alphabet = ['A','C','D','E','F','G','H','I','K','L','M','N','P','Q','R','S','T','V','W','Y','-'] M = 5643 L = 48 q = 21 function getSequenceFamily(filename): from Bio import SeqIO fasta_sequences = SeqIO.parse(open(filename),'fasta') family =[] with open(output_file) as out_file: for fasta in fasta_sequences: family.append(fasta.seq.tostring()) return family function getOccurenceMatrix(filename): family = getSequenceFamily(filename) '''matrice 48X21''' occMatrix = [[0]*L for i in range(q)] for col in range(L): for seq_number in range(M): AA=alphabet.index(family[seq_number][col]) occurenceMatrix[col][AA]++ #occurenceMatrix[i -> (0,48)][AA Concernee]++ return occurenceMatrix function scoreMatrix(filename): scoreMatrix = list(getOccurenceMatrix(filename)) for i in range(len(scoreMatrix[0])): for j in range(len(scoreMatrix)): scoreMatrix[i][j] += 1 scoreMatrix[i][j] /= M+q return scoreMatrix
Run
Reset
Share
Import
Link
Embed
Language▼
English
中文
Python Fiddle
Python Cloud IDE
Follow @python_fiddle
Browser Version Not Supported
Due to Python Fiddle's reliance on advanced JavaScript techniques, older browsers might have problems running it correctly. Please download the latest version of your favourite browser.
Chrome 10+
Firefox 4+
Safari 5+
IE 10+
Let me try anyway!
url:
Go
Python Snippet
Stackoverflow Question