#! /usr/bin/python3 # Usage: python3 update_network.py # Put this script under directory Code/. # IMPORTANT: Run this script under directory Code/. # Execute the above command regularly, or # Cron job this command to make it run everyday at 5am: # # 1. crontab -e. # 2. Add this line: 01 05 * * * cd /home/hui/network/v03/Code && python3 update_network.py # # IMPORTANT: Make sure that you execute this script (update_network.py) under the directory Code. # # Purpose: periodically (e.g., per week) run this script to see if the network needs update. If yes, update it. # # Set HOLDON=NO in parameter_for_buildCmatrix.txt, # parameter_for_buildRmatrix.txt and parameter_for_net.txt to make # changes in these file effective. # # parameter_for_buildRmatrix.txt will be updated automatically (I # hope). However, we need to update parameter_for_buildCmatrix.txt # manually. # # Revision history: # # Last modified: 26 Feb 2017 # Last modified: 17 Mar 2017 # Last modified: 04 Apr 2017 # Last modified: 05 Apr 2017 # Last modified: 10 Apr 2017 # Last modified: 19 Apr 2017 # Last modified: 20 Apr 2017 [addded create_edges0B.py which calls correlation_per_tissue.R] # Last modified: 21 Jun 2017 [added correlation_per_group.R and wedge.R] # Last modified: 30 Jun 2017 [added get_sample_size so that we have sample size for correlations of type all, added in ll_dict ] # Last modified: 23 Jan 2018 [edited a few print-out messages] # Last modified: 25 Jan 2018 [updated function compute_metric(), set S=365.0 and modified return statement] # Last modified: 24 Aug 2018 [updated function from get_sample_size(d, sorted_keys, day) to get_sample_size(d, sorted_keys, day, rcond_string)] # Last modified: 03 Feb 2019 # Last modified: 08 Aug 2019, hui # Last modified: 10 Aug 2019, hui # Last modified: 23 Aug 2019, hui [correlation_mixtools(num_component)] # Last modified: 10 Sep 2019, hui [correlation_mixtools, check the previous R session has finished before starting a new one.] import os, sys import numpy as np import glob import time import subprocess from datetime import datetime from param4net import make_global_param_dict, get_key_value from configure import HISTORY_DIR, HISTORY_DIR2, FILE_TIMESTAMP, SAMPLE_SIZE_FILE, TEMP_DIR, \ PARAMETER_FOR_BUILDCMATRIX, PARAMETER_FOR_BUILDRMATRIX, \ PARAMETER_FOR_NET, PARAMETER_FOR_NET_TRAVADB_STRESS, PARAMETER_FOR_NET_TRAVADB_MAP, PARAMETER_FOR_NET_MILD_DROUGHT, PARAMETER_FOR_NET_WIGGELAB_DIURNAL, \ BINDING_FILE, TPM_FILE, \ BUILDRMATRIX_RENEW_INTERVAL, MIN_RNA_SEQ_INCREASE, UPDATE_NETWORK_LOG_FILE, NEW_OR_UPDATED_CHIP_FILE, \ RNA_SEQ_INFO_DATABASE, RNA_SEQ_INFO_DATABASE_JSON, GENE_ID_FIRST_TWO_LETTERS, MEMORY_STRENGTH, \ MAPPED_RDATA_DIR, MAPPED_CDATA_DIR, \ EDGE_POOL_DIR, MERGED_EDGE_FILE, \ TARGET_TF_FILE ## Helper functions def get_value(s, delimit): lst = s.split(delimit, 1) # only split at the first delimit return lst[1].strip() def validate_webapp_dir(para_for_net): ''' Make sure this function is executed under the directory Code. ''' glb_param_dict = make_global_param_dict(para_for_net) # if genes.json is not present, create one if not os.path.exists('../Webapp/static/json/genes.json'): print('[update_network.py]: cannot find genes.json, make one ...') cmd = 'python3 text2json.py %s > ../Webapp/static/json/genes.json' % (glb_param_dict['GENE_ID_AND_GENE_NAME']) os.system(cmd) def make_paths(s): if not os.path.isdir(s): os.makedirs(s) def make_important_dirs(): make_paths('../Data/history/edges/many_targets') make_paths('../Data/history/edges/one_target') make_paths('../Data/log') make_paths('../Data/information') make_paths('../Data/temp') make_paths('../Data/upload') make_paths('../Data/parameter') make_paths('../Data/R/Mapped') make_paths('../Data/R/Mapped/public') make_paths('../Data/R/Mapped/inhouse') make_paths('../Data/R/Mapped/other') make_paths('../Data/R/Raw') make_paths('../Data/C/Mapped') make_paths('../Data/C/Raw') make_paths('../Data/history/edges') make_paths(EDGE_POOL_DIR) make_paths('../Data/history/bind') make_paths('../Data/history/expr') make_paths('../Webapp/static/json') make_paths('../Webapp/static/edges') make_paths('../Webapp/templates') def