Species-agnostic transfer learning for cross-species transcriptomics data integration without gene orthology.

Publisher: Oxford University Press Country of Publication: England NLM ID: 100912837 Publication Model: Print Cited Medium: Internet ISSN: 1477-4054 (Electronic) Linking ISSN: 14675463 NLM ISO Abbreviation: Brief Bioinform Subsets: MEDLINE

Publication: Oxford : Oxford University Press
Original Publication: London ; Birmingham, AL : H. Stewart Publications, [2000-

Algorithms* ; Zebrafish*/genetics; Mice ; Humans ; Animals ; Gene Expression Profiling ; Species Specificity ; Machine Learning

Novel hypotheses in biomedical research are often developed or validated in model organisms such as mice and zebrafish and thus play a crucial role. However, due to biological differences between species, translating these findings into human applications remains challenging. Moreover, commonly used orthologous gene information is often incomplete and entails a significant information loss during gene-id conversion. To address these issues, we present a novel methodology for species-agnostic transfer learning with heterogeneous domain adaptation. We extended the cross-domain structure-preserving projection toward out-of-sample prediction. Our approach not only allows knowledge integration and translation across various species without relying on gene orthology but also identifies similar GO among the most influential genes composing the latent space for integration. Subsequently, during the alignment of latent spaces, each composed of species-specific genes, it is possible to identify functional annotations of genes missing from public orthology databases. We evaluated our approach with four different single-cell sequencing datasets focusing on cell-type prediction and compared it against related machine-learning approaches. In summary, the developed model outperforms related methods working without prior knowledge when predicting unseen cell types based on other species' data. The results demonstrate that our novel approach allows knowledge transfer beyond species barriers without the dependency on known gene orthology but utilizing the entire gene sets.
(© The Author(s) 2024. Published by Oxford University Press.)

Brief Bioinform. 2021 Nov 5;22(6):. (PMID: 34351383)
Nat Biotechnol. 2021 Oct;39(10):1202-1215. (PMID: 33941931)
Cell Syst. 2016 Oct 26;3(4):346-360.e4. (PMID: 27667365)
Nat Biotechnol. 2024 Feb;42(2):243-246. (PMID: 37156916)
Cell. 2021 Jun 24;184(13):3573-3587.e29. (PMID: 34062119)
BMC Bioinformatics. 2023 Jun 8;24(1):242. (PMID: 37291492)
Sci Signal. 2020 Aug 04;13(643):. (PMID: 32753478)
Cell Metab. 2016 Oct 11;24(4):593-607. (PMID: 27667667)
Protein Sci. 2022 Jan;31(1):8-22. (PMID: 34717010)
Nat Commun. 2019 Jan 23;10(1):390. (PMID: 30674886)
Genome Res. 2021 Oct;31(10):1781-1793. (PMID: 33627475)
Nat Commun. 2023 Oct 14;14(1):6495. (PMID: 37838716)
Elife. 2021 May 04;10:. (PMID: 33944782)
Cell Syst. 2019 Aug 28;9(2):207-213.e2. (PMID: 31377170)
Commun Biol. 2020 Dec 4;3(1):736. (PMID: 33277618)
Nucleic Acids Res. 2023 Jul 5;51(W1):W207-W212. (PMID: 37144459)
IEEE Trans Image Process. 2019 Dec;28(12):6103-6115. (PMID: 31251190)
Nature. 2021 Aug;596(7873):583-589. (PMID: 34265844)
IEEE Trans Pattern Anal Mach Intell. 2019 Sep;41(9):2251-2265. (PMID: 30028691)
Front Cell Dev Biol. 2019 Sep 02;7:175. (PMID: 31552245)
Brief Bioinform. 2021 Nov 5;22(6):. (PMID: 34351383)
Nat Rev Genet. 2004 Jan;5(1):69-76. (PMID: 14708017)
Nat Biotechnol. 2018 Jun;36(5):421-427. (PMID: 29608177)
Nat Rev Genet. 2023 Aug;24(8):550-572. (PMID: 37002403)
Genome Biol. 2016 Feb 17;17:29. (PMID: 26887813)
Nat Methods. 2019 Aug;16(8):715-721. (PMID: 31363220)
mBio. 2019 Jan 29;10(1):. (PMID: 30696739)
Nat Commun. 2021 Sep 6;12(1):5261. (PMID: 34489404)
Cell Syst. 2016 Oct 26;3(4):385-394.e3. (PMID: 27693023)
IEEE Trans Pattern Anal Mach Intell. 2023 Apr;45(4):4051-4070. (PMID: 35849673)
BMC Bioinformatics. 2012 May 08;13:84. (PMID: 22568790)
Nat Rev Nephrol. 2021 Nov;17(11):710-724. (PMID: 34417589)
Mol Med. 2018 Aug 30;24(1):46. (PMID: 30165816)
Nat Methods. 2024 Feb 16;:. (PMID: 38366243)
Mol Syst Biol. 2019 Jun 19;15(6):e8746. (PMID: 31217225)
IEEE Trans Neural Netw Learn Syst. 2020 Dec;31(12):5588-5602. (PMID: 32149697)
Nature. 2018 Nov;563(7730):197-202. (PMID: 30356220)
Nat Commun. 2019 Oct 25;10(1):4899. (PMID: 31653878)

01KD2208A German Ministry of Education and Research; International Max Planck Research School for Genome Science; Göttingen Graduate Center for Neurosciences, Biophysics, und Molecular Biosciences

Keywords: cross-species; domain adaptation; single-cell sequencing; transcriptomics; transfer learning

Date Created: 20240202 Date Completed: 20240205 Latest Revision: 20250203

20250204

PMC10835749

10.1093/bib/bbae004

38305455