def main(prj_dh,test=False):
"""
**--step 4**. Compares test (eg. treated) and control (eg. untreated) experiments.
The output data is saved in `data_comparison` format as described in :ref:`io`.
:param prj_dh: path to project directory.
"""
logging.info("start")
if not exists(prj_dh) :
logging.error("Could not find '%s'" % prj_dh)
sys.exit()
configure.main(prj_dh)
from dms2dfe.tmp import info
cores=info.cores
# SET global variables
global prj_dh_global
prj_dh_global=prj_dh
if exists('%s/cfg/comparison' % prj_dh):
comparison_pairs_list =getusable_comparison_list(prj_dh)
if test:
pooled_data_fit2data_comparison(comparison_pairs_list[0])
else:
pool=Pool(processes=int(cores))
pool.map(pooled_data_fit2data_comparison,comparison_pairs_list)
pool.close(); pool.join()
else :
logging.warning("do not exist: cfg/comparison")
data_fit_metrics=get_data_metrics(prj_dh)
logging.shutdown()
def main(prj_dh):
"""
**--step 5**. Generates vizualizations.
#. Scatter grid plots raw counts in replicates, if present.
#. Mutation matrix. of frequencies of mutants (log scaled).
#. Scatter plots of raw counts among selected and unselected samples
#. Mutation matrix. of Fitness values.
#. DFE plot. ie. Distribution of Fitness values for samples.
#. Projections on PDB. Average of fitness values per residue are projected onto PDB file.
:param prj_dh: path to project directory.
"""
logging.info("start")
if not exists(prj_dh):
logging.error("Could not find '%s'" % prj_dh)
sys.exit()
configure.main(prj_dh)
from dms2dfe.tmp import info
for type_form in ['aas', 'cds']:
plots_dh = '%s/plots/%s' % (prj_dh, type_form)
if not exists(plots_dh):
makedirs(plots_dh)
plot_coverage(info)
plot_mutmap(info)
plot_submap(info)
plot_multisca(info)
plot_pdb(info)
plot_violin(info)
def main(prj_dh, test=False):
"""
**--step 4**. Compares test (eg. treated) and control (eg. untreated) experiments.
The output data is saved in `data_comparison` format as described in :ref:`io`.
:param prj_dh: path to project directory.
"""
logging.info("start")
if not exists(prj_dh):
logging.error("Could not find '%s'" % prj_dh)
sys.exit()
configure.main(prj_dh)
from dms2dfe.tmp import info
cores = info.cores
# SET global variables
global prj_dh_global
prj_dh_global = prj_dh
if exists('%s/cfg/comparison' % prj_dh):
comparison_pairs_list = getusable_comparison_list(prj_dh)
if test:
pooled_data_fit2data_comparison(comparison_pairs_list[0])
else:
pool = Pool(processes=int(cores))
pool.map(pooled_data_fit2data_comparison, comparison_pairs_list)
pool.close()
pool.join()
else:
logging.warning("do not exist: cfg/comparison")
data_fit_metrics = get_data_metrics(prj_dh)
logging.shutdown()
def main(prj_dh, test=False):
"""
**--step 1**. Processes alignment (.sam file) and produces codon level mutation matrix of counts of mutations.
:param prj_dh: path to project directory.
