toulligqc 2.5.3__tar.gz → 2.5.5__tar.gz

{toulligqc-2.5.3 → toulligqc-2.5.5}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: toulligqc
-Version: 2.5.3
+Version: 2.5.5
 Summary: A post sequencing QC tool for Oxford Nanopore sequencers
 Home-page: https://github.com/GenomicParisCentre/toulligQC
 Author: Genomic Paris Centre team

{toulligqc-2.5.3 → toulligqc-2.5.5}/toulligqc/bam_extractor.py

@@ -231,8 +231,10 @@ class uBAM_Extractor:
         """
         #def process_bam_chunk(bam_chunk):
         rec_data = []
+        record_count = 0
         for rec in uBAM_chunk:
-            rec_dict = self._process_record(rec)
+            record_count += 1
+            rec_dict = self._process_record(rec, record_count)
             rec_data.append(rec_dict)
         return rec_data
 
@@ -258,35 +260,43 @@ class uBAM_Extractor:
 
 
     def _get_header(self):
-        samfile = pysam.AlignmentFile(self.ubam[0], "rb", check_sq=False)
-        header = samfile.header.to_dict()
-        run_id, model_version_id =  extract_headerTag(header,'RG','ID').split('_', 1)
+        sam_file = pysam.AlignmentFile(self.ubam[0], "rb", check_sq=False)
+        header = sam_file.header.to_dict()
+        run_id, model_version_id = extract_headerTag(header, 'RG','ID',
+                                                     'Unknown_Unknown').split('_', 1)
         self.header = {
-        "run_id" : run_id,
-        "run_date" : extract_headerTag(header, 'RG', 'DT'),
-        "sample_id" : extract_headerTag(header,'RG','SM'),
-        "basecaller" : extract_headerTag(header,'PG','PN'),
-        "basecaller_version" : extract_headerTag(header,'PG','VN'),
-        "model_version_id" : model_version_id,
-        "flow_cell_id" : extract_headerTag(header,'RG','PU')
+            "run_id": run_id,
+            "run_date": extract_headerTag(header, 'RG', 'DT', 'Unknown'),
+            "sample_id": extract_headerTag(header, 'RG', 'SM', 'Unknown'),
+            "basecaller": extract_headerTag(header, 'PG', 'PN', 'Unknown'),
+            "basecaller_version": extract_headerTag(header, 'PG', 'VN', 'Unknown'),
+            "model_version_id": model_version_id,
+            "flow_cell_id": extract_headerTag(header, 'RG', 'PU', 'Unknown')
         }
 
 
-    def _process_record(self, rec):
+    def _process_record(self, rec, record_count):
         """
         extract QC info from BAM record
         return : dict of QC info
         """
-        tags = rec.split("\t")
-        iso_start_time = tags[17].split(':',2)[2]
-        qual = avg_qual(tags[10])
+        fields = rec.split("\t")
+
+        # Parse optional fields
+        attributes = {}
+        for t in fields[11:]:
+            k, t, v = t.split(':', 2)
+            attributes[k] = v
+
+        iso_start_time = attributes.get('st', None)
+        qual = avg_qual(fields[10])
         passes_filtering = True if qual > self.threshold_Qscore else False
         data = [
-            len(tags[9]), # read length
+            len(fields[9]), # read length
             qual, # AVG Qscore
             passes_filtering, # Passing filter
-            timeISO_to_float(iso_start_time, '%Y-%m-%dT%H:%M:%S.%f%z'), # start time
-            tags[16].split(':',2)[2], # Channel
-            tags[12].split(':',2)[2] # Duration
+            float(record_count) if iso_start_time is None else timeISO_to_float(iso_start_time, '%Y-%m-%dT%H:%M:%S.%f%z'), # start time
+            attributes.get('ch', '1'),  # Channel
+            attributes.get('du', '1')  # Duration
         ]
-        return data
+        return data

{toulligqc-2.5.3 → toulligqc-2.5.5}/toulligqc/fastq_bam_common.py

@@ -2,8 +2,23 @@ import multiprocessing as mp
 from tqdm import tqdm
 from concurrent.futures import ProcessPoolExecutor, as_completed
 
-def extract_headerTag(header, tagGroup, tag):
-        return header[tagGroup][0][tag]
+def extract_headerTag(header, tagGroup, tag, defaultValue = None):
+
+    if tagGroup not in header:
+        if defaultValue is not None:
+            return defaultValue
+        else:
+            raise KeyError(tagGroup)
+
+    first_entry = header[tagGroup][0]
+
+    if tag not in first_entry:
+        if defaultValue is not None:
+            return defaultValue
+        else:
+            raise KeyError(tag)
+
+    return first_entry[tag]
 
 
 def batch_iterator(iterator, batch_size):

{toulligqc-2.5.3 → toulligqc-2.5.5}/toulligqc/plotly_graph_common.py

@@ -22,6 +22,7 @@
 
 from collections import defaultdict
 
+import pkgutil
 import numpy as np
 import pandas as pd
 import plotly.graph_objs as go
@@ -301,6 +302,10 @@ def _transparent_component(c, b, a):
         return '0' + r
     return r
 
+def _copy_latest_minjs(result_directory, js_file):
+    with open(result_directory + '/' + js_file , 'w+') as f:
+        plotly_min_js = pkgutil.get_data(__name__, "resources/plotly-latest.min.js").decode('utf8')
+        f.write(plotly_min_js) 
 
 def _create_and_save_div(fig, result_directory, main):
     div = py.plot(fig,
@@ -311,11 +316,13 @@ def _create_and_save_div(fig, result_directory, main):
 
     if result_directory is not None:
         output_file = result_directory + '/' + '_'.join(main.split())
+        js_file="plotly.min.js"
         py.plot(fig,
                 filename=output_file,
                 output_type="file",
-                include_plotlyjs="directory",
+                include_plotlyjs= js_file, 
                 auto_open=False)
+        _copy_latest_minjs(result_directory, js_file)
     else:
         output_file = None
 
@@ -622,9 +629,9 @@ def _pie_chart_graph(graph_name, count_sorted, color_palette, one_d_square, resu
                         method="update"
                     ),
                     dict(
-                        args=[{'visible': [False, False, False, True]},
+                        args=[{'visible': [False, False, True, False]},
                               {**_xaxis('Barcodes', dict(visible=True)),
-                               **_yaxis('Base count', dict(visible=True)),
+                               **_yaxis('Read count', dict(visible=True)),
                                'plot_bgcolor': plotly_background_color}],
                         label="Reads Histogram",
                         method="update"
@@ -638,9 +645,9 @@ def _pie_chart_graph(graph_name, count_sorted, color_palette, one_d_square, resu
                         method="update"
                     ),
                     dict(
-                        args=[{'visible': [False, False, True, False]},
+                        args=[{'visible': [False, False, False, True]},
                               {**_xaxis('Barcodes', dict(visible=True)),
-                               **_yaxis('Read count', dict(visible=True)),
+                               **_yaxis('Base count', dict(visible=True)),
                                'plot_bgcolor': plotly_background_color}],
                         label="Bases Histogram",
                         method="update"

toulligqc-2.5.5/toulligqc/version.py

@@ -0,0 +1 @@
+__version__ = '2.5.5'

{toulligqc-2.5.3 → toulligqc-2.5.5}/toulligqc.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: toulligqc
-Version: 2.5.3
+Version: 2.5.5
 Summary: A post sequencing QC tool for Oxford Nanopore sequencers
 Home-page: https://github.com/GenomicParisCentre/toulligQC
 Author: Genomic Paris Centre team

toulligqc-2.5.3/toulligqc/version.py

@@ -1 +0,0 @@
-__version__ = '2.5.3'