def __init__(self, args, display_title=None):
Step.__init__(self, args, display_title=display_title)
# set
self.match_barcode_list, self.n_cell = utils.read_barcode_file(args.match_dir)
self.match_barcode = set(self.match_barcode_list)
if args.panel:
self.gene_list = utils.get_gene_region_from_bed(args.panel)[0]
self.n_gene = len(self.gene_list)
else:
self.gene_list, self.n_gene = utils.read_one_col(args.gene_list)
if not self.gene_list:
sys.exit("You must provide either --panel or --gene_list!")
self.count_dict = utils.genDict(dim=3, valType=int)
self.add_metric(
name="Number of Target Genes",
value=self.n_gene,
)
self.add_metric(
name="Number of Cells",
value=self.n_cell,
)
# out file
self.out_bam_file = f'{self.out_prefix}_filtered.bam'
self.out_bam_file_sorted = f'{self.out_prefix}_filtered_sorted.bam'
def __init__(self, args, display_title=None):
Step.__init__(self, args, display_title=display_title)
# set
self.chains = CHAINS[args.type]
self.cols = []
for chain in self.chains:
for seq in SEQUENCES_HEADER:
self.cols.append("_".join([seq, chain]))
self.match_bool = False
if args.match_dir and args.match_dir.strip() != 'None':
self.match_cell_barcodes, _match_cell_number = utils.read_barcode_file(
args.match_dir)
self.match_bool = True
elif args.matrix_dir and args.matrix_dir.strip() != 'None':
self.match_cell_barcodes = utils.get_barcodes_from_matrix_dir(
args.matrix_dir)
self.match_bool = True
if self.match_bool:
self.match_cell_barcodes = set(self.match_cell_barcodes)
# out files
self.cell_confident_file = f"{self.out_prefix}_cell_confident.tsv"
self.cell_confident_count_file = f"{self.out_prefix}_cell_confident_count.tsv"
self.clonetypes_file = f"{self.out_prefix}_clonetypes.tsv"
self.match_clonetypes_file = f"{self.out_prefix}_match_clonetypes.tsv"
# add args data
self.add_data(iUMI=args.iUMI)
def __init__(self, args, display_title=None):
Step.__init__(self, args, display_title=display_title)
# read args
self.fq = args.fq
self.fq_pattern = args.fq_pattern
self.linker_fasta = args.linker_fasta
self.barcode_fasta = args.barcode_fasta
# process
self.barcode_dict, self.barcode_length = utils.read_fasta(self.barcode_fasta, equal=True)
if self.linker_fasta and self.linker_fasta != 'None':
self.linker_dict, self.linker_length = utils.read_fasta(self.linker_fasta, equal=True)
else:
self.linker_dict, self.linker_length = {}, 0
self.pattern_dict = parse_pattern(self.fq_pattern)
# check barcode length
barcode1 = self.pattern_dict["C"][0]
# end - start
pattern_barcode_length = barcode1[1] - barcode1[0]
if pattern_barcode_length != self.barcode_length:
raise Exception(
f'''barcode fasta length {self.barcode_length}
!= pattern barcode length {pattern_barcode_length}'''
)
self.res_dic = utils.genDict()
self.res_sum_dic = utils.genDict(dim=2)
self.match_barcode = []
# out files
self.read_count_file = f'{self.outdir}/{self.sample}_read_count.tsv'
self.UMI_count_file = f'{self.outdir}/{self.sample}_UMI_count.tsv'
self.stat_file = f'{self.outdir}/stat.txt'
def __init__(self, args):
Step.__init__(self, args)
# input files
self.sample = args.sample
self.bam_file = args.bam
self.outdir = args.outdir
# output files
self.outstat = os.path.join(self.outdir, self.sample+'.substitution.txt')
def __init__(self, args, display_title=None):
Step.__init__(self, args, display_title=display_title)
# set
self.gtf = Mkref_rna.parse_genomeDir(self.args.genomeDir)['gtf']
self.featureCounts_param = args.featureCounts_param
# out files
input_basename = os.path.basename(self.args.input)
self.featureCounts_bam = f'{self.outdir}/{input_basename}.featureCounts.bam'
self.name_sorted_bam = f'{self.out_prefix}_name_sorted.bam'
self.featureCount_log_file = f'{self.out_prefix}.summary'
def __init__(self, args, display_title=None):
Step.__init__(self, args, display_title=display_title)
if not (args.split_matrix or args.split_fastq or args.split_vdj):
return
# set
df_umi_tag = pd.read_csv(args.umi_tag_file, sep='\t', index_col=0)
df_umi_tag = df_umi_tag.rename_axis('barcode').reset_index()
self.tag_barcode_dict = {
tag: set(row["barcode"].tolist())
for tag, row in df_umi_tag.groupby("tag")
}
if args.split_matrix:
self.matrix_outdir = f'{args.outdir}/matrix/'
if args.match_dir:
matrix_10X_dir = glob.glob(
f'{args.match_dir}/05.count/*_matrix_10X*')[0]
elif args.matrix_dir:
matrix_10X_dir = args.matrix_dir
else:
raise ValueError("--match_dir or --matrix_dir is required.")