"""
logging.info("start")
# SET global variables
global fsta_id, fsta_seqlen, fsta_seq, cds_ref, Q_cutoff, prj_dh_global
prj_dh_global = prj_dh
if not exists(prj_dh):
logging.error("Could not find '%s'\n" % prj_dh)
sys.exit()
configure.main(prj_dh)
from dms2dfe.tmp import info
fsta_fh = info.fsta_fh
Q_cutoff = int(info.Q_cutoff)
cores = int(info.cores)
samtools_fh = info.samtools_fh
with open(fsta_fh, 'r') as fsta_data:
for fsta_record in SeqIO.parse(fsta_data, "fasta"):
fsta_id = fsta_record.id
fsta_seq = str(fsta_record.seq)
fsta_seqlen = len(fsta_seq)
logging.info("ref name : '%s', length : '%d' " %
(fsta_record.id, fsta_seqlen))
cds_ref = []
for cdi in range(len(fsta_seq) / 3):
cds_ref.append(str(fsta_seq[cdi * 3:cdi * 3 + 3]))
sbam_fhs = getusablesbams_list(prj_dh)
# check if bams are indexed
for sbam_fh in sbam_fhs:
sbam_index_fh = "%s.bai" % sbam_fh
log_fh = "%s.log" % sbam_index_fh
log_f = open(log_fh, 'a')
if not exists(sbam_index_fh):
com = "%s index %s" % (samtools_fh, sbam_fh)
subprocess.call(com,
shell=True,
stdout=log_f,
stderr=subprocess.STDOUT)
log_f.close()
if len(sbam_fhs) != 0:
if test:
pooled(sbam_fhs[0])
else:
pool = Pool(processes=int(cores)) # T : get it from xls
pool.map(pooled, sbam_fhs)
pool.close()
pool.join()
else:
logging.info("already processed")
logging.shutdown()
def main(prj_dh,test=False):
"""
**--step 1**. Processes alignment (.sam file) and produces codon level mutation matrix of counts of mutations.
:param prj_dh: path to project directory.
"""
logging.info("start")
# SET global variables
global fsta_id,fsta_seqlen,fsta_seq,cds_ref,Q_cutoff,prj_dh_global
prj_dh_global=prj_dh
if not exists(prj_dh) :
logging.error("Could not find '%s'\n" % prj_dh)
sys.exit()
configure.main(prj_dh)
from dms2dfe.tmp import info
fsta_fh=info.fsta_fh
Q_cutoff=int(info.Q_cutoff)
cores=int(info.cores)
samtools_fh=info.samtools_fh
with open(fsta_fh,'r') as fsta_data:
for fsta_record in SeqIO.parse(fsta_data, "fasta") :
fsta_id=fsta_record.id
fsta_seq=str(fsta_record.seq)
fsta_seqlen=len(fsta_seq)
logging.info("ref name : '%s', length : '%d' " % (fsta_record.id, fsta_seqlen))
cds_ref=[]
for cdi in range(len(fsta_seq)/3) :
cds_ref.append(str(fsta_seq[cdi*3:cdi*3+3]))
sbam_fhs=getusablesbams_list(prj_dh)
# check if bams are indexed
for sbam_fh in sbam_fhs:
sbam_index_fh="%s.bai" % sbam_fh
log_fh="%s.log" % sbam_index_fh
log_f = open(log_fh,'a')
if not exists(sbam_index_fh):
com= "%s index %s" % (samtools_fh,sbam_fh)
subprocess.call(com,shell=True,stdout=log_f, stderr=subprocess.STDOUT)
log_f.close()
if len(sbam_fhs)!=0:
if test:
pooled(sbam_fhs[0])
else:
pool=Pool(processes=int(cores)) # T : get it from xls
pool.map(pooled, sbam_fhs)
pool.close(); pool.join()
else:
logging.info("already processed")
logging.shutdown()
def main(prj_dh, test=False):
"""
**--step 0.2**. Preprocesses and aligns sequencing files.
The steps and required dependendencies are following.
.. code-block:: text
Quality filtering : using Trimmomatic.
Alignment : using bowtie2
.sam to .bam conversion : using samtools
:param prj_dh: path to project directory
"""
logging.info("start")
global trimmomatic_fh, fsta_fh, alignment_type, bt2_ref_fh, bowtie2_fh, samtools_fh, bowtie2_com
if not exists(prj_dh):
logging.error("Could not find '%s'\n" % prj_dh)
sys.exit()
configure.main(prj_dh)
from dms2dfe.tmp import info
fsta_fh = info.fsta_fh
cores = info.cores
trimmomatic_fh = info.trimmomatic_fh
bowtie2_fh = info.bowtie2_fh
trimmomatic_com = info.trimmomatic_com
bowtie2_com = info.bowtie2_com
samtools_fh = info.samtools_fh
alignment_type = info.alignment_type
# make bowtie index
bt2_ref_fh = splitext(fsta_fh)[0]
if not exists("%s.1.bt2" % bt2_ref_fh):
bowtie_ref_com="%s-build --quiet %s %s &> %s.logbt2bld" \
% (bowtie2_fh,fsta_fh,splitext(bt2_ref_fh)[0],bt2_ref_fh)
subprocess.call(bowtie_ref_com, shell=True)
logging.info("bt2_ref_fh do not exist, made one.")
