初始化

.gitignore

@@ -0,0 +1,215 @@
+# ---> Python
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+# ---> Perl
+!Build/
+.last_cover_stats
+/META.yml
+/META.json
+/MYMETA.*
+*.o
+*.pm.tdy
+*.bs
+
+# Devel::Cover
+cover_db/
+
+# Devel::NYTProf
+nytprof.out
+
+# Dist::Zilla
+/.build/
+
+# Module::Build
+_build/
+Build
+Build.bat
+
+# Module::Install
+inc/
+
+# ExtUtils::MakeMaker
+/blib/
+/_eumm/
+/*.gz
+/Makefile
+/Makefile.old
+/MANIFEST.bak
+/pm_to_blib
+/*.zip
+
+# ---> Perl6
+# Gitignore for Perl 6 (http://www.perl6.org)
+# As part of https://github.com/github/gitignore
+
+# precompiled files
+.precomp
+lib/.precomp
+
+nohup.out
+
+log/*
+!log/readme.md
+example/*
+!example/readme.md
+
+/.report/

database/chemo_drug_combine.csv

@@ -0,0 +1,28 @@
+癌种	用药方案	方案缩写	source
+非小细胞肺癌	顺铂+紫杉醇	TP	lung85gene
+非小细胞肺癌	卡铂+紫杉醇	TP	lung85gene
+非小细胞肺癌	顺铂+紫杉醇脂质体	LP	lung85gene
+非小细胞肺癌	卡铂+紫杉醇脂质体	LP	lung85gene
+非小细胞肺癌	顺铂+白蛋白紫杉醇	nab-TP	lung85gene
+非小细胞肺癌	卡铂+白蛋白紫杉醇	nab-TP	lung85gene
+非小细胞肺癌	顺铂+多西他赛	DP	lung85gene
+非小细胞肺癌	卡铂+多西他赛	DP	lung85gene
+非小细胞肺癌	奈达铂+多西他赛	DP	lung85gene
+非小细胞肺癌	顺铂+吉西他滨	GP	lung85gene
+非小细胞肺癌	卡铂+吉西他滨	GP	lung85gene
+非小细胞肺癌	顺铂+培美曲塞	PP	lung85gene
+非小细胞肺癌	卡铂+培美曲塞	PP	lung85gene
+非小细胞肺癌	顺铂+长春瑞滨	NP	lung85gene
+非小细胞肺癌	顺铂+依托泊苷	EP	lung85gene
+小细胞肺癌	顺铂+依托泊苷	EP	lung85gene
+小细胞肺癌	卡铂+依托泊苷	EC	lung85gene
+小细胞肺癌	洛铂+依托泊苷	EL	lung85gene
+小细胞肺癌	顺铂+伊立替康	IP	lung85gene
+小细胞肺癌	卡铂+伊立替康	IC	lung85gene
+结直肠癌	奥沙利铂+亚叶酸钙+氟尿嘧啶	FOLFOX	crc88gene
+结直肠癌	伊立替康+亚叶酸钙+氟尿嘧啶	FOLFIRI	crc88gene
+结直肠癌	奥沙利铂+卡培他滨	CAPEOX（又称Xelox）	crc88gene
+结直肠癌	伊立替康+奥沙利铂+亚叶酸钙+氟尿嘧啶	FOLFOXIRI	crc88gene
+结直肠癌	伊立替康+卡培他滨	CapIRI或XELIRI	crc88gene
+结直肠癌	奥沙利铂+雷替曲塞	/	crc88gene
+结直肠癌	伊立替康+雷替曲塞	/	crc88gene

main.py

@@ -0,0 +1,24 @@
+import json
+import os
+import socket
+import sys
+
+from docxtpl import DocxTemplate
+
+from tools.parsexlsx import run
+
+
+def main(path):
+    resjson = run(path)
+    res = json.loads(resjson)
+    barcode = res['c']['barcode']
+    tplpath = os.path.join(os.path.dirname(__file__), 'template', 'nreport.docx')
+    tpl = DocxTemplate(tplpath)
+    tpl.render(res)
+    path = os.path.join(os.path.dirname(__file__), 'result', f'{barcode}.docx')
+    tpl.save(path)
+    return path
+
+
+if __name__ == '__main__':
+    main(sys.argv[1])

