ExplaiNN: interpretable and transparent neural networks for genomics.
| Title: | ExplaiNN: interpretable and transparent neural networks for genomics. |
|---|---|
| Authors: | Novakovsky G; Department of Medical Genetics, Centre for Molecular Medicine and Therapeutics, BC Children's Hospital Research Institute, University of British Columbia, Vancouver, BC, Canada.; Fornes O; Department of Medical Genetics, Centre for Molecular Medicine and Therapeutics, BC Children's Hospital Research Institute, University of British Columbia, Vancouver, BC, Canada.; Saraswat M; Department of Medical Genetics, Centre for Molecular Medicine and Therapeutics, BC Children's Hospital Research Institute, University of British Columbia, Vancouver, BC, Canada.; Division of Computational Genomics and Systems Genetics, German Cancer Research Center (DKFZ), Heidelberg, Germany.; European Molecular Biology Laboratory (EMBL), Genome Biology Unit, Heidelberg, Germany.; Mostafavi S; Paul G. Allen School of Computer Science and Engineering, University of Washington (UW), Seattle, USA.; Wasserman WW; Department of Medical Genetics, Centre for Molecular Medicine and Therapeutics, BC Children's Hospital Research Institute, University of British Columbia, Vancouver, BC, Canada. wyeth@cmmt.ubc.ca. |
| Source: | Genome biology [Genome Biol] 2023 Jun 27; Vol. 24 (1), pp. 154. Date of Electronic Publication: 2023 Jun 27. |
| Publication Type: | Journal Article; Research Support, Non-U.S. Gov't |
| Language: | English |
| Journal Info: | Publisher: BioMed Central Ltd Country of Publication: England NLM ID: 100960660 Publication Model: Electronic Cited Medium: Internet ISSN: 1474-760X (Electronic) Linking ISSN: 14747596 NLM ISO Abbreviation: Genome Biol Subsets: MEDLINE |
| Imprint Name(s): | Publication: London, UK : BioMed Central Ltd; Original Publication: London : Genome Biology Ltd., c2000- |
| MeSH Terms: | Genomics*/methods ; Neural Networks, Computer*; Chromatin/genetics ; Protein Binding |
| Abstract: | Deep learning models such as convolutional neural networks (CNNs) excel in genomic tasks but lack interpretability. We introduce ExplaiNN, which combines the expressiveness of CNNs with the interpretability of linear models. ExplaiNN can predict TF binding, chromatin accessibility, and de novo motifs, achieving performance comparable to state-of-the-art methods. Its predictions are transparent, providing global (cell state level) as well as local (individual sequence level) biological insights into the data. ExplaiNN can serve as a plug-and-play platform for pretrained models and annotated position weight matrices. ExplaiNN aims to accelerate the adoption of deep learning in genomic sequence analysis by domain experts.; (© 2023. The Author(s).) |
| References: | Nat Immunol. 2007 May;8(5):463-70. (PMID: 17440452); Nat Rev Genet. 2023 Feb;24(2):125-137. (PMID: 36192604); Nature. 2020 Sep;585(7825):357-362. (PMID: 32939066); Nat Biotechnol. 2013 Feb;31(2):126-34. (PMID: 23354101); Genome Biol. 2023 Jun 27;24(1):154. (PMID: 37370113); Nat Genet. 2022 May;54(5):613-624. (PMID: 35551305); Sci Immunol. 2023 Jan 20;8(79):eade7953. (PMID: 36662884); Nat Biotechnol. 2006 Nov;24(11):1429-35. (PMID: 16998473); Nat Immunol. 2003 Jun;4(6):533-9. (PMID: 12717433); Bioinformatics. 2000 Jan;16(1):16-23. (PMID: 10812473); Nat Methods. 2021 Oct;18(10):1196-1203. (PMID: 34608324); Nucleic Acids Res. 2022 Jul 5;50(W1):W670-W676. (PMID: 35544234); Nat Biotechnol. 2022 Feb;40(2):163-166. (PMID: 35132262); Nat Methods. 