Explaining protein-protein interactions with knowledge graph-based semantic similarity.

The application of artificial intelligence and machine learning methods for several biomedical applications, such as protein-protein interaction prediction, has gained significant traction in recent decades. However, explainability is a key aspect of using machine learning as a tool for scientific discovery. Explainable artificial intelligence approaches help clarify algorithmic mechanisms and identify potential bias in the data. Given the complexity of the biomedical domain, explanations should be grounded in domain knowledge which can be achieved by using ontologies and knowledge graphs. These knowledge graphs express knowledge about a domain by capturing different perspectives of the representation of real-world entities. However, the most popular way to explore knowledge graphs with machine learning is through using embeddings, which are not explainable. As an alternative, knowledge graph-based semantic similarity offers the advantage of being explainable. Additionally, similarity can be computed to capture different semantic aspects within the knowledge graph and increasing the explainability of predictive approaches. We propose a novel method to generate explainable vector representations, KGsim2vec, that uses aspect-oriented semantic similarity features to represent pairs of entities in a knowledge graph. Our approach employs a set of machine learning models, including decision trees, genetic programming, random forest and eXtreme gradient boosting, to predict relations between entities. The experiments reveal that considering multiple semantic aspects when representing the similarity between two entities improves explainability and predictive performance. KGsim2vec performs better than black-box methods based on knowledge graph embeddings or graph neural networks. Moreover, KGsim2vec produces global models that can capture biological phenomena and elucidate data biases.

Multi-domain knowledge graph embeddings for gene-disease association prediction.

BACKGROUND: Predicting gene-disease associations typically requires exploring diverse sources of information as well as sophisticated computational approaches. Knowledge graph embeddings can help tackle these challenges by creating representations of genes and diseases based on the scientific knowledge described in ontologies, which can then be explored by machine learning algorithms. However, state-of-the-art knowledge graph embeddings are produced over a single ontology or multiple but disconnected ones, ignoring the impact that considering multiple interconnected domains can have on complex tasks such as gene-disease association prediction. RESULTS: We propose a novel approach to predict gene-disease associations using rich semantic representations based on knowledge graph embeddings over multiple ontologies linked by logical definitions and compound ontology mappings. The experiments showed that considering richer knowledge graphs significantly improves gene-disease prediction and that different knowledge graph embeddings methods benefit more from distinct types of semantic richness. CONCLUSIONS: This work demonstrated the potential for knowledge graph embeddings across multiple and interconnected biomedical ontologies to support gene-disease prediction. It also paved the way for considering other ontologies or tackling other tasks where multiple perspectives over the data can be beneficial. All software and data are freely available.

A Collection of Benchmark Data Sets for Knowledge Graph-based Similarity in the Biomedical Domain.

The ability to compare entities within a knowledge graph is a cornerstone technique for several applications, ranging from the integration of heterogeneous data to machine learning. It is of particular importance in the biomedical domain, where semantic similarity can be applied to the prediction of protein-protein interactions, associations between diseases and genes, cellular localization of proteins, among others. In recent years, several knowledge graph-based semantic similarity measures have been developed, but building a gold standard data set to support their evaluation is non-trivial. We present a collection of 21 benchmark data sets that aim at circumventing the difficulties in building benchmarks for large biomedical knowledge graphs by exploiting proxies for biomedical entity similarity. These data sets include data from two successful biomedical ontologies, Gene Ontology and Human Phenotype Ontology, and explore proxy similarities calculated based on protein sequence similarity, protein family similarity, protein-protein interactions and phenotype-based gene similarity. Data sets have varying sizes and cover four different species at different levels of annotation completion. For each data set, we also provide semantic similarity computations with state-of-the-art representative measures. Database URL: https://github.com/liseda-lab/kgsim-benchmark.

Evolving knowledge graph similarity for supervised learning in complex biomedical domains.

BACKGROUND: In recent years, biomedical ontologies have become important for describing existing biological knowledge in the form of knowledge graphs. Data mining approaches that work with knowledge graphs have been proposed, but they are based on vector representations that do not capture the full underlying semantics. An alternative is to use machine learning approaches that explore semantic similarity. However, since ontologies can model multiple perspectives, semantic similarity computations for a given learning task need to be fine-tuned to account for this. Obtaining the best combination of semantic similarity aspects for each learning task is not trivial and typically depends on expert knowledge. RESULTS: We have developed a novel approach, evoKGsim, that applies Genetic Programming over a set of semantic similarity features, each based on a semantic aspect of the data, to obtain the best combination for a given supervised learning task. The approach was evaluated on several benchmark datasets for protein-protein interaction prediction using the Gene Ontology as the knowledge graph to support semantic similarity, and it outperformed competing strategies, including manually selected combinations of semantic aspects emulating expert knowledge. evoKGsim was also able to learn species-agnostic models with different combinations of species for training and testing, effectively addressing the limitations of predicting protein-protein interactions for species with fewer known interactions. CONCLUSIONS: evoKGsim can overcome one of the limitations in knowledge graph-based semantic similarity applications: the need to expertly select which aspects should be taken into account for a given application. Applying this methodology to protein-protein interaction prediction proved successful, paving the way to broader applications.