scripts/check_report_merge_20230713.py

@@ -0,0 +1,486 @@
+#!/usr/bin/python3
+# -*- coding: UTF-8 -*-
+
+import pandas as pd
+from pandas import DataFrame
+import numpy as np
+import logging
+import re
+import sys
+import os
+import json
+import glob
+import openpyxl
+from openpyxl import Workbook, load_workbook
+from openpyxl.drawing.image import Image
+
+if len(sys.argv) != 3:
+    print(" ".join(['usage:python', sys.argv[0], 'output_dir', 'name']))
+    sys.exit()
+
+
+def snv_fusion_cnv(output_dir, name):
+    out_xlsx = "".join([output_dir, '/report/', name, '.check_new.xlsx'])
+
+    # genefunction
+    genefunction = {}
+    gf = open("/dataseq/jmdna/codes/reportbase/gene_function.txt", 'r', encoding='utf-8').readlines()
+    for line in gf[1:]:
+        gene = line.strip().split("\t")[0]
+        func = line.strip().split("\t")[1]
+        genefunction[gene.upper()] = func
+        genefunction['.'] = '.'
+
+        ##drug_mechanism
+    drug_mechanism = {}
+    drug_fh = open("/dataseq/jmdna/codes/reportbase/target_drug.txt", 'r', encoding='utf-8').readlines()
+    for line in drug_fh[1:]:
+        disease = line.split("\t")[8]
+        mechanism = line.split("\t")[11]
+        drugs = line.split("\t")[0].split('|') + line.split("\t")[1].split('|')
+        if disease or mechanism:
+            for drug in drugs:
+                drug_mechanism[drug.upper()] = "\\\\".join([disease, mechanism]).strip()
+
+    '''
+    snvindel_sheet
+    '''
+
+    ##input
+    filter_file = "".join([output_dir, '/report/', name, '.snp.indel.Somatic.annoall.hg19_multianno_filtered.txt'])
+    pos_file = "".join([output_dir, '/mutation/', name, '.snvindel.pos.dedup.txt'])
+    vus_file = "".join([output_dir, '/mutation/', name, '.snvindel.vus.txt'])
+    neg_file = "".join([output_dir, '/mutation/', name, '.snvindel.neg.txt'])
+    ##filter_file
+    if os.path.getsize(filter_file) > 0:
+        snv = pd.read_table(filter_file, sep="\t")
+        cols = [index for index, row in snv[snv['可信'] == 0].iterrows()]
+        snv.drop(cols, inplace=True)
+        snv.insert(loc=24, column='ACMG_level', value=0)
+        snv.insert(loc=25, column='Deleterious', value=0)
+        snv.insert(loc=26, column='freq_high', value=0)
+        for index, row in snv.iterrows():
+            if re.search("Likely_pathogenic|drug", (row['CLNSIG']), re.I):
+                snv.loc[index, 'ACMG_level'] = '2'
+            elif re.search("pathogenic", (row['CLNSIG']), re.I) and not re.search("Conflicting", (row['CLNSIG']), re.I):
+                snv.loc[index, 'ACMG_level'] = '1'
+            else:
+                snv.loc[index, 'ACMG_level'] = '3'
+            snv.loc[index, "Deleterious"] = (
+                snv.loc[index, ['MutationTaster_pred', 'FATHMM_pred', 'MetaLR_pred']].tolist().count("D"))
+            snv.loc[index, "freq_high"] = ((snv.loc[
+                index, ['1000g2015aug_all', '1000g2015aug_eas', 'esp6500siv2_all', 'ExAC_nontcga_ALL',
+                        'ExAC_nontcga_EAS', 'gnomAD_genome_ALL', 'gnomAD_genome_EAS']]).replace('.', '0')).max()
+        snv_1 = snv.iloc[:, list(range(14)) + [15, 17, 18, 20, 23, 24, 25, 26, 111, 112, 113]]
+    else:
+        snv_1 = pd.DataFrame(columns=[])
+
+    ##pos_file
+    if os.path.getsize(pos_file) > 0:
+        pos = pd.read_table(pos_file, sep="\t")
+        pos = pos.iloc[:, [7, 10, 18, 23, 24, 25, 29, 30, 31, 32]]
+        pos_1 = pd.DataFrame(
+            columns=['AAChange.refGene', 'OKBSIG', 'AMP_evidence_level', 'AMP_mut_level', 'Indication', 'Drug',
+                     'Response_Type', 'Evidence_Source', 'EfficacyEvidence', 'Drug_Detail', 'Gene_function',
+                     'Drug_Category'])
+        pos = list(pos.groupby(['Gene.refGene', 'AAChange.refGene', 'fun_change']))
+        for i in pos:
+            for index, row in i[1].iterrows():
+                drugs = row['药物中文名'].replace(" + ", ",")
+                drugs = list(set(drugs.split(",")))
+                drug_mm = ''
+                for drug in drugs:
+                    if drug.upper() in drug_mechanism.keys():
+                        drug_mm += '[[' + drug + ']]' + drug_mechanism[drug.upper()]
+                i[1].loc[index, ['Drug_Detail']] = drug_mm
+                if row['标签'] == '非适应症':
+                    row['证据等级'] = 'C'
+                if (re.search("敏感", row['Response_Type_C']) and row['证据等级'] == 'A'):
+                    i[1].loc[index, ['Drug_Category']] = 'a'
+                elif re.search("敏感", row['Response_Type_C']) and row['证据等级'] == 'C':
+                    i[1].loc[index, ['Drug_Category']] = 'b'
+                elif re.search("耐药", row['Response_Type_C']):
+                    i[1].loc[index, ['Drug_Category']] = 'd'
+                else:
+                    i[1].loc[index, ['Drug_Category']] = 'c'
+            i[1]['AMP_mut_level'] = i[1]['证据等级'].replace(['A', 'B', 'C', 'D'], ['I', 'I', 'II', 'II'])
+            pos_1.loc[len(pos_1)] = [i[0][1], i[0][2], '|'.join(list(i[1]['证据等级'])),
+                                     '|'.join(list(i[1]['AMP_mut_level'])), '|'.join(list(i[1]['疾病中文名'])),
+                                     '|'.join(list(i[1]['药物中文名'])), \
+                                     '|'.join(list(i[1]['Response_Type_C'])), '|'.join(list(i[1]['Evidence_Source_C'])),
+                                     '|'.join(list(i[1]['EfficacyEvidence'])), '|'.join(list(i[1]['Drug_Detail'])),
+                                     genefunction[i[0][0].upper()], '|'.join(list(i[1]['Drug_Category']))]
+    else:
+        pos_1 = pd.DataFrame(columns=[])
+
+    ##vus_file
+    if os.path.getsize(vus_file) > 0:
+        vus = pd.read_table(vus_file, sep="\t")
+        vus_1 = vus.iloc[:, [9, 17]]
+        vus_1.insert(loc=2, column='AMP_mut_level', value='III')
+        vus_1 = vus_1.rename(columns={'fun_change': 'OKBSIG'})
+    else:
+        vus_1 = pd.DataFrame(columns=[])
+
+    ##neg_file
+    if os.path.getsize(neg_file) > 0:
+        neg = pd.read_table(neg_file, sep="\t")
+        neg_1 = neg.iloc[:, [9, 17]]
+        neg_1.insert(loc=2, column='AMP_mut_level', value='IIII')
+        neg_1 = neg_1.rename(columns={'fun_change': 'OKBSIG'})
+    else:
+        neg_1 = pd.DataFrame(columns=[])
+
+    snvindel_sheet = pd.DataFrame(
+        columns=['可信', 'Chr', 'Start', 'End', 'Ref', 'Alt', 'AAChange.refGene', 'mutant_frequency', 'total_reads',
+                 'mutant_reads', 'strand_bias', 'Otherinfo10', 'Func.refGene', 'Gene.refGene', 'ExonicFunc.refGene',
+                 'avsnp150', 'cosmic91', 'CLNDN', 'CLNSIG', 'ACMG_level', 'Deleterious', 'freq_high', 'OKBSIG',
+                 'AMP_evidence_level', 'AMP_mut_level', 'Indication', 'Drug', 'Response_Type', 'Evidence_Source',
+                 'EfficacyEvidence', 'Drug_Detail', 'Gene_function', 'Drug_Category', 'Otherinfo11', 'Otherinfo12',
+                 'Otherinfo13'])
+    pos_vus_neg = pd.concat([pos_1, vus_1, neg_1])
+    snv_pos_vus_neg = snv_1.merge(pos_vus_neg, how='left', on='AAChange.refGene')
+    snvindel_sheet = pd.concat([snvindel_sheet, snv_pos_vus_neg])
+    snvindel_sheet.rename(columns={"可信": "Validated"})
+    snvindel_sheet = snvindel_sheet.replace(np.nan, '.')
+    snvindel_sheet.rename(columns={"可信": "Validated"}, inplace=True)
+
+    '''
+    fusion_sheet
+    '''
+
+    fusion_pos_file = "".join([output_dir, '/fusion/', name, '.fusion.pos.dedup.txt'])
+    fusion_vus_file = "".join([output_dir, '/fusion/', name, '.fusion.vus.txt'])
+    if os.path.getsize(fusion_pos_file) > 0:
+        fusion_pos = pd.read_table(fusion_pos_file, sep="\t")
+    else:
+        fusion_pos = pd.DataFrame(columns=[])
+
+    if os.path.getsize(fusion_vus_file) > 0:
+        fusion_vus = pd.read_table(fusion_vus_file, sep="\t")
+        fusion_vus.insert(loc=0, column='可信', value=1)
+    else:
+        fusion_vus = pd.DataFrame(columns=[])
+    fusion_pos_vus = pd.concat([fusion_pos, fusion_vus])
+    fusion_sheet = pd.DataFrame(
+        columns=['Validated', 'CHROM1', 'POS1', 'CHROM2', 'POS2', 'GENE1', 'GENE2', 'FUSION', 'Support_reads(PE:SR)',
+                 'Depth', 'FREQ1', 'FREQ2', 'OKBSIG', 'AMP_evidence_level', \
+                 'AMP_mut_level', 'Indication', 'Drug', 'Response_Type', 'Evidence_Source', 'Efficacy_Evidence',
+                 'Drug_Detail', 'Gene_function', 'Drug_Category', 'INFO', 'FORMAT', 'Sample'])
+
+    if not fusion_pos_vus.empty:
+        fusion_pos_vus = fusion_pos_vus.replace(np.nan, '.')
+        fusion = list(fusion_pos_vus.groupby(
+            ['可信', '#CHROM', 'POS', 'CHROM2', 'POS2', 'GENE1', 'GENE2', 'FUSION', 'FREQ1', 'FREQ2', 'fun_change',
+             'INFO', 'FORMAT', name, 'Gene_Symbol']))
+        for i in fusion:
+            for index, row in i[1].iterrows():
+                drugs = row['药物中文名'].replace(" + ", ",")
+                drugs = list(set(drugs.split(",")))
+                drug_mm = ''
+                for drug in drugs:
+                    if drug.upper() in drug_mechanism.keys():
+                        drug_mm += '[[' + drug + ']]' + drug_mechanism[drug.upper()]
+                i[1].loc[index, ['Drug_Detail']] = drug_mm
+                if row['标签'] == '非适应症':
+                    row['证据等级'] = 'C'
+                if (re.search("敏感", row['Response_Type_C']) and row['证据等级'] == 'A'):
+                    i[1].loc[index, ['Drug_Category']] = 'a'
+                elif re.search("敏感", row['Response_Type_C']) and row['证据等级'] == 'C':
+                    i[1].loc[index, ['Drug_Category']] = 'b'
+                elif re.search("耐药", row['Response_Type_C']):
+                    i[1].loc[index, ['Drug_Category']] = 'd'
+                elif row['Response_Type_C'] == '.':
+                    i[1].loc[index, ['Drug_Category']] = '.'
+                else:
+                    i[1].loc[index, ['Drug_Category']] = 'c'
+            i[1]['AMP_mut_level'] = i[1]['证据等级'].replace(['A', 'B', 'C', 'D'], ['I', 'I', 'II', 'II'])
+            fusion_sheet.loc[len(fusion_sheet)] = list(i[0][0:8]) + [i[0][13].split(":")[1],
+                                                                     i[0][13].split(":")[7]] + list(i[0][8:11]) + [
+                                                      '|'.join(list(i[1]['证据等级'])),
+                                                      '|'.join(list(i[1]['AMP_mut_level'])), \
+                                                      '|'.join(list(i[1]['疾病中文名'])), '|'.join(list(i[1]['药物中文名'])),
+                                                      '|'.join(list(i[1]['Response_Type_C'])),
+                                                      '|'.join(list(i[1]['Evidence_Source_C'])),
+                                                      '|'.join(list(i[1]['EfficacyEvidence'])), \
+                                                      '|'.join(list(i[1]['Drug_Detail'])),
+                                                      genefunction[i[0][14].upper()],
+                                                      '|'.join(list(i[1]['Drug_Category']))] + list(i[0][11:14])
+        fusion_sheet = fusion_sheet.replace(np.nan, '.')
+
+    '''
+    cnv_sheet
+    '''
+
+    cnv_pos_file = "/home/jm001/test/reference_standard/lung85gene/Tissue/BKDL202603539-1a/cnvkit/BKDL202603539-1a.cnv.pos.dedup.txt"
+    cnv_sheet = pd.DataFrame(
+        columns=['Validated', 'Chromosome', 'Start', 'End', 'Gene', 'Depth', 'Probes', 'Copy_number', 'OKBSIG',
+                 'Gene_Symbol', 'AMP_evidence_level', 'AMP_mut_level', \
