Mercurial > repos > kaymccoy > consolidate_fitnesses

comparison consol_fit.py @ 7:4b2fc35b32b0 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author kaymccoy
date Fri, 12 Aug 2016 16:44:28 -0400
parents
children
comparison
equal deleted inserted replaced
6:b2943ce019bb 7:4b2fc35b32b0
1 # Consol_fit! It's a script & it'll consolidate your fitness values if you got them from a looping trimming pipeline instead of the standard split-by-transposon pipeline. That's all.
2 # K. McCoy
3
4 import math
5 import csv
6
7
8
9
10
11
12
13
14
15
16 ##### ARGUMENTS #####
17
18 def print_usage():
19 print "\n" + "You are missing one or more required flags. A complete list of flags accepted by calc_fitness is as follows:" + "\n\n"
20 print "\033[1m" + "Required" + "\033[0m" + "\n"
21 print "-i" + "\t\t" + "The calc_fit file to be consolidated" + "\n"
22 print "-out" + "\t\t" + "Name of a file to enter the .csv output." + "\n"
23 print "-out2" + "\t\t" + "Name of a file to put the percent blank score in (used in aggregate)." + "\n"
24 print "-calctxt" + "\t\t" + "The txt file output from calc_fit" + "\n"
25 print "-normalize" + "\t" + "A file that contains a list of genes that should have a fitness of 1" + "\n"
26 print "\n"
27 print "\033[1m" + "Optional" + "\033[0m" + "\n"
28 print "-cutoff" + "\t\t" + "Discard any positions where the average of counted transcripts at time 0 and time 1 is below this number (default 0)" + "\n"
29 print "-cutoff2" + "\t\t" + "Discard any positions within the normalization genes where the average of counted transcripts at time 0 and time 1 is below this number (default 0)" + "\n"
30 print "-wig" + "\t\t" + "Create a wiggle file for viewing in a genome browser. Provide a filename." + "\n"
31 print "-maxweight" + "\t" + "The maximum weight a transposon gene can have in normalization calculations" + "\n"
32 print "-multiply" + "\t" + "Multiply all fitness scores by a certain value (e.g., the fitness of a knockout). You should normalize the data." + "\n"
33 print "\n"
34
35 import argparse
36 parser = argparse.ArgumentParser()
37 parser.add_argument("-calctxt", action="store", dest="calctxt")
38 parser.add_argument("-normalize", action="store", dest="normalize")
39 parser.add_argument("-i", action="store", dest="input")
40 parser.add_argument("-out", action="store", dest="outfile")
41 parser.add_argument("-out2", action="store", dest="outfile2")
42 parser.add_argument("-cutoff", action="store", dest="cutoff")
43 parser.add_argument("-cutoff2", action="store", dest="cutoff2")
44 parser.add_argument("-wig", action="store", dest="wig")
45 parser.add_argument("-maxweight", action="store", dest="max_weight")
46 parser.add_argument("-multiply", action="store", dest="multiply")
47 arguments = parser.parse_args()
48
49 if (not arguments.input or not arguments.outfile or not arguments.calctxt):
50 print_usage()
51 quit()
52
53 if (not arguments.max_weight):
54 arguments.max_weight = 75
55
56 if (not arguments.cutoff):
57 arguments.cutoff = 0
58
59 # Cutoff2 only has an effect if it's larger than cutoff, since the normalization step references a list of insertions already affected by cutoff.
