CoChat
Sign Up
Cited by 148Single-cell and spatial transcriptomicsGene Regulatory Network AnalysisGenomics and Chromatin Dynamics

GeneCompass: deciphering universal gene regulatory mechanisms with a knowledge-informed cross-species foundation model

Open access
Yang, Xiaodong, Liu, Guole, Feng, Guihai, Bu, Dechao, Wang, Pengfei, Jiang, Jie, Chen, Shubai, Yang, Qinmeng +133 more·2024·Cell Research
DOI 10.1038/s41422-024-01034-yPMC PMC11615217

Published version of a preprint

Open this paper in CoChat — free account

Abstract

Deciphering universal gene regulatory mechanisms in diverse organisms holds great potential for advancing our knowledge of fundamental life processes and facilitating clinical applications. However, the traditional research paradigm primarily focuses on individual model organisms and does not integrate various cell types across species. Recent breakthroughs in single-cell sequencing and deep learning techniques present an unprecedented opportunity to address this challenge. In this study, we built an extensive dataset of over 120 million human and mouse single-cell transcriptomes. After data preprocessing, we obtained 101,768,420 single-cell transcriptomes and developed a knowledge-informed cross-species foundation model, named GeneCompass. During pre-training, GeneCompass effectively integrated four types of prior biological knowledge to enhance our understanding of gene regulatory mechanisms in a self-supervised manner. By fine-tuning for multiple downstream tasks, GeneCompass outperformed state-of-the-art models in diverse applications for a single species and unlocked new realms of cross-species biological investigations. We also employed GeneCompass to search for key factors associated with cell fate transition and showed that the predicted candidate genes could successfully induce the differentiation of human embryonic stem cells into the gonadal fate. Overall, GeneCompass demonstrates the advantages of using artificial intelligence technology to decipher universal gene regulatory mechanisms and shows tremendous potential for accelerating the discovery of critical cell fate regulators and candidate drug targets.

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1038/s41422-024-01034-y

Cites

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • Yang et al. developed GeneCompass, a knowledge-informed cross-species foundation model for understanding universal gene regulatory mechanisms.

    “Yang et al. developed GeneCompass, a knowledge-informed cross-species foundation model for understanding the universal gene regulatory mechanisms [190].”

    From Challenges in AI-driven Biomedical Multimodal Data Fusion and Analysis (2025) · cites this paper as [190]

