EVA: a Foundation Model Advancing Translational Drug Development in Immuno-Inflammation
Bibliographic record
Abstract
Abstract Drug development is a lengthy and high-risk process, with most investigational drug candidates failing in phase II randomized clinical trials (RCT) due to insufficient efficacy. It makes early prediction of trial outcomes crucial for reducing attrition and guiding strategic decisions, especially in immunology and inflammation (I&I) diseases. Herein, we present EVA, the first pre-trained foundation model in complex inflammatory diseases tailored to support drug development. EVA learns generalizable patterns from large-scale data of cell biology and immunology, enabling superior predictive performance and generalization compared to traditional approaches. EVA is pre-trained on tens of millions of single-cell RNA-seq samples and tens of thousands of bulk RNA-seq samples from I&I diseases patients, enabling it to learn disease-relevant transcriptomic patterns in this therapeutic area. By fine-tuning EVA in few-shot settings on both preclinical (mouse) and clinical (human) data and harnessing its wide pre-training knowledge, EVA predicts drug responses in I&I with high precision at both cohort and patient levels, as illustrated by accurate forecasting of anti-TNF therapeutic activity in ulcerative colitis. By deciphering its decision process, we further highlight that EVA’s ability to stratify patients based on predicted drug response can also be leveraged to discover drug response biomarkers as early as preclinical stages. EVA’s applications in precision immunology encompass therapeutic target validation prior to clinical entry, identification of patient subpopulations most likely to benefit from treatment, and comparative efficacy analysis against competitor compounds. EVA’s versatility makes it an invaluable tool for strategic decision-making throughout the drug development pipeline: by leveraging it to prioritize the most promising drug candidates and optimize RCT designs, it can contribute to reduce late-stage failures and accelerate the delivery of effective therapies. Overall, this work represents a significant advancement in utilizing a pre-trained foundation model for precision drug development in complex inflammatory diseases. Graphical abstract EVA is a pre-trained foundation model specific to immune-mediated inflammatory diseases. It enables the prediction of therapeutic efficacy in patients leveraging data from preclinical disease models.
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 | 0.003 | 0.007 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.003 | 0.001 |
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".