60
61 if (not arguments.cutoff2):
62 arguments.cutoff2 = 10
63
64 #Gets total & refname from calc_fit outfile2
65
66 with open(arguments.calctxt) as file:
67 calctxt = file.readlines()
68 total = float(calctxt[1].split()[1])
69 refname = calctxt[2].split()[1]
70
71
72
73
74
75
76
77
78
79
80 ##### CONSOLIDATING THE CALC_FIT FILE #####
81
82 with open(arguments.input) as file:
83 input = file.readlines()
84 results = [["position", "strand", "count_1", "count_2", "ratio", "mt_freq_t1", "mt_freq_t2", "pop_freq_t1", "pop_freq_t2", "gene", "D", "W", "nW"]]
85 i = 1
86 d = float(input[i].split(",")[10])
87 while i < len(input):
88 position = float(input[i].split(",")[0])
89 strands = input[i].split(",")[1]
90 c1 = float(input[i].split(",")[2])
91 c2 = float(input[i].split(",")[3])
92 gene = input[i].split(",")[9]
93 while i + 1 < len(input) and float(input[i+1].split(",")[0]) - position <= 4:
94 if i + 1 < len(input):
95 i += 1
96 c1 += float(input[i].split(",")[2])
97 c2 += float(input[i].split(",")[3])
98 strands = input[i].split(",")[1]
99 if strands[0] == 'b':
100 new_strands = 'b/'
101 elif strands[0] == '+':
102 if input[i].split(",")[1][0] == 'b':
103 new_strands = 'b/'
104 elif input[i].split(",")[1][0] == '+':
105 new_strands = '+/'
106 elif input[i].split(",")[1][0] == '-':
107 new_strands = 'b/'
108 elif strands[0] == '-':
109 if input[i].split(",")[1][0] == 'b':
110 new_strands = 'b/'
111 elif input[i].split(",")[1][0] == '+':
112 new_strands = 'b/'
113 elif input[i].split(",")[1][0] == '-':
114 new_strands = '-/'
115 if len(strands) == 3:
116 if len(input[i].split(",")[1]) < 3:
117 new_strands += strands[2]
118 elif strands[0] == 'b':
119 new_strands += 'b'
120 elif strands[0] == '+':
121 if input[i].split(",")[1][2] == 'b':
122 new_strands += 'b'
123 elif input[i].split(",")[1][2] == '+':
124 new_strands += '+'
125 elif input[i].split(",")[1][2] == '-':
126 new_strands += 'b'
127 elif strands[0] == '-':
128 if input[i].split(",")[1][2] == 'b':
129 new_strands += 'b'
130 elif input[i].split(",")[1][2] == '+':
131 new_strands += 'b'
132 elif input[i].split(",")[1][2] == '-':
133 new_strands += '-'
134 else:
135 if len(input[i].split(",")[1]) == 3:
136 new_strands += input[i].split(",")[1][2]
137 strands = new_strands
138 i +=1
139 if c2 != 0:
140 ratio = c2/c1
141 else:
142 ratio = 0
143 mt_freq_t1 = c1/total
144 mt_freq_t2 = c2/total
145 pop_freq_t1 = 1 - mt_freq_t1
146 pop_freq_t2 = 1 - mt_freq_t2
147 w = 0
148 if mt_freq_t2 != 0:
149 top_w = math.log(mt_freq_t2*(d/mt_freq_t1))
150 bot_w = math.log(pop_freq_t2*(d/pop_freq_t1))
151 w = top_w/bot_w
152 row = [position, strands, c1, c2, ratio, mt_freq_t1, mt_freq_t2, pop_freq_t1, pop_freq_t2, gene, d, w, w]
153 results.append(row)
154 with open(arguments.outfile, "wb") as csvfile:
155 writer = csv.writer(csvfile)
156 writer.writerows(results)
157
158
159
160
161
162
163
164
165
166
167 ##### REDOING NORMALIZATION #####
168
169 # The header below is just in a typical WIG file format; if you'd like to look into this more UCSC has notes on formatting WIG files on their site.
170
171 if (arguments.wig):
172 wigstring = "track type=wiggle_0 name=" + arguments.wig + "\n" + "variableStep chrom=" + refname + "\n"
173
174 if (arguments.normalize):
175 with open(arguments.normalize) as file:
176 transposon_genes = file.read().splitlines()
177 print "Normalize genes loaded" + "\n"
178 blank_ws = 0
179 sum = 0
180 count = 0
181 weights = []
182 scores = []
183 for list in results:
184 if list[9] != '' and list[9] in transposon_genes and list[11]:
185 c1 = list[2]
186 c2 = list[3]
187 score = list[11]
188 avg = (c1 + c2)/2
189
190 # Skips over those insertion locations with too few insertions - their fitness values are less accurate because they're based on such small insertion numbers.
191
192 if float(c1) >= float(arguments.cutoff2):
193
194 # Sets a max weight, to prevent insertion location scores with huge weights from unbalancing the normalization.
195
196 if (avg >= float(arguments.max_weight)):
197 avg = float(arguments.max_weight)
198
199 # Tallies how many w values are 0 within the blank_ws value; you might get many transposon genes with a w value of 0 if a bottleneck occurs, which is especially common with in vivo experiments.
