refactor: setup.py, CI

.gitlab-ci.yml

@@ -13,9 +13,8 @@ build-job:       # First stage deployment and installation of dependencies.
     - pip install -r requirements.txt
     - pip install -r requirements_dev.txt
     - pip install -e .
-    - echo "Dependencies successfully deployed."
 
-Coverage-test-job:   # Test Stage
+unit-test-job:   # Test Stage
   stage: test        # Starts when the above build stages finishes installing dependencies.
   script:
     - pip install -r requirements.txt
@@ -23,9 +22,8 @@ Coverage-test-job:   # Test Stage
     - pip install -e .
     - coverage run --source tsg -m pytest
     - coverage report -m
-    - echo "Coverage successfully deployed."
 
-Flake8/Pylint/mypy-test-job:   # Test Stage
+lint-test-job:   # Test Stage
   stage: test    # Deploys and runs all 3 linters.
   script:
     - pip install -r requirements.txt
@@ -34,4 +32,3 @@ Flake8/Pylint/mypy-test-job:   # Test Stage
     - flake8 --docstring-convention google tsg/ tests/
     - pylint tsg/ tests/
     - mypy tsg/ tests/
-    - echo "Linters successfully deployed."

Dockerfile

-FROM python:3.9-slim-buster
-
-WORKDIR /usr/src/app
-
-COPY README.md pyproject.toml ./
-ADD tsg ./tsg
-ADD data ./data
-
-RUN pip install .
-
-ENTRYPOINT [ "transcript-generator" ]
\ No newline at end of file

README.md

@@ -6,11 +6,11 @@ We hope that others would find use for this transcript_structure generator that
 
 # Installation
 
-To install the Python virtual environment, run
+To install package, run
 
 ```
-conda env create --file environment.yml
-conda activate transcript-structure-generator
+pip install "setuptools>=62.1.0"
+pip install .
 ```
 
 # Usage
@@ -27,45 +27,17 @@ Output:
 	- id of original transcript (without intron inclusions)
 	- count
 
-To install package, run
-
-```
-pip install "setuptools>=62.1.0"
-pip install .
-```
 
-To generate the sampled transcripts, open a new shell, activate your environment and run
+To generate the sampled transcripts, run
 
 ```
-conda activate transcript-structure-generator
-
-transcript-generator --prob-inclusion <probability_inclusion> [--log "INFO"] <transcripts_file> <annotations_file>
+transcript-structure-generator --prob-inclusion <probability_inclusion> [--log "INFO"] <transcripts_file> <annotations_file>
 ```
 
 where the transcripts file should be csv-formatted, the annotation file gtf-formatted and the inclusion probability for introns a float in the range [0,1]. The log parameter is optional and can be one of `["CRITICAL", "ERROR", "WARNING", "INFO", "DEBUG"]`. The default is `INFO`.
 
 Sample Transcripts and Annotation files can be found in the repository under main/tests/resources.
 
-# Development
-
-To perform all tests, make sure your environment corresponds to the `environment.yml` file and run
-
-```
-pytest tests
-```
-
-To build Docker image, run
-
-```
-docker build -t transcript-app .
-```
-
-Afterwards, you can use the Docker image like so
-
-```
-docker run transcript-app --prob_inclusion <probability_inclusion> [--log "INFO"] <transcripts_file> <annotations_file>
-```
-
 # License
 
