __main__():
#check aruguments
if len(sys.argv) == 1:
details()
sys.exit()
if len(sys.argv) < 2:
usage()
processArgs(2)
if _N % 2 == 0:
folded_size = int(_N / 2 + 1)
else:
folded_size = int(ceil(float(_N) / 2))
summaryReader = summary.Reader(open(sys.argv[1], "rb"))
#read the infile file...
lastGeneSite = None # only count exon, 4, and 0 fold sites
currentCNCs = [] # list of tuples (start, stop, div, pi)
cncStart = None #start of current stretch of CNCs
cncDiv = 0
cncDivTot = 0
cncWindow = []
pScaf = None
pSite = None
geneTypes = [
summaryReader.summary.typeToCode['exon'],
summaryReader.summary.typeToCode['4fold'],
summaryReader.summary.typeToCode['0fold']
]
cncTypes = [summaryReader.summary.typeToCode['cnc']]
for t in _t:
cncTypes.append[summaryReader.summary.typeToCode[t]]
print("CHROM\tCNC_START\tCNC_END\tCNC_DIV\tCNC_PI\tUP_DIST\tDOWN_DIST")
for site in summaryReader:
if pScaf == None:
pScaf = site.CHROM
if pScaf != site.CHROM: #on next scaf, clean up
if cncStart != None: #end CNC at last site
if cncDivTot:
div = float(cncDiv) / cncDivTot
else:
div = "NA"
pi = calcPi(cncWindow)
currentCNCs.append((cncStart, pSite, div, pi))
outputCNCs(pScaf, currentCNCs, lastGeneSite, None)
cncStart = None
cncWindow = []
cncDiv = 0
cncDivTot = 0
currentCNCs = []
pScaf = site.CHROM
if isCNC(cncTypes, site.Types):
if cncStart == None:
cncStart = site.POS
if site.REF_NUM + site.ALT_NUM != _N or site.TOTAL != _N:
sys.stderr.write("Bad data at site %s %s, ignoring it.\n" %
(site.CHROM, site.POS))
cncWindow.append(site.REF_NUM)
if site.DIVERGENCE == 1:
cncDiv += 1
cncDivTot += 1
elif site.DIVERGENCE == 0:
cncDivTot += 1
elif isGene(geneTypes, site.Types):
if cncStart != None:
if cncDivTot:
div = float(cncDiv) / cncDivTot
else:
div = "NA"
pi = calcPi(cncWindow)
currentCNCs.append((cncStart, pSite, div, pi))
cncStart = None
cncWindow = []
cncDiv = 0
cncDivTot = 0
if currentCNCs:
outputCNCs(pScaf, currentCNCs, lastGeneSite, site.POS)
currentCNCs = []
lastGeneSite = site.POS
else:
if cncStart != None:
if cncDivTot:
div = float(cncDiv) / cncDivTot
else:
div = "NA"
pi = calcPi(cncWindow)
currentCNCs.append((cncStart, pSite, div, pi))
cncStart = None
cncWindow = []
cncDiv = 0
cncDivTot = 0
pSite = site.POS
import sys
import summary
reader = summary.Reader(open(sys.argv[1]))
_w = int(sys.argv[2])#this is a dumb way to do this!
print(reader.Header)
prev = []
skip = 0
for record in reader:
dup = False
#sys.stderr.write("Checking %s %s.\n"%(skip,record))
if prev and record.POS == prev[-1].POS:#reached an indel
#do stuff to fix it
#clear the buffer, because we're skipping stuff
for r in prev:
r.TOTAL = 0
#is it an deletion
if len(record.REF) > 1:
skip = len(record.REF)+_w
else:#it is an insertion
skip = _w
#DONOT add this record to the list, because it is a duplicate
#the previous non-indel version is already in there with a total of 0
dup = True
if len(prev) == _w+1:#+1 because we want to keep one mroe than window size, to throw out the duplicate site too
print(prev.pop(0))
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"))
if _t not in summaryReader.Types:
intCodes = map(int, summaryReader.Codes)
summaryReader.addCode(max(intCodes) + 1, _t)
print(summaryReader.Header)
sites = open(sys.argv[2], "r")
if (sites == None):
print("Bad sites file name: " + sys.argv[1])
sys.exit()
next_site = getNextSite(sites)
#read the infile file...
for site in summaryReader:
if next_site == (None, None): #print the remaining sites
if _d and summaryReader.TypeToCode[_t] in site.Types:
site.Types.remove(summaryReader.TypeToCode[_t])
site.Types.append(0)
print(site)
continue
while next_site[0] != None and site.CHROM > next_site[
0]: #we missed this site
sys.stderr.write("Missed a site (CHROM): " + str(next_site) + "\n")
next_site = getNextSite(sites)
if next_site == (None, None):
sys.stderr.write("Ran out of sites\n")
if _d and summaryReader.TypeToCode[_t] in site.Types:
site.Types.remove(summaryReader.TypeToCode[_t])
site.Types.append(0)
print(site)
continue
if site.CHROM < next_site[
0]: #we havent found the right scaf yet, go to the next site.
