Filters








10,387 Hits in 4.5 sec

Applying Support Vector Machines for Gene Ontology based gene function prediction

Arunachalam Vinayagam, Rainer König, Jutta Moormann, Falk Schubert, Roland Eils, Karl-Heinz Glatting, Sándor Suhai
2004 BMC Bioinformatics  
In our approach, annotation was provided through Gene Ontology terms by applying multiple Support Vector Machines (SVM) for the classification of correct and false predictions.  ...  The current progress in sequencing projects calls for rapid, reliable and accurate function assignments of gene products.  ...  Acknowledgments We thank the Gene Ontology Consortium and all groups that established GO association databases for making their data available through the web.  ... 
doi:10.1186/1471-2105-5-116 pmid:15333146 pmcid:PMC517617 fatcat:r24avql2qze7xbyjf7lwbnjbqi

SVM-Based Multi-Dividing Ontology Learning Algorithm and Similarity Measuring on Topological Indices

Linli Zhu, Gang Hua, Haci Mehmet Baskonus, Wei Gao
2020 Frontiers in Physics  
In this work, a support vector machines based multi-dividing ontology learning algorithm is proposed.  ...  We pay attention to the similarity of topological indices in chemical graph theory, and apply SVM-based multi-dividing ontology learning algorithms to give some calculation results of similarity between  ...  ACKNOWLEDGMENTS Thanks to the reviewers for their constructive comments on the revision of this article.  ... 
doi:10.3389/fphy.2020.547963 fatcat:7kikfznumjeftb3r77knrn7x3i

Ontology-based prediction of cancer driver genes [article]

Sara Althubaiti, Andreas Karwath, Ashraf Dallol, Adeeb Noor, Shadi Salem Alkhayyat, Rolina Alwassia, Katsuhiko Mineta, Takashi Gojobori, Andrew D Beggs, Paul N Schofield, Georgios V Gkoutos, Robert Hoehndorf
2019 bioRxiv   pre-print
Accurate identification of driver genes and driver mutations is critical for advancing cancer research and personalizing treatment based on accurate stratification of patients.  ...  We have developed a novel method for identifying cancer driver genes.  ...  However, we 107 can only generate the feature vectors if there are ontology-based annotations for a gene 108 and therefore we obtain a different number of feature vectors when utilizing different 109 ontologies  ... 
doi:10.1101/561480 fatcat:fbh7qv6x5bfaxb2nwcnh6vpnoa

Predicting candidate genes from phenotypes, functions, and anatomical site of expression [article]

Jun Chen, Azza Althagafi, Robert Hoehndorf
2020 biorxiv/medrxiv   pre-print
We then develop a machine learning model to predict gene--disease associations based on the associations between genes and multiple biomedical ontologies, and this model significantly improves over state  ...  Information about functions of gene products and anatomical site of gene expression is available for more genes and can also be related to phenotypes through ontologies and machine learning models.  ...  For this purpose, we first embed the information about genes and diseases together with the ontologies used to characterize them in a vector space and then use a supervised machine learning model to predict  ... 
doi:10.1101/2020.03.30.015594 fatcat:vsr2lpzbmvcz7jesaio7dvrd6i

Ontology-based prediction of cancer driver genes

Sara Althubaiti, Andreas Karwath, Ashraf Dallol, Adeeb Noor, Shadi Salem Alkhayyat, Rolina Alwassia, Katsuhiko Mineta, Takashi Gojobori, Andrew D. Beggs, Paul N. Schofield, Georgios V. Gkoutos, Robert Hoehndorf
2019 Scientific Reports  
Accurate identification of driver genes and driver mutations is critical for advancing cancer research and personalizing treatment based on accurate stratification of patients.  ...  We have developed a novel method for identifying cancer driver genes.  ...  As our method can accurately predict cancer driver genes, we apply our model to all human genes for which we have ontology-based annotations and predict 112 novel candidate driver genes for 20 different  ... 
doi:10.1038/s41598-019-53454-1 pmid:31757986 pmcid:PMC6874647 fatcat:lfrtketkjfdodhs3zf7blq7gam

Special issue on semantic data analytics and bioinformatics

Haiying Wang, Man-Wai Mak, Hui Wang
2017 International Journal of Machine Learning and Cybernetics  
Guo et al. proposed a method based on integrated support vector machines (SVM) with a hybrid kernel to predict protein interaction sites which is crucial for the understanding of the mechanism of protein-protein  ...  Gene Ontology (GO) is becoming the de facto standard for annotating gene products. However, its significance is not limited to annotation applications.  ...  Guo et al. proposed a method based on integrated support vector machines (SVM) with a hybrid kernel to predict protein interaction sites which is crucial for the understanding of the mechanism of protein-protein  ... 
doi:10.1007/s13042-017-0749-6 fatcat:avywwtmaanc6zochhyzo4mfrbq

Semantic similarity and machine learning with ontologies

Maxat Kulmanov, Fatima Zohra Smaili, Xin Gao, Robert Hoehndorf
2020 Briefings in Bioinformatics  
Recently, ontologies are increasingly being used to provide background knowledge in similarity-based analysis and machine learning models.  ...  embeddings can exploit the background knowledge in ontologies and how ontologies can provide constraints that improve machine learning models.  ...  Structured SVMs have been applied both to the prediction of functions based on the Gene Ontology [95] and phenotypes based on the Human Phenotype Ontology [96] .  ... 
doi:10.1093/bib/bbaa199 pmid:33049044 pmcid:PMC8293838 fatcat:3mqrjqnggrhdrkvsl6w4odazeu

Compact Integration of Multi-Network Topology for Functional Analysis of Genes

Hyunghoon Cho, Bonnie Berger, Jian Peng
2016 Cell Systems  
These vectors can then be plugged into off-the-shelf machine learning methods to derive functional insights about genes or proteins.  ...  We present tools based on Mashup that achieve state-of-the-art performance in three diverse functional inference tasks: protein function prediction, gene ontology reconstruction, and genetic interaction  ...  support vector machine (SVM) toolbox, LIBSVM (Chang and Lin, 2011).  ... 
doi:10.1016/j.cels.2016.10.017 pmid:27889536 pmcid:PMC5225290 fatcat:kbcyts5cavb3vmtrocyjziww2m

Predicting Candidate Genes From Phenotypes, Functions, And Anatomical Site Of Expression

Jun Chen, Azza Althagafi, Robert Hoehndorf, Peter Robinson
2020 Bioinformatics  
We then develop a machine learning model to predict gene–disease associations based on the associations between genes and multiple biomedical ontologies, and this model significantly improves over state  ...  Information about functions of gene products and anatomical site of gene expression is available for more genes and can also be related to phenotypes through ontologies and machine learning models.  ...  Funding This work was supported by funding from King Abdullah University of Science and Technology (KAUST) Office of Sponsored Research (OSR) under Award No.  ... 
doi:10.1093/bioinformatics/btaa879 pmid:33051643 fatcat:3wb4wr6tzvfdxexm7vuva66rmi

Knowledge Discovery and Risk Prediction for Chronic Diseases: An Integrated Approach [chapter]

Anju Verma, Maurizio Fiasché, Maria Cuzzola, Francesco C. Morabito, Giuseppe Irrera
2011 IFIP Advances in Information and Communication Technology  
A novel ontology based type 2 diabetes risk analysis system framework is described, which allows the creation of global knowledge representation (ontology) and personalized modeling for a decision support  ...  ontology-based personalized risk evaluation for chronic diseases.  ...  Nik Kasabov for his support.  ... 
doi:10.1007/978-3-642-23957-1_31 fatcat:ryfjiuzfonbypngoxxuj3ajyti

Predicting gene function in a hierarchical context with an ensemble of classifiers

Yuanfang Guan, Chad L Myers, David C Hess, Zafer Barutcuoglu, Amy A Caudy, Olga G Troyanskaya
2008 Genome Biology  
Results: In this paper, we describe our contribution to this project, an ensemble framework based on the support vector machine that integrates diverse datasets in the context of the Gene Ontology hierarchy  ...  The wide availability of genome-scale data for several organisms has stimulated interest in computational approaches to gene function prediction.  ...  We thank Rob Kuper, John Wiggins and Mark Schroeder for excellent technical support.  ... 
doi:10.1186/gb-2008-9-s1-s3 pmid:18613947 pmcid:PMC2447537 fatcat:3xti24dnszfsfosdaeu336an2y

Prediction of Drosophila melanogaster gene function using Support Vector Machines

Nicholas Mitsakakis, Zak Razak, Michael Escobar, J Timothy Westwood
2013 BioData Mining  
We have applied Support Vector Machines (SVM), a sigmoid fitting function and a stratified cross-validation approach to analyze a large microarray experiment dataset from Drosophila melanogaster in order  ...  to predict possible functions for previously un-annotated genes.  ...  to parse data from Gene Ontology, Han Yan for making available the data used in the Yan et al. study [10] and William Noble (Departments of Genome Sciences and of  ... 
doi:10.1186/1756-0381-6-8 pmid:23547736 pmcid:PMC3669044 fatcat:vrvpvcyswzd77csa7pdhfy2cy4

Self-normalizing learning on biomedical ontologies using a deep Siamese neural network [article]

Fatima Zohra Smaili, Xin Gao, Robert Hoehndorf
2020 biorxiv/medrxiv   pre-print
Our method also allows us to apply ontology based annotations and axioms to the prediction of toxicological effects of chemicals where our method shows superior performance.  ...  tasks: prediction of interactions between proteins and prediction of gene disease associations.  ...  The research reported in this work was supported by the King Abdullah University of Science and Technology (KAUST) Office of Sponsored Research (OSR) under Award No.  ... 
doi:10.1101/2020.04.23.057117 fatcat:qr5yw7n4ajhxxebpxzjtcodhde

Recovering key biological constituents through sparse representation of gene expression

Yosef Prat, Menachem Fromer, Nathan Linial, Michal Linial
2011 Computer applications in the biosciences : CABIOS  
the Gene Ontology (GO) hierarchy and protein-protein interaction map.  ...  Specifically, we find, for the expression profile of each particular gene, its approximation as a linear combination of profiles of a few other genes.  ...  Prediction of gene associations The Gene Ontology (GO) is structured as three directed acyclic graphs (DAG): the cellular component (CC), the biological process (BP), and the molecular function (MF) ontology  ... 
doi:10.1093/bioinformatics/btr002 pmid:21258061 fatcat:gt5ghbuf5rhffgbbiqhwzfrp4m

OPA2Vec: combining formal and informal content of biomedical ontologies to improve similarity-based prediction [article]

Fatima Zohra Smaili, Xin Gao, Robert Hoehndorf
2018 arXiv   pre-print
Second, we evaluate our method on predicting gene-disease associations based on phenotype similarity by generating vector representations of genes and diseases using a phenotype ontology, and applying  ...  the obtained vectors to predict gene-disease associations.  ...  We applied our OPA2Vec algorithm to the combined knowledge base to generate vector representations of genes and diseases.  ... 
arXiv:1804.10922v1 fatcat:u6vwrilmnndyvirpghvmazqxom
« Previous Showing results 1 — 15 out of 10,387 results