+                 'Indication', 'Drug', 'Response_Type', 'Evidence_Source', 'Efficacy_Evidence', 'Drug_Detail',
+                 'Gene_Function', 'Drug_Category'])
+    if os.path.getsize(cnv_pos_file) > 0:
+        cnv_pos = pd.read_table(cnv_pos_file, sep="\t")
+        cnv = list(cnv_pos.groupby(
+            ['可信', 'chromosome', 'start', 'end', 'gene', 'depth', 'probes', 'cn', 'fun_change', 'Gene_Symbol']))
+        for i in cnv:
+            for index, row in i[1].iterrows():
+                drugs = row['药物中文名'].replace(" + ", ",")
+                drugs = list(set(drugs.split(",")))
+                drug_mm = ''
+                for drug in drugs:
+                    if drug.upper() in drug_mechanism.keys():
+                        drug_mm += '[[' + drug + ']]' + drug_mechanism[drug.upper()]
+                i[1].loc[index, ['Drug_Detail']] = drug_mm
+                if row['标签'] == '非适应症':
+                    row['证据等级'] = 'C'
+                if (re.search("敏感", row['Response_Type_C']) and row['证据等级'] == 'A'):
+                    i[1].loc[index, ['Drug_Category']] = 'a'
+                elif re.search("敏感", row['Response_Type_C']) and row['证据等级'] == 'C':
+                    i[1].loc[index, ['Drug_Category']] = 'b'
+                elif re.search("耐药", row['Response_Type_C']):
+                    i[1].loc[index, ['Drug_Category']] = 'd'
+                elif row['Response_Type_C'] == '.':
+                    i[1].loc[index, ['Drug_Category']] = '.'
+                else:
+                    i[1].loc[index, ['Drug_Category']] = 'c'
+            i[1]['AMP_mut_level'] = i[1]['证据等级'].replace(['A', 'B', 'C', 'D'], ['I', 'I', 'II', 'II'])
+            cnv_sheet.loc[len(cnv_sheet)] = list(i[0][0:10]) + ['|'.join(list(i[1]['证据等级'])),
+                                                                '|'.join(list(i[1]['AMP_mut_level'])), \
+                                                                '|'.join(list(i[1]['疾病中文名'])),
+                                                                '|'.join(list(i[1]['药物中文名'])),
+                                                                '|'.join(list(i[1]['Response_Type_C'])),
+                                                                '|'.join(list(i[1]['Evidence_Source_C'])),
+                                                                '|'.join(list(i[1]['EfficacyEvidence'])), \
+                                                                '|'.join(list(i[1]['Drug_Detail'])),
+                                                                genefunction[i[0][9].upper()],
+                                                                '|'.join(list(i[1]['Drug_Category']))]
+    else:
+        cnv_pos = pd.DataFrame(columns=[])
+
+    with pd.ExcelWriter(out_xlsx) as writer:
+        snvindel_sheet.to_excel(writer, sheet_name="snvindel", index=False)
+        fusion_sheet.to_excel(writer, sheet_name="fusion", index=False)
+        cnv_sheet.to_excel(writer, sheet_name="cnv", index=False)
+
+    ##加入cnvkit/*.cnv.png
+    wb = openpyxl.load_workbook(filename=out_xlsx)
+    ws = wb['cnv']
+    mr = ws.max_row
+    cell = 'C' + str(mr + 4)
+    cnv_pic = "".join([output_dir, '/cnvkit/', name, '.cnv.png'])
+    image = Image(cnv_pic)
+    ws.add_image(image, cell)
+    wb.save(out_xlsx)
+
+
+class PostProcess:
+    """
+    excel处理
+    """
+
+    def __init__(self, path, outpath):
+        self.path = path
+        self.outpath = outpath
+        self.neeecol = self.need_col()
+
+    def need_col(self):
+        """
+        读取所需列
+        """
+        path = os.path.join(os.path.dirname(__file__), 'columns.csv')
+        cols = pd.read_csv(path)
+        cols = cols.fillna('')
+        cols_record = cols.to_dict('list')
+        for sheet in cols_record:
+            cols_record[sheet] = [x for x in cols_record[sheet] if x]
+        return cols_record
+
+    def msi(self):
+        """
+            Process msi result files
+        """
+        msi_files = glob.glob(os.path.join(self.path, 'MSI', '*.msi'))
+        msi_res = dict()
+        if msi_files:
+            df = pd.read_csv(msi_files[0], sep='\t')
+            res = df.to_dict('records')[0]
+            msi_res['msi_count'] = res['Total_Number_of_Sites']
+            msi_res['msi_value'] = res['%']
+            if msi_res['msi_value'] >= 0.3:
+                msi_res['msi_result'] = 'MSI-H'
+                msi_res['msi_predict'] = '对免疫检查点抑制剂可能敏感'
+            else:
+                msi_res['msi_result'] = 'MSS'
+                msi_res['msi_predict'] = '对免疫检查点抑制剂可能不敏感'
+        return [msi_res]
+
+    def chemo(self):
+        """
+        化疗
+        """
+        chemo_files = glob.glob(os.path.join(self.path, 'chemo', '*chemo.res.txt'))
+        chemo_res = []
+        if chemo_files:
+            df = pd.read_csv(chemo_files[0], sep='\t')
+            df = df.fillna('.')
+            chemo_res = df.to_dict('records')
+        return chemo_res
+
+    def heredity(self):
+        """
+        遗传
+        """
+        heredi_files = glob.glob(os.path.join(self.path, 'mutation', '*Germline*filtered.txt'))
+        heredires = []
+        if heredi_files:
+            df = pd.read_csv(heredi_files[0], sep='\t')
+            df = df.fillna('.')
+            tmdf1 = df[
+                ['1000g2015aug_all', '1000g2015aug_eas', 'esp6500siv2_all', 'ExAC_nontcga_ALL', 'ExAC_nontcga_EAS',
+                 'gnomAD_genome_ALL', 'gnomAD_genome_EAS']].replace('.', 0).applymap(lambda x: eval(str(x)))
+            df['freq_high'] = tmdf1.max(axis=1)
+            tmdf2 = df[['MutationTaster_pred', 'FATHMM_pred', 'MetaLR_pred']]
+            df['Deleterious'] = tmdf2.apply(lambda x: x.tolist().count('D'), axis=1)
+            df_need = df[self.neeecol.get('HCS', [])]
+            try:
+                heredires = df_need.to_dict('records')
+            except KeyError as e:
+                raise UserWarning('表头设置和配置文件不对应', e)
+        return heredires
+
+    def MMR(self):
+        """
+        MMR
+        """
+        mmr_files = glob.glob(os.path.join(self.path, 'MMR', '*mmr.pre.txt'))
+        mmr = []
+        if mmr_files:
+            df = pd.read_csv(mmr_files[0], sep='\t')
+            df = df.fillna('.')
+            tmdf1 = df[
+                ['1000g2015aug_all', '1000g2015aug_eas', 'esp6500siv2_all', 'ExAC_nontcga_ALL', 'ExAC_nontcga_EAS',
+                 'gnomAD_genome_ALL', 'gnomAD_genome_EAS']].replace('.', 0).applymap(lambda x: eval(str(x)))
+            df['freq_high'] = tmdf1.max(axis=1)
+            tmdf2 = df[['MutationTaster_pred', 'FATHMM_pred', 'MetaLR_pred']]
+            df['Deleterious'] = tmdf2.apply(lambda x: x.tolist().count('D'), axis=1)
+            df_need = df[self.neeecol.get('HCS', [])]
+            try:
+                mmr = df_need.to_dict('records')
+            except KeyError as e:
+                raise UserWarning('表头设置和配置文件不对应', e)
+        return mmr
+
+    def hotspot(self):
+        hotspot_files = glob.glob(
+            os.path.join(self.path, 'mutation', 'hotspot', '*hotspot.snp.indel.filter.anno.hg19_multianno.txt'))
+        if hotspot_files:
+            return self.txt_2_excel(hotspot_files[0])
+
+    def splicing(self):
+        splicing_files = glob.glob(
+            os.path.join(self.path, 'mutation', '*.target.splicing.txt'))
+        if splicing_files:
+            return self.txt_2_excel(splicing_files[0])
+
+    def indication(self):
+        indication_files = glob.glob(
+            os.path.join(self.path, 'mutation', '*indication.txt'))
+        if indication_files:
+            return self.txt_2_excel(indication_files[0])
+
+    def longindel(self):
+        longindel_files = glob.glob(
+            os.path.join(self.path, 'fusion', '*.longindel.pos.txt'))
+        if longindel_files:
+            return self.txt_2_excel(longindel_files[0])
+
+    def cms(self):
+        """
+        样本信息
+        """
+        cms_files = glob.glob(os.path.join(self.path, 'qc', '*_post.json'))
+        cms_info_need = []
+        if cms_files:
+            file_read = open(cms_files[0], 'r')
+            cms_info = json.load(file_read)['data']
+            file_read.close()
+            df = pd.DataFrame(cms_info)
+            df_need = df[self.neeecol.get('sample_info', [])]
+            try:
+                cms_info_need = df_need.to_dict('records')
+            except KeyError as e:
+                raise UserWarning('表头设置和配置文件不对应', e)
+        return cms_info_need
+
+    def qc(self):
+        qc_files = glob.glob(os.path.join(self.path, 'qc', '*_post.json'))
+        qc_res = []
+        if qc_files:
+            df = pd.read_csv(qc_files[0], sep='\t', header=None)
+            df = df.set_index(0).T
+            qc_res = df.to_dict('records')
+        return qc_res
+
+    #
+    # def snv(self):
+    #     # filter file
+    #     filter_files = glob.glob(os.path.join(self.path, 'report', '*snp.indel.Somatic.annoall.hg19_multianno_filtered.txt'))
+    #     if filter_files:
+    #         snv = pd.read_csv(filter_files[0], sep="\t")
+    #     def sign_drug_Category(x):
+    #         if '敏感' in x['Response_Type_C'] and x['证据等级'] == 'A':
+    #             return 'a'
+    #         elif '敏感' in x['Response_Type_C'] and x['证据等级'] == 'C':
+    #             return 'b'
+    #         elif '耐药' in x['Response_Type_C']:
+    #             return 'd'
+    #         else:
+    #             return 'c'
+    #     # pos_file 处理
+    #     pos_files = glob.glob(os.path.join(self.path, 'mutation', '*snvindel.pos.txt'))
+    #     if pos_files:
+    #         pos = pd.read_csv(pos_files[0], sep='\t')
+    #         pos['证据等级'] = pos.apply(lambda x: 'C' if x['标签'] == '非适应症' else x['证据等级'], axis=1)
+    #         pos['Drug_Category'] = pos.apply(sign_drug_Category, axis=1)
+    #         pos['AMP_mut_level'] = pos['证据等级'].replace(['A', 'B', 'C', 'D'], ['I', 'I', 'II', 'II'])
+    #         agg_list = ['证据等级', 'AMP_mut_level', '疾病中文名', '药物中文名', '证据等级', 'Response_Type_C', 'Evidence_Source_C',
+    #                     'EfficacyEvidence', 'Drug_Category']
+    #         agg_dict = {column: ','.join for column in agg_list}
+    #         pos_group =pos.groupby(['Gene.refGene','AAChange.refGene','fun_change']).agg(agg_dict, axis=1)
+
+    def txt_2_excel(self, path):
+        try:
+            df = pd.read_csv(path, sep='\t')
+        except pd.errors.EmptyDataError:
+            return []
+        return df.to_dict('records')
+
+    def collect(self):
+        writer = pd.ExcelWriter(self.outpath, mode='a', engine='openpyxl')
+        sheet = {
+            'MSI': self.msi(),
+            'chemo': self.chemo(),
+            'HCS': self.heredity(),
+            'sample_info': self.cms(),
+            'MMR': self.MMR(),
+            'hotspot': self.hotspot(),
+            'MET': self.splicing(),
+            'indication': self.indication(),
+            'longindel': self.longindel(),
+            'qc': self.qc()
+        }
+        # 遍历CSV文件列表
+        for sheet_name in sheet:
+            # 读取CSV文件为DataFrame
+            df = pd.DataFrame(sheet[sheet_name])
+            df.to_excel(writer, sheet_name=sheet_name, index=False)
+        # 保存并关闭Excel写入器
+        writer.close()
+
+
+if __name__ == '__main__':
+    snv_fusion_cnv(sys.argv[1], sys.argv[2])
+    # 未加日志，未添加路径
+    out_xlsx = "".join([sys.argv[1], '/report/', sys.argv[2], '.check_new.xlsx'])
+    postprocess = PostProcess(sys.argv[1], out_xlsx)
+    postprocess.collect()