num_line(fname): ''' Return number of lines in file fname. ''' if not os.path.exists(fname): return 0 f = open(fname) lines = f.readlines() f.close() return len(lines) def num_ids(fname): ''' Return number of IDs in fname. ''' f = open(fname) lines = f.readlines() f.close() return len(lines[0].split('\t')) - 1 def write_log_file(s, fname): f = open(fname, 'a') curr_time = datetime.now().strftime('%Y-%m-%d %H:%M') s = '[' + curr_time + ']: ' + s if not '\n' in s: s += '\n' f.write(s) f.close() print('Log: %s' % (s.strip())) def write_sample_size_file(sample_size_file, curr_date, tpm_sample_size): if not os.path.exists(sample_size_file): f = open(sample_size_file, 'w') else: f = open(sample_size_file, 'a') f.write('%s\t%s\n' % (curr_date, tpm_sample_size)) f.close() def age_of_file_in_days(fname): ''' Return age of fname in days. ''' st = os.stat(fname) days = (time.time() - st.st_mtime)/(3600*24.0) return days def age_of_file_in_seconds(fname): ''' Return age of fname in days. ''' st = os.stat(fname) seconds = time.time() - st.st_mtime return seconds def hold_on(fname): f = open(fname) lines = f.readlines() f.close() for line in lines[:100]: # check the first 100 lines for HOLDON line = line.strip() if line.startswith('%%HOLDON=YES'): return True return False def all_files_present(lst): missing_file_lst = [] for path in lst: # lst is a list of file names to check if not os.path.exists(path): if 'edges.txt' in path: write_log_file('[update_network.py] WARNING: must have %s to update network. Call create_edges*.py to create edge files.' % (path), UPDATE_NETWORK_LOG_FILE) missing_file_lst.append(path) return missing_file_lst def record_file_time(lst, fname): ''' lst - a list of files fname - a recorder file ''' f = open(fname, 'w') s = '' for x in lst: if os.path.exists(x): s += '%s\t%d\n' % (os.path.basename(x), int(os.stat(x).st_mtime)) else: s += '%s\t%d\n' % (os.path.basename(x), 0) f.write(s) f.close() def read_file_timestamp(ftimestamp): d = {} f = open(ftimestamp) for line in f: line = line.strip() lst = line.split() fname = lst[0] t = lst[1] d[fname] = int(t) f.close() return d def file_updated(fname, d): ft = int(os.stat(fname).st_mtime) k = os.path.basename(fname) return ft > d[k] def get_updated_files(lst, d): result = [] for x in lst: if file_updated(x, d): result.append(os.path.basename(x)) return result def get_sample_size(d, sorted_keys, day, rcond_string): if rcond_string.isdigit(): return int(rcond_string) if len(d) == 0: return 1200 # a default number of sample size, CHANGE for x in sorted_keys: if x >= day: return d[x] k = sorted_keys[-1] # last key, latest date return d[k] def number_rnaseq_id(tpm_file): f = open(tpm_file) first_line = f.readlines()[0] f.close() first_line = first_line.strip() return len(first_line.split()) - 1 def number_rnaseq_diff(para_file, tpm_file): ''' count the number @ in para_file, and count the number of columns in tpm_file, return their difference ''' a = 0 f = open(para_file) for line in f: line = line.strip() if line.startswith('@'): a += 1 f.close() b = number_rnaseq_id(tpm_file) return a - b def validate_gene_file(fname): f = open(fname) lines = f.readlines() f.close() for line in lines: # check all lines line = line.strip() lst = line.split('\t') if len(lst) < 6: print('[update_network.py]:Not enought fields: %s. Only %d are given. Each line must have gene_id, gene_name, chr, start, end, strand, description (optional). See prepare_gene_file.py in the documentation on how to prepare this file.' % (line, len(lst))) sys.exit() def validate_parameter_for_buildcmatrix(fname): # first the file must exist if not os.path.exists(fname): print('[update_network.py]:CANNOT FIND %s.' % (fname)) sys.exit() f = open(fname) lines = f.readlines() f.close() d = {} location_count = 0 for line in lines: line = line.strip() if line.startswith('%%'): k, v = get_key_value(line[2:]) d[k] = v if k == 'GENE_FILE' or k == 'CHR_INFO': if not os.path.exists(v): print('[update_network.py]:%s not exists.' % (v)) sys.exit() if k == 