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

The citation lists haven’t been fetched yet

References 75 · Cited by 148

Research works printed but not linked: 42

  1. [3]Hwang, B., Lee, J. H. & Bang, D. Single-cell RNA sequencing technologies and bioinformatics pipelines. Exp. Mol. Med. 50, 1–14 (2018). 30089861 PMC6082860 · DOI
  2. [4]Zhu, C., Preissl, S. & Ren, B. Single-cell multimodal omics: the power of many. Nat. Methods 17, 11–14 (2020). 31907462 · DOI · Paper page
  3. [5]Li, M. & Belmonte, J. C. I. Ground rules of the pluripotency gene regulatory network. Nat. Rev. Genet. 18, 180–191 (2017). 28045100 · DOI
  4. [6]Halfon, M. S. Perspectives on gene regulatory network evolution. Trends Genet. 33, 436–447 (2017). 28528721 PMC5608025 · DOI
  5. [7]Angermueller, C., Pärnamaa, T., Parts, L. & Stegle, O. Deep learning for computational biology. Mol. Syst. Biol. 12, 878 (2016). 27474269 PMC4965871 · DOI · Paper page
  6. [8]Devlin, J. Bert: Pre-training of deep bidirectional transformers for language understanding. ArXiv 10.48550/arXiv.1810.04805 (2018). · DOI · Paper page
  7. [9]OpenAI. GPT-4 technical report. ArXiv10.48550/arXiv.2303.08774 (2023).
  8. [10]Anil, R. et al. Palm 2 technical report. ArXiv10.48550/arXiv.2305.10403 (2023).
  9. [12]Touvron, H. et al. Llama: Open and efficient foundation language models. ArXiv10.48550/arXiv.2302.13971 (2023).
  10. [16]Rosen, Y. et al. Universal cell embeddings: a foundation model for cell biology. bioRxiv 10.1101/2023.11.28.568918 (2023).38168360 · DOI
  11. [18]Berthelot, C., Villar, D., Horvath, J. E., Odom, D. T. & Flicek, P. Complexity and conservation of regulatory landscapes underlie evolutionary resilience of mammalian gene expression. Nat. Ecol. Evol. 2, 152–163 (2018). 29180706 PMC5733139 · DOI
  12. [19]Thompson, D., Regev, A. & Roy, S. Comparative analysis of gene regulatory networks: from network reconstruction to evolution. Annu. Rev. Cell Dev. Biol. 31, 399–428 (2015). 26355593 · DOI
  13. [20]Consortium, T. S. et al. The Tabula Sapiens: a multiple-organ, single-cell transcriptomic atlas of humans. Science 376, eabl4896 (2022). 35549404 PMC9812260 · DOI · Paper page
  14. [21]Papatheodorou, I. et al. Expression Atlas update: from tissues to single cells. Nucleic Acids Res. 48, D77–D83 (2019). PMC7145605 31665515
  15. [22]Wang, R. et al. Construction of a cross-species cell landscape at single-cell level. Nucleic Acids Res. 51, 501–516 (2022). PMC9881150 35929025 · DOI
  16. [23]Vaswani, A. et al. Attention is all you need. Adv. Neural Inform. Proc. Syst. 30 (2017).
  17. [24]Ji, Y., Zhou, Z., Liu, H. & Davuluri, R. V. DNABERT: pre-trained bidirectional encoder representations from transformers model for DNA-language in genome. Bioinformatics 37, 2112–2120 (2021). 33538820 PMC11025658 · DOI · Paper page
  18. [25]Du, J. et al. Gene2vec: distributed representation of genes based on co-expression. BMC Genomics 20, 7–15 (2019). 30712510 PMC6360648 · DOI · Paper page
  19. [26]Hrycaj, S. M. & Wellik, D. M. Hox genes and evolution. F1000Res. 5, 859 (2016). PMC4863668 27239281
  20. [27]Ang, Y.-S. et al. Disease model of GATA4 mutation reveals transcription factor cooperativity in human cardiogenesis. Cell 167, 1734–1749.e22 (2016). 27984724 PMC5180611 · DOI · Paper page
  21. [28]Cao, J. et al. A human cell atlas of fetal gene expression. Science 370, eaba7721 (2020). 33184181 PMC7780123 · DOI · Paper page
  22. [29]Theodoris, C. V. et al. Human disease modeling reveals integrated transcriptional and epigenetic mechanisms of NOTCH1 haploinsufficiency. Cell 160, 1072–1086 (2015). 25768904 PMC4359747 · DOI · Paper page
  23. [30]Anderson, D. J. et al. NKX2-5 regulates human cardiomyogenesis via a HEY2 dependent transcriptional network. Nat. Commun. 9, 1373 (2018). 29636455 PMC5893543 · DOI
  24. [32]Shu, H. et al. Modeling gene regulatory networks using neural network architectures. Nat. Comput. Sci. 1, 491–501 (2021). 38217125 · DOI
  25. [33]Lotfollahi, M. et al. Predicting cellular responses to complex perturbations in high‐throughput screens. Mol. Syst. Biol. 19, e11517 (2023). 37154091 PMC10258562 · DOI · Paper page
  26. [34]Pham, T.-H., Qiu, Y., Zeng, J., Xie, L. & Zhang, P. A deep learning framework for high-throughput mechanism-driven phenotype compound screening and its application to COVID-19 drug repurposing. Nat. Mach. Intell. 3, 247–257 (2021). 33796820 PMC8009091 · DOI
  27. [36]Norman, T. M. et al. Exploring genetic interaction manifolds constructed from rich single-cell phenotypes. Science 365, 786–793 (2019). 31395745 PMC6746554 · DOI · Paper page
  28. [37]Takahashi, K. & Yamanaka, S. Induction of pluripotent stem cells from mouse embryonic and adult fibroblast cultures by defined factors. Cell 126, 663–676 (2006). 16904174 · DOI · Paper page
  29. [38]Garipler, G. et al. The BTB transcription factors ZBTB11 and ZFP131 maintain pluripotency by repressing pro-differentiation genes. Cell Rep. 38, 110524 (2022). 35294876 PMC8972945 · DOI
  30. [39]Wen, Q. et al. Wt1 dictates the fate of fetal and adult Leydig cells during development in the mouse testis. Am. J. Physiol. Endocrinol. Metab. 307, E1131–E1143 (2014). 25336526 PMC6189632 · DOI
  31. [40]Sekido, R. & Lovell-Badge, R. Sex determination involves synergistic action of SRY and SF1 on a specific Sox9 enhancer. Nature 456, 824–824 (2008). 18454134 · DOI
  32. [41]Anamthathmakula, P. et al. Steroidogenic factor 1 (Nr5a1) is required for Sertoli cell survival post sex determination. Sci. Rep. 9, 4452 (2019). PMC6418149 30872705
  33. [42]Shen, Y.-C. et al. TCF21+ mesenchymal cells contribute to testis somatic cell development, homeostasis, and regeneration in mice. Nat. Commun. 12, 3876 (2021). 34162856 PMC8222243 · DOI
  34. [43]Guo, J. et al. Single-cell analysis of the developing human testis reveals somatic niche cell specification and fetal germline stem cell establishment. Cell Stem Cell 28, 764–778.e4 (2021). 33453151 PMC8026516 · DOI
  35. [44]Garcia-Alonso, L. et al. Single-cell roadmap of human gonadal development. Nature 607, 540–547 (2022). 35794482 PMC9300467 · DOI
  36. [45]Karpova, T. et al. Steroidogenic factor 1 differentially regulates fetal and adult Leydig cell development in male mice. Biol. Reprod. 93, 81–15 (2015). PMC4711904 26269506 · DOI
  37. [47]Wolf, T. et al. Huggingface’s transformers: State-of-the-art natural language processing. ArXiv10.48550/arXiv.1910.03771 (2019).
  38. [48]Duren, Z., Chen, X., Xin, J., Wang, Y. & Wong, W. H. Time course regulatory analysis based on paired expression and chromatin accessibility data. Genome Res. 30, 622–634 (2020). 32188700 PMC7197475 · DOI
  39. [49]Liu, X. Y., Shen, Q. L. & Zhang, S. H. Cross-species cell-type assignment from single-cell RNA-seq data by a heterogeneous graph neural network. Genome Res. 33, 96–111 (2023). 36526433 PMC9977153 · DOI
  40. [50]Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J. & Wojna, Z. Rethinking the inception architecture for computer vision. IEEE Conf. Comput. Vis. Pattern. Recog. 33, 2818–2826 (2016).
  41. [51]Kingma, D. P. Adam: a method for stochastic optimization. ArXiv10.48550/arXiv.1412.6980 (2014).
  42. [52]Szklarczyk, D. et al. STRING v11: protein–protein association networks with increased coverage, supporting functional discovery in genome-wide experimental datasets. Nucleic Acids Res. 47, D607–D613 (2019). 30476243 PMC6323986 · DOI · Paper page

