The paper "Hybrid semantic recommender system for chemical compounds in large-scale datasets", authored by LASIGE's PhD student Márcia Barros has been published in Journal of Cheminformatics, a top-ranked journal (h-5 index=41; Scimago Q1). The paper co-authors are LASIGE's integrated researcher Francisco M. Couto and André Moitinho from CENTRA/FCUL.
Chemical compounds databases are increasing in number and complexity. This paper proposes the usage of recommender systems to identify compounds of interest to scientific researchers. The approach consists of a hybrid recommender model with a collaborative-filtering module based on state-of-the-art algorithms and new content-based algorithm based on the semantic similarity of the chemical compounds. The algorithms were assessed on an implicit feedback dataset of chemical compounds, CheRM-20, with more than 16.000 items (chemical compounds). The hybrid model was able to improve the results of the collaborative-filtering algorithms, by more than ten percentage points in most of the assessed evaluation metrics.
The paper is available here.