Cheminformatics Modeling of Adverse Drug Responses by Clinically Relevant Mutants of Human Androgen Receptor
Bibliographic record
Abstract
The human androgen receptor (AR) is a ligand-activated transcription factor that plays a pivotal role in the development and progression of prostate cancer (PCa). Many forms of castration-resistant prostate cancer (CRPC) still rely on the AR for survival. Currently used antiandrogens face clinical limitations as drug resistance develops in patients over time since they all target the mutation-prone androgen binding site (ABS), where gain-of-function mutations eventually convert antagonists into agonists. With a significant number of reported distinct mutations located across the ABS, it is imperative to develop a prognostic platform which would equip clinicians with prior knowledge and actionable strategies if cases of previously unreported AR mutations are encountered. The goal of this study is to develop a theoretical approach that can predict such previously unreported AR mutants in response to current treatment options for PCa. The expected drug response by these mutants has been modeled using cheminformatics methodology. The corresponding QSAR pipeline has been created, which extracts key protein-ligand interactions and quantifies them by 4D molecular descriptors. The developed models reported with an accuracy reaching 90% and enable prediction of activation of AR mutants by its native ligand as well as assess whether known antiandrogens will act on them as agonists or antagonists. As a result, a previously uncharacterized mutant, T878G, has been predicted to be activated by the latest antiandrogen enzalutamide, and the corresponding experimental evaluation confirmed this prediction. Overall, the developed cheminformatics pipeline provides useful insights toward understanding the changing genomic landscape of advanced PCa.
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 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.004 | 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".