diff options
| author | Hui Lan <lanhui@zjnu.edu.cn> | 2025-04-09 15:45:21 +0800 |
|---|---|---|
| committer | Hui Lan <lanhui@zjnu.edu.cn> | 2025-04-09 15:45:21 +0800 |
| commit | 75ec1d1e8c10fec0d4a29029fe0e35813271e020 (patch) | |
| tree | 7ff18d679da0806dbdc81b8c5d3caa197673e840 | |
| parent | 078feb13937fe6566307e4ad612a7bc93b7fcf9c (diff) | |
Maintenance
| -rw-r--r-- | Code/configure.py | 2 | ||||
| -rw-r--r-- | Code/download_and_map.py | 5 |
2 files changed, 3 insertions, 4 deletions
diff --git a/Code/configure.py b/Code/configure.py index 5c89cae..a798e4d 100644 --- a/Code/configure.py +++ b/Code/configure.py @@ -12,7 +12,7 @@ RNA_SEQ_INFO_FILE = '../Data/information/rnaseq_info_database.json' # some data DOWNLOADED_SRA_ID_LOG_FILE = '../Data/log/download_log.txt' # a list of downloaded SRA IDs IGNORED_SRA_ID_LOG_FILE = '../Data/log/download_log_small_sized_ids.txt' # store SRA IDs with small file size. MAPPED_RDATA_DIR = '../Data/R/Mapped/public' # mapped RNA-seq (file names ended with _quant.txt) go here -RAW_RDATA_DIR = '/disk1/Data/R/Raw' # downloaded files go here, was "../Data/R/Raw" (now almost full). +RAW_RDATA_DIR = '/disk1/Data/R/Raw' # downloaded files go here, was "../Data/R/Raw" # From update_network.py # Don'T change the following paths and names diff --git a/Code/download_and_map.py b/Code/download_and_map.py index 3f6e14b..c21e114 100644 --- a/Code/download_and_map.py +++ b/Code/download_and_map.py @@ -1,7 +1,6 @@ # Usage: python dowload_and_map.py # python download_and_map.py run_ids.txt # -# Edit DAILY_DOWNLOAD_NUMBER and MIN_FILE_SIZE # # This program checks RNA_SEQ_INFO_FILE for not yet downloaded, *public* RNA-seq data, make a list of them, download and map using Salmon. It is very important to prepare # RNA_SEQ_INFO_FILE (see parse_end_xlm.py). In fact, only first column of RNA_SEQ_INFO_FILE is required in this file, that is a list of RNA-seq IDs. @@ -25,8 +24,6 @@ from datetime import datetime ########################################################################################## from configure import DAILY_MAP_NUMBER, MIN_FASTQ_FILE_SIZE, RNA_SEQ_INFO_FILE, DOWNLOADED_SRA_ID_LOG_FILE, IGNORED_SRA_ID_LOG_FILE, UPDATE_NETWORK_LOG_FILE, MAPPED_RDATA_DIR, RAW_RDATA_DIR, SALMON_MAP_RESULT_DIR -FASTQ_DUMP_PATH = '/home/hui/software/sratoolkit/sratoolkit.2.8.0-ubuntu64/bin/fastq-dump' - ########################################################################################## def glob_files(directory, pattern): @@ -229,8 +226,10 @@ def download_and_map_data(lst, daily_map_num, dest): return downloaded_files, map_list + def download_data2(lst, dest): ''' Download data from SRA, slow ''' + FASTQ_DUMP_PATH = '/home/hui/software/sratoolkit/sratoolkit.2.8.0-ubuntu64/bin/fastq-dump' if not os.path.exists(FASTQ_DUMP_PATH): print('%s not exists.' % (FASTQ_DUMP_PATH)) sys.exit() |