Multi-omics machine learning to study host-microbiome interactions in early-onset colorectal cancer.
Journal
NPJ precision oncology
ISSN: 2397-768X
Titre abrégé: NPJ Precis Oncol
Pays: England
ID NLM: 101708166
Informations de publication
Date de publication:
17 Jul 2024
17 Jul 2024
Historique:
received:
25
02
2024
accepted:
09
07
2024
medline:
18
7
2024
pubmed:
18
7
2024
entrez:
17
7
2024
Statut:
epublish
Résumé
The incidence of early-onset colorectal cancer (eoCRC) is rising, and its pathogenesis is not completely understood. We hypothesized that machine learning utilizing paired tissue microbiome and plasma metabolome features could uncover distinct host-microbiome associations between eoCRC and average-onset CRC (aoCRC). Individuals with stages I-IV CRC (n = 64) were categorized as eoCRC (age ≤ 50, n = 20) or aoCRC (age ≥ 60, n = 44). Untargeted plasma metabolomics and 16S rRNA amplicon sequencing (microbiome analysis) of tumor tissue were performed. We fit DIABLO (Data Integration Analysis for Biomarker Discovery using Latent variable approaches for Omics studies) to construct a supervised machine-learning classifier using paired multi-omics (microbiome and metabolomics) data and identify associations unique to eoCRC. A differential association network analysis was also performed. Distinct clustering patterns emerged in multi-omic dimension reduction analysis. The metabolomics classifier achieved an AUC of 0.98, compared to AUC 0.61 for microbiome-based classifier. Circular correlation technique highlighted several key associations. Metabolites glycerol and pseudouridine (higher abundance in individuals with aoCRC) had negative correlations with Parasutterella, and Ruminococcaceae (higher abundance in individuals with eoCRC). Cholesterol and xylitol correlated negatively with Erysipelatoclostridium and Eubacterium, and showed a positive correlation with Acidovorax with higher abundance in individuals with eoCRC. Network analysis revealed different clustering patterns and associations for several metabolites e.g.: urea cycle metabolites and microbes such as Akkermansia. We show that multi-omics analysis can be utilized to study host-microbiome correlations in eoCRC and demonstrates promising biomarker potential of a metabolomics classifier. The distinct host-microbiome correlations for urea cycle in eoCRC may offer opportunities for therapeutic interventions.
Identifiants
pubmed: 39020083
doi: 10.1038/s41698-024-00647-1
pii: 10.1038/s41698-024-00647-1
doi:
Types de publication
Journal Article
Langues
eng
Pagination
146Informations de copyright
© 2024. The Author(s).
Références
Cancer of the colon and rectum—cancer stat facts. SEER. https://seer.cancer.gov/statfacts/html/colorect.html .
Wolf, A. M. D. et al. Colorectal cancer screening for average-risk adults: 2018 guideline update from the American Cancer Society. CA Cancer J. Clin. 68, 250–281 (2018).
pubmed: 29846947
doi: 10.3322/caac.21457
Kamath, S. D. et al. Racial disparities negatively impact outcomes in early‐onset colorectal cancer independent of socioeconomic status. Cancer Med. 10, 7542–7550 (2021).
pubmed: 34647438
pmcid: 8559495
doi: 10.1002/cam4.4276
Siegel, R. L. et al. Colorectal cancer statistics, 2020. CA Cancer J. Clin. 70, 145–164 (2020).
pubmed: 32133645
doi: 10.3322/caac.21601
Giannakis, M. & Ng, K. A common cancer at an uncommon age. Science. 379, 1088–1090 (2023).
pubmed: 36927016
doi: 10.1126/science.ade7114
Eng, C. et al. A comprehensive framework for early-onset colorectal cancer research. Lancet Oncol. 23, e116–e128 (2022).
pubmed: 35090673
doi: 10.1016/S1470-2045(21)00588-X
Spaander, M. C. W. et al. Young-onset colorectal cancer. Nat. Rev. Dis. Prim. 9, 21 (2023).
pubmed: 37105987
doi: 10.1038/s41572-023-00432-7
Weinberg, B. A. & Marshall, J. L. Colon cancer in young adults: trends and their implications. Curr. Oncol. Rep. 21, 3 (2019).
pubmed: 30659375
doi: 10.1007/s11912-019-0756-8
Kong, C. et al. Integrated metagenomic and metabolomic analysis reveals distinct gut-microbiome-derived phenotypes in early-onset colorectal cancer. Gut gutjnl-2022-327156. https://doi.org/10.1136/gutjnl-2022-327156 (2022).
