|
0
|
1 # A translation of aggregate.pl into python! For analysis of Tn-Seq.
|
|
|
2 # This script requires BioPython just like calc_fitness.py, so you need it installed along with its dependencies if you want to run these scripts on your own.
|
|
|
3 # How to install BioPython and a list of its dependencies can be found here: http://biopython.org/DIST/docs/install/Installation.html
|
|
|
4 # K. McCoy
|
|
|
5
|
|
|
6
|
|
|
7
|
|
|
8
|
|
|
9
|
|
|
10
|
|
|
11
|
|
|
12
|
|
|
13
|
|
|
14 ##### ARGUMENTS #####
|
|
|
15
|
|
|
16 def print_usage():
|
|
|
17 print "Aggregate.py's usage is as follows:" + "\n\n"
|
|
|
18 print "\033[1m" + "Required" + "\033[0m" + "\n"
|
|
|
19 print "-o" + "\t\t" + "Output file for aggregated data." + "\n"
|
|
|
20 print "\n"
|
|
|
21 print "\033[1m" + "Optional" + "\033[0m" + "\n"
|
|
|
22 print "-c" + "\t\t" + "Check for missing genes in the data set - provide a reference genome in genbank format. Missing genes will be sent to stdout." + "\n"
|
|
|
23 print "-m" + "\t\t" + "Place a mark in an extra column for this set of genes. Provide a file with a list of genes seperated by newlines." + "\n"
|
|
|
24 print "-x" + "\t\t" + "Cutoff: Don't include fitness scores with average counts (c1+c2)/2 < x (default: 0)" + "\n"
|
|
|
25 print "-b" + "\t\t" + "Blanks: Exclude -b % of blank fitness scores (scores where c2 = 0) (default: 0 = 0%)" + "\n"
|
|
|
26 print "-f" + "\t\t" + "An in-between file carrying information on the blank count found from calc_fitness or consol_fitness; one of two ways to pass a blank count to this script" + "\n"
|
|
|
27 print "-w" + "\t\t" + "Use weighted algorithm to calculate averages, variance, sd, se" + "\n"
|
|
|
28 print "-l" + "\t\t" + "Weight ceiling: maximum value to use as a weight (default: 999,999)" + "\n"
|
|
|
29 print "\n"
|
|
|
30 print "All remainder arguements will be treated as fitness files (those files created by calc_fitness.py)" + "\n"
|
|
|
31 print "\n"
|
|
|
32
|
|
|
33 import argparse
|
|
|
34 parser = argparse.ArgumentParser()
|
|
|
35 parser.add_argument("-o", action="store", dest="summary")
|
|
|
36 parser.add_argument("-c", action="store", dest="find_missing")
|
|
|
37 parser.add_argument("-m", action="store", dest="marked")
|
|
|
38 parser.add_argument("-x", action="store", dest="cutoff")
|
|
|
39 parser.add_argument("-b", action="store", dest="blank_pc")
|
|
|
40 parser.add_argument("-f", action="store", dest="blank_file")
|
|
|
41 parser.add_argument("-w", action="store", dest="weighted")
|
|
|
42 parser.add_argument("-l", action="store", dest="weight_ceiling")
|
|
|
43 parser.add_argument("fitnessfiles", nargs=argparse.REMAINDER)
|
|
|
44
|
|
|
45 arguments = parser.parse_args()
|
|
|
46
|
|
|
47 if not arguments.summary:
|
|
|
48 print "\n" + "You are missing a value for the -o flag. "
|
|
|
49 print_usage()
|
|
|
50 quit()
|
|
|
51
|
|
|
52 if not arguments.fitnessfiles:
|
|
|
53 print "\n" + "You are missing fitness file(s); these should be entered immediately after all the flags. "
|
|
|
54 print_usage()
|
|
|
55 quit()
|
|
|
56
|
|
|
57 # 999,999 is a trivial placeholder number
|
|
|
58
|
|
|
59 if (not arguments.weight_ceiling):
|
|
|
60 arguments.weight_ceiling = 999999
|
|
|
61
|
|
|
62 # Cutoff exists to discard positions with a low number of counted transcripts, because their fitness may not be as accurate - for the same reasoning that studies with low sample sizes can be innacurate.
