def main():
####################################################################
### define parser of arguments
parser = argparse.ArgumentParser(
description='Plot correlation bar of multiple condition')
# parser.add_argument('--condition_ls', type=str, default='seq+shape:seq:shape', help='Condition list')
# parser.add_argument('--correlation_ls', type=str, default='0.78:0.305:0.343', help='Correlation list')
# parser.add_argument('--savefn', type=str, default='/home/gongjing/project/shape_imputation/results/condition_compare_correlation.pdf', help='Path to plot file')
parser.add_argument(
'--condition_ls',
type=str,
default=
'HEK293(wc, vivo):HEK293(wc, vitro):HEK293(ch, vivo):HEK293(np, vivo):HEK293(cy, vivo):mES(wc, vivo)',
help='Condition list')
parser.add_argument('--correlation_ls',
type=str,
default='0.78:0.702:0.704:0.761:0.723:0.675',
help='Correlation list')
parser.add_argument(
'--savefn',
type=str,
default=
'/home/gongjing/project/shape_imputation/results/condition_compare_correlation.vivo_vitro_WcChNpCy.pdf',
help='Path to plot file')
# get args
args = parser.parse_args()
util.print_args('Plot correlation bar of multiple condition', args)
plot_corr_bar(condition_ls=args.condition_ls,
correlation_ls=args.correlation_ls,
savefn=args.savefn)
def main():
####################################################################
### define parser of arguments
parser = argparse.ArgumentParser(
description='Plot dms-seq m6AC score dist')
parser.add_argument(
'--shape_ls',
type=str,
default=
'/home/gongjing/project/shape_imputation/data/RBMbase/download_20191204/RMBase_hg38_all_m6A_site.tran.e1.tx_has_shape_base_valid.bed.shape100.txt:/home/gongjing/project/shape_imputation/exper/d06_DMSseq_K562_vitro_trainRandmask0.3x50_vallownull100_lossDMSloss_all/prediction.dmsseq_k562_vivo_m6A_null.txt',
help='List of shape file')
parser.add_argument('--label_ls',
type=str,
default='valid:null_predict',
help='Label list')
parser.add_argument(
'--savefn',
type=str,
default=
'/home/gongjing/project/shape_imputation/results/dmsseq_m6AC_valid_vs_nullpredict.pdf',
help='Savefn pdf')
args = parser.parse_args()
util.print_args('Plot dms-seq m6AC score dist', args)
plot_m6AC(shape_ls=args.shape_ls,
label_ls=args.label_ls,
savefn=args.savefn)
def main():
####################################################################
### define parser of arguments
parser = argparse.ArgumentParser(
description='Plot AUC for single known structure')
parser.add_argument(
'--AUC_txt_ls',
type=str,
default=
'/home/gongjing/project/shape_imputation/exper/b28_trainLossall_GmultiplyX_randomNperfragmentpct0.3L20x10_randomNperValidate/prediction.rfam.AUCs.txt:/home/gongjing/project/shape_imputation/exper/b92_trainLossall_shapeOnly_x10/prediction.rfam.AUCs.txt:/home/gongjing/project/shape_imputation/exper/b91_trainLossall_seqOnly_x10/prediction.rfam.AUCs.txt',
help='AUC file list')
parser.add_argument('--AUC_label_ls',
type=str,
default='seq+shape:shape:seq',
help='AUC label list')
parser.add_argument(
'--savefn',
type=str,
default=
'/home/gongjing/project/shape_imputation/results/condition_compare_AUC_rfam.pdf',
help='Pdf file to save plot')
# get args
args = parser.parse_args()
util.print_args(parser.description, args)
compare_AUCs(AUC_txt_ls=args.AUC_txt_ls,
AUC_label_ls=args.AUC_label_ls,
savefn=args.savefn)
def main():
####################################################################
### define parser of arguments
parser = argparse.ArgumentParser(
description='Plot correlation bar of multiple condition')
parser.add_argument(
'--condition_ls',
type=str,
default=
'hek_wc_vivo:hek_wc_vitro:hek_ch_vivo:hek_np_vivo:hek_cy_vivo:mes_wc_vivo',
help='Condition list')
parser.add_argument('--SHAPEImpute_ls',
type=str,
