def __init__(self, species, sex, tissue, replicate):
self.species = species
self.sex = sex
self.tissue = tissue
self.replicate = replicate
self.name = species + "_" + sex + "_" + tissue + "_" + replicate
self.filenamePacBioBed = self.name + ".bam.bed"
print("get lines of " + self.filenamePacBioBed)
self.linesPacBioBed = get_lines("../data/pacbio",
self.filenamePacBioBed)
print("get isoseqid to exonlen ...")
self.isoseqid2exonlen, self.isoseqid2line = get_id2exonlen_id2line(
self.linesPacBioBed)
self.filenameAnnotationBedA = self.species + ".genePred.bed"
print("get lines of " + self.filenameAnnotationBedA)
self.linesAnnotationBedA = get_lines("../data/annotation",
self.filenameAnnotationBedA)
print("get gtf's transid to exonlen ...")
self.transidA2exonlen, self.transidA2line = get_id2exonlen_id2line(
self.linesAnnotationBedA)
self.filenameAnnotationBedB = self.species + ".v3.genePred.bed"
print("get lines of " + self.filenameAnnotationBedB)
self.linesAnnotationBedB = get_lines("../data/annotation",
self.filenameAnnotationBedB)
print("get v3.gtf's transid to exonlen ...")
self.transidB2exonlen, self.transidB2line = get_id2exonlen_id2line(
self.linesAnnotationBedB)
self.filenameA = self.name + ".bam.gtf.intersect_gtf"
self.filenameB = self.name + ".bam.gtf.intersect_v3gtf"
print("get lines of " + self.filenameA)
self.linesA = get_lines("../data/pacbio", self.filenameA)
print("get lines of " + self.filenameB)
self.linesB = get_lines("../data/pacbio", self.filenameB)
print("get intersection A info ...")
(self.isoseqid2transidA,
self.transidA2isoseqid) = self.get_intersectinfo("A")
print("get intersection B info ...")
(self.isoseqid2transidB,
self.transidB2isoseqid) = self.get_intersectinfo("B")
self.isoseqid2besttransidA = self.get_isoseqid2besttransid("A")
self.isoseqid2besttransidB = self.get_isoseqid2besttransid("B")
""" get jaccard info such as intersection union jaccard for each isoseqid """
print("get jaccard A info ...")
self.jaccard_infoA = self.get_jaccard_info("A")
print("get jaccard B info ...")
self.jaccard_infoB = self.get_jaccard_info("B")
""" get end info for each isoseqid """
print("get end A info ...")
self.end_infoA = self.get_end_info("A")
print("get end B info ...")
self.end_infoB = self.get_end_info("B")
def __init__(self, sample):
self.sample = sample
self.species, self.sex, self.tissue, self.replicate = self.sample.split(
"_")
self.v3exonmap = self.get_exonmap("v3") # transcript level
self.fbexonmap = self.get_exonmap("fb") # transcript level
self.v3salmonlines = get_lines("../data/salmon/FB2017_03_v3/",
sample + ".salmon.txt")
self.fbsalmonlines = get_lines("../data/salmon/FB2017_03/",
sample + ".salmon.txt")
self.fbsalmon = self.get_fbsalmon()
self.DxxxTID2YOtrID = self.get_DxxxTID2YOtrID()
self.DxxxTID2FBtrID = self.get_DxxxTID2FBtrID()
self.DxxxTID2jaccard = self.get_DxxxTID2jaccard()
def __init__(self, species):
self.species = species
# v3 updated annotation
self.filename = species + ".expression.nrc.tab"
self.lines = get_lines("../data/expression", self.filename)
self.expressionheader, self.geneid2expression = self.get_geneid2expression(
1)
# FB2017_03 old annotation
self.oldfilename = species + ".expression.onrc.tab"
self.oldlines = get_lines("../data/expression", self.oldfilename)
self.oldexpressionheader, self.oldgeneid2expression = self.get_geneid2expression(
0)
def __init__(self, sample):
self.sample = sample
self.species, self.sex, self.tissue, self.replicate = self.sample.split(
"_")
self.v3exonmap = self.get_exonmap("v3")
self.fbexonmap = self.get_exonmap("fb")
self.v3htseqlines = get_lines("../data/htseq/FB2017_03_v3/",
sample + ".htseq_reverse_HiSAT2.txt")
self.fbhtseqlines = get_lines("../data/htseq/FB2017_03/",
sample + ".htseq_reverse_HiSAT2.txt")
self.fbhtseq = self.get_fbhtseq()
self.DxxxGID2YOgnID = self.get_DxxxGID2YOgnID()
self.DxxxGID2FBgnID = self.get_DxxxGID2FBgnID()
self.DxxxGID2jaccard = self.get_DxxxGID2jaccard()
self.update_v3htseq_lines()
def __init__(self, species, sex, tissue):
self.species = species
self.sex = sex
self.tissue = tissue
self.filename = self.species + "_" + sex + "_" + tissue + ".merged.events"
self.lines = get_lines("../data/event", self.filename)
self.eventinfo = self.get_eventinfo()
def __init__(self, species, sex, tissue):
self.species = species
self.sex = sex
self.tissue = tissue
# self.filename = self.species + "_" + sex + "_" + tissue + ".merged.juncs" # spanki juncs
self.filename = self.species + "_" + sex + "_" + tissue + ".sorted.junc.bed"
self.lines = get_lines("../data/junction", self.filename)