scripts/comcancergene_report.py

@@ -0,0 +1,864 @@
+#!/usr/bin/python3
+# -*- coding: UTF-8 -*-
+
+##https://www.pianshen.com/article/5314917437/
+##https://zhuanlan.zhihu.com/p/366902690
+##https://itpcb.com/a/277599
+import docxtpl
+from docx.shared import Mm
+from docxtpl import DocxTemplate,RichText
+import pandas as pd
+from pandas import DataFrame
+import re
+import sys
+import os
+import json
+import time
+
+if len(sys.argv) != 5:
+    print(" ".join(['usage:python',sys.argv[0],'output_dir','tumor','sample_type(t for tissue,c for cfdna)']),'projcet')
+    sys.exit()
+
+
+output_dir=sys.argv[1]
+name=sys.argv[2]
+Sample_type=sys.argv[3]
+projcet=sys.argv[4]
+snv_base="".join([name,'.snvindel.pos.dedup.txt'])
+snv_file='/'.join([output_dir,'mutation',snv_base])
+snv_base_vus="".join([name,'.snvindel.vus.txt'])
+snv_file_vus='/'.join([output_dir,'mutation',snv_base_vus])
+fusion_base="".join([name,'.fusion.pos.dedup.txt'])
+fusion_file='/'.join([output_dir,'fusion',fusion_base])
+cnv_base="".join([name,'.cnv.pos.dedup.txt'])
+cnv_file='/'.join([output_dir,'cnvkit',cnv_base])
+qc_base=''.join([name,'_qc.txt'])
+qc_file='/'.join([output_dir,'qc',qc_base])
+report_base="".join([name,'_report.docx'])
+report_file='/'.join([output_dir,'report',report_base])
+indication_file="".join([output_dir,'/mutation/','indication.txt'])
+
+context = {'list1':[],'list2':{},'list3':{},'clingene1':[],'clingene2':[],'nonclingenes':[],'genefunc':{},
+'indication':[],'mmr':[],'chemo':[]}
+
+
+#genefunction
+genefunction={}
+gf=open("/dataseq/jmdna/codes/reportbase/gene_function.txt",'r',encoding='utf-8').readlines()
+for line in gf[1:]:
+    gene=line.strip().split("\t")[0]
+    func=line.strip().split("\t")[1]
+    genefunction[gene.upper()]=func
+
+##sensitive_resistant_drug
+drug_disease={}
+drug_mechanism={}
+drug_fh=open("/dataseq/jmdna/codes/reportbase/target_drug.txt",'r',encoding='utf-8').readlines()
+for line in drug_fh[1:]:
+    disease=line.split("\t")[8]
+    mechanism=line.split("\t")[11]
+    drugs=line.split("\t")[0].split('|')
+    if disease or mechanism:
+        for drug in drugs:
+            drug_disease[drug.upper()]=disease
+            drug_mechanism[drug.upper()]=mechanism
+
+       
+sensitive_resistant_drug=[{'type':'可能敏感药物','drug':[]},{'type':'可能耐药药物','drug':[]}]
+    
+##somatic snvindel处理
+snv_size = os.path.getsize(snv_file)
+if snv_size>0:
+    snv=pd.read_table(snv_file,sep="\t")
+    cols=[index for index,row in snv[snv['可信']==0].iterrows()]
+    snv.drop(cols,inplace=True)    
+    genes=snv['Gene.refGene'].drop_duplicates()
+    if len(genes):
+      for gene in genes:
+        rt={}
+        rt[gene]=[]
+        muts=snv['AAChange.refGene'][snv['Gene.refGene']==gene].drop_duplicates()
+        for mut in muts:
+            info2={mut:[]}
+            for index,row in snv[snv['AAChange.refGene']==mut].iterrows():    
+                info3={}
+                info3['drug']=row['药物中文名']
+                info3['effect']=row['Response_Type_C']
+                info3['tumor']=row['疾病中文名']
+                info3['evidence']=row['Evidence_Source_C']
+                info3['sig']=row['EfficacyEvidence']
+                info2[mut].append(info3)
+##sensitive_resistant_drug
+                drugs=row['Drug'].replace(" + ",",")
+                drugs=drugs.split(",")
+                drugs_chinese=row['药物中文名'].replace(" + ",",")
+                drugs_chinese=drugs_chinese.split(",")
+                bool=0
+                for drug in drugs:
+                    if drug.upper() in drug_disease.keys():
+                        if re.search(r'敏感',row['Response_Type_C']):
+                            sensitive_drug={}
+                            sensitive_drug['name']=drugs_chinese[bool]                    
+                            sensitive_drug['mechanism']=("\n".join([drug_disease[drug.upper()],drug_mechanism[drug.upper()]])).strip()
+                            if sensitive_drug not in sensitive_resistant_drug[0]['drug']:
+                                sensitive_resistant_drug[0]['drug'].append(sensitive_drug)
+                        elif re.search(r'耐药',row['Response_Type_C']): 
+                            resistant_drug={}
+                            resistant_drug['name']=drugs_chinese[bool]
+                            resistant_drug['mechanism']=("\n".join([drug_disease[drug.upper()],drug_mechanism[drug.upper()]])).strip()
+                            if resistant_drug not in sensitive_resistant_drug[1]['drug']:
+                                sensitive_resistant_drug[1]['drug'].append(resistant_drug)
+                    bool+=1                            
+            context['list2'][mut]=info2[mut]
+            info={}
+            info['gene']=snv['Gene.refGene'][snv['AAChange.refGene']==mut].reset_index(drop=True)[0]
+            m=re.search(r'(p\..*)$',mut)
+            if m:
+                info['p']=m.group(1)
+            else:
+                m=re.search(r'(c\..*)$',mut)
+                info['p']=m.group(1)
+            info['freq']=snv['Freq'][snv['AAChange.refGene']==mut].reset_index(drop=True)[0]
+            A=[]
+            B=[]
+            C=[]
+            D=[]  			
+            for index,row in snv[(snv['AAChange.refGene']==mut) & (snv['标签']=='适应症') & snv['Response_Type_C'].str.contains("敏感")].iterrows():
+                ds=row['药物中文名'].split(",")
+                evidence='A'
+                ds_new=[str(x) + '【' + evidence + ' 级】'for x in ds]
+                A.extend(ds_new)			
+            for index,row in snv[(snv['AAChange.refGene']==mut) & (snv['标签']=='非适应症') & snv['Response_Type_C'].str.contains("敏感")].iterrows():
+                ds=row['药物中文名'].split(",")
+                evidence='C'
+                ds_new=[str(x) + '【' + evidence + ' 级】'for x in ds]
+                B.extend(ds_new)				
+            for index,row in snv[(snv['AAChange.refGene']==mut) & (snv['标签']=='.') & snv['Response_Type_C'].str.contains("敏感")].iterrows():
+                ds=row['药物中文名'].split(",")
+                evidence=row['证据等级']
+                ds_new=[str(x) + '【' + evidence + ' 级】'for x in ds]
+                C.extend(ds_new)
+            for index,row in snv[(snv['AAChange.refGene']==mut) & snv['Response_Type_C'].str.contains("耐药")].iterrows():
+                evidence=''
+                if row['标签']=='非适应症':
+                    evidence='C'
+                else:
+                    evidence=row['证据等级']				
+                ds=row['药物中文名'].split(",")
+                ds_new=[str(x) + '【' + evidence + ' 级】'for x in ds]
+                D.extend(ds_new)
+            A=sorted(set(A),key=A.index)
+            B=sorted(set(B),key=B.index)
+            C=sorted(set(C),key=C.index)
+            D=sorted(set(D),key=D.index)            
+            info['drug_A']="\n".join(A)
+            info['drug_B']="\n".join(B)
+            info['drug_C']="\n".join(C)
+            info['drug_D']="\n".join(D)
+            if not info['drug_A']:
+                info['drug_A']='/'
+            if not info['drug_B']:
+                info['drug_B']='/'
+            if not info['drug_C']:
+                info['drug_C']='/'
+            if not info['drug_D']:
+                info['drug_D']='/'
+            context['list1'].append(info)
+            rt[gene].append("".join([info['p'],'(',info['freq'],')']))
+##genefunc            
+            context['genefunc'][mut]=genefunction[gene.upper()]          
+##clingenes            
+            clingene1={}
+            clingene2={}            
+            for index,row in snv[(snv['AAChange.refGene']==mut)].iterrows():
+                if row['标签']=='适应症' or row['证据等级']=='B':
+                    clingene1['freq']=snv['Freq'][snv['AAChange.refGene']==mut].reset_index(drop=True)[0]
+                    if len((snv['AAChange.refGene'][snv['AAChange.refGene']==mut].reset_index(drop=True)[0]).split(":")) == 5:
+                        (clingene1['gene'],clingene1['transcript'],clingene1['exon'],clingene1['nacid'],clingene1['aacid'])=(snv['AAChange.refGene'][snv['AAChange.refGene']==mut].reset_index(drop=True)[0]).split(":")
+                    else:
+                        (clingene1['gene'],clingene1['transcript'],clingene1['exon'],clingene1['nacid'])=(snv['AAChange.refGene'][snv['AAChange.refGene']==mut].reset_index(drop=True)[0]).split(":")
+                        clingene1['aacid'] = '/'
+                    clingene1['muttype']=snv['ExonicFunc.refGene'][snv['AAChange.refGene']==mut].reset_index(drop=True)[0]
+                    if re.match("nonsynonymous SNV",clingene1['muttype']):
+                        clingene1['muttype']='错义突变'
+                    elif re.search("^frameshift",clingene1['muttype']):
+                        clingene1['muttype']='移码突变'
+                    elif re.search("^nonframeshift",clingene1['muttype']):
+                        clingene1['muttype']='非移码突变'
+                    elif re.match("stopgain",clingene1['muttype']):
+                        clingene1['muttype']='提前终止'
+                    else:
+                        clingene1['muttype']='/'
+                    context['clingene1'].append(clingene1)
+                else:
+                    clingene2['freq']=snv['Freq'][snv['AAChange.refGene']==mut].reset_index(drop=True)[0]
+                    if len((snv['AAChange.refGene'][snv['AAChange.refGene']==mut].reset_index(drop=True)[0]).split(":")) == 5:
+                        (clingene2['gene'],clingene2['transcript'],clingene2['exon'],clingene2['nacid'],clingene2['aacid'])=(snv['AAChange.refGene'][snv['AAChange.refGene']==mut].reset_index(drop=True)[0]).split(":")
+                    else:
+                        (clingene2['gene'],clingene2['transcript'],clingene2['exon'],clingene2['nacid'])=(snv['AAChange.refGene'][snv['AAChange.refGene']==mut].reset_index(drop=True)[0]).split(":")
+                        clingene2['aacid'] = '/'
+                    clingene2['muttype']=snv['ExonicFunc.refGene'][snv['AAChange.refGene']==mut].reset_index(drop=True)[0]
+                    if re.match("nonsynonymous SNV",clingene2['muttype']):
+                        clingene2['muttype']='错义突变'
+                    elif re.search("^frameshift",clingene2['muttype']):
+                        clingene2['muttype']='移码突变'
+                    elif re.search("^nonframeshift",clingene2['muttype']):
+                        clingene2['muttype']='非移码突变'
+                    elif re.match("stopgain",clingene2['muttype']):
+                        clingene2['muttype']='提前终止'
+                    else:
+                        clingene2['muttype']='/'
+                    context['clingene2'].append(clingene2)						
+                break                
+        context['list3'][gene]="\n".join(rt[gene])
+    else:     
+      snv_size=0
+
+
+##target vus and nontarget vus
+
+snv_size_vus = os.path.getsize(snv_file_vus)
+if snv_size_vus>0:
+    snv_vus=pd.read_table(snv_file_vus,sep="\t")
+    for index,row in snv_vus.iterrows():
+        if float(row['Freq'].replace('%',''))>=2:
+            nonclingene={}
+            if len(row['AAChange.refGene'].split(":")) == 5:
+                (nonclingene['gene'],nonclingene['transcript'],nonclingene['exon'],nonclingene['nacid'],nonclingene['aacid'])=row['AAChange.refGene'].split(":")
+            else:
+                (nonclingene['gene'],nonclingene['transcript'],nonclingene['exon'],nonclingene['nacid'])=row['AAChange.refGene'].split(":")
+                nonclingene['aacid'] = '/'
+            nonclingene['freq']=row['Freq']
+            nonclingene['muttype']=row['ExonicFunc.refGene']
+            if re.match("nonsynonymous SNV",nonclingene['muttype']):
+                nonclingene['muttype']='错义突变'
+            elif re.search("^frameshift",nonclingene['muttype']):
+                nonclingene['muttype']='移码突变'
+            elif re.search("^nonframeshift",nonclingene['muttype']):
+                nonclingene['muttype']='非移码突变'
+            elif re.match("stopgain",nonclingene['muttype']):
+                nonclingene['muttype']='提前终止'
+            else:
+                nonclingene['muttype']='/'
+            context['nonclingenes'].append(nonclingene)   
+ 
+
+##fusion处理
+fusion_size = os.path.getsize(fusion_file)
+if fusion_size>0:
+    fusion=pd.read_table(fusion_file,sep="\t")
+    cols=[index for index,row in fusion[fusion['可信']==0].iterrows()]
+    fusion.drop(cols,inplace=True)
+    genes=fusion['Gene_Symbol'].drop_duplicates()
+    if len(genes):
+      for gene in genes:
+        rt={}
+        rt[gene]=[]
+        fusions=fusion['FUSION'][fusion['Gene_Symbol']==gene].drop_duplicates()
+        for mut in fusions:
+            info2={mut:[]}
+            for index,row in fusion[fusion['FUSION']==mut].iterrows():    
+                info3={}
+                info3['drug']=row['药物中文名']
