Persistent spectral theory-guided protein engineering
This paper introduces TopFit, a framework that combines persistent spectral theory and sequence embeddings to predict protein fitness from mutations, validated on 34 benchmark datasets.
Author
Michigan State UniversityORCID 0000-0002-5781-2937Unclaimed ORCID profile · follow to get notified of new preprints
3 papers
Recent·Most cited
This paper introduces TopFit, a framework that combines persistent spectral theory and sequence embeddings to predict protein fitness from mutations, validated on 34 benchmark datasets.
Duc Duy Nguyen, Kaifu Gao, Jiahui Chen…·Guo‐Wei Wei
Structure-based drug repositioning using a homology model of the 2019-nCoV 3CL protease screens 1465 FDA-approved DrugBank compounds to identify candidate therapeutics against the virus.
Kaifu Gao, Duc Duy Nguyen, Rui Wang, Guo‐Wei Wei
The 2019-nCoV protease shares 96.1% sequence identity and near-identical inhibitor binding sites with SARS-CoV, so a generative machine-learning model proposes candidate inhibitors; existing HIV drugs are also assessed.