Abstract A003: An active learning platform for predictive oncology in rare cancers
Bibliographic record
Abstract
Abstract Directly testing patient tissues ex vivo against panels of anti-cancer agents has been shown in multiple recent clinical trials to provide superior treatment guidance for patients with rare and high-risk cancers. All trials to date have focused on recommending a single agent, even though rationally designed combination therapies typically lead to better outcomes. The main bottleneck in these trials is the combinatorial explosion of exhaustively screening all combinations in a panel of drugs. We developed a new Bayesian active learning algorithm called BATCHIE that enables large-scale combination drug screens over huge libraries in cancer cell line experiments. Given a set of previous experiments, BATCHIE optimally designs the next batch of combination screens to maximize the utility of the batch. To bootstrap our predictive models, we collected and integrated more than 2M ex vivo drug screen results from two dozen published studies. The talk will conclude with initial results translating our platform into the clinic for patients with desmoplastic small round cell tumor, an ultra-rare cancer with no standard of care or targetable recurrent alterations. Citation Format: Christopher Tosh, Glorymar Ibanez Sanchez, Emily Stockfisch, Andrew Kung, Filemon Dela Cruz, Emily Slotkin, Wesley Tansey. An active learning platform for predictive oncology in rare cancers [abstract]. In: Proceedings of the AACR Special Conference in Cancer Research: Artificial Intelligence and Machine Learning; 2025 Jul 10-12; Montreal, QC, Canada. Philadelphia (PA): AACR; Clin Cancer Res 2025;31(13_Suppl):Abstract nr A003.
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 | 0.002 | 0.005 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.002 | 0.003 |
| Insufficient payload (model declined to judge) | 0.019 | 0.006 |
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".