QAseq-Fusion_v2.1/py_script/breakpoint_stat_v6.3.py

#!/usr/bin/python
# -*- coding:utf-8 -*-

import argparse,time
from StatReadsFusion import StatDoubleReadsFusion as SDRF

def GetUniqUMIPrimer(ID_list,readsPrimer_dict):
    UMIs_dict={}
    Primer_dict={}
    for ID in ID_list:
        temp=ID.split("_")
        if len(temp)>=5:
            UMI_tmp=ID.split("_")
            UMI = UMI_tmp[2]
            ReadsID = UMI_tmp[0]
            primer = readsPrimer_dict[ReadsID]
            UMIs_dict[UMI]=0
            Primer_dict[primer]=0
    return len(UMIs_dict),len(Primer_dict)

def OutResults(double_readsID_dict,double_site_dict,readsPrimer_dict,indir):
#out fusionseq and stat double and single readsID
    Final_FusionSeq_dict={}
    for key_seq in double_readsID_dict.keys():
        site_list = double_site_dict[key_seq]
        ID_list=double_readsID_dict[key_seq]
        doubleID=len(ID_list)
        singleID=0

        results=GetUniqUMIPrimer(ID_list,readsPrimer_dict)
        UMIs = results[0]
        primerNum = results[1]
        site_list.append(str(doubleID))
        site_list.append(str(singleID))
        site_list.append(str(UMIs))
        site_list.append(str(primerNum))
        Final_FusionSeq_dict[key_seq]=site_list
    
    fusion_points_file=indir+"/fusion_stat.txt"
    fusion_points=open(fusion_points_file,'w')
    fusion_points.write("\t".join(['Point','Point1_End','Point2_End','Overlap','DoubleRead','SingleRead','UMIkind','PrimerPair','FusionSeq'])+"\n")
    for key_seq in Final_FusionSeq_dict.keys():
        fusion_points.write("\t".join(Final_FusionSeq_dict[key_seq])+"\t"+key_seq+"\n")
    fusion_points.close()

    #输出每个ID对应fusion
    fusion_points_readsID_file=indir+"/fusion_readsID.txt"
    fusion_points_readsID=open(fusion_points_readsID_file,'w')
    fusion_points_readsID.write("\t".join(['Point','ReadsID','DoubleSingle'])+"\n")
    for key_seq in double_readsID_dict.keys():
        ID_list=double_readsID_dict[key_seq]
        site=double_site_dict[key_seq][0]
        for ID in ID_list:
            fusion_points_readsID.write("\t".join([site,ID,"Double"])+"\n")

    fusion_points_readsID.close()

def main(indir,readsIDFile):

    t1=time.time()

    double_readsID_dict={}
    double_site_dict={}
    readsPrimer_dict={}

    sdrf=SDRF()
    #double fusion
    double_points_file=indir+"/double_breakpoint.txt"
    sdrf.StatDouble(double_points_file,double_readsID_dict,double_site_dict)

    sdrf.StatPrimer(readsIDFile,readsPrimer_dict)
    #out results
    OutResults(double_readsID_dict,double_site_dict,readsPrimer_dict,indir)

    t2=time.time()
    print("Times: "+str(int(t2-t1))+"s")
    print("BreakPoints Stat Done!")


if __name__ == '__main__':
    parser = argparse.ArgumentParser(description='get reads mapping location')
    parser.add_argument('-i', required=True, type=str, help="indir")
    parser.add_argument('-r', required=True, type=str, help="reads primer file")
    args = parser.parse_args()
    main(args.i,args.r)