'GENE_FILE': validate_gene_file(v) if k == 'DESTINATION': if not os.path.isdir(v): print('[update_network.py]:%s not exists.' % (v)) sys.exit() if k == 'TARGET_RANGE': if int(v) <= 0: print('[update_network.py]:Target range (%d) must be greater than 0.' % (v)) sys.exit() if line.startswith('LOCATION:'): v = get_value(line, ':') location_count += 1 if not os.path.exists(v): print('[Warning] update_network.py: Location %s does not exists.' % (v)) #sys.exit() if not 'GENE_FILE' in d: print('[update_network.py]:Must specify GENE_FILE.') sys.exit() if not 'DESTINATION' in d: print('[update_network.py]:Must specify DESTINATION.') sys.exit() if not 'CHR_INFO' in d: print('[update_network.py]:Must specify CHR_INFO.') sys.exit() if location_count == 0: print('[update_network.py]:Must contain at least one ChIP-seq.') sys.exit() def validate_parameter_for_buildrmatrix(fname): # first the file must exist if not os.path.exists(fname): print('[update_network.py]:CANNOT FIND %s.' % (fname)) sys.exit() f = open(fname) lines = f.readlines() f.close() d = {} location_count = 0 for line in lines: line = line.strip() if line.startswith('%%'): k, v = get_key_value(line[2:]) d[k] = v if k == 'GENE_LIST': if not os.path.exists(v): print('[update_network.py]:%s not exists.' % (v)) sys.exit() if line.startswith('LOCATION:'): v = get_value(line, ':') location_count += 1 if not os.path.exists(v): print('[update_network.py]:Location %s does not exists.' % (v)) #sys.exit() if not 'GENE_LIST' in d: print('[update_network.py]:Must specify GENE_LIST.') sys.exit() if location_count == 0: print('[update_network.py]:Must contain at least one RNA-seq.') sys.exit() def validate_parameter_for_net(fname): # first the file must exist if not os.path.exists(fname): print('[update_network.py]:CANNOT FIND %s.' % (fname)) sys.exit() f = open(fname) lines = f.readlines() f.close() d = {} location_count = 0 for line in lines: line = line.strip() if line.startswith('%%'): k, v = get_key_value(line[2:]) d[k] = v if k == 'GENE_LIST': if not os.path.exists(v): print('[update_network.py]:%s not exists.' % (v)) sys.exit() if k == 'GENE_ID_AND_GENE_NAME': if not os.path.exists(v): print('[update_network.py]:%s not exists.' % (v)) sys.exit() if k == 'BINDING_INFO': if not os.path.exists(v): print('[update_network.py]:%s not exists.' % (v)) sys.exit() if k == 'EXPRESSION_INFO': if not os.path.exists(v): print('[update_network.py]:%s not exists.' % (v)) sys.exit() if k == 'BINDING_MATRIX': if not os.path.exists(v): print('[update_network.py]:%s not exists.' % (v)) print('[update_network.py]:Use python3 buildCmatrix.py paramter_for_buildCmatrix.txt > binding.txt to create binding.txt.') if k == 'EXPRESSION_MATRIX': if not os.path.exists(v): print('[update_network.py]:%s not exists.' % (v)) print('[update_network.py]:Use python3 buildRmatrix.py paramter_for_buildRmatrix.txt to create TPM.txt.') if not 'GENE_LIST' in d: print('[update_network.py]:Must specify GENE_FILE.') sys.exit() if not 'GENE_ID_AND_GENE_NAME' in d: print('[update_network.py]:Must specify GENE_ID_AND_GENE_NAME.') sys.exit() if not 'BINDING_INFO' in d: print('[update_network.py]:Must specify BINDING_INFO.') sys.exit() if not 'EXPRESSION_INFO' in d: print('[update_network.py]:Must specify EXPRESSION_INFO.') sys.exit() if not 'BINDING_MATRIX' in d: print('[update_network.py]:%s not exists.' % (v)) print('[update_network.py]:Use python3 buildCmatrix.py paramter_for_buildCmatrix.txt > binding.txt to create binding.txt.') if not 'EXPRESSION_MATRIX' in d: print('[update_network.py]:%s not exists.' % (v)) print('[update_network.py]:Use python3 buildRmatrix.py paramter_for_buildRmatrix.txt to create TPM.txt.') def need_update_parameter_file(param_file, dirs): ''' Make sure param_file is consistent with dirs (a list of directories to check against). ''' result = [] files_in_parameter = {} f = open(param_file) for line in f: line = line.strip() if line.startswith('LOCATION:'): lst = line.split(':') k = os.path.abspath(lst[1]) files_in_parameter[k] = 1 f.close() param_modification_time = os.path.getmtime(param_file) files_in_dirs = {} for directory in dirs: for root, dirnames, filenames in os.walk(os.path.abspath(directory)): for filename in filenames: k = os.path.join(root, filename) files_in_dirs[k] = 1 if 'narrowPeak' in k or '_quant' in k: if not k in files_in_parameter and os.path.getmtime(k) > param_modification_time: result.append('%s is not in %s' % (k, param_file)) return result def validate_binding_file(fname): f = open(fname) lines = f.readlines() for line in lines: line = line.strip() if 'buildCmatrix: ChIP-seq ID list is empty.' in line: return False f.close() return True def lines_with_10_fields(s): result = [] for line in s.split('\n'): line = line.strip() if len(line.split('\t')) == 10: result.append(line) return result def concatenate_edge_files(fname_lst, fname_out): fout = open(fname_out, 'w') for fname in fname_lst: f = open(fname) s = f.read() f.close() # Make sure each edge has 10 fields before writing. lines = lines_with_10_fields(s) if lines != []: write_log_file('[update_network.py] In function concatenate_edge_files. File %s has %d rows with 10 columns.' % (fname, len(lines)), UPDATE_NETWORK_LOG_FILE) fout.write('\n'.join(lines) + '\n') else: write_log_file('[update_network.py] In function concatenate_edge_files. Check file %s. It has no rows with 10 fields.' % (fname), UPDATE_NETWORK_LOG_FILE) fout.close() def delete_edge_files(fname_lst): for fname in fname_lst: # Before we delete, we should make sure it is not being written. Make sure it is old enough. Otherwise, don't delete. if age_of_file_in_seconds(fname) > 12*60*60: # 10 minutes os.remove(fname) else: write_log_file('[update_network.py] In function delete_edge_files. Check file %s. It is probably still being written. So I don\'t delete it.' % (fname), UPDATE_NETWORK_LOG_FILE) def create_edges0(): if os.path.exists(PARAMETER_FOR_NET): write_log_file('[update_network.py] Create simple edges.txt using create_edges0.py with %s' % (PARAMETER_FOR_NET), UPDATE_NETWORK_LOG_FILE) cmd = 'python3 create_edges0.py %s' % (PARAMETER_FOR_NET) os.system(cmd) # The following commands are optional. For example, if a user wants to run it locally, he don't have to provide these TPM tables. if os.path.exists(PARAMETER_FOR_NET_TRAVADB_STRESS): #write_log_file('[update_network.py] Create simple edges.txt using create_edges0.py with %s' % (PARAMETER_FOR_NET_TRAVADB_STRESS), UPDATE_NETWORK_LOG_FILE) cmd = 'python3 create_edges0.py %s' % (PARAMETER_FOR_NET_TRAVADB_STRESS) #os.system(cmd) if os.path.exists(PARAMETER_FOR_NET_TRAVADB_MAP): #write_log_file('[update_network.py] Create simple edges.txt using create_edges0.py with %s' % (PARAMETER_FOR_NET_TRAVADB_MAP), UPDATE_NETWORK_LOG_FILE) cmd = 'python3 create_edges0.py %s' % (PARAMETER_FOR_NET_TRAVADB_MAP) #os.system(cmd) if os.path.exists(PARAMETER_FOR_NET_MILD_DROUGHT): #write_log_file('[update_network.py] Create simple edges.txt using create_edges0.py with %s' % (PARAMETER_FOR_NET_MILD_DROUGHT), UPDATE_NETWORK_LOG_FILE) cmd = 'python3 create_edges0.py %s' % (PARAMETER_FOR_NET_MILD_DROUGHT) #os.system(cmd) if os.path.exists(PARAMETER_FOR_NET_WIGGELAB_DIURNAL): #write_log_file('[update_network.py] Create simple edges.txt using create_edges0.py with %s' % (PARAMETER_FOR_NET_WIGGELAB_DIURNAL), UPDATE_NETWORK_LOG_FILE) cmd = 'python3 create_edges0.py %s' % (PARAMETER_FOR_NET_WIGGELAB_DIURNAL) #os.system(cmd) def create_edges0B(): if os.path.exists(PARAMETER_FOR_NET): write_log_file('[update_network.py] Create tissue-specific edges.txt using new binding.txt (size=%d). create_edges0B.py' % (num_ids(BINDING_FILE)), UPDATE_NETWORK_LOG_FILE) cmd = 'python3 create_edges0B.py %s' % (PARAMETER_FOR_NET) # call correlation_per_tissue.R os.system(cmd) def wedge(): if os.path.exists(PARAMETER_FOR_NET): write_log_file('[update_network.py] Create edges using wedge shapes. wedge.R', UPDATE_NETWORK_LOG_FILE) cmd = 'Rscript wedge.R' os.system(cmd) def correlation_per_group(): # For 3,130 RNA-seq samples and 30,000 pairs, need at least 10 hours. if os.path.exists(PARAMETER_FOR_NET): write_log_file('[update_network.py] Create group-specific