The pretrained models for scProTrans
Abstract
This archive contains two pretrained models used in the paper: "A sequence knowledge-guided deep learning method for single-cell multi-omics translation" ----------------------------------------Contents---------------------------------------- After extraction, the following files are obtained: 1. dna2vec_1w.npz - Description: Pretrained embedding model for DNA sequences - Purpose: Used to represent gene sequences in the experiments 2. per-protein.h5 - Description: Pretrained embedding model for protein sequences - Purpose: Used to represent protein features in the experimentsThese models are used to reproduce the experimental results reported in the manuscript.
Publication details
- Journal / source
- Zenodo (CERN European Organization for Nuclear Research)
- Publication date
- 25 March 2026
- Document type
- Dataset