From df05b47ed3e8d9c3788fd02841165c422ccc83ff Mon Sep 17 00:00:00 2001
From: Mate Balajti <mate.balajti@unibas.ch>
Date: Mon, 18 Sep 2023 12:12:52 +0000
Subject: [PATCH] refactor: minor updates

---
 .gitlab-ci.yml     |   2 +-
 Dockerfile         |  18 -------
 frag_selec.nf      | 126 ---------------------------------------------
 setup.py           |   2 +-
 tests/test_frag.py |   4 +-
 5 files changed, 4 insertions(+), 148 deletions(-)
 delete mode 100644 Dockerfile
 delete mode 100644 frag_selec.nf

diff --git a/.gitlab-ci.yml b/.gitlab-ci.yml
index 0ab9bf0..0c14af8 100644
--- a/.gitlab-ci.yml
+++ b/.gitlab-ci.yml
@@ -31,4 +31,4 @@ lint-test-job:   # This job also runs in the test stage.
     - pip install -e .
     - flake8 --docstring-convention google term_frag_sel/ tests/
     - pylint term_frag_sel/ tests/
-    - mypy term_frag_sel/
+    - mypy term_frag_sel/ tests/
diff --git a/Dockerfile b/Dockerfile
deleted file mode 100644
index 4ca5d5f..0000000
--- a/Dockerfile
+++ /dev/null
@@ -1,18 +0,0 @@
-##### BASE #####
-FROM python:3.10-slim-buster
-
-##### VARIABLES #####
-WORKDIR /Users/terminal-fragment-selector/
-
-COPY requirements.txt /Users/terminal-fragment-selector/requirements.txt
-COPY requirements_dev.txt /Users/terminal-fragment-selector/requirements_dev.txt
-
-##### INSTALL #####
-RUN apt-get update \
-&& apt-get install gcc -y \
-&& apt-get clean
-RUN pip install -r requirements.txt -r requirements_dev.txt
-
-
-
-
diff --git a/frag_selec.nf b/frag_selec.nf
deleted file mode 100644
index 1fc9bdc..0000000
--- a/frag_selec.nf
+++ /dev/null
@@ -1,126 +0,0 @@
-#!/usr/bin/env nextflow
-
-nextflow.enable.dsl=2
-
-```c
-/*   
- * Define the input parameters"""Takes as input FASTA file
-                                     of cDNA sequences, a CSV/TSV with sequence
-                                     counts, and mean and std. dev. of fragment
-                                     lengths and 4 nucleotide probabilities
-                                     for the cuts. Outputs most terminal
-                                     fragment (within desired length range)
-                                     for each sequence."""
- */ 
-params.fasta_file = "$projectDir/tests/test_files/test,fasta"
-params.counts_file = "$projectDir/tests/test_files/test.csv"        
-params.sep = "$projectDir/data/yeast/sep/sep.csv"
-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 
-         ===================================       
-         fasta_file   : ${params.fasta_file}      
-         counts_file  : ${params.counts_file}             
-         outdir       : ${params.outdir}          
-         """                                        
-         .stripIndent() 
-         
-/* 
- * Define the `file_validation` process:
- * Validate input files exist and are the correct format
- */ 
-
-process file_validation { 
-
-    input:
-    path fasta_file
-    path counts_file
-    path sep 
-    
-    output:
-    tuple: fasta dict and sequence for counts file
-    
-    script: 
-    """
-    salmon index --threads $task.cpus -t $transcriptome -i index
-    """ 
-}    
-    
-
-/*
- * Define the get_cut_number process:
- * Get the number of cuts for a particular sequence 
- */
-
-process get_cut_number {
-
-    tag "get_cut_numbern on $n_cuts" 
-    publishDir "${params.outdir}/get_cut_number", mode:'copy' 
-    
-    input:
-    path index
-    tuple val(n_cuts), path(seq_len, mean)                                                                                   
-    
-    output:
-    path(n_cuts)
-    
-    script:
-    """
-      
-    """                                                      
-}
-
-
-/* 
- * Define the fragmentation process:
- * Fragment cDNA sequences and select terminal fragment 
- */
-
-process fragmentation {
-
-    tag "fragmentation on $fasta, seq_counts, nuc_probs, mu_length, std"
-    
-    input:
-    dict val(fasta), pd.DataFrame(seq_counts), dict(nuc_probs),int(mu_length),int(std)
-    
-    output:
-    path("term_frags")
-    
-    script:
-    """
-    mkdir fastqc_${sample_id}_logs
-    
-    """
-}
-
-
-
-/* Start the job:
- * initialize variables
- */
- 
-Channel
-    .fromFilePairs( params.reads, checkIfExists:true ) 
-    .set { read_pairs_ch }     
-
-
-/* The "main" function:
- * Use CLI arguments to fragment sequences and output text file with selected terminal fragments
- */
-
-workflow {
-  file_validation_ch=file_validation(params.fasta_file, params.counts_file, params.sep)
-  get_cut_number_ch = get_cut_number(seq_len, mean)
-  framentation_ch = fregmentation(fasta, seq_counts, nuc_probs, mu_length, std)                                                                           }                                                                                                                     
-
-
-/* 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") 
-   )
-}                                                                                                                     
-```
diff --git a/setup.py b/setup.py
index 3fe12de..469d786 100644
--- a/setup.py
+++ b/setup.py
@@ -1,6 +1,6 @@
 """Set up project."""
 from pathlib import Path
-from setuptools import setup, find_packages
+from setuptools import setup, find_packages  # type: ignore
 
 project_root_dir = Path(__file__).parent.resolve()
 with open(project_root_dir / "requirements.txt",
diff --git a/tests/test_frag.py b/tests/test_frag.py
index da2d5bb..90c0f94 100644
--- a/tests/test_frag.py
+++ b/tests/test_frag.py
@@ -1,7 +1,7 @@
 """Test utils.py functions."""
-import pandas as pd
+import pandas as pd  # type: ignore
 import pytest
-from Bio import SeqIO
+from Bio import SeqIO  # type: ignore
 
 from term_frag_sel.fragmentation import fragmentation
 
-- 
GitLab