self.raw_mat, self.raw_features_path, self.raw_barcodes = read_raw_matrix(
matrix_10X_dir)
if args.split_fastq:
self.rna_fq_file = glob.glob(
f'{args.match_dir}/*barcode/*_2.fq*')[0]
fastq_outdir = f'{args.outdir}/fastqs/'
os.system(f'mkdir -p {fastq_outdir}')
self.r2_fastq_files_handle = {}
self.r1_fastq_files_handle = {}
for tag in self.tag_barcode_dict:
r2_fastq_file_name = f'{fastq_outdir}/{tag}_2.fq'
self.r2_fastq_files_handle[tag] = open(r2_fastq_file_name, 'w')
r1_fastq_file_name = f'{fastq_outdir}/{tag}_1.fq'
self.r1_fastq_files_handle[tag] = open(r1_fastq_file_name, 'w')
self.tag_read_index_dict = defaultdict(set)
if args.split_vdj:
self.cell_confident_vdj = glob.glob(
f'{args.vdj_dir}/*count_vdj/*cell_confident.tsv*')[0]
self.vdj_outdir = f'{args.outdir}/vdj/'
if not os.path.exists(self.vdj_outdir):
os.system(f'mkdir -p {self.vdj_outdir}')
def __init__(self, args):
Step.__init__(self, args)
# input files
self.outdir = args.outdir
self.sample = args.sample
self.bam_file = args.bam
self.snp_file = args.bg
self.bg_cov = args.bg_cov
self.cell_keep = args.cell_keep
# output files
self.outread = os.path.join(
self.outdir, self.sample + '.corrected_gene_cell_UMI_read.txt')
self.outrds = os.path.join(self.outdir, self.sample + '.TC_matrix.rds')
self.outpre = os.path.join(self.outdir, self.sample)
def __init__(self, args):
Step.__init__(self, args)
# input files
self.sample = args.sample
self.tsnefile = args.tsne
self.matfile = args.mat
self.repfile = args.rep
self.mincell = args.mincell
self.topgene = args.topgene
# output files
self.outdot = os.path.join(self.outdir,
self.sample + '.rep_in_tsne.txt')
self.outtbl = os.path.join(self.outdir,
self.sample + '.rep_in_tsne_top10.txt')
def test_stat_to_metric(self):
os.chdir('/SGRNJ01/RD_dir/pipeline_test/zhouyiqi/multi_tests/rna')
args_dict = {
'sample': 'test1',
'assay': 'rna',
'thread': 1,
'outdir': 'test1/06.analysis',
'debug': True,
}
Args = namedtuple('Args', list(args_dict.keys()))
args = Args(**args_dict)
obj = Step(args, 'analysis')
obj.stat_to_metric()
print(obj.__content_dict['metric'])
def __init__(self, args):
Step.__init__(self, args)
# input files
self.ifile = os.path.join(args.outdir, args.sample + '.bam')
self.sample = args.sample
self.strandednessfile = args.strand
self.inbam = args.bam
self.bcfile = args.cell
self.outdir = args.outdir
self.thread = args.thread
# output files
self.outfile_bam = os.path.join(args.outdir,
args.sample + '.PosTag.bam')
self.outfile_csv = os.path.join(args.outdir,
args.sample + '.PosTag.csv')
def __init__(self, args, display_title=None):
Step.__init__(self, args, display_title=display_title)
# set
self.read_type = "UMIs"
if args.not_consensus:
self.read_type = 'Reads'
self.chains = CHAINS[args.type]
# out files
self.UMI_count_unfiltered_file = f'{self.out_prefix}_UMI_count_unfiltered.tsv'
self.UMI_count_filtered_file = f'{self.out_prefix}_UMI_count_filtered.tsv'
self.mixcr_report = f"{self.out_prefix}_align.txt"
self.not_align_fq = f"{self.out_prefix}_not_align.fq"
self.read2_vdjca = f"{self.out_prefix}_read2.vdjca"
self.alignments = f"{self.out_prefix}_alignments.txt"
def __init__(self, args, display_title=None):
Step.__init__(self, args, display_title=display_title)
self.fq1_list = args.fq1.split(",")
self.fq2_list = args.fq2.split(",")
self.fq_number = len(self.fq1_list)
if self.fq_number != len(self.fq2_list):
raise Exception('fastq1 and fastq2 do not have same file number!')
if args.chemistry == 'auto':
ch = Chemistry(args.fq1)
self.chemistry_list = ch.check_chemistry()
else:
self.chemistry_list = [args.chemistry] * self.fq_number
self.barcode_corrected_num = 0
self.linker_corrected_num = 0
self.total_num = 0
self.clean_num = 0
self.no_polyT_num = 0
self.lowQual_num = 0
self.no_linker_num = 0
self.no_barcode_num = 0
self.barcode_qual_Counter = Counter()
self.umi_qual_Counter = Counter()
self.pattern = args.pattern
self.linker = args.linker
self.whitelist = args.whitelist
self.lowNum = args.lowNum
self.lowQual = args.lowQual
self.allowNoPolyT = args.allowNoPolyT
self.allowNoLinker = args.allowNoLinker
self.nopolyT = args.nopolyT # true == output nopolyT reads
self.noLinker = args.noLinker
self.output_R1 = args.output_R1
# out file
if args.gzip:
suffix = ".gz"
else:
suffix = ""
self.out_fq2 = f'{self.out_prefix}_2.fq{suffix}'
self.out_fq1 = f'{self.out_prefix}_1.fq{suffix}'
if self.nopolyT:
self.nopolyT_1 = f'{self.out_prefix}_noPolyT_1.fq'
self.nopolyT_2 = f'{self.out_prefix}_noPolyT_2.fq'
if self.noLinker:
self.noLinker_1 = f'{self.out_prefix}_noLinker_1.fq'
self.noLinker_2 = f'{self.out_prefix}_noLinker_2.fq'
def __init__(self, args, step_name):
Step.__init__(self, args, step_name)
self.outdir = args.outdir
self.sample = args.sample
self.Seqtype = args.Seqtype
self.all_rep = args.all_rep
self.fa = args.fa
if self.Seqtype == 'TCR':
self.string = 't'
self.chain = ['TRA', 'TRB']
self.paired_groups = ['TRA_TRB']
elif self.Seqtype == 'BCR':
self.string = 'b'
self.chain = ['IGH', 'IGL', 'IGK']
self.paired_groups = ['IGH_IGL', 'IGH_IGK']
def __init__(self, args):
Step.__init__(self, args)
# set
self.barcodes, _num = utils.read_barcode_file(args.match_dir)
self.fasta = Mkref_rna.parse_genomeDir(args.genomeDir)['fasta']
self.df_vcf = None
self.panel = args.panel
self.bed = utils.get_bed_file_path(self.panel)
# out
self.splitN_bam = f'{self.out_prefix}_splitN.bam'
self.splitN_bam_name_sorted = f'{self.out_prefix}_splitN_name_sorted.bam'
self.raw_bcf_file = f'{self.out_prefix}_raw.bcf'
self.raw_vcf_file = f'{self.out_prefix}_raw.vcf'
self.fixed_header_vcf = f'{self.out_prefix}_fixed.vcf'
self.norm_vcf_file = f'{self.out_prefix}_norm.vcf'
def __init__(self, args, display_title=None):
Step.__init__(self, args, display_title=display_title)
self.force_cell_num = args.force_cell_num
self.cell_calling_method = args.cell_calling_method
self.expected_cell_num = int(args.expected_cell_num)
self.bam = args.bam
# set
self.gtf_file = Mkref_rna.parse_genomeDir(args.genomeDir)['gtf']
self.gtf_dict = utils.Gtf_dict(self.gtf_file)
self.downsample_dict = {}
# output files
self.count_detail_file = f'{self.outdir}/{self.sample}_count_detail.txt'
self.marked_count_file = f'{self.outdir}/{self.sample}_counts.txt'
self.raw_matrix_10X_dir = f'{self.outdir}/{self.sample}_all_matrix'
self.cell_matrix_10X_dir = f'{self.outdir}/{self.sample}_matrix_10X'
self.downsample_file = f'{self.outdir}/{self.sample}_downsample.txt'
def __init__(self, args, display_title=None):
Step.__init__(self, args, display_title=display_title)
self.read_count_file = args.read_count_file
self.UMI_min = args.UMI_min
self.SNR_min = args.SNR_min
self.combine_cluster = args.combine_cluster
self.dim = int(args.dim)
self.coefficient = float(args.coefficient)
# read
self.df_read_count = pd.read_csv(self.read_count_file,
sep="\t",
index_col=0)
if args.match_dir:
match_dict = utils.parse_match_dir(args.match_dir)
self.match_barcode = match_dict['match_barcode']
self.n_match_barcode = match_dict['n_match_barcode']
self.tsne_file = match_dict['tsne_coord']
self.matrix_dir = match_dict['matrix_dir']
elif args.matrix_dir:
df_barcode = pd.read_csv(f'{args.matrix_dir}/barcodes.tsv',
header=None)
self.match_barcode = df_barcode[0].tolist()
self.n_match_barcode = len(self.match_barcode)
self.tsne_file = args.tsne_file
self.matrix_dir = args.matrix_dir
else:
raise ValueError("--match_dir or --matrix_dir is required.")
# init
self.no_noise = False
# out files
self.UMI_tag_file = f'{self.outdir}/{self.sample}_umi_tag.tsv'
self.tsne_tag_file = f'{self.outdir}/{self.sample}_tsne_tag.tsv'
self.cluster_count_file = f'{self.outdir}/{self.sample}_cluster_count.tsv'
self.cluster_plot = f'{self.outdir}/{self.sample}_cluster_plot.pdf'
if self.combine_cluster:
self.combine_cluster_count_file = f'{self.outdir}/{self.sample}_combine_cluster_count.tsv'
self.combine_cluster_plot = f'{self.outdir}/{self.sample}_combine_cluster_plot.pdf'
def __init__(self, args):
Step.__init__(self, args)
self.assay_description = utils.get_assay_text(self.assay)
self.version = __VERSION__
self.chemistry = args.chemistry