def run_ballgown(self):
build([ballgown.ballgown(
workdir=self.workdir,
kingdom="eukarya",
exp_design=self.exp_desn_file,
p_value=self.p_value)],
local_scheduler=self.local_scheduler, workers=1)
def merge_stringtie(self, new_gff):
build([stringtie.MergeStringTies(fastq_dic=self.fastq_dic,
num_cpus=self.num_cpus,
workdir=self.workdir,
gff_file=new_gff,
kingdom=self.kingdom)],
local_scheduler=self.local_scheduler, workers=1)
def run_deseq2(self):
build([
DGE.DESeq2(fastq_dic=self.fastq_dic,
num_cpus=self.num_cpus,
indexfile=self.hisat_index,
bindir=self.bindir,
workdir=self.workdir,
ref_file=self.ref_fastas.split(",")[0],
kingdom='prokarya',
gff=os.path.join(self.workdir, "prok_updated.gff"),
exp_design=self.exp_desn_file,
p_value=self.p_value),
DGE.DESeq2(fastq_dic=self.fastq_dic,
num_cpus=self.num_cpus,
indexfile=self.hisat_index,
bindir=self.bindir,
workdir=self.workdir,
ref_file=self.ref_fastas.split(",")[1],
kingdom='eukarya',
gff=os.path.join(self.workdir, "euk_updated.gff"),
exp_design=self.exp_desn_file,
p_value=self.p_value)
],
local_scheduler=self.local_scheduler,
workers=self.no_of_jobs)
def test_restringtie():
"""Test restringtie approach."""
build([
stringtie.ReStringTieScoresW(fastq_dic={
'samp1':
"l",
'samp2': ['b'],
'samp3': ['b'],
'samp4': ['b'],
'samp5': ['b'],
'samp6': [
'tests/data/fastqs/BTT_test27_R1.fastq.gz',
"tests/data/fastqs/BTT_test27_R2.fastq.gz"
]
},
num_cpus=2,
workdir=os.path.join(
"tests", "data", "test_prok"),
kingdom="prokarya")
],
local_scheduler=True)
assert os.stat(
os.path.join("tests", "data", "test_prok", "processes", "ballgown",
"prokarya", "samp6", "e_data.ctab")).st_size > 1
def NovelRegions(self):
"""Find novel regions."""
build([srna.FindNovelRegionsW(fastq_dic=self.fastq_dic,
workdir=self.workdir,
kingdom=self.kingdom,
gff_file=self.prok_gff + "," + self.euk_gff)],
local_scheduler=self.local_scheduler)
def run_opaver(self, method):
build([
RunOpaver(
workdir=self.workdir, kingdom=self.kingdom, method=method)
],
local_scheduler=self.local_scheduler,
workers=1)
def test_featurecount():
"""Test star index creation and mapping."""
map_dir = os.path.join("tests/test_count", "processes", "mapping", "samp5")
if os.path.exists(map_dir) is False:
os.makedirs(map_dir)
cp_cmd = [
"tests/data/test_prok/processes/mapping/samp5/samp5_srt.bam", map_dir
]
cp[cp_cmd]()
build([
fc.FeatureCounts(fastq_dic={'samp5': ''},
kingdom="prokarya",
gff_file="tests/data/test_prok.gff",
workdir="tests/test_count",
indexfile="",
num_cpus=2,
ref_file="tests/data/test_prok.fna",
fid="ID",
stranded=0)
],
local_scheduler=True)
assert os.path.exists(
"tests/test_count/processes/featureCounts/prokarya/gene_count.tsv"
) is True
rm_cmd = rm["-rf", "tests/test_count"]
rm_cmd()
def run_emapper(self, new_gff, kingdom, fasta):
build([function.RunEmapper(workdir=self.workdir,
gff_file=new_gff,
fasta_file=fasta,
kingdom=kingdom,
emapper_dir=self.emap_dir)],
local_scheduler=self.local_scheduler, workers=1)
def test_CreateReadSketches():
"""
Test if this first luigi class works
test for creating sketches
"""
build([
faqcs.RunAllQC(in_folder="tests/data/fqs",
out_folder="tests/sk_test",
num_cpus=1,
faqc_min_L=50,
n_cutoff=4),
sketch.AllSketches(in_folder="tests/data/fqs",
kmer=31,
threads=2,
sketch=100,
seed=2500,
min_copy=2,
out_folder="tests/sk_test",
mash_tool="mash")
],
local_scheduler=True,
workers=1)
file_exist = os.path.exists("tests/sk_test/.mash/SRR059451_.msh")
shutil.rmtree("tests/sk_test")
assert file_exist is True
def create_db(self):
"""Function to create hisat index."""
