Biomedical Entities Research Articles

ABEE: automated bio entity extraction from biomedical text documents

PurposeThe purpose of this study was to design a multitask learning model so that biomedical entities can be extracted without having any ambiguity from biomedical texts.Design/methodology/approachIn the proposed automated bio entity extraction (ABEE) model, a multitask learning model has been introduced with the combination of single-task learning models. Our model used Bidirectional Encoder Representations from Transformers to train the single-task learning model. Then combined model's outputs so that we can find the verity of entities from biomedical text.FindingsThe proposed ABEE model targeted unique gene/protein, chemical and disease entities from the biomedical text. The finding is more important in terms of biomedical research like drug finding and clinical trials. This research aids not only to reduce the effort of the researcher but also to reduce the cost of new drug discoveries and new treatments.Research limitations/implicationsAs such, there are no limitations with the model, but the research team plans to test the model with gigabyte of data and establish a knowledge graph so that researchers can easily estimate the entities of similar groups.Practical implicationsAs far as the practical implication concerned, the ABEE model will be helpful in various natural language processing task as in information extraction (IE), it plays an important role in the biomedical named entity recognition and biomedical relation extraction and also in the information retrieval task like literature-based knowledge discovery.Social implicationsDuring the COVID-19 pandemic, the demands for this type of our work increased because of the increase in the clinical trials at that time. If this type of research has been introduced previously, then it would have reduced the time and effort for new drug discoveries in this area.Originality/valueIn this work we proposed a novel multitask learning model that is capable to extract biomedical entities from the biomedical text without any ambiguity. The proposed model achieved state-of-the-art performance in terms of precision, recall and F1 score.

Ontology characterization, enrichment analysis, and similarity calculation-based evaluation of disease-syndrome-formula associations by applying SoFDA.

Clinical symptom-based diagnosis and therapy play a crucial role in personalized medicine and drug discovery. The syndromes, distinctive groups of clinical symptoms summarized by traditional Chinese medicine (TCM) theories and clinical experiences, are used as the core diagnostic criteria and therapeutic guidance in TCM. However, there is still a lack of standardized data, information, and intrinsic molecular basis to help TCM syndromes better classify diseases and guide tailored medications. To address this problem, we built the first integrated web platform, SoFDA (http://www.tcmip.cn/Syndrome/front/), with a curated ontology of 319 TCM syndromes, 8045 diseases, and 1359 TCM herbal formulas and their relationships with genes, diseases, and formulas. This platform proposed an association measurement by calculating Jaccard/Cosine similarities between TCM syndromes and their related biomedical entities with case and control validations. On this basis, the SoFDA platform enables biomedical and pharmaceutical scientists to rank and filter the most promising associations for disease diagnosis and tailored interventions. Conversely, the targeted gene sets and symptom sets can also be associated with TCM syndromes, formulas, and diseases for function illustration. Notably, SoFDA explores the multi-way associations among diseases, TCM syndromes, symptom genes, herbal formulas, drug targets, and pathways in heterogeneous biomedical networks with lots of customization. The protocol here implements all the analyses above using the SoFDA platform. Collectively, SoFDA may provide insights into the biological basis of disease-specific TCM syndromes and the underlying molecular mechanisms, as well as a tailored treatment for single or multiple symptoms within a syndrome.

Negation-based transfer learning for improving biomedical Named Entity Recognition and Relation Extraction