default='0.766:0.715:0.699:0.755:0.710:0.666',
help='Correlation list')
parser.add_argument('--ShaKer_ls',
type=str,
default='0.274:0.256:0.226:0.228:0.242:0.264',
help='Correlation list')
parser.add_argument(
'--savefn',
type=str,
default=
'/home/gongjing/project/shape_imputation/results/condition_compare_correlation.shapeimpute_vs_shaker_multiple_set.pdf',
help='Path to plot file')
# get args
args = parser.parse_args()
util.print_args('Plot correlation bar of multiple condition', args)
plot_corr_bar(condition_ls=args.condition_ls,
SHAPEImpute_ls=args.SHAPEImpute_ls,
ShaKer_ls=args.ShaKer_ls,
savefn=args.savefn)
def main():
####################################################################
### define parser of arguments
parser = argparse.ArgumentParser(
description=
'Compare replicates correlation between true and predicted shape')
parser.add_argument('--rep1_out', type=str, help='Rep1 shape.out')
parser.add_argument('--rep1_validate', type=str, help='Rep1 fragment')
parser.add_argument('--rep1_predict',
type=str,
help='Rep1 fragment prediction')
parser.add_argument('--rep2_out', type=str, help='Rep2 shape.out')
parser.add_argument('--rep2_validate', type=str, help='Rep2 fragment')
parser.add_argument('--rep2_predict',
type=str,
help='Rep2 fragment prediction')
parser.add_argument('--tx_null_pct',
type=float,
default=0.3,
help='Cutoff filtering fragment with null pct')
parser.add_argument('--savefn', type=str, help='Pdf file to save plot')
# get args
args = parser.parse_args()
util.print_args(parser.description, args)
rep_compare(rep1_out=args.rep1_out,
rep1_validate=args.rep1_validate,
rep1_predict=args.rep1_predict,
rep2_out=args.rep2_out,
rep2_validate=args.rep2_validate,
rep2_predict=args.rep2_predict,
tx_null_pct=args.tx_null_pct,
savefn=args.savefn)
def main():
####################################################################
### define parser of arguments
parser = argparse.ArgumentParser(
description='Split into train & validation based on blastn')
parser.add_argument(
'--blastn',
type=str,
default=
'/home/gongjing/project/shape_imputation/data/seq_similarity/windowLen100.sliding10.all2.outputfile_E10',
help='Path to blastn file')
parser.add_argument(
'--txt',
type=str,
default=
'/home/gongjing/project/shape_imputation/data/hek_wc_vivo/3.shape/shape.c200T2M0m0.out.windowsHasNull/windowLen100.sliding10.txt',
help='Path to all fragment file')
parser.add_argument('--validation_pct',
type=float,
default=0.2,
help='Valiation percentage')
# get args
args = parser.parse_args()
util.print_args('Split into train & validation based on blastn', args)
split(blastn=args.blastn, txt=args.txt, validation_pct=args.validation_pct)
def main():
# get argument
args = util.get_args()
# print argument
util.print_args(args)
# run te
mlus = []
rcs = []
# at every T step
for t in range(args.num_test):
if t % args.T == 0:
repetita_args = util.get_repetita_args(args, t)
print('command:', ' '.join(repetita_args))
stdout = util.call(repetita_args)
if stdout:
print('stdout:', stdout)
mlu, rc = util.parse_result(t, stdout, args)
if len(mlu) == args.T:
mlus.append(mlu)
if rc is not None:
rcs.append(rc)
util.save(mlus, rcs, args)
def main():
####################################################################
### define parser of arguments
parser = argparse.ArgumentParser(description='Sort shape by NULL count')
parser.add_argument(
'--shape1',
type=str,
default=
'/home/gongjing/project/shape_imputation/data/CLIP/human_trx_clip/CLIPDB20162_IGF2BP1_HEK293_trx.tx_has_shape_region_null_ok.fimo/fimo.new.IGF2BP1_11.txt.shape100.txt',
help='Path to shape2')
parser.add_argument(
'--shape2',
type=str,
default=
'/home/gongjing/project/shape_imputation/data/CLIP/human_trx_clip/CLIPDB20162_IGF2BP1_HEK293_trx.tx_has_shape_region_null_ok.fimo/fimo.new.IGF2BP1_11.txt.shape',
