diff --git a/.gitignore b/.gitignore
index 7a8baad3fbb9055363fc60eda6a2113c091f85f5..2a680d3b0a4bafbaa25ed4d8d76d524aafe15891 100644
--- a/.gitignore
+++ b/.gitignore
@@ -4,4 +4,9 @@
# ignore ALL files in ANY directory named temp
temp/
__pycache__
-output_files
\ No newline at end of file
+output_files
+*_cache
+*egg-info/
+.coverage
+build/
+*/play.py
\ No newline at end of file
diff --git a/README.md b/README.md
index fee84f77ae53f93f3ef3466c1261a323e7f336a4..75d56db07b37124880f302961414fd32aedcf86d 100644
--- a/README.md
+++ b/README.md
@@ -1,22 +1,50 @@
# Transcript Sampler
+## Overview
This workflow samples representative transcripts per gene, in proportion to their relative abundance levels. Sampling is done by Poisson sampling.
-**This workflow takes as input:**
- - Path to genome annotation file in gtf format
- - Integer of number of transcripts to sample
- - Path to csv or tsv file with transcript IDs and expression levels
- - Path to output sample gtf file
- - Path to output sample transcript IDs and counts
+This workflow takes as input:
+- Path to genome annotation file in gtf format
+- Path to csv or tsv file with transcript IDs and expression levels
+- Path to output sample gtf file
+- Path to output sample transcript IDs and counts
+- Integer of number of transcripts to sample
- **The outputs are :**
- - trancript sample gtf file
- - csv file containing sample transcript IDs and counts.
+The outputs are :
+- trancript sample gtf file
+- csv file containing sample transcript IDs and counts.
- **The workflow can be run via the command line as**
-
- `python transcript_sampler/new_exe.py --input_gtf={gtf input file} --input_csv={input csv file} --output_gtf={output gtf file} --output_csv={output csv file} --n_to_sample={number of transcripts}`
+## Installation from github
+Transcript sampler requires Python 3.9 or later.
+
+Install Transcript sampler from Github using:
+
+```
+git clone https://git.scicore.unibas.ch/zavolan_group/tools/transcript-sampler.git
+cd transcript-sampler
+pip install .
+```
+
+## Usage
+```
+usage: transcript-sampler [-h] --input_gtf INPUT_GTF --input_csv INPUT_CSV --output_gtf OUTPUT_GTF --output_csv OUTPUT_CSV --n_to_sample N_TO_SAMPLE
+
+Transcript sampler
+
+options:
+ -h, --help show this help message and exit
+ --input_gtf INPUT_GTF
+ GTF file with genome annotation (default: None)
+ --input_csv INPUT_CSV
+ CSV or TSV file with transcripts and their expression level (default: None)
+ --output_gtf OUTPUT_GTF
+ Output path for the new GTF file of representative transcripts (default: None)
+ --output_csv OUTPUT_CSV
+ Output path for the new CSV file of representative transcripts and their sampled number (default: None)
+ --n_to_sample N_TO_SAMPLE
+ Total number of transcripts to sample (default: None)
+```
- Example :
+Example :
- `python transcript_sampler/new_exe.py --input_gtf="input_files/test.gtf" --input_csv="input_files/expression.csv" --output_gtf="output_files/output.gtf" --output_csv="output_files/output.csv" --n_to_sample=100`
+`transcript_sampler --input_gtf="tests/input_files/test.gtf" --input_csv="tests/input_files/expression.csv" --output_gtf="output_files/output.gtf" --output_csv="output_files/output.csv" --n_to_sample=100`
diff --git a/requirements.txt b/requirements.txt
index 98d4d622197cba5a0b39ff5ffc87237dea9045f5..3fd96b317696344e9d5c3dcf7d66d92d45f05421 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -1,5 +1,6 @@
argparse
biopython
gtfparse
+polars == 0.16.17
numpy >= 1.23.3
pandas >= 1.4.4
\ No newline at end of file
diff --git a/setup.py b/setup.py
index 873c7b46c925f8abb195f35ed9a0b7af1117b5f9..9542e8a5d2e5e83f2e3f1ce44a26a9bfc796731e 100644
--- a/setup.py
+++ b/setup.py
@@ -18,5 +18,8 @@ setup(
author_email='mate.balajti@unibas.ch',
description='Transcript sampler',
packages=find_packages(),
- install_requires=INSTALL_REQUIRES
+ install_requires=INSTALL_REQUIRES,
+ entry_points={
+ 'console_scripts': ['transcript-sampler=transcript_sampler.cli:main']
+ }
)
diff --git a/input_files/expression.csv b/tests/input_files/expression.csv
similarity index 100%
rename from input_files/expression.csv
rename to tests/input_files/expression.csv
diff --git a/input_files/test.gtf b/tests/input_files/test.gtf
similarity index 100%
rename from input_files/test.gtf
rename to tests/input_files/test.gtf
diff --git a/transcript_sampler/__init__.py b/transcript_sampler/__init__.py
index 4572092b49877321a9bb2f4fc1483a63bbbd1aed..bb7d5f3186cb2e516714c06c9a5e8d2b57696586 100644
--- a/transcript_sampler/__init__.py
+++ b/transcript_sampler/__init__.py
@@ -1 +1 @@
-"""Init.py."""