+                info3['effect']=row['Response_Type_C']
+                info3['tumor']=row['疾病中文名']
+                info3['evidence']=row['Evidence_Source_C']
+                info3['sig']=row['EfficacyEvidence']
+                info2[mut].append(info3)
+##sensitive_resistant_drug
+                drugs=row['Drug'].replace(" + ",",")
+                drugs=drugs.split(",")
+                drugs_chinese=row['药物中文名'].replace(" + ",",")
+                drugs_chinese=drugs_chinese.split(",")
+                bool=0
+                for drug in drugs:
+                    if drug.upper() in drug_disease.keys():
+                        if re.search(r'敏感',row['Response_Type_C']):
+                            sensitive_drug={}
+                            sensitive_drug['name']=drugs_chinese[bool]                    
+                            sensitive_drug['mechanism']=("\n".join([drug_disease[drug.upper()],drug_mechanism[drug.upper()]])).strip()
+                            if sensitive_drug not in sensitive_resistant_drug[0]['drug']:
+                                sensitive_resistant_drug[0]['drug'].append(sensitive_drug)
+                        elif re.search(r'耐药',row['Response_Type_C']): 
+                            resistant_drug={}
+                            resistant_drug['name']=drugs_chinese[bool]
+                            resistant_drug['mechanism']=("\n".join([drug_disease[drug.upper()],drug_mechanism[drug.upper()]])).strip()
+                            if resistant_drug not in sensitive_resistant_drug[1]['drug']:
+                                sensitive_resistant_drug[1]['drug'].append(resistant_drug)
+                    bool+=1  
+            context['list2'][mut]=info2[mut]
+            info={}
+            info['gene']=mut
+            info['p']='融合'
+            info['freq']="".join([str(fusion['FREQ1'][fusion['FUSION']==mut].reset_index(drop=True)[0]),'%'])
+            A=[]
+            B=[]
+            C=[]
+            D=[]  			
+            for index,row in fusion[(fusion['FUSION']==mut) & (fusion['标签']=='适应症') & fusion['Response_Type_C'].str.contains("敏感")].iterrows():
+                ds=row['药物中文名'].split(",")
+                evidence='A'
+                ds_new=[str(x) + '【' + evidence + ' 级】'for x in ds]
+                A.extend(ds_new)			
+            for index,row in fusion[(fusion['FUSION']==mut) & (fusion['标签']=='非适应症') & fusion['Response_Type_C'].str.contains("敏感")].iterrows():
+                ds=row['药物中文名'].split(",")
+                evidence='C'
+                ds_new=[str(x) + '【' + evidence + ' 级】'for x in ds]
+                B.extend(ds_new)				
+            for index,row in fusion[(fusion['FUSION']==mut) & (fusion['标签']=='.') & fusion['Response_Type_C'].str.contains("敏感")].iterrows():
+                ds=row['药物中文名'].split(",")
+                evidence=row['证据等级']
+                ds_new=[str(x) + '【' + evidence + ' 级】'for x in ds]
+                C.extend(ds_new)
+            for index,row in fusion[(fusion['FUSION']==mut) & fusion['Response_Type_C'].str.contains("耐药")].iterrows():
+                evidence=''
+                if row['标签']=='非适应症':
+                    evidence='C'
+                else:
+                    evidence=row['证据等级']				
+                ds=row['药物中文名'].split(",")
+                ds_new=[str(x) + '【' + evidence + ' 级】'for x in ds]
+                D.extend(ds_new)
+            A=sorted(set(A),key=A.index)
+            B=sorted(set(B),key=B.index)
+            C=sorted(set(C),key=C.index)
+            D=sorted(set(D),key=D.index) 
+            info['drug_A']="\n".join(A)
+            info['drug_B']="\n".join(B)
+            info['drug_C']="\n".join(C)
+            info['drug_D']="\n".join(D)
+#            info['drug_A']="\n".join(list(set(fusion['药物中文名'][(fusion['FUSION']==mut) & (fusion['标签']=='适应症') & fusion['Response_Type_C'].str.contains("敏感")].str.cat(sep=",").split(","))))
+#            info['drug_B']="\n".join(list(set(fusion['药物中文名'][(fusion['FUSION']==mut) & (fusion['标签']=='非适应症') & fusion['Response_Type_C'].str.contains("敏感")].str.cat(sep=",").split(","))))
+#            info['drug_C']="\n".join(list(set(fusion['药物中文名'][(fusion['FUSION']==mut) & (fusion['标签']=='.') & fusion['Response_Type_C'].str.contains("敏感")].str.cat(sep=",").split(","))))
+#            info['drug_D']="\n".join(list(set(fusion['药物中文名'][(fusion['FUSION']==mut) & fusion['Response_Type_C'].str.contains("耐药")].str.cat(sep=",").split(","))))
+            if not info['drug_A']:
+                info['drug_A']='/'
+            if not info['drug_B']:
+                info['drug_B']='/'
+            if not info['drug_C']:
+                info['drug_C']='/'
+            if not info['drug_D']:
+                info['drug_D']='/'    
+            context['list1'].append(info)
+            rt[gene].append("".join([info['gene'],'(',info['freq'],')']))
+##genefunc            
+            context['genefunc'][mut]=genefunction[gene.upper()]
+##clingenes
+            clingene1={}
+            clingene2={}            
+            for index,row in fusion[(fusion['FUSION']==mut)].iterrows():
+                if row['标签']=='适应症' or row['证据等级']=='B':            
+                    clingene1['gene']= info['gene']
+                    clingene1['freq']= info['freq']
+                    (clingene1['transcript'],clingene1['exon'],clingene1['nacid'],clingene1['aacid'])=("/","/","/","/")
+                    clingene1['muttype']= '融合'
+                    context['clingene1'].append(clingene1)
+                else:
+                    clingene2['gene']= info['gene']
+                    clingene2['freq']= info['freq']
+                    (clingene2['transcript'],clingene2['exon'],clingene2['nacid'],clingene2['aacid'])=("/","/","/","/")
+                    clingene2['muttype']= '融合'
+                    context['clingene2'].append(clingene2)            
+        context['list3'][gene]="\n".join(rt[gene])
+    else:
+      fusion_size=0
+
+
+##cnv处理
+cnv_size = os.path.getsize(cnv_file)
+if cnv_size>0:
+    cnv=pd.read_table(cnv_file,sep="\t")
+    cols=[index for index,row in cnv[cnv['可信']==0].iterrows()]
+    cnv.drop(cols,inplace=True)
+    genes=cnv['gene'].drop_duplicates()
+    if len(genes):
+      for gene in genes:
+        rt={}
+        rt[gene]=[]
+        cnvs=cnv['Gene_Symbol'][cnv['gene']==gene].drop_duplicates()
+        for mut in cnvs:
+            info={}
+            info['gene']=mut
+            copy=cnv['cn'][cnv['Gene_Symbol']==mut].reset_index(drop=True)[0]
+            if copy > 2:
+                info['p']='扩增'
+            else:
+                info['p']='缺失'
+            A=[]
+            B=[]
+            C=[]
+            D=[]  			
+            for index,row in cnv[(cnv['Gene_Symbol']==mut) & (cnv['标签']=='适应症') & cnv['Response_Type_C'].str.contains("敏感")].iterrows():
+                ds=row['药物中文名'].split(",")
+                evidence='A'
+                ds_new=[str(x) + '【' + evidence + ' 级】'for x in ds]
+                A.extend(ds_new)			
+            for index,row in cnv[(cnv['Gene_Symbol']==mut) & (cnv['标签']=='非适应症') & cnv['Response_Type_C'].str.contains("敏感")].iterrows():
+                ds=row['药物中文名'].split(",")
+                evidence='C'
+                ds_new=[str(x) + '【' + evidence + ' 级】'for x in ds]
+                B.extend(ds_new)				
+            for index,row in cnv[(cnv['Gene_Symbol']==mut) & (cnv['标签']=='.') & cnv['Response_Type_C'].str.contains("敏感")].iterrows():
+                ds=row['药物中文名'].split(",")
+                evidence=row['证据等级']
+                ds_new=[str(x) + '【' + evidence + ' 级】'for x in ds]
+                C.extend(ds_new)
+            for index,row in cnv[(cnv['Gene_Symbol']==mut) & cnv['Response_Type_C'].str.contains("耐药")].iterrows():
+                evidence=''
+                if row['标签']=='非适应症':
+                    evidence='C'
+                else:
+                    evidence=row['证据等级']				
+                ds=row['药物中文名'].split(",")
+                ds_new=[str(x) + '【' + evidence + ' 级】'for x in ds]
+                D.extend(ds_new)
+            A=sorted(set(A),key=A.index)
+            B=sorted(set(B),key=B.index)
+            C=sorted(set(C),key=C.index)
+            D=sorted(set(D),key=D.index) 
+            info['drug_A']="\n".join(A)
+            info['drug_B']="\n".join(B)
+            info['drug_C']="\n".join(C)
+            info['drug_D']="\n".join(D)
+            info['freq']=" ".join([str(copy),'拷贝'])
+#            info['drug_A']="\n".join(list(set(cnv['药物中文名'][(cnv['Gene_Symbol']==mut) & (cnv['标签']=='适应症') & cnv['Response_Type_C'].str.contains("敏感")].str.cat(sep=",").split(","))))
+#            info['drug_B']="\n".join(list(set(cnv['药物中文名'][(cnv['Gene_Symbol']==mut) & (cnv['标签']=='非适应症') & cnv['Response_Type_C'].str.contains("敏感")].str.cat(sep=",").split(","))))
+#            info['drug_C']="\n".join(list(set(cnv['药物中文名'][(cnv['Gene_Symbol']==mut) & (cnv['标签']=='.') & cnv['Response_Type_C'].str.contains("敏感")].str.cat(sep=",").split(","))))
+#            info['drug_D']="\n".join(list(set(cnv['药物中文名'][(cnv['Gene_Symbol']==mut) & cnv['Response_Type_C'].str.contains("耐药")].str.cat(sep=",").split(","))))
+            if not info['drug_A']:
+                info['drug_A']='/'
+            if not info['drug_B']:
+                info['drug_B']='/'
+            if not info['drug_C']:
+                info['drug_C']='/'
+            if not info['drug_D']:
+                info['drug_D']='/'
+            context['list1'].append(info)
+            info2={mut:[]}
+            for index,row in cnv[cnv['Gene_Symbol']==mut].iterrows():    
+                info3={}
+                info3['drug']=row['药物中文名']
+                info3['effect']=row['Response_Type_C']
+                info3['tumor']=row['疾病中文名']
+                info3['evidence']=row['Evidence_Source_C']
+                info3['sig']=row['EfficacyEvidence']
+                info2[mut].append(info3)
+##sensitive_resistant_drug
+                drugs=row['Drug'].replace(" + ",",")
+                drugs=drugs.split(",")
+                drugs_chinese=row['药物中文名'].replace(" + ",",")
+                drugs_chinese=drugs_chinese.split(",")
+                bool=0
+                for drug in drugs:
+                    if drug.upper() in drug_disease.keys():
+                        if re.search(r'敏感',row['Response_Type_C']):
+                            sensitive_drug={}
+                            sensitive_drug['name']=drugs_chinese[bool]                    
+                            sensitive_drug['mechanism']=("\n".join([drug_disease[drug.upper()],drug_mechanism[drug.upper()]])).strip()
+                            if sensitive_drug not in sensitive_resistant_drug[0]['drug']:
+                                sensitive_resistant_drug[0]['drug'].append(sensitive_drug)
+                        elif re.search(r'耐药',row['Response_Type_C']): 
+                            resistant_drug={}
+                            resistant_drug['name']=drugs_chinese[bool]
+                            resistant_drug['mechanism']=("\n".join([drug_disease[drug.upper()],drug_mechanism[drug.upper()]])).strip()
+                            if resistant_drug not in sensitive_resistant_drug[1]['drug']:
+                                sensitive_resistant_drug[1]['drug'].append(resistant_drug)
+                    bool+=1      
+            rt[gene].append("".join([info['p'],'(',info['freq'],')']))
+            context['list2'][" ".join([mut,info['p']])]=info2[mut]
+##genefunc            
+            context['genefunc'][" ".join([mut,info['p']])]=genefunction[mut.upper()]
+##clingenes            
+            clingene1={}
+            clingene2={}            
+            for index,row in cnv[(cnv['Gene_Symbol']==mut)].iterrows():
+                if row['标签']=='适应症' or row['证据等级']=='B': 
+                   clingene1['gene']=info['gene']
+                   clingene1['freq']= info['freq']
+                   (clingene1['transcript'],clingene1['exon'],clingene1['nacid'],clingene1['aacid'])=("/","/","/","/")
+                   clingene1['muttype']= info['p']
+                   context['clingene1'].append(clingene1)
+                else:
+                   clingene2['gene']=info['gene']
+                   clingene2['freq']= info['freq']
+                   (clingene2['transcript'],clingene2['exon'],clingene2['nacid'],clingene2['aacid'])=("/","/","/","/")
+                   clingene2['muttype']= info['p']
+                   context['clingene2'].append(clingene2) 
+        context['list3'][gene]="\n".join(rt[gene])
+    else:
+      cnv_size=0
+
+
+##msi
+if Sample_type == 't':
+    msi_file=''.join([output_dir,'/MSI/',name,'.msi'])
+    msi=(open(msi_file,'r').readlines()[1]).split("\t")
+    context['msi_count']=msi[0]
