From b8d858bb1c5cbb748f4c74b424a49c343ab3d5e2 Mon Sep 17 00:00:00 2001 From: balajtimate <51365402+balajtimate@users.noreply.github.com> Date: Wed, 18 Oct 2023 16:00:06 +0200 Subject: [PATCH] Remove gtf header (#13) * fix: do not write header for gtf file * fix: write bed files without header * update dockerfile * update dev env --------- Co-authored-by: CJ Herrmann --- Dockerfile | 3 ++- environment-dev.yml | 8 ++++++++ scRNAsim_toolz/sequence_extractor/pre_bedtools.py | 2 +- 3 files changed, 11 insertions(+), 2 deletions(-) diff --git a/Dockerfile b/Dockerfile index 2ba76c6..3cbaf9d 100644 --- a/Dockerfile +++ b/Dockerfile @@ -16,7 +16,8 @@ LABEL maintainer="Máté Balajti " # COPY THE YAML & INSTALL SOFTWARE WITH CONDA WORKDIR /usr/src/app COPY ./ ./ -RUN conda env create --file environment.yml +RUN conda env create --file environment.yml \ + && conda clean --all # VARIABLES ARG WORKDIR="/home/USER" diff --git a/environment-dev.yml b/environment-dev.yml index b1cd936..4afecea 100644 --- a/environment-dev.yml +++ b/environment-dev.yml @@ -3,6 +3,14 @@ channels: - conda-forge - bioconda dependencies: + - pip>=20.2.3 + - biopython>=1.78 + - polars==0.16.17 + - gtfparse + - numpy>=1.23.3 + - pandas>=1.4.4 + - python>=3.6, <=3.10 + - pyarrow - black - coverage - flake8 diff --git a/scRNAsim_toolz/sequence_extractor/pre_bedtools.py b/scRNAsim_toolz/sequence_extractor/pre_bedtools.py index 98142f9..e4f5a6c 100644 --- a/scRNAsim_toolz/sequence_extractor/pre_bedtools.py +++ b/scRNAsim_toolz/sequence_extractor/pre_bedtools.py @@ -43,5 +43,5 @@ def pre_bedtools_mode(args): args.output_bed_file = "default_output.bed" pd.concat([gtf_df_pos, gtf_df_neg]).to_csv( - args.output_bed_file, sep="\t", index=False + args.output_bed_file, sep="\t", index=False, header=False ) # gtf_df_pos and gtf_df_neg must be dataframes