Niloofar Arazkhani

BELL: Biomodel Evidence and LLM-based Logic

BELL automates evidence retrieval and scoring for biological interactions, achieving high confidence in 49.5% of tested interactions and guiding curators effectively.

GBM model refinement with literature curation, rule-based NLP, and LLMs

This work improves a GBM mechanistic model and evaluates NLP and LLM approaches for model refinement using graph metrics and literature curation.

The BioRECIPE Knowledge Representation Format

The paper introduces the BioRECIPE format for representing biological models to enable human-machine interaction and model development.

VIOLIN: A modular framework for scalable reconciliation of heterogeneous interaction graphs

VIOLIN reconciles heterogeneous interaction graphs with extracted molecular interactions, showing stable and interpretable results across different models and datasets.