Barros Marcia, Moitinho Andre, Couto Francisco M
LASIGE, Departamento de Informática, Faculdade de Ciências, Universidade de Lisboa, 1749-016, Lisboa, Portugal.
CENTRA, Departamento de Física, Faculdade de Ciências, Universidade de Lisboa, 1749-016, Lisboa, Portugal.
J Cheminform. 2021 Feb 23;13(1):15. doi: 10.1186/s13321-021-00495-2.
The large, and increasing, number of chemical compounds poses challenges to the exploration of such datasets. In this work, we propose the usage of recommender systems to identify compounds of interest to scientific researchers. Our approach consists of a hybrid recommender model suitable for implicit feedback datasets and focused on retrieving a ranked list according to the relevance of the items. The model integrates collaborative-filtering algorithms for implicit feedback (Alternating Least Squares and Bayesian Personalized Ranking) and a new content-based algorithm, using the semantic similarity between the chemical compounds in the ChEBI ontology. The algorithms were assessed on an implicit 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.
大量且不断增加的化合物给探索此类数据集带来了挑战。在这项工作中，我们建议使用推荐系统来识别科研人员感兴趣的化合物。我们的方法包括一个适用于隐性反馈数据集的混合推荐模型，该模型专注于根据项目的相关性检索一个排名列表。该模型整合了用于隐性反馈的协同过滤算法（交替最小二乘法和贝叶斯个性化排序）以及一种新的基于内容的算法，该算法利用了ChEBI本体中化合物之间的语义相似性。这些算法在一个包含超过16000个项目（化合物）的化合物隐性数据集CheRM - 20上进行了评估。在大多数评估指标中，混合模型能够将协同过滤算法的结果提高超过十个百分点。
