CoChat
Sign Up
Cited by 42Bioinformatics and Genomic NetworksGene expression and cancer classificationBreast Cancer Treatment Studies

Interpretable meta-learning of multi-omics data for survival analysis and pathway enrichment

Open access
Cho, Hyun Jae, Shu, Mia, Bekiranov, Stefan, Zang, Chongzhi, Zhang, Aidong·2023·Bioinformatics
DOI 10.1093/bioinformatics/btad113PMC PMC10079355
Open this paper in CoChat — free account

Abstract

Motivation: Despite the success of recent machine learning algorithms’ applications to survival analysis, their black-box nature hinders interpretability, which is arguably the most important aspect. Similarly, multi-omics data integration for survival analysis is often constrained by the underlying relationships and correlations that are rarely well understood. The goal of this work is to alleviate the interpretability problem in machine learning approaches for survival analysis and also demonstrate how multi-omics data integration improves survival analysis and pathway enrichment. We use meta-learning, a machine-learning algorithm that is trained on a variety of related datasets and allows quick adaptations to new tasks, to perform survival analysis and pathway enrichment on pan-cancer datasets. In recent machine learning research, meta-learning has been effectively used for knowledge transfer among multiple related datasets. Results: We use meta-learning with Cox hazard loss to show that the integration of TCGA pan-cancer data increases the performance of survival analysis. We also apply advanced model interpretability method called DeepLIFT (Deep Learning Important FeaTures) to show different sets of enriched pathways for multi-omics and transcriptomics data. Our results show that multi-omics cancer survival analysis enhances performance compared with using transcriptomics or clinical data alone. Additionally, we show a correlation between variable importance assignment from DeepLIFT and gene coenrichment, suggesting that genes with higher and similar contribution scores are more likely to be enriched together in the same enrichment sets. Availability and implementation: https://github.com/berkuva/TCGA-omics-integration.

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 · 10.1093/bioinformatics/btad113

Cites

3 of 3 references verified0 citation errors · 0 not checkable

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?