|
|
|
63
|
|
|
64 if (not arguments.cutoff):
|
|
|
65 arguments.cutoff = 0
|
|
|
66
|
|
|
67 # Gets information from the txt output file of calc_fit / consol, if inputted
|
|
|
68
|
|
|
69 if arguments.blank_file:
|
|
|
70 with open(arguments.blank_file) as file:
|
|
|
71 blank_pc = file.read().splitlines()
|
|
|
72 arguments.blank_pc = float(blank_pc[0].split()[1])
|
|
|
73
|
|
|
74 if (not arguments.blank_pc):
|
|
|
75 arguments.blank_pc = 0
|
|
|
76
|
|
|
77
|
|
|
78
|
|
|
79
|
|
|
80
|
|
|
81 ##### SUBROUTINES #####
|
|
|
82
|
|
|
83 # A subroutine that calculates the average, variance, standard deviation (sd), and standard error (se) of a group of scores; for use when aggregating scores by gene later on
|
|
|
84
|
|
|
85 import math
|
|
|
86 def unweighted_average(scores):
|
|
|
87 sum = 0
|
|
|
88 num = 0
|
|
|
89 i = 0
|
|
|
90 while i < len(scores):
|
|
|
91 if not scores[i]:
|
|
|
92 scores[i] = 0.0
|
|
|
93 sum += float(scores[i])
|
|
|
94 num += 1
|
|
|
95 i += 1
|
|
|
96 average = sum/num
|
|
|
97 xminusxbars = 0
|
|
|
98 while i < len(scores):
|
|
|
99 xminusxbars += (float(scores[i]) - average)**2
|
|
|
100 if num <= 1:
|
|
|
101 variance = 0
|
|
|
102 else:
|
|
|
103 variance = xminusxbars/(num-1)
|
|
|
104 sd = math.sqrt(variance)
|
|
|
105 se = sd / math.sqrt(num)
|
|
|
106 return (average, variance, sd, se)
|
|
|
107
|
|
|
108 # A subroutine that calculates the weighted average, variance, standard deviation (sd), and standard error (se) of a group of scores; the weights come from the number of reads each insertion location has
|
|
|
109 # For use when aggregating scores by gene later on, if the weighted argument is called
|
|
|
110
|
|
|
111 def weighted_average(scores,weights):
|
|
|
112 sum = 0
|
|
|
113 weighted_average = 0
|
|
|
114 weighted_variance = 0
|
|
|
115 top = 0
|
|
|
116 bottom = 0
|
|
|
117 i = 0
|
|
|
118 while i < len(weights):
|
|
|
119 if not scores[i]:
|
|
|
120 scores[i] = 0.0
|
|
|
121 top += float(weights[i])*float(scores[i])
|
|
|
122 bottom += float(weights[i])
|
|
|
123 i += 1
|
|
|
124 if bottom == 0:
|
|
|
125 return 0
|
|
|
126 weighted_average = top/bottom
|
|
|
127 top = 0
|
|
|
128 bottom = 0
|
|
|
129 i = 0
|
|
|
130 while i < len(weights):
|
|
|
131 top += float(weights[i]) * (float(scores[i]) - weighted_average)**2
|
|
|
132 bottom += float(weights[i])
|
|
|
133 i += 1
|
|
|
134 weighted_variance = top/bottom
|
|
|
135 weighted_stdev = math.sqrt(weighted_variance)
|
|
|
136 weighted_stder = weighted_stdev/math.sqrt(len(scores))
|
|
|
137 return (weighted_average, weighted_variance, weighted_stdev, weighted_stder)
|
|
|
138
|
|
|
139
|
|
|
140
|
|
|
141
|
|
|
142
|
|
|
143
|
|
|
144
|
|
|
145
|
|
|
146
|
|
|
147
|
|
|
148 ##### AGGREGATION / CALCULATIONS #####
|
|
|
149
|
|
|
150 #Reads the genes which should be marked in the final aggregate file into an array
|
|
|
151
|
|
|
152 import os.path
|
|
|
153 if arguments.marked:
|
|
|
154 with open(arguments.marked) as file:
|
|
|
155 marked_set = file.read().splitlines()