fastqs_list = getusablefastqs_list(prj_dh)
# print fastqs_list
if len(fastqs_list) != 0:
if test:
for fastq in fastqs_list:
pooled(fastq)
else:
pool = Pool(processes=int(cores))
pool.map(pooled, fastqs_list)
pool.close()
pool.join()
else:
logging.info("already processed")
# cfg_h5.close()
logging.shutdown()
def main(prj_dh,test=False):
"""
**--step 0.2**. Preprocesses and aligns sequencing files.
The steps and required dependendencies are following.
.. code-block:: text
Quality filtering : using Trimmomatic.
Alignment : using bowtie2
.sam to .bam conversion : using samtools
:param prj_dh: path to project directory
"""
logging.info("start")
global trimmomatic_fh,fsta_fh,alignment_type,bt2_ref_fh,bowtie2_fh,samtools_fh,bowtie2_com
if not exists(prj_dh) :
logging.error("Could not find '%s'\n" % prj_dh)
sys.exit()
configure.main(prj_dh)
from dms2dfe.tmp import info
fsta_fh=info.fsta_fh
cores=info.cores
trimmomatic_fh=info.trimmomatic_fh
bowtie2_fh=info.bowtie2_fh
trimmomatic_com=info.trimmomatic_com
bowtie2_com=info.bowtie2_com
samtools_fh=info.samtools_fh
alignment_type=info.alignment_type
# make bowtie index
bt2_ref_fh = splitext(fsta_fh)[0]
if not exists("%s.1.bt2" % bt2_ref_fh):
bowtie_ref_com="%s-build --quiet %s %s &> %s.logbt2bld" \
% (bowtie2_fh,fsta_fh,splitext(bt2_ref_fh)[0],bt2_ref_fh)
subprocess.call(bowtie_ref_com,shell=True)
logging.info("bt2_ref_fh do not exist, made one.")
fastqs_list=getusablefastqs_list(prj_dh)
# print fastqs_list
if len(fastqs_list)!=0:
if test:
for fastq in fastqs_list:
pooled(fastq)
else:
pool=Pool(processes=int(cores))
pool.map(pooled,fastqs_list)
pool.close(); pool.join()
else:
logging.info("already processed")
# cfg_h5.close()
logging.shutdown()
def main(prj_dh):
"""
**--step 0.3**. Extracts molecular features of the gene.
The out files are created in `prj_dh/data_feats`
The steps and required dependendencies are following.
.. code-block:: text
Secondary structure : using DSSP.
Solvent Accessible Surface Area : using DSSP.
Distance of a residue from reference atom: using Bio.PDB
:param prj_dh: path to project directory.
"""
logging.basicConfig(
format='[%(asctime)s] %(levelname)s from %(funcName)s:\t%(message)s',
level=logging.DEBUG) # filename=cfg_xls_fh+'.log'
logging.info("start")
if not exists(prj_dh):
logging.error("Could not find '%s'\n" % prj_dh)
sys.exit()
configure.main(prj_dh)
from dms2dfe.tmp import info
#FEATS PER POSITION
data_feats_pos_fh = "%s/data_feats/aas/data_feats_pos" % prj_dh
data_feats_pos = get_data_feats_pos(prj_dh,
info,
data_out_fh=data_feats_pos_fh)
#FEATS PER SUBSTITUTION
data_feats_sub_fh = "%s/data_feats/aas/data_feats_sub" % prj_dh
data_feats_sub = get_data_feats_sub(data_out_fh=data_feats_sub_fh)
#FEATS PER MUTATION
data_feats_mut_fh = "%s/data_feats/aas/data_feats_mut" % prj_dh
data_feats_mut = get_data_feats_mut(prj_dh, data_feats_mut_fh, info)
#FEATS ALL
data_feats_all_fh = "%s/data_feats/aas/data_feats_all" % prj_dh
data_feats_all = get_data_feats_all(data_feats_mut_fh, data_feats_pos_fh,
data_feats_sub_fh, data_feats_all_fh,
info)
#back compatibility
feats_all_fh = "%s/data_feats/aas/feats_all" % prj_dh
if not data_feats_pos is None:
data_feats_pos.to_csv(feats_all_fh)
logging.shutdown()
def main(prj_dh):
"""
