Article

Counterfactual Consistency as a Metric for Biological Foundation Models

2026-05-18

Abstract excerpt

Biological foundation models (BFMs)—large-scale models pretrained on diverse biological data such as genomes, transcriptomes, or protein sequences—hold promise for predicting the effects of genetic perturbations, drug interventions, and disease mutations. However, evaluating their reliability beyond simple next-token prediction or task-specific accuracy remains challenging. In this study, we introduce counterfactu...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: 9e3b8f1f-c1aa-59f6-89b4-e78902a4d13d
DOI: 10.14293/pr2199.003545.v2

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Counterfactual Consistency as a Metric for Biological Foundation ModelsDOI 10.14293/pr2199.003545.v2Read

Counterfactual Consistency as a Metric for Biological Foundation ModelsSemantic proximity Read

Mechanisms Matter: Transportability of Cellular Perturbation EffectsSemantic proximity Read

Rapid and Reproducible Multimodal Biological Foundation Model Development with AIDO.ModelGeneratorSemantic proximity Read

PertEval-scFM: Benchmarking Single-Cell Foundation Models for Perturbation Effect PredictionSemantic proximity Read

DeepSeq: High-Throughput Single-Cell RNA Sequencing Data Labeling via Web Search-Augmented Agentic Generative AI Foundation ModelsSemantic proximity Read

Tabular Foundation Models Are Competitive Cellular Perturbation Predictors Across Biological ScalesSemantic proximity Read

BiomniBench: Process-level Evaluation of LLM Agents for Real-world Biomedical ResearchSemantic proximity Read

Genome modeling and design across all domains of life with Evo 2Semantic proximity Read

Signature Recontextualization: Mapping perturbational signatures across biological contextsSemantic proximity Read

Agentic systems are adept at solving well-scoped, verifiable problems in computational biologySemantic proximity Read

ESM-Effect: An Effective and Efficient Fine-Tuning Framework towards accurate prediction of Mutation’s Functional EffectSemantic proximity Read

UniPert-G2CP bridges genetic and chemical screens from molecular representation to phenotype modeling.Semantic proximity Read