|
|
|
156
|
|
|
157 #Creates a dictionary of dictionaries to contain a summary of all genes and their fitness values
|
|
|
158 #The fitness values and weights match up, so that the weight of gene_summary[locus]["w"][2] would be gene_summary[locus]["s"][2]
|
|
|
159
|
|
|
160 import csv
|
|
|
161 gene_summary = {}
|
|
|
162 for eachfile in arguments.fitnessfiles:
|
|
|
163 with open(eachfile) as csvfile:
|
|
|
164 lines = csv.reader(csvfile)
|
|
|
165 for line in lines:
|
|
|
166 locus = line[9]
|
|
|
167 w = line[12]
|
|
|
168 if w == 'nW':
|
|
|
169 continue
|
|
|
170 if not w:
|
|
|
171 w == 0
|
|
|
172 c1 = float(line[2])
|
|
|
173 c2 = float(line[3])
|
|
|
174 avg = (c1+c2)/2
|
|
|
175 if avg < float(arguments.cutoff):
|
|
|
176 continue
|
|
|
177 if avg > float(arguments.weight_ceiling):
|
|
|
178 avg = arguments.weight_ceiling
|
|
|
179 if locus not in gene_summary:
|
|
|
180 gene_summary[locus] = {"w" : [], "s": []}
|
|
|
181 gene_summary[locus]["w"].append(w)
|
|
|
182 gene_summary[locus]["s"].append(avg)
|
|
|
183
|
|
|
184 #If finding any missing gene loci is requested in the arguments, starts out by loading all the known features from a genbank file
|
|
|
185
|
|
|
186 from Bio import SeqIO
|
|
|
187 if (arguments.find_missing):
|
|
|
188 output = [["locus","mean","var","sd","se","gene","Total","Blank","Not Blank","Blank Removed","M\n"]]
|
|
|
189 handle = open(arguments.find_missing, "rU")
|
|
|
190 for record in SeqIO.parse(handle, "genbank"):
|
|
|
191 refname = record.id
|
|
|
192 features = record.features
|
|
|
193 handle.close()
|
|
|
194
|
|
|
195 #Goes through the features to find which are genes
|
|
|
196
|
|
|
197 for feature in features:
|
|
|
198 gene = ""
|
|
|
199 if feature.type == "gene":
|
|
|
200 locus = "".join(feature.qualifiers["locus_tag"])
|
|
|
201 if "gene" in feature.qualifiers:
|
|
|
202 gene = "".join(feature.qualifiers["gene"])
|
|
|
203 else:
|
|
|
204 continue
|
|
|
205
|
|
|
206 #Goes through the fitness scores of insertions within each gene, and removes whatever % of blank fitness scores were requested along with their corresponding weights
|
|
|
207
|
|
|
208 sum = 0
|
|
|
209 num = 0
|
|
|
210 avgsum = 0
|
|
|
211 blank_ws = 0
|
|
|
212 i = 0
|
|
|
213 if locus in gene_summary.keys():
|
|
|
214 for w in gene_summary[locus]["w"]:
|
|
|
215 if float(w) == 0:
|
|
|
216 blank_ws += 1
|
|
|
217 else:
|
|
|
218 sum += float(w)
|
|
|
219 num += 1
|
|
|
220 count = num + blank_ws
|
|
|
221 removed = 0
|
|
|
222 to_remove = int(float(arguments.blank_pc)*count)
|
|
|
223 if blank_ws > 0:
|
|
|
224 i = 0
|
|
|
225 while i < len(gene_summary[locus]["w"]):
|
|
|
226 w = gene_summary[locus]["w"][i]
|
|
|
227 if removed == to_remove:
|
|
|
228 break
|
|
|
229 if float(w) == 0:
|
|
|
230 del gene_summary[locus]["w"][i]
|
|
|
231 del gene_summary[locus]["s"][i]
|
|
|
232 removed += 1
|
|
|
233 i -= 1
|
|
|
234 i += 1
|
|
|
235
|
|
|
236 #If all the fitness values within a gene are empty, sets mean/var to 0.10 and Xs out sd/se; marks the gene if that's requested
|
|
|
237
|
|
|
238 if num == 0:
|
|
|
239 if (arguments.marked and locus in marked_set):
|
|
|
240 output.append([locus, "0.10", "0.10", "X", "X", gene, count, blank_ws, num, removed, "M", "\n"])
|
|
|
241 else:
|
|
|
242 output.append([locus, "0.10", "0.10", "X", "X", gene, count, blank_ws, num, removed, "\n"])
|
|
|
243
|
|
|
244 #Otherwise calls average() or weighted_average() to find the aggregate w / count / standard deviation / standard error of the insertions within each gene; marks the gene if that's requested
|
|
|
245
|
|
|
246 else:
|
|
|
247 if not arguments.weighted:
|
|
|
248 (average, variance, stdev, stderr) = unweighted_average(gene_summary[locus]["w"])
|
|
|
249 else:
|
|
|
250 (average, variance, stdev, stderr) = weighted_average(gene_summary[locus]["w"],gene_summary[locus]["s"])
|
|
|
251 if (arguments.marked and locus in marked_set):
|
|
|
252 output.append([locus, average, variance, stdev, stderr, gene, count, blank_ws, num, removed, "M", "\n"])
|
|
|
253 else:
|
|
|
254 output.append([locus, average, variance, stdev, stderr, gene, count, blank_ws, num, removed, "\n"])
|
|
|
255
|
|
|
256 #If a gene doesn't have any insertions, sets mean/var to 0.10 and Xs out sd/se, plus leaves count through removed blank because there were no reads.
|
|
|
257
|
|
|
258 else:
|
|
|
259 if (arguments.marked and locus in marked_set):
|
|
|
260 output.append([locus, "0.10", "0.10", "X", "X", gene, "", "", "", "", "M", "\n"])
|
|
|
261 else:
|
|
|
262 output.append([locus, "0.10", "0.10", "X", "X", gene, "", "", "", "", "\n"])
|
|
|
263
|
|
|
264 #Writes the aggregated fitness file
|
|
|
265
|
|
|
266 with open(arguments.summary, "wb") as csvfile:
|
|
|
267 writer = csv.writer(csvfile)
|
|
|
268 writer.writerows(output)
|
|
|
269
|
|
|
270 #If finding missing genes is not requested, just finds the aggregate w / count / standard deviation / standard error of the insertions within each gene, and writes them to a file, plus marks the genes requested
|
|
|
271 #This is never called through Galaxy since finding missing genes is just better than not finding them.
|
|
|
272
|
|
|
273 else:
|
|
|
274 output = [["Locus","W","Count","SD","SE","M\n"]]
|
|
|
275 for gene in gene_summary.keys():
|
|
|
276 sum = 0
|
|
|
277 num = 0
|
|
|
278 average = 0
|
|
|
279 if "w" not in gene_summary[gene]:
|
|
|
280 continue
|
|
|
281 for i in gene_summary[gene]["w"]:
|
|
|
282 sum += i
|
|
|
283 num += 1
|
|
|
284 average = sum/num
|
|
|
285 xminusxbars = 0
|
|
|
286 for i in w:
|
|
|
287 xminusxbars += (i-average)**2
|
|
|
288 if num > 1:
|
|
|
289 sd = math.sqrt(xminusxbars/(num-1))
|
|
|
290 se = sd / math.sqrt(num)
|
|
|
291 if (arguments.marked and locus in marked_set):
|
|
|
292 output.append([gene, average, num, sd, se, "M", "\n"])
|
|
|
293 else:
|
|
|
294 output.append([gene, average, num, sd, se, "\n"])
|
|
|
295 with open(arguments.summary, "wb") as csvfile:
|
|
|
296 writer = csv.writer(csvfile)
|
|
|
297 writer.writerows(output) |