if self.aligner == "hisat2":
ref_fastas = self.prok_fasta + "," + self.euk_fasta
build([hisat2.HisatIndex(fasta=ref_fastas,
hi_index=self.hisat_index,
num_cpus=self.num_cpus),
Map.SAMindex(fasta=ref_fastas, workdir=self.workdir)],
# Map.CreateSplice(gff_file=self.ref_gffs.split(",")[1],
# workdir=self.workdir),
# Map.GetChromName(prok_ref=self.ref_fastas.split(",")[0],
# euk_ref=self.ref_fastas.split(",")[1],
# workdir=self.workdir)],
local_scheduler=self.local_scheduler,
workers=1)
elif self.aligner in ["STAR", "star"]:
ref_fastas = self.prok_fasta + "," + self.euk_fasta
build([star.STARindex(fasta=ref_fastas,
num_cpus=self.num_cpus,
gff_file=self.euk_gff,
stardb_dir = self.stardb_dir,
kingdom=self.kingdom),
Map.SAMindex(fasta=ref_fastas, workdir=self.workdir)
# Map.CreateSplice(gff_file=self.euk_gff,
# workdir=self.workdir),
# Map.GetChromName(prok_ref=self.prok_fasta,
# euk_ref=self.euk_fasta,
# workdir=self.workdir)
],
local_scheduler=self.local_scheduler)
def restringtie(self):
build([
stringtie.ReStringTieScoresW(fastq_dic=self.fastq_dic,
num_cpus=self.num_cpus,
workdir=self.workdir,
kingdom=self.kingdom)
],
local_scheduler=self.local_scheduler,
workers=1)
def create_new_gff(self):
build([
srna.CompileGFF(fastq_dic=self.fastq_dic,
kingdom=self.kingdom,
workdir=self.workdir,
gff_file=self.gff_file)
],
local_scheduler=self.local_scheduler,
workers=1)
def summ_json(self, new_gff, method, NovelRegions, kingdom, fasta):
build([summarize.conver2json(gff_file=new_gff,
fasta_file=fasta,
pathway=self.pathway,
workdir=self.workdir,
kingdom=kingdom,
method=method,
NovelRegions=NovelRegions)],
local_scheduler=self.local_scheduler, workers=1)
def feature_counts(self, new_gff, kingdom):
build([featurecounts.FeatureCounts(fastq_dic=self.fastq_dic,
num_cpus=self.num_cpus,
gff_file=new_gff,
indexfile=self.hisat_index,
kingdom=kingdom,
workdir=self.workdir,
ref_file=self.prok_fasta + "," + self.euk_fasta)],
local_scheduler=self.local_scheduler, workers=1)
def run_emapper(self, new_gff):
build([
RunEmapper(workdir=self.workdir,
gff_file=new_gff,
fasta_file=self.ref_fasta,
kingdom=self.kingdom,
emapper_dir=self.emap_dir)
],
local_scheduler=self.local_scheduler,
workers=1)
def extract_pp(self):
"""Extract properly paired reads."""
build([
srna.ExtractPPW(fastq_dic=self.fastq_dic,
num_cpus=self.num_cpus,
indexfile=self.hisat_index,
workdir=self.workdir,
kingdom=self.kingdom)
],
local_scheduler=self.local_scheduler)
def split_prokeuk(self):
build([
Map.Split2ProkEukW(fastq_dic=self.fastq_dic,
num_cpus=self.num_cpus,
indexfile=self.hisat_index,
workdir=self.workdir,
ref_file=self.ref_fastas)
],
local_scheduler=self.local_scheduler,
workers=self.no_of_jobs)
def map_hisat(self):
"""Function that maps reads to hisat2 index."""
build([
Map.HisatMapW(fastq_dic=self.fastq_dic,
num_cpus=self.num_cpus,
indexfile=self.hisat_index,
workdir=self.workdir,
ref_file=self.ref_fastas)
],
local_scheduler=self.local_scheduler,
workers=self.no_of_jobs)
def map_reads(self):
"""Function to map reads."""
