toulligqc 2.5.2__tar.gz → 2.5.4__tar.gz

{toulligqc-2.5.2 → toulligqc-2.5.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: toulligqc
-Version: 2.5.2
+Version: 2.5.4
 Summary: A post sequencing QC tool for Oxford Nanopore sequencers
 Home-page: https://github.com/GenomicParisCentre/toulligQC
 Author: Genomic Paris Centre team
@@ -15,8 +15,8 @@ Classifier: Intended Audience :: Science/Research
 Classifier: Topic :: Scientific/Engineering :: Bio-Informatics
 Classifier: License :: OSI Approved :: GNU General Public License v3 (GPLv3)
 Classifier: License :: OSI Approved :: CEA CNRS Inria Logiciel Libre License, version 2.1 (CeCILL-2.1)
-Classifier: Programming Language :: Python :: 3.8
-Requires-Python: >=3.8.0
+Classifier: Programming Language :: Python :: 3.11
+Requires-Python: >=3.11.0
 License-File: LICENSE-CeCILL.txt
 License-File: LICENSE.txt
 License-File: AUTHORS

{toulligqc-2.5.2 → toulligqc-2.5.4}/setup.py

@@ -34,7 +34,7 @@ setup(
         'License :: OSI Approved :: GNU General Public License v3 (GPLv3)',
         'License :: OSI Approved :: CEA CNRS Inria Logiciel Libre License, version 2.1 (CeCILL-2.1)',
 
-        'Programming Language :: Python :: 3.8'
+        'Programming Language :: Python :: 3.11'
     ],
 
     keywords='Nanopore MinION QC report',
@@ -45,9 +45,10 @@ setup(
     zip_safe=False,
     include_package_data=True,
 
-    python_requires='>=3.8.0',
-    install_requires=['matplotlib>=3.1.2', 'plotly>=4.5.0', 'h5py>=2.10',
-                      'pandas>=0.25.3', 'numpy>=1.17.4', 'scipy>=1.3.3', 'scikit-learn>=0.22'],
+    python_requires='>=3.11.0',
+    install_requires=['matplotlib>=3.6.3',   'plotly>=5.15.0', 'h5py>=3.7.0',
+                      'pandas>=1.5.3',       'numpy>=1.24.2',  'scipy>=1.10.1',
+                      'scikit-learn>=1.2.1', 'tqdm>=4.64.1',   'pysam>=0.21.0'],
 
     entry_points={
         'console_scripts': [

{toulligqc-2.5.2 → toulligqc-2.5.4}/test/test_sequencing_summary_extractor.py

@@ -6,6 +6,7 @@ from unittest.mock import patch, Mock, MagicMock
 import config as cfg
 import pandas as pd
 import pandas.util.testing as testing
+from toulligqc.common import is_numpy_1_24
 import numpy as np
 from distutils import util
 
@@ -65,7 +66,7 @@ class TestSequencingSummaryExtractorWholeConfig (unittest.TestCase):
         cls.expected_df = cls.expected_df.astype({
             'channel': np.int16,
             'start_time': np.float,
-            'passes_filtering': np.bool,
+            'passes_filtering': np.bool_ if is_numpy_1_24 else np.bool,
             'sequence_length': np.uint32,
             'mean_qscore_template': np.float,
             'duration': np.float,

{toulligqc-2.5.2 → toulligqc-2.5.4}/toulligqc/bam_extractor.py

@@ -18,6 +18,7 @@ from toulligqc.extractor_common import timeISO_to_float
 from toulligqc.common_statistics import compute_NXX, compute_LXX, occupancy_channel, avg_qual
 from toulligqc.fastq_bam_common import multiprocessing_submit, extract_headerTag
 from toulligqc.fastq_bam_common import batch_iterator
+from toulligqc.common import is_numpy_1_24
 from toulligqc import plotly_graph_generator as pgg
 
