Parsing large files having different contigs( contigs contain details about genes)

Following  python source code counts the total number of contigs present in a file and extracts number of genes, Complementary DNA strand, and other information. This program will run on files downloaded from NCBI.

#Nadia Baig

fr=open("C:\\Users\\XYZ\\Desktop\\chromosome.gbk,r") #Path and file name

a=fr.read()

b=a.split("//\n")  #split the whole file on //

length=len(b)#counting length

i=0

genes=[]

for base in b:

 a=base.split("\n")

 for bb in a:

    if bb.startswith("     gene            ") :

     i=i+1

    

 genes.append(i)

print(genes)  # printing information about contigs having genes

total=0

j=0

while j<len(genes):

    if genes[j]==0:

        total=total+1   #counting contigs having no genes

    j=j+1

Tgene=sum(genes)

print("total number of genes present in file",Tgene)   #total number of genes present in contig

print("total number of contigs having no genes are",total)

# printing those genes which have an attached cds or mRNA

#Having attached CDS

cds=[]

i=0

for CDS in b:

    c=CDS.split("\n")

    for cds1 in c:

        if cds1.startswith("     CDS             " ):

            i=i+1

           

    cds.append(i)

    i=0

print("details of CDS")      

print(cds)    #showing list of genes having attached cds

nad=sum(cds)  #TOtal number of cds

print('total number of attached cds',nad)

#genes having attached mRNA

mrna=[]

i=0

for CDS in b:

    c=CDS.split("\n")

    for cds1 in c:

        if cds1.startswith("     mRNA            "):

            i=i+1

           

    mrna.append(i)

    i=0

print("details of genes having attached mRNA")      

print(mrna) # list of total number of attached mrna,s in each contig

msum=sum(mrna)  #Total number of attached mrna,s in all contigs

print('total number of attached mrnas',msum)