**--step 0.1**. Demultipexes .fastq files based on barcodes located at `prj_dh/cfg/barcodes`.
:param prj_dh: path to project directory
"""
logging.info("start")
if not exists(prj_dh) :
logging.error("Could not find '%s'\n" % prj_dh)
sys.exit()
configure.main(prj_dh)
from dms2dfe.tmp import info
trimmomatic_fh=info.trimmomatic_fh
if exists('%s/cfg/barcodes' % prj_dh) :
barcodes=pd.read_csv(prj_dh+'/cfg/barcodes')
# print barcodes
if len(barcodes)!=0:
fastq_R1_fhs=[str(s) for s in barcodes.loc[:,'fastq_R1_fh'].unique()]
fastq_fhs_list=[[s, s.replace('R1','R2')] for s in fastq_R1_fhs if not exists("%s.qcd.fastq" % s)] # pairs
for fastq_fhs_tp in fastq_fhs_list:
fastq2qcd(fastq_fhs_tp,trimmomatic_fh)
# fastq_R1_fhs=[fastq_R1_fh+".qcd.fastq" for fastq_R1_fh in fastq_R1_fhs if not ".qcd." in fastq_R1_fh]
barcodes=barcodes.set_index('fastq_R1_fh')
for fastq_R1_fh in fastq_R1_fhs:
if exists(fastq_R1_fh):
fastq_R1_fh_barcodes=barcodes.loc[fastq_R1_fh,:]
fastq_R2_fh=fastq_R1_fh.replace('R1','R2') #str(fastq_R1_fh_barcodes.ix[0,'fastq_R2_fh'])
if (not exists("%s.qcd.fastq_unresolved_joined.qcd.fastq" % (fastq_R1_fh)))\
and (not exists("%s.qcd.fastq_unresolved_joined.qcd.fastq" % (fastq_R1_fh))):
if exists(fastq_R1_fh):
logging.info("processing: %s" % basename(fastq_R1_fh))
# print fastq_R1_fh_barcodes
barcode_R1s=[str(s) for s in list(fastq_R1_fh_barcodes.loc[:,'barcode_R1'])]
barcode_R2s=[str(s) for s in list(fastq_R1_fh_barcodes.loc[:,'barcode_R2'])]
fastq_fns =[str(s) for s in list(fastq_R1_fh_barcodes.loc[:,'fastq_fn'])]
fastq2dplx(fastq_R1_fh+".qcd.fastq",fastq_R2_fh+".qcd.fastq",\
barcode_R1s,barcode_R2s,fastq_fns)
else:
logging.info("fastq_R2_fh do not exist: %s" % fastq_R2_fh)
else:
logging.info("already done : %s" % fastq_R1_fh)
else:
logging.info("fastq_R1_fh do not exist: %s" % fastq_R1_fh)
else:
logging.info("skipping: because barcodes not present in cfg")
else:
logging.info("skipping: because barcodes not present in cfg")
logging.shutdown()
def pipeline(prj_dh,step=None,test=False):
from dms2dfe import configure, ana0_fastq2dplx,ana0_fastq2sbam,ana0_getfeats,ana1_sam2mutmat,ana2_mutmat2fit,ana3_fit2comparison,ana4_modeller,ana4_plotter
if exists(prj_dh):
if step==0 or step==None:
configure.main(prj_dh,"deps")
configure.main(prj_dh)
if step==0.1 or step==None:
ana0_fastq2dplx.main(prj_dh)
if step==0.2 or step==None:
ana0_fastq2sbam.main(prj_dh,test)
if step==0.3:
ana0_getfeats.main(prj_dh)
if step==1 or step==None:
ana1_sam2mutmat.main(prj_dh)
if step==2 or step==None:
ana2_mutmat2fit.main(prj_dh,test)
if step==3 or step==None:
ana0_getfeats.main(prj_dh)
ana4_modeller.main(prj_dh,test)
if step==4 or step==None:
ana3_fit2comparison.main(prj_dh,test)
if step==5 or step==None:
ana0_getfeats.main(prj_dh)
ana4_plotter.main(prj_dh)
if step==None:
logging.info("Location of output data: %s/plots/aas/data_comparison" % (prj_dh))
logging.info("Location of output visualizations: %s/plots/aas/" % (prj_dh))
logging.info("For information about file formats of outputs, refer to http://kc-lab.github.io/dms2dfe/io .")
