Knowledge organization systems, such as ontologies and knowledge graphs, are essential for organizing biomedical and clinical information and data. However, the growing volume of available scientific literature raises challenges in their maintenance. Entity linking approaches assist humans in curation by mapping entities described in text to entries of the knowledge organization systems, but their lack of coverage originates unlinkable or NIL entities. Besides, the state-of-the-art depends on deep learning models trained on large amounts of human-annotated data, which is hard to acquire. The present research work focuses on tackling these limitations of human-annotated data in the biomedical entity linking task. First, it addresses the lack of coverage of biomedical knowledge organization systems by using relation extraction to find missing relations and focusing on the problem of the NIL entities. Relation extraction increases the semantic information available for graph-based entity linking approaches (REEL), and focusing on the partial mapping of NIL entities (i.e. NIL entity linking) also improves the performance of such approaches (NILINKER). Second, the research work proposes a new deep learning model trained on a large-scale training dataset generated through automatic methods. The model is part of the pipeline X-Linker integrating different entity linking models, providing more flexibility and performance. The pipeline achieved state-of-the-art performance in the biomedical entity linking task in several datasets (BC5CDR-Disease, BioRED-Chemical, NCBI Disease). The described approaches and several others focusing on related tasks, such as named entity recognition, text classification, and recommendation of biomedical entities, were applied to several case studies, including competitions, workshops and challenges.

Background: Complex diseases such as neurodevelopmental disorders (NDDs) exhibit multiple etiologies. The multi-etiological nature of complex-diseases emerges from distinct but functionally similar group of genes. Different diseases sharing genes of such groups show related clinical outcomes that further restrict our understanding of disease mechanisms, thus, limiting the applications of personalized medicine approaches to complex genetic disorders. Results: Here, we present an interactive and user-friendly application, called DGH-GO. DGH-GO allows biologists to dissect the genetic heterogeneity of complex diseases by stratifying the putative disease-causing genes into clusters that may contribute to distinct disease outcome development. It can also be used to study the shared etiology of complex-diseases. DGH-GO creates a semantic similarity matrix for the input genes by using Gene Ontology (GO). The resultant matrix can be visualized in 2D plots using different dimension reduction methods (T-SNE, Principal component analysis, umap and Principal coordinate analysis). In the next step, clusters of functionally similar genes are identified from genes functional similarities assessed through GO. This is achieved by employing four different clustering methods (K-means, Hierarchical, Fuzzy and PAM). The user may change the clustering parameters and explore their effect on stratification immediately. DGH-GO was applied to genes disrupted by rare genetic variants in Autism Spectrum Disorder (ASD) patients. The analysis confirmed the multi-etiological nature of ASD by identifying four clusters of genes that were enriched for distinct biological mechanisms and clinical outcome. In the second case study, the analysis of genes shared by different NDDs showed that genes causing multiple disorders tend to aggregate in similar clusters, indicating a possible shared etiology. Conclusion: DGH-GO is a user-friendly application that allows biologists to study the multi-etiological nature of complex diseases by dissecting their genetic heterogeneity. In summary, functional similarities, dimension reduction and clustering methods, coupled with interactive visualization and control over analysis allows biologists to explore and analyze their datasets without requiring expert knowledge on these methods. The source code of proposed application is available at https://github.com/Muh-Asif/DGH-GO