[med-svn] [Git][med-team/pycoqc][upstream] New upstream version 2.5.0.23+dfsg
Nilesh Patra
gitlab at salsa.debian.org
Wed Aug 19 15:50:31 BST 2020
Nilesh Patra pushed to branch upstream at Debian Med / pycoqc
Commits:
ac4408fc by Nilesh Patra at 2020-08-19T20:14:09+05:30
New upstream version 2.5.0.23+dfsg
- - - - -
7 changed files:
- README.md
- docs/index.md
- meta.yaml
- pycoQC/Fast5_to_seq_summary.py
- pycoQC/__init__.py
- pycoQC/templates/spectre.html.j2
- setup.py
Changes:
=====================================
README.md
=====================================
@@ -8,9 +8,13 @@
[](https://badge.fury.io/py/pycoQC)
[](https://pepy.tech/project/pycoqc)
+
[](https://anaconda.org/aleg/pycoqc)
[](https://anaconda.org/aleg/pycoqc)
+[](http://bioconda.github.io/recipes/pycoqc/README.html)
+[](https://anaconda.org/bioconda/pycoqc)
+
[](https://travis-ci.com/a-slide/pycoQC)
[](https://www.codacy.com/app/a-slide/pycoQC?utm_source=github.com&utm_medium=referral&utm_content=a-slide/pycoQC&utm_campaign=Badge_Grade)
---
@@ -23,6 +27,8 @@
PycoQC relies on the *sequencing_summary.txt* file generated by Albacore and Guppy, but if needed it can also generates a summary file from basecalled fast5 files. The package supports 1D and 1D2 runs generated with Minion, Gridion and Promethion devices and basecalled with Albacore 1.2.1+ or Guppy 2.1.3+. PycoQC is written in pure Python3. **Python 2 is not supported**.
+Great tutorial with detailed explanations by [Tim Kahlke](https://github.com/timkahlke) available at https://timkahlke.github.io/LongRead_tutorials/QC_P.html
+
## Gallery
=====================================
docs/index.md
=====================================
@@ -6,6 +6,7 @@
PycoQC relies on the *sequencing_summary.txt* file generated by Albacore and Guppy, but if needed it can also generates a summary file from basecalled fast5 files. The package supports 1D and 1D2 runs generated with Minion, Gridion and Promethion devices and basecalled with Albacore 1.2.1+ or Guppy 2.1.3+. PycoQC is written in pure Python3. **Python 2 is not supported**.
+Great tutorial with detailed explanations by [Tim Kahlke](https://github.com/timkahlke) available at https://timkahlke.github.io/LongRead_tutorials/QC_P.html
## Gallery
=====================================
meta.yaml
=====================================
@@ -1,4 +1,4 @@
-{% set version = "2.5.0.21" %}
+{% set version = "2.5.0.23" %}
{% set name = "pycoQC" %}
package:
@@ -23,7 +23,7 @@ requirements:
- pip>=19.2.1
- ripgrep>=11.0.1
run:
- - python=3.6
+ - python>=3.6
- numpy=1.17.1
- scipy=1.3.1
- pandas=0.25.1
@@ -45,5 +45,9 @@ test:
about:
home: "https://github.com/a-slide/pycoQC"
- license: "GPLv3"
+ license: "GNU General Public v3 (GPLv3)"
+ license_file: LICENSE
+ license_family: GPL
summary: "PycoQC computes metrics and generates interactive QC plots for Oxford Nanopore technologies sequencing data"
+ doc_url: "https://a-slide.github.io/pycoQC/"
+ dev_url: ""
=====================================
pycoQC/Fast5_to_seq_summary.py
=====================================
@@ -197,54 +197,73 @@ class Fast5_to_seq_summary ():
for fast5_fn in iter(in_q.get, None):
- # Try to extract data from the fast5 file
- d = OrderedDict()
with h5py.File(fast5_fn, "r") as h5_fp:
- # Define group names for current read
- grp_dict = {
- "raw_read" : "/Raw/Reads/{}/".format(list(h5_fp["/Raw/Reads"].keys())[0]),
- "summary_basecall" : "/Analyses/Basecall_1D_{:03}/Summary/basecall_1d_template/".format(self.basecall_id),
- "summary_calibration" : "/Analyses/Calibration_Strand_Detection_{:03}/Summary/calibration_strand_template/".format(self.basecall_id),
- "summary_barcoding" : "/Analyses/Barcoding_{:03}/Summary/barcoding/".format(self.basecall_id),
- "tracking_id" : "UniqueGlobalKey/tracking_id",
- "channel_id" : "UniqueGlobalKey/channel_id"}
-
- # Fetch required fields is available
- for field in self.fields:
-
- # Special case for start time
- if field == "start_time":
- start_time = self._get_h5_attrs (fp=h5_fp,
- grp=grp_dict[self.attrs_grp_dict["start_time"]["grp"]],
- attrs=self.attrs_grp_dict["start_time"]["attrs"])
- sampling_rate = self._get_h5_attrs (fp=h5_fp,
- grp=grp_dict[self.attrs_grp_dict["channel_sampling_rate"]["grp"]],
- attrs=self.attrs_grp_dict["channel_sampling_rate"]["attrs"])
- if start_time and sampling_rate:
- d[field] = int(start_time/sampling_rate)
- c["fields_found"][field] +=1
- else:
- c["fields_not_found"][field] +=1
- # Everything else
- else:
- v = self._get_h5_attrs (
