def matrix_10X(df,
outdir,
sample,
gtf_file,
dir_name='matrix_10X',
validated_barcodes=None):
matrix_10X_dir = f"{outdir}/{sample}_{dir_name}/"
if not os.path.exists(matrix_10X_dir):
os.mkdir(matrix_10X_dir)
id_name = gene_convert(gtf_file)
if validated_barcodes:
df = df.loc[df['Barcode'].isin(validated_barcodes), :]
df_UMI = df.groupby(['geneID', 'Barcode']).agg({'UMI': 'count'})
mtx = coo_matrix(
(df_UMI.UMI, (df_UMI.index.labels[0], df_UMI.index.labels[1])))
id = df_UMI.index.levels[0].to_series()
# add gene symbol
name = id.apply(lambda x: id_name[x])
genes = pd.concat([id, name], axis=1)
genes.columns = ['gene_id', 'gene_name']
barcodes = df_UMI.index.levels[1].to_series()
genes.to_csv(f'{matrix_10X_dir}/genes.tsv',
index=False,
sep='\t',
header=False)
barcodes.to_csv(f'{matrix_10X_dir}/barcodes.tsv', index=False, sep='\t')
mmwrite(f'{matrix_10X_dir}/matrix', mtx)
def count_capture_rna(args):
# check
_refFlat, gtf = glob_genomeDir(args.genomeDir)
id_name = gene_convert(gtf)
# 检查和创建输出目录
if not os.path.exists(args.outdir):
os.system('mkdir -p %s' % (args.outdir))
# umi纠错，输出Barcode geneID UMI count为表头的表格
count_detail_file = args.outdir + '/' + args.sample + '_count_detail.txt'
df_probe = bam2table(args.bam, count_detail_file, id_name)
df_probe.to_csv(f'{args.outdir}/{args.sample}_probe_gene_count.tsv',
sep='\t',
index=False)
df = pd.read_table(count_detail_file, header=0)
# call cells
pdf = args.outdir + '/barcode_filter_magnitude.pdf'
marked_counts_file = args.outdir + '/' + args.sample + '_counts.txt'
(validated_barcodes, threshold, cell_num,
CB_describe) = call_cells(df, args.cells, pdf, marked_counts_file)
# match barcode
sc_cell_barcodes, sc_cell_number = read_barcode_file(args.match_dir)
# 输出matrix
(CB_total_Genes, CB_reads_count, reads_mapped_to_transcriptome,
match_cell_str,
match_UMI_median) = expression_matrix(df, validated_barcodes, args.outdir,
args.sample, id_name,
sc_cell_barcodes, sc_cell_number)
# downsampling
validated_barcodes = set(validated_barcodes)
downsample_file = args.outdir + '/' + args.sample + '_downsample.txt'
Saturation = downsample(count_detail_file, validated_barcodes,
downsample_file)
# summary
stat_file = args.outdir + '/stat.txt'
get_summary(df, args.sample, Saturation, CB_describe, CB_total_Genes,
CB_reads_count, reads_mapped_to_transcriptome, match_cell_str,
match_UMI_median, stat_file, args.outdir + '/../')
report_prepare(marked_counts_file, downsample_file, args.outdir + '/..')
t = reporter(assay=args.assay,
name='count_capture_rna',
sample=args.sample,
stat_file=args.outdir + '/stat.txt',
outdir=args.outdir + '/..')
