Abstract B025: An agentic platform for designing cancer immunotherapies: From automated variant interpretation to in silico therapeutic validation
Bibliographic record
Abstract
Abstract The development of personalized cancer immunotherapies is critically hampered by the inability to rapidly interpret the functional consequences of genetic variants, particularly non-coding variants and variants of uncertain significance (VUS). This interpretation bottleneck creates significant delays in designing effective, patient-specific treatments. To address this catastrophic failure, we have developed an agentic platform that automates the end-to-end in silico workflow from variant discovery to therapeutic design and validation. Our platform, CrisPRO.ai integrates a powerful intelligence engine and a generative therapeutic forge, orchestrated by a central command agent. The intelligence engine leverages a state-of-the-art biological foundation model (Evo2) to provide zero-shot, quantitative predictions of variant pathogenicity across the entire genome. This allows for the rapid annihilation of VUS in critical immune-regulating genes and pathways, such as JAK/STAT and PD-L1, by providing a definitive functional score. Furthermore, the engine can perform in silico gene knockouts to identify novel synthetic lethal targets in the tumor microenvironment. The intelligence gathered is then passed to the therapeutic forge, which is commanded to generate novel biologics. Leveraging the model's generative capabilities, the forge can design high-efficacy CRISPR guide RNAs for gene knockout or correction, and even design custom regulatory elements like promoters and enhancers to ensure precise, context-specific expression of therapeutic payloads. Crucially, CrisPRO.ai closes the loop by performing fully computational therapeutic validation. After a pathogenic variant is identified and a corrective therapeutic is designed, the resulting "repaired" sequence is fed back into the intelligence engine. By comparing the pathogenicity scores before and after the intervention, we conduct a complete in silico trial, generating high-tier evidence of therapeutic efficacy. This agentic, closed-loop system represents a paradigm shift, collapsing the timeline for designing and validating personalized cancer immunotherapies from years to hours. Citation Format: Fahad Kiani, Rahima Nayeem. An agentic platform for designing cancer immunotherapies: From automated variant interpretation to in silico therapeutic validation [abstract]. In: Proceedings of the AACR Special Conference in Cancer Research: Mechanisms of Cancer Immunity and Cancer-related Autoimmunity; 2025 Sep 24-27; Montreal, QC, Canada. Philadelphia (PA): AACR; Cancer Immunol Res 2025;13(9 Suppl):Abstract nr B025.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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 teacher head, 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".