+"""Initialise package."""
diff --git a/transcript_sampler/cli.py b/transcript_sampler/cli.py
new file mode 100644
index 0000000000000000000000000000000000000000..8b650422e98331948f550776373767617ac2a161
--- /dev/null
+++ b/transcript_sampler/cli.py
@@ -0,0 +1,82 @@
+"""This module executes the transcript_sampler."""
+import argparse
+import time
+import logging
+
+logging.basicConfig(
+ format='[%(asctime)s: %(levelname)s] %(message)s \
+ (module "%(module)s")',
+ level=logging.INFO,
+ )
+
+from transcript_sampler.find_reptrans import FindRepTrans # noqa: E402,E501 # pylint:disable=wrong-import-position
+from transcript_sampler.match_reptrans_explvl import MatchReptransExplvl # noqa: E402,E501 # pylint:disable=wrong-import-position
+from transcript_sampler.poisson_sampling import SampleTranscript # noqa: E402,E501 # pylint:disable=wrong-import-position
+
+find_rep_trans = FindRepTrans()
+match_reptrs_explvl = MatchReptransExplvl()
+poisson_sample = SampleTranscript()
+
+
+def main():
+ """Execute transcript sampler."""
+ parser = argparse.ArgumentParser(
+ description="Transcript sampler",
+ formatter_class=argparse.ArgumentDefaultsHelpFormatter,
+ )
+ parser.add_argument(
+ "--input_gtf", required=True, default=None,
+ help="GTF file with genome annotation"
+ )
+ parser.add_argument(
+ "--input_csv", required=True, default=None,
+ help="CSV or TSV file with transcripts and their expression level"
+ )
+ parser.add_argument(
+ "--output_gtf", required=True, default=None,
+ help="Output path for the new GTF file of representative transcripts"
+ )
+ parser.add_argument(
+ "--output_csv", required=True, default=None,
+ help="Output path for the new CSV file of representative transcripts \
+ and their sampled number"
+ )
+ parser.add_argument(
+ "--n_to_sample", required=True, default=None,
+ help="Total number of transcripts to sample"
+ )
+ args = parser.parse_args()
+
+ log = logging.getLogger("main")
+ start = time.time()
+ log.info("Started transcript sampler...")
+ dict_repr_trans = find_rep_trans.get_rep_trans(args.input_gtf)
+ df_repr = match_reptrs_explvl.match_repr_transcript_expression_level(
+ dict_reprTrans=dict_repr_trans,
+ exprTrans=args.input_csv,
+ gtf_file=args.input_gtf
+ )
+ log.info(
+ "Finding match between representative transcripts \
+ and expression level file"
+ )
+ log.info("Poisson sampling of transcripts")
+ poisson_sample.transcript_sampling(
+ args.n_to_sample, df_repr, args.output_csv)
+ log.info("Output CSV file ready")
+
+ log.info("Writing output GTF file")
+ find_rep_trans.gtf_file_writer(
+ args.input_gtf, dict_repr_trans, args.output_gtf)
+
+ end = time.time()
+ log.info("Script executed in %s sec", (end - start))
+
+
+if __name__ == "__main__":
+ logging.basicConfig(
+ format='[%(asctime)s: %(levelname)s] %(message)s \
+ (module "%(module)s")',
+ level=logging.INFO,
+ )
+ main()
diff --git a/images/.gitkeep b/transcript_sampler/images/.gitkeep
similarity index 100%
rename from images/.gitkeep
rename to transcript_sampler/images/.gitkeep
diff --git a/images/screenshot_git_tutorial_1_hGillet.png b/transcript_sampler/images/screenshot_git_tutorial_1_hGillet.png
similarity index 100%
rename from images/screenshot_git_tutorial_1_hGillet.png
rename to transcript_sampler/images/screenshot_git_tutorial_1_hGillet.png
diff --git a/images/screenshot_git_tutorial_2_hGillet.png b/transcript_sampler/images/screenshot_git_tutorial_2_hGillet.png
similarity index 100%
rename from images/screenshot_git_tutorial_2_hGillet.png
rename to transcript_sampler/images/screenshot_git_tutorial_2_hGillet.png
diff --git a/images/screenshot_markdown_tutorial_hGillet.png b/transcript_sampler/images/screenshot_markdown_tutorial_hGillet.png
similarity index 100%