else:
configure.main(prj_dh)
logging.shutdown()
def main(prj_dh):
"""
**--step 0.1**. Demultipexes .fastq files based on barcodes located at `prj_dh/cfg/barcodes`.
:param prj_dh: path to project directory
"""
logging.info("start")
if not exists(prj_dh):
logging.error("Could not find '%s'\n" % prj_dh)
sys.exit()
configure.main(prj_dh)
from dms2dfe.tmp import info
trimmomatic_fh = info.trimmomatic_fh
if exists('%s/cfg/barcodes' % prj_dh):
barcodes = pd.read_csv(prj_dh + '/cfg/barcodes')
# print barcodes
if len(barcodes) != 0:
fastq_R1_fhs = [
str(s) for s in barcodes.loc[:, 'fastq_R1_fh'].unique()
]
fastq_fhs_list = [[s, s.replace('R1', 'R2')] for s in fastq_R1_fhs
if not exists("%s.qcd.fastq" % s)] # pairs
for fastq_fhs_tp in fastq_fhs_list:
fastq2qcd(fastq_fhs_tp, trimmomatic_fh)
# fastq_R1_fhs=[fastq_R1_fh+".qcd.fastq" for fastq_R1_fh in fastq_R1_fhs if not ".qcd." in fastq_R1_fh]
barcodes = barcodes.set_index('fastq_R1_fh')
for fastq_R1_fh in fastq_R1_fhs:
if exists(fastq_R1_fh):
fastq_R1_fh_barcodes = barcodes.loc[fastq_R1_fh, :]
fastq_R2_fh = fastq_R1_fh.replace(
'R1',
'R2') #str(fastq_R1_fh_barcodes.ix[0,'fastq_R2_fh'])
if (not exists("%s.qcd.fastq_unresolved_joined.qcd.fastq" % (fastq_R1_fh)))\
and (not exists("%s.qcd.fastq_unresolved_joined.qcd.fastq" % (fastq_R1_fh))):
if exists(fastq_R1_fh):
logging.info("processing: %s" %
basename(fastq_R1_fh))
# print fastq_R1_fh_barcodes
barcode_R1s = [
str(s) for s in list(
fastq_R1_fh_barcodes.loc[:, 'barcode_R1'])
]
barcode_R2s = [
str(s) for s in list(
fastq_R1_fh_barcodes.loc[:, 'barcode_R2'])
]
fastq_fns = [
str(s) for s in list(
fastq_R1_fh_barcodes.loc[:, 'fastq_fn'])
]
fastq2dplx(fastq_R1_fh+".qcd.fastq",fastq_R2_fh+".qcd.fastq",\
barcode_R1s,barcode_R2s,fastq_fns)
else:
logging.info("fastq_R2_fh do not exist: %s" %
fastq_R2_fh)
else:
logging.info("already done : %s" % fastq_R1_fh)
else:
logging.info("fastq_R1_fh do not exist: %s" % fastq_R1_fh)
else:
logging.info("skipping: because barcodes not present in cfg")
else:
logging.info("skipping: because barcodes not present in cfg")
logging.shutdown()
def main(prj_dh, test=False, ml=False):
"""
**--step 3**. Identifies molecular features that may determine fitness scores.
This plots the results in following visualisations.
.. code-block:: text
ROC plots
Relative importances of features
:param prj_dh: path to project directory.