Background and Objectives:Named Entity Recognition (NER) and Relation Extraction (RE) are two of the most studied tasks in biomedical Natural Language Processing (NLP). The detection of specific terms and entities and the relationships between them are key aspects for the development of more complex automatic systems in the biomedical field. In this work, we explore transfer learning techniques for incorporating information about negation into systems performing NER and RE. The main purpose of this research is to analyse to what extent the successful detection of negated entities in separate tasks helps in the detection of biomedical entities and their relationships. Methods:Three neural architectures are proposed in this work, all of them mainly based on Bidirectional Long Short-Term Memory (Bi-LSTM) networks and Conditional Random Fields (CRFs). While the first architecture is devoted to detecting triggers and scopes of negated entities in any domain, two specific models are developed for performing isolated NER tasks and joint NER and RE tasks in the biomedical domain. Then, weights related to negation detection learned by the first architecture are incorporated into those last models. Two different languages, Spanish and English, are taken into account in the experiments. Results:Performance of the biomedical models is analysed both when the weights of the neural networks are randomly initialized, and when weights from the negation detection model are incorporated into them. Improvements of around 3.5% of F-Measure in the English language and more than 7% in the Spanish language are achieved in the NER task, while the NER+RE task increases F-Measure scores by more than 13% for the NER submodel and around 2% for the RE submodel. Conclusions:The obtained results allow us to conclude that negation-based transfer learning techniques are appropriate for performing biomedical NER and RE tasks. These results highlight the importance of detecting negation for improving the identification of biomedical entities and their relationships. The explored techniques show robustness by maintaining consistent results and improvements across different tasks and languages.

A Comprehensive Evaluation of Biomedical Entity Linking Models.

Biomedical entity linking (BioEL) is the process of connecting entities referenced in documents to entries in biomedical databases such as the Unified Medical Language System (UMLS) or Medical Subject Headings (MeSH). The study objective was to comprehensively evaluate nine recent state-of-the-art biomedical entity linking models under a unified framework. We compare these models along axes of (1) accuracy, (2) speed, (3) ease of use, (4) generalization, and (5) adaptability to new ontologies and datasets. We additionally quantify the impact of various preprocessing choices such as abbreviation detection. Systematic evaluation reveals several notable gaps in current methods. In particular, current methods struggle to correctly link genes and proteins and often have difficulty effectively incorporating context into linking decisions. To expedite future development and baseline testing, we release our unified evaluation framework and all included models on GitHub at https://github.com/davidkartchner/biomedical-entity-linking.

Improving biomedical named entity recognition through transfer learning and asymmetric tri-training

Today, electronic health records have turned into prime sources of information for physicians looking after their patients. EHRs and computerized patient data resources have expedited the accelerated discovery of formerly obscure biomedical and clinical information. Because of the lengthy, error-prone, non-scalable, and expensive manual abstraction process, natural language processing (NLP) procedures are being wielded more and more in biomedical and clinical fields. One of the building blocks of all NLP systems, Named Entity Recognition (NER) is considered a sub-activity of information retrieval. To extract biomedical knowledge from electronic health records, a prerequisite is the efficient recognition of biomedical entities. Deep-learning techniques have gained more and more consideration recently for the above-mentioned task. Notwithstanding, these methods are based on high-caliber, high-cost, labeled data. In this work, a biomedical-named entity recognition model based on transfer learning and asymmetric tri-training is proposed to diminish the limited annotated data problem in the biomedical-named entity recognition domain. The proposed model showed a significant improvement of more than 9% over the baseline BiLSTM-CRF model in the exact F1 scores on four different datasets considered in this work.

Hetnet connectivity search provides rapid insights into how biomedical entities are related.

Hetnets, short for "heterogeneous networks," contain multiple node and relationship types and offer a way to encode biomedical knowledge. One such example, Hetionet, connects 11 types of nodes-including genes, diseases, drugs, pathways, and anatomical structures-with over 2 million edges of 24 types. Previous work has demonstrated that supervised machine learning methods applied to such networks can identify drug repurposing opportunities. However, a training set of known relationships does not exist for many types of node pairs, even when it would be useful to examine how nodes of those types are meaningfully connected. For example, users may be curious about not only how metformin is related to breast cancer but also how a given gene might be involved in insomnia. We developed a new procedure, termed hetnet connectivity search, that proposes important paths between any 2 nodes without requiring a supervised gold standard. The algorithm behind connectivity search identifies types of paths that occur more frequently than would be expected by chance (based on node degree alone). Several optimizations were required to precompute significant instances of node connectivity at the scale of large knowledge graphs. We implemented the method on Hetionet and provide an online interface at https://het.io/search. We provide an open-source implementation of these methods in our new Python package named hetmatpy.