Self-check

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

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

Cites

Flagged first, then by citations

Research works printed but not linked: 68

  1. Alhmoud JF, Woolley JF, Al Moustafa A-E et al DNA damage/repair management in cancers. Cancers 2020; 12: 1050. 32340362 PMC7226105
  2. Alipanahi B, Delong A, Weirauch MT et al Predicting the sequence specificities of DNA- and RNA-binding proteins by deep learning. Nat Biotechnol 2015; 33: 831– 8. 26213851
  3. Bai Y, Wang G, Fu W et al Circulating essential metals and lung cancer: risk assessment and potential molecular effects. Environ Int 2019; 127: 685– 93. 30991224
  4. Chalise P, Fridley BL. Integrative clustering of multi-level ‘omic data based on non-negative matrix factorization algorithm. PLoS One 2017; 12: e0176278. 28459819 PMC5411077
  5. Chang YS, Tu SJ, Chen YC et al Mutation profile of non-small cell lung cancer revealed by next generation sequencing. Respir Res 2021; 22(1):3. 10.1186/s12931-020-01608-5. PMC7789556 33407425 · DOI
  6. Chen C-Y, Kao C-L, Liu C-M et al The cancer prevention, anti-inflammatory and anti-oxidation of bioactive phytochemicals targeting the TLR4 signaling pathway. Int J Mol Sci 2018; 19: 2729. 30213077 PMC6164406
  7. Choi CH. ABC transporters as multidrug resistance mechanisms and the development of chemosensitizers for their reversal. Cancer Cell Int 2005;5:30. 10.1186/1475-2867-5-30. PMC1277830 16202168 · DOI
  8. Chou J et al Analysis of meta-learning approaches for TCGA pan-cancer datasets. In: 2020 IEEE International Conference on Bioinformatics and Biomedicine (BIBM). IEEE. 2020.
  9. Chun YJ, Choi JW, Hong MH, Korean Lung Cancer Consortium (KLCC) et al Molecular characterization of lung adenocarcinoma from korean patients using next generation sequencing. PLoS One 2019; 14: e0224379. 31765373 PMC6876835
  10. Clarke A, Wallis SE. The observed integrated brier score for verifying ensemble forecasts. J R Stat Soc C 2008; 57: 471– 84.
  11. Elfaki I, Mir R, Almutairi FM, Duhier FMA. Cytochrome P450: Polymorphisms and roles in cancer, diabetes and atherosclerosis. Asian Pac J Cancer Prev 2018; 19(8): 2057– 2070. 10.22034/APJCP.2018.19.8.2057. PMC6171375 30139042 · DOI
  12. Fan Y et al TGF-β-induced upregulation of malat1 promotes bladder cancer metastasis by associating with suz12. Clin Cancer Res 2014; 20: 1531– 41. 24449823
  13. Finn C, Abbeel P, Levine S. Model-agnostic meta-learning for fast adaptation of deep networks. In: International Conference on Machine Learning 2017; 1126– 1135.
  14. Furey TS, Cristianini N, Duffy N et al Support vector machine classification and validation of cancer tissue samples using microarray expression data. Bioinformatics 2000; 16: 906– 14. 11120680
  15. Gao Y, Lyu Q, Luo P et al Applications of machine learning to predict cisplatin resistance in lung cancer. Int J Gen Med 2021; 14: 5911– 25. 34588799 PMC8473573
  16. García-Caballero M, Torres-Vargas JA, Marrero AD et al Angioprevention of urologic cancers by plant-derived foods. Pharmaceutics 2022; 14: 256. 35213989 PMC8875200
  17. Huang B, Zhao J, Unkeless JC et al TLR signaling by tumor and immune cells: a double-edged sword. Oncogene 2008; 27: 218– 24. 18176603
  18. Huang R, Zhou P-K. DNA damage repair: historical perspectives, mechanistic pathways and clinical translation for targeted cancer therapy. Sig Transduct Target Ther 2021; 6. PMC8266832 34238917
  19. Imaoka S, Yoneda Y, Sugimoto T et al CYP4b1 is a possible risk factor for bladder cancer in humans. Biochem Biophys Res Commun 2000; 277: 776– 80. 11062028
  20. Jensen LJ, Kuhn M, Stark M et al STRING 8–a global view on proteins and their functional interactions in 630 organisms. Nucleic Acids Res 2009; 37: D412– 6. 18940858 PMC2686466
  21. Jiang N, Xie F, Chen L et al The effect of TLR4 on the growth and local inflammatory microenvironment of HPV-related cervical cancer in vivo. Infect Agents Cancer 2020; 15. PMC7027303 32095158
  22. Kanehisa M, Goto S. KEGG: Kyoto encyclopedia of genes and genomes. Nucleic Acids Res 2000; 28: 27– 30. 10592173 PMC102409
  23. Kim S, Kim K, Choe J et al Improved survival analysis by learning shared genomic information from pan-cancer data. Bioinformatics (Oxf, Engl) 2020; 36: i389– 98. PMC7355236 32657401
  24. Kiwerska K, Szyfter K. DNA repair in cancer initiation, progression, and therapy—a double-edged sword. J Appl Genetics 2019; 60: 329– 34. 31468363 PMC6803590
  25. Kong L, Chen Y, Xu F et al Mining influential genes based on deep learning. BMC Bioinformatics 2021; 22: 27. 33482718 PMC7821411
  26. Larroquette M, Guegan J-P, Besse B et al Spatial transcriptomics of macrophage infiltration in non-small cell lung cancer reveals determinants of sensitivity and resistance to anti-PD1/PD-l1 antibodies. J Immunother Cancer 2022; 10: e003890. 35618288 PMC9125754
