Transfer learning across the EC classification hierarchy overcomes data scarcity in drug-target interaction prediction
Predicting drug-target interactions (DTIs) with deep learning offers opportunities to accelerate drug discovery, yet performance is often constrained by the scarcity of target-specific training data. Transfer learning relieves this limitation but requires choosing a relevant source task, a choice usually made ad hoc. Here we use the Enzyme Commission (EC) classification hierarchy as a systematic criterion for source selection, ascending the EC tree from the target enzyme until a related family carries sufficient ChEMBL bioactivity data to pre-train a deep feedforward network, which is then fine-tuned on the scarce target. We applied this approach to SHMT2 and MTHFD2, two pharmacologically understudied enzymes of the mitochondrial one-carbon (1C) pathway, which is implicated in cancer and fibrosis and supports fibroblast collagen production through glycine synthesis. With 29 active compounds for MTHFD2 and only 6 for SHMT2 which has no ligands of its own, the six coming from its paralogue SHMT1 in the same EC class. EC-guided transfer learning produced usable models in a system where training from scratch failed (Matthews correlation coefficient 0.00 for SHMT2). Virtual screening of the DrugBank library identified six candidates, three of which, carbimazole, crizotinib, and GSK-2018682, reduced TGF-β-induced collagen production and glycine accumulation in human lung fibroblasts. The methodology, datasets, and code are released as a reusable template for enzyme targets with scarce bioactivity coverage.
Authors
- Rengül Çetin-Atalay (ORCID: https://orcid.org/0000-0003-2408-6606)
- Volkan Atalay (ORCID: https://orcid.org/0000-0001-7850-0601)
- Obada R. Shamaa
- Robert B. Hamanaka (ORCID: https://orcid.org/0000-0002-8909-356X)
- Alperen Dalkıran (ORCID: https://orcid.org/0000-0002-4243-7281)
- Parker S. Woods (ORCID: https://orcid.org/0000-0002-9054-4196)
- Takugo Cho
- Angelo Y. Meliton
- Kun Woo D Shin (ORCID: https://orcid.org/0009-0000-0477-153X)
- Gökhan M. Mutlu
Institutions
- Middle East Technical University (TR)
- University of Chicago (US)
- University of Edinburgh (GB)
Publication Details
- Journal
- Research Square
- Published
- 2026-11-18
- DOI
- https://doi.org/10.21203/rs.3.rs-10999675/v1
- Primary Topic
- Computational Drug Discovery Methods
- Type
- preprint
Funders
- U.S. Department of Defense
- Orta Doğu Teknik Üniversitesi