"""
logging.info("start")
if not exists(prj_dh):
logging.error("Could not find '%s'" % prj_dh)
sys.exit()
configure.main(prj_dh)
from dms2dfe.tmp import info
from dms2dfe.tmp import info
from dms2dfe.lib.io_ml import corrplot
corrplot(info)
if ml:
from dms2dfe.lib.io_dfs import set_index
from dms2dfe.lib.io_ml import data_fit2ml #,get_cols_del,make_data_combo,data_combo2ml
cores = int(info.cores)
if hasattr(info, 'mut_type'):
mut_type = info.mut_type
else:
mut_type = 'single'
if hasattr(info, 'ml_input'):
if info.ml_input == 'FC':
ml_input = 'FCA_norm'
elif info.ml_input == 'Fi':
ml_input = 'FiA'
else:
ml_input = 'FCA_norm'
type_form = "aas"
if not exists("%s/plots/%s" % (prj_dh, type_form)):
makedirs("%s/plots/%s" % (prj_dh, type_form))
if not exists("%s/data_ml/%s" % (prj_dh, type_form)):
makedirs("%s/data_ml/%s" % (prj_dh, type_form))
data_feats = pd.read_csv("%s/data_feats/aas/data_feats_all" % (prj_dh))
if mut_type == 'single':
data_fit_keys = ["data_fit/%s/%s" % (type_form,basename(fh)) \
for fh in glob("%s/data_fit/aas/*" % prj_dh) \
if (not "inferred" in basename(fh)) and ("_WRT_" in basename(fh))]
data_fit_keys = np.unique(data_fit_keys)
if len(data_fit_keys) != 0:
if test:
pooled_io_ml(data_fit_keys[0])
# for data_fit_key in data_fit_keys:
# pooled_io_ml(data_fit_key)
else:
for data_fit_key in data_fit_keys:
pooled_io_ml(data_fit_key)
# pool_io_ml=Pool(processes=int(cores))
# pool_io_ml.map(pooled_io_ml,data_fit_keys)
# pool_io_ml.close(); pool_io_ml.join()
else:
logging.info("already processed")
elif mut_type == 'double':
data_feats = set_index(data_feats, 'mutids')
data_fit_dh = 'data_fit_dm'
data_fit_keys = ["%s/%s/%s" % (data_fit_dh,type_form,basename(fh)) \
for fh in glob("%s/%s/aas/*" % (prj_dh,data_fit_dh)) \
if (not "inferred" in basename(fh)) and ("_WRT_" in basename(fh))]
data_fit_keys = np.unique(data_fit_keys)
ycol = ml_input
Xcols = data_feats.columns
if len(data_fit_keys) != 0:
for data_fit_key in data_fit_keys:
data_fit_dm_fh = '%s/%s' % (prj_dh, data_fit_key)
data_combo_fh = '%s/data_ml/aas/%s.combo' % (
prj_dh, basename(data_fit_dm_fh))
force = False
if not exists(data_combo_fh) or force:
data_fit_dm = pd.read_csv(data_fit_dm_fh).set_index(
'mutids')
data_combo = make_data_combo(data_fit_dm, data_feats,
ycol, Xcols)
if not exists(dirname(data_combo_fh)):
makedirs(dirname(data_combo_fh))
data_combo.to_csv(data_combo_fh)
else:
data_combo = pd.read_csv(data_combo_fh).set_index(
'mutids')
logging.info('ml: start')
data_combo2ml(
data_combo,
basename(data_fit_dm_fh),
dirname(data_combo_fh),
dirname(data_combo_fh),
ycoln=ycol,
col_idx='mutids',
ml_type='cls',
middle_percentile_skipped=0.1,
force=False,
)
def pooled_io_ml(data_fit_key):
"""
This module makes use of muti threading to speed up `dms2dfe.lib.io_ml.data_fit2ml`.
:param data_fit_key: in the form <data_fit>/<aas/cds>/<name of file>.