edges.txt using new TPM.txt (size=%d). correlation_per_group.R' % (number_rnaseq_id(TPM_FILE)), UPDATE_NETWORK_LOG_FILE) cmd = 'Rscript correlation_per_group.R' os.system(cmd) def correlation_per_group_fixed_number(): if os.path.exists(PARAMETER_FOR_NET): write_log_file('[update_network.py] Create group-specific (fixed) edges.txt using new TPM.txt (size=%d). correlation_per_group_fixed_number.R' % (number_rnaseq_id(TPM_FILE)), UPDATE_NETWORK_LOG_FILE) cmd = 'Rscript correlation_per_group_fixed_number.R' os.system(cmd) def correlation_mixtools(num_component): if os.system('pidof R') != 0: # since it take long time (several days) to run create_edges_mixtool.R, so we make sure the previous R computing has finished before we start a new one. os.system returns 0 if R is running. write_log_file('[update_network.py] Create edges.txt using TPM.txt (size=%d). create_edges_mixtool.R with %d components.' % (number_rnaseq_id(TPM_FILE), num_component), UPDATE_NETWORK_LOG_FILE) cmd = 'Rscript create_edges_mixtool.R %d' % (num_component) os.system(cmd) def check_rnaseq_info(): # check rnaseq_info_database.txt and rnaseq_info_database.json. If they are outdated, then remind us to update it in log file. if os.path.exists(RNA_SEQ_INFO_DATABASE): if age_of_file_in_days(RNA_SEQ_INFO_DATABASE) > 120: # older than 120 days write_log_file('[update_network.py] Need update %s. It is %d days old.' % (RNA_SEQ_INFO_DATABASE, age_of_file_in_days(RNA_SEQ_INFO_DATABASE)), UPDATE_NETWORK_LOG_FILE) else: write_log_file('[update_network.py] [MISSING] Must create %s.' % (RNA_SEQ_INFO_DATABASE), UPDATE_NETWORK_LOG_FILE) if os.path.exists(RNA_SEQ_INFO_DATABASE_JSON): if age_of_file_in_days(RNA_SEQ_INFO_DATABASE_JSON) > 120: write_log_file('[update_network.py] Need update %s. It is %d days old.' % (RNA_SEQ_INFO_DATABASE_JSON, age_of_file_in_days(RNA_SEQ_INFO_DATABASE_JSON)), UPDATE_NETWORK_LOG_FILE) else: write_log_file('[update_network.py] [MISSING] Must create %s.' % (RNA_SEQ_INFO_DATABASE_JSON), UPDATE_NETWORK_LOG_FILE) # main FILE_LIST_TO_CHECK = [PARAMETER_FOR_BUILDCMATRIX, PARAMETER_FOR_BUILDRMATRIX, PARAMETER_FOR_NET, \ MERGED_EDGE_FILE, BINDING_FILE, TPM_FILE] # a list of important files make_important_dirs() # make important directories (if non-existent) for holding various kinds of files, must be put after os.chdir(CODE_DIR) #validate_webapp_dir(PARAMETER_FOR_NET) # make sure the directory Webapp contains necessary files, e.g., genes.json. check_rnaseq_info() # rnaseq informtion is useful for displaying scatterplots # Make sure all necessary files are present, if not, make them if possible miss_lst = all_files_present(FILE_LIST_TO_CHECK) # check if any of them are missing if miss_lst != []: # miss_lst is non-empty in the beginning. print('These mandatory files are missing: %s.\nPrepare them first.' % (' '.join(miss_lst))) write_log_file('[update_network.py] Cannot find these required files:%s' % (' '.join(miss_lst)), UPDATE_NETWORK_LOG_FILE) # initially, we (at most) only have three parameter files, no binding.txt, TPM.txt or edges.txt ... important_miss_number = 0 if PARAMETER_FOR_BUILDCMATRIX in miss_lst: print('[update_network.py]: must prepare %s first.' % (PARAMETER_FOR_BUILDCMATRIX)) important_miss_number += 1 if PARAMETER_FOR_BUILDRMATRIX in miss_lst: print('[update_network.py]: must prepare %s first.' % (PARAMETER_FOR_BUILDRMATRIX)) important_miss_number += 1 if PARAMETER_FOR_NET in miss_lst: print('[update_network.py]: must prepare %s first.' % (PARAMETER_FOR_NET)) important_miss_number += 1 if important_miss_number > 0: sys.exit() # need to provide all the above three files; otherwise cannot proceed if BINDING_FILE in miss_lst: print('[update_network.py]: make initial binding.txt ... wait') write_log_file('[update_network.py] Make initial binding.txt', UPDATE_NETWORK_LOG_FILE) cmd = 'python3 get_binding.py %s' % (PARAMETER_FOR_BUILDCMATRIX) #os.system(cmd) cmd = 'python3 buildCmatrix.py %s > %s' % (PARAMETER_FOR_BUILDCMATRIX, BINDING_FILE) #os.system(cmd) print('[update_network.py]: IMPORATNT: make sure BINDING_MATRIX in %s was