NodeCoder: a graph-based machine learning platform to predict active sites of modeled protein structures

1 code implementation • 7 Feb 2023 • Nasim Abdollahi, Seyed Ali Madani Tonekaboni, Jay Huang, Bo wang, Stephen MacKinnon

While accurate protein structure predictions are now available for nearly every observed protein sequence, predicted structures lack much of the functional context offered by experimental structure determination.

Learning across label confidence distributions using Filtered Transfer Learning

no code implementations • 3 Jun 2020 • Seyed Ali Madani Tonekaboni, Andrew E. Brereton, Zhaleh Safikhani, Andreas Windemuth, Benjamin Haibe-Kains, Stephen MacKinnon

In this work, we apply a transfer learning approach to improve predictive power in noisy data systems with large variable confidence datasets.

Transfer Learning