  27. Lee DD, Seung HS. Learning the parts of objects by non-negative matrix factorization. Nature 1999; 401: 788– 91. 10548103
  28. Li J, Yang F, Wei F et al The role of toll-like receptor 4 in tumor microenvironment. Oncotarget 2017; 8: 66656– 67. 29029545 PMC5630445
  29. Lin Y, Zhang W, Cao H, Li G, Du W. Classifying breast cancer subtypes using deep neural networks based on multi-omics Data. Genes (Basel). 2020; 11(8): 888. 10.3390/genes11080888. PMC7464481 32759821 · DOI
  30. Lin Y, Zhang W, Cao H et al Classifying breast cancer subtypes using deep neural networks based on multi-omics data. Genes 2020; 11: 888. 32759821 PMC7464481
  31. Liñares-Blanco J, Munteanu CR, Pazos A, Fernandez-Lozano C. Molecular docking and machine learning analysis of Abemaciclib in colon cancer. BMC Mol Cell Biol 2020; 21(1):52. 10.1186/s12860-020-00295-w. PMC7346626 32640984 · DOI
  32. Liu J, Lichtenberg T, Hoadley KA et al An integrated TCGA pan-cancer clinical data resource to drive high-quality survival outcome analytics. Cell 2018; 173: 400– 16.e11. 29625055 PMC6066282
  33. Lundberg SM, Lee S-I. A Unified Approach to Interpreting Model Predictions. In: Proceedings of the 31st International Conference on Neural Information Processing Systems, 2017; 4768– 4777.
  34. Ma T, Zhang A. Multi-view factorization autoencoder with network constraints for multi-omic integrative analysis. CoRR, abs/1809.01772. 2018. · arXiv
  35. Mankoo PK, Shen R, Schultz N et al Time to recurrence and survival in serous ovarian tumors predicted from integrated genomic profiles. PLoS One 2011; 6: e24709. 22073136 PMC3207809
  36. Neville EM, Stewart M, Myskow M, Donnelly RJ, Field JK. Loss of heterozygosity at 9p23 defines a novel locus in non-small cell lung cancer. Oncogene 1995; 11(3): 581– 585. 7630642
  37. Oh S, Yeom J, Cho HJ et al Integrated pharmaco-proteogenomics defines two subgroups in isocitrate dehydrogenase wild-type glioblastoma with prognostic and therapeutic opportunities. Nat Commun 2020; 11: 3288. 32620753 PMC7335111
  38. Oughtred R, Rust J, Chang C et al The BioGRID database: a comprehensive biomedical resource of curated protein, genetic, and chemical interactions. Protein Sci 2021; 30: 187– 200. 33070389 PMC7737760
  39. Picard M, Scott-Boyer M-P, Bodein A et al Integration strategies of multi-omics data for machine learning analysis. Comput Struct Biotechnol J 2021; 19: 3735– 46. 34285775 PMC8258788
  40. Qiu YL, Zheng H, Devos A et al A meta-learning approach for genomic survival analysis. Nat Commun 2020; 11: 6350. 33311484 PMC7733508
  41. Raudvere U, Kolberg L, Kuzmin I et al g: profiler: a web server for functional enrichment analysis and conversions of gene lists (2019 update). Nucleic Acids Res 2019; 47: W191– 8. 31066453 PMC6602461
  42. Relli V, Trerotola M, Guerra E et al Abandoning the notion of non-small cell lung cancer. Trends Mol Med 2019; 25: 585– 94. 31155338
  43. Sharifi-Noghabi H, Zolotareva O, Collins CC et al MOLI: multi-omics late integration with deep neural networks for drug response prediction. Bioinformatics 2019; 35: i501– 9. 31510700 PMC6612815
  44. Sharma J, Deb B, George IA et al Somatic Mutations Profile of a Young Patient With Metastatic Urothelial Carcinoma Reveals Mutations in Genes Involved in Ion Channels. Front Oncol 2019; 9: 435. 10.3389/fonc.2019.00435. PMC6549525 31192134 · DOI
  45. Shen R, Olshen AB, Ladanyi M et al Integrative clustering of multiple genomic data types using a joint latent variable model with application to breast and lung cancer subtype analysis. Bioinformatics 2009; 25: 2906– 12. 19759197 PMC2800366
  46. Shibuya M. Vascular endothelial growth factor (VEGF) and its receptor (VEGFR) signaling in angiogenesis: a crucial target for anti- and pro-angiogenic therapies. Genes Cancer 2011; 2: 1097– 105. 22866201 PMC3411125
  47. Sohn BH, Hwang J-E, Jang H-J et al Clinical significance of four molecular subtypes of gastric cancer identified by the cancer genome atlas project. Clin Cancer Res 2017; 23: 4441– 9. 28747339 PMC5785562
  48. Spooner A, Chen E, Sowmya A et al A comparison of machine learning methods for survival analysis of high-dimensional clinical data for dementia prediction. Sci Rep 2020; 10(1):20410. 10.1038/s41598-020-77220-w. PMC7683682 33230128 · DOI · Paper page
  49. Srujana B et al Machine learning vs. survival analysis models: a study on right censored heart failure data. Commun Stat Simul Comput 2022; 0: 1– 18.
  50. Subramanian I, Verma S, Kumar S et al Multi-omics data integration, interpretation, and its application. Bioinform Biol Insights 2020; 14: 117793221989905. PMC7003173 32076369
