Skip to content
2000
Volume 20, Issue 6
  • ISSN: 1574-8936
  • E-ISSN: 2212-392X

Abstract

Background

Integrating multi-omics data for cancer classification brings complementary biological insights while also facing challenges such as data integration, gene grouping, and adaptive weight construction.

Objective

This paper aims to address the challenges faced by the cancer subtype classification and gene screening based on multi-omics data.

Methods

Multinomial logistic regression with adaptive regularization (MLRAR) was proposed by integrating DNA methylation, gene mutation, and RNA-seq information. A data preprocessing strategy that effectively utilizes multi-omics information was presented, and the local maximum quasi-clique merging (lmQCM) algorithm was implemented to group genes. Biological pathway information was utilized to evaluate the significance of gene groups, while the significance of each gene within a group was evaluated by integrating mutation information, information theory, and methylation information.

Results

Compared to MRlasso, MRGL, MSGL, MROGL, AMRSOGL, and AGLRMR, the proposed method yielded improvements in subtype classification accuracy of breast cancer by 2.6%, 2.9%, 3.5%, 2.3%, 2.0%, and 1.8%, respectively. In addition, MLRAR also achieved significant improvements in ovarian cancer by 8.2%, 5.0%, 6.8%, 5.2%, 12.7%, and 6.3%, respectively.

Conclusion

The proposed method can effectively deal with data integration, gene grouping, and adaptive weight construction.

© 2025 Bentham Science Publishers
Loading

Article metrics loading...

/content/journals/cbio/10.2174/0115748936308171240605075531
2024-06-20
2025-09-11

  • From This Site

    /content/journals/cbio/10.2174/0115748936308171240605075531
    dcterms_title,dcterms_subject,pub_keyword
    -contentType:Contributor -contentType:Concept -contentType:Institution
    10
    5
Loading full text...

Full text loading...

