Benchmarking and Evaluation of AI Models in Biology: Outcomes and Recommendations from the CZI Virtual Cells Workshop

TL;DR

This paper discusses the importance of standardized benchmarking in AI for biology, highlighting challenges and proposing recommendations to develop robust, reproducible, and comprehensive evaluation frameworks to advance biological AI research.

Contribution

It introduces a set of recommendations for creating effective benchmarking frameworks in biological AI, addressing current systemic and technical bottlenecks.

Findings

Identification of key bottlenecks like data heterogeneity and noise

Proposal of standardized evaluation metrics and open platforms

Emphasis on high-quality data curation and collaborative tools

Abstract

Artificial intelligence holds immense promise for transforming biology, yet a lack of standardized, cross domain, benchmarks undermines our ability to build robust, trustworthy models. Here, we present insights from a recent workshop that convened machine learning and computational biology experts across imaging, transcriptomics, proteomics, and genomics to tackle this gap. We identify major technical and systemic bottlenecks such as data heterogeneity and noise, reproducibility challenges, biases, and the fragmented ecosystem of publicly available resources and propose a set of recommendations for building benchmarking frameworks that can efficiently compare ML models of biological systems across tasks and data modalities. By promoting high quality data curation, standardized tooling, comprehensive evaluation metrics, and open, collaborative platforms, we aim to accelerate the development of robust benchmarks for AI driven Virtual Cells. These benchmarks are crucial for ensuring rigor, reproducibility, and biological relevance, and will ultimately advance the field toward integrated models that drive new discoveries, therapeutic insights, and a deeper understanding of cellular systems.