Irajizad, E. et al. A blood-based metabolomic signature predictive of risk for pancreatic cancer. Cell Rep. Med. 4, 101194 (2023).
pubmed: 37729870
pmcid: 10518621
doi: 10.1016/j.xcrm.2023.101194
Barot, S. V. et al. Distinct intratumoral microbiome of young-onset and average-onset colorectal cancer. eBioMedicine 100, 104980 (2024).
pubmed: 38306898
pmcid: 10850116
doi: 10.1016/j.ebiom.2024.104980
Jayakrishnan, T. et al. Plasma metabolomic differences in early-onset compared to average-onset colorectal cancer. Sci. Rep. 14, 4294 (2024).
pubmed: 38383634
pmcid: 10881959
doi: 10.1038/s41598-024-54560-5
Yoon, G., Gaynanova, I. & Müller, C. L. Microbial networks in SPRING—semi-parametric rank-based correlation and partial correlation estimation for quantitative microbiome data. Front. Genet. 10, 516 (2019).
pubmed: 31244881
pmcid: 6563871
doi: 10.3389/fgene.2019.00516
Stockert, J. A., Weil, R., Yadav, K. K., Kyprianou, N. & Tewari, A. K. Pseudouridine as a novel biomarker in prostate cancer. Urol. Oncol. 39, 63–71 (2021).
pubmed: 32712138
doi: 10.1016/j.urolonc.2020.06.026
DeGuzman, A., Lorenson, M. Y. & Walker, A. M. Bittersweet: relevant amounts of the common sweet food additive, glycerol, accelerate the growth of PC3 human prostate cancer xenografts. BMC Res. Notes 15, 101 (2022).
pubmed: 35272680
pmcid: 8908677
doi: 10.1186/s13104-022-05990-9
Koundouros, N. & Poulogiannis, G. Reprogramming of fatty acid metabolism in cancer. Br. J. Cancer 122, 4–22 (2020).
pubmed: 31819192
doi: 10.1038/s41416-019-0650-z
Zhu, G. et al. Untargeted GC-MS-based metabolomics for early detection of colorectal cancer. Front. Oncol. 11, 729512 (2021).
pubmed: 34804922
pmcid: 8599589
doi: 10.3389/fonc.2021.729512
Sakai, M. et al. Arachidonic acid and cancer risk: a systematic review of observational studies. BMC Cancer 12, 606 (2012).
pubmed: 23249186
pmcid: 3574856
doi: 10.1186/1471-2407-12-606
Chhetri, D. R. Myo-inositol and its derivatives: their emerging role in the treatment of human diseases. Front. Pharmacol. 10, 1172 (2019).
pubmed: 31680956
pmcid: 6798087
doi: 10.3389/fphar.2019.01172
Xu, C. et al. FADS1-arachidonic acid axis enhances arachidonic acid metabolism by altering intestinal microecology in colorectal cancer. Nat. Commun. 14, 2042 (2023).
pubmed: 37041160
pmcid: 10090135
doi: 10.1038/s41467-023-37590-x
Yang, Z., Tang, H., Lu, S., Sun, X. & Rao, B. Relationship between serum lipid level and colorectal cancer: a systemic review and meta-analysis. BMJ Open 12, e052373 (2022).
pubmed: 35732386
pmcid: 9226934
doi: 10.1136/bmjopen-2021-052373
Nassani, R., AlAmri, H. & Alrfaei, B. M. Abstract LB183: Erythritol acts as tumor enhancer and suppressor depending on concentrations in brain tumor cell lines. Cancer Res. 81, LB183 (2021).
doi: 10.1158/1538-7445.AM2021-LB183
Kumar, V. Adenosine as an endogenous immunoregulator in cancer pathogenesis: where to go? Purinergic Signal. 9, 145–165 (2013).
pubmed: 23271562
doi: 10.1007/s11302-012-9349-9
Vigano, S. et al. Targeting adenosine in cancer immunotherapy to enhance T-cell function. Front. Immunol. 10, 925 (2019).
pubmed: 31244820
pmcid: 6562565
doi: 10.3389/fimmu.2019.00925
Chen, H. et al. Urea cycle activation triggered by host-microbiota maladaptation driving colorectal tumorigenesis. Cell Metab. 35, 651–666.e7 (2023).