2017 Mar;14(3):316-322. (PMID: 28092692); Cell Rep. 2020 May 19;31(7):107663. (PMID: 32433972); Nat Mach Intell. 2019 May;1(5):206-215. (PMID: 35603010); Nat Genet. 2021 Apr;53(4):455-466. (PMID: 33795864); Immunol Res. 2009;43(1-3):109-17. (PMID: 18806934); Bioinformatics. 2018 Oct 15;34(20):3578-3580. (PMID: 29790915); Nat Biotechnol. 2018 Jul;36(6):521-529. (PMID: 29786094); Bioinformatics. 2009 Jun 1;25(11):1422-3. (PMID: 19304878); Science. 2017 May 5;356(6337):. (PMID: 28473536); Semin Cell Dev Biol. 2015 Aug;44:115-25. (PMID: 26424495); Bioinformatics. 2022 Apr 28;38(9):2397-2403. (PMID: 35238376); Nucleic Acids Res. 2016 Jun 20;44(11):e107. (PMID: 27084946); Nat Biotechnol. 2015 Aug;33(8):831-8. (PMID: 26213851); Bioinformatics. 2021 Jul 12;37(11):1607-1609. (PMID: 33135764); Genome Biol. 2021 Sep 27;22(1):280. (PMID: 34579793); Nucleic Acids Res. 2020 Jan 8;48(D1):D87-D92. (PMID: 31701148); Nucleic Acids Res. 2015 Jan;43(Database issue):D117-22. (PMID: 25378322); Nat Methods. 2020 Nov;17(11):1111-1117. (PMID: 33046897); Oncoimmunology. 2012 Nov 1;1(8):1376-1386. (PMID: 23243601); Proc Natl Acad Sci U S A. 2020 Oct 13;117(41):25655-25666. (PMID: 32978299); Bioinformatics. 2020 Dec 30;36(Suppl_2):i634-i642. (PMID: 33381817); Nucleic Acids Res. 2013 Nov;41(21):e197. (PMID: 24057214); Nat Immunol. 2013 Aug;14(8):867-75. (PMID: 23812095); Biochim Biophys Acta Gene Regul Mech. 2021 Nov-Dec;1864(11-12):194765. (PMID: 34673265); Genome Biol. 2021 Oct 7;22(1):285. (PMID: 34620190); Nat Genet. 2018 Aug;50(8):1171-1179. (PMID: 30013180); Genome Biol. 2020 May 11;21(1):114. (PMID: 32393327); Nat Mach Intell. 2021 Mar;3(3):258-266. (PMID: 34322657); Nat Rev Genet. 2015 Jun;16(6):321-32. (PMID: 25948244); Nat Rev Genet. 2019 Jul;20(7):389-403. (PMID: 30971806); Genome Res. 2018 May;28(5):739-750. (PMID: 29588361); Nat Commun. 2021 Oct 6;12(1):5863. (PMID: 34615872); Nat Methods. 2013 Dec;10(12):1213-8. (PMID: 24097267); Nat Methods. 2017 Oct;14(10):975-978. (PMID: 28825706); Nucleic Acids Res. 2018 Jan 4;46(D1):D267-D275. (PMID: 29126285); Nat Rev Genet. 2019 May;20(5):257-272. (PMID: 30696980); Protein Sci. 2018 Nov;27(11):1876-1892. (PMID: 30109749); Elife. 2015 Mar 17;4:. (PMID: 25779349); Nat Genet. 2001 Mar;27(3):263-70. (PMID: 11242107); Nat Methods. 2015 Oct;12(10):931-4. (PMID: 26301843); Cell Rep Methods. 2022 Mar 15;2(3):100182. (PMID: 35475224); PLoS Comput Biol. 2019 Dec 19;15(12):e1007560. (PMID: 31856220); Bioinformatics. 2021 Sep 29;37(18):2834-2840. (PMID: 33760053); Protein Cell. 2021 Jan;12(1):29-38. (PMID: 32946061); Science. 2007 Jun 8;316(5830):1497-502. (PMID: 17540862); Bioinformatics. 2010 Oct 15;26(20):2622-3. (PMID: 20736340); J Mol Biol. 1998 Apr 24;278(1):167-81. (PMID: 9571041); Genome Biol. 2007;8(2):R24. (PMID: 17324271); Bioinformatics. 2010 Mar 15;26(6):841-2. (PMID: 20110278); Genome Res. 2016 Jul;26(7):990-9. (PMID: 27197224); Curr Opin Syst Biol. 2020 Feb;19:16-23. (PMID: 32905524) |
| Grant Information: | PJT-162120 Canada CIHR |
| Contributed Indexing: | Keywords: Deep learning; Explainable artificial intelligence; Gene regulation; Genomics; Model interpretation; Transcription factors |
| Substance Nomenclature: | 0 (Chromatin) |
| Entry Date(s): | Date Created: 20230627 Date Completed: 20230629 Latest Revision: 20230703 |
| Update Code: | 20260130 |
| PubMed Central ID: | PMC10303849 |
| DOI: | 10.1186/s13059-023-02985-y |
| PMID: | 37370113 |
| Database: | MEDLINE |
Journal Article; Research Support, Non-U.S. Gov't