Academic Journal
Προβολή σε EDS
Συνδεδεμένο Πλήρες Κείμενο

Gene-Chronos: parameter-efficient developmental time inference using a pretrained single-cell foundation model.

Λεπτομέρειες βιβλιογραφικής εγγραφής
Τίτλος: Gene-Chronos: parameter-efficient developmental time inference using a pretrained single-cell foundation model.
Συγγραφείς: Liu Y; School of Computer Science, Wuhan University, No. 299 Bayi Road, Wuchang District, Wuhan 430072, Hubei, China.; School of Artificial Intelligence, Wuhan University, No. 299 Bayi Road, Wuchang District, Wuhan 430072, Hubei, China., Gao H; School of Mathematics and Statistics, Wuhan University, No. 299 Bayi Road, Wuchang District, Wuhan 430072, Hubei, China., Tian T; School of Computer Science, Wuhan University, No. 299 Bayi Road, Wuchang District, Wuhan 430072, Hubei, China.; School of Artificial Intelligence, Wuhan University, No. 299 Bayi Road, Wuchang District, Wuhan 430072, Hubei, China.
Πηγή: Briefings in bioinformatics [Brief Bioinform] 2026 Sep 01; Vol. 27 (5).
Τύπος έκδοσης: Journal Article
Γλώσσα: English
Στοιχεία περιοδικού: 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
Imprint Name(s): Publication: Oxford : Oxford University Press
Original Publication: London ; Birmingham, AL : H. Stewart Publications, [2000-
Ιατρικοί όροι (MeSH): Single-Cell Analysis*/methods , Gene Expression Regulation, Developmental* , Transcriptome*, Animals ; Single-Cell Gene Expression Analysis ; Gene Expression Profiling ; Spatial Transcriptomics ; Humans
Περίληψη: Large-scale single-cell and spatial transcriptomic atlases enable the study of developmental processes at high resolution. However, most datasets capture only static snapshots of cells, making it difficult to infer continuous biological time from transcriptomic profiles. Existing temporal inference methods often show limited robustness across heterogeneous datasets, and recent single-cell foundation models, although powerful for representation learning, are not designed to capture continuous temporal relationships. We present Gene-Chronos, a parameter-efficient framework for developmental time inference built on a frozen pretrained Geneformer backbone. The model introduces learnable temporal prompt tokens and a temporal contrastive objective to extract time-informative signals and encourage temporally coherent organization of cell representations. Across multiple benchmark datasets spanning diverse species and developmental stages, Gene-Chronos outperforms existing approaches and demonstrates strong generalization to previously unseen samples. Attention-based analyses further identify genes associated with developmental progression, providing interpretable insights into temporal gene expression dynamics.
(© The Author(s) 2026. Published by Oxford University Press.)
References: Nat Methods. 2022 Jan;19(1):41-50. (PMID: 34949812)
J Dev Biol. 2017 Sep;5(3):. (PMID: 29057214)
Nat Biotechnol. 2019 May;37(5):547-554. (PMID: 30936559)
Cell. 2022 May 12;185(10):1777-1792.e21. (PMID: 35512705)
Dev Cell. 2022 May 23;57(10):1284-1298.e5. (PMID: 35512701)
Nat Commun. 2021 May 28;12(1):3222. (PMID: 34050150)
Nat Methods. 2024 Aug;21(8):1470-1480. (PMID: 38409223)
Nat Methods. 2022 Feb;19(2):159-170. (PMID: 35027767)
Mol Biol Cell. 2011 Nov;22(21):4047-58. (PMID: 21900491)
Nature. 2019 Feb;566(7745):496-502. (PMID: 30787437)
Bioinformatics. 2022 Jun 24;38(Suppl 1):i290-i298. (PMID: 35758781)
Front Physiol. 2014 Jan 28;5:3. (PMID: 24478716)
Nature. 2023 Jun;618(7965):616-624. (PMID: 37258680)
Nat Cell Biol. 2025 Nov;27(11):1982-1992. (PMID: 41152557)
Nat Methods. 2025 Dec;22(12):2525-2538. (PMID: 41168487)
Nat Methods. 2024 Aug;21(8):1481-1491. (PMID: 38844628)
Science. 2022 Aug 5;377(6606):eabn5800. (PMID: 35926038)
Grant Information: 2042025kf0038 Lei Jun Foundation Limited and the Fundamental Research Funds for the Central Universities
Contributed Indexing: Keywords: developmental time inference; single-cell transcriptomics; spatial transcriptomics; transfer generalization
Entry Date(s): Date Created: 20260904 Date Completed: 20260904 Latest Revision: 20260907
Update Code: 20260907
PubMed Central ID: PMC13544629
DOI: 10.1093/bib/bbag469
PMID: 42696754
Βάση Δεδομένων: MEDLINE
FullText Links:
  – Type: other
    Url: https://resolver.ebsco.com:443/public/rma-ftfapi/ejs/direct?AccessToken=48E9A061870969828D64&Show=Object
Text:
  Availability: 0
Header DbId: cmedm
DbLabel: MEDLINE
An: 42696754
AccessLevel: 3
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Gene-Chronos: parameter-efficient developmental time inference using a pretrained single-cell foundation model.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AU" term="%22Liu+Y%22">Liu Y</searchLink>; School of Computer Science, Wuhan University, No. 299 Bayi Road, Wuchang District, Wuhan 430072, Hubei, China.; School of Artificial Intelligence, Wuhan University, No. 299 Bayi Road, Wuchang District, Wuhan 430072, Hubei, China.<br /><searchLink fieldCode="AU" term="%22Gao+H%22">Gao H</searchLink>; School of Mathematics and Statistics, Wuhan University, No. 299 Bayi Road, Wuchang District, Wuhan 430072, Hubei, China.<br /><searchLink fieldCode="AU" term="%22Tian+T%22">Tian T</searchLink>; School of Computer Science, Wuhan University, No. 299 Bayi Road, Wuchang District, Wuhan 430072, Hubei, China.; School of Artificial Intelligence, Wuhan University, No. 299 Bayi Road, Wuchang District, Wuhan 430072, Hubei, China.