self.juncinfo = self.get_juncinfo()
def get_geneidtransid2strand(self):
""" get transid 2 strand """
dct = dict()
for line in get_lines("../data/annotation/", self.species + ".v3.gtf"):
(scaffold, tag, feature, start, end, scoare, strand, dot, others) = line.rstrip().split("\t")
this_geneid = get_id(others, 'gene_id')
this_transid = get_id(others, 'transcript_id')
dct[this_geneid + "|" + this_transid] = strand
return dct
def __init__(self, species, sex, tissue, replicate):
self.species = species
self.sex = sex
self.tissue = tissue
self.replicate = replicate
self.sample = species + "_" + sex + "_" + tissue + "_" + replicate
self.geneidtransid2strand = self.get_geneidtransid2strand()
self.trackinglines = get_lines("../data/pacbio/", "jaccard_zero." + self.sample + ".exon.gtf.tracking")
self.isoseqid2overlaptype = self.get_isoseqid2overlaptype()
def __init__(self, filename):
""" filename example: pacbio_new_gene_model.all_phase_peptide """
self.filename = filename
self.peptidefasta = Fasta("../data/pacbio/" + filename + ".fasta")
print(self.peptidefasta)
self.signalplines = get_lines("../data/pacbio",
filename + ".fasta.signalp")
self.position2manualinfo = get_position2manualinfo(
"../data/pacbio/pacbio_new_gene_model.tab")
def get_DxxxGID2FBgnID(self):
""" get connection between DxxxGID and FBgn """
lines = get_lines("../data/ortholog/", self.species + ".ee")
DxxxGID2FBgnID = dict()
for line in lines:
temp = line.rstrip().split()
DxxxGID = temp[0]
FBgnID = temp[1]
DxxxGID2FBgnID[DxxxGID] = FBgnID
return (DxxxGID2FBgnID)
def get_isoseqid2position(self):
lines = get_lines("../data/pacbio", self.sample + ".bam.bed")
dct = dict()
for line in lines:
(chrom, chromStart, chromEnd, position_isoseqid, score, strand,
thickStart, thickEnd, itemRgb, blockCount, blockSizes,
blockStarts) = line.rstrip().split("\t")
position, isoseqid = position_isoseqid.split(".")
dct[isoseqid] = position
return dct
def get_jaccard_plus_isoseqid(self):
""" get jaccard > 0 isoseqid """
lines = get_lines(
"../data/output", self.species + "_" + self.sex + "_" +
self.tissue + "_" + self.replicate + ".B.txt")
st = set()
for line in lines:
(position_isoseqid, transid, intersection, union,
jaccard) = line.rstrip().split("\t")
position, isoseqid = position_isoseqid.split(".")
if float(jaccard) > 0:
st.add(isoseqid)
return st
def get_isoseqid2intronnum(self):
""" get intron information from bam.bed """
lines = get_lines("../data/pacbio", self.sample + ".bam.bed")
dct = dict()
for line in lines:
(chrom, chromStart, chromEnd, position_isoseqid, score, strand,
thickStart, thickEnd, itemRgb, blockCount, blockSizes,
blockStarts) = line.rstrip().split("\t")
position, isoseqid = position_isoseqid.split(".")
exons = focalintersect.get_exons(int(chromStart), int(chromEnd),
blockSizes, blockStarts)
num_exons = len(exons)
dct[isoseqid] = num_exons - 1
return dct
def __init__(self, species):
self.species = species
# self.filename = species + ".SVGpredAdded.v2.gtf"
self.filename = species + ".v3.gtf"
self.lines = get_lines("../data/annotation", self.filename)
self.GdxxxID = self.get_geneid_from_annotation(ver="new")
# old annotation (to compare)
self.oldfilename = species + ".gtf"
self.oldlines = get_lines("../data/annotation", self.oldfilename)
self.dxxxFBgn = self.get_geneid_from_annotation(ver="old")
# compare updated annotation with old (postive v3 vs old-gtf; negative old-gtf vs v3)
self.statspositivelines = get_lines("../data/annotation",
species + ".statspositive")
self.statsnegativelines = get_lines("../data/annotation",
species + ".statsnegative")
self.stats = self.get_stats()
self.tmaplines = get_lines("../data/annotation",
species + ".v3.gtf.tmap")
self.dxxxFBgn2GdxxxID, self.GdxxxID2dxxxFBgn = self.get_tmap()
# there are ortholog one2one (GdxxxID 2 dxxxFBgn 2 dmelFBgn)
self.filenameolo121 = species + ".concise.one2one"
self.linesolo121 = get_lines("../data/ortholog", self.filenameolo121)
(self.GdxxxID2dmelFBgn,
self.dxxxFBgn2dmelFBgn) = self.get_olo121_info()
# these dmelFBgn lost one2one due to annotation update, and I need to use dxxxFBgn
self.lost1_dmelFBgn = set(self.dxxxFBgn2dmelFBgn.values()) - set(
self.GdxxxID2dmelFBgn.values())
self.lost1_dxxxFBgn = set([
switch_key_value_in_dict(self.dxxxFBgn2dmelFBgn)[i]
for i in self.lost1_dmelFBgn
])
## there are some newly identified orthologs 121
self.filenameneo121 = species + ".neo121"
self.linesneo121 = get_lines("../data/ortholog", self.filenameneo121)
self.add_neo_to_GdxxxID2dmelFBgn()
if species == "dmel":
self.dmelFBgn2dmelSymbol = self.get_dmelFBgn2dmelSymbol()