diff --git a/.gitignore b/.gitignore index 42770ec5750d8d11f9d2c139003b8307d923f626..83c7b50c8245b55dd94024d0f61fd9706d9c9591 100644 --- a/.gitignore +++ b/.gitignore @@ -1,6 +1,7 @@ .DS_Store .idea/ - +read_sequencer.egg-info +readsequencer.egg-info # Created by https://www.toptal.com/developers/gitignore/api/python # Edit at https://www.toptal.com/developers/gitignore?templates=python diff --git a/Dockerfile b/Dockerfile index eb44f01c37918b26983bca39ff9fb14cd050cc26..f2b74d79ed80385868c001801b96b62c67601d50 100644 --- a/Dockerfile +++ b/Dockerfile @@ -1,7 +1,7 @@ FROM python:3.11.1-slim-bullseye # MAINTAINER add_maintainer - +MAINTAINER "Christoph Harmel" # set names for user, group and user home ARG USER="bioc" ARG GROUP="bioc" diff --git a/README.md b/README.md index 3003dfb80d3d09bd805b71f5eb1b1c13bbfea12d..4895b8793876d5eb72db3497bb99391d155755fe 100644 --- a/README.md +++ b/README.md @@ -2,25 +2,48 @@ ## Overview -Read Sequencer is a test python package to simulate sequencing. +Read Sequencer is a python package to simulate sequencing. It reads fasta files, simulate sequencing with specified read length and writes the resulting sequences into a new fasta file. -## Installation from PyPI +## Installation from github Read Sequencer requires Python 3.9 or later. -Install Read Sequencer from PyPI using: +Install Read Sequencer from Github using: ``` -pip install -i https://test.pypi.org/simple/ read-sequencer==0.1.1 +git clone https://git.scicore.unibas.ch/zavolan_group/tools/read-sequencer.git +cd read-sequencer +pip install . ``` ## Usage ``` -read_sequencer --input_file_path --output_file_path --read_length +usage: read_sequencer [-h] [-i INPUT] [-r READ_LENGTH] [-n N_RANDOM] [-s CHUNK_SIZE] output +Simulates sequencing of DNA sequences specified by an FASTA file. + +positional arguments: + output path to FASTA file + +optional arguments: + -h, --help show this help message and exit + -i INPUT, --input INPUT + path to FASTA file + -r READ_LENGTH, --read-length READ_LENGTH + read length for sequencing + -n N_RANDOM, --n_random N_RANDOM + n random sequences. Just used if input fasta file is not specified. + -s CHUNK_SIZE, --chunk-size CHUNK_SIZE + chunk_size for batch processing + ``` + +## Docker + +The docker image is available on docker hub: https://hub.docker.com/r/grrchrr/readsequencer + ## Contributors and Contact Information Christoph Harmel - christoph.harmel@unibas.ch diff --git a/readsequencer/cli.py b/readsequencer/cli.py index 76afc5a934c4a7f3f9a082fd53cc5a27e4078f0c..cc74c44cef025035b96a8963e79b3c89b280a4c2 100644 --- a/readsequencer/cli.py +++ b/readsequencer/cli.py @@ -7,7 +7,7 @@ LOG = logging.getLogger(__name__) def main(): parser = argparse.ArgumentParser( - prog="read_sequencer", + prog="readsequencer", description="Simulates sequencing of DNA sequences specified by an FASTA file.", )