Integrating Genome-Scale Metabolic Modeling with Machine Learning Improves Gene Essentiality Prediction in Triple-Negative Breast Cancer
Bo Kyung Kim, Changdai Gu, Mohamed El-Agamy Farh, Jae Yong Ryu · 2026
Read Integrating Genome-Scale Metabolic Modeling with Machine Learning Improves Gene Essentiality Prediction in Triple-Negative Breast Cancer by Bo Kyung Kim, Changdai Gu, Mohamed El-Agamy Farh, Jae Yong Ryu (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-13256420.txt.
Description
Bo Kyung Kim and colleagues present a 2026 computational study predicting which genes triple-negative breast cancer cannot live without. This aggressive subtype lacks drug targets found in other breast cancers, so hidden metabolic dependencies are valuable. The team built cell-line-specific metabolic models for fifty breast cancer lines and fed their simulated flows into a machine learning classifier.
Adding the metabolic features clearly beat using the model alone, lifting sensitivity for spotting essential genes. The combined approach found fifty-seven genes essential specifically in triple-negative lines, including ENO1, a glycolysis enzyme the simpler method missed. It also predicted thirty backup-lethal partners for one metabolic gene, SDHA, whose loss could be exploited in pairs. The authors offer the framework as a target-finding engine for cancers defined by their metabolism.
Catalog record
| CREATOR | Bo Kyung Kim, Changdai Gu, Mohamed El-Agamy Farh, Jae Yong Ryu |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 31 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |