Analyzing RsMergeArch

gistfile1.txt

#!/usr/bin/env python3                                                                                
                                                                                                      
import gzip                                                                                           
import os                                                                                             
import sys                                                                                            
import collections                                                                                    
                                                                                                      
def load_rsmerge_records(fname):                                                                      
    fields = ["rshigh", "rslow", "build_id", "orien", "create_time", "last_updated_time", "rscurrent", "orien2current", "comment"]
    Record = collections.namedtuple("Record", fields)                                                 
                                                                                                      
    with gzip.open(fname, "rt", encoding="utf-8") as f:                                               
        for line in f:                                                                                
            fields = line.rstrip("\n").split("\t")                                                    
            yield Record(*fields)                                                                     

def main(argv):                                                                                       
    rsmerge_fname = "/shares/hii/bioinfo/ref/ncbi/human_9606/2020/RsMergeArch.bcp.gz"                 
                                                                                                      
    records = []                                                                                      
    db = {}                                                                                           
                                                                                                      
    records = list(load_rsmerge_records(rsmerge_fname))                                               
                                                                                                      
    for r in records:                                                                                 
        db[r.rshigh] = r                                                                              

if __name__ == "__main__":                                                                            
    main(sys.argv)                                                                                    
                                                                                                      
# Record(rshigh='10674', rslow='3789', build_id='85', orien='0', create_time='2000-09-19 14:28:00.0', last_updated_time='2015-03-10 18:18:07.857', rscurrent='1228', orien2current='0', comment='[orien] estimaded per JIRA:SNP-7510')