+    context['msi_value']=round(float(msi[2].strip())/100,2)
+    if context['msi_value']>=0.3:
+        context['msi_result']='MSI-H'
+        context['msi_predict']='对免疫检查点抑制剂可能敏感'
+    else:
+        context['msi_result']='MSS'
+        context['msi_predict']='对免疫检查点抑制剂可能不敏感'
+
+
+##MMR处理
+mmr_file=''.join([output_dir,'/MMR/',name,"_mmr.txt"])
+mmr_size = os.path.getsize(mmr_file)
+mmr_result=0
+mmr_result_summary=[]
+if mmr_size>0:
+    mmr_fh=open(mmr_file,'r',encoding='utf-8').readlines()
+    for line in mmr_fh[1:]:
+        mmr={}
+        mmr['gene']= line.strip().split("\t")[0]
+        mmr['transcript'] = line.strip().split("\t")[1]
+        mmr['nacid'] = line.strip().split("\t")[2]
+        mmr['aacid'] = line.strip().split("\t")[3]
+        mmr['muttype'] = line.strip().split("\t")[5]    
+        mmr['freq'] = line.strip().split("\t")[4]
+        mmr['sig'] = line.strip().split("\t")[6]
+        if mmr['sig'] != '意义未明突变':
+            mmr_result+=1
+            mmr_result_summary.append(mmr['gene'] + ' ' + mmr['aacid']) 
+        context['mmr'].append(mmr)
+
+context['mmr_result']=mmr_result
+mmr_result_summary=' | '.join(mmr_result_summary)
+if mmr_result_summary:
+    context['mmr_result_summary']=mrr_result_summary
+    context['mmr_predict']="对免疫检查点抑制剂可能敏感"
+else:
+    context['mmr_result_summary']="未检测到相关基因突变"
+    context['mmr_predict']="对免疫检查点抑制剂可能不敏感"
+
+
+
+##chemo
+chemo_file=''.join([output_dir,'/chemo/',name,".drug.res.txt"])
+chemo_fh=open(chemo_file,'r')
+bool=0
+chemos=chemo_fh.readlines()[1:]
+chemo_result=0
+recommend_drug=[]
+normal_drug=[]
+restrict_drug=[]
+while bool<len(chemos):
+    chemo={}
+    lines=chemos[bool].strip().split("\t")
+    chemo['bool1']=bool+1
+    chemo['name1']=lines[0]
+    chemo['result1']=lines[4]
+    if lines[3] == '推荐':
+#        chemo['result1']=RichText('推荐使用', color='00FF00')
+        chemo_result+=1
+        recommend_drug.append(chemo['name1'])
+    elif lines[3] == '常规':
+#        chemo['result1']=RichText('常规使用')
+        normal_drug.append(chemo['name1'])
+    elif lines[3] == '谨慎':
+#        chemo['result1']=RichText('谨慎使用', color='FF0000')
+        restrict_drug.append(chemo['name1'])
+    if bool+1<len(chemos):
+        lines=chemos[bool+1].strip().split("\t")
+        chemo['bool2']=bool+2
+        chemo['name2']=lines[0]
+        chemo['result2']=lines[4]    
+        if lines[3] == '推荐':
+#            chemo['result2']=RichText('推荐使用', color='00FF00')
+            chemo_result+=1
+            recommend_drug.append(chemo['name2'])
+        elif lines[3] == '常规':
+#            chemo['result2']=RichText('常规使用')
+            normal_drug.append(chemo['name2'])
+        elif lines[3] == '谨慎':
+#            chemo['result2']=RichText('谨慎使用', color='FF0000')
+            restrict_drug.append(chemo['name2'])
+#    print(chemo)
+    context['chemo'].append(chemo)
+    bool+=2
+context['chemo_result']=chemo_result
+chemo_detail=[]
+chemo_detail_file=''.join([output_dir,'/chemo/',name,".drug.infos.txt"])
+chemo_data=pd.read_table(chemo_detail_file,sep="\t")
+chemo_drugs=chemo_data['药物'].drop_duplicates()
+context['recommend_drug']=','.join(recommend_drug)
+context['normal_drug']=','.join(normal_drug)
+context['restrict_drug']=','.join(restrict_drug)
+
+for drug in chemo_drugs:
+    c={}
+    c['drug']=drug
+    c['info']=[]
+    for index,row in chemo_data[chemo_data['药物'] == drug].iterrows():        
+        d={}
+        d['gene']=row['检测基因']
+        d['site']=row['检测位点']
+        d['gt']=row['基因型']
+        d['level']=row['证据等级']
+        d['sig']=row['用药提示']
+        c['info'].append(d)
+    chemo_detail.append(c)
+
+context['chemo_detail']=chemo_detail
+context['sensitive_resistant_drug']=sensitive_resistant_drug
+
+##化疗联合用药
+chemo_comb_file=''.join([output_dir,'/chemo/',name,".chemo.comb.txt"])
+chemo=pd.read_table(chemo_comb_file,sep="\t")
+type=chemo['癌种'].drop_duplicates()
+
+bool=-1
+chemo_comb=[]
+for i in type:
+    bool+=1
+    chemo_comb.append({'type':i,'drug':[]})
+    for index,row in chemo[chemo['癌种']==i].iterrows():
+        info={}
+        info['name']=row['用药方案']
+        info['abbr']=row['方案缩写']
+        info['sig']=row['临床提示']
+        chemo_comb[bool]['drug'].append(info)
+context['chemo_comb']=chemo_comb
+
+##hereditary cancer
+if os.path.exists(''.join([output_dir,'/hereditary/',name,'.hereditary.pre.txt'])):
+    context['hereditary_cancer_1']=[]
+    context['hereditary_cancer_2']=[]
+    hereditary_file1=''.join([output_dir,'/hereditary/',name,".hereditary.txt"])
+    hereditary_file2=''.join([output_dir,'/hereditary/',name,".risk.txt"])
+    hereditary_file1_fh=open(hereditary_file1,'r')
+    hereditary_file2_fh=open(hereditary_file2,'r')
+
+    hereditary_result=0
+    hereditary_result_summary=[]
+    hereditary_disease=[]
+    if os.path.getsize(hereditary_file1)>0:
+        hereditary_file1_fh=open(hereditary_file1,'r')
+        for line in hereditary_file1_fh.readlines()[1:]:
+            hereditary_cancer_1={}
+            lines=line.strip().split("\t")
+            hereditary_cancer_1['gene']=lines[0]
+            hereditary_cancer_1['syndrome']=lines[1]
+            hereditary_cancer_1['hereditary_type']=lines[2]
+            hereditary_cancer_1['type']=lines[3]
+            hereditary_cancer_1['result']=lines[4]
+            hereditary_result+=len(lines[4].split(";"))
+            hereditary_result_summary.append(hereditary_cancer_1['gene'] + ' ' + hereditary_cancer_1['result'])
+            hereditary_disease.append(hereditary_cancer_1['syndrome'])
+            context['hereditary_cancer_1'].append(hereditary_cancer_1)
+
+    context['hereditary_result']=hereditary_result
+    if hereditary_result_summary:
+        context['hereditary_disease']=';'.join(hereditary_disease)
+        context['hereditary_result_summary']=' | '.join(hereditary_result_summary)
+    else:
+        context['hereditary_disease']='/'
+        context['hereditary_result_summary']='未检测到相关基因突变'
+
+    hereditary_risk=[]
+    bool=0
+    heres=hereditary_file2_fh.readlines()[1:]
+    while bool<len(heres):
+        hereditary_cancer_2={}
+        lines=(heres[bool]).strip().split("\t")
+        hereditary_cancer_2['type1']=lines[0]
+        if lines[1] == '偏高':
+            hereditary_risk.append(lines[0])
+            hereditary_cancer_2['risk1']=RichText('偏高', color='FF0000')
+        elif lines[1] == '同一般人群':
+            hereditary_cancer_2['risk1']=RichText('同一般人群')
+        if bool+1<len(heres):
+            lines=heres[bool+1].strip().split("\t")
+            hereditary_cancer_2['type2']=lines[0]
+            if lines[1] == '偏高':
+                hereditary_cancer_2['risk2']=RichText('偏高', color='FF0000')
+            elif lines[1] == '同一般人群':
+                hereditary_cancer_2['risk2']=RichText('同一般人群')
+        context['hereditary_cancer_2'].append(hereditary_cancer_2)
+        bool+=2
+
+    if hereditary_risk:
+        context['hereditary_risk']=','.join(hereditary_risk) + '风险可能较高'
+    else:
+        context['hereditary_risk']='风险同一般人群' 
+    if len(context['hereditary_cancer_1'])==0:
+        context['hereditary_cancer_1']=[{'gene':'/','syndrome':'/','hereditary_type':'/','type':'/','result':'/'}]        
+    
+##可能获益的临床药物处理
+total_drug_count=[]
+for i in context['list1']:
+    if i['drug_A'] != '/':
+        for j in i['drug_A'].split("\n"):
+            if j not in total_drug_count:
+                total_drug_count.append(j)
+    if i['drug_B'] != '/':
+        for j in i['drug_B'].split("\n"):
+            if j not in total_drug_count:
+                total_drug_count.append(j)
+    if i['drug_C'] != '/':
+        for j in i['drug_C'].split("\n"):
+            if j not in total_drug_count:
+                total_drug_count.append(j)
+
+context['total_drug_count']=len(total_drug_count)                
+
+##去重处理
+context['clingenes1']=[]
+context['clingenes2']=[]
+for i in context['clingene1']:
+    if i not in context['clingenes1']:
+        context['clingenes1'].append(i)
+
+for i in context['clingene2']:
+    if i not in context['clingenes2'] and i not in context['clingenes1']:
+        context['clingenes2'].append(i) 
+
+##检测到的基因变异
+context['total_mut_count']=len(context['clingenes1'])+len(context['clingenes2'])
+
+
+##本癌种FDA/NMPA/NCCN批准基因检测
+indication_fh=open(indication_file,'r',encoding='utf-8').readlines()
+indication_genes=[]
+for line in indication_fh[1:]:
+    indication={}
+    indication['gene']=line.strip().split("\t")[0]
+    indication['content']=line.strip().split("\t")[1]
+    if indication['gene'] in context['list3'].keys():
+        indication['result']=RichText(context['list3'][indication['gene']], color='FF0000')
+    else:
+        indication['result']='未检出变异'
+    context['indication'].append(indication)
+
+##qc处理
+qc_file=''.join([output_dir,'/qc/',name,'_qc.txt'])
+qc=pd.read_table(qc_file,sep="\t",header=None,index_col=0,names=['A','B'])
+
+Q30=qc.loc['Q30(%)','B']
+if Q30>=85:
+    Q30_result='合格'
+else:
+    Q30_result='警戒'
+
+depth=qc.loc['mean_depth(dedup)','B']
+if Sample_type == 'c':
+    if depth>=1000:
+        depth_result='合格'
+    else:
+        depth_result='警戒'
+elif Sample_type == 't':
+    if depth>=500:
+        depth_result='合格'
+    else:
+        depth_result='警戒'
+
+uniformity=qc.loc['coverage(>=0.2*meanx)','B']
+if uniformity>=90:
+    uniformity_result='合格'
+else:
+    uniformity_result='警戒'
+
+if Q30_result=='合格' and depth_result=='合格' and uniformity_result=='合格':
+    context['qc_result']='合格'
+else:
+    context['qc_result']='警戒'
+
+context['Q30']=Q30
+context['Q30_result']=Q30_result
+context['depth']=depth
+context['uniformity']=uniformity
+context['depth_result']=depth_result
+context['uniformity_result']=uniformity_result 
+
+     
+
+##阴性模块处理
+##list1
+if len(context['list1'])==0:
+    context['list1']=[{'gene':'/','freq':'/','drug_A':'/','drug_B':'/','drug_C':'/','drug_D':'/'}]
+
+##list2
+if len(context['list2'])==0:
+    context['list2']= {'/':[{'drug':'/','effect':'/','tumor':'/','evidence':'/','sig':'/'}]}
+    context['genefunc']['/']='/'
+
+
+##clingenes,nonclingenes 
+if len(context['clingenes1'])==0:
+    context['clingenes1']=[{'gene':'/','transcript':'/','nacid':'/','aacid':'/','exon':'/','muttype':'/','freq':'/'}]
+if len(context['clingenes2'])==0:
+    context['clingenes2']=[{'gene':'/','transcript':'/','nacid':'/','aacid':'/','exon':'/','muttype':'/','freq':'/'}]
+if len(context['nonclingenes'])==0:
+    context['nonclingenes']=[{'gene':'/','transcript':'/','nacid':'/','aacid':'/','exon':'/','muttype':'/','freq':'/'}]
+
+##sensitive_resistant_drug
+if len(context['sensitive_resistant_drug'][0]['drug'])==0:
+    context['sensitive_resistant_drug'][0]['drug']=[{'name':'/','mechanism':'/'}]
+if len(context['sensitive_resistant_drug'][1]['drug'])==0:
+    context['sensitive_resistant_drug'][1]['drug']=[{'name':'/','mechanism':'/'}]
+
+##mmr
+if len(context['mmr'])==0:
+    context['mmr']=[{'gene':'/','transcript':'/','nacid':'/','aacid':'/','muttype':'/','freq':'/','sig':'/'}]
+
+##info
+post_file=''.join([output_dir,'/qc/',name,'_post.json'])
+sex='/'
+age='/'
+phone='/'
+medical_history='/'
+family_history='/'
+sample_id=name
+sample_type='/'
+report_date=time.strftime("%Y-%m-%d", time.localtime())
+arrival_date=report_date
+cancer_type='/'
+pathologic_diagnosis='/'
+
+if os.path.isfile(post_file):
+# if post_file.exists():
+    post_fh=open(post_file,'r')
+    post=json.load(post_fh)
+    name=post["data"][0]["name"]
+    sex=post["data"][0]["gender"]
+    age=post["data"][0]["age"]
+    medical_history=post["data"][0]["treatHistory"]
+    family_history=post["data"][0]["sickFamilyHistory"]
+    sample_id=post["data"][0]["barcode"]
+    # sample_id_control=post["data"][0]["barcode_N"]
+    sample_type=post["data"][0]["source"]
+    # sample_type_control=post["data"][0]["source_N"]
+#    sample_type_control = post["data"][0].get('source_N', '/')
+    arrival_date=post["data"][0]["receiveTime"].split(' ')[0]
+    cancer_type=post["data"][0]["zlType"]
+    pathologic_diagnosis=post["data"][0]["treatResult"]
+
+context['info']={
+'name':name,
+'sex':sex,
+'age':age,
+'phone':phone,
+'medical_history':medical_history,
+'family_history':family_history,
+'sample_id':sample_id,
+'sample_type':sample_type,
+'report_date':report_date,
+'arrival_date':arrival_date,
+'cancer_type':cancer_type,
+'pathologic_diagnosis':pathologic_diagnosis}
+context['report_time']=report_date
+
+##模板替换
+file_real = os.path.realpath(sys.argv[0])
+Exe_Path = os.path.dirname(file_real)
+
+report_template={'lung85gene':{'t':'lung85-tissue-oem.docx','c':'lung85-blood-oem.docx'},
+'crc88gene':{'t':'CRC88-tissue-oem.docx','c':'CRC88-blood-oem.docx'}}
+doc_full = os.path.join(Exe_Path, report_template[projcet][Sample_type])
+
+doc = DocxTemplate(doc_full)
+
+doc.render(context)
+doc.save(report_file)

