feat: add cli

README.md

 # 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`

requirements.txt

 argparse
 biopython
 gtfparse
+polars == 0.16.17
 numpy >= 1.23.3
 pandas >= 1.4.4
\ No newline at end of file

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']
+        }
 )

transcript_sampler/cli.py

@@ -2,92 +2,81 @@
 import argparse
 import time
 import logging
-from find_reptrans import FindRepTrans
-from match_reptrans_explvl import MatchReptransExplvl
-from poisson_sampling import SampleTranscript
-
-find_rep_trans = FindRepTrans()
-match_reptrs_explvl = MatchReptransExplvl()
-poisson_sample = SampleTranscript()
 
 logging.basicConfig(
     format='[%(asctime)s: %(levelname)s] %(message)s \
         (module "%(module)s")',
     level=logging.INFO,
-)
-LOG = logging.getLogger("main")
-
-
-def main(args: argparse.Namespace):
-    """Execute transcript sampler."""
-    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.transcript_nr, 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))
+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 parse_arguments() -> argparse.Namespace:
-    """Request parameters from user on CLI.
 
-    Returns:
-        argparse.Namespace: object of arguments from CLI.
-    """
+def main():
+    """Execute transcript sampler."""
     parser = argparse.ArgumentParser(
         description="Transcript sampler",
         formatter_class=argparse.ArgumentDefaultsHelpFormatter,
     )
     parser.add_argument(
-        "--input_gtf", required=True,
+        "--input_gtf", required=True, default=None,
         help="GTF file with genome annotation"
         )
     parser.add_argument(
-        "--input_csv", required=True,
+        "--input_csv", required=True, default=None,
         help="CSV or TSV file with transcripts and their expression level"
         )
     parser.add_argument(
-        "--output_gtf", required=True,
+        "--output_gtf", required=True, default=None,
         help="Output path for the new GTF file of representative transcripts"
         )
     parser.add_argument(
-        "--output_csv", required=True,
+        "--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,
+        "--n_to_sample", required=True, default=None,
         help="Total number of transcripts to sample"
         )
     args = parser.parse_args()
 
-    return 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)
 
-if __name__ == '__main__':
+    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,
-    )
-    logger = logging.getLogger(__name__)
-
-    arguments = parse_arguments()
-    main(arguments)
+        )
+    main()