pubmed: 36963394
doi: 10.1016/j.cmet.2023.03.003
Alexandrou, C. et al. Sensitivity of colorectal cancer to arginine deprivation therapy is shaped by differential expression of urea cycle enzymes. Sci. Rep. 8, 12096 (2018).
pubmed: 30108309
pmcid: 6092409
doi: 10.1038/s41598-018-30591-7
Yang, J. et al. High-fat diet promotes colorectal tumorigenesis through modulating gut microbiota and metabolites. Gastroenterology 162, 135–149.e2 (2022).
pubmed: 34461052
doi: 10.1053/j.gastro.2021.08.041
Xu, Z. et al. Dysbiosis of human tumor microbiome and aberrant residence of actinomyces in tumor-associated fibroblasts in young-onset colorectal cancer. Front. Immunol. 13, 1008975 (2022).
pubmed: 36119074
pmcid: 9481283
doi: 10.3389/fimmu.2022.1008975
Zwezerijnen-Jiwa, F. H., Sivov, H., Paizs, P., Zafeiropoulou, K. & Kinross, J. A systematic review of microbiome-derived biomarkers for early colorectal cancer detection. Neoplasia 36, 100868 (2022).
pubmed: 36566591
pmcid: 9804137
doi: 10.1016/j.neo.2022.100868
Hua, H. et al. Intestinal microbiota in colorectal adenoma-carcinoma sequence. Front. Med. 9, 888340 (2022).
doi: 10.3389/fmed.2022.888340
Gates, T. J. et al. Fecal microbiota restoration modulates the microbiome in inflammation-driven colorectal cancer. Cancers 15, 2260 (2023).
pubmed: 37190186
pmcid: 10137216
doi: 10.3390/cancers15082260
Zhang, H. et al. Disease‐associated gut microbiome and critical metabolomic alterations in patients with colorectal cancer. Cancer Med. cam4.6194. https://doi.org/10.1002/cam4.6194 (2023).
Wang, N. & Fang, J.-Y. Fusobacterium nucleatum, a key pathogenic factor and microbial biomarker for colorectal cancer. Trends Microbiol. 31, 159–172 (2023).
pubmed: 36058786
doi: 10.1016/j.tim.2022.08.010
Sobhani, I. et al. Colorectal cancer-associated microbiota contributes to oncogenic epigenetic signatures. Proc. Natl Acad. Sci. USA 116, 24285–24295 (2019).
pubmed: 31712445
pmcid: 6883805
doi: 10.1073/pnas.1912129116
Sun, J. & Kato, I. Gut microbiota, inflammation and colorectal cancer. Genes Dis. 3, 130–143 (2016).
pubmed: 28078319
pmcid: 5221561
doi: 10.1016/j.gendis.2016.03.004
Artemev, A., Naik, S., Pougno, A., Honnavar, P. & Shanbhag, N. M. The association of microbiome dysbiosis with colorectal cancer. Cureus 14, e22156 (2022).
pubmed: 35174040
pmcid: 8840808
Chen, Q. et al. Rubidium chloride modulated the fecal microbiota community in mice. BMC Microbiol. 21, 46 (2021).
pubmed: 33588762
pmcid: 7885239
doi: 10.1186/s12866-021-02095-4
Kim, D. J. et al. Colorectal cancer diagnostic model utilizing metagenomic and metabolomic data of stool microbial extracellular vesicles. Sci. Rep. 10, 2860 (2020).
pubmed: 32071370
pmcid: 7029032
doi: 10.1038/s41598-020-59529-8
Wu, J., Wu, M. & Wu, Q. Identification of potential metabolite markers for colon cancer and rectal cancer using serum metabolomics. J. Clin. Lab Anal. 34, e23333 (2020).
pubmed: 32281150
pmcid: 7439421
doi: 10.1002/jcla.23333
León-Letelier, R. A. et al. Contributions of the microbiome-derived metabolome for risk assessment and prognostication of pancreatic cancer. Clin. Chem. 70, 102–115 (2024).
pubmed: 38175578
doi: 10.1093/clinchem/hvad186
Swanton, C. et al. Embracing cancer complexity: hallmarks of systemic disease. Cell 187, 1589–1616 (2024).
pubmed: 38552609
doi: 10.1016/j.cell.2024.02.009
Singh, A. et al. DIABLO: an integrative approach for identifying key molecular drivers from multi-omics assays. Bioinformatics 35, 3055–3062 (2019).
pubmed: 30657866
pmcid: 6735831
doi: 10.1093/bioinformatics/bty1054
Cai, Z., Poulos, R. C., Liu, J. & Zhong, Q. Machine learning for multi-omics data integration in cancer. iScience 25, 103798 (2022).
