BioMINTREL expands biological problem solving through cross-disciplinary representations
- 1King Abdullah University of Science and Technology
Abstract
Biological research agents often rely on familiar analytical methods, limiting the questions explored in existing data. We introduce BioMINTREL, an AI agent that finds methods from other disciplines and connects them to biological measurements. It can draw on relationships among datasets and complementary ideas from several methods to develop new questions and analyses. We evaluate it on BioMDC-Bench, which assesses 228 possible applications of computational methods to biological tasks. Compared with GPT-5.4 mini and Qwen3.6-35B, BioMINTREL improves F1 agreement with human experts by up to 45.3 percentage points and increases coverage of applications supported by studies published in subsequent years by up to 58.8 percentage points. Four case studies on real data go beyond previous analyses to reveal dose-specific variant effects, constraints on spatial cell communication and routes through perturbation-response states, and identify the sampling needed to test whether rare high-state cells predict later lineage size. These results highlight BioMINTREL's potential to expand questions in existing data and suggest directions for subsequent research.
Related
- Operationalizing open-ended biological discovery across single-cell representations
- A Transformer-Based Delta Expression Encoder for Psilocybin Transcriptional Response: Architecture, Representations, and Biological Validation
- Stress Urinary Incontinence in Elite Female Athletes: A Cross-Disciplinary Survey of Prevalence and Contributing Factors
- Increased Cognitive Load Expands, Stabilizes, and Aligns Visual Representation Across the Human Brain
- Episodic memory adaptively expands retrieval through typicality-guided transformation while concrete details remain accessible
BibTeX
@misc{dong2026biomintrel,
title = {{BioMINTREL expands biological problem solving through cross-disciplinary representations}},
author = {J. Dong and Y. Zhang and E. Gao and C. Yang and J. Wang and C. Zha and Z. Wu and X. Xu and J. Zhou and X. Gao},
howpublished = {bioRxiv},
year = {2026},
month = oct,
doi = {10.64898/2026.10.10.757703},
url = {https://www.biorxiv.org/content/10.64898/2026.10.10.757703v1},
note = {CC BY-NC-ND},
}
RIS
TY - UNPB
TI - BioMINTREL expands biological problem solving through cross-disciplinary representations
AU - J. Dong
AU - Y. Zhang
AU - E. Gao
AU - C. Yang
AU - J. Wang
AU - C. Zha
AU - Z. Wu
AU - X. Xu
AU - J. Zhou
AU - X. Gao
PY - 2026
DA - 2026/10/10
PB - bioRxiv
DO - 10.64898/2026.10.10.757703
UR - https://www.biorxiv.org/content/10.64898/2026.10.10.757703v1
AB - Biological research agents often rely on familiar analytical methods, limiting the questions explored in existing data. We introduce BioMINTREL, an AI agent that finds methods from other disciplines and connects them to biological measurements. It can draw on relationships among datasets and complementary ideas from several methods to develop new questions and analyses. We evaluate it on BioMDC-Bench, which assesses 228 possible applications of computational methods to biological tasks. Compared with GPT-5.4 mini and Qwen3.6-35B, BioMINTREL improves F1 agreement with human experts by up to 45.3 percentage points and increases coverage of applications supported by studies published in subsequent years by up to 58.8 percentage points. Four case studies on real data go beyond previous analyses to reveal dose-specific variant effects, constraints on spatial cell communication and routes through perturbation-response states, and identify the sampling needed to test whether rare high-state cells predict later lineage size. These results highlight BioMINTREL's potential to expand questions in existing data and suggest directions for subsequent research.
ER -