diff --git a/README.md b/README.md index 3161d7aca06b2e3acdecc4c7d7483e1a775f4f77..58cfa033adb314cd8add28f69dc37ea581cbb0b8 100644 --- a/README.md +++ b/README.md @@ -7,3 +7,16 @@ conda env create --file environment.yml conda activate transcript-structure-generator ``` +# Usage + +Input: +- Csv-formatted file ("ID,Count") with counts for individual transcripts +- Probability of intron inclusion (float in range [0,1]) +- gtf-formatted file with exon coordinates of the transcripts included in the csv file + +Output: +- gtf-formatted file containing generated intron/exon structures per transcript +- csv-formatted file ("NewTranscriptID,ID,Count") with + - id of generated transcript + - id of original transcript (without intron inclusions) + - count \ No newline at end of file diff --git a/src/__init__.py b/src/__init__.py new file mode 100644 index 0000000000000000000000000000000000000000..d9744d3ffce1f105fb23f0129578fbeb2cc6b9da --- /dev/null +++ b/src/__init__.py @@ -0,0 +1,3 @@ +"""Transcript structure generator package.""" + +__version__ = '0.0.0' \ No newline at end of file diff --git a/src/main.py b/src/main.py new file mode 100644 index 0000000000000000000000000000000000000000..ea1a4d93fbc05e94153cc1e612826a096ec138cd --- /dev/null +++ b/src/main.py @@ -0,0 +1,17 @@ +import argparse +from pathlib import Path + +if __name__ == "__main__": + parser = argparse.ArgumentParser() + parser.add_argument("--transcripts", type=str) + parser.add_argument("--annotation", type=str) + parser.add_argument("--prob_inclusion", type=float) + args = parser.parse_args() + + input_transcripts_file = args.transcripts + input_annotations_file = args.annotation + prob_inclusion = args.prob_inclusion + input_transcripts_path = Path(input_transcripts_file) + input_annotations_path = Path(input_annotations_file) + output_transcripts_file = "generated_" + input_transcripts_path.stem + ".csv" + output_annotations_file = "generated_" + input_annotations_path.name