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22100912837%22">Briefings in bioinformatics</searchLink> [Brief Bioinform] 2026 Sep 01; Vol. 27 (5).
– Name: TypePub
  Label: Publication Type
  Group: TypPub
  Data: Journal Article
– Name: Language
  Label: Language
  Group: Lang
  Data: English
– Name: TitleSource
  Label: Journal Info
  Group: Src
  Data: <i>Publisher: </i><searchLink fieldCode="PB" term="%22Oxford+University+Press%22">Oxford University Press </searchLink><i>Country of Publication: </i>England <i>NLM ID: </i>100912837 <i>Publication Model: </i>Print <i>Cited Medium: </i>Internet <i>ISSN: </i>1477-4054 (Electronic) <i>Linking ISSN: </i><searchLink fieldCode="IS" term="%2214675463%22">14675463 </searchLink><i>NLM ISO Abbreviation: </i>Brief Bioinform <i>Subsets: </i>MEDLINE
– Name: PublisherInfo
  Label: Imprint Name(s)
  Group: PubInfo
  Data: <i>Publication</i>: Oxford : Oxford University Press<br /><i>Original Publication</i>: London ; Birmingham, AL : H. Stewart Publications, [2000-
– Name: SubjectMESH
  Label: MeSH Terms
  Group: Su
  Data: <searchLink fieldCode="MM" term="%22Single-Cell+Analysis%22">Single-Cell Analysis*</searchLink>/<searchLink fieldCode="MM" term="%22Single-Cell+Analysis+methods%22">methods</searchLink> <br /><searchLink fieldCode="MM" term="%22Gene+Expression+Regulation%2C+Developmental%22">Gene Expression Regulation, Developmental*</searchLink> <br /><searchLink fieldCode="MM" term="%22Transcriptome%22">Transcriptome*</searchLink><br /><searchLink fieldCode="MH" term="%22Animals%22">Animals</searchLink> ; <searchLink fieldCode="MH" term="%22Single-Cell+Gene+Expression+Analysis%22">Single-Cell Gene Expression Analysis</searchLink> ; <searchLink fieldCode="MH" term="%22Gene+Expression+Profiling%22">Gene Expression Profiling</searchLink> ; <searchLink fieldCode="MH" term="%22Spatial+Transcriptomics%22">Spatial Transcriptomics</searchLink> ; <searchLink fieldCode="MH" term="%22Humans%22">Humans</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Large-scale single-cell and spatial transcriptomic atlases enable the study of developmental processes at high resolution. However, most datasets capture only static snapshots of cells, making it difficult to infer continuous biological time from transcriptomic profiles. Existing temporal inference methods often show limited robustness across heterogeneous datasets, and recent single-cell foundation models, although powerful for representation learning, are not designed to capture continuous temporal relationships. We present Gene-Chronos, a parameter-efficient framework for developmental time inference built on a frozen pretrained Geneformer backbone. The model introduces learnable temporal prompt tokens and a temporal contrastive objective to extract time-informative signals and encourage temporally coherent organization of cell representations. Across multiple benchmark datasets spanning diverse species and developmental stages, Gene-Chronos outperforms existing approaches and demonstrates strong generalization to previously unseen samples. Attention-based analyses further identify genes associated with developmental progression, providing interpretable insights into temporal gene expression dynamics.<br /> (© The Author(s) 2026. Published by Oxford University Press.)