help='Path to shape1')
parser.add_argument('--value_col1',
type=int,
default=7,
help='Which column index to sort')
# get args
args = parser.parse_args()
util.print_args(parser.description, args)
sort(shape1=args.shape1, shape2=args.shape2, value_col1=args.value_col1)
def main():
####################################################################
### define parser of arguments
parser = argparse.ArgumentParser(
description='RNA modification site analysis')
parser.add_argument(
'--modification_bed',
type=str,
default=
'/home/gongjing/project/shape_imputation/data/RBMbase/download_20191204/RMBase_hg38_all_PseudoU_site.tran.bed',
help='Modification bed file')
parser.add_argument(
'--icshape',
type=str,
default=
'/home/gongjing/project/shape_imputation/data/hek_wc_vivo/3.shape/shape.c200T2M0m0.out',
help='icSHAPE out file')
parser.add_argument('--label', type=str, default='e1')
# get args
args = parser.parse_args()
util.print_args('RNA modification site analysis', args)
# modification_has_shape(bed=args.modification_bed, out=args.icshape)
modification_extend_1_has_shape(
bed=args.modification_bed, out=args.icshape,
label=args.label) # for dms-seq, check xxACx, C=>e1
def main():
####################################################################
### define parser of arguments
parser = argparse.ArgumentParser(
description=
'Retain common fragments in two validation file with different depth')
parser.add_argument('--fragment_high',
type=str,
help='Path to fragment file with depth1')
parser.add_argument('--fragment_low',
type=str,
help='Path to fragment file with depth2')
parser.add_argument('--fragment_common',
type=str,
help='Path to fragment file with depth2')
parser.add_argument('--savefn', type=str, help='Path to save plot file')
parser.add_argument(
'--process_type',
type=str,
default='generate_common_fragment|corr_of_common_fragment',
help='process')
# get args
args = parser.parse_args()
util.print_args(
'Retain common fragments in two validation file with different depth',
args)
if args.process_type == 'generate_common_fragment':
fragment_for_test(fragment_high=args.fragment_high,
fragment_low=args.fragment_low)
if args.process_type == 'corr_of_common_fragment':
fragment_compare_corr(fragment_common=args.fragment_common,
savefn=args.savefn)
def extract_process_kmers(name):
"""Extract k-mers from genomic sequence and run initial processing.
Load project arguments and produce three files:
extract k-mers from the genome: <name>/<name>_kmers.txt.gz
shuffle all extracted k-mers: <name>/<name>_kmers_shuffled.txt.gz
count occurrences of k-mers: <name>/<name>_kmers_counts.txt.gz
Args:
name: project name, used to get project args and in all output
"""
util.print_log('start extract_process_kmers()')
util.print_log('load arguments...')
args = util.load_args(name)
util.print_args(args)
util.print_log('done')
util.print_log('load FASTA...')
util.print_log('load from %s' % args['fasta'])
fasta = load_fasta(args['fasta'])
util.print_log('done')
util.print_log('extract k-mers...')
kmers_filename = '%s/%s_kmers.txt.gz' % (name, name)
allpams = [args['pam']] + args['altpam']
util.print_log('write in file %s' % kmers_filename)
genome = extract_kmers(name=name,
fasta=fasta,
length=args['length'],
pams=allpams,
pampos=args['pampos'],
filename=kmers_filename,
chroms=args['chrom'],
minchrlen=args['minchrlen'],
processes=args['processes'])
sys.stdout.write('genome: %s' % genome)
util.print_log('save genome info')
args['genome'] = genome
util.save_args(args)
util.print_log('calculate k-mer statistics')
print_stats_kmers(kmers_filename, gnupath=args['gnupath'])
util.print_log('done')
util.print_log('shuffle k-mers...')
