The Last Mile Problem: A Critical Assessment of Physics-Based and AI Tools for Small Molecule Binding Prediction in Virtual Screening
Xiaowen Wang, Hamza Hentabli, Akhila Mettu, Shubha Gautam, Dmitri Kireev · 2026
Read The Last Mile Problem: A Critical Assessment of Physics-Based and AI Tools for Small Molecule Binding Prediction in Virtual Screening by Xiaowen Wang, Hamza Hentabli, Akhila Mettu, Shubha Gautam, Dmitri Kireev (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-13213910.txt.
Description
Virtual screening hunts drug candidates by computer, but docking alone floods hit lists with false positives. Xiaowen Wang and co-authors benchmark in 2026 whether costly physics-based energy calculations can clean those lists. They tested the gold-standard method on 632 known complexes for accuracy, and on 315 binders mixed with decoys for sorting power, alongside cheaper physics methods and five machine learning models.
Accuracy tracked cost: the expensive method did well on both tests. Cheaper physics sorted actives from decoys but missed measured values. Most learning models shone only where their training data overlapped. The authors recommend a staged funnel: a strong AI filter first, then the costly physics on survivors.
Catalog record
| CREATOR | Xiaowen Wang, Hamza Hentabli, Akhila Mettu, Shubha Gautam, Dmitri Kireev |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 57 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |