Identifying disease trajectories with predicate information from a knowledge graph

Vlietstra, Wytze J.; Vos, Rein; Akker, Marjan van den; Mulligen, Erik M. van; Kors, Jan A.

doi:10.1186/s13326-020-00228-8

Cited by 6 publications

(6 citation statements)

References 60 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In particular, the proposed methods can be employed in discovering disease trajectories, which can reveal disease correlations and temporal disease progression, thus equipping clinicians with tools for predicting and preventing future complications in individual patients [ 46 ]. Previous studies have based their solutions for discovering disease trajectories on statistical analysis [ 47 ] and knowledge graphs [ 48 ]. Both approaches have their limitations: while the former approach is prone to statistical bias, the latter is not scalable and requires significant expert input.…”

Section: Discussionmentioning

confidence: 99%

PGraphD*: Methods for Drift Detection and Localisation Using Deep Learning Modelling of Business Processes

Hanga

Kovalchuk

Gaber

2022

Entropy

View full text Add to dashboard Cite

This paper presents a set of methods, jointly called PGraphD*, which includes two new methods (PGraphDD-QM and PGraphDD-SS) for drift detection and one new method (PGraphDL) for drift localisation in business processes. The methods are based on deep learning and graphs, with PGraphDD-QM and PGraphDD-SS employing a quality metric and a similarity score for detecting drifts, respectively. According to experimental results, PGraphDD-SS outperforms PGraphDD-QM in drift detection, achieving an accuracy score of 100% over the majority of synthetic logs and an accuracy score of 80% over a complex real-life log. Furthermore, PGraphDD-SS detects drifts with delays that are 59% shorter on average compared to the best performing state-of-the-art method.

show abstract

Section: Discussionmentioning

confidence: 99%

PGraphD*: Methods for Drift Detection and Localisation Using Deep Learning Modelling of Business Processes

Hanga

Kovalchuk

Gaber

2022

Entropy

View full text Add to dashboard Cite

show abstract

“…Apart from DIAMOnD and the graphlets, the disease gene identification methods tested by us were trained and evaluated using the supervised learning algorithms that were used in the original studies. These are: logistic regression (LR) (used by Agrawal et al [ 35 ] and by Ristoski et al [ 36 ]), support-vector machines (SVM) (used by Peng et al [ 37 ]), decision trees (DT) (used by Ristoski et al [ 36 ]), and random forest (RF) (used by Vlietstra et al [ 19 ]). We excluded the K-nearest neighbour classifiers used by Xu et al [ 38 ], Ristoski et al [ 36 ], and Milenković et al [ 39 ] due to their limited ability to rank, often leading to tied ranks for genes.…”

Section: Methodsmentioning

confidence: 99%

“…Predicates between genes have not yet been used for disease gene identification, but previous research has leveraged predicates and their directional information from protein knowledge graphs to improve performance for drug efficacy screening and identification of disease trajectories [ 17 , 19 ].…”

Section: Methodsmentioning

confidence: 99%

“…(used by Ristoski et al [36]), and random forest (RF) (used by Vlietstra et al [19]). We excluded the K-nearest neighbour classifiers used by Xu et al [38], Ristoski et al [36], and Milenković et al [39] due to their limited ability to rank, often leading to tied ranks for genes.…”

Section: Plos Onementioning

confidence: 99%

“…Because proteins are encoded by genes, genetic variations can affect the way proteins interact with each other, thereby disrupting molecular pathways and ultimately leading to disease. Besides using protein knowledge graphs for disease gene identification, they have been commonly used for many types of analyses [ 15 ], such as drug efficacy screening [ 16 , 17 ] identifying interrelationships between diseases [ 18 , 19 ], and drug target identification [ 20 ]. Within protein knowledge graphs, biomedical knowledge published in literature and databases is formalized as subject–predicate–object triples, where pairs of entities, such as proteins, are related to each other by verbs or predicates [ 21 , 22 ] An example of such a subject–predicate–object triple is MAPK –regulates– ALOX5 .…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Identifying genes targeted by disease-associated non-coding SNPs with a protein knowledge graph

et al. 2022

Self Cite

View full text Add to dashboard Cite

Genome-wide association studies (GWAS) have identified many single nucleotide polymorphisms (SNPs) that play important roles in the genetic heritability of traits and diseases. With most of these SNPs located on the non-coding part of the genome, it is currently assumed that these SNPs influence the expression of nearby genes on the genome. However, identifying which genes are targeted by these disease-associated SNPs remains challenging. In the past, protein knowledge graphs have often been used to identify genes that are associated with disease, also referred to as “disease genes”. Here, we explore whether protein knowledge graphs can be used to identify genes that are targeted by disease-associated non-coding SNPs by testing and comparing the performance of six existing methods for a protein knowledge graph, four of which were developed for disease gene identification. We compare our performance against two baselines: (1) an existing state-of-the-art method that is based on guilt-by-association, and (2) the leading assumption that SNPs target the nearest gene on the genome. We test these methods with four reference sets, three of which were obtained by different means. Furthermore, we combine methods to investigate whether their combination improves performance. We find that protein knowledge graphs that include predicate information perform comparable to the current state of the art, achieving an area under the receiver operating characteristic curve (AUC) of 79.6% on average across all four reference sets. Protein knowledge graphs that lack predicate information perform comparable to our other baseline (genetic distance) which achieved an AUC of 75.7% across all four reference sets. Combining multiple methods improved performance to 84.9% AUC. We conclude that methods for a protein knowledge graph can be used to identify which genes are targeted by disease-associated non-coding SNPs.

show abstract

Application of Medical Knowledge Graphs in Cardiology and Cardiovascular Medicine: A Brief Literature Review

Wang

et al. 2022

Adv Ther

View full text Add to dashboard Cite

A knowledge graph is defined as a collection of interlinked descriptions of concepts, relationships, entities and events. Medical knowledge graphs have been the most recent advances in technology, therapy and medicine. Nowadays, a number of specific uses and applications rely on knowledge graphs. The application of the knowledge graph, another form of artificial intelligence (AI) in cardiology and cardiovascular medicine, is a new concept, and only a few studies have been carried out on this particular aspect. In this brief literature review, the use and importance of disease-specific knowledge graphs in exploring various aspects of Kawasaki disease were described. A vision of individualized knowledge graphs (iKGs) in cardiovascular medicine was also discussed. Such iKGs would be based on a modern informatics platform of exchange and inquiry that could comprehensively integrate biologic knowledge with medical histories and health outcomes of individual patients. This could transform how clinicians and scientists discover, communicate and apply new knowledge. In addition, we also described how a study based on the comprehensive longitudinal evaluation of dietary factors associated with acute myocardial infarction and fatal coronary heart disease used a knowledge graph to show the dietary factors associated with cardiovascular diseases in Nurses’ Health Study data. To conclude, in this fast-developing world, medical knowledge graphs have emerged as attractive methods of data storage and hypothesis generation. They could be a major and effective tool in cardiology and cardiovascular medicine and play an important role in reaching effective clinical decisions during treatment and management of patients in the cardiology department.

show abstract

Identifying disease trajectories with predicate information from a knowledge graph

Cited by 6 publications

References 60 publications

PGraphD*: Methods for Drift Detection and Localisation Using Deep Learning Modelling of Business Processes

PGraphD*: Methods for Drift Detection and Localisation Using Deep Learning Modelling of Business Processes

Identifying genes targeted by disease-associated non-coding SNPs with a protein knowledge graph

Application of Medical Knowledge Graphs in Cardiology and Cardiovascular Medicine: A Brief Literature Review

Contact Info

Product

Resources

About