set %s and rerun update_network.py.' % (PARAMETER_FOR_NET, BINDING_FILE)) sys.exit() if TPM_FILE in miss_lst: print('[update_network.py]: make initial TPM.txt ... wait') write_log_file('[update_network.py] Make initial TPM.txt', UPDATE_NETWORK_LOG_FILE) cmd = 'python3 buildRmatrix.py %s' % (PARAMETER_FOR_BUILDRMATRIX) # produce TPM.txt os.system(cmd) print('[update_network.py]:IMPORTANT: make sure EXPRESSION_MATRIX in %s was set %s and rerun update_network.py.' % (PARAMETER_FOR_NET, TPM_FILE)) sys.exit() miss_lst2 = all_files_present(FILE_LIST_TO_CHECK) # check files again if len(miss_lst2) == 1 and miss_lst2[0] == MERGED_EDGE_FILE: # all other files are ready except edges.txt, make one. print('[update_network.py]: make initial edges.txt ... wait') create_edgeds0() # Make json2 (sliced binding.txt) if it does not exist. Copy json2 to # the web application folder static/edges [do it manually] for displaying # binding strength plots. if not os.path.isdir('../Data/history/bind/json2') and os.path.exists(BINDING_FILE): write_log_file('Make directory ../Data/history/bind/json2. Don\'t forget to copy json2 to static/edges in the web application.', UPDATE_NETWORK_LOG_FILE) cmd = 'python3 slice_binding_to_JSON.py %s' % (PARAMETER_FOR_NET) os.system(cmd) # Make json (sliced TPM.txt) if it does not exist. Copy json to the # web application folder static/edges [manual] for displaying gene # expression scatterplots. if not os.path.isdir('../Data/history/expr/json') and os.path.exists(TPM_FILE): write_log_file('Make directory ../Data/history/expr/json. Don\'t forget to copy json to static/edges in the web application.', UPDATE_NETWORK_LOG_FILE) cmd = 'python3 slice_TPM_to_JSON.py %s' % (PARAMETER_FOR_NET) os.system(cmd) # Make sure parameter files are present and valid (rudimentary check but important) validate_parameter_for_buildcmatrix(PARAMETER_FOR_BUILDCMATRIX) validate_parameter_for_buildrmatrix(PARAMETER_FOR_BUILDRMATRIX) validate_parameter_for_net(PARAMETER_FOR_NET) # If the file timestamp does not exist, create one if not os.path.exists(FILE_TIMESTAMP): record_file_time(FILE_LIST_TO_CHECK, FILE_TIMESTAMP) # Get update time of mandatory files timestamp_dict = read_file_timestamp(FILE_TIMESTAMP) ################## binding.txt stuff ##################################### # Check parameter_for_buildCmatrix.txt updated_file_list = get_updated_files(FILE_LIST_TO_CHECK, timestamp_dict) if 'parameter_for_buildCmatrix.txt' in updated_file_list and not hold_on(PARAMETER_FOR_BUILDCMATRIX): write_log_file('[update_network.py] Parameter file %s has been updated.' % (PARAMETER_FOR_BUILDCMATRIX), UPDATE_NETWORK_LOG_FILE) write_log_file('[update_network.py] Make binding column files', UPDATE_NETWORK_LOG_FILE) cmd = 'python3 get_binding.py %s' % (PARAMETER_FOR_BUILDCMATRIX) # won't re-compute existing binding columns unless updated os.system(cmd) updated_file_list = get_updated_files(FILE_LIST_TO_CHECK, timestamp_dict) if 'binding.txt' in updated_file_list: write_log_file('[update_network.py] binding.txt has been updated. This update will take effect next time TPM.txt is updated.', UPDATE_NETWORK_LOG_FILE) # create_edges0() # create_edges0B() # wedge() # correlation_per_group() # correlation_per_group_fixed_number() # correlation_mixtools(2) # correlation_mixtools(3) ## TODO mixtool stuff, forget it for now. #cmd = 'nohup python3 create_edges4.py %s &' % (temp_file_name) #os.system(cmd) ################## TPM.txt stuff ##################################### # update parameter_for_buildRmatrix.txt periodically and automatically. if datetime.now().day % BUILDRMATRIX_RENEW_INTERVAL == 0: # check if need to update parameter_for_buildRmatrix.txt bi-weekly curr_time = datetime.now().strftime('%Y%m%d%H%M') new_parameter_file = '../Data/temp/parameter_for_buildRmatrix.