 MIT license, Copyright (c) 2021 Zavolan Lab, Biozentrum, University of Basel

Trans_Struc_Gen.nf

-#!/usr/bin/env nextflow
-
-nextflow.enable.dsl=2
-
-```c
-/*   
- * Define the input parameters"""Takes input from csv-formatted file ("ID,Count") 
-                                     with counts for individual transcripts. 
-                                     Also a gtf-formatted file with exon coordinates 
-                                     of the transcripts included in the csv file. 
-                                     Outputs gtf-formatted file containing 
-                                     generated intron/exon structures per transcript.
-                                     Outputs csv-formatted file 
-                                     ("NewTranscriptID,ID,Count") with id of 
-                                     generated transcript, id of original 
-                                     transcript (without intron inclusions) and
-                                     Counts. 
- */ 
-params.cvs_file = "$projectDir/tests/ #Input cvs file from group 1
-params.gtf_file = "$projectDir/tests/ #Input gtf file from group 1       
-params.outdir = "results" 
-
-
-/* Log some information for the user */
-
-log.info """\
-         R N A S E Q - N F   P I P E L I N E 
-         ===================================       
-         cvs_file     : ${params.cvs_file}      
-         gtf_file     : ${params.gtf_file}             
-         outdir       : ${params.outdir}          
-         """                                        
-         .stripIndent() 
-         
-/* 
- * define the `file_validation` process
- * given that the input files exist and are the correct format
- */ 
-
-process file_validation { 
-
-    input:
-    path cvs_file
-    path gtf_file 
-    
-    output:
-    path cvs_file into struc_gen
-    path gtf_file into struc_gen
-    
-    script: 
-    """
-    
-    """ 
-}  
-
-/* 
- * Define the transcript structure generation
- * Read gtf files to define exons/introns and add random mutation coefficient. 
- */
-
-process struc_gen {
-    
-    input:
-    
-    
-    output:
-    
-    
-    script:
-    """
-    
-    
-    """
-}
-
-
-
-/* Start the job:
- * initialize variables
- */
- 
-Channel
-    .fromFilePairs( params.reads, checkIfExists:true ) 
-    .set { read_pairs_ch }     
-
-
-/* The "main" function:
- * Use CLI arguments to create structure sequences and output text file & gtf file with selected exon structures
- */
-
-workflow {
-  file_validation_ch = file_validation(params.cvs_file, params.gtf_file)
-  struc_gen_ch = struc_gen( # No idea yet)                                                                           }                                                                                                                     
-
-
-/* Book keeping upon workflow completion */
-workflow.onComplete {
-   log.info (workflow.success ? "\nDone! Open the following report in your browser -->     $params.outdir/multiqc/multiqc_report.html\n" : "Oops .. something went wrong") 
-   )
-}                                                                                                                     
-```

environment.yml

-name: transcript-structure-generator
-channels:
-  - defaults
-  - conda-forge
-dependencies:
-  - python=3.9
-  - matplotlib
-  - pandas
-  - pip
-  - tqdm
-  - flake8-docstrings
-  - mypy
-  - flake8
-  - pytest
-  - pylint
-  - coverage

pyproject.toml

-[project]
-name = "tsg"
-version = "0.2.0"
-authors = [
-  { name="Michael Zimmermann", email="michael.zimmermann@unibas.ch" },
-  { name="Andri Fraenkl", email="andri.fraenkl@unibas.ch" },
-  { name="Larissa Glass", email="larissa.glass@unibas.ch" },
-]
-description = "Transcript Structure Generator"
-readme = "README.md"
-requires-python = ">=3.7"
-license = {text = "MIT"}
-dependencies = [
-    "pandas",
-    "tqdm",
-]
-
-[tool.setuptools]
-packages = ["tsg"]
-
-[project.urls]
-"Homepage" = "https://git.scicore.unibas.ch/zavolan_group/tools/transcript-structure-generator"
-
-[project.scripts]
-transcript-generator = "tsg.cli:app"
\ No newline at end of file

tests/__init__.py

-"""Tests for the package tsg."""
+"""Initialise tests."""

tsg/__init__.py

 """Transcript structure generator package."""
 import importlib.metadata
-
 from tsg.main import Gtf, TranscriptGenerator, sample_transcripts
 
-__version__ = importlib.metadata.version("tsg")
+__version__ = importlib.metadata.version("transcript-structure-generator")
 __all__ = ["Gtf", "TranscriptGenerator", "sample_transcripts"]

tsg/main.py

@@ -308,6 +308,7 @@ class Gtf:
 class TranscriptGenerator:
     """Class to sample a transcript."""
 
+    # pylint: disable=W0613
     def __new__(
         cls,
         transcript_id: str,