if _d and summaryReader.TypeToCode[_t] in site.Types:
site.Types.remove(summaryReader.TypeToCode[_t])
site.Types.append(0)
print(site)
continue
#on the right scaf, now deal with pos info
while next_site[1] != None and site.POS > next_site[
1]: #we missed a site WARNING, this while loop could bring us to the next chromosome....
sys.stderr.write("Missed a site (POS): " + str(next_site) + "\n")
next_site = getNextSite(sites)
if next_site[1] > site.POS: #haven't reached the site yet
if _d and summaryReader.TypeToCode[_t] in site.Types:
site.Types.remove(summaryReader.TypeToCode[_t])
site.Types.append(0)
print(site)
continue
if next_site == (None, None):
sys.stderr.write("Ran out of sites\n")
if _d and summaryReader.TypeToCode[_t] in site.Types:
site.Types.remove(summaryReader.TypeToCode[_t])
site.Types.append(0)
print(site)
continue
if next_site[1] == site.POS: #at the site
if _r:
for r in _r:
if summaryReader.TypeToCode[r] in site.Types:
site.Types.remove(summaryReader.TypeToCode[r])
site.Types.append(summaryReader.TypeToCode[_t])
print(site)
next_site = getNextSite(sites)
# gffDic[i] = [0]*2000
#make a dic of all the gene locations
geneFile = open(sys.argv[2],'r')
#geneFile = open('../test_gff_gene_flatfile','r')
for line in geneFile:
scaf, gene, start, end = line.split()
scafNum = int(scaf.split('_')[1])
for i in range(int(start), int(end)+1): #not that worried about 0 or 1 based coordinates because we're only dealing with 0 and 4 fold sites.
gffDic[scafNum][i] = gene
geneFile.close()
#myOut = open('../../0fold4fold.withgenes.summary','w'))
#sumRead = summary.Reader(open('/data/youngwha.lee/189_genomes/UG_all_vars/recal_vcfs/vcfsummaries/downsampled320/sc8_down_320_4','rb'))
sumRead = summary.Reader(open(sys.argv[1],'rb'))
sumRead.addGenes()
print(sumRead.Header)
for site in sumRead:
if gffDic[int(site.CHROM.split('_')[1])][site.POS] == 0: #not in a gene?
sys.stderr.write("err not in gene "+site.prettyStr()+"\n")
continue
else:
geneName = gffDic[int(site.CHROM.split('_')[1])][site.POS]
site.GENE = geneName
print(site)
#print(" ".join([site.__str__(),geneName,"NA"]))
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],"r"))
sites = open(sys.argv[2],"r")
summaryReader.addGenes()
print(summaryReader.Header)
next_site = getNextSite(sites)
#read the infile file...
for site in summaryReader:
if next_site == (None, None, None, None, None):#print the remaining sites
site.GENE = "N"
site.DIR = "0"
print(site)
continue
while next_site[0] != None and site.CHROM > next_site[0]:#we missed this site
sys.stderr.write("Missed a site (CHROM): %s %s\n" % (next_site[0], next_site[1]))
next_site = getNextSite(sites)
if next_site == (None, None, None, None, None):
site.GENE = "N"
site.DIR = "0"
print(site)
continue
if site.CHROM < next_site[0]:#we havent found the right scaf yet, go to the next site.
site.GENE = "N"
site.DIR = "0"
print(site)
continue
#on the right scaf, now deal with pos info
while next_site[1] != None and site.POS > next_site[1]:#we missed a site WARNING, this while loop could bring us to the next chromosome....
