Abstract B016: Discovering novel synthetic lethal relationships with large-scale cellular simulations
Bibliographic record
Abstract
Abstract Synthetic Lethality (SL) is a compelling example of a large combinatorial space, with the number of (order-independent) pairwise combinations of human genes totaling approximately 400 million. When further considering higher-order combinations beyond pairs i.e. additional biomarkers that modulate the the efficacy of an SL pair, this space grows exponentially larger still. Understanding these higher-order combinations is crucial for the discovery of synthetic lethal pairs with better defined therapeutic windows and improved segmentation in clinical trials. As the size of this combinatorial space is far greater than can be searched by existing screening technologies, novel approaches are required to efficiently search this space and prioritize higher-order candidate SL combinations for screening. DeepOrigin is developing large-scale dynamical models of cellular systems to drive the in silico discovery of novel therapeutics across a range of diseases. These models can be simulated efficiently and in parallel, and are therefore ideally suited for searching large combinatorial spaces. We have applied our proprietary Cellular Simulation Pipeline to the problem of identifying higher-order combinations in Synthetic Lethality, so far predicting hundreds of novel synthetic lethal pairs. These pairs are currently being validated in vitro, and we present a selection of these results that demonstrate the utility of this approach. This approach could provide both novel therapeutic targets while providing additional stratification criteria for increased clinical study success. Citation Format: Oliver Purcell, Paul Lang, James Komianos, Nimi Vashi. Discovering novel synthetic lethal relationships with large-scale cellular simulations [abstract]. In: Proceedings of the AACR Special Conference in Cancer Research: Expanding and Translating Cancer Synthetic Vulnerabilities; 2024 Jun 10-13; Montreal, Quebec, Canada. Philadelphia (PA): AACR; Mol Cancer Ther 2024;23(6 Suppl):Abstract nr B016.
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 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.001 | 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) | 0.004 | 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".