%s' % (curr_time) cmd = 'python3 make_parameter_rnaseq.py > %s' % (new_parameter_file) # new_parameter_file will not be updated unless download_and_map.py has finished. os.system(cmd) num = number_rnaseq_diff(new_parameter_file, TPM_FILE) if num >= MIN_RNA_SEQ_INCREASE: # sufficient number of RNA-seq samples have been added write_log_file('[update_network.py] Update %s' % (PARAMETER_FOR_BUILDRMATRIX), UPDATE_NETWORK_LOG_FILE) cmd = 'cp %s %s' % (new_parameter_file, PARAMETER_FOR_BUILDRMATRIX) os.system(cmd) else: write_log_file('[update_network.py] You have downloaded %d RNA-seq since last build of TPM.txt. TPM.txt will be rebuilt if this number reaches %d.' % (num, MIN_RNA_SEQ_INCREASE), UPDATE_NETWORK_LOG_FILE) # Check if parameter_for_buildRmatrix.txt has been updated updated_file_list = get_updated_files(FILE_LIST_TO_CHECK, timestamp_dict) # TODO To simplify things, I will provide TPM.txt directly. So set the # HOLDON option to YES in parameter_for_buildRmatrix.txt to prevent # the following from being True. if 'parameter_for_buildRmatrix.txt' in updated_file_list and not hold_on(PARAMETER_FOR_BUILDRMATRIX): write_log_file('[update_network.py] Parameter file %s has been updated.' % (PARAMETER_FOR_BUILDRMATRIX), UPDATE_NETWORK_LOG_FILE) write_log_file('[update_network.py] Rebuild TPM.txt ...', UPDATE_NETWORK_LOG_FILE) curr_time = datetime.now().strftime('%Y%m%d%H%M%S') if os.path.exists(TPM_FILE): backup_file_name = '../Data/history/expr/TPM.txt.backup.at.%s' % (curr_time) cmd = 'cp %s %s' % (TPM_FILE, backup_file_name) os.system(cmd) cmd = 'gzip %s' % (backup_file_name) os.system(cmd) cmd = 'python3 buildRmatrix.py %s' % (PARAMETER_FOR_BUILDRMATRIX) # produce TPM.txt, whose location is specified in TPM_TABLE in buidlRmatrix.py os.system(cmd) curr_date = datetime.now().strftime('%Y%m%d') tpm_sample_size = number_rnaseq_id(TPM_FILE) write_sample_size_file(SAMPLE_SIZE_FILE, curr_date, tpm_sample_size) # Create edges using all RNA-seq experiments updated_file_list = get_updated_files(FILE_LIST_TO_CHECK, timestamp_dict) if 'TPM.txt' in updated_file_list: # we could _touch_ TPM.txt to make it recent. We will recompute edges using the full binding.txt. # Make a full binding.txt since we are going to use the new TPM.txt to recompute all edges write_log_file('[update_network.py] Build full binding matrix for the new TPM.txt.', UPDATE_NETWORK_LOG_FILE) cmd = 'python3 buildCmatrix.py %s include-all > %s' % (PARAMETER_FOR_BUILDCMATRIX, BINDING_FILE) # include all ChIP-seq IDs. Pay attention to include-all in the command-line argument. os.system(cmd) # target_tf.txt write_log_file('[update_network.py] Make target_tf.txt.', UPDATE_NETWORK_LOG_FILE) cmd = 'python3 make_target_tf.py %s > %s' % (PARAMETER_FOR_NET, TARGET_TF_FILE) os.system(cmd) write_log_file('[update_network.py] Update ../Data/history/expr/json using the new TPM.txt. Don\'t forget to update the static/edges/json folder in the web application.', UPDATE_NETWORK_LOG_FILE) ## json -- make/renew json directory for displaying scatterplots cmd = 'python3 slice_TPM_to_JSON.py %s' % (PARAMETER_FOR_NET) ## os.system(cmd) # turn this on if we are going to use this TPM.txt for displaying scatterplots write_log_file('[update_network.py] Update directory ../Data/history/bind/json2. Don\'t forget to copy json2 to static/edges in the web application.', UPDATE_NETWORK_LOG_FILE) cmd = 'python3 slice_binding_to_JSON.py %s' % (PARAMETER_FOR_NET) #os.system(cmd) # turn this on if we are going to use this binding.txt for displaying bar charts of binding strengths ## copy ../Data/history/bind/json2 and ../Data/history/expr/json to the web application folder 'static/edges' [manual] if False: # TODO For now I will always use travadb's TPM.txt (138 columns) to display scatterplots. Simpler and faster. write_log_file('Assign tissue, refine tissue and update rnaseq_info_database.json', UPDATE_NETWORK_LOG_FILE) os.environ["PYTHONIOENCODING"] = "UTF-8" # for non-ascii letters in ENA RNA-sample description. If this statement does not work, try 'export PYTHONIOENCODING=UTF-8' in the command line instead. The export command can be put in crontab -e before running this script cmd = 'python3 assign_tissue.py' os.system(cmd) cmd = 'python3 refine_tissue.py > ../Data/information/experiment.and.tissue.2.txt' os.system(cmd) cmd = 'python3 update_rnaseq_info_json.py' os.system(cmd) # Compute