kmers_shuffled_filename = '%s/%s_kmers_shuffled.txt.gz' % (name, name)
util.print_log('write in file %s' % kmers_shuffled_filename)
shuffle_kmers(fileinput=kmers_filename,
fileoutput=kmers_shuffled_filename,
gnupath=args['gnupath'])
util.print_log('done')
util.print_log('count k-mers...')
count_filename = '%s/%s_kmers_counts.txt.gz' % (name, name)
util.print_log('write in file %s' % count_filename)
sort_count_kmers(fileinput=kmers_filename,
fileoutput=count_filename,
mincount=args['maxoffpos'],
gnupath=args['gnupath'])
util.print_log('done')
return True
def produce_bams_main(kmers_trie, name):
"""Produce BAM file with all guideRNAs and info about their off-targets.
Run after all files and trie were generated
by kmers.extract_process_kmers() and guides.analyze_guides()
Produce files:
sorted BAM file with off-target info: <name>/<name>_guides.bam
index for the BAM file with off-target info: <name>/<name>_guides.bam.bai
also, BAM file and index for all guideRNAs without any off-target info
(produced much faster):
<name>/<name>_guides_nooff.bam
<name>/<name>_guides_nooff.bam.bai
Args:
kmers_trie: trie.trie object as produced by guides.analyze_guides()
name: project name, used to get project args and in all output
"""
util.print_log('start produce_bam()')
util.print_log('load arguments...')
args = util.load_args(name)
util.print_args(args)
util.print_log('done')
util.print_log('produce SAM file with guideRNAs only (no off-targets)...')
# guides_filename = '%s/%s_guides.txt.gz' % (name, name)
# parts = 256
n = args['greateroffdist']
parts = 4 ** n
guides_dir = '%s%s' % (name,'/classifiedfiles/guides')
guides_filenames = ['%s/%s.txt.gz' % (guides_dir, i) for i in range(parts)]
util.print_log('read guides from %s' % guides_dir)
produce_bam_custom(kmers_trie=kmers_trie, name=name, label='nooff',
guides_filename=guides_filenames,
args=args, offdist=-1, # -1 for no off-targets
maxoffcount=args['maxoffcount'],
processes=args['processes'],
n = n,
parts=parts)
util.print_log('done')
if args['offdist'] != -1:
util.print_log('produce SAM file with guideRNAs'
' and off-target info...')
# guides_filename = '%s/%s_guides.txt.gz' % (name, name)
util.print_log('read guides from %s' % guides_dir)
produce_bam_custom(kmers_trie=kmers_trie, name=name,
label='offdist%s' % args['offdist'],
guides_filename=guides_filenames,
args=args, offdist=args['offdist'],
maxoffcount=args['maxoffcount'],
processes=args['processes'],
n = n,
parts=parts)
util.print_log('done')
def main():
# get argument
args = util.get_args()
# print argument
util.print_args(args)
# at every T + 1 step
t = 1995
repetita_args = util.get_repetita_args(args, t)
print('command:', ' '.join(repetita_args))
stdout = util.call(repetita_args)
print('stdout:', stdout)
def main():
####################################################################
### define parser of arguments
parser = argparse.ArgumentParser(
description='Parse dataset of bpRNA in SPOT-RNA project')
parser.add_argument('--d', type=str, help='Dir of bpRNA')
parser.add_argument('--savefn', type=str, help='File to save parsed info')
# get args
args = parser.parse_args()
util.print_args(parser.description, args)
read_dir_rfam(d=args.d, savefn=args.savefn)
def main():
####################################################################
### define parser of arguments
parser = argparse.ArgumentParser(description='Plot NULL percentage along iterations')
parser.add_argument('--stat_ls', type=str, default='/home/gongjing/project/shape_imputation/data/hek_wc_vivo/3.shape/test_prediction/t.out.predict/iteration.stat.txt,/home/gongjing/project/shape_imputation/data/hek_wc_vivo/3.shape/test_prediction/hek_wc.out.predict/iteration.stat.txt', help='List of stat file')
parser.add_argument('--label_ls', type=str, default='test,hek_wc_vivo', help='Label list')
parser.add_argument('--corr_ls', type=str, default='/home/gongjing/project/shape_imputation/data/hek_wc_vivo/3.shape/test_prediction/hek_wc.out.c80.newwithNULL.nominus.predict/corr.txt', help='Correlation text list')
parser.add_argument('--savefn', type=str, default='/home/gongjing/project/shape_imputation/results/null_pct_interation.pdf', help='Savefn pdf')
args = parser.parse_args()