rename from images/screenshot_markdown_tutorial_hGillet.png
rename to transcript_sampler/images/screenshot_markdown_tutorial_hGillet.png
diff --git a/transcript_sampler/new_exe.py b/transcript_sampler/new_exe.py
deleted file mode 100644
index d96f6136bf181b6c98078bb94a222893ab6e1ef5..0000000000000000000000000000000000000000
--- a/transcript_sampler/new_exe.py
+++ /dev/null
@@ -1,78 +0,0 @@
-"""This module executes the transcript_sampler"""
-import argparse
-import time
-import logging
-logging.basicConfig(
- format='[%(asctime)s: %(levelname)s] %(message)s (module "%(module)s")',
- level=logging.INFO,
- )
-from find_reptrans import FindRepTrans # pylint: disable=E0401,C0413
-from match_reptrans_explvl import MatchReptransExplvl # pylint: disable=E0401,C0413
-from poisson_sampling import SampleTranscript # pylint: disable=E0401,C0413
-
-find_rep_trans = FindRepTrans()
-match_reptrs_explvl = MatchReptransExplvl()
-poisson_sample = SampleTranscript()
-
-LOG = logging.getLogger(__name__)
-
-
-def exe(input_gtf, input_csv, output_gtf, output_csv, transcript_nr):
- """Execute transcript sampler."""
- start = time.time()
- LOG.info("Started transcript sampler...")
- dict_repr_trans = find_rep_trans.get_rep_trans(input_gtf)
- df_repr = match_reptrs_explvl.match_repr_transcript_expression_level(
- dict_reprTrans=dict_repr_trans, exprTrans=input_csv, gtf_file=input_gtf
- )
- LOG.info(
- "Finding match between representative transcripts \
- and expression level file"
- )
- LOG.info("Poisson sampling of transcripts")
- poisson_sample.transcript_sampling(transcript_nr, df_repr, output_csv)
- LOG.info("Output CSV file ready")
-
- LOG.info("Writing output GTF file")
- find_rep_trans.gtf_file_writer(input_gtf, dict_repr_trans, output_gtf)
-
- end = time.time()
- LOG.info("Script executed in %s sec", (end - start))
-
-
-if __name__ == "__main__":
- parser = argparse.ArgumentParser(
- description="Transcript sampler",
- formatter_class=argparse.ArgumentDefaultsHelpFormatter,
- )
- parser.add_argument(
- "--input_gtf", required=True,
- help="GTF file with genome annotation"
- )
- parser.add_argument(
- "--input_csv", required=True,
- help="CSV or TSV file with transcripts and their expression level"
- )
- parser.add_argument(
- "--output_gtf", required=True,
- help="Output path for the new GTF file of representative transcripts"
- )
- parser.add_argument(
- "--output_csv", required=True,
- help="Output path for the new CSV file of representative transcripts \
- and their sampled number"
- )
- parser.add_argument(
- "--n_to_sample", required=True,
- help="Total number of transcripts to sample"
- )
- args = parser.parse_args()
- print(args)
-
- exe(
- args.input_gtf,
- args.input_csv,
- args.output_gtf,
- args.output_csv,
- args.n_to_sample,
- )
diff --git a/scripts/exon_length_filter.py b/transcript_sampler/obsolete_scripts/exon_length_filter.py
similarity index 100%
rename from scripts/exon_length_filter.py
rename to transcript_sampler/obsolete_scripts/exon_length_filter.py
diff --git a/scripts/org_test_representative.py b/transcript_sampler/obsolete_scripts/org_test_representative.py
similarity index 100%
rename from scripts/org_test_representative.py
rename to transcript_sampler/obsolete_scripts/org_test_representative.py
diff --git a/scripts/representative.py b/transcript_sampler/obsolete_scripts/representative.py
similarity index 100%
rename from scripts/representative.py
rename to transcript_sampler/obsolete_scripts/representative.py
diff --git a/scripts/transcript_extractor.py b/transcript_sampler/obsolete_scripts/transcript_extractor.py
similarity index 100%
rename from scripts/transcript_extractor.py
rename to transcript_sampler/obsolete_scripts/transcript_extractor.py