Drug Target Ontology to Classify and Integrate Drug Discovery Data

Abstract

Background: One of the most successful approaches to develop new small molecule therapeutics has been to start from a validated druggable protein target. However, only a small subset of potentially druggable targets has attracted significant research and development resources. TheIlluminating the Druggable Genome (IDG) project develops resources to catalyze the development of likely targetable, yet currently understudied prospective drug targets. A central component of the IDG program is a comprehensive knowledge resource of the druggable genome. Conclusions: DTO was built based on the need for a formal semantic model for druggable targets including various related information such as protein, gene, protein domain, protein structure, peer-reviewed) is the author/funder. All rights reserved. No reuse allowed without permission.The copyright holder for this preprint (which was not . http://dx.doi.org/10.1101/117564 doi: bioRxiv preprint first posted online Mar. 16, 2017; -3 -binding site, small molecule drug, mechanism of action, protein tissue localization, disease association, and many other types of information. DTO will further facilitate the otherwise challenging integration and formal linking to biological assays, phenotypes, disease models, drug poly-pharmacology, binding kinetics and many other processes, functions and qualities that are at the core of drug discovery.The first version of DTO is publically available via several mechanisms.The long-term goal of DTO is to provide such an integrative framework and to populate the ontology with this information as a community resource.peer-reviewed)

Kinome-wide activity classification of small molecules by deep learning

“…Another relevant aspect of Kinome-wide classification models is how they perform across the kinase target protein target family, as defined here by the kinase groups. 20 Each kinase task was organized into its corresponding group (see methods) and model evaluation metrics were aggregated to discriminate differences in predictive performance. We observed that the multi-task models maintained high predictive performance across and within all kinase groups, even for those tasks that do not contain many active examples and are underrepresented globally (Supporting Figure 6).…”

“…We compiled our kinase target prediction dataset by obtaining all publicly available kinase bioactivity data from ChEMBL (release 21), 23 a curated database of bioactivity measurements, and commercial kinase bioactivity data from KKB (release Q12016). 24 Using kinase domain annotations from the Drug Target Ontology (DTO) 20 we mapped domain information to UniProt, obtaining 485 unique UniProt identifiers. All UniProt IDs were mapped to ChEMBL release 21 target IDs and the corresponding KKB target ID.…”

Autophagy dark genes: Can we find them with machine learning?

“…All gene sets mentioned throughout this paper are available in the Supplementary Material. Future validation steps may include integration of chemical-protein annotation resources, using Pharos [48] and Chem-Prot [78], the use of a semantic model to evaluate druggability via the drug target ontology [79].…”

The Clinical Kinase Index: Prioritizing Understudied Kinases as Targets for the Treatment of Cancer

“…Consistent with this is the fact that the current kinase inhibitors target not only a narrow range of targets, but also a narrow range of pathways including Angiogenesis, Cell Adhesion, Immune System Signaling (Cytokine, TCR, BCR) and anti-apoptotic pathways[10]. For example, all kinase inhibitors for renal cell carcinoma target angiogenic pathways [11]. It is probable that there exists a strategy for targeting multiple, orthogonal pathways that work in a synergistic manner, as opposed to targeting kinases with overlapping pathways.…”

“…The CKI scores for each cancer for this kinase will be generated in table form, along with target development level, rank, kinase group and family and whether or not this kinase has an approved drug MOA. Many annotations from the Drug Target Ontology (DTO) [11] are available as facets to filter and select kinase targets. To start from a disease of interest, one can select a TCGA cancer in the “Disease” tab.…”