DeepPheno: Predicting single gene loss-of-function phenotypes using an ontology-aware hierarchical classifier

Kulmanov, Maxat; Hoehndorf, Robert

doi:10.1101/839332

Cited by 5 publications

(9 citation statements)

References 56 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…DeepSVP relies on machine learning for predicting pathogenic and phenotype-associated variants. For this purpose, it relies on advances in machine learning with ontologies that incorporate the background knowledge contained in ontologies in the form of axioms and annotations to ontology classes (Kulmanov et al, 2020). Many such approaches convert ontologies into a graph-based form based on syntactic patterns within the ontology axioms and then apply a graph embedding on the resulting graph (Kulmanov et al, 2020).…”

Section: Machine Learning With Semantic Background Knowledge For Variant Prioritizationmentioning

confidence: 99%

“…For this purpose, it relies on advances in machine learning with ontologies that incorporate the background knowledge contained in ontologies in the form of axioms and annotations to ontology classes (Kulmanov et al, 2020). Many such approaches convert ontologies into a graph-based form based on syntactic patterns within the ontology axioms and then apply a graph embedding on the resulting graph (Kulmanov et al, 2020). In DeepSVP, we use DL2Vec which includes a large variety of ontology axioms and can significantly improve the phenotype-based prediction of disease genes.…”

Section: Machine Learning With Semantic Background Knowledge For Variant Prioritizationmentioning

confidence: 99%

“…Several deep learning methods are now available that can predict phenotypes (Kulmanov and Hoehndorf, 2020;Zhou et al, 2019) or associate phenotypes with different types of information available for genes, including functions of gene products and site of expression (Chen et al, 2020;Smaili et al, 2019). These methods use machine learning to relate information through background knowledge contained in ontologies, and can accurately identify phenotypeassociated genes without prior knowledge about phenotypes, often significantly improving over the use of semantic similarity measures (Kulmanov et al, 2020). A limitation of these methods is that they are often transductive instead of inductive (Kulmanov et al, 2020), i.e.…”

Section: Introductionmentioning

confidence: 99%

“…These methods use machine learning to relate information through background knowledge contained in ontologies, and can accurately identify phenotypeassociated genes without prior knowledge about phenotypes, often significantly improving over the use of semantic similarity measures (Kulmanov et al, 2020). A limitation of these methods is that they are often transductive instead of inductive (Kulmanov et al, 2020), i.e. the diseases or disorders for which associated genes are predicted should already be available at the time of training the model.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

DeepSVP: integration of genotype and phenotype for structural variant prioritization using deep learning

et al. 2021

Self Cite

View full text Add to dashboard Cite

Motivation Structural genomic variants account for much of human variability and are involved in several diseases. Structural variants are complex and may affect coding regions of multiple genes, or affect the functions of genomic regions in different ways from single nucleotide variants. Interpreting the phenotypic consequences of structural variants relies on information about gene functions, haploinsufficiency or triplosensitivity, and other genomic features. Phenotype-based methods to identifying variants that are involved in genetic diseases combine molecular features with prior knowledge about the phenotypic consequences of altering gene functions. While phenotype-based methods have been applied successfully to single nucleotide variants as well as short insertions and deletions, the complexity of structural variants makes it more challenging to link them to phenotypes. Furthermore, structural variants can affect a large number of coding regions, and phenotype information may not be available for all of them. Results We developed DeepSVP, a computational method to prioritize structural variants involved in genetic diseases by combining genomic and gene functions information. We incorporate phenotypes linked to genes, functions of gene products, gene expression in individual celltypes, and anatomical sites of expression, and systematically relate them to their phenotypic consequences through ontologies and machine learning. DeepSVP significantly improves the success rate of finding causative variants in several benchmarks and can identify novel pathogenic structural variants in consanguineous families. Availability https://github.com/bio-ontology-research-group/DeepSVP

show abstract

Section: Machine Learning With Semantic Background Knowledge For Variant Prioritizationmentioning

confidence: 99%

Section: Machine Learning With Semantic Background Knowledge For Variant Prioritizationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

DeepSVP: integration of genotype and phenotype for structural variant prioritization using deep learning

et al. 2021

Self Cite

View full text Add to dashboard Cite

show abstract

“…Hence, we use these two previously developed methods as comparators for evaluating the proposed deep semi-supervised ensemble model for co-mention classification. While there are other methods for predicting HPO terms for a given protein using heterogeneous data sources such as PHENOstruct [ 15 , 54 ], Notaro et al [ 55 ], HPO2Protein [ 56 ], AiProAnnotator [ 57 ], DeepPheno [ 58 ], HPOLabeler [ 59 ], HPOAnnotator [ 60 ], and HPOFiller [ 61 ], they do not employ any text-mining techniques to directly extract relations from biomedical literature. Therefore, these methods are not directly comparable to our proposed model.…”

Section: Introductionmentioning

confidence: 99%

Deep semi-supervised learning ensemble framework for classifying co-mentions of human proteins and phenotypes

Shahri

Kahanda

2021

BMC Bioinformatics

View full text Add to dashboard Cite

Background Identifying human protein-phenotype relationships has attracted researchers in bioinformatics and biomedical natural language processing due to its importance in uncovering rare and complex diseases. Since experimental validation of protein-phenotype associations is prohibitive, automated tools capable of accurately extracting these associations from the biomedical text are in high demand. However, while the manual annotation of protein-phenotype co-mentions required for training such models is highly resource-consuming, extracting millions of unlabeled co-mentions is straightforward. Results In this study, we propose a novel deep semi-supervised ensemble framework that combines deep neural networks, semi-supervised, and ensemble learning for classifying human protein-phenotype co-mentions with the help of unlabeled data. This framework allows the ability to incorporate an extensive collection of unlabeled sentence-level co-mentions of human proteins and phenotypes with a small labeled dataset to enhance overall performance. We develop PPPredSS, a prototype of our proposed semi-supervised framework that combines sophisticated language models, convolutional networks, and recurrent networks. Our experimental results demonstrate that the proposed approach provides a new state-of-the-art performance in classifying human protein-phenotype co-mentions by outperforming other supervised and semi-supervised counterparts. Furthermore, we highlight the utility of PPPredSS in powering a curation assistant system through case studies involving a group of biologists. Conclusions This article presents a novel approach for human protein-phenotype co-mention classification based on deep, semi-supervised, and ensemble learning. The insights and findings from this work have implications for biomedical researchers, biocurators, and the text mining community working on biomedical relationship extraction.

show abstract

HPODNets: deep graph convolutional networks for predicting human protein–phenotype associations

2021

View full text Add to dashboard Cite

Motivation Deciphering the relationship between human genes/proteins and abnormal phenotypes is of great importance in the prevention, diagnosis and treatment against diseases. The Human Phenotype Ontology (HPO) is a standardized vocabulary that describes the phenotype abnormalities encountered in human disorders. However, the current HPO annotations are still incomplete. Thus, it is necessary to computationally predict human protein-phenotype associations. In terms of current, cutting-edge computational methods for annotating proteins (such as functional annotation), three important features are 1) multiple network input, 2) semi-supervised learning, and 3) deep graph convolutional network (GCN), whereas there are no methods with all these features for predicting HPO annotations of human protein. Results We develop HPODNets with all above three features for predicting human protein-phenotype associations. HPODNets adopts a deep GCN with eight layers which allows to capture high-order topological information from multiple interaction networks. Empirical results with both cross-validation and temporal validation demonstrate that HPODNets outperforms seven competing state-of-the-art methods for protein function prediction. HPODNets with the architecture of deep GCNs is confirmed to be effective for predicting HPO annotations of human protein and, more generally, node label ranking problem with multiple biomolecular networks input in bioinformatics. Availability https://github.com/liulizhi1996/HPODNets Supplementary information Supplementary data are available at Bioinformatics online.

show abstract

DeepPheno: Predicting single gene loss-of-function phenotypes using an ontology-aware hierarchical classifier

Cited by 5 publications

References 56 publications

DeepSVP: integration of genotype and phenotype for structural variant prioritization using deep learning

DeepSVP: integration of genotype and phenotype for structural variant prioritization using deep learning

Deep semi-supervised learning ensemble framework for classifying co-mentions of human proteins and phenotypes

HPODNets: deep graph convolutional networks for predicting human protein–phenotype associations

Contact Info

Product

Resources

About