util.print_args('Plot NULL percentage along iterations', args)
plot_iteration(stat_ls=args.stat_ls, label_ls=args.label_ls, savefn=args.savefn, corr_ls=args.corr_ls)
def main():
####################################################################
### define parser of arguments
parser = argparse.ArgumentParser(description='Plot correlation bar of multiple condition')
parser.add_argument('--validation_ls', type=str, help='Validation file list')
parser.add_argument('--predict_ls', type=str, help='Predict file list')
parser.add_argument('--label_ls', type=str, help='Lable list')
parser.add_argument('--savefn', type=str, default='/home/gongjing/project/shape_imputation/results/condition_compare_correlation.track.wc_vs_cy.pdf', help='Path to plot file')
# get args
args = parser.parse_args()
util.print_args('Plot correlation bar of multiple condition', args)
compare_predict(validation_ls=args.validation_ls, predict_ls=args.predict_ls, label_ls=args.label_ls, savefn=args.savefn)
def main():
####################################################################
### define parser of arguments
parser = argparse.ArgumentParser(description='Plot correlation bar of multiple condition')
parser.add_argument('--condition_ls', type=str, default='0.1:0.2:0.3:0.4:0.5)', help='Condition list')
parser.add_argument('--correlation_ls', type=str, default='0.940:0.915:0.885:0.810:0.755', help='Correlation list')
parser.add_argument('--savefn', type=str, default='/home/gongjing/project/shape_imputation/results/condition_compare_correlation.18S.pdf', help='Path to plot file')
# get args
args = parser.parse_args()
util.print_args('Plot correlation bar of multiple condition', args)
plot_corr_bar(condition_ls=args.condition_ls, correlation_ls=args.correlation_ls, savefn=args.savefn)
def main():
####################################################################
### define parser of arguments
parser = argparse.ArgumentParser(description='Extract start/stop condon shape')
parser.add_argument('--species', type=str, default='human', help='human')
parser.add_argument('--icshape', type=str, default='/home/gongjing/project/shape_imputation/data/hek_wc_vivo/3.shape/shape.c200T2M0m0.out', help='icSHAPE out file')
parser.add_argument('--savefn', type=str, help='Pdf file to save plot', default='/home/gongjing/project/shape_imputation/results/start_stop_codon/hek_wc.shape')
# get args
args = parser.parse_args()
util.print_args(parser.description, args)
extract_start_codon_shape(species=args.species, shape=args.icshape, savefn=args.savefn)
def main():
####################################################################
### define parser of arguments
parser = argparse.ArgumentParser(
description='Compare two shape column in a fragment file')
parser.add_argument('--fragment', type=str, help='fragment file')
parser.add_argument('--savefn', type=str, help='Pdf file to save plot')
# get args
args = parser.parse_args()
util.print_args(parser.description, args)
compare(fragment=args.fragment, savefn=args.savefn)
def main():
####################################################################
### define parser of arguments
parser = argparse.ArgumentParser(description='Complete a input shape.out')
parser.add_argument(
'--icshape',
type=str,
default=
'/home/gongjing/project/shape_imputation/data/hek_wc_vivo/3.shape/shape.c200T2M0m0.out',
help='icSHAPE out file')
parser.add_argument('--species', type=str, default='human', help='Species')
parser.add_argument('--predict_label',
type=str,
default='wc_all_fragment',
help='Predict_label')
parser.add_argument(
'--predict_model',
type=str,
default=
'b28_trainLossall_GmultiplyX_randomNperfragmentpct0.3L20x10_randomNperValidate2',
help='Model used to predict')
parser.add_argument('--pct',
type=float,
default=0.5,
help='Max NULL percentage in fragment to predict')
parser.add_argument('--window_len',
type=int,
default=100,
help='window_len')
parser.add_argument('--sliding', type=int, default=10, help='sliding')
parser.add_argument('--shape_null_pct',
type=float,
default=0.3,
help='Stop predict when remains pct(NULL) <= cutoff')
parser.add_argument('--gpu_id', type=str, default="1", help='GPU id')
# get args
args = parser.parse_args()
util.print_args('Complete a input shape.out', args)