Klarigi: Characteristic explanations for semantic biomedical data

Annotation of biomedical entities with ontology classes provides for formal semantic analysis and mobilisation of background knowledge in determining their relationships. To date, enrichment analysis has been routinely employed to identify classes that are over-represented in annotations across sets of groups, such as biosample gene expression profiles or patient phenotypes, and is useful for a range of tasks including differential diagnosis and causative variant prioritisation. These approaches, however, usually consider only univariate relationships, make limited use of the semantic features of ontologies, and provide limited information and evaluation of the explanatory power of both singular and grouped candidate classes. Moreover, they are not designed to solve the problem of deriving cohesive, characteristic, and discriminatory sets of classes for entity groups. We have developed a new tool, called Klarigi, which introduces multiple scoring heuristics for identification of classes that are both compositional and discriminatory for groups of entities annotated with ontology classes. The tool includes a novel algorithm for derivation of multivariable semantic explanations for entity groups, makes use of semantic inference through live use of an ontology reasoner, and includes a classification method for identifying the discriminatory power of candidate sets, in addition to significance testing apposite to traditional enrichment approaches. We describe the design and implementation of Klarigi, including its scoring and explanation determination methods, and evaluate its use in application to two test cases with clinical significance, comparing and contrasting methods and results with literature-based and enrichment analysis methods. We demonstrate that Klarigi produces characteristic and discriminatory explanations for groups of biomedical entities in two settings. We also show that these explanations recapitulate and extend the knowledge held in existing biomedical databases and literature for several diseases. We conclude that Klarigi provides a distinct and valuable perspective on biomedical datasets when compared with traditional enrichment methods, and therefore constitutes a new method by which biomedical datasets can be explored, contributing to improved insight into semantic data.

Tracking biomedical articles along the translational continuum: a measure based on biomedical knowledge representation.

Keeping track of translational research is essential to evaluating the performance of programs on translational medicine. Despite several indicators in previous studies, a consensus measure is still needed to represent the translational features of biomedical research at the article level. In this study, we first trained semantic representations of biomedical entities and documents (i.e., bio-entity2vec and bio-doc2vec) based on over 30 million PubMed articles. With these vectors, we then developed a new measure called Translational Progression (TP) for tracking biomedical articles along the translational continuum. We validated the effectiveness of TP from two perspectives (Clinical trial phase identification and ACH classification), which showed excellent consistency between TP and other indicators. Meanwhile, TP has several advantages. First, it can track the degree of translation of biomedical research dynamically and in real-time. Second, it is straightforward to interpret and operationalize. Third, it doesn't require labor-intensive MeSH labeling and it is suitable for big scholarly data as well as papers that are not indexed in PubMed. In addition, we examined the translational progressions of biomedical research from three dimensions (including overall distribution, time, and research topic), which revealed three significant findings. The proposed measure in this study could be used by policymakers to monitor biomedical research with high translational potential in real-time and make better decisions. It can also be adopted and improved for other domains, such as physics or computer science, to assess the application value of scientific discoveries.

Unifying the identification of biomedical entities with the Bioregistry

The standardized identification of biomedical entities is a cornerstone of interoperability, reuse, and data integration in the life sciences. Several registries have been developed to catalog resources maintaining identifiers for biomedical entities such as small molecules, proteins, cell lines, and clinical trials. However, existing registries have struggled to provide sufficient coverage and metadata standards that meet the evolving needs of modern life sciences researchers. Here, we introduce the Bioregistry, an integrative, open, community-driven metaregistry that synthesizes and substantially expands upon 23 existing registries. The Bioregistry addresses the need for a sustainable registry by leveraging public infrastructure and automation, and employing a progressive governance model centered around open code and open data to foster community contribution. The Bioregistry can be used to support the standardized annotation of data, models, ontologies, and scientific literature, thereby promoting their interoperability and reuse. The Bioregistry can be accessed through https://bioregistry.io and its source code and data are available under the MIT and CC0 Licenses at https://github.com/biopragmatics/bioregistry.

