ECNet: Evolutionary Context-Integrated Neural Network


CABBI Theme: Conversion

Keyword: Software



Luo, Y. Aug. 30, 2021. “loyunan/ECNet: First release (v0.1).” Zenodo. DOI: 10.5281/zenodo.5294461


An overview of ECNet, an evolutionary context-integrated, deep learning model for protein engineering.


ECNet (evolutionary context-integrated neural network) is a deep learning model that guides protein engineering by predicting protein fitness from the sequence. It integrates local evolutionary context from homologous sequences that explicitly model residue-residue epistasis for the protein of interest with the global evolutionary context that encodes rich semantic and structural features from the enormous protein sequence universe.



ECNet Code Repository


Related Publication

Luo, Y., Jiang, G., Yu, T., Liu, Y., Vo, L., Ding, H., Su, Y., Qian, W.W., Zhao, H., Peng, J. Sept. 30, 2021. “ECNet is an Evolutionary Context-Integrated Deep Learning Framework for Protein Engineering.” Nature Communications 12, 5743. DOI: 10.1038/s41467-021-25976-8.