sys.stderr.write("Missed a site (POS): "+str(next_site)+"\n")
next_site = getNextSite(sites)
if next_site[1] > site.POS:#haven't reached the site yet
site.GENE = "N"
site.DIR = "0"
print(site)
continue
if next_site == (None, None, None, None, None):
site.GENE = "N"
site.DIR = "0"
print(site)
continue
if next_site[1] == site.POS:#at the site
site.GENE = next_site[3]
site.DIR = next_site[4]
print(site)
next_site = getNextSite(sites)
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
def __main__():
#check aruguments
if len(sys.argv) == 1:
details()
sys.exit()
if len(sys.argv) < 2:
usage()
processArgs(2)
reader = summary.Reader(open(sys.argv[1], 'rb'))
if not "GENE" in reader.summary.Fields:
sys.stderr.write(
"Your summary does not have gene names. Please add gene info to this summary and try again.\n"
)
sys.exit()
myHeader = "GENE DIR IntronNum IntronLen Window CNCnum "
for i in range(int(floor(_N / 2.0) + 1)):
myHeader += "afs_%s " % i
print(myHeader)
currentGene = ""
dir = ""
introns = []
currentIntronAF = []
currentIntronCNC = []
if _v: sys.stderr.write("Reading in Summary...\n")
for record in reader:
if record.GENE != "N": #we are in a gene
if record.GENE != currentGene and currentGene != "N": #finish off the previous gene
if currentIntronAF:
introns.append(zip(currentIntronAF, currentIntronCNC))
processGene(currentGene, dir, introns)
currentGene = record.GENE
dir = record.DIR
introns = []
currentIntronAF = []
currentIntronCNC = []
elif not currentGene: #start this new gene
currentGene = record.GENE
dir = record.DIR
introns = []
currentIntronAF = []
currentIntronCNC = []
if reader.TypeToCode[_intron] in record.Types: #in an intron
if record.TOTAL == _N:
currentIntronAF.append(min(record.REF_NUM, record.ALT_NUM))
else: #no data
currentIntronAF.append(-1)
if reader.TypeToCode[_cnc] in record.Types: #also a CNC site
currentIntronCNC.append(1)
else: #not a CNC
currentIntronCNC.append(0)
else: #not in an intron
if currentIntronAF: #we have passed the previous intron
introns.append(zip(currentIntronAF, currentIntronCNC))
currentIntronAF = []
currentIntronCNC = []
else: #we arent in a gene
if currentGene and currentGene != "N":
if currentIntronAF:
introns.append(zip(currentIntronAF, currentIntronCNC))
processGene(currentGene, dir, introns)
currentGene = ""
dir = ""
introns = []
currentIntronAF = []
currentIntronCNC = []
if introns: #get the last set of introns, if any
if currentIntronAF:
introns.append(zip(currentIntronAF, currentIntronCNC))
processGene(currentGene, dir, introns)
def __main__():
#check aruguments
processArgs()
summaryReader = summary.Reader(open(_args.summary, "rb"))
#dictionary of site codes
#types = {'0fold': 3, 'stop': 8, 'intergene': 0, '5utr': 6, '3utr': 5, 'exon': 2, 'intron': 1, 'istop': 7, '4fold': 4, 'unknown': 9, 'cnc':10}
#reverse_types = {v:k for k, v in types.items()}
#Read in the file and build the regions of each size. Calculate the local AFS for each region.
if _args.sample_size % 2 == 0:
folded_size = int(_args.sample_size / 2 + 1)
else:
folded_size = int(ceil(float(_args.sample_size) / 2))
regions = {}
i = -1
currscaf = None
afs = resetAFS({}, summaryReader.summary.typeToCode, folded_size)
div = resetAFS(
{}, summaryReader.summary.typeToCode, 2
) #just makes a dictionary for each type with a list of length 2, store num sites and num div sites
added = 0
for site in summaryReader: #"#CHROM\tPOS\tREF\tALT\tREF_NUMBER\tALT_NUMBER\tTOTAL\tSITE_TYPE")
if currscaf == None:
currscaf = site.CHROM
#if i == -1:#start the window at the first site we have
# i = site.POS
if added >= _args.window or currscaf != site.CHROM:
#if site.POS >= i+_args.window or currscaf != site.CHROM:
regions[currscaf + "_" + str(site.POS)] = (afs, div)
afs = resetAFS({}, summaryReader.summary.typeToCode, folded_size)
div = resetAFS({}, summaryReader.summary.typeToCode, 2)
# i += _args.window
added = 0
if currscaf != site.CHROM:
currscaf = site.CHROM
if site.TOTAL != _args.sample_size or site.TOTAL != site.REF_NUM + site.ALT_NUM: #not enough alleles at this locus, or total is wrong (filtered data)
sys.stderr.write(
"Skipping site, either not enough alleles or the total number of alleles does not match the sum of alleles.\n\t%s\n"
% site)
continue
af = min(site.REF_NUM, site.ALT_NUM)
#if in SNP mode only add to the window size if we are not at a fixed site
if af != 0 and af != 1:
added += 1
elif not _args.snps:
added += 1
for t in site.Types:
if t not in afs.keys():
sys.stderr.write("Weird site type encountered: \n\t" +
str(site) + "\n")
continue
afs[t][af] += 1
#store divergence info for the window