Authors
Yang, X., Liu, G., Feng, G., Bu, D., Wang, P., Jiang, J., Chen, S., Yang, Q., Miao, H., Zhang, Y., Man, Z., Liang, Z., Wang, Z., Li, Y., Li, Z., Liu, Y., Tian, Y., Liu, W., Li, C., Li, A., Dong, J., Hu, Z., Fang, C., Cui, L., Deng, Z., Jiang, H., Cui, W., Zhang, J., Yang, Z., Li, H., He, X., Zhong, L., Zhou, J., Wang, Z., Long, Q., Xu, P., The X-Compass Consortium, Li, X., Wang, H., Hu, B., Li, W., Gao, F., Guo, J., Yu, L., Gu, Q., Zhai, W., Zou, Z., Feng, G., Liu, W., Tian, Y., Fang, C., Dong, J., Liu, Y., Yu, J., Wu, W., Lin, X., Li, C., Zou, Y., Ren, Y., Li, F., Zhao, Y., Xin, Y., Han, L., Jiang, S., Ma, K., Chen, Q., Wang, H., Wu, H., He, C., Hu, Y., Guo, S., Li, Y., Zhou, Y., Wang, Y., Wang, X., Wang, P., Li, F., Meng, Z., Wang, Z., Xu, P., Cui, W., Hu, Z., He, H., Zong, S., Wang, J., Chen, Y., Zhang, C., Wang, C., Zhang, R., Xiao, M., Wang, Y., Chen, Y., Zhao, Y., Yang, X., Bu, D., Qin, X., Qin, J., Yang, Z., Li, C., Xu, Z., Zhang, Z., Qi, X., Chen, S., Huang, W., Li, Y., Yang, G., Liu, J., Liu, G., Zhong, L., Luo, Y., Zhou, J., Wang, Z., Luo, Q., Liu, Z., Li, A., Wang, T., Huang, Y., Li, H., Wang, Y., Zhang, S., Zhang, J., Zhang, Y., Li, S., Liang, Z., Man, Z., Dong, K., Shen, Q., Wang, H., Meng, Z., Wang, X., Wang, Y., Wang, Y., Zhang, S., Guo, J., Zhao, Y., Zhou, Y., Li, F., Liu, J., Chen, Y., Yang, G., & Li, X.
Affiliations
Chinese Academy of Sciences (CN)
Corresponding author
  • Li, Fan
  • Zhao, Yixiao
  • Chen, Yan
ORCID
Venue
Cell Research
Publisher
Springer Science and Business Media LLC
Published
2024-10-08
Volume
34
Issue
12
Pages
830-845
ISSN
  • 1001-0602 (ISSN-L)
  • 1748-7838
DOI
10.1038/s41422-024-01034-y
PMC
PMC11615217
OpenAlex
W4403174218
Cited by
148
References
75
Citations by year
2026: 63 · 2025: 63 · 2024: 20 · 2023: 1
FWCI
19.88
Type
journal article
Language
en
Open access
Licence
Locations
  • Cell Research (publishedVersion, cc-by)
  • bioRxiv (Cold Spring Harbor Laboratory) (acceptedVersion)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
Funders
  • National Natural Science Foundation of China (62202455, No.91954201, No.32341013, 31971289, 91954201, No.62202455, No.31971289, 32341019, 32341013)
  • Chinese Academy of Sciences (YSBR‐076, CAS-WX2021SF-0101, YSBR-034)
  • Institute of Zoology, Chinese Academy of Sciences
Topics
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Single-cell and spatial transcriptomics
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Gene Regulatory Network Analysis
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Genomics and Chromatin Dynamics
Keywords
gene regulatory mechanisms, single-cell transcriptomics, self-supervised learning, cell fate transitions, gonadal differentiation, human embryonic stem cells, drug target identification
MeSH terms
Animals, Cell Differentiation, Gene Expression Regulation, Humans, Species Specificity, Mice, Gene Regulatory Networks, Single-Cell Analysis, Transcriptome

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review