Active Learning Guided Hit Optimization for the Leucine-Rich Repeat Kinase 2 WDR Domain Based on In Silico Ligand Binding Affinities
Bibliographic record
Abstract
The leucine-rich repeat kinase 2 (LRRK2) is the most mutated gene in familial Parkinson’s disease, whose mutations lead to pathogenic hallmarks of the disease. The LRRK2 WDR domain is an understudied drug target for Parkinson’s disease with no known inhibitors prior to the first phase of the Critical Assessment of Computational Hit-Finding Experiments (CACHE) Challenge. CACHE challenges are designed to attract state-of-the-art computational methods for both hit-finding and lead optimization of small molecule inhibitors to challenging protein targets. A unique advantage of the CACHE challenge is that the predicted molecules are experimentally validated in-house. Here we report on our winning submission of experimentally confirmed LRRK2 WDR inhibitor molecules, predicted from thermodynamics integration (TI) calculations performed on only 672 compounds within a chemical space of 25,171 molecules. We used a free energy molecular dynamics (MD) -based active learning (AL) workflow to optimize our two previously confirmed hit molecules. We identified 8 experimentally verified novel inhibitors out of 35 tested (23% hit rate) with a maximum affinity increase of almost 35-fold. These results demonstrate the efficacy of free energy-based active learning workflow to quickly and efficiently explore large chemical spaces while minimizing the number and length of computational simulations. This workflow is widely applicable to the screening of any chemical space for small molecule analogs with increased affinity, subject to the general constraints of RBFE calculations. The mean absolute error of TI MD calculations was 1.30 kcal/mol with respect to measured KD of hit compounds.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".