200 # For example, when studying a nasal infection in a mouse model, what bacteria "sticks" and is able to survive and what bacteria is swallowed and killed or otherwise flushed out tends to be a matter of chance not fitness; all mutants with an insertion in a specific transposon gene could be flushed out by chance!
201
202 if score == 0:
203 blank_ws += 1
204 sum += score
205 count += 1
206 weights.append(avg)
207 scores.append(score)
208
209 print str(list[9]) + " " + str(score) + " " + str(c1)
210
211 # Counts and removes all "blank" fitness values of normalization genes - those that = 0 - because they most likely don't really have a fitness value of 0, and you just happened to not get any reads from that location at t2.
212
213 blank_count = 0
214 original_count = len(scores)
215 i = 0
216 while i < original_count:
217 w_value = scores[i]
218 if w_value == 0:
219 blank_count += 1
220 weights.pop[i]
221 scores.pop[i]
222 i-=1
223 i += 1
224
225 # If no normalization genes can pass the cutoff, normalization cannot occur, so this ends the script advises the user to try again and lower cutoff and/or cutoff2.
226
227 if len(scores) == 0:
228 print 'ERROR: The normalization genes do not have enough reads to pass cutoff and/or cutoff2; please lower one or both of those arguments.' + "\n"
229 quit()
230
231 pc_blank_normals = float(blank_count) / float(original_count)
232 print "# blank out of " + str(original_count) + ": " + str(pc_blank_normals) + "\n"
233 with open(arguments.outfile2, "w") as f:
234 f.write("blanks: " + str(pc_blank_normals) + "\n" + "total: " + str(total) + "\n" + "refname: " + refname)
235
236 average = sum / count
237 i = 0
238 weighted_sum = 0
239 weight_sum = 0
240 while i < len(weights):
241 weighted_sum += weights[i]*scores[i]
242 weight_sum += weights[i]
243 i += 1
244 weighted_average = weighted_sum/weight_sum
245
246 print "Normalization step:" + "\n"
247 print "Regular average: " + str(average) + "\n"
248 print "Weighted Average: " + str(weighted_average) + "\n"
249 print "Total Insertions: " + str(count) + "\n"
250
251 old_ws = 0
252 new_ws = 0
253 wcount = 0
254 for list in results:
255 if list[11] == 'W':
256 continue
257 new_w = float(list[11])/weighted_average
258
259 # Sometimes you want to multiply all the fitness values by a constant; this does that.
260 # For example you might multiply all the values by a constant for a genetic interaction screen - where Tn-Seq is performed as usual except there's one background knockout all the mutants share.
261
262 if arguments.multiply:
263 new_w *= float(arguments.multiply)
264
265 if float(list[11]) > 0:
266 old_ws += float(list[11])
267 new_ws += new_w
268 wcount += 1
269
270 list[12] = new_w
271
272 if (arguments.wig):
273 wigstring += str(list[0]) + " " + str(new_w) + "\n"
274
275 old_w_mean = old_ws / wcount
276 new_w_mean = new_ws / wcount
277 print "Old W Average: " + str(old_w_mean) + "\n"
278 print "New W Average: " + str(new_w_mean) + "\n"
279
280 with open(arguments.outfile, "wb") as csvfile:
281 writer = csv.writer(csvfile)
282 writer.writerows(results)
283
284 if (arguments.wig):
285 if (arguments.normalize):
286 with open(arguments.wig, "wb") as wigfile:
287 wigfile.write(wigstring)
288 else:
289 for list in results:
290 wigstring += str(list[0]) + " " + str(list[11]) + "\n"
291 with open(arguments.wig, "wb") as wigfile:
292 wigfile.write(wigstring)
293
294
295 # ___ ___ ___ ___ ___ ___ ___ ___
296 # /\__\ /\ \ /\__\ /\__\ /\ \ /\ \ /\ \ /\__\
297 # /:/ _/_ /::\ \ |::L__L /::L_L_ /::\ \ /::\ \ /::\ \ |::L__L
298 # /::-"\__\ /::\:\__\ |:::\__\ /:/L:\__\ /:/\:\__\ /:/\:\__\ /:/\:\__\ |:::\__\
299 # \;:;-",-" \/\::/ / /:;;/__/ \/_/:/ / \:\ \/__/ \:\ \/__/ \:\/:/ / /:;;/__/
300 # |:| | /:/ / \/__/ /:/ / \:\__\ \:\__\ \::/ / \/__/
301 # \|__| \/__/ \/__/ \/__/ \/__/ \/__/