- fp=h5_fp, grp=grp_dict[self.attrs_grp_dict[field]["grp"]], attrs=self.attrs_grp_dict[field]["attrs"])
- if v:
- d[field] = v
- c["fields_found"][field] +=1
- else:
- c["fields_not_found"][field] +=1
+ multi_read = 'file_type' in h5_fp.attrs.keys() and h5_fp.attrs['file_type'] == b'multi-read'
+
+ if multi_read:
+ read_ids = list(h5_fp["/"].keys())
+ else:
+ read_ids = list(h5_fp["/Raw/Reads"].keys())
- if self.include_path:
- d["path"] = os.path.abspath(fast5_fn)
+ for read_id in read_ids:
+ # Try to extract data from the fast5 file
+ d = OrderedDict()
- # Put read data in queue
- if d:
- out_q.put(d)
- c["overall"]["valid files"] += 1
- else:
- c["overall"]["invalid files"] += 1
+ if multi_read:
+ grp_dict = {
+ "raw_read" : "/{}/Raw/".format(read_id),
+ "summary_basecall" : "/{read_id}/Analyses/Basecall_1D_{bc_id:03}/Summary/basecall_1d_template/".format(read_id=read_id, bc_id=self.basecall_id),
+ "summary_calibration" : "/{read_id}/Analyses/Calibration_Strand_Detection_{bc_id:03}/Summary/calibration_strand_template/".format(read_id=read_id, bc_id=self.basecall_id),
+ "summary_barcoding" : "/{read_id}/Analyses/Barcoding_{bc_id:03}/Summary/barcoding/".format(read_id=read_id, bc_id=self.basecall_id),
+ "tracking_id" : "/{}/tracking_id".format(read_id),
+ "channel_id" : "/{}/channel_id".format(read_id)}
+
+ else:
+ # Define group names for current read
+ grp_dict = {
+ "raw_read" : "/Raw/Reads/{}/".format(read_id),
+ "summary_basecall" : "/Analyses/Basecall_1D_{:03}/Summary/basecall_1d_template/".format(self.basecall_id),
+ "summary_calibration" : "/Analyses/Calibration_Strand_Detection_{:03}/Summary/calibration_strand_template/".format(self.basecall_id),
+ "summary_barcoding" : "/Analyses/Barcoding_{:03}/Summary/barcoding/".format(self.basecall_id),
+ "tracking_id" : "UniqueGlobalKey/tracking_id",
+ "channel_id" : "UniqueGlobalKey/channel_id"}
+
+ # Fetch required fields is available
+ for field in self.fields:
+
+ # Special case for start time
+ if field == "start_time":
+ start_time = self._get_h5_attrs (fp=h5_fp,
+ grp=grp_dict[self.attrs_grp_dict["start_time"]["grp"]],
+ attrs=self.attrs_grp_dict["start_time"]["attrs"])
+ sampling_rate = self._get_h5_attrs (fp=h5_fp,
+ grp=grp_dict[self.attrs_grp_dict["channel_sampling_rate"]["grp"]],
+ attrs=self.attrs_grp_dict["channel_sampling_rate"]["attrs"])
+ if start_time and sampling_rate:
+ d[field] = int(start_time/sampling_rate)
+ c["fields_found"][field] +=1
+ else:
+ c["fields_not_found"][field] +=1
+ # Everything else
+ else:
+ v = self._get_h5_attrs (
+ fp=h5_fp, grp=grp_dict[self.attrs_grp_dict[field]["grp"]], attrs=self.attrs_grp_dict[field]["attrs"])
+ if v:
+ d[field] = v
+ c["fields_found"][field] +=1
+ else:
+ c["fields_not_found"][field] +=1
+
+ if self.include_path:
+ d["path"] = os.path.abspath(fast5_fn)
+
+ # Put read data in queue
+ if d:
+ out_q.put(d)
+ c["overall"]["valid files"] += 1
+ else:
+ c["overall"]["invalid files"] += 1
# Put counter in counter queue
counter_q.put(c)
=====================================
pycoQC/__init__.py
=====================================
@@ -1,4 +1,4 @@
# -*- coding: utf-8 -*-
-__version__ = '2.5.0.21'
+__version__ = '2.5.0.23'
__all__ = ["pycoQC", "Fast5_to_seq_summary", "Barcode_split", "common"]
=====================================
pycoQC/templates/spectre.html.j2
=====================================
@@ -68,10 +68,6 @@
{{ src_files }}
</div>
</div>
-
- <!-- <div class="column col-12 col-mx-auto text-center">
- <h6>SHA256: {{ summary_file_hash }}</h6>
- </div> -->
</div>
</div>
</body>
=====================================
setup.py
=====================================
@@ -5,7 +5,7 @@ from setuptools import setup
# Define package info
name = "pycoQC"
-version = "2.5.0.21"
+version = "2.5.0.23"
description = "PycoQC computes metrics and generates interactive QC plots for Oxford Nanopore technologies sequencing data"
with open("README.md", "r") as fh:
long_description = fh.read()
View it on GitLab: https://salsa.debian.org/med-team/pycoqc/-/commit/ac4408fcf50d6bea2a6caa9267f7f0e4788c7bb3
--
View it on GitLab: https://salsa.debian.org/med-team/pycoqc/-/commit/ac4408fcf50d6bea2a6caa9267f7f0e4788c7bb3
You're receiving this email because of your account on salsa.debian.org.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://alioth-lists.debian.net/pipermail/debian-med-commit/attachments/20200819/5153b7df/attachment-0001.html>
More information about the debian-med-commit
mailing list