– Name: Ref
  Label: References
  Group: RefInfo
  Data: Nat Methods. 2022 Jan;19(1):41-50. (PMID: <searchLink fieldCode="PM" term="%2234949812%22">34949812)</searchLink><br />J Dev Biol. 2017 Sep;5(3):. (PMID: <searchLink fieldCode="PM" term="%2229057214%22">29057214)</searchLink><br />Nat Biotechnol. 2019 May;37(5):547-554. (PMID: <searchLink fieldCode="PM" term="%2230936559%22">30936559)</searchLink><br />Cell. 2022 May 12;185(10):1777-1792.e21. (PMID: <searchLink fieldCode="PM" term="%2235512705%22">35512705)</searchLink><br />Dev Cell. 2022 May 23;57(10):1284-1298.e5. (PMID: <searchLink fieldCode="PM" term="%2235512701%22">35512701)</searchLink><br />Nat Commun. 2021 May 28;12(1):3222. (PMID: <searchLink fieldCode="PM" term="%2234050150%22">34050150)</searchLink><br />Nat Methods. 2024 Aug;21(8):1470-1480. (PMID: <searchLink fieldCode="PM" term="%2238409223%22">38409223)</searchLink><br />Nat Methods. 2022 Feb;19(2):159-170. (PMID: <searchLink fieldCode="PM" term="%2235027767%22">35027767)</searchLink><br />Mol Biol Cell. 2011 Nov;22(21):4047-58. (PMID: <searchLink fieldCode="PM" term="%2221900491%22">21900491)</searchLink><br />Nature. 2019 Feb;566(7745):496-502. (PMID: <searchLink fieldCode="PM" term="%2230787437%22">30787437)</searchLink><br />Bioinformatics. 2022 Jun 24;38(Suppl 1):i290-i298. (PMID: <searchLink fieldCode="PM" term="%2235758781%22">35758781)</searchLink><br />Front Physiol. 2014 Jan 28;5:3. (PMID: <searchLink fieldCode="PM" term="%2224478716%22">24478716)</searchLink><br />Nature. 2023 Jun;618(7965):616-624. (PMID: <searchLink fieldCode="PM" term="%2237258680%22">37258680)</searchLink><br />Nat Cell Biol. 2025 Nov;27(11):1982-1992. (PMID: <searchLink fieldCode="PM" term="%2241152557%22">41152557)</searchLink><br />Nat Methods. 2025 Dec;22(12):2525-2538. (PMID: <searchLink fieldCode="PM" term="%2241168487%22">41168487)</searchLink><br />Nat Methods. 2024 Aug;21(8):1481-1491. (PMID: <searchLink fieldCode="PM" term="%2238844628%22">38844628)</searchLink><br />Science. 2022 Aug 5;377(6606):eabn5800. (PMID: <searchLink fieldCode="PM" term="%2235926038%22">35926038)</searchLink>
– Name: GrantInfo
  Label: Grant Information
  Group: Grant
  Data: 2042025kf0038 Lei Jun Foundation Limited and the Fundamental Research Funds for the Central Universities
– Name: SubjectMinor
  Label: Contributed Indexing
  Group:
  Data: <i>Keywords: </i>developmental time inference; single-cell transcriptomics; spatial transcriptomics; transfer generalization
– Name: DateEntry
  Label: Entry Date(s)
  Group: Date
  Data: <i>Date Created: </i>20260904 <i>Date Completed: </i>20260904 <i>Latest Revision: </i>20260907
– Name: DateUpdate
  Label: Update Code
  Group: Date
  Data: 20260907
– Name: PubmedCentralID
  Label: PubMed Central ID
  Group: ID
  Data: PMC13544629
– Name: DOI
  Label: DOI
  Group: ID
  Data: 10.1093/bib/bbag469
– Name: AN
  Label: PMID
  Group: ID
  Data: 42696754
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=cmedm&AN=42696754
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1093/bib/bbag469
    Languages:
      – Code: eng
        Text: English
    Subjects:
      – SubjectFull: Animals
        Type: general
      – SubjectFull: Single-Cell Gene Expression Analysis
        Type: general
      – SubjectFull: Gene Expression Profiling
        Type: general
      – SubjectFull: Spatial Transcriptomics
        Type: general
      – SubjectFull: Humans
        Type: general
      – SubjectFull: Single-Cell Analysis methods
        Type: general
      – SubjectFull: Gene Expression Regulation, Developmental
        Type: general
      – SubjectFull: Transcriptome
        Type: general
    Titles:
      – TitleFull: Gene-Chronos: parameter-efficient developmental time inference using a pretrained single-cell foundation model.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Liu Y
      – PersonEntity:
          Name:
            NameFull: Gao H
      – PersonEntity:
          Name:
            NameFull: Tian T
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 09
              Text: 2026 Sep 01
              Type: published
              Y: 2026
          Identifiers:
            – Type: issn-electronic
              Value: 1477-4054
          Numbering:
            – Type: volume
              Value: 27
            – Type: issue
              Value: 5
          Titles:
            – TitleFull: Briefings in bioinformatics
              Type: main
ResultId 1