• Hetnet connectivity search pro...

Treffer: Hetnet connectivity search provides rapid insights into how two biomedical entities are related.

Title:
Hetnet connectivity search provides rapid insights into how two biomedical entities are related.
Authors:
Himmelstein DS; Department of Systems Pharmacology and Translational Therapeutics, University of Pennsylvania, Philadelphia, Pennsylvania, United States of America; Related Sciences., Zietz M; Department of Systems Pharmacology and Translational Therapeutics, University of Pennsylvania, Philadelphia, Pennsylvania, United States of America; Department of Biomedical Informatics, Columbia University, New York, New York, United States of America., Rubinetti V; Department of Systems Pharmacology and Translational Therapeutics, University of Pennsylvania, Philadelphia, Pennsylvania, United States of America; Center for Health AI, University of Colorado School of Medicine, Aurora, Colorado, United States of America., Kloster K; Carbon, Inc.; Department of Computer Science, North Carolina State University, Raleigh, North Carolina, United States of America., Heil BJ; Genomics and Computational Biology Graduate Group, Perelman School of Medicine, University of Pennsylvania., Alquaddoomi F; Department of Biochemistry and Molecular Genetics, University of Colorado School of Medicine, Aurora, Colorado, United States of America; Center for Health AI, University of Colorado School of Medicine, Aurora, Colorado, United States of America., Hu D; Department of Pathology, Perelman School of Medicine University of Pennsylvania, Philadelphia PA, USA., Nicholson DN; Department of Systems Pharmacology and Translational Therapeutics, Perelman School of Medicine University of Pennsylvania, Philadelphia PA, USA., Hao Y; Genomics and Computational Biology Graduate Group, Perelman School of Medicine, University of Pennsylvania, Philadelphia PA, USA., Sullivan BD; School of Computing, University of Utah, Salt Lake City, Utah, USA., Nagle MW; Integrative Biology, Internal Medicine Research Unit, Worldwide Research, Development, and Medicine, Pfizer Inc, Cambridge, Massachusetts, United States of America; Neurogenomics, Translational Sciences, Neurology Business Group, Eisai Inc, Cambridge, Massachusetts, United States of America., Greene CS; Department of Systems Pharmacology and Translational Therapeutics, University of Pennsylvania, Philadelphia, Pennsylvania, United States of America; Department of Biochemistry and Molecular Genetics, University of Colorado School of Medicine, Aurora, Colorado, United States of America; Center for Health AI, University of Colorado School of Medicine, Aurora, Colorado, United States of America.
Source:
BioRxiv : the preprint server for biology [bioRxiv] 2023 Jan 07. Date of Electronic Publication: 2023 Jan 07.
Publication Type:
Preprint; Journal Article
Language:
English
Journal Info:
Country of Publication: United States NLM ID: 101680187 Publication Model: Electronic Cited Medium: Internet ISSN: 2692-8205 (Electronic) Linking ISSN: 26928205 NLM ISO Abbreviation: bioRxiv Subsets: PubMed not MEDLINE
Comments:
Update in: Gigascience. 2022 Dec 28;12:giad047. doi: 10.1093/gigascience/giad047. (PMID: 37503959)
References:
Bioinformatics. 2018 Sep 1;34(17):i901-i907. (PMID: 30423077)
JMIR Med Inform. 2020 May 21;8(5):e17645. (PMID: 32436854)
BMC Bioinformatics. 2022 Sep 29;23(1):400. (PMID: 36175836)
Genome Biol. 2019 Jun 4;20(1):118. (PMID: 31164141)
Gigascience. 2024 Jan 2;13:. (PMID: 38323677)
Brief Bioinform. 2022 Nov 19;23(6):. (PMID: 36151740)
PLoS Comput Biol. 2015 Jul 09;11(7):e1004259. (PMID: 26158728)
Bioinformatics. 2012 Dec 1;28(23):3158-60. (PMID: 23044550)
J Am Med Inform Assoc. 2018 Nov 1;25(11):1452-1459. (PMID: 30357378)
BMC Bioinformatics. 2019 Jun 10;20(1):306. (PMID: 31238875)
Sci Rep. 2020 Oct 26;10(1):18250. (PMID: 33106501)
BMC Bioinformatics. 2019 Dec 11;20(1):653. (PMID: 31829175)
BMC Med Genomics. 2019 Dec 23;12(Suppl 10):188. (PMID: 31865919)
IEEE Trans Pattern Anal Mach Intell. 2015 Jan;37(1):41-53. (PMID: 26353207)
Nucleic Acids Res. 2019 Jan 8;47(D1):D955-D962. (PMID: 30407550)
Nat Commun. 2022 Sep 9;13(1):5304. (PMID: 36085310)
Bioinformatics. 2017 Aug 01;33(15):2337-2344. (PMID: 28430977)
PLoS Comput Biol. 2019 Jun 24;15(6):e1007128. (PMID: 31233491)
Elife. 2017 Sep 22;6:. (PMID: 28936969)
KDD. 2016 Aug;2016:855-864. (PMID: 27853626)
Elife. 2020 Mar 17;9:. (PMID: 32180547)
Grant Information:
R01 CA237170 United States CA NCI NIH HHS; R01 HG010067 United States HG NHGRI NIH HHS; T32 HG000046 United States HG NHGRI NIH HHS
Entry Date(s):
Date Created: 20230130 Latest Revision: 20240923
Update Code:
20250114
PubMed Central ID:
PMC9882000
DOI:
10.1101/2023.01.05.522941
PMID:
36711546
Database:
MEDLINE

Weitere Informationen

Hetnets, short for "heterogeneous networks", contain multiple node and relationship types and offer a way to encode biomedical knowledge. One such example, Hetionet connects 11 types of nodes - including genes, diseases, drugs, pathways, and anatomical structures - with over 2 million edges of 24 types. Previous work has demonstrated that supervised machine learning methods applied to such networks can identify drug repurposing opportunities. However, a training set of known relationships does not exist for many types of node pairs, even when it would be useful to examine how nodes of those types are meaningfully connected. For example, users may be curious not only how metformin is related to breast cancer, but also how the GJA1 gene might be involved in insomnia. We developed a new procedure, termed hetnet connectivity search, that proposes important paths between any two nodes without requiring a supervised gold standard. The algorithm behind connectivity search identifies types of paths that occur more frequently than would be expected by chance (based on node degree alone). We find that predictions are broadly similar to those from previously described supervised approaches for certain node type pairs. Scoring of individual paths is based on the most specific paths of a given type. Several optimizations were required to precompute significant instances of node connectivity at the scale of large knowledge graphs. We implemented the method on Hetionet and provide an online interface at https://het.io/search . We provide an open source implementation of these methods in our new Python package named hetmatpy .