if self.aligner == "hisat2":
build([hisat2.HisatMapW(fastq_dic=self.fastq_dic, num_cpus=self.num_cpus,
indexfile=self.hisat_index, workdir=self.workdir,
kingdom=self.kingdom)],
local_scheduler=self.local_scheduler)
elif self.aligner in ["STAR", "star"]:
build([star.map_starW(fastq_dic=self.fastq_dic, num_cpus=self.num_cpus,
stardb_dir=self.stardb_dir, workdir=self.workdir)],
local_scheduler=self.local_scheduler)
def summarize_map(self):
build([
srna.SummarizeMap(fastq_dic=self.fastq_dic,
num_cpus=self.num_cpus,
indexfile=self.hisat_index,
workdir=self.workdir,
ref_file=self.ref_fastas,
kingdom=self.kingdom)
],
local_scheduler=self.local_scheduler,
workers=self.no_of_jobs)
def find_NovelRegions(self):
build([
srna.FindNovelRegionsW(fastq_dic=self.fastq_dic,
num_cpus=self.num_cpus,
indexfile=self.hisat_index,
kingdom=self.kingdom,
workdir=self.workdir,
ref_file=self.ref_fasta,
gff_file=self.gff_file)
],
local_scheduler=self.local_scheduler,
workers=1)
def restringtie(self):
build([
Summ.ReStringTieScoresW(fastq_dic=self.fastq_dic,
num_cpus=self.num_cpus,
indexfile=self.hisat_index,
workdir=self.workdir,
ref_file=self.ref_fastas,
gff_file=self.ref_gffs,
kingdom=self.kingdom)
],
local_scheduler=self.local_scheduler,
workers=self.no_of_jobs)
def map_hisat_summarize(self):
no_of_jobs = 1
build([
srna.SummarizeHisatMap(fastq_dic=self.fastq_dic,
num_cpus=self.num_cpus,
indexfile=self.hisat_index,
workdir=self.workdir,
ref_file=self.ref_fasta,
kingdom=self.kingdom)
],
local_scheduler=self.local_scheduler,
workers=no_of_jobs)
def merge_stringties(self):
build([
Summ.MergeStringTies(fastq_dic=self.fastq_dic,
num_cpus=self.num_cpus,
indexfile=self.hisat_index,
workdir=self.workdir,
ref_file=self.ref_fastas,
gff_file=self.ref_gffs,
kingdom="both")
],
local_scheduler=self.local_scheduler,
workers=self.no_of_jobs)
def feature_count_updated(self, new_gff):
build([
featurecounts.FeatureCounts(fastq_dic=self.fastq_dic,
num_cpus=self.num_cpus,
gff_file=new_gff,
indexfile=self.hisat_index,
kingdom=self.kingdom,
workdir=self.workdir,
ref_file=self.ref_fasta)
],
local_scheduler=self.local_scheduler,
workers=1)
def compile_gff(self):
build([
srna.CompileGFF(fastq_dic=self.fastq_dic,
num_cpus=self.num_cpus,
indexfile=self.hisat_index,
kingdom=self.kingdom,
workdir=self.workdir,
ref_file=self.ref_fastas,
gff_file=self.ref_gffs)
],
local_scheduler=self.local_scheduler,
workers=self.no_of_jobs)
def novel_regions(self):
build([
srna.FindNovelRegionsW(fastq_dic=self.fastq_dic,
num_cpus=self.num_cpus,
indexfile=self.hisat_index,
workdir=self.workdir,
ref_file=self.ref_fastas,
gff_file=self.ref_gffs,
kingdom=self.kingdom)
],
local_scheduler=self.local_scheduler,
workers=self.no_of_jobs)
def run_stringtie(self):
build([
Map.StringTieScoresW(fastq_dic=self.fastq_dic,
num_cpus=self.num_cpus,
indexfile=self.hisat_index,
workdir=self.workdir,
ref_file=self.ref_fasta,
gff_file=os.path.join(self.workdir,
"updated.gff"),
kingdom=self.kingdom)
],
local_scheduler=self.local_scheduler,
workers=1)
def test_opaver():
"""Test deseq3."""
build([
opaver.RunOpaver(workdir=os.path.join("tests", "data", "test_prok"),
kingdom="prokarya",
method="edgeR")
],
local_scheduler=True)
assert os.stat(
os.path.join("tests", "data", "test_prok", "processes", "DESeq2",
"prokarya", "gene",
"liver__over__spleen__gene__sig.csv")).st_size > 1
def run_deseq2(self):
build(
[
DESeq2.DESeq2(
workdir=self.workdir,
kingdom=self.kingdom,
# gff_file=self.gff_file,
# pathway=pathway,
# GAGE=GAGE,
exp_design=self.exp_desn_file,
p_value=self.p_value)
],
local_scheduler=self.local_scheduler,
workers=1)
