File: json_output.py

package info (click to toggle)
qcumber 2.3.0-2
  • links: PTS, VCS
  • area: main
  • in suites: bullseye, sid
  • size: 2,276 kB
  • sloc: python: 3,097; sh: 153; makefile: 18
file content (385 lines) | stat: -rwxr-xr-x 16,057 bytes parent folder | download
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
#!/usr/bin/python3
import json
import re
import sys

from collections import OrderedDict
from io import StringIO
from matplotlib import pyplot as plt
from os.path import basename, getsize, join
from pandas import DataFrame, Series, read_csv, concat
from shutil import copyfile

def get_plot_type_names():
    return [x.replace(" ", "_") for x in get_store_data() if x not in get_skip_csv()]

def get_skip_csv():
    return ["Adapter Content", "Overrepresented sequences"]

def get_skip():
    return ["Basic Statistics", "Kmer Content", "Overrepresented sequences"]

def get_store_data():
    return ['Sequence Length Distribution', 'Per sequence quality scores', 'Per sequence GC content', 'Adapter Content', 'Overrepresented sequences']


# convert result type to color (adapted to color blindness)
def get_color(value):
    if (value == "pass"):
        return "green"
    elif (value == "fail"):
        return "red"
    else:
        return "orange"

def combine_csv(inputcsvs, data_path):
    files = dict()
    for plot_type in get_plot_type_names():
        files[plot_type] = open(data_path + "/" + plot_type + ".csv", "w")
    for csv in inputcsvs:
        f = open(csv, "r")
        s = f.read()
        f.close()
        for plot_type in get_plot_type_names():
            if plot_type in csv:
                files[plot_type].write(s)
                break
    for plot_type in get_plot_type_names():
        files[plot_type].close()


# creates CSV used for boxplotting
def createCSV(name, data, plot_type, path, trimmed, paired_end=True):
    df = read_csv(StringIO("".join(data)), sep="\t")
    name_groups = re.search(r"(?P<samplename>.*)_(?P<read>(R1|R2)).*", name)
#    if exists(filename):
#        summary = read_csv (filename, header = None, sep = ",")
#    else:
#        summary = DataFrame()
    summary = DataFrame()

    if plot_type == "Sequence Length Distribution":
        try:
            df["#Length"] = DataFrame(df["#Length"].str.split("-", expand=True), dtype=int).mean(axis=1)
        except:
            # Length is already of type int
            pass
    samplename = "NA"
    if name_groups and paired_end:
        samplename = name_groups.group("samplename")
        df = concat([ Series([name_groups.group("samplename")]* len(df.index), name = "Sample") ,
                      Series([trimmed ]* len(df.index), name="Trimmed"),
                      Series([name_groups.group("read") ]* len(df.index), name="Read"),
                      df ],axis =1)
    else:
        samplename = name
        df = concat([Series([name] * len(df.index), name="Sample"),
                     Series([trimmed] * len(df.index), name="type"),
                     Series([""] * len(df.index), name="read"),
                     df],axis=1)
    if len(summary) !=0:
        summary.columns = df.columns

    filename = path + '/' + samplename + "_" + plot_type.replace(" ", "_") + ".csv"
    summary = concat([summary, df], axis=0, ignore_index = True)
    summary_path = open(filename, 'a')
    summary.to_csv(summary_path, header = False, index = False)
    summary_path.close()




def get_fastqc_results(parameter, fastqc_path, outdir, type, to_base64,
                       paired_end=True):
    """
    Parses trimmomatics Sample(ID)_fastqc_data.txt files