Biomedical named entity recognition with the combined feature attention and fully-shared multi-task learning

BackgroundBiomedical named entity recognition (BioNER) is a basic and important task for biomedical text mining with the purpose of automatically recognizing and classifying biomedical entities. The performance of BioNER systems directly impacts downstream applications. Recently, deep neural networks, especially pre-trained language models, have made great progress for BioNER. However, because of the lack of high-quality and large-scale annotated data and relevant external knowledge, the capability of the BioNER system remains limited.ResultsIn this paper, we propose a novel fully-shared multi-task learning model based on the pre-trained language model in biomedical domain, namely BioBERT, with a new attention module to integrate the auto-processed syntactic information for the BioNER task. We have conducted numerous experiments on seven benchmark BioNER datasets. The proposed best multi-task model obtains F1 score improvements of 1.03% on BC2GM, 0.91% on NCBI-disease, 0.81% on Linnaeus, 1.26% on JNLPBA, 0.82% on BC5CDR-Chemical, 0.87% on BC5CDR-Disease, and 1.10% on Species-800 compared to the single-task BioBERT model.ConclusionThe results demonstrate our model outperforms previous studies on all datasets. Further analysis and case studies are also provided to prove the importance of the proposed attention module and fully-shared multi-task learning method used in our model.

Semisupervised neural biomedical sense disambiguation approach for aspect-based sentiment analysis on social networks

Patient narratives on social networks contain large amounts of objective information, such as the descriptions of examinations and interventions. Sentiment analysis (SA) models are mostly used to evaluate the conveyed sentiments by patients in these narratives to assess positive or negative clinical outcomes or to judge the impact of a drug or a medical condition. To date, many state-of-the-art SA models often result in false assessment coverage due to the natural medical entities recognition deficiency and ambiguity problem. In this work, we propose a semisupervised-based neural sense disambiguation approach that helps to substantially define ambiguities, their levels, and the relational mappings between biomedical targets and dependencies for accurate aspect-based sentiment prediction. Three main modules are proposed: (1) generate a sentiment value based on extracted concepts and their synsets, (2) encode the representations of the contextual senses and sentiment inputs, and (3) estimate an aspect-based sentiment weight based on the context-dependency sentiment units vs. the biomedical sense. Both intrinsic and extrinsic evaluation proved how the proposed method have succeeded in pruning contextual sense feature generation and showed a strong agreement for biomedical data property parameterization and ambiguity type extraction. Thus, the model offers a significant rate of discrimination of biomedical natural concept senses by critically analysing constraints from conjunctions of positive or negative contextual semantics. A total of 21% of the vocabulary is drug names, 11% is a multiword drug reaction expressions, 7% is disease symptoms, and 5% is disease-related concepts such as symptoms and related therapy terms. Furthermore, the experiments on a multisource data from Twitter and health-related forums have overshadowed sentiment assessment and achieved an accuracy of 0.91 regarding concepts-based biomedical aspects. These results provide fresh insights into how to investigate biomedical knowledge, e.g., Medical Subject Headings (MeSH) and PubMed, to clarify the correspondence of various biomedical descriptive entities, definitions, and data properties from shared medication-related content.