complete_shape_out_nullpct(icshape=args.icshape,
species=args.species,
predict_label=args.predict_label,
predict_model=args.predict_model,
pct=args.pct,
window_len=args.window_len,
sliding=args.sliding,
shape_null_pct=args.shape_null_pct,
gpu_id=args.gpu_id)
def main():
####################################################################
### define parser of arguments
parser = argparse.ArgumentParser(description='CLIP data analysis')
parser.add_argument(
'--clip_bed',
type=str,
default=
'/home/gongjing/project/shape_imputation/data/CLIP/human_trx_clip/STARBASE20007_DGCR8_HEK293T_trx.bed',
help='Bed file of CLIP data')
parser.add_argument(
'--clip_bed_dir',
type=str,
default=
'/home/gongjing/project/shape_imputation/data/CLIP/human_trx_clip',
help='Dir to bed file')
parser.add_argument('--bed_peak_len',
type=int,
default=10,
help='Min peak length to keep')
parser.add_argument(
'--icshape',
type=str,
default=
'/home/gongjing/project/shape_imputation/data/hek_wc_vivo/3.shape/shape.c200T2M0m0.out',
help='icSHAPE out file')
parser.add_argument('--max_null_pct',
type=float,
default=0.4,
help='Max percentage of NULL values in peak regions')
parser.add_argument(
'--clip_table_list',
type=str,
default=
'/home/gongjing/project/shape_imputation/data/CLIP/human.RBP.CLIP.combined.tbl',
help='All CLIP table list')
# get args
args = parser.parse_args()
util.print_args('CLIP data analysis', args)
# read_bed(bed=args.clip_bed)
# iclip_has_shape(bed=args.clip_bed, bed_peak_len=args.bed_peak_len, out=args.icshape, max_null_pct=args.max_null_pct)
iclip_has_shape_batch(clip_table_list=args.clip_table_list,
clip_bed_dir=args.clip_bed_dir,
bed_peak_len=args.bed_peak_len,
out=args.icshape,
max_null_pct=args.max_null_pct)
def main():
####################################################################
### define parser of arguments
parser = argparse.ArgumentParser(
description='Plot NULL corr across iterations')
parser.add_argument(
'--icshape',
type=str,
default=
'/home/gongjing/project/shape_imputation/data/hek_wc_vivo/3.shape/test_prediction/hek_wc.out.c80',
help='predict file dir')
parser.add_argument(
'--predict_dir',
type=str,
default=
'/home/gongjing/project/shape_imputation/data/hek_wc_vivo/3.shape/test_prediction/hek_wc.out.predict',
help='predict file dir')
parser.add_argument(
'--validation',
type=str,
default=
'/home/gongjing/project/shape_imputation/data/hek_wc_vivo/3.shape/shape.c200T2M0m0.out.windowsHasNull/validation_randomnullfragment/windowLen100.sliding100.validation.randomNperfragmentNullPct0.3.maxL20.S1234.txt',
help='validation file')
parser.add_argument('--max_iterations',
type=int,
default=100,
help='plot <= max_iterations')
parser.add_argument('--tx',
type=str,
default='ENST00000331434',
help='shape plot of tx')
parser.add_argument(
'--icshape_true',
type=str,
default=
'/home/gongjing/project/shape_imputation/data/hek_wc_vivo/3.shape/test_prediction/hek_wc.out.c80',
help='predict file dir')
# get args
args = parser.parse_args()
util.print_args('Plot NULL corr across iterations', args)
# plot_dir_null_corr(args)
# generate_new_shape_out_with_validation_null(args)
plot_tx_shape_iterations(args)
def main():
####################################################################
### define parser of arguments
parser = argparse.ArgumentParser(description='Generate N DA data for a train set')
parser.add_argument('--txt', type=str, default='/home/gongjing/project/shape_imputation/data/hek_wc_vivo/3.shape/shape.c200T2M0m0.out.windowsHasNull/train_randomnullfragment_DA/windowLen100.sliding100.train.txt', help='Path to blastn file')
parser.add_argument('--seed', type=int, default=1234, help='random seed')
parser.add_argument('--times', type=int, default=20, help='DA times')
parser.add_argument('--strategy', type=str, default='random', help='DA strategy: random|shadow_null_shuffle')
# get args
args = parser.parse_args()
util.print_args('Generate N DA data for a train set', args)
random.seed(args.seed)
data_agumentation(txt=args.txt, times=args.times, strategy=args.strategy)
def main():
####################################################################
### define parser of arguments
parser = argparse.ArgumentParser(description='Search motif from a fasta')