    While parsing fastqc_data records are transcribed into a csv file

        Returns:
            fastq_results (obj::`dict`):
                Key (obj::`str`): Basename of File without "_fastqc"
                Value (obj::`dict`): Statistics
                    Key (obj::`str`): Name of stat
                    Value: value
            (int): number of sequences
            (double): Percentage of overrepresented sequences
    """
    skip = get_skip()
    store_data = get_store_data()
    total_seq = 0
    overrepr_count = 0
    adapter_content = []

    fastqc_results = OrderedDict()
    data = []
    store = False

    for fastqc in fastqc_path:
        sample = OrderedDict()
        name = basename(fastqc).replace("_fastqc","")
        sample["img"]= OrderedDict()
        if getsize(fastqc) != 0:
            with open(join(fastqc, "fastqc_data.txt"), "r") as fastqc_data:
                for line in iter(fastqc_data):
                    if line.startswith("Total Sequences"):
                        sample["Total Sequences"] = int(line.strip().split("\t"
                                                                     )[-1])
                        total_seq += int(line.strip().split("\t")[-1])
                    elif line.startswith('>>END_MODULE'):
                        if len(data) > 0:
                            if key[0] in store_data:
                                if key[0] == 'Adapter Content':
                                    ac = max(read_csv(StringIO("".join(data)),
                                                      sep="\t", index_col=0
                                             ).max().round(2))
                                    adapter_content.append(ac)
                                    sample["%Adapter content"] = ac

                                elif key[0] == "Overrepresented sequences":
                                    ors= read_csv(StringIO("".join(data)),
                                                  sep="\t")["Count"].sum()
                                    overrepr_count += ors
                                    sample["%Overrepr sequences"] =int(ors)
                                else:
                                    createCSV(name, data, key[0],
                                              outdir, type,
                                              paired_end=paired_end)
                            data = []
                            store = False
                    elif line.startswith('>>'):
                        key = line.split("\t")
                        key[0] = key[0].replace(">>", "")
                        if key[0] in store_data:
                            store = True
                        if not key[0] in skip:
                            img = {}
                            img["color"] = get_color(key[1].replace("\n",""))
                            try:
                                img["base64" ] = to_base64(
                                    join(fastqc, "Images",
                                         parameter["FastQC"][key[0]]))
                                img["path"] = join(fastqc, "Images",
                                                   parameter["FastQC"][key[0]])
                                sample["img"][key[0]] =  img
                            except Exception as exp:
                                print(exp)
                                pass #img["base64"] = ""

                    if store and not line.startswith(">>"):
                        data.extend([line])
            fastqc_results[name] = sample
    try:
        adapter = round(sum(adapter_content)/len(adapter_content) ,2)
    except:
        adapter = 0
    if total_seq == 0:
        overrepr = 0
    else:
        overrepr = round(100*overrepr_count / total_seq ,2)
    #print(fastqc_results)
    return  fastqc_results, int(total_seq), overrepr , adapter


def write_sample_json(outfilename, samplename, snakeinput, cmd_input):
# Fastqc_dict is historical, omitted from output for now, but still present in call to
# maintain tuple unpacking order
    fastqc_dict, total_seq ,overrepr_perc, adapter_content = (
        get_fastqc_results(
            (x for x in snakeinput.raw_fastqc if x[-4:] != ".txt" ),
            data_path , "raw" ))
    res = dict()
    res["Sample"] = dict()
    res["Sample"]["Name"] = samplename
    res["Sample"]["TS"] = total_seq
    res["Sample"]["PAC"] = adapter_content
    res["Sample"]["PORS"] = overrepr_perc
    res["Sample"]["POST"] = "N/A"
    res["Sample"]["PACT"] = "N/A"
    res["Sample"]["NRR"] = "N/A"
    res["Sample"]["PRR"] = "N/A"
    res["Sample"]["NAR"] = "N/A"
    res["Sample"]["PAR"] = "N/A"
    res["Sample"]["NC"] = "N/A"
    res["Sample"]["PC"] = "N/A"


    if not cmd_input["notrimming"]:
        fastqc_dict, total_seq, overrepr_perc, adapter_content = (
            get_fastqc_results(input.trimming_fastqc, data_path,"trimmed"))
        trimmomatic_results = get_trimmomatic_result(list(snakeinput.trimming), list(snakeinput.trimming_params))