An automatic hypothesis generation for plausible linkage between xanthium and diabetes

There has been a significant increase in text mining implementation for biomedical literature in recent years. Previous studies introduced the implementation of text mining and literature-based discovery to generate hypotheses of potential candidates for drug development. By conducting a hypothesis-generation step and using evidence from published journal articles or proceedings, previous studies have managed to reduce experimental time and costs. First, we applied the closed discovery approach from Swanson’s ABC model to collect publications related to 36 Xanthium compounds or diabetes. Second, we extracted biomedical entities and relations using a knowledge extraction engine, the Public Knowledge Discovery Engine for Java or PKDE4J. Third, we built a knowledge graph using the obtained bio entities and relations and then generated paths with Xanthium compounds as source nodes and diabetes as the target node. Lastly, we employed graph embeddings to rank each path and evaluated the results based on domain experts’ opinions and literature. Among 36 Xanthium compounds, 35 had direct paths to five diabetes-related nodes. We ranked 2,740,314 paths in total between 35 Xanthium compounds and three diabetes-related phrases: type 1 diabetes, type 2 diabetes, and diabetes mellitus. Based on the top five percentile paths, we concluded that adenosine, choline, beta-sitosterol, rhamnose, and scopoletin were potential candidates for diabetes drug development using natural products. Our framework for hypothesis generation employs a closed discovery from Swanson’s ABC model that has proven very helpful in discovering biological linkages between bio entities. The PKDE4J tools we used to capture bio entities from our document collection could label entities into five categories: genes, compounds, phenotypes, biological processes, and molecular functions. Using the BioPREP model, we managed to interpret the semantic relatedness between two nodes and provided paths containing valuable hypotheses. Lastly, using a graph-embedding algorithm in our path-ranking analysis, we exploited the semantic relatedness while preserving the graph structure properties.

Expanding a database-derived biomedical knowledge graph via multi-relation extraction from biomedical abstracts

BackgroundKnowledge graphs support biomedical research efforts by providing contextual information for biomedical entities, constructing networks, and supporting the interpretation of high-throughput analyses. These databases are populated via manual curation, which is challenging to scale with an exponentially rising publication rate. Data programming is a paradigm that circumvents this arduous manual process by combining databases with simple rules and heuristics written as label functions, which are programs designed to annotate textual data automatically. Unfortunately, writing a useful label function requires substantial error analysis and is a nontrivial task that takes multiple days per function. This bottleneck makes populating a knowledge graph with multiple nodes and edge types practically infeasible. Thus, we sought to accelerate the label function creation process by evaluating how label functions can be re-used across multiple edge types.ResultsWe obtained entity-tagged abstracts and subsetted these entities to only contain compounds, genes, and disease mentions. We extracted sentences containing co-mentions of certain biomedical entities contained in a previously described knowledge graph, Hetionet v1. We trained a baseline model that used database-only label functions and then used a sampling approach to measure how well adding edge-specific or edge-mismatch label function combinations improved over our baseline. Next, we trained a discriminator model to detect sentences that indicated a biomedical relationship and then estimated the number of edge types that could be recalled and added to Hetionet v1. We found that adding edge-mismatch label functions rarely improved relationship extraction, while control edge-specific label functions did. There were two exceptions to this trend, Compound-binds-Gene and Gene-interacts-Gene, which both indicated physical relationships and showed signs of transferability. Across the scenarios tested, discriminative model performance strongly depends on generated annotations. Using the best discriminative model for each edge type, we recalled close to 30% of established edges within Hetionet v1.ConclusionsOur results show that this framework can incorporate novel edges into our source knowledge graph. However, results with label function transfer were mixed. Only label functions describing very similar edge types supported improved performance when transferred. We expect that the continued development of this strategy may provide essential building blocks to populating biomedical knowledge graphs with discoveries, ensuring that these resources include cutting-edge results.

