HKU-BAL/ClairS-TO
ClairS-TO - a deep-learning method for tumor-only somatic variant calling
This project helps cancer researchers and clinicians identify somatic small variants in tumor samples using long-read sequencing data. It takes raw sequencing reads from a tumor sample as input and outputs a list of potential somatic variants, even without a matched normal sample. This tool is designed for specialists in cancer genomics or molecular pathology who need to precisely detect mutations specific to a tumor.
Use this if you need to find genetic mutations present only in tumor tissue from long-read sequencing data, especially when a healthy control sample is unavailable.
Not ideal if you are working with paired tumor and normal samples, in which case a tool like ClairS for paired variant calling would be more suitable.
Stars
82
Forks
4
Language
Python
License
BSD-3-Clause
Category
Last pushed
Nov 13, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/HKU-BAL/ClairS-TO"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Compare
Higher-rated alternatives
google/deepvariant
DeepVariant is an analysis pipeline that uses a deep neural network to call genetic variants...
cgoliver/rnaglib
Toolkit for structure-based deep learning on RNA.
google/deepsomatic
DeepSomatic is an analysis pipeline that uses a deep neural network to call somatic variants...
Kuanhao-Chao/OpenSpliceAI
🤖 Open‑source deep-learning-based splice‑site predictor that decodes splicing patterns across species
Merck/deepbgc
BGC Detection and Classification Using Deep Learning