        res["Sample"]["POST"] = overrepr_perc
        res["Sample"]["PACT"] = adapter_content
        res["Sample"]["NRR"] = trimmomatic_results["#Remaining Reads"]
        res["Sample"]["PRR"] = trimmomatic_results["%Remaining Reads"]
    if not cmd_input["nomapping"]:
        mapping_results = get_bowtie2_result(str(snakeinput.mapping))
        res["Sample"]["NAR"] = mapping_result["#AlignedReads"]
        res["Sample"]["PAR"] = mapping_result["%AlignedReads"]
    if not cmd_input["nokraken"]:
        kraken_results = get_kraken_result(str(snakeinput.kraken), str(snakeoutput.kraken_plot))
        res["Sample"]["NC"] = kraken_results["#Classified"]
        res["Sample"]["PC"] = kraken_results["%Classified"]
    json.dump(res, open(outfilename, "w"))

def write_summary_json_new(output, sample_json):
    res = dict()
    res["Headers"] = dict()
    res["Headers"]["Name"] = "Sample name"
    res["Headers"]["TS"] = "Total sequences"
    res["Headers"]["PAC"] = "% Adapter content"
    res["Headers"]["PORS"] = "% Overrepresented sequences"
    res["Headers"]["POST"] = "% Overrepresented sequences (trimmed)"
    res["Headers"]["PACT"] = "% Adapter content (trimmed)"
    res["Headers"]["NRR"] = "# Remaining reads"
    res["Headers"]["PRR"] = "% Remaining reads"
    res["Headers"]["NAR"] = "# Aligned reads"
    res["Headers"]["PAR"] = "% Aligned reads"
    res["Headers"]["NC"] = "# Classified"
    res["Headers"]["PC"] = "% Classified"
    res["Samples"] = []
    for sample in list(sample_json):
        res["Samples"] += [json.load(open(str(sample)))["Sample"]]
    json.dump(res, open(str(output.summary_json_new), "w"))


def write_summary_json(output, cmd_input, ruleinput, fastqc_csv, config, boxplots, shell, get_name, to_base64):
    summary = OrderedDict()
    summary["summary_img"] = {}

    for infile, outfile in zip(fastqc_csv, list(output.fastqc_plots)):
        shell("Rscript --vanilla {path}/Rscripts/boxplot.R" +
              " {input} {output} '{title}' '{xlab}' '{ylab}'",
              path = config["QCumber_path"],
              input = infile,
              output = outfile,
              title = boxplots[get_name(infile)]["title"],
              xlab = boxplots[get_name(infile)]["xlab"],
              ylab = boxplots[get_name(infile)]["ylab"])
        summary["summary_img"][ boxplots[get_name(infile)]["title"]] = (
            to_base64(outfile))

    if not cmd_input["nomapping"]:
        insertsizes = []
        samplenames = []
        notzero = 0
        for infile in ruleinput["insertsize"]:
            f = open(infile, "r")
            data = [int(x) for x in f.read().split(",")]
            notzero += len([x for x in data if x != 0])
            f.close()
            insertsizes += [data]
            samplenames += [get_name(infile).replace("_insertsizes", "")]
        if notzero == 0:
            insertsizes = [[0, 0, 0, 0, 0] for x in ruleinput["insertsize"]]
        boxplt = plt.boxplot(insertsizes, 0, '', patch_artist=True)
        for patch in boxplt['boxes']:
            patch.set_facecolor('#E25845')
        plt.xticks([x+1 for x in range(len(ruleinput["insertsize"]))], samplenames, rotation="vertical")
        try:
            plt.tight_layout()  # This breaks when sample names are to large.
            #                     It raises a value error: bottom cannot be
            #                     larger than top in matplotlib 2.1.x
            #                     Might get fixed in 2.2.x
        except ValueError:
            print("Warning: (%s:matplotlib) Some labels to "
                  "long for tight_layout plot" % __file__, file=sys.stderr)
        plt.title("Fragment lengths")
        plt.savefig(str(output.insertsize_plot), bbox_inches='tight')
        summary["summary_img"]["Insertsize"] = to_base64(output.insertsize_plot)
        plt.clf()

