Article

Surprisal-based large language models reveal immunologic insights in lobular breast cancer

2026-08-31

Abstract excerpt

In large data sets discovery is often limited to pre-conceived hypotheses and data fishing. Here we tested whether systematic exploration of AI generated hypotheses could uncover clinically meaningful signals in extensively studied data. We deployed AutoDiscovery, a newly launched large language model (LLM) framework designed to search for hypotheses based on surprisal and systematically interrogate complex datase...

Identifiers and source

Literature Corpus work: 67becdd4-51b4-5439-94dc-56f62f94adaa
DOI: 10.64898/2026.08.25.26361365

Open publication

Related research

Semantic proximity does not establish scientific evidence. Graph snapshot: 2026-09-29.

Click a neighbor to travelStep 1 · 12 closest

Surprisal-based large language models reveal immunologic insights in lobular breast cancerDOI 10.64898/2026.08.25.26361365Read

IMMUNIA: A Multi-LLM Reasoning Agent for Immunoregulatory Surfaceome DiscoverySemantic proximity Read

A Systematic Multi-LLM AI Framework for Immunotherapy Biomarker Discovery and Target IdentificationSemantic proximity Read

A Domain-Specific Language Model Approach for Identifying Immunogenic Epitopes from Publicly Available Data: EpitopeMinerSemantic proximity Read

Three multimodal large language models fail at clinically actionable breast pathology in three different directionsSemantic proximity Read

Comparison of Large Language Models in Answering Immuno-Oncology Questions: A Cross-Sectional StudySemantic proximity Read

Implementing a context-augmented large language model to guide precision cancer medicineSemantic proximity Read

Scaling Large Language Models for Next-Generation Single-Cell AnalysisSemantic proximity Read

Language may be all omics needs: Harmonizing multimodal data for omics understanding with CellHermesSemantic proximity Read

Enhancing Gene Set Overrepresentation Analysis with Large Language ModelsSemantic proximity Read

Metappuccino: Large Language Model-driven Reconstruction of Sequence Read Archive Metadata for Cancer ResearchSemantic proximity Read

Cancer vs. Conversational Artificial IntelligenceSemantic proximity Read

AI-HOPE-TGFbeta: A Conversational AI Agent for Integrative Clinical and Genomic Analysis of TGF-β Pathway Alterations in Colorectal Cancer to Advance Precision MedicineSemantic proximity Read