Indonesian Journal of Medical Chemistry and Bioinformatics


Pancreatic cancer is one of the deadliest cancers in the world. This cancer is caused by multiple factors and mostly detected at late stadium. Biomarker is a marker that can identify some diseases very specific. For pancreatic cancer, biomarker has been recognized using blood sample known as liquid biopsy, breath, pancreatic secret, and tumor marker CA19-9. Those biomarkers are invasive, so we want to identify the disease using a very convenient method. Metabolite is product from cell metabolism. Metabolites can become a biomarker especially from difficult diseases. In this paper, we want to find biomarker from metabolite using machine learning and enrichment. Metabolites data was obtained from Metabolomic workbench, while the detection and identification is done using in silico. From 106 samples, control and cancer, we found 61 metabolites and analyze them. We got 8 metabolites that play important role in pancreatic cancer and found out 2 of them are the most impactful. From that we found that ethanol is one of the best candidate of biomarker that we provide for pancreatic detection cancer. However, the simulation need to be improved to find another biomarker that provide a better marker for prognosis.

Keyword : metabolite, pancreatic, cancer, machine learning

Bahasa Abstract

Kanker pancreas merupakan salah satu penyakit mematikan di dunia. Kanker pancreas disebabkan oleh banyak factor dan biasanya terdiagnosis pada stadium lanjut. Biomarker adalah penentu yang digunakan dalam mendiagnosis suatu penyakit dengan akurat. Pada kanker pancreas terdapat beberapa biomarker yaitu biopsy cairan seperti darah, hembusan napas, secret pancreas, dan juga tumor marker CA19-9. Namun demikian, biomarker tersebut dinilai invasih sehingga saat ini dicari biomarker yang tidak invasive seperti dari metabolit. Metabolit sendiri merupakan hasil metabolism dari sel. Perbedaan metabolit dari sel normal dan kanker dinilai bisa menunjang prognosis kanker pancreas. Data metabolit diambil dari Metabolomic workbench dan identifikasi serta validasi lanjutan dilakukan secara in silico. Sebanyak 106 sampel ditemukan 61 metabolit yang kemudian dilakukan analisis lanjutan. Ditemukan sebanyak 8 metabolit yang memegang peranan penting dalam kanker pancreas. Dari 8 metabolit tersebut ditemukan 2 kandidat biomarker yang sangat penting dalam deteksi kanker. Kandidat biomarker metabolit tersebut adalah etanol dan 3-hydroxybutirat. Namun demikian, simulasi tersebut perlu dilakukan pengulangan dan penambahan data lain untuk mendapatkan biomarker yang lebih akurat dan menunjang diagnosis.


[1] A. McGuigan, P. Kelly, R. C. Turkington, C. Jones, H. G. Coleman, and R. S. McCain, “Pancreatic cancer: A review of clinical diagnosis, epidemiology, treatment and outcomes,” World J. Gastroenterol., vol. 24, no. 43, pp. 4846–4861, 2018, doi: 10.3748/wjg.v24.i43.4846.

[2] Y. J. McConnell et al., “Distinguishing benign from malignant pancreatic and periampullary lesions using combined use of1h-nmr spectroscopy and gas chromatography–mass spectrometry,” Metabolites, vol. 7, no. 1, pp. 1–15, 2017, doi: 10.3390/metabo7010003.

[3] P. Rawla, T. Sunkara, and V. Gaduputi, “Epidemiology of Pancreatic Cancer: Global Trends, Etiology and Risk Factors,” World J. Oncol., vol. 10, no. 1, pp. 10–27, 2019, doi: 10.14740/wjon1166.

[4] J. M. Winter, A. Maitra, and C. J. Yeo, “Genetics and pathology of pancreatic cancer,” Hpb, vol. 8, no. 5, pp. 324–336, 2006, doi: 10.1080/13651820600804203.

[5] “Pancreatic Cancer—Patient Version - NCI.” 2018. Retrieved on 11th May 2022.

[6] R. Rikarni, “Pancreatic Cancer: Pathogenesis, Diagnosis, and Laboratory Tests,” Indones. J. Clin. Pathol. Med. Lab., vol. 27, no. 3, pp. 333–340, 2021, doi: 10.24293/ijcpml.v27i3.1891.

[7] J. Mayerle et al., “Metabolic biomarker signature to differentiate pancreatic ductal adenocarcinoma from chronic pancreatitis,” Gut, vol. 67, no. 1, pp. 128–137, 2018, doi: 10.1136/gutjnl-2016-312432.

[8] R. A. C. M. Boonen, M. P. G. Vreeswijk, and H. van Attikum, “Functional Characterization of PALB2 Variants of Uncertain Significance: Toward Cancer Risk and Therapy Response Prediction,” Front. Mol. Biosci., vol. 7, no. September, 2020, doi: 10.3389/fmolb.2020.00169.

[9] J. G. T. 3 Emalie J. Clement 1, Henry C.-H. Law 1 , Fangfang Qiao 1 , Dragana Noe 2 and and N. T. Woods, “Combined Alcohol Exposure and KRAS Mutation in Human Pancreatic Ductal Epithelial