parser.add_argument('--species', type=str, default='human', help='Species')
parser.add_argument(
'--savefn',
type=str,
default=
'/home/gongjing/project/shape_imputation/data/RBMbase/download_20191204/hg38_m6A_motif.bed',
help='Savefn')
# get args
args = parser.parse_args()
util.print_args('Search motif from a fasta', args)
search(species=args.species, savefn=args.savefn)
def main():
####################################################################
### define parser of arguments
parser = argparse.ArgumentParser(
description='Set random NULL position as other signal')
parser.add_argument(
'--txt',
type=str,
default=
'/home/gongjing/project/shape_imputation/data/hek_wc_vivo_rRNA/3.shape/shape.c200T2M0m0.out.windowsHasNull/windowLen100.sliding100.fulllength18S.validation_randomNULL0.3.txt',
help='validation data set')
# get args
args = parser.parse_args()
util.print_args('Set random NULL position as other signal', args)
convert(txt=args.txt)
def main():
####################################################################
### define parser of arguments
parser = argparse.ArgumentParser(
description='Plot null pct scatter of common tx between two icshape.out'
)
parser.add_argument(
'--icshape1',
type=str,
default=
'/home/gongjing/project/shape_imputation/data/hek_wc_vivo/3.shape/shape.c200T2M0m0.out',
help='icSHAPE out file1')
parser.add_argument(
'--icshape2',
type=str,
default=
'/home/gongjing/project/shape_imputation/data/hek_wc_vivo/3.shape/shape.c200T2M0m0.allfragment.0.5+exceed0.5.txt2.predict.out',
help='icSHAPE out file2')
parser.add_argument('--out1_label',
type=str,
default='True',
help='icSHAPE out file1 label')
parser.add_argument('--out2_label',
type=str,
default='Predict',
help='icSHAPE out file2 label')
parser.add_argument(
'--savefn',
type=str,
default=
'/home/gongjing/project/shape_imputation/data/hek_wc_vivo/3.shape/shape.c200T2M0m0.allfragment.0.5+exceed0.5.txt2.predict.out.scatter.pdf',
help='Save plot file')
parser.add_argument('--species', type=str, default='human', help='Species')
# get args
args = parser.parse_args()
util.print_args(
'Plot null pct scatter of common tx between two icshape.out', args)
plot_shape_tx_null_pct(out1=args.icshape1,
out2=args.icshape2,
out1_label=args.out1_label,
out2_label=args.out2_label,
savefn=args.savefn,
species=args.species)
def main():
####################################################################
### define parser of arguments
parser = argparse.ArgumentParser(
description='Generate a shuffle fragment based on a null pattern')
parser.add_argument(
'--txt',
type=str,
default=
'/data/gongjing/project/shape_imputation/data/hek_wc_vivo/3.shape/shape.c200T2M0m0.out.windowsHasNull/low_depth_null/sampling/windowLen100.sliding100.validation.low_60_1234.null_pattern.txt',
help='Path to dir')
args = parser.parse_args()
util.print_args('Generate a shuffle fragment based on a null pattern',
args)
null_pattern_to_bed(txt=args.txt)
def main():
####################################################################
### define parser of arguments
parser = argparse.ArgumentParser(description='Calc NULL/nonNULL value distribution in train/validation set')
parser.add_argument('--data', type=str, default='/home/gongjing/project/shape_imputation/data/hek_wc_vivo/3.shape/c200T2/w100s100.train_null0.1.txt', help='Path to fragment file')
parser.add_argument('--col', type=str, default='7:8', help='Columns to calc')
parser.add_argument('--savefn', type=str, default='/home/gongjing/project/shape_imputation/data/hek_wc_vivo/3.shape/c200T2/w100s100.train_null0.1.stat.pdf', help='Path to save stat file')
parser.add_argument('--dist_type', type=str, default='null_pattern', help='Type of dist')
# get args
args = parser.parse_args()
util.print_args('Calc NULL/nonNULL value distribution in train/validation set', args)
if 'null_pattern' in args.dist_type:
null_count_dist(data=args.data, col=args.col, savefn=(args.data).replace('.txt', '.pdf'))
if 'shape_value' in args.dist_type:
reactivity_dist(data=args.data, col=args.col, savefn=args.savefn)
def run_model() -> None:
"Execute model according to the configuration"
print('#' * 5, 'PARAMETERS', '#' * 5)
print_args(ARGS)
print('#' * 10, '\n\n')