References

  1. LiW. HuangY. ZhuangB.W. Multiparametric ultrasomics of significant liver fibrosis: A machine learning-based analysis.Eur. Radiol.20192931496150610.1007/s00330‑018‑5680‑z 30178143
     [Google Scholar]
  2. CaoQ.Q. ZhaoJ.P. ZhengC.H. Multi-channel partial graph integration learning of partial multi-omics data for cancer subtyping.Curr. Bioinform.202318868069110.2174/1574893618666230519145545
     [Google Scholar]
  3. WangZ. YinJ. ZhouW. Complex impact of DNA methylation on transcriptional dysregulation across 22 human cancer types.Nucleic Acids Res.20204852287230210.1093/nar/gkaa041 32002550
     [Google Scholar]
  4. RoyD. TiirikainenM. Diagnostic power of DNA methylation classifies for early detection of cancer.Trends Cancer202062788110.1016/j.trecan.2019.12.006 32061307
     [Google Scholar]
  5. EbrahimiV. SoleimanianA. EbrahimiT. Epigenetic modifications in gastric cancer: Focus on DNA methylation.Gene202074214457710.1016/j.gene.2020.144577 32171825
     [Google Scholar]
  6. ChingT. ZhuX. GarmireL.X. Cox-nnet: An artificial neural network method for prognosis prediction of high-throughput omics data.PLOS Comput. Biol.2018144e100607610.1371/journal.pcbi.1006076 29634719
     [Google Scholar]
  7. XuJ. ShiJ. CuiX. Cellular heterogeneity–adjusted clonal methylation (CHALM) improves prediction of gene expression.Nat. Commun.202112140010.1038/s41467‑020‑20492‑7 33452255
     [Google Scholar]
  8. FuJ. CaoZ. ZhangJ. Identification of two immune-related risk score signatures through integrated analysis of multi-omics data in hepatocellular carcinoma.Gene202282914651910.1016/j.gene.2022.146519 35447248
     [Google Scholar]
  9. TangG. ChoM. WangX. OncoD.B. An interactive online database for analysis of gene expression and viral infection in cancer.Nucleic Acids Res.202250D1D1334D133910.1093/nar/gkab970 34718715
     [Google Scholar]
  10. YangB ZhangY PangS Integrating multi-omic data with deep subspace fusion clustering for cancer subtype prediction.IEEE/ACM Trans Comput Biol Bioinform2021181216226
     [Google Scholar]
  11. YangY. TianS. QiuY. MDICC: Novel method for multi-omics data integration and cancer subtype identification.Brief. Bioinform.2022233bbac13210.1093/bib/bbac132 35437603
     [Google Scholar]
  12. YangB. YangY. SuX. Deep structure integrative representation of multi-omics data for cancer subtyping.Bioinformatics202238133337334210.1093/bioinformatics/btac345 35639657
     [Google Scholar]
  13. LangfelderP. HorvathS. WGCNA: An R package for weighted correlation network analysis.BMC Bioinformatics20089155910.1186/1471‑2105‑9‑559 19114008
     [Google Scholar]
  14. LiJ DongW MengD Grouped gene selection of cancer via adaptive sparse group lasso based on conditional mutual information.IEEE/ACM Trans Comput Biol Bioinform20181562028203810.1109/TCBB.2017.2761871
     [Google Scholar]
  15. WangY. LiX. RuizR. Weighted general group lasso for gene selection in cancer classification.IEEE Trans. Cybern.20194982860287310.1109/TCYB.2018.2829811 29993764
     [Google Scholar]
  16. SongX LiangK LiJ. WGRLR: A weighted group regularized logistic regression for cancer diagnosis and gene selection.IEEE/ACM Trans Comput Biol Bioinform20232021563157310.1109/TCBB.2022.3203167
     [Google Scholar]
  17. LiJ. WangY. SongX. XiaoH. Adaptive multinomial regression with overlapping groups for multi-class classification of lung cancer.Comput. Biol. Med.20181001910.1016/j.compbiomed.2018.06.014 29957558
     [Google Scholar]
  18. LiJ. WangY. JiangT. XiaoH. SongX. Grouped gene selection and multi-classification of acute leukemia via new regularized multinomial regression.Gene2018667182410.1016/j.gene.2018.05.012 29753048
     [Google Scholar]
  19. OuY. ZhangC.Q. A new multimembership clustering method.J. Ind. Manage. Optim.20073461962410.3934/jimo.2007.3.619
     [Google Scholar]
  20. ZhangJ. HuangK. Normalized lmQCM: An algorithm for detecting weak quasi-cliques in weighted graph with applications in gene co-expression module discovery in cancers.Cancer Inform.201613Suppl. 3137146 27486298
     [Google Scholar]
  21. BichindaritzI. LiuG. BartlettC. Integrative survival analysis of breast cancer with gene expression and DNA methylation data.Bioinformatics202137172601260810.1093/bioinformatics/btab140 33681976
     [Google Scholar]
  22. HuangZ. HanZ. WangT. TSUNAMI: Translational bioinformatics tool suite for network analysis and mining.Genom. Proteom. Bioinform.20211961023103110.1016/j.gpb.2019.05.006 33705981
     [Google Scholar]
  23. YuC.Y. MitrofanovaA. Mechanism-centric approaches for biomarker detection and precision therapeutics in cancer.Front. Genet.20211268781310.3389/fgene.2021.687813 34408770
     [Google Scholar]
  24. YuanM. LinY. Model selection and estimation in regression with grouped variables.J. R. Stat. Soc. Series B Stat. Methodol.2006681496710.1111/j.1467‑9868.2005.00532.x
