Created
April 21, 2014 18:54
-
-
Save 1328/11152589 to your computer and use it in GitHub Desktop.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| import numpy as np | |
| from PIL import Image | |
| import collections | |
| colors = [ | |
| (238,203,173), | |
| (49,79,79), | |
| (100,149,237), | |
| (127,255,0), | |
| (255,255,0), | |
| (178,34,34), | |
| (255,140,0), | |
| (147,112,219), | |
| (199,21,133), | |
| (255,0,0), | |
| (139,69,19), | |
| (34,139,34), | |
| (0,100,0), | |
| (0,0,128), | |
| (255,250,205), | |
| (220,220,220), | |
| (255,228,225), | |
| (49,79,79), | |
| (0,191,255), | |
| (107,142,35), | |
| ] | |
| signifiers = ['A', 'C', 'D', 'E', 'F', 'G', 'H', | |
| 'I', 'K', 'L', 'M', 'N', 'P', 'Q', | |
| 'R', 'S', 'T', 'V', 'W', 'Y'] | |
| mask = {k:v for k,v in zip(signifiers, colors)} | |
| mask[' ']=(255,255,255) | |
| Y_LIMIT = 50 | |
| def read_genes(fn): | |
| c = 0 | |
| result = [] | |
| buffer = '' | |
| with open(fn, mode='r') as fh: | |
| for line in fh: | |
| if line.startswith('>') and buffer: | |
| result.append(buffer[0:500]) | |
| buffer = '' | |
| elif line.startswith('>'): | |
| pass | |
| else: | |
| buffer += line.strip() | |
| if len(result)>Y_LIMIT: | |
| break | |
| ## for x,r in enumerate(result): | |
| ## print(x,':',len(r)) | |
| ## print(collections.Counter(r)) | |
| return result | |
| def build_image_array(data): | |
| '''for each data point apply mask to build a 3d of colors''' | |
| x_max = max([len(r) for r in data]) | |
| y_max = len(data) | |
| result = np.zeros((y_max, x_max, 3)) | |
| for y_idx, line in enumerate(data): | |
| for x_idx, c in enumerate(line): | |
| try: | |
| result[y_idx, x_idx] = mask[c] | |
| except KeyError: | |
| print('mask missing key for {}'.format(c)) | |
| print('on line: {}'.format(line)) | |
| result[y_idx, x_idx] = mask[' '] | |
| return result | |
| def find(line, what): | |
| try: | |
| return line.index(what) | |
| except ValueError: | |
| return None | |
| def slicie(some_string): | |
| for length in range(len(some_string),1,-1): | |
| for start_at in range(len(some_string)-length): | |
| yield start_at, some_string[start_at:start_at+length] | |
| def offset(a,b): | |
| '''offset b to match a''' | |
| found = '' | |
| found_offset = 0 | |
| for start, sliver in slicie(b): | |
| test = find(a, sliver) | |
| if not test: | |
| pass | |
| elif test>start and ((len(sliver)>len(found)) or \ | |
| (len(sliver) == len(found) and found_offset>test-start)): | |
| found = sliver | |
| found_offset = test-start | |
| ## print('found: {}, began at {} in a and repeats at {} in b -> {}'.format( | |
| ## sliver, start, test, found_offset)) | |
| elif len(found)<len(sliver): | |
| return found_offset | |
| return found_offset | |
| def align(data): | |
| '''jigger rows to align similar sequences''' | |
| for row in range(2, len(data)): | |
| move = offset(data[row-1],data[row]) | |
| if move: | |
| print('moving row {} -> {} spaces'.format( | |
| row, move)) | |
| data[row] = ''.join(' ' for _ in range(move)) + data[row] | |
| return(data) | |
| def main(): | |
| data = read_genes('some.fasta') | |
| data = align(data) | |
| img_array = build_image_array(data) | |
| img = Image.fromarray(img_array, 'RGB') | |
| img.show() | |
| ## img.save('test.png', 'PNG') | |
| return | |
| main() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment