A Unified Architecture for Biomedical Search Engines Based on Semantic Web Technologies

Jalali, Vahid; Borujerdi, Mohammad Reza Matash

doi:10.1007/s10916-009-9360-z

Cited by 9 publications

(2 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Medical Knowledge Graphs are widely used in automatic diagnosis systems [1], professional medical search engines [2], answering of medical questions [3], and other applications. However, most Medical Knowledge Graphs on existing networks, such as PHARE [4], are manually established by domain experts.…”

Section: Introductionmentioning

confidence: 99%

Medical Knowledge Graph Completion Based on Word Embeddings

Gao

Lü

Chen³

2022

Information

View full text Add to dashboard Cite

The aim of Medical Knowledge Graph Completion is to automatically predict one of three parts (head entity, relationship, and tail entity) in RDF triples from medical data, mainly text data. Following their introduction, the use of pretrained language models, such as Word2vec, BERT, and XLNET, to complete Medical Knowledge Graphs has become a popular research topic. The existing work focuses mainly on relationship completion and has rarely solved entities and related triples. In this paper, a framework to predict RDF triples for Medical Knowledge Graphs based on word embeddings (named PTMKG-WE) is proposed, for the specific use for the completion of entities and triples. The framework first formalizes existing samples for a given relationship from the Medical Knowledge Graph as prior knowledge. Second, it trains word embeddings from big medical data according to prior knowledge through Word2vec. Third, it can acquire candidate triples from word embeddings based on analogies from existing samples. In this framework, the paper proposes two strategies to improve the relation features. One is used to refine the relational semantics by clustering existing triple samples. Another is used to accurately embed the expression of the relationship through means of existing samples. These two strategies can be used separately (called PTMKG-WE-C and PTMKG-WE-M, respectively), and can also be superimposed (called PTMKG-WE-C-M) in the framework. Finally, in the current study, PubMed data and the National Drug File-Reference Terminology (NDF-RT) were collected, and a series of experiments was conducted. The experimental results show that the framework proposed in this paper and the two improvement strategies can be used to predict new triples for Medical Knowledge Graphs, when medical data are sufficiently abundant and the Knowledge Graph has appropriate prior knowledge. The two strategies designed to improve the relation features have a significant effect on the lifting precision, and the superposition effect becomes more obvious. Another conclusion is that, under the same parameter setting, the semantic precision of word embedding can be improved by extending the breadth and depth of data, and the precision of the prediction framework in this paper can be further improved in most cases. Thus, collecting and training big medical data is a viable method to learn more useful knowledge.

show abstract

Section: Introductionmentioning

confidence: 99%

Medical Knowledge Graph Completion Based on Word Embeddings

Gao

Lü

Chen³

2022

Information

View full text Add to dashboard Cite

show abstract

“…On the other hand, Semantic Technologies have been pointed out as the future of the Web [21] and a new way to support knowledge [22,23] in a wide range of domains [24], including medicine and biomedical domains [25][26][27]. Semantic Technologies, based on ontologies [28], provide a common framework that enables data integration, sharing and reusing from multiple sources.…”

Section: Introductionmentioning

confidence: 99%

SeDeLo: Using Semantics and Description Logics to Support Aided Clinical Diagnosis

et al. 2011

View full text Add to dashboard Cite

Automated medical diagnosis systems based on knowledge-oriented descriptions have gained momentum with the emergence of semantic descriptions. The objective of this paper is to propose a normalized design that solves some of the problems which have been detected by authors in previous tools. The authors bring together two different technologies to develop a new clinical decision support system: description logics aimed at developing inference systems to improve decision support for the prevention, treatment and management of illness and semantic technologies. Because of its new design, the system is capable of obtaining improved diagnostics compared with previous efforts. However, this evaluation is more focused in the computational performance, giving as result that description logics is a good solution with small data sets. In this paper, we provide a well-structured ontology for automated diagnosis in the medical field and a three-fold formalization based on Description Logics with the use of Semantic Web technologies.

show abstract

Discovering new PI3Kα inhibitors with a strategy of combining ligand-based and structure-based virtual screening

2018

J Comput Aided Mol Des

View full text Add to dashboard Cite

PI3Kα is a promising drug target for cancer chemotherapy. In this paper, we report a strategy of combing ligand-based and structure-based virtual screening to identify new PI3Kα inhibitors. First, naïve Bayesian (NB) learning models and a 3D-QSAR pharmacophore model were built based upon known PI3Kα inhibitors. Then, the SPECS library was screened by the best NB model. This resulted in virtual hits, which were validated by matching the structures against the pharmacophore models. The pharmacophore matched hits were then docked into PI3Kα crystal structures to form ligand-receptor complexes, which are further validated by the Glide-XP program to result in structural validated hits. The structural validated hits were examined by PI3Kα inhibitory assay. With this screening protocol, ten PI3Kα inhibitors with new scaffolds were discovered with IC values ranging 0.44-31.25 μM. The binding affinities for the most active compounds 33 and 74 were estimated through molecular dynamics simulations and MM-PBSA analyses.

show abstract

A Unified Architecture for Biomedical Search Engines Based on Semantic Web Technologies

Cited by 9 publications

References 20 publications

Medical Knowledge Graph Completion Based on Word Embeddings

Medical Knowledge Graph Completion Based on Word Embeddings

SeDeLo: Using Semantics and Description Logics to Support Aided Clinical Diagnosis

Discovering new PI3Kα inhibitors with a strategy of combining ligand-based and structure-based virtual screening

Contact Info

Product

Resources

About