Reliable Identification and Interpretation of Single‐Cell Molecular Heterogeneity and Transcriptional Regulation using Dynamic Ensemble Pruning
Source abstract
Abstract
Abstract Unsupervised clustering is an essential step in identifying cell types from single‐cell RNA sequencing (scRNA‐seq) data. However, a common issue with unsupervised clustering models is that the optimization direction of the objective function and the final generated clustering labels in the absence of supervised information may be inconsistent or even arbitrary. To address this challenge, a dynamic ensemble pruning framework (DEPF) is proposed to identify and interpret single‐cell molecular heterogeneity. In particular, a silhouette coefficient‐based indicator is developed to determine the optimization direction of the bi‐objective function. In addition, a hierarchical autoencoder is employed to project the high‐dimensional data onto multiple low‐dimensional latent space sets, and then a clustering ensemble is produced in the latent space by the basic clustering algorithm. Following that, a bi‐objective fruit fly optimization algorithm is designed to prune dynamically the low‐quality basic clustering in the ensemble. Multiple experiments are conducted on 28 real scRNA‐seq datasets and one large real scRNA‐seq dataset from diverse platforms and species to validate the effectiveness of the DEPF. In addition, biological interpretability and transcriptional and post‐transcriptional regulatory are conducted to explore biological patterns from the cell types identified, which could provide novel insights into characterizing the mechanisms.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Single-cell and spatial transcriptomics · Gene Regulatory Network Analysis · Cell Image Analysis Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Artificial Intelligence Jilin University Jilin China
School of Artificial Intelligence Hebei University of Technology Tianjin China
Department of Computer Science City University of Hong Kong Kowloon Hong Kong
Donnelly Centre for Cellular and Biomolecular Research University of Toronto Toronto ON Canada
References (91)
Show source-provided references
1. 10.1038/s41576-018-0088-910.1038/s41576-018-0088-9 ↗
2. 10.1038/s41467-019-13993-710.1038/s41467-019-13993-7 ↗
3. 10.1109/TIT.1982.105648910.1109/TIT.1982.1056489 ↗
4. 10.1007/BF0228958810.1007/BF02289588 ↗
5. 10.1103/PhysRevE.80.05611710.1103/PhysRevE.80.056117 ↗
6. 10.1371/journal.pcbi.100457510.1371/journal.pcbi.1004575 ↗
7. 10.1038/nmeth.423610.1038/nmeth.4236 ↗
8. 10.1186/s13059-016-1139-110.1186/s13059-016-1139-1 ↗
9. 10.1038/nbt.409610.1038/nbt.4096 ↗
10. 10.1186/s13059-017-1382-010.1186/s13059-017-1382-0 ↗
11. 10.1093/bioinformatics/bty79310.1093/bioinformatics/bty793 ↗
12. 10.1101/gr.254557.11910.1101/gr.254557.119 ↗
13. 10.1093/nar/gkz95910.1093/nar/gkz959 ↗
14. 10.1038/nmeth.420710.1038/nmeth.4207 ↗
15. 10.1038/s41598-020-79139-810.1038/s41598-020-79139-8 ↗
16. 10.1038/s41467-020-20314-w10.1038/s41467-020-20314-w ↗
17. 10.1038/s41467-020-20314-w10.1038/s41467-020-20314-w ↗
18. 10.1016/j.knosys.2011.07.00110.1016/j.knosys.2011.07.001 ↗
19. 10.1109/TSMC.2016.261634710.1109/TSMC.2016.2616347 ↗
20. 10.1038/s41588-020-0636-z10.1038/s41588-020-0636-z ↗
21. 10.1038/s41590-018-0276-y10.1038/s41590-018-0276-y ↗
22. 10.1093/nar/gky90010.1093/nar/gky900 ↗
23. 10.1016/j.cellimm.2020.10426010.1016/j.cellimm.2020.104260 ↗
24. 10.1016/j.celrep.2022.11129510.1016/j.celrep.2022.111295 ↗
25. 10.1038/s41420-021-00550-910.1038/s41420-021-00550-9 ↗
