Context-aware knowledge selection and reliable model recommendation with ACCORDION

Abstract

Querying new information from knowledge sources, in general, and published literature, in particular, aims to provide precise and quick answers to questions raised about a system under study. In this paper, we present ACCORDION (ACCelerating and Optimizing model RecommenDatIONs), a novel methodology and a tool to enable efficient addressing of biological questions, by automatically recommending models that recapitulate desired dynamic behavior. Our approach integrates information extraction from literature, clustering, simulation and formal analysis to allow for automated, consistent, and robust assembling, testing and selection of context-specific models. We used ACCORDION in nine benchmark case studies and compared its performance with other previously published tools. ACCORDION is comprehensive as it can capture all relevant knowledge from literature, obtained by automated literature search and machine reading. At the same time, as our results show, ACCORDION is selective, recommending only the most relevant and useful subset (15-20%) of candidate model extensions found in literature, while guided by baseline model context and goal properties. ACCORDION is very effective, also demonstrated by our results, as it can reduce the error of the initial baseline model by more than 80%, recommending models that closely recapitulate desired behavior, and outperforming previously published tools. In this process, ACCORDION can also suggest more than one highly scored model, thus providing alternative solutions to user questions and novel insights for treatment directions.

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

“…For analysis of an existing model, interactions are corroborated, contradicted, or flagged for further investigation. For users looking to update and improve a model, VIOLIN provides extensions for further processing using tools such as ACCORDION 14 .…”

“…Small numbers of flagged interactions can be evaluated manually if they are of interest. The model extension tools 13,15,[17][18][19]30 that explore a large number of new interaction candidates in an automated manner use only extensions that VIOLIN selects from interaction lists. Two elements satisfy the necessary element match condition if they have the same name or same ID, and they have the same type.…”

“…Several open-source tools have been developed recently that aim to automatically enhance or extend existing models. The BEL enrichment workflow 12 maintains knowledge graphs using literature, CLARINET 13 and ACCORDION 14 recommend extensions of executable models based on graph features or dynamic properties, respectively. These and several other tools [15][16][17][18][19] integrate new information and knowledge from literature, databases, and experts, employing techniques such as clustering, graph search algorithms, genetic algorithm, and model checking.…”