A framework combines supervised learning and dense subgraphs discovery to predict protein complexes.

Multi-label multi-instance transfer learning for simultaneous reconstruction and cross-talk modeling of multiple human signaling pathways.

Computational reconstruction of proteome-wide protein interaction networks between HTLV retroviruses and Homo sapiens.

Gene ontology based transfer learning for protein subcellular localization.

Amino acid classification based spectrum kernel fusion for protein subnuclear localization.