| Name |
Description |
Publication |
| DTI-Voodoo |
Accurate prediction of drug--target interactions through graph neural networks and side-effects |
Hinnerichs, T., & Hoehndorf, R. (2021). DTI-Voodoo: machine learning over interaction networks and ontology-based background knowledge predicts drug–target interactions. Bioinformatics, 37(24), 4835–4843. https://doi.org/10.1093/bioinformatics/btab548
|
| MESH2OWL |
Converts the MESH metathesaurus into OWL |
|
| Onto2Graph |
Generating graphs from ontology axioms |
Rodríguez-García, M. Á., & Hoehndorf, R. (2018). Inferring ontology graph structures using OWL reasoning. BMC Bioinformatics, 19(1). https://doi.org/10.1186/s12859-017-1999-8 |
| SMUDGE |
Semantic Disease Gene Embeddings |
Alshahrani, M., & Hoehndorf, R. (2018). Semantic Disease Gene Embeddings (SmuDGE): phenotype-based disease gene prioritization without phenotypes. Bioinformatics, 34(17), i901–i907. https://doi.org/10.1093/bioinformatics/bty559
|
| VSIM |
Simulation and visualization of genomes |
|
| PredCAN |
Ontology-based prediction of cancer driver genes |
Althubaiti, S., Karwath, A., Dallol, A., Noor, A., Alkhayyat, S. S., Alwassia, R., … Hoehndorf, R. (2019). Ontology-based prediction of cancer driver genes. Scientific Reports, 9(1). https://doi.org/10.1038/s41598-019-53454-1 |
| Semantic Haiku |
Generate poetry from knowledge graphs |
|
| UMLS2OWL |
Represent UMLS as OWL knowledgebase |
|
|
Onto2Vec
|
Embedding ontology axioms through language models |
Smaili, F. Z., Gao, X., & Hoehndorf, R. (2018). Onto2Vec: joint vector-based representation of biological entities and their ontology-based annotations. Bioinformatics, 34(13), i52–i60. https://doi.org/10.1093/bioinformatics/bty259 |
| OPA2Vec |
Embedding ontology axioms and metadata through language models |
Smaili, F. Z., Gao, X., & Hoehndorf, R. (2018). OPA2Vec: combining formal and informal content of biomedical ontologies to improve similarity-based prediction. Bioinformatics, 35(12), 2133–2140. https://doi.org/10.1093/bioinformatics/bty933
|
| UnMIREOT |
Automatic detection and repair of inconsistencies in biomedical ontologies |
Slater, L. T., Gkoutos, G. V., & Hoehndorf, R. (2020). Towards semantic interoperability: finding and repairing hidden contradictions in biomedical ontologies. BMC Medical Informatics and Decision Making, 20(S10). https://doi.org/10.1186/s12911-020-01336-2 |
| DeepViral |
Prediction of host pathogen interactions |
Liu-Wei, W., Kafkas, Ş., Chen, J., Dimonaco, N. J., Tegnér, J., & Hoehndorf, R. (2021). DeepViral: prediction of novel virus–host interactions from protein sequences and infectious disease phenotypes. Bioinformatics, 37(17), 2722–2729. https://doi.org/10.1093/bioinformatics/btab147 |
| Vec2SPARQL |
Querying vector similarity through SPARQL |
Kulmanov, M., Kafkas, S., Karwath, A., Malic, A., Gkoutos, G. V., Dumontier, M., & Hoehndorf, R. (2018). Vec2SPARQL: integrating SPARQL queries and knowledge graph embeddings. https://doi.org/10.1101/463778 |
| DL2Vec |
Graph-based embedding of Description Logic ontologies |
Chen, J., Althagafi, A., & Hoehndorf, R. (2020). Predicting candidate genes from phenotypes, functions and anatomical site of expression. Bioinformatics, 37(6), 853–860. https://doi.org/10.1093/bioinformatics/btaa879 |
| EL Embeddings |
Geometric embedding of knowledge bases in EL++ |
|
| DeepGO |
Protein function prediction from sequence |
Kulmanov, M., Khan, M. A., & Hoehndorf, R. (2017). DeepGO: predicting protein functions from sequence and interactions using a deep ontology-aware classifier. Bioinformatics, 34(4), 660–668. https://doi.org/10.1093/bioinformatics/btx624 |
| DeepPheno |
Prediction of loss-of-function phenotypes in human and mouse |
Kulmanov, M., & Hoehndorf, R. (2020). DeepPheno: Predicting single gene loss-of-function phenotypes using an ontology-aware hierarchical classifier. PLOS Computational Biology, 16(11), e1008453. https://doi.org/10.1371/journal.pcbi.1008453 |
| PhenomeNet Variant Prioritizer (PVP) |
Phenotype-based prediction of disease-associated genomic variants |
Boudellioua, I., Mahamad Razali, R. B., Kulmanov, M., Hashish, Y., Bajic, V. B., Goncalves-Serra, E., … Hoehndorf, R. (2017). Semantic prioritization of novel causative genomic variants. PLOS Computational Biology, 13(4), e1005500. https://doi.org/10.1371/journal.pcbi.1005500
Boudellioua, I., Kulmanov, M., Schofield, P. N., Gkoutos, G. V., & Hoehndorf, R. (2019). DeepPVP: phenotype-based prioritization of causative variants using deep learning. BMC Bioinformatics, 20(1). https://doi.org/10.1186/s12859-019-2633-8
Boudellioua, I., Kulmanov, M., Schofield, P. N., Gkoutos, G. V., & Hoehndorf, R. (2018). OligoPVP: Phenotype-driven analysis of individual genomic information to prioritize oligogenic disease variants. Scientific Reports, 8(1). https://doi.org/10.1038/s41598-018-32876-3
