MetaComb: a meta-learning framework for drug combination response prediction from cell lines to patients
Congcong Guo, Tongtong Li, Xinru Deng, Yajie Ma, Feng He, Lihong Diao, Ze Wang, Dong Li, Zhongyang Liu · 2026
Read MetaComb: a meta-learning framework for drug combination response prediction from cell lines to patients by Congcong Guo, Tongtong Li, Xinru Deng, Yajie Ma, Feng He, Lihong Diao, Ze Wang, Dong Li, Zhongyang Liu (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/pmc-13268602.txt.
Description
Congcong Guo and co-authors present in 2026 MetaComb, a learning framework that predicts how cancer drug pairs will work in real patients by borrowing knowledge from cell line experiments. Models trained on cell lines often fail on patients, whose data are scarce for cost and ethical reasons. Their method uses meta-learning, where a model trained across many cell line tasks is fine-tuned with only a few patient samples.
MetaComb beat standard transfer learning on both data-poor cell lines and patient samples grown outside the body. Accuracy gains were clear, though the patient group was small. The authors frame the work as proof of concept: larger patient datasets must confirm whether the approach generalizes across cancers and clinics.
Catalog record
| CREATOR | Congcong Guo, Tongtong Li, Xinru Deng, Yajie Ma, Feng He, Lihong Diao, Ze Wang, Dong Li, Zhongyang Liu |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 45 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |