Biological applications of knowledge graph embedding models

Mohamed, Sameh K.; Nounu, Aayah; Nováček, Vít

doi:10.1093/bib/bbaa012

Cited by 89 publications

(56 citation statements)

References 93 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In recent years, relational learning models (RLMs) became a popular method in many bioinformatics predictive tasks where they outperform other state-of-the-art approaches in various tasks [24]. They use knowledge graphs to model complex biological systems and they then learn feature representations of entities and relationships to provide accurate and scalable predictions.…”

Section: Relational Learning In Bioinformaticsmentioning

confidence: 99%

“…Despite the high coverage of biological entries in the BioKG, it still suffers from sparsity of data due to the unbalanced representation biological entities in open biological databases [24]. This unbalance is a result of the unbalanced research focus on specific entities, where some biological entities which are related to popular phenomenons are heavily studied, therefore, have richer database entries and annotations.…”

Section: Limitations and Potential Issuesmentioning

confidence: 99%

“…In each of these tasks, KGs were used to model biological networks, and then relational learning models were used to provide new predictions. Despite the effectiveness of such approaches [24], there is a lack of open biological knowledge graphs to support them. Furthermore, current approaches rely on building customized knowledge graph by parsing and transforming open biological databases [24,26,29].…”

Section: Introductionmentioning

confidence: 99%

“…The Bio2RDF project consists of a set of web parsers for open biological data which consume, process and convert these database to RDF graphs. Despite the high coverage of its generated RDF graphs, they are not commonly used in the different predictive biological task by relational learning models [24]. One of the main reasons is the large volume of metadata information stored in these graphs which often decreases the predictive accuracy of relational models.…”

Section: Introductionmentioning

confidence: 99%

“…The current studies of the applications of relational leaning models in biological settings commonly involve building customized biological graphs from open biological databases [24,26,29]. This process involves repeated procedures such as parsing the different database sources into intermediate formats then merging these format into knowledge graphs.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

BioKG

Walsh

Mohamed

Nováček

2020

Proceedings of the 29th ACM International Conference on Information &Amp; Knowledge Management

Self Cite

View full text Add to dashboard Cite

Knowledge graphs became a popular means for modelling complex biological systems where they model the interactions between biological entities and their effects on the biological system. They also provide support for relational learning models which are known to provide highly scalable and accurate predictions of associations between biological entities. Despite the success of the combination of biological knowledge graph and relation learning models in biological predictive tasks, there is a lack of unified biological knowledge graph resources. This forced all current efforts and studies for applying a relational learning model on biological data to compile and build biological knowledge graphs from open biological databases. This process is often performed inconsistently across such efforts, especially in terms of choosing the original resources, aligning identifiers of the different databases and assessing the quality of included data. To make relational learning on biomedical data more standardised and reproducible, we propose a new biological knowledge graph which provides a compilation of curated relational data from open biological databases in a unified format with common, interlinked identifiers. We also provide a new module for mapping identifiers and labels from different databases which can be used to align our knowledge graph with biological data from other heterogeneous sources. Finally, to illustrate practical relevance of our work, we provide a set of benchmarks based on the presented data that can be used to train and assess the relational learning models in various tasks related to pathway and drug discovery.

show abstract

Section: Relational Learning In Bioinformaticsmentioning

confidence: 99%

Section: Limitations and Potential Issuesmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

BioKG

Walsh

Mohamed

Nováček

2020

Proceedings of the 29th ACM International Conference on Information &Amp; Knowledge Management

Self Cite

View full text Add to dashboard Cite

show abstract

Embedding knowledge graph of patent metadata to measure knowledge proximity

Siddharth

Luo

2023

Asso for Info Science & Tech

View full text Add to dashboard Cite

Knowledge proximity refers to the strength of association between any two entities in a structural form that embodies certain aspects of a knowledge base. In this work, we operationalize knowledge proximity within the context of the US Patent Database (knowledge base) using a knowledge graph (structural form) named “PatNet” built using patent metadata, including citations, inventors, assignees, and domain classifications. We train various graph embedding models using PatNet to obtain the embeddings of entities and relations. The cosine similarity between the corresponding (or transformed) embeddings of entities denotes the knowledge proximity between these. We compare the embedding models in terms of their performances in predicting target entities and explaining domain expansion profiles of inventors and assignees. We then apply the embeddings of the best‐preferred model to associate homogeneous (e.g., patent–patent) and heterogeneous (e.g., inventor–assignee) pairs of entities.

show abstract

Deep learning for drug repurposing: Methods, databases, and applications

Pan

Lin

Cao

et al. 2022

WIREs Comput Mol Sci

View full text Add to dashboard Cite

Drug development is time-consuming and expensive. Repurposing existing drugs for new therapies is an attractive solution that accelerates drug development at reduced experimental costs, specifically for Coronavirus Disease 2019 (COVID-19), an infectious disease caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). However, comprehensively obtaining and productively integrating available knowledge and big biomedical data to effectively advance deep learning models is still challenging for drug repurposing in other complex diseases. In this review, we introduce guidelines on how to utilize deep learning methodologies and tools for drug repurposing. We first summarized the commonly used bioinformatics and pharmacogenomics databases for drug repurposing. Next, we discuss recently developed sequence-based and graph-based representation approaches as well as state-of-the-art deep learning-based methods. Finally, we present applications of drug repurposing to fight the COVID-19 pandemic, and outline its future challenges.

show abstract

Biological applications of knowledge graph embedding models

Cited by 89 publications

References 93 publications

BioKG

BioKG

Embedding knowledge graph of patent metadata to measure knowledge proximity

Deep learning for drug repurposing: Methods, databases, and applications

Contact Info

Product

Resources

About