# Which model to use?
build_fn, reader_type = common.get_modelfn_reader()
reader = common.create_reader(reader_type)
def optimiser(model: Model) -> torch.optim.Optimizer:
return AdamW(model.parameters(), lr=1e-3, weight_decay=1e-3)
# Create SAVE_FOLDER if it doesn't exist
ARGS.SAVE_PATH.mkdir(exist_ok=True, parents=True)
train_dataset = load_data(data_path=ARGS.TRAIN_DATA_PATH,
reader=reader,
pre_processed_path=ARGS.TRAIN_PREPROCESSED_PATH)
val_dataset = load_data(data_path=ARGS.VAL_DATA_PATH,
reader=reader,
pre_processed_path=ARGS.VAL_PREPROCESSED_PATH)
test_dataset = load_data(data_path=ARGS.TEST_DATA_PATH,
reader=reader,
pre_processed_path=ARGS.TEST_PREPROCESSED_PATH)
model = train_model(build_fn,
train_data=train_dataset,
val_data=val_dataset,
test_data=test_dataset,
save_path=ARGS.SAVE_PATH,
num_epochs=ARGS.NUM_EPOCHS,
batch_size=ARGS.BATCH_SIZE,
optimiser_fn=optimiser,
cuda_device=ARGS.CUDA_DEVICE,
sorting_keys=reader.keys)
common.evaluate(model, reader, test_dataset)
result = make_prediction(model, reader, verbose=False)
common.error_analysis(model, test_dataset)
print('Save path', ARGS.SAVE_PATH)
cuda_device = 0 if is_cuda(model) else -1
test_load(build_fn, reader, ARGS.SAVE_PATH, result, cuda_device)
def main():
####################################################################
### define parser of arguments
parser = argparse.ArgumentParser(
description='Plot AUC for single known structure')
parser.add_argument('--dot', type=str, help='Dot file for known structure')
parser.add_argument('--validate', type=str, help='Validate fragment file')
parser.add_argument('--predict', type=str, help='Predicted fragment file')
parser.add_argument('--tx', type=str, help='Transcript to plot')
parser.add_argument('--start',
type=int,
default=0,
metavar='N',
help='Dot start index')
parser.add_argument('--savefn', type=str, help='Pdf file to save plot')
parser.add_argument('--title',
type=str,
default='',
help='Title of the plot')
parser.add_argument(
'--predict_bases',
type=str,
default='ATCG',
help='Bases considered while calc AUC for predict sample')
parser.add_argument(
'--validate_bases',
type=str,
default='ATCG',
help='Bases considered while calc AUC for validate sample')
# get args
args = parser.parse_args()
util.print_args(parser.description, args)
known_structure_compare(dot=args.dot,
validate=args.validate,
predict=args.predict,
tx=args.tx,
start=args.start,
savefn=args.savefn,
title=args.title,
predict_bases=args.predict_bases,
validate_bases=args.validate_bases)