|
| DeepGOPlus |
Protein function prediction from amino acid sequence |
Kulmanov, M., & Hoehndorf, R. (2019). DeepGOPlus: improved protein function prediction from sequence. Bioinformatics. https://doi.org/10.1093/bioinformatics/btz595
|
| DeepSVP |
Phenotype-based prioritization of structural genomic variants associated with Mendelian disease |
Althagafi, A., Alsubaie, L., Kathiresan, N., Mineta, K., Aloraini, T., Almutairi, F., Hoehndorf, R. (2021). DeepSVP: Integration of genotype and phenotype for structural variant prioritization using deep learning. https://doi.org/10.1101/2021.01.28.428557
|
| MOWL |
Machine Learning with OWL Ontologies software library |
|
| AberOWL |
A framework for ontology-based data access that consists of an ontology repository containing over 500 ontologies that can be queried through an OWL 2 EL reasoner. The result of these queries can also be used in SPARQL queries and for literature search |
Hoehndorf R, Slater L, Schofield PM, Gkoutos GV (2015) Aber-OWL: a framework for ontology-based data access in biology. BMC Bioinformatics, https://doi.org/10.1186/s12859-015-0456-9 |
| PhenomeNET: VP |
A system to prioritize variants in whole exome and whole genome sequence data. PVP takes a VCF file and a set of phenotypes as input and identifies the most likely causal variants. We consider a variant causal if it is both pathogenic and involved in the pathogenesis of the patient's phenotype. |
Boudellioua I, Razali RBM, Kulmanov M, Hashush Y, Bajic V, Goncalves-Serra E, Schoenmakers N, Gkoutos GV, Schofield PN, Hoehndorf R (2017) Semantic prioritization of novel causative genomic variants. PLOS Computational Biology, https://doi.org/10.1371/journal.pcbi.1005500 |
| Onto2Graph: Generating graph structures from ontologies |
A method to generate graph structures from ontologies. Onto2Graph differs from other method in that it uses a reasoner to generate a proof for each edge created, and thereby uses the deductive closure of an ontology for generating a graph structure. These graphs can then be used in a variety of applications, including visualization of ontologies and ontology-based data analysis. |
|
| UniProt-to-OWL converter |
A database of proteins and one of the central databases in biology. UniProt is available in RDF format as Linked Data. We created a method to convert UniProt (or parts thereof) to OWL so that it can be used for automated reasoning and semantic queries. |
|
| PhenomeNET: a cross-species phenotype network |
A cross-species phenotype network that systematically integrates phenotype descriptions of model organisms and human diseases and establishes a measure of semantic similarity to determine phenotypic similarity. PhenomeNET can be used for prioritization of candidate genes, discovery of drug targets, or discovery of protein functions. |
Hoehndorf R, Schofield PN, Gkoutos GV (2011) PhenomeNET: a whole-phenome approach to disease gene discovery. Nuclein Acids Research, https://doi.org/10.1093/nar/gkr538 |
| OntoFUNC: enrichment analysis |
A wrapper around the popular FUNC tool, and can be used to perform an ontology enrichment analysis over arbitrary ontologies. OntoFUNC uses the ELK reasoner to classify ontologies and generate an ontology structure that is used by the FUNC tool. |
Hoehndorf, R., Hancock, J. M., Hardy, N. W., Mallon, A.-M., Schofield, P. N., & Gkoutos, G. V. (2013). Analyzing gene expression data in mice with the Neuro Behavior Ontology. Mammalian Genome, 25(1-2), 32–40. https://doi.org/10.1007/s00335-013-9481-z |
| ELvira: ontology modularization |
A tool to extract modules from ontologies. ELvira retains the full ontology signature and extracts modules that fall in one of the OWL 2 profiles that are amenable to tractable (i.e., polynomial-time) reasoning. |
Hoehndorf, R., Dumontier, M., Oellrich, A., Wimalaratne, S., Rebholz-Schuhmann, D., Schofield, P., & Gkoutos, G. V. (2011). A common layer of interoperability for biomedical ontologies based on OWL EL. Bioinformatics, 27(7), 1001–1008. https://doi.org/10.1093/bioinformatics/btr058 |
| Walking RDF and OWL |
A set of tools for neuro-symbolic feature learning over Description Logic theories. The set of tools includes support for classifying knowledge graphs and adding inferred edges, generating a text corpus from the inferred graphs, and learning embeddings for nodes and edges in this graph. These embeddings can be used as features in machine learning models or directly be used to evaluate similarity between entities. |
Alshahrani, M., Khan, M. A., Maddouri, O., Kinjo, A. R., Queralt-Rosinach, N., & Hoehndorf, R. (2017). Neuro-symbolic representation learning on biological knowledge graphs. Bioinformatics, 33(17), 2723–2730. https://doi.org/10.1093/bioinformatics/btx275 |