pubmed: 35169688
pmcid: 8829812
doi: 10.1016/j.isci.2022.103798
Schmidt, D. R. et al. Metabolomics in cancer research and emerging applications in clinical oncology. CA Cancer J. Clin. 71, 333–358 (2021).
pubmed: 33982817
pmcid: 8298088
doi: 10.3322/caac.21670
Liu, L. & Shah, K. The potential of the gut microbiome to reshape the cancer therapy paradigm: a review. JAMA Oncol. 8, 1059 (2022).
pubmed: 35482355
doi: 10.1001/jamaoncol.2022.0494
Routy, B. et al. Fecal microbiota transplantation plus anti-PD-1 immunotherapy in advanced melanoma: a phase I trial. Nat. Med. https://doi.org/10.1038/s41591-023-02453-x (2023).
West Coast Metabolomics Center—Assays and Services. https://metabolomics.ucdavis.edu/core-services/assays-and-services .
West Coast Metabolomics Center—Metabolites. https://metabolomics.ucdavis.edu/core-services/metabolites .
Fiehn, O. Metabolomics by gas chromatography-mass spectrometry: combined targeted and untargeted profiling. Curr. Protoc. Mol. Biol. 114, 30.4.1–30.4.32 (2016).
pubmed: 27038389
doi: 10.1002/0471142727.mb3004s114
Aboud, O. et al. Application of machine learning to metabolomic profile characterization in glioblastoma patients undergoing concurrent chemoradiation. Metabolites 13, 299 (2023).
pubmed: 36837918
pmcid: 9961856
doi: 10.3390/metabo13020299
Ismail, I. T. et al. Sugar alcohols have a key role in pathogenesis of chronic liver disease and hepatocellular carcinoma in whole blood and liver tissues. Cancers 12, 484 (2020).
pubmed: 32092943
pmcid: 7072169
doi: 10.3390/cancers12020484
Miyamoto, S. et al. Systemic metabolomic changes in blood samples of lung cancer patients identified by gas chromatography time-of-flight mass spectrometry. Metabolites 5, 192–210 (2015).
pubmed: 25859693
pmcid: 4495369
doi: 10.3390/metabo5020192
Krishnapuram, B., Carin, L., Figueiredo, M. A. T. & Hartemink, A. J. Sparse multinomial logistic regression: fast algorithms and generalization bounds. IEEE Trans. Pattern Anal. Mach. Intell. 27, 957–968 (2005).
pubmed: 15943426
doi: 10.1109/TPAMI.2005.127
Chambers, L. M. et al. Disruption of the gut microbiota confers cisplatin resistance in epithelial ovarian cancer. Cancer Res. 82, 4654–4669 (2022).
pubmed: 36206317
pmcid: 9772178
doi: 10.1158/0008-5472.CAN-22-0455
Weiss, K. et al. Barrier housing and gender effects on allergic airway disease in a murine house dust mite model. Immunohorizons 5, 33–47 (2021).
pubmed: 33478982
doi: 10.4049/immunohorizons.2000096
Bolyen, E. et al. Reproducible, interactive, scalable and extensible microbiome data science using QIIME 2. Nat. Biotechnol. 37, 852–857 (2019).
pubmed: 31341288
pmcid: 7015180
doi: 10.1038/s41587-019-0209-9
Callahan, B. J. et al. DADA2: high-resolution sample inference from Illumina amplicon data. Nat. Methods 13, 581–583 (2016).
pubmed: 27214047
pmcid: 4927377
doi: 10.1038/nmeth.3869
McMurdie, P. J. & Holmes, S. phyloseq: an R package for reproducible interactive analysis and graphics of microbiome census data. PLoS ONE 8, e61217 (2013).
pubmed: 23630581
pmcid: 3632530
doi: 10.1371/journal.pone.0061217
Benjamini, Y. & Hochberg, Y. Controlling the false discovery Rate: a practical and powerful approach to multiple testing. J. R. Stat. Soc. Ser. B Methodol. 57, 289–300 (1995).
doi: 10.1111/j.2517-6161.1995.tb02031.x
R: The R Project for Statistical Computing. https://www.r-project.org/ .
Sangwan, N. & Khorana, A. Distinct intratumoral microbiome of young-onset and average-onset colorectal cancer [Data set]. Zenodo. https://doi.org/10.5281/zenodo.10401639 (2023).