Context-driven interaction retrieval and classification for modeling, curation, and reuse

Computational modeling seeks to construct and simulate intracellular signaling networks to understand health and disease. The scientific literature contains descriptions of experimental results that can be interpreted by machines using NLP or LLMs to itemize molecular interactions. This machine readable output can then be used to assess, update or improve existing biological models if there is a tool for comparing the existing model with the information extracted from the papers. Here we describe VIOLIN a tool for classifying machine outputs of molecular interactions with respect to a biological model. VIOLIN classifies interactions as corroborations, contradictions, flagged or extensions with subcategories of each class. This paper analyzes 2 different models, 9 reading sets, 2 NLP and 2 LLM tools to test VIOLIN's capabilities. The results show that VIOLIN successfully classifies interaction types and can be combined with automated filtering to provide a versatile tool for use by the systems biology community.