BELL: Biomodel Evidence and LLM-based Logic
- 1University of Pittsburgh
Abstract
Building accurate and predictive mechanistic models requires careful biological interaction curation and verification against existing knowledge. When done manually, these tasks become impractical, especially with massive extraction of interactions facilitated by advanced natural language processing methods and large language models (LLMs). We present BELL (Biomodel Evidence and LLM-based Logic), a biocuration support framework that automates evidence retrieval, scoring, and explanation for interaction-level verification. BELL processes each interaction through a five-step pipeline: entity grounding, database ranking, evidence retrieval from seven biological databases, a heuristic four-dimension programmatic scoring, and chain-of-thought explanation with a recommended curator action generated by LLMs. We applied BELL on 210 protein-protein interactions from a curated Glioblastoma Multiforme (GBM) model. Results show that 49.5% of interactions achieved HIGH confidence and 72.4% received a positive curator recommendation, while qualitative flags precisely directed curator attention to evidence gaps. BELL is integrated into the KALIMBA curation platform and available at www.boheme.pitt.edu/Kalimba.
Related
- NeuroGraphBench: Interacting with Drosophila Connectomes at Scale for Exploring the Functional Logic of Neural Circuits
- An embedded deep learning–fuzzy logic framework for intelligent and automated irrigation in smart farming
- Boolean Logic-responsive FRET Biosensors via Genetically Encoded Autonomous Compilation
- Mechanistic Interpretability Needs a Logic of Inference
- A proof-carrying architecture for synthetic genetic logic circuits under stochastic temporal contracts
BibTeX
@misc{arazkhani2026bell,
title = {{BELL: Biomodel Evidence and LLM-based Logic}},
author = {N. Arazkhani and B. H. Cochran and N. Miskov-Zivanov},
howpublished = {bioRxiv},
year = {2026},
month = sep,
doi = {10.64898/2026.09.18.721350},
url = {https://www.biorxiv.org/content/10.64898/2026.09.18.721350v1},
note = {CC BY},
}
RIS
TY - UNPB
TI - BELL: Biomodel Evidence and LLM-based Logic
AU - N. Arazkhani
AU - B. H. Cochran
AU - N. Miskov-Zivanov
PY - 2026
DA - 2026/09/18
PB - bioRxiv
DO - 10.64898/2026.09.18.721350
UR - https://www.biorxiv.org/content/10.64898/2026.09.18.721350v1
AB - Building accurate and predictive mechanistic models requires careful biological interaction curation and verification against existing knowledge. When done manually, these tasks become impractical, especially with massive extraction of interactions facilitated by advanced natural language processing methods and large language models (LLMs). We present BELL (Biomodel Evidence and LLM-based Logic), a biocuration support framework that automates evidence retrieval, scoring, and explanation for interaction-level verification. BELL processes each interaction through a five-step pipeline: entity grounding, database ranking, evidence retrieval from seven biological databases, a heuristic four-dimension programmatic scoring, and chain-of-thought explanation with a recommended curator action generated by LLMs. We applied BELL on 210 protein-protein interactions from a curated Glioblastoma Multiforme (GBM) model. Results show that 49.5% of interactions achieved HIGH confidence and 72.4% received a positive curator recommendation, while qualitative flags precisely directed curator attention to evidence gaps. BELL is integrated into the KALIMBA curation platform and available at www.boheme.pitt.edu/Kalimba.
ER -