t.get_report()
def generate_matrix(gtf_file, matrix_file):
id_name = gene_convert(gtf_file)
matrix = pd.read_csv(matrix_file, sep="\t")
gene_name_col = matrix.geneID.apply(lambda x: id_name[x])
matrix.geneID = gene_name_col
matrix = matrix.drop_duplicates(subset=["geneID"], keep="first")
matrix = matrix.dropna()
matrix = matrix.rename({"geneID": ""}, axis='columns')
return matrix
def convert(gene_list_file, gtf):
gene_list_name, _count = read_one_col(gene_list_file)
id_name = gene_convert(gtf)
name_id = {}
for id in id_name:
name = id_name[id]
name_id[name] = id
gene_id_name_dic = {}
for gene_name in gene_list_name:
gene_id = name_id[gene_name]
gene_id_name_dic[gene_id] = gene_name
return gene_id_name_dic
def test_gtf(self):
'''
gtf_file = '/SGRNJ/Database/script/genome/hs/gtf/Homo_sapiens.GRCh38.99.gtf'
id_name = gene_convert(gtf_file)
print(f"ENSG00000001629: {id_name['ENSG00000001629']}")
gtf_file = '/SGRNJ01/RD_dir/pipeline_test/litao/genomes/Cricetulus_griseus/Cricetulus_griseus_crigri.CriGri_1.0.101.gtf'
id_name = gene_convert(gtf_file)
print(id_name)
'''
gtf_file = '/Public/Database/genome/Sus_scrofa/ncbi/GCF_000003025.6_Sscrofa11.1_genomic_new.gtf'
id_name = gene_convert(gtf_file)
print(id_name['tRNA-Asp'])
def expression_matrix(df, validated_barcodes, outdir, sample, gtf_file):
matrix_10X_dir = f"{outdir}/{sample}_matrix_10X/"
matrix_table_file = f"{outdir}/{sample}_matrix.tsv.gz"
if not os.path.exists(matrix_10X_dir):
os.mkdir(matrix_10X_dir)
df.loc[:, 'mark'] = 'UB'
df.loc[df['Barcode'].isin(validated_barcodes), 'mark'] = 'CB'
CB_total_Genes = df.loc[df['mark'] == 'CB', 'geneID'].nunique()
CB_reads_count = df.loc[df['mark'] == 'CB', 'count'].sum()
reads_mapped_to_transcriptome = df['count'].sum()
table = df.loc[df['mark'] == 'CB', :].pivot_table(
index='geneID', columns='Barcode', values='UMI',
aggfunc=len).fillna(0).astype(int)
id_name = gene_convert(gtf_file)
id = table.index.to_series()
name = id.apply(lambda x: id_name[x])
genes = pd.concat([id, name], axis=1)
genes.columns = ['gene_id', 'gene_name']
# write 10X matrix
table.columns.to_series().to_csv(f'{matrix_10X_dir}/barcodes.tsv',
index=False,
sep='\t')
genes.to_csv(f'{matrix_10X_dir}/genes.tsv',
index=False,
header=False,
sep='\t')
mmwrite(f'{matrix_10X_dir}/matrix', csr_matrix(table))
# convert id to name; write table matrix
table.index = name
table.index.name = ""
table.to_csv(matrix_table_file, sep="\t", compression='gzip')
return (CB_total_Genes, CB_reads_count, reads_mapped_to_transcriptome)
def expression_matrix(df, validated_barcodes, outdir, sample, gtf_file):
id_name = gene_convert(gtf_file)
df.loc[:, 'mark'] = 'UB'
df.loc[df['Barcode'].isin(validated_barcodes), 'mark'] = 'CB'
CB_total_Genes = df.loc[df['mark'] == 'CB', 'geneID'].nunique()
CB_reads_count = df.loc[df['mark'] == 'CB', 'count'].sum()
reads_mapped_to_transcriptome = df['count'].sum()
table = df.loc[df['mark'] == 'CB', :].pivot_table(
index='geneID', columns='Barcode', values='UMI',
aggfunc=len).fillna(0).astype(int)
# convert id to name; write table matrix
matrix_table_file = f"{outdir}/{sample}_matrix.tsv.gz"
id = table.index.to_series()
name = id.apply(lambda x: id_name[x])
table.index = name
table.index.name = ""
table.to_csv(matrix_table_file, sep="\t", compression='gzip')
return (CB_total_Genes, CB_reads_count, reads_mapped_to_transcriptome)