if site.DIVERGENCE != -1:
div[t][0] += 1
if site.DIVERGENCE == 1:
div[t][1] += 1
#this is commented out because the last region is usually not long enough to be useful
#regions[currscaf+"_"+str(i)] = (afs, div)#store the last region
#make sure all wanted types are actually present
safe = []
for w in _args.site_types:
if w in summaryReader.summary.Types.keys():
safe.append(w)
else:
sys.stderr.write(
"Wanted type not present in codes: %s. Excluding it from analysis.\n"
% w)
_args.site_types = safe
counts = resetAFS({}, summaryReader.summary.typeToCode, 1)
for r in regions.values():
for t in summaryReader.summary.Types.keys():
counts[t][0] += sum(r[0][t])
sys.stderr.write("Numbers of each site type in whole analysis:\n")
for t, val in summaryReader.summary.typeToCode.items():
sys.stderr.write("%s %s\n" % (t, counts[val][0]))
region_names = list(regions.keys())
num_regions = len(region_names)
#print out the non-bootstrapped afs
output_bootstrap(summaryReader.summary.typeToCode,
summaryReader.summary.Types, folded_size, region_names,
regions, "real")
#perform the bootstraps
for i in range(_args.bootstraps):
boot_regions = []
while len(boot_regions) < num_regions:
boot_regions.append(choice(region_names))
#output the AFS for this bootstrap
output_bootstrap(summaryReader.summary.typeToCode,
summaryReader.summary.Types, folded_size,
boot_regions, regions, str(i))
def main():
reader = summary.Reader(open(args.summary, 'rb'))
if reader.summary.Samples:
N = reader.summary.Ploidy * len(reader.summary.Samples)
elif not args.sample_size:
sys.stderr.write(
"No samples listed in this summary. You must provide a sample size with -N.\n"
)
sys.exit()
else:
N = args.sample_size
genAFS = lambda: [0] * (N + 1)
if "GENE" not in reader.summary.Fields:
sys.stderr.write(
"The gene names are not in this summary. All gene names will be blank if you use this file.\n"
)
try:
intronCode = reader.summary.typeToCode['intron']
except KeyError:
sys.stderr.write(
"Summary has no 'intron' codes, you need to add them or use a different summary.\n"
)
sys.exit()
#output header
outputIntron(N=N)
currentIntron = None
for record in reader:
if intronCode in record.Types:
if not currentIntron:
#new one
currentIntron = Intron(record.GENE, record.CHROM, record.POS,
genAFS())
elif currentIntron.gene != record.GENE:
#end of previous one, we're on a new one
#this should really not happen
sys.stderr.write(
"Reached a new intron adjacent to an old one at %s %s, you may want to check your annotation.\n"
% (record.CHROM, record.POS))
outputIntron(N, currentIntron)
currentIntron = Intron(record.GENE, record.CHROM, record.POS,
genAFS())
# print(record.POS, currentIntron.afs)
#doesn't count AF at sites with too few alleles
if record.TOTAL == N:
try:
currentIntron.afs[record.ALT_NUM] += 1
except IndexError:
sys.stderr.write(
"At %s %s there is a problem with the ALT_NUM. It is out of acceptable ranges. Is there a problem with your summary? Or with the provided sample size?\n"
% (record.CHROM, record.POS))
currentIntron.end = record.POS
elif currentIntron:
#we reached the end on this one
outputIntron(N, currentIntron)
currentIntron = None
#get the last one
if currentIntron:
outputIntron(N, currentIntron)
def __main__():
#check aruguments
if len(sys.argv) == 1:
details()
sys.exit()
if len(sys.argv) < 2:
usage()
processArgs(2)
summaryReader = summary.Reader(open(sys.argv[1], "rb"))
global _t
safeT = []
myCounts = {}
for t in _t:
if t not in summaryReader.summary.typeToCode.keys():
sys.stderr.write(
"Type %s not found in summary. It will be ignored. The valid options are: %s.\n"
% (t, summaryReader.summary.typeToCode.keys()))
else:
safeT.append(summaryReader.summary.typeToCode[t])
myCounts[summaryReader.summary.typeToCode[t]] = []
_t = safeT
if len(_t) == 0:
sys.stderr.write(
"No valid types to count were provided. Use the -t option to specify sites of interest.\n"
)
sys.exit(0)
start = None
pScaf = None
pSite = None
print("TYPE\tCHROM\tMIDPOINT\tCOUNT")
#read the infile file...
for site in summaryReader:
if start == None:
start = site.POS
pScaf = site.CHROM
pSite = site.POS
if pScaf != site.CHROM:
printWindow(myCounts, summaryReader.summary, (pSite + start) / 2.0,
pScaf)
for t in _t:
myCounts[t] = []
start = site.POS
pScaf = site.CHROM
if site.POS - start >= _w:
printWindow(myCounts, summaryReader.summary,
(site.POS + start) / 2.0, pScaf)
for t in _t:
myCounts[t] = []
start = site.POS
for t in _t:
if t in site.Types:
myCounts[t].append(1)
else:
myCounts[t].append(0)
pSite = site.POS
printWindow(myCounts, summaryReader.summary, (pSite - start) / 2.0, pScaf)