server.py

@@ -0,0 +1,85 @@
+import json
+import os
+import socket
+import struct
+import sys
+from datetime import datetime
+
+from main import main
+from tools.common import basedir
+
+
+def recvdata(conn, path):
+    """
+    接受文件
+    :param conn:
+    :param path:
+    :return:
+    """
+    header_size = struct.unpack('i', conn.recv(4))[0]
+    header_bytes = conn.recv(header_size)
+    header_json = header_bytes.decode('utf-8')
+    header_dic = json.loads(header_json)
+    content_len = header_dic['contentlen']
+    content_name = header_dic['contentname']
+    recv_len = 0
+    fielpath = os.path.join(path, '%s_%s' % (datetime.now().strftime("%m%d%H%M"), content_name))
+    file = open(fielpath, 'wb')
+    while recv_len < content_len:
+        correntrecv = conn.recv(1024 * 1000)
+        file.write(correntrecv)
+        recv_len += len(correntrecv)
+    file.close()
+    return fielpath
+
+
+def senddata(conn, path, message=None):
+    name = os.path.basename(os.path.realpath(path))
+    if not message:
+        with open(path, 'rb') as file:
+            content = file.read()
+        headerdic = dict(
+            contentlen=len(content),
+            contentname=name
+        )
+        headerjson = json.dumps(headerdic)
+        headerbytes = headerjson.encode('utf-8')
+        headersize = len(headerbytes)
+        conn.send(struct.pack('i', headersize))
+        conn.send(headerbytes)
+        conn.sendall(content)
+    else:
+        headerdic = dict(
+            contentlen=len(path),
+            contentname='message'
+        )
+        headerjson = json.dumps(headerdic)
+        headerbytes = headerjson.encode('utf-8')
+        headersize = len(headerbytes)
+        conn.send(struct.pack('i', headersize))
+        conn.send(headerbytes)
+        conn.sendall(path.encode('utf-8'))
+
+
+def server():
+    myserver = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
+    adrss = ("", 8190)
+    myserver.bind(adrss)
+    myserver.listen(5)
+    while True:
+        try:
+            myclient, adddr = myserver.accept()
+            recv_content = recvdata(myclient, os.path.join(basedir, 'xlsx'))
+            outputpath = main(recv_content)
+            senddata(myclient, outputpath)
+            print('生成成功')
+        except Exception as e:
+            print(e, '有错误')
+            # continue
+
+
+if __name__ == '__main__':
+    if len(sys.argv) > 1:
+        outputpath = main(sys.argv[1])
+    else:
+        server()

tools/common.py

@@ -0,0 +1,3 @@
+import os
+
+basedir = os.path.dirname(os.path.dirname(os.path.realpath(__file__)))

