Operationalizing open-ended biological discovery across single-cell representations
Abstract
Single-cell studies are typically initiated from predefined research questions, leaving much of the biological information encoded within existing data unexplored. We formalize open-ended discovery as an analytical paradigm, in which data-derived signals are identified before biological context is interrogated and subsequently evaluated according to their potential to justify prospective experimental investment. Here we develop PROSPECTor, an end-to-end framework that searches for reproducible biological structures across conventional expression representations and diverse foundation-model embeddings, translating robust signals into quantitatively testable candidate hypotheses. Projection into unseen datasets then evaluates their generalizability and phenotype association, providing a scalable screen for candidates that warrant prospective validation. Supported signals emerged from different representation spaces and search strategies. PROSPECTor-nominated hypotheses were then examined in independent biological settings: fibroblast extracellular-matrix programmes demonstrated transferability to an independent mouse cohort with an intervention context, while a patient-resolved gastric-cancer T-cell programme recurred across single-cell, bulk and spatial cohorts. PROSPECTor establishes an auditable framework for systematically revisiting single-cell datasets across expanding representation spaces, turning retrospective collections into prospective resources for biological discovery that can motivate new research questions.
Related
- Novel two-stage deep learning-based approach applied to gene expression data pertaining to esophageal adenocarcinoma boosting biological knowledge discovery
- BioMINTREL expands biological problem solving through cross-disciplinary representations
- A Transformer-Based Delta Expression Encoder for Psilocybin Transcriptional Response: Architecture, Representations, and Biological Validation
- Distributed AI agents enable comprehensive discovery of biological insights at scale
- Network geometry shapes the transformation of task representations across the human cortex
BibTeX
@misc{zhang2026operationalizing,
title = {{Operationalizing open-ended biological discovery across single-cell representations}},
author = {Ningxuan Zhang and Ziwei Wang and Ning Xie and Na Liu},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.00681},
eprint = {2609.00681},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.00681},
}
RIS
TY - UNPB
TI - Operationalizing open-ended biological discovery across single-cell representations
AU - Ningxuan Zhang
AU - Ziwei Wang
AU - Ning Xie
AU - Na Liu
PY - 2026
DA - 2026/09/01
PB - arXiv
DO - 10.48550/arxiv.2609.00681
UR - https://arxiv.org/abs/2609.00681
AB - Single-cell studies are typically initiated from predefined research questions, leaving much of the biological information encoded within existing data unexplored. We formalize open-ended discovery as an analytical paradigm, in which data-derived signals are identified before biological context is interrogated and subsequently evaluated according to their potential to justify prospective experimental investment. Here we develop PROSPECTor, an end-to-end framework that searches for reproducible biological structures across conventional expression representations and diverse foundation-model embeddings, translating robust signals into quantitatively testable candidate hypotheses. Projection into unseen datasets then evaluates their generalizability and phenotype association, providing a scalable screen for candidates that warrant prospective validation. Supported signals emerged from different representation spaces and search strategies. PROSPECTor-nominated hypotheses were then examined in independent biological settings: fibroblast extracellular-matrix programmes demonstrated transferability to an independent mouse cohort with an intervention context, while a patient-resolved gastric-cancer T-cell programme recurred across single-cell, bulk and spatial cohorts. PROSPECTor establishes an auditable framework for systematically revisiting single-cell datasets across expanding representation spaces, turning retrospective collections into prospective resources for biological discovery that can motivate new research questions.
ER -