26. 10.1038/s41523-022-00466-210.1038/s41523-022-00466-2 ↗
27. 10.1016/j.biochi.2007.04.00610.1016/j.biochi.2007.04.006 ↗
28. 10.1002/jcb.2549610.1002/jcb.25496 ↗
29. 10.1016/j.cell.2017.10.04410.1016/j.cell.2017.10.044 ↗
30. 10.1038/s41572-020-00224-310.1038/s41572-020-00224-3 ↗
31. 10.1089/omi.2011.011810.1089/omi.2011.0118 ↗
32. 10.3390/cells902036810.3390/cells9020368 ↗
33. 10.1093/nar/gkaa107410.1093/nar/gkaa1074 ↗
34. 10.1093/nar/gkz24010.1093/nar/gkz240 ↗
35. Fornes O. · Nucleic Acids Res. · 2019 · 48 · D87
36. 10.1152/ajpheart.00740.201910.1152/ajpheart.00740.2019 ↗
37. 10.1165/rcmb.2019-0396OC10.1165/rcmb.2019-0396OC ↗
38. Huang H.‐Y. · Nucleic Acids Res. · 2019 · 48 · D148
39. 10.17219/acem/13175310.17219/acem/131753 ↗
40. 10.1093/bioinformatics/btv31310.1093/bioinformatics/btv313 ↗
41. 10.1056/NEJMoa05522910.1056/NEJMoa055229 ↗
42. 10.1016/j.cell.2008.09.00210.1016/j.cell.2008.09.002 ↗
43. 10.1016/S2352-3026(21)00134-410.1016/S2352-3026(21)00134-4 ↗
44. 10.1016/j.intimp.2019.10597310.1016/j.intimp.2019.105973 ↗
45. Wawruszak A. · Cancers · 2021 · 13 · 14
46. 10.1016/j.csbj.2021.05.01510.1016/j.csbj.2021.05.015 ↗
47. 10.1038/nsmb.266010.1038/nsmb.2660 ↗
48. 10.1016/j.cell.2016.01.04710.1016/j.cell.2016.01.047 ↗
49. 10.1126/science.124531610.1126/science.1245316 ↗
50. 10.1038/nbt.296710.1038/nbt.2967 ↗
51. 10.1126/science.125425710.1126/science.1254257 ↗
52. 10.2337/db16-040510.2337/db16-0405 ↗
53. 10.1073/pnas.150712511210.1073/pnas.1507125112 ↗
54. 10.1073/pnas.152076011210.1073/pnas.1520760112 ↗
55. 10.1038/nn.388110.1038/nn.3881 ↗
56. 10.1016/j.stem.2015.09.01110.1016/j.stem.2015.09.011 ↗
57. 10.1016/j.cmet.2016.08.01810.1016/j.cmet.2016.08.018 ↗
58. 10.1016/j.cels.2016.08.01110.1016/j.cels.2016.08.011 ↗
59. 10.1016/j.cels.2016.09.00210.1016/j.cels.2016.09.002 ↗
60. 10.1016/j.cmet.2016.08.02010.1016/j.cmet.2016.08.020 ↗
61. 10.1016/j.cell.2015.04.04410.1016/j.cell.2015.04.044 ↗
62. 10.1038/nn.446210.1038/nn.4462 ↗
63. 10.1126/science.aaa193410.1126/science.aaa1934 ↗
64. 10.1126/science.aaf120410.1126/science.aaf1204 ↗
65. 10.1038/s41586-018-0393-710.1038/s41586-018-0393-7 ↗
66. 10.1016/j.celrep.2017.03.00410.1016/j.celrep.2017.03.004 ↗
67. 10.1016/j.immuni.2019.03.00910.1016/j.immuni.2019.03.009 ↗
68. 10.1016/j.cell.2015.05.00210.1016/j.cell.2015.05.002 ↗
69. 10.1038/s41593-017-0029-510.1038/s41593-017-0029-5 ↗
70. 10.1038/s41586-018-0590-410.1038/s41586-018-0590-4 ↗
71. 10.1038/s41467-020-16159-y10.1038/s41467-020-16159-y ↗
72. 10.1016/j.celrep.2019.12.08210.1016/j.celrep.2019.12.082 ↗
73. 10.1109/TKDE.2019.290341010.1109/TKDE.2019.2903410 ↗
74. Nguyen N. · 2007 · 607
75. 10.1145/274264210.1145/2742642 ↗
76. 10.1016/0377-0427(87)90125-710.1016/0377-0427(87)90125-7 ↗
77. 10.1109/TCYB.2017.270234310.1109/TCYB.2017.2702343 ↗
78. 10.1007/BF0190807510.1007/BF01908075 ↗
79. 10.1162/15324430332189773510.1162/153244303321897735 ↗
80. Cover T. M. · 1999
81. 10.1080/01621459.1971.1048235610.1080/01621459.1971.10482356 ↗
82. 10.1109/BIBM49941.2020.931356910.1109/BIBM49941.2020.9313569 ↗
83. 10.1093/nargab/lqaa03910.1093/nargab/lqaa039 ↗
84. 10.1038/s41467-018-07931-210.1038/s41467-018-07931-2 ↗
85. J.Xie R.Girshick A.Farhadi inInt. Conf. on machine learning PMLR 2016 48 pp.478–487.
86. 10.1093/bioinformatics/btx16710.1093/bioinformatics/btx167 ↗
87. 10.1109/TSMC.2018.287620210.1109/TSMC.2018.2876202 ↗
88. 10.1109/TKDE.2014.231651210.1109/TKDE.2014.2316512 ↗
89. 10.1162/15324430332189773510.1162/153244303321897735 ↗
90. 10.1109/TKDE.2015.250375310.1109/TKDE.2015.2503753 ↗
91. 10.1109/TKDE.2017.265022910.1109/TKDE.2017.2650229 ↗