Comparison of biomedical relationship extraction methods and models for knowledge graph creation

Biomedical research is growing at such an exponential pace that scientists, researchers, and practitioners are no more able to cope with the amount of published literature in the domain. The knowledge presented in the literature needs to be systematized in such a way that claims and hypotheses can be easily found, accessed, and validated. Knowledge graphs can provide such a framework for semantic knowledge representation from literature. However, in order to build a knowledge graph, it is necessary to extract knowledge as relationships between biomedical entities and normalize both entities and relationship types. In this paper, we present and compare a few rule-based and machine learning-based (Naive Bayes, Random Forests as examples of traditional machine learning methods and DistilBERT, PubMedBERT, T5, and SciFive-based models as examples of modern deep learning transformers) methods for scalable relationship extraction from biomedical literature, and for the integration into the knowledge graphs. We examine how resilient are these various methods to unbalanced and fairly small datasets. Our experiments show that transformer-based models handle well both small (due to pre-training on a large dataset) and unbalanced datasets. The best performing model was the PubMedBERT-based model fine-tuned on balanced data, with a reported F1-score of 0.92. The distilBERT-based model followed with an F1-score of 0.89, performing faster and with lower resource requirements. BERT-based models performed better than T5-based generative models.

An explainable framework for drug repositioning from disease information network

Exploring efficient and high-accuracy computational drug repositioning methods has become a popular and attractive topic in drug development. This technology can systematically identify potential drug-disease interactions, which could greatly alleviate the pressures from the high cost and long period taken by traditional drug research and discovery. However, plenty of current computational drug repositioning approaches lack interpretability in predicting drug-disease associations, which will not be friendly to their subsequent in-depth research.To this end, we hereby propose a novel computational framework, called EDEN, for exploring explainable drug repositioning from the disease information network (DIN). EDEN is a graph neural network framework that learns the local semantics and global structure of the DIN, and models the drug-disease associations into the DIN by maximizing the mutual information of both and an end-to-end manner. In this way, the learned biomedical entity and link embeddings are enabled to retain the ability to drug repositioning with the semantical structure of external knowledge, thereby making interpretation possible. Meanwhile, we also propose a matching score based on the final embeddings to generate the predictive drug repositioning explanation. Empirical results on the real-world dataset show that EDEN outperforms other state-of-the-art baselines on most of the metrics. Further studies reveal the effectiveness of the explainability of our approach.

BertSRC: transformer-based semantic relation classification

The relationship between biomedical entities is complex, and many of them have not yet been identified. For many biomedical research areas including drug discovery, it is of paramount importance to identify the relationships that have already been established through a comprehensive literature survey. However, manually searching through literature is difficult as the amount of biomedical publications continues to increase. Therefore, the relation classification task, which automatically mines meaningful relations from the literature, is spotlighted in the field of biomedical text mining. By applying relation classification techniques to the accumulated biomedical literature, existing semantic relations between biomedical entities that can help to infer previously unknown relationships are efficiently grasped. To develop semantic relation classification models, which is a type of supervised machine learning, it is essential to construct a training dataset that is manually annotated by biomedical experts with semantic relations among biomedical entities. Any advanced model must be trained on a dataset with reliable quality and meaningful scale to be deployed in the real world and can assist biologists in their research. In addition, as the number of such public datasets increases, the performance of machine learning algorithms can be accurately revealed and compared by using those datasets as a benchmark for model development and improvement. In this paper, we aim to build such a dataset. Along with that, to validate the usability of the dataset as training data for relation classification models and to improve the performance of the relation extraction task, we built a relation classification model based on Bidirectional Encoder Representations from Transformers (BERT) trained on our dataset, applying our newly proposed fine-tuning methodology. In experiments comparing performance among several models based on different deep learning algorithms, our model with the proposed fine-tuning methodology showed the best performance. The experimental results show that the constructed training dataset is an important information resource for the development and evaluation of semantic relation extraction models. Furthermore, relation extraction performance can be improved by integrating our proposed fine-tuning methodology. Therefore, this can lead to the promotion of future text mining research in the biomedical field.

BERN2: an advanced neural biomedical named entity recognition and normalization tool.

