DNAR-06. Discovery and development of novel CNS-penetrating PARP1-selective inhibitors
Bibliographic record
Abstract
Abstract Poly(ADP-ribose) polymerase (PARP) is a key enzyme in DNA damage repair (DDR) and inhibition of PARP1 specifically has been shown to be an effective treatment for cancers with DDR deficiencies, such as BRCA mutations. First generation PARP inhibitors have achieved commercial success in the treatment of BRCA-mutated cancers, but are limited in their clinical utility as they are unable to penetrate the blood-brain barrier (BBB) and therefore cannot be used to treat central nervous system (CNS) tumors. These inhibitors also show adverse side effects, likely due to their collateral inhibition of PARP2. Development of a novel PARP1-specific, CNS-penetrating drug could provide a new therapeutic option for patients with brain tumors, both primary and metastatic with the desired advantage of reduced toxicity. Here, we describe the use of artificial intelligence (AI) methods for the discovery and development of a novel, PARP1-selective and CNS-penetrating inhibitor. Deep docking is a process that uses deep learning to accelerate the prediction of binding of target proteins with a large compound library of 1.6 billion compounds. This was combined with generative AI and machine learning techniques that predict CNS penetrance to generate molecules predicted to be CNS-penetrating, potent, and selective for PARP1 inhibition. The most promising of these molecules were synthesized and validating data for these molecules will be presented, including in vitro PARP1 inhibition and selectivity, metabolic stability, in vivo pharmacokinetic profiles, and BBB penetration. This approach has enabled deep and rapid exploration of chemical space, accelerating the drug discovery process compared to traditional drug discovery methods.
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 | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| 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) | 0.003 | 0.002 |
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".