python_read_coodenate

from Bio import AlignIO

import re



alnfile  = "S_aa_MSA_pathogenic_v2.fasta"

OGlycTab = "O_S_glyc_all.txt"

InTab1 = open(OGlycTab, "r")

selected = []



with InTab1:

	for line in InTab1:

		lineArray = line.split()

		id = lineArray[0]

		coord = lineArray[3]

		score = lineArray[5]

		#print(id, coord, score) ### DIAG

		#score = float(score)

		#if (score < 0.5): continue ### If filter is applied

		score = str(score)

		selected.append(id + "\t" + coord+ "\t" +  score)

		### in case of empty line

		if 'str' in line:

			break

### close

InTab1.close()



###### MORE



##### OPENING fasta

alnfileObj = AlignIO.read(alnfile, "fasta")

for record in alnfileObj:

### Defining variants

	seqAln = record.seq

	NameSeqAln = record.id

	length = len(record.seq)

	length = int(length) 	### this number will be useful



	#print (NameSeqAln)



	# One by one

	gaps = 0

	for x in range(length):

		y = int(x - gaps + 1) ### This number is required for the number for every set

		a = seqAln[x:x+1:1] ### moving residue by residue

		a = (a.upper())

		if (a == '-'):

			gaps = (gaps + 1) ### Considerating gaps

		print (NameSeqAln,  end="")

		print ("\t", end="")

		print ( x+1 , end="")

		print ("\t", end="")

		print (y , end="")

		print ("\t", end="")

		print (a , end="")



		### Review for a score

		currscor = 0

		for alpha in selected:

			lineArray = alpha.split("\t")

			dd = lineArray[0]

			coordd = lineArray[1]

			scoree = lineArray[2]

			temp = dd.split(".") #New string to take dd before the underscore

			dd2 = temp[0]

			temp2 = NameSeqAln.split("_")

			NameSeqAln2 = temp2[0]

			if (NameSeqAln == dd): ### If the id from the fasta is the same as the tab id

				if (coordd == y):

					currscor = scoree

				if (a == '-'): ### Put a zero if the character is a gap

					currscor = 0

		print ("\t", end="")

		print (currscor , end="")

		print ( "" , end="\n")





### End.