In biomedical natural language processing, named entity recognition (NER) and named entity normalization (NEN) are key tasks that enable the automatic extraction of biomedical entities (e.g. diseases and drugs) from the ever-growing biomedical literature. In this article, we present BERN2 (Advanced Biomedical Entity Recognition and Normalization), a tool that improves the previous neural network-based NER tool by employing a multi-task NER model and neural network-based NEN models to achieve much faster and more accurate inference. We hope that our tool can help annotate large-scale biomedical texts for various tasks such as biomedical knowledge graph construction.Availability and implementationWeb service of BERN2 is publicly available at http://bern2.korea.ac.kr. We also provide local installation of BERN2 at https://github.com/dmis-lab/BERN2.Supplementary information Supplementary data are available at Bioinformatics online.

Beyond biomedical classifications: breast cancer experience in Brazil, 1990-2015.

The paper analyses illness experiences of breast cancer in women undergoing treatment at the Hospital of Cancer III of the National Institute of Cancer. It argues that part of the interviewed women's experience was constructed from the interaction between family coexistence and the mobilisation of different cultural meanings of the disease and femininity, negotiating senses for biomedical entities. The study results from a qualitative research of ethnographic inspiration that interviewed women undergoing treatment from breast cancer during 2015. It draws on the accounts to discuss the interaction of society with biomedical entities for the significance of cancer in Brazil between the 1990s and 2010s.

Biomedical Relation Extraction With Knowledge Graph-Based Recommendations.

Biomedical Relation Extraction (RE) systems identify and classify relations between biomedical entities to enhance our knowledge of biological and medical processes. Most state-of-the-art systems use deep learning approaches, mainly to target relations between entities of the same type, such as proteins or pharmacological substances. However, these systems are mostly restricted to what they directly identify on the text and ignore specialized domain knowledge bases, such as ontologies, that formalize and integrate biomedical information typically structured as direct acyclic graphs. On the other hand, Knowledge Graph (KG)-based recommendation systems already showed the importance of integrating KGs to add additional features to items. Typical systems have users as people and items that can range from movies to books, which people saw or read and classified according to their satisfaction rate. This work proposes to integrate KGs into biomedical RE through a recommendation model to further improve their range of action. We developed a new RE system, named K-BiOnt, by integrating a baseline state-of-the-art deep biomedical RE system with an existing KG-based recommendation state-of-the-art system. Our results show that adding recommendations from KG-based recommendation improves the system's ability to identify true relations that the baseline deep RE model could not extract from the text. The code supporting this system is available at https://github.com/lasigeBioTM/K-BiOnt.

KG-Predict: A knowledge graph computational framework for drug repurposing

The emergence of large-scale phenotypic, genetic, and other multi-model biochemical data has offered unprecedented opportunities for drug discovery including drug repurposing. Various knowledge graph-based methods have been developed to integrate and analyze complex and heterogeneous data sources to find new therapeutic applications for existing drugs. However, existing methods have limitations in modeling and capturing context-sensitive inter-relationships among tens of thousands of biomedical entities. In this paper, we developed KG-Predict: a knowledge graph computational framework for drug repurposing. We first integrated multiple types of entities and relations from various genotypic and phenotypic databases to construct a knowledge graph termed GP-KG. GP-KG was composed of 1,246,726 associations between 61,146 entities. KG-Predict then aggregated the heterogeneous topological and semantic information from GP-KG to learn low-dimensional representations of entities and relations, and further utilized these representations to infer new drug–disease interactions. In cross-validation experiments, KG-Predict achieved high performances [AUROC (the area under receiver operating characteristic) = 0.981, AUPR (the area under precision–recall) = 0.409 and MRR (the mean reciprocal rank) = 0.261], outperforming other state-of-art graph embedding methods. We applied KG-Predict in identifying novel repositioned candidate drugs for Alzheimer’s disease (AD) and showed that KG-Predict prioritized both FDA-approved and active clinical trial anti-AD drugs among the top (AUROC = 0.868 and AUPR = 0.364).