GraphTransDTI: A novel hybrid framework combining graph transformer and CNN-BiLSTM for enhanced Drug-Protein Interaction prediction
Van-Vang Le, Mai Thi Anh Nhu, Pham Truong Viet Thong · 2026
Read GraphTransDTI: A novel hybrid framework combining graph transformer and CNN-BiLSTM for enhanced Drug-Protein Interaction prediction by Van-Vang Le, Mai Thi Anh Nhu, Pham Truong Viet Thong (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/plos-pone-0351314.txt.
Description
Le, Nhu, and Thong built a hybrid AI framework to predict drug and protein pairings in a 2026 study. Knowing which proteins a drug touches speeds discovery and reuse of old drugs. Their system reads drug shapes with one network and protein sequences with another, then lets the two views attend to each other.
Tests used two standard benchmark sets under three splits, including hard cases with unseen drugs or unseen proteins. Performance matched leading rival methods across those tests. Gains came from joining shape and sequence views rather than relying on either alone. Better pairing predictions cut the number of lab tests wasted on hopeless combinations.
Catalog record
| CREATOR | Van-Vang Le, Mai Thi Anh Nhu, Pham Truong Viet Thong |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 58281 |
| LICENSE | CC_BY |
| RIGHTS | CC BY |
| SOURCE | PLOS |