  51. Sundararajan M et al Axiomatic attribution for deep networks. In: Precup D, Teh YW (eds), Proceedings of the 34th International Conference on Machine Learning, Vol. 70 of Proceedings of Machine Learning Research. pp. 3319– 28. PMLR, 2017.
  52. Szklarczyk D, Gable AL, Nastou KC et al The STRING database in 2021: customizable protein-protein networks, and functional characterization of user-uploaded gene/measurement sets. Nucleic Acids Res 2021; 49: D605– 12. 33237311 PMC7779004
  53. Tariq M, Zhang J-Q, Liang G-K et al Gefitinib inhibits m2-like polarization of tumor-associated macrophages in Lewis lung cancer by targeting the STAT6 signaling pathway. Acta Pharmacol Sin 2017; 38: 1501– 11. 29022575 PMC5672074
  54. Teo W-Y, Sekar K, Seshachalam P et al Relevance of a TCGA-derived glioblastoma subtype gene-classifier among patient populations. Sci Rep 2019; 9: 7442. 31092847 PMC6520485
  55. Toth R, Schiffmann H, Hube-Magg C et al Random forest-based modelling to detect biomarkers for prostate cancer progression. Clin Epigenet 2019; 11: 148. PMC6805338 31640781
  56. Triantafillou E, Zhu T, Dumoulin V et al Meta-dataset: A dataset of datasets for learning to learn from few examples 2019. 10.48550/ARXIV.1903.03096. · DOI
  57. van Olst ES et al A genome-wide siRNA screen for regulators of tumor suppressor p53 activity in human non-small cell lung cancer cells identifies components of the RNA splicing machinery as targets for anticancer treatment. Mol Oncol 2017; 11: 534– 51. 28296343 PMC5527466
  58. Vaske CJ, Benz SC, Sanborn JZ et al Inference of patient-specific pathway activities from multi-dimensional cancer genomics data using PARADIGM. Bioinformatics 2010; 26: i237– 45. 20529912 PMC2881367
  59. Wang X, Li J, Duan Y et al Whole genome sequencing analysis of lung adenocarcinoma in Xuanwei, China. Thorac Cancer 2017; 8: 88– 96. 28083984 PMC5334298
  60. Wang Y, McKay JD, Rafnar T et al Rare variants of large effect in BRCA2 and CHEK2 affect risk of lung cancer. Nat Genet 2014; 46: 736– 41. 24880342 PMC4074058
  61. William WN Jr, Zhao X, Bianchi JJ et al Immune evasion in HPV- head and neck precancer-cancer transition is driven by an aneuploid switch involving chromosome 9p loss. Proc Natl Acad Sci USA 2021; 118(19):e2022655118. 10.1073/pnas.2022655118. PMC8126856 33952700 · DOI
  62. Withnell E, Zhang X, Sun K et al XOmiVAE: an interpretable deep learning model for cancer classification using high-dimensional omics data. Brief Bioinformatics 2021; 22: bbab315. 34402865 PMC8575033
  63. Yang Z, Michailidis G. A non-negative matrix factorization method for detecting modules in heterogeneous omics multi-modal data. Bioinformatics 2016; 32: 1– 8. 26377073 PMC5006236
  64. Yi K, Liu J, Rong Y et al Biological functions and prognostic value of ferroptosis-related genes in bladder cancer. Front Mol Biosci 2021; 8: 631152. 10.3389/fmolb.2021.631152. PMC8635965 34869576 · DOI
  65. Zang C, Wang T, Deng K et al High-dimensional genomic data bias correction and data integration using MANCIE. Nat Commun 2016; 7: 11305. 27072482 PMC4833864
  66. Zhang S, Liu C-C, Li W et al Discovery of multi-dimensional modules by integrative analysis of cancer genomic data. Nucleic Acids Res 2012; 40: 9379– 91. 22879375 PMC3479191
  67. Zhang Y, Lin Y, Lv D et al Identification and validation of a novel signature for prediction the prognosis and immunotherapy benefit in bladder cancer. PeerJ 2022; 10: e12843. 35127296 PMC8796709
  68. Zhou J, Troyanskaya OG. Predicting effects of noncoding variants with deep learning-based sequence model. Nat Methods 2015; 12: 931– 4. 26301843 PMC4768299

Cited by

Sorted by citations

Authors
Cho, H. J., Shu, M., Bekiranov, S., Zang, C., & Zhang, A.
Affiliations
University of Virginia (US)
Corresponding author
Cho, Hyun Jae
ORCID
Venue
Bioinformatics
Publisher
Oxford University Press (OUP)
Published
2023-03-02
Volume
39
Issue
4
ISSN
  • 1367-4803 (ISSN-L)
  • 1367-4811
DOI
10.1093/bioinformatics/btad113
PMC
PMC10079355
OpenAlex
W4323036825
Cited by
42
References
3
Citations by year
2026: 8 · 2025: 19 · 2024: 13 · 2023: 2
FWCI
3.74
Type
journal article
Language
en
Open access
Licence
Locations
  • Bioinformatics (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
Topics
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Bioinformatics and Genomic Networks
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Gene expression and cancer classification
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Cancer Research › Breast Cancer Treatment Studies
Keywords
meta-learning, multi-omics integration, survival analysis, pathway enrichment, model interpretability, DeepLIFT, Cox proportional hazards model, pan-cancer, TCGA, transcriptomics, feature importance
MeSH terms
Machine Learning, Multiomics, Algorithms, Humans, Neoplasms, Gene Expression Profiling

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