#26 · Structural bio & protein design
Docking, deep learning and MD resolve inhibitor binding at NDM-1, ABCG2 and tubulin
The dominant thread is computational binding analysis in which predicted or simulated poses are tied to explicit structural features. The NDM-1 study uses AMDock docking and 100 ns GROMACS molecular dynamics to compare cyclic boronate inhibitors QPX7728 and VNRX5133 against carbapenems, with stability metrics as the readout. The ABCG2 study applies the PPLK deep learning model, which predicts protein-ligand pKd, to screen approximately 1.58M compounds, followed by MD simulation of selected candidates. The tubulin study integrates Protenix, RFAA and Umol structure prediction with MD to locate CPPF at a composite α/β-tubulin interface dominated by β-tubulin contacts, naming VAL236 and LEU253. What is new is the emphasis on localizing model output to named pockets and residues, rather than reporting affinity or classification alone.
Published papers
Leveraging a Deep Learning Model and Computational Screening for the Discovery of ABCG2 Inhibitors against Drug-Resistant Breast Cancer.
Deep learning model PPLK predicts protein-ligand pKd to screen ~1.58M compounds, with MD simulations, yielding ABCG2 inhibitors that reverse adriamycin…
Integrative AI-assisted modeling suggests CPPF binding at a composite α/β-tubulin interface pocket dominated by β-tubulin contacts.
Structure prediction (Protenix, RFAA, Umol) and MD simulations place CPPF at the α/β-tubulin interface, dominated by β-tubulin residues VAL236 and LEU253.
Preprints
Insight into the mechanism of molecular interactions of the NDM metallo-beta-lactamase and cyclic boronate inhibition by molecular docking and molecular dynamics simulations
Docking with AMDock and 100 ns GROMACS MD compares NDM-1 binding of cyclic boronate inhibitors (QPX7728, VNRX5133) against carbapenems, with stability metrics.
Topic history
| Date | Rank |
|---|---|
| #26 | |
| #21 | |
| #9 | |
| #22 | |
| #6 | |
| #20 | |
| #5 | |
| #3 | |
| #19 | |
| #10 | |
| #12 | |
| #14 | |
| #6 | |
| #11 | |
| #5 | |
| #15 | |
| #17 | |
| #5 | |
| #19 | |
| #34 | |
| #18 | |
| #39 | |
| #12 | |
| #38 | |
| #31 | |
| #30 | |
| #19 | |
| #18 | |
| #14 | |
| #13 | |
| #19 | |
| #21 | |
| #10 | |
| #12 | |
| #28 | |
| #30 | |
| #27 | |
| #25 | |
| #17 | |
| #15 | |
| #33 | |
| #6 | |
| #10 | |
| #8 | |
| #3 | |
| #9 | |
| #6 | |
| #22 | |
| #15 | |
| #38 | |
| #36 | |
| #36 | |
| #40 | |
| #39 | |
| #36 |