 
@@ -215,7 +216,7 @@ class uBAM_Extractor:
 
         uBAM_data['sequence_length'] = uBAM_data['sequence_length'].astype(np.uint32)
         uBAM_data['mean_qscore'] = uBAM_data['mean_qscore'].astype(np.float32)
-        uBAM_data['passes_filtering'] = uBAM_data['passes_filtering'].astype(np.bool)
+        uBAM_data['passes_filtering'] = uBAM_data['passes_filtering'].astype(np.bool_ if is_numpy_1_24 else np.bool)
         uBAM_data["start_time"] = uBAM_data["start_time"] - uBAM_data["start_time"].min()
         uBAM_data['channel'] = uBAM_data['channel'].astype(np.int16)
         uBAM_data['start_time'] = uBAM_data['start_time'].astype(np.float64)
@@ -230,8 +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
 
@@ -257,35 +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-2.5.2 → toulligqc-2.5.4}/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-2.5.2 → toulligqc-2.5.4}/toulligqc/fastq_extractor.py

@@ -16,6 +16,7 @@ from toulligqc.extractor_common import set_result_dict_telemetry_value
 from toulligqc.extractor_common import timeISO_to_float
 from toulligqc.common_statistics import compute_NXX, compute_LXX, occupancy_channel, avg_qual
 from toulligqc.fastq_bam_common import multiprocessing_submit
+from toulligqc.common import is_numpy_1_24
 from toulligqc import plotly_graph_generator as pgg
 
 
@@ -226,7 +227,7 @@ class fastqExtractor:
 
         fq_data['sequence_length'] = fq_data['sequence_length'].astype(np.uint32)
         fq_data['mean_qscore'] = fq_data['mean_qscore'].astype(np.float32)
-        fq_data['passes_filtering'] = fq_data['passes_filtering'].astype(np.bool)
+        fq_data['passes_filtering'] = fq_data['passes_filtering'].astype(np.bool_ if is_numpy_1_24 else np.bool)
 
         if self.rich:
             fq_data["start_time"] = fq_data["start_time"] - fq_data["start_time"].min()

toulligqc-2.5.4/toulligqc/version.py

@@ -0,0 +1 @@
+__version__ = '2.5.4'

{toulligqc-2.5.2 → toulligqc-2.5.4}/toulligqc.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: toulligqc
-Version: 2.5.2
+Version: 2.5.4
 Summary: A post sequencing QC tool for Oxford Nanopore sequencers
 Home-page: https://github.com/GenomicParisCentre/toulligQC
 Author: Genomic Paris Centre team
@@ -15,8 +15,8 @@ Classifier: Intended Audience :: Science/Research
 Classifier: Topic :: Scientific/Engineering :: Bio-Informatics
 Classifier: License :: OSI Approved :: GNU General Public License v3 (GPLv3)
 Classifier: License :: OSI Approved :: CEA CNRS Inria Logiciel Libre License, version 2.1 (CeCILL-2.1)
-Classifier: Programming Language :: Python :: 3.8
-Requires-Python: >=3.8.0
+Classifier: Programming Language :: Python :: 3.11
+Requires-Python: >=3.11.0
 License-File: LICENSE-CeCILL.txt
 License-File: LICENSE.txt
 License-File: AUTHORS

toulligqc-2.5.4/toulligqc.egg-info/requires.txt

@@ -0,0 +1,9 @@
+h5py>=3.7.0
+matplotlib>=3.6.3
+numpy>=1.24.2
+pandas>=1.5.3
+plotly>=5.15.0
+pysam>=0.21.0
+scikit-learn>=1.2.1
+scipy>=1.10.1
+tqdm>=4.64.1

toulligqc-2.5.2/toulligqc/version.py

@@ -1 +0,0 @@
-__version__ = '2.5.2'

toulligqc-2.5.2/toulligqc.egg-info/requires.txt

@@ -1,7 +0,0 @@
-h5py>=2.10
-matplotlib>=3.1.2
-numpy>=1.17.4
-pandas>=0.25.3
-plotly>=4.5.0
-scikit-learn>=0.22
-scipy>=1.3.3