    summary["Results"] = []
    batch_plot = DataFrame()
    for sample in sorted(list(ruleinput.sample_json)):
        sample_dict = json.load(open(str(sample),"r"),
                                object_pairs_hook=OrderedDict)
        summary["Results"].append(sample_dict )
        df = DataFrame.from_dict(
            dict((key, val) for key, val
                 in sample_dict.items()
                 if key in ["Total sequences", "#Remaining Reads",
                            "%Classified","%AlignedReads",
                            "%Adapter content",
                            "%Adapter content (trimmed)",
                            "%Overrepr sequences",
                            "%Overrepr sequences (trimmed)"]
            ),
            orient="index").T
        df.index=[sample_dict["Name"]]
        batch_plot=batch_plot.append(df)


    if not cmd_input["notrimming"]:
        batch_plot["Total sequences"] = (batch_plot["Total sequences"] -
                                         batch_plot["#Remaining Reads"])
        batch_plot[["#Remaining Reads","Total sequences"]].plot.bar(
            stacked=True, edgecolor='black',
            title="Number of Reads", alpha=0.9)
    else:
        batch_plot["Total sequences"].plot.bar(
            stacked=True, edgecolor='black',
            title="Number of Reads", alpha=0.9)

    legend = plt.legend(bbox_to_anchor=(1.05, 1), loc=2, borderaxespad=0.)
    plt.savefig(str(output.n_read_plot),
                bbox_extra_artists=(legend,), bbox_inches='tight')
    plt.close()

    summary["summary_img"]["n_read"] = to_base64(str(output.n_read_plot))
    try:
        if not cmd_input["notrimming"]:
            batch_plot[
                    ["%Adapter content",
                     "%Adapter content (trimmed)"]
                ].plot.bar(edgecolor='black',
                           title = "Adapter content [%]",alpha=0.9)
        else:
            batch_plot["%Adapter content"].plot.bar(
                edgecolor='black',title="Adapter content [%]", alpha=0.9)
        legend = plt.legend(bbox_to_anchor=(1.05, 1),
                            loc=2, borderaxespad=0.)
        plt.savefig("QCResults/_data/adapter.png" ,
                    bbox_extra_artists=(legend,),bbox_inches='tight')
        plt.close()

        summary["summary_img"]["adapter"] = to_base64(data_path +
                                                      "/adapter.png")
    except:
        pass
    try:
        if not cmd_input["notrimming"]:
            batch_plot[
                    ["%Overrepr sequences",
                     "%Overrepr sequences (trimmed)"]
                ].plot.bar(edgecolor='black',
                           title="Overrepresented sequences [%]",
                           alpha=0.9)
        else:
            batch_plot["%Overrepr sequences"].plot.bar(
                edgecolor='black', title="Overrepresented sequences [%]",
                alpha=0.9)
        legend = plt.legend(bbox_to_anchor=(1.05, 1),
                            loc=2, borderaxespad=0.)
        plt.savefig("QCResults/_data/overrepr_seq.png",
                    bbox_extra_artists=(legend,), bbox_inches='tight')
        plt.close()
        summary["summary_img"]["overrepr_seq"] = to_base64(
            data_path + "/overrepr_seq.png")
    except:
        pass

    if not cmd_input["nomapping"]:
        batch_plot["%AlignedReads"].plot.bar(
            edgecolor='black', title = "Map to Reference [%]",alpha=0.9)
        plt.savefig(str(output.mapping_plot),  bbox_inches='tight')
        summary["summary_img"]["mapping"] = to_base64(
            str(output.mapping_plot))
        plt.close()


    if not cmd_input["nokraken"]:
        summary["summary_img"]["kraken"] = to_base64(ruleinput.kraken_batch)

    json.dump(summary, open(str(output.summary_json), "w"))