ORCA - H1-ESC (1M) Predictor for GAME
Abstract
The ORCA_H1ESC_1M_predictor.sif contains the following: The scripts required to process, error check and predict in the GAME API format for 1M H1-ESC Hi-C model A .json file to return for help message requests All dependencies, scripts, model weights and hg38 ref genome required to run the ORCA model are downloaded into the container at build time How to run: apptainer run --nv --containall ORCA_H1ESC_1M_predictor.sif HOST PORT Notes: The container can be run using the --nv flag for GPU compatibility This version of the container can only predict for H1-ESC cells in homo_sapiens Each sequence prediction returns a matrix with each value representing a 4,000bp x 4,000bp interaction region. For example, for a 1Mbp input sequence the returned matrix will be 250x250 Additional information regarding ORCA can be found here: https://github.com/jzhoulab/orca Additional information regarding the API can be found here: https://github.com/de-Boer-Lab/Genomic-API-for-Model-Evaluation
Publication details
- Journal / source
- Zenodo (CERN European Organization for Nuclear Research)
- Publication date
- 8 January 2026