     [Google Scholar]
  25. SimonN. FriedmanJ. HastieT. TibshiraniR. A sparse group lasso.J. Comput. Graph. Stat.201322223124510.1080/10618600.2012.681250
     [Google Scholar]
  26. FangK. WangX. ZhangS. ZhuJ. MaS. Bi-level variable selection via adaptive sparse group Lasso.J. Stat. Comput. Simul.201585132750276010.1080/00949655.2014.938241
     [Google Scholar]
  27. LiJ. LiangK. SongX. Logistic regression with adaptive sparse group lasso penalty and its application in acute leukemia diagnosis.Comput. Biol. Med.202214110515410.1016/j.compbiomed.2021.105154 34952336
     [Google Scholar]
  28. AbramovichF. GrinshteinV. LevyT. Multiclass classification by sparse multinomial logistic regression.IEEE Trans. Inf. Theory20216774637464610.1109/TIT.2021.3075137
     [Google Scholar]
  29. KayabolK. Approximate sparse multinomial logistic regression for classification.IEEE Trans. Pattern Anal. Mach. Intell.202042249049310.1109/TPAMI.2019.2904062 30869609
     [Google Scholar]
  30. VincentM. HansenN.R. Sparse group lasso and high dimensional multinomial classification.Comput. Stat. Data Anal.20147177178610.1016/j.csda.2013.06.004
     [Google Scholar]
  31. KimY. KwonS. Heun SongS. Multiclass sparse logistic regression for classification of multiple cancer types using gene expression data.Comput. Stat. Data Anal.20065131643165510.1016/j.csda.2006.06.007
     [Google Scholar]
  32. LiJ. CaoF. GaoQ. Improving diagnosis accuracy of non-small cell lung carcinoma on noisy data by adaptive group lasso regularized multinomial regression.Biomed. Signal Process. Control202379210414810.1016/j.bspc.2022.104148
     [Google Scholar]
  33. ChakrabortyS. BeggC.B. ShenR. Using the “Hidden” genome to improve classification of cancer types.Biometrics20217741445145510.1111/biom.13367 32914442
     [Google Scholar]
  34. LeiM. XuJ. HuangL.C. Network module-based model in the differential expression analysis for RNA-seq.Bioinformatics201733172699270510.1093/bioinformatics/btx214 28407034
     [Google Scholar]
  35. ChowdhuryHA BhattacharyyaDK KalitaJK Differential expression analysis of RNA-seq reads: Overview, taxonomy, and tools.IEEE/ACM Trans Comput Biol Bioinform2020172566586
     [Google Scholar]
  36. BabaO. BidikianA. MukherjiD. Tumor profiling of KRAS, BRAF, and NRAS gene mutations in patients with colorectal cancer: A Lebanese major center cohort study.Gene202283414664610.1016/j.gene.2022.146646 35680020
     [Google Scholar]
  37. MendirattaG. KeE. AzizM. Cancer gene mutation frequencies for the U.S. population.Nat. Commun.2021121596110.1038/s41467‑021‑26213‑y 34645806
     [Google Scholar]
  38. Martínez-JiménezF. MuiñosF. SentísI. A compendium of mutational cancer driver genes.Nat. Rev. Cancer2020201055557210.1038/s41568‑020‑0290‑x 32778778
     [Google Scholar]
  39. UzmaH.Z. HalimZ. An ensemble filter-based heuristic approach for cancerous gene expression classification.Knowl. Base. Syst.202123410756010.1016/j.knosys.2021.107560
     [Google Scholar]
  40. DaiJ. ChenJ. LiuY. HuH. Novel multi-label feature selection via label symmetric uncertainty correlation learning and feature redundancy evaluation.Knowl. Base. Syst.202020710634210.1016/j.knosys.2020.106342
     [Google Scholar]
  41. GuX. GuoJ. A feature subset selection algorithm based on equal interval division and three-way interaction information.Soft Comput.202125138785879510.1007/s00500‑021‑05800‑7
     [Google Scholar]
  42. ChengN. SchulteA.J. SantosaF. KimJ.H. Machine learning application identifies novel gene signatures from transcriptomic data of spontaneous canine hemangiosarcoma.Brief. Bioinform.2021224bbaa25210.1093/bib/bbaa252 33078825
     [Google Scholar]
  43. PengH. FanY. Feature selection by optimizing a lower bound of conditional mutual information.Inf. Sci.2017418-41965266710.1016/j.ins.2017.08.036 30283157
     [Google Scholar]
/content/journals/cbio/10.2174/0115748936308171240605075531
Loading
Multinomial Logistic Regression with Adaptive Regularization for Cancer Subtype Classification via Multi-omics Data
Curr Bioinform 20, 506 (2025); https://doi.org/10.2174/0115748936308171240605075531
/content/journals/cbio/10.2174/0115748936308171240605075531
/content/journals/cbio/10.2174/0115748936308171240605075531
Loading

Data & Media loading...


  • Article Type:     Research Article
Keyword(s): Adaptive regularization; cancer subtype classification; data integration; gene grouping; multi-omics data; multinomial logistic regression

Most Cited Most Cited RSS feed

This is a required field
Please enter a valid email address
Approval was a Success
Invalid data
An Error Occurred
Approval was partially successful, following selected items could not be processed due to error
Please enter a valid_number test