edges. This could take a lot of time so update FILE_TIMESTAMP first. record_file_time(FILE_LIST_TO_CHECK, FILE_TIMESTAMP) create_edges0() create_edges0B() wedge() correlation_per_group() correlation_per_group_fixed_number() correlation_mixtools(2) # two components #correlation_mixtools(3) ########## Merge edges ####################### # update edges.txt, a merged file from two sources, HISTORY_DIR and HISTORY_DIR2. Some new edge files are being generated ... time.sleep(5) edge_file_lst = [] # collect edge files. most_recent_edge_modification_time = 0 write_log_file('[update_network.py] Look at edge files in %s.' % (HISTORY_DIR), UPDATE_NETWORK_LOG_FILE) for fname in glob.glob(os.path.join(HISTORY_DIR, 'edges.txt.*')): # many small edges.txt.* are to be merged edge_file_lst.append(fname) if os.path.getmtime(fname) > most_recent_edge_modification_time: most_recent_edge_modification_time = os.path.getmtime(fname) write_log_file('[update_network.py] Look at edge files in %s.' % (HISTORY_DIR2), UPDATE_NETWORK_LOG_FILE) for fname in glob.glob(os.path.join(HISTORY_DIR2, 'edges.txt.*')): # edges.txt.* are to be merged edge_file_lst.append(fname) if os.path.getmtime(fname) > most_recent_edge_modification_time: most_recent_edge_modification_time = os.path.getmtime(fname) if edge_file_lst == []: write_log_file('[update_network.py] No edge files to merge in %s and %s.' % (HISTORY_DIR, HISTORY_DIR2), UPDATE_NETWORK_LOG_FILE) elif os.path.getmtime(MERGED_EDGE_FILE) < most_recent_edge_modification_time: # update edges.txt only if there are newer edges to add. # concatenate edge files into one write_log_file('[update_network.py] Concatenate edge files in %s and %s into one file.' % (HISTORY_DIR, HISTORY_DIR2), UPDATE_NETWORK_LOG_FILE) curr_time = datetime.now().strftime('%Y%m%d_%H%M') concatenate_edge_files(edge_file_lst, os.path.join(EDGE_POOL_DIR, 'edges.txt.many.one.targets.' + curr_time)) delete_edge_files(edge_file_lst) if os.path.getmtime(MERGED_EDGE_FILE) < os.path.getmtime(EDGE_POOL_DIR): # edge pool directory has been updated, create new edges.txt write_log_file('[update_network.py] Make a new edges.txt from edge files in %s.' % (EDGE_POOL_DIR), UPDATE_NETWORK_LOG_FILE) write_log_file('[update_network.py] Number of lines in the old edges.txt: %d.' % (num_line(MERGED_EDGE_FILE)), UPDATE_NETWORK_LOG_FILE) cmd = 'python3 merge_edges.py' os.system(cmd) write_log_file('[update_network.py] Number of lines in the new edges.txt: %d.' % (num_line(MERGED_EDGE_FILE)), UPDATE_NETWORK_LOG_FILE) manual_copy_commands = 'Please copy files to the web application: sudo cp /home/lanhui/brain/Data/temp/edges.txt /var/www/brain/brain/static/edges/edges.txt sudo cp /home/lanhui/brain/Data/temp/html_edges/edges.sqlite /var/www/brain/brain/static/edges' write_log_file('[update_network.py] %s' % (manual_copy_commands), UPDATE_NETWORK_LOG_FILE) # exclude edges as suggested by Phil Wigge. # write_log_file('Exclude edges (now ineffective)', UPDATE_NETWORK_LOG_FILE) # cmd = 'python3 exclude_edges.py %s' % (EDGE_FILE) #os.system(cmd) # # check if parameter_for_net.txt, or TPM.txt is updated, if yes, create edges. # updated_file_list = get_updated_files(FILE_LIST_TO_CHECK, timestamp_dict) # if ('parameter_for_net.txt' in updated_file_list or 'TPM.txt' in updated_file_list) and not hold_on(PARAMETER_FOR_NET): # write_log_file('Create edges.txt using new TPM.txt (size=%d) ...' % (number_rnaseq_id(TPM_FILE)), UPDATE_NETWORK_LOG_FILE) # time.sleep(7200) # wait one hour for the previous create_edges4.py (if any) to finish creating JSON_DIR and target_tf_fname # cmd = 'nohup python3 create_edges4.py %s &' % (PARAMETER_FOR_NET) # put process to background # os.system(cmd) # time.sleep(60) # remove .R files in ../Data/temp. Files older than 3 days will be removed cmd = 'find %s -mtime +2 -name \"*.R\" -delete' % (TEMP_DIR) os.system(cmd) # update time stamp file record_file_time(FILE_LIST_TO_CHECK, FILE_TIMESTAMP) write_log_file('[update_network.py] Update done at %s.\n\n' % (datetime.now().strftime('%Y-%m-%d %H:%M:%S')), UPDATE_NETWORK_LOG_FILE)