"""
from dms2dfe.tmp import info
dX_fh = "%s/data_feats/aas/data_feats_all" % (info.prj_dh)
dy_fh = '%s/%s' % (info.prj_dh, data_fit_key)
logging.info('processing: %s' % basename(dy_fh))
data_fit2ml(dX_fh, dy_fh, info, regORcls='cls')
logging.shutdown()
def main(prj_dh,test=False):
"""
**--step 2**. Converts mutation matrices (.mat files produced in upstream ana1_sam2mutmat module) and calculates the fitness scores.
The output data is saved in `data_fit` format as described in :ref:`io`.
:param prj_dh: path to project directory.
"""
logging.info("start")
if not exists(prj_dh) :
logging.error("Could not find '%s'" % prj_dh)
sys.exit()
configure.main(prj_dh)
global prj_dh_global,host,norm_type,fsta_len,cctmr_global,output_dh,prj_dh_global,lbls,Ni_cutoff,fsta_fh_global,clips
from dms2dfe.tmp import info
fsta_fh=info.fsta_fh
cctmr=info.cctmr
host=info.host
cores=info.cores
transform_type=info.transform_type
norm_type=info.norm_type
fsta_len=info.fsta_len
Ni_cutoff=int(info.Ni_cutoff)
rscript_fh=info.rscript_fh
if hasattr(info, 'mut_type'):
mut_type=info.mut_type
else:
mut_type='single'
lbls=pd.read_csv(prj_dh+'/cfg/lbls')
lbls=lbls.set_index('varname')
# SET global variables
prj_dh_global=prj_dh
fsta_fh_global=fsta_fh
if cctmr != 'nan':
cctmr=[int("%s" % i) for i in cctmr.split(" ")]
cctmr_global=[(cctmr[0],cctmr[1]),(cctmr[2],cctmr[3])]
else:
cctmr_global=None
if info.clips != 'nan':
clips=[int(s) for s in info.clips.split(' ')]
else:
clips=None
if mut_type=='single':
lbls_list=getusable_lbls_list(prj_dh)
if len(lbls_list)!=0:
if test:
pooled_mut_mat_cds2data_lbl(lbls_list[0])
else:
pool_mut_mat_cds2data_lbl=Pool(processes=int(cores))
pool_mut_mat_cds2data_lbl.map(pooled_mut_mat_cds2data_lbl,lbls_list)
pool_mut_mat_cds2data_lbl.close(); pool_mut_mat_cds2data_lbl.join()
else:
logging.info("already processed: mut_mat_cds2data_lbl")
#TRANSFORM
if (transform_type=='rlog') or (transform_type=='vst'):
logging.info("transforming frequencies: %s" % transform_type)
transform_data_lbl_deseq(prj_dh,transform_type,rscript_fh)
else:
logging.info("transforming frequencies: %s" % transform_type)
transform_data_lbl(prj_dh,transform_type)
#FITNESS
fits_pairs_list=getusable_fits_list(prj_dh,data_fit_dh='data_fit')
if len(fits_pairs_list)!=0:
if test:
# pooled_data_lbl2data_fit(fits_pairs_list[0])
for fits_pairs in fits_pairs_list:
pooled_data_lbl2data_fit(fits_pairs)
else:
pool_data_lbl2data_fit=Pool(processes=int(cores))
pool_data_lbl2data_fit.map(pooled_data_lbl2data_fit,
fits_pairs_list)
pool_data_lbl2data_fit.close(); pool_data_lbl2data_fit.join()
else:
logging.info("already processed: data_lbl2data_fit")
elif mut_type=='double':
fits_pairs_list_dm=getusable_fits_list(prj_dh,data_fit_dh='data_fit_dm')
if len(fits_pairs_list_dm)!=0:
if test:
data_lbl2data_fit_dm(fits_pairs_list_dm[0],prj_dh,data_lbl_dh='data_lbl_dm',
data_fit_dh='data_fit_dm')
else:
for fits_pairs in fits_pairs_list_dm:
data_lbl2data_fit_lite(fits_pairs,prj_dh,data_lbl_dh='data_lbl_dm',
data_fit_dh='data_fit_dm')
else:
logging.info("already processed: data_lbl2data_fit")
logging.shutdown()
def test_configure():
from dms2dfe import configure
configure.main('prj')