comparison filter_fasta.py @ 10:c9e6e2e7697c draft

Uploaded

9:6794a638a504

    data = readtab(infile)
    cnt = 0
    header_start = 0
    prot_start = 0
    for i in data:
        if "Accession" in i: # finds the start of header
            header_start = cnt
            break
        cnt += 1
    header = data[header_start]
    if "Accession Number" in header:
        prot_start = header.index("Accession Number")
    elif "Accession" in header:
        prot_start = header.index("Accession")
    proteins = []
    for protein in data[1:]:
        proteins.append(protein[prot_start])
    return proteins
def FilterFastaSeq(infile,accession): # fasta file and UniprotID/SwissprotID
    input_data = readtab(infile)
    seq=[]
    header=[]

    for i in input_data:
        cnt+=1
        if flag == 1: # once we have a hit, start adding the sequences
            if ">" not in i[0]: # don't add the headers to the sequence
                temp.append(i[0])
                #print temp
        if i[0].startswith(">"): # is it a fasta header?    
            if temp != []: # if it is a continued fasta header, add old sequences to the sequence list
            # will this cutoff the last on of the file?
                merged = "\n".join(temp)
                if merged!="":

    x = open("output.txt","w")
    for i in header:
        x.write(i+'\n'+seq[cnt]+'\n')
        cnt+=1
    x.close()
fasta = sys.argv[1] # fasta file to filter
data = sys.argv[2] # scaffold report #2 -- filename

FilterFastaSeq(fasta,getAccessions(data))
os.rename("output.txt", sys.argv[3])

10:c9e6e2e7697c

    data = readtab(infile)
    cnt = 0
    header_start = 0
    prot_start = 0
    for i in data:
        if "Accession Number" in i: # finds the start of header
            header_start = cnt
            break
        cnt += 1
    header = data[header_start]
    if "Accession Number" in header:
        prot_start = header.index("Accession Number")
    elif "Accession" in header:
        prot_start = header.index("Accession")
    proteins = []
    for protein in data[header_start:]:
        if len(protein) > prot_start:
            proteins.append(protein[prot_start])
    return proteins
def FilterFastaSeq(infile,accession): # fasta file and UniprotID/SwissprotID
    input_data = readtab(infile)
    seq=[]
    header=[]

    for i in input_data:
        cnt+=1
        if flag == 1: # once we have a hit, start adding the sequences
            if ">" not in i[0]: # don't add the headers to the sequence
                temp.append(i[0])
        if i[0].startswith(">"): # is it a fasta header?    
            if temp != []: # if it is a continued fasta header, add old sequences to the sequence list
            # will this cutoff the last on of the file?
                merged = "\n".join(temp)
                if merged!="":

    x = open("output.txt","w")
    for i in header:
        x.write(i+'\n'+seq[cnt]+'\n')
        cnt+=1
    x.close()
#fasta = sys.argv[1] # fasta file to filter
#data = sys.argv[2] # scaffold report #2 -- filename
fasta = r"C:\Users\Owner\Desktop\APOSTL\SAINT_preprocessing\SwissProt_HUMAN_2014_08.fasta"
data = r"C:\Users\Owner\Desktop\APOSTL\Scaffold\scaffold_EGFR.txt"

FilterFastaSeq(fasta,getAccessions(data))
os.rename("output.txt", "output1.txt")