Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: Jul 9, 2026

DeepOmicsAE: Representing Signaling Modules in Alzheimer's Disease with Deep Learning Analysis of Proteomics, Metabolomics, and Clinical Data

DeepOmicsAE: Representing Signaling Modules in Alzheimer's Disease with Deep Learning Analysis of Proteomics, Metabolomics, and Clinical Data

Published on: December 15, 2023

Benchmarking AI scientists for omics data-driven biological discovery.

Erpai Luo¹, Jinmeng Jia¹, Yifan Xiong¹

¹MOE Key Laboratory of Bioinformatics and Bioinformatics Division of BNRIST, Department of Automation, Tsinghua University, Beijing, 100084, China.

Bioinformatics (Oxford, England)

|July 7, 2026

Summary

Related Concept Videos

Genomics

Genomics

Genomics is the science of genomes: it is the study of all the genetic material of an organism. In humans, the genome consists of information carried in 23 pairs of chromosomes in the nucleus, as well as mitochondrial DNA. In genomics, both coding and non-coding DNA is sequenced and analyzed. Genomics allows a better understanding of all living things, their evolution, and their diversity. It has a myriad of uses: for example, to build phylogenetic trees, to improve productivity and...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

A multi-modal diffusion model with dual-cross-attention for multi-omics data generation and translation.

Nature communications·2026

Same author

CASHeart: A database of single cells chromatin accessibility for the human heart.

Quantitative biology (Beijing, China)·2026

Same author

A generic reference defined by consensus peaks for single-cell ATAC-seq data analysis.

Nature communications·2026

Same author

hECA v2.0: an AI-ready ensemble cell atlas of single-cell RNA and ATAC sequencing data.

Scientific data·2025

Same author

ERNIE-RNA: an RNA language model with structure-enhanced representations.

Nature communications·2025

Same author

Multitemporal single-cell profiling uncovers alveolar IL1β<sup>hi</sup> neutrophils: A significant indicator of CARDS progression.

Clinical and translational medicine·2025

This summary is machine-generated.

A new benchmark, BAISBench, evaluates AI scientists on real biological data. While not fully autonomous, AI scientists show potential for supporting data-driven biological research and discovery.

Area of Science:

Computational Biology
Artificial Intelligence in Science

Background:

Large language models are enabling AI scientists for biological data analysis.
Current benchmarks do not adequately assess AI scientists' ability to extract insights from real experimental data.

Purpose of the Study:

To introduce BAISBench, a benchmark for evaluating AI scientists on real single-cell transcriptomic datasets.
To assess the capabilities and limitations of current AI scientists in biological research.

Main Methods:

BAISBench includes cell type annotation on 15 datasets and scientific discovery tasks with 193 multiple-choice questions.
Evaluated AI scientists and compared performance against human bioinformaticians.

Main Results:

Related Experiment Videos

Last Updated: Jul 9, 2026

DeepOmicsAE: Representing Signaling Modules in Alzheimer's Disease with Deep Learning Analysis of Proteomics, Metabolomics, and Clinical Data

DeepOmicsAE: Representing Signaling Modules in Alzheimer's Disease with Deep Learning Analysis of Proteomics, Metabolomics, and Clinical Data

Published on: December 15, 2023

Current AI scientists show potential in supporting data-driven research but are not yet fully autonomous.

BAISBench effectively characterizes AI scientists' current capabilities and limitations.

Conclusions:

BAISBench serves as a practical benchmark for advancing AI scientists in biology.
It aids in identifying AI systems that can support real-world biological research workflows.