tools/parsexlsx.py

@@ -0,0 +1,457 @@
+import json
+import re
+import sys
+import time
+from collections import defaultdict
+
+import pandas as pd
+
+from tools.readxlsx import read
+
+
+def tree():
+    return defaultdict(tree)
+
+
+class BaseAssignment:
+    def __init__(self, *args, **kwargs):
+        super().__init__(*args, **kwargs)
+        self.result = tree()  # 报告结果
+        self.signtb = set()  # 具有明确或潜在临床意义的基因变异
+        self.signdurg = set()  # 潜在临床获益的治疗药物
+
+        self.drugs_type = dict()
+
+
+class Parse(BaseAssignment):
+
+    def __init__(self, sampledata, *args, **kwargs):
+        super().__init__(*args, **kwargs)
+        self.sampledata = sampledata
+
+    def cms(self):
+        """
+        样本信息处理
+        """
+        data = pd.DataFrame(self.sampledata['sample_info'])
+        if data.empty:
+            raise UserWarning('sample_info表为空，生成报告失败！')
+        data = data.applymap(
+            lambda x: str(x).replace('.', '/').replace('-', '/').replace('——', '/') if str(x) in ['.', '-', '——'] else x)
+        data_dict = data.to_dict('index')[0]
+        data_dict['receiveTime'] = re.split(' ', data_dict['receiveTime'])[0]
+        data_dict['reportTime'] = time.strftime("%Y-%m-%d", time.localtime())
+        self.result['c'] = data_dict
+
+    def target(self):
+        data = pd.DataFrame(self.sampledata['snvindel'])
+        res = []
+        if data.empty:
+            self.result['snvindel'] = res
+            return
+
+        data = data[data['Validated'] == 1].reset_index()
+        data['muttype'] = '/'
+        data.loc[data['ExonicFunc.refGene'].str.match('nonsynonymous SNV'), 'muttype'] = '错义突变'
+        data.loc[data['ExonicFunc.refGene'].str.match('^frameshift'), 'muttype'] = '移码突变'
+        data.loc[data['ExonicFunc.refGene'].str.match('^nonframeshift'), 'muttype'] = '非移码突变'
+        data.loc[data['ExonicFunc.refGene'].str.match('stopgain'), 'muttype'] = '提前终止'
+
+        # 拆分hgvs
+        data[['gene', 'transcript', 'exon', 'nacid', 'aacid']] = data['AAChange.refGene'].str.split(':', expand=True)
+        # 没有氨基酸改变用核苷酸改变代替
+        data['aacid'] = data['aacid'].fillna(data['nacid'])
+
+        for alter, alter_data in data.groupby('AAChange.refGene'):
+            alter_data_need = alter_data[['gene', 'transcript', 'exon', 'nacid', 'aacid', 'mutant_frequency',
+                                          'AMP_mut_level', 'muttype', 'Gene_function']]
+            alter_res = alter_data_need.iloc[0].to_dict()
+            alter_res['drug_category'] = self._drug_category(alter_data)
+            drug_content = alter_data[
+                ['DrugCn', 'Response_Type', 'Indication', 'Evidence_Source', 'Efficacy_Evidence']]
+            drug_content = drug_content[drug_content['DrugCn'] != '.']
+            alter_res['drug_content'] = drug_content.reset_index().to_dict('records')
+            alter_res['alter'] = alter
+            res.append(alter_res)
+
+            # 汇总
+            if alter_res['AMP_mut_level'] in ['I', 'II']:
+                self.signtb.add(alter)
+
+        self.result['snvindel'] = res
+
+    def fusion(self):
+        data = pd.DataFrame(self.sampledata['fusion'])
+        res = []
+        if data.empty:
+            self.result['fusion'] = res
+            return
+        data = data[data['Validated'] == 1].reset_index()
+        for alter, alter_data in data.groupby('FUSION'):
+            alter_data_need = alter_data[['FUSION', 'FREQ1', 'AMP_mut_level', 'Gene_function']]
+            alter_res = alter_data_need.iloc[0].to_dict()
+            alter_res['drug_category'] = self._drug_category(alter_data)
+            drug_content = alter_data[
+                ['DrugCn', 'Response_Type', 'Indication', 'Evidence_Source', 'Efficacy_Evidence']]
+            drug_content = drug_content[drug_content['DrugCn'] != '.']
+            alter_res['drug_content'] = drug_content.reset_index().to_dict('records')
+            alter_res['alter'] = '%s 融合' % (alter_res['FUSION'].replace('-', ':'))
+            res.append(alter_res)
+
+            # 汇总
+            if alter_res['AMP_mut_level'] in ['I', 'II']:
+                self.signtb.add(alter)
+
+        self.result['fusion'] = res
+
+    def cnv(self):
+        data = pd.DataFrame(self.sampledata['cnv'])
+        res = []
+        if data.empty:
+            self.result['cnv'] = res
+            return
+        data = data[data['Validated'] == 1].reset_index()
+        for alter, alter_data in data.groupby('Gene_Symbol'):
+            alter_data_need = alter_data[['Gene_Symbol', 'Copy_number', 'AMP_mut_level', 'Gene_function']].reset_index()
+            alter_data_need['muttype'] = '缺失'
+            alter_data_need.loc[alter_data_need['Copy_number'] > 2, 'muttype'] = '扩增'
+            alter_res = alter_data_need.iloc[0].to_dict()
+            alter_res['drug_category'] = self._drug_category(alter_data)
+            drug_content = alter_data[
+                ['DrugCn', 'Response_Type', 'Indication', 'Evidence_Source', 'Efficacy_Evidence']]
+            drug_content = drug_content[drug_content['DrugCn'] != '.']
+            alter_res['drug_content'] = drug_content.reset_index().to_dict('records')
+            alter_res['alter'] = '%s %s' % (alter, alter_res['muttype'])
+            res.append(alter_res)
+
+            # 汇总
+            if alter_res['AMP_mut_level'] in ['I', 'II']:
+                self.signtb.add(alter)
+        self.result['cnv'] = res
+
+    def hotspot(self):
+        self._to_records('hotspot')
+
+    def met(self):
+        self._to_records('MET')
+
+    def longindel(self):
+        self._to_records('longindel')
+
+    def mmr(self):
+        data = pd.DataFrame(self.sampledata['MMR'])
+        result_summary = '未检测到相关基因突变'
+        predict = '对免疫检查点抑制剂可能不敏感'
+        mmr_num = 0
+        res = []
+
+        if not data.empty:
+            tmdf = data[['gene', 'p_change']].reset_index()
+            tmdf['result_summary'] = tmdf.apply(lambda x: '%s %s' % (x['gene'], x['p_change']), axis=1)
+            result_summary = ' | '.join(tmdf['result_summary'].to_list())
+            predict = '对免疫检查点抑制剂可能敏感'
+            mmr_num = len(data.index)
+            res = data.to_dict('records')
+
+        self.result['MMR'] = res
+        self.result['sum']['mmr'] = dict(
+            result_summary=result_summary,
+            predict=predict,
+            mmr_num=mmr_num
+        )
+
+    def msi(self):
+        self._to_dicts('MSI')
+
+    # def chemo(self):
+    #     data = pd.DataFrame(self.sampledata['chemo'])
+    #
+    #     project = data['project'].to_list()[0]
+    #
+    #     # 分类汇总 同位点，药物合并 drug.infos.txt
+    #     drugrsid = data[['drugname', 'genename', 'rsid', 'result', 'level', 'tips', 'drugsort']]
+    #     drugrsid = drugrsid.drop_duplicates()
+    #     resdrugrsid = drugrsid.groupby(['drugname', 'genename', 'rsid', 'result', 'level', 'drugsort'])['tips'].agg(
+    #         ','.join).reset_index()
+    #     resdrugrsid.rename(columns=
+    #                        {'drugname': '药物', 'genename': '检测基因', 'rsid': '检测位点', 'result': '基因型',
+    #                         'level': '证据等级', 'tips': '用药提示'},
+    #                        inplace=True)
+    #     resdrugrsid = resdrugrsid.sort_values(by=['drugsort', '药物', '检测基因'])
+    #     self.result['chemo']['druginfo'] = resdrugrsid.to_dict('records')
+    #
+    #     # 药物 药物疗效 推荐程度合并 drug.res.txt
+    #     drugtypesum = data[['drugname', 'drugtype', 'rsid', 'weights']]
+    #     drugtypesum = drugtypesum.drop_duplicates()
+    #     drugtyperes = list()
+    #     drugsum = dict()
+    #     for drug, drugdata in drugtypesum.groupby('drugname'):
+    #         tipsnum = drugdata.groupby(['drugtype']).agg({'weights': 'sum'}).to_dict('index')
+    #         sumlist = list()
+    #         if 'LX' in tipsnum:
+    #             LX = tipsnum['LX']['weights']
+    #             if LX > 0:
+    #                 lxdes = '疗效较好'
+    #                 lxnum = 1
+    #             elif LX == 0:
+    #                 lxdes = '疗效一般'
+    #                 lxnum = 0
+    #             else:
+    #                 lxdes = '疗效较差'
+    #                 lxnum = -1
+    #             sumlist.append(lxdes)
+    #         else:
+    #             LX = 0
+    #             lxnum = 0
+    #         if 'DF' in tipsnum:
+    #             DF = tipsnum['DF']['weights']
+    #             if DF > 0:
+    #                 dfdes = '毒副较低'
+    #                 dfnum = 1
+    #             elif DF == 0:
+    #                 dfdes = '毒副一般'
+    #                 dfnum = 0
+    #             else:
+    #                 dfdes = '毒副较高'
+    #                 dfnum = -1
+    #             sumlist.append(dfdes)
+    #         else:
+    #             DF = 0
+    #             dfnum = 0
+    #
+    #         # 评价方式 疗效 1 0 -1, 毒副 1 0 -1 ，可形成9宫格
+    #         sumnum = lxnum + dfnum
+    #         if sumnum > 0:
+    #             sumdes = '推荐'
+    #         elif sumnum == 0:
+    #             sumdes = '常规'
+    #         else:
+    #             sumdes = '谨慎'
+    #
+    #         # 特别药物处理
+    #         if (drug == "氟尿嘧啶" or drug == "卡培他滨") and DF < 0:
+    #             sumdes = '谨慎'
+    #
+    #         drugtyperes.append(dict(
+    #             药物名称=drug,
+    #             疗效=LX,
+    #             毒副=DF,
+    #             推荐程度=sumdes,
+    #             疗效和毒副总结=','.join(sumlist)
+    #         ))
+    #         drugsum[drug] = sumdes
+    #
+    #     # 报告中展示药物有顺序
+    #     drugsort = data[['drugname', 'drugsort']].drop_duplicates()
+    #     drugsort_dict = drugsort.set_index('drugname')['drugsort'].to_dict()
+    #     drugtyperes_sort = sorted(drugtyperes, key=lambda x: (
+    #         drugsort_dict[x['药物名称']] if x['药物名称'] in drugsort_dict else 100, x['药物名称']))
+    #
+    #     drugtyperes_sort_df = pd.DataFrame(drugtyperes_sort)
+    #     self.result['chemo']['sum'] = drugtyperes_sort_df.groupby('推荐程度')['药物名称'].apply(','.join).to_dict()
+    #     self.result['chemo']['drugres'] = drugtyperes_sort_df.to_dict('records')
+    #
+    #     # 联合用药
+    #     drug_combine_path = os.path.join(os.path.dirname(os.path.dirname(__file__)), 'database',
+    #                                      'chemo_drug_combine.csv')
+    #     drug_combine = pd.read_csv(drug_combine_path, sep='\t')
+    #     drug_combine.fillna('.', inplace=True)
+    #     drug_combine_data = drug_combine[drug_combine['source'].str.contains(project)]
+    #     drug_combine_data = drug_combine_data.reset_index()
+    #     if not drug_combine_data.empty:
+    #         drug_combine_data['临床提示'] = drug_combine_data['用药方案'].apply(self._get_drug_plan, args=(drugsum,))
+    #         self.result['chemo']['combine'] = drug_combine_data.groupby('癌种').apply(
+    #             lambda group: group.set_index('癌种').to_dict('records')).to_dict()
+    #     else:
+    #         self.result['chemo']['combine'] = dict()
+    #     self.result['sum']['chemo_drug_num'] = len(drugsum.keys())
+
+    def chemo(self):
+        chemo_res = self._to_records('chemo_res', need=True)
+        chemo_res_df = pd.DataFrame(chemo_res)
+        chemo_res_df.index = chemo_res_df.index + 1
+        chemo_res_df = chemo_res_df.reset_index()
+        self.result['chemo']['chemo_res'] = chemo_res_df.to_dict('records')
+        self.result['sum']['chemo']['drug_num'] = len(chemo_res)
+        self.result['sum']['chemo']['drug_category'] = pd.DataFrame(chemo_res).groupby('推荐程度')['药物名称'].apply(
+            ','.join).to_dict()
+
+        chemo_comb = self._to_records('chemo_comb', need=True)
+        chemo_comb_res = dict()
+        if chemo_comb:
+            chemo_comb_res = pd.DataFrame(chemo_comb).groupby('癌种').apply(
+                lambda group: group.set_index('癌种').to_dict('records')).to_dict()
+        self.result['chemo']['chemo_comb'] = chemo_comb_res
+
+        chemo_info = self._to_records('chemo_info', need=True)
+        chemo_info_res = dict()
+        if chemo_info:
+            chemo_info_res = pd.DataFrame(chemo_info).groupby('药物').apply(
+                lambda group: group.set_index('药物').to_dict('records')).to_dict()
+        self.result['chemo']['chemo_info'] = chemo_info_res
+
+    def hcs(self):
+        self._to_records('HCS')
+        self.result['sum']['hcs']['num'] = len(self.result['HCS'])
+
+    def heredity(self):
+        """
+        遗传的结果文件
+        :return:
+        """
+        hereditary = pd.DataFrame(self.sampledata['hereditary'])
+        result = '/'
+        disease = '/'
+        risk = '/'
+        if not hereditary.empty:
+            result = '|'.join(hereditary.apply(lambda x: '%s %s' % (x['基因'], x['检测结果']), axis=1).to_list())
+            disease = '|'.join(hereditary['遗传性肿瘤综合征'].to_list())
+
+        hereditary_risk = pd.DataFrame(self.sampledata['hereditary_risk'])
+        if not hereditary_risk.empty:
+            risk = ','.join(hereditary_risk[hereditary_risk['风险值'] == '偏高']['肿瘤类型'].to_list())
+
+        self.result['hereditary'] = hereditary.to_dict('records')
+        self.result['sum']['hereditary']['result'] = result
+        self.result['sum']['hereditary']['disease'] = disease
+        self.result['sum']['hereditary']['risk'] = risk
+
+    def qc(self):
+        # self._to_dicts('qc')
+        data = pd.DataFrame(self.sampledata['qc'])
+        res = {}
+        if not data.empty:
+            data.rename(columns={
+                'Q30(%)': 'q30',
+                'mean_depth(dedup)': 'depth',
+                'coverage(>=0.2*meanx)': 'coverage'
+            }, inplace=True)
+            res = data.to_dict('index')[0]
+        self.result['qc'] = res
+
+    def drugs(self):
+        data = pd.DataFrame(self.sampledata['drugs'])
+        res = {}
+        if not data.empty:
+            data = data.dropna()
+            data = data[data['drug_detail'] != '.']
+            res = data.set_index('drug_name')['drug_detail'].to_dict()
+        self.result['drugs']['drugs_detail'] = res
+
+    def indication(self):
+        self._to_records('indication')
+
+    def _to_records(self, sheetname, need=False):
+        """
+        for many lines
+        :param sheetname:
+        :return:
+        """
+        data = pd.DataFrame(self.sampledata[sheetname])
+        res = []
+        if data.empty:
+            self.result[sheetname] = res
+            return
+        res = data.to_dict('records')
+        if need:
+            return res
+        self.result[sheetname] = res
+
+    def _to_dicts(self, sheetname):
+        """
+        for single line
+        :param sheetname:
+        :return:
+        """
+        data = pd.DataFrame(self.sampledata[sheetname])
+        res = {}
+        if data.empty:
+            self.result[sheetname] = res
+            return
+        res = data.to_dict('index')[0]
+        self.result[sheetname] = res
+
+    def _drug_category(self, groupdata):
+        drug_category_res = dict()
+        for drug_category, drug_category_alter_data in groupdata.groupby('Drug_Category'):
+            if drug_category == '.':
+                continue
+            # 敏感，可能敏感药物统计
+            if drug_category in ['a', 'b', 'c']:
+                self.signdurg.update(set(drug_category_alter_data['DrugCn'].str.split(',').explode().tolist()))
+            drug_category_alter_data['drugdes'] = drug_category_alter_data.apply(
+                lambda x: '%s 【%s 级】' % (x['DrugCn'], x['AMP_evidence_level']), axis=1)
+            drug_category_res[drug_category] = '\n'.join(drug_category_alter_data['drugdes'].to_list())
+
+        # 所有药物信息
+        groupdata['list_col'] = groupdata['DrugCn'].str.replace(' + ', '+').str.split(r'[+,]')
+        exploded_df = groupdata.explode('list_col').reset_index()
+        exploded_df = exploded_df[(exploded_df['list_col'] != '.') & (exploded_df['list_col'] != '')]
+        exploded_dict = exploded_df.groupby('Response_Type')['list_col'].agg(lambda x: list(set(x))).to_dict()
+
+        for drug_type in exploded_dict:
+            if drug_type in self.drugs_type:
+                self.drugs_type[drug_type].extend(exploded_dict[drug_type])
+            else:
+                self.drugs_type[drug_type] = exploded_dict[drug_type]
+
+        # for drugall in exploded_df['Drug_Detail'].to_list():
+        #     for drug in drugall.split('|'):
+        #         match = re.search(r'\[\[(.*?)]](.*?)$', drug)
+        #         if match:
+        #             self.drugs_record['drugs'].update({match.group(1).strip(): match.group(2).strip()})
+        return drug_category_res
+
+    @staticmethod
+    def _get_drug_plan(x, drugsum):
+        tlist = x.split('+')
+        tdeslist = list()
+        for tdes in tlist:
+            if tdes.strip() in drugsum:
+                t1_des = drugsum[tdes.strip()]
+                tdeslist.append(t1_des)
+
+        if '慎用' in tdeslist or '谨慎' in tdeslist:
+            return '慎用'
+        elif '推荐' in tdeslist:
+            return '推荐'
+        elif '常规' in tdeslist:
+            return '可选'
+        else:
+            return '可选'
+
+    def collect(self):
+        self.cms()
+        self.target()
+        self.fusion()
+        self.cnv()
+        self.hotspot()
+        self.met()
+        self.longindel()
+        self.mmr()
+        self.msi()
+        self.chemo()
+        self.hcs()
+        self.heredity()
+        self.qc()
+        self.indication()
+        self.drugs()
+
+        # 汇总
+        self.result['sum']['signtb_num'] = len(self.signtb)
+        self.result['sum']['signdrug_num'] = len(self.signdurg)
+        self.result['drugs']['drugs_type'] = {key: self.drugs_type[key] for key in sorted(self.drugs_type.keys())}
+        return self.result
+
+
+def run(path):
+    parse = Parse(read(path))
+    res = parse.collect()
+    resjson = json.dumps(res, indent=4, ensure_ascii=False)
+    with open('t.json', 'w') as f:
+        f.write(resjson)
+    return resjson
+
+
+if __name__ == '__main__':
+    run(sys.argv[1])

tools/readxlsx.py

@@ -0,0 +1,27 @@
+import pandas as pd
+import logging
+import json
+import sys
+
+logger = logging.getLogger('main.sub')
+
+
+def read(merge):
+    df = pd.read_excel(merge, None)
+    samplelist = df['sample_info']['sampleSn'].to_list()
+    if not samplelist:
+        logger.error('sample_info表为空！读取excel信息失败！')
+        raise UserWarning('sample_info表为空！读取excel信息失败！')
+    samdict = dict()
+    for name, contents in df.items():
+        if contents.empty:
+            samdict[name] = []
+            continue
+        contents.fillna('.', inplace=True)
+        samdict[name] = contents.to_dict('list')
+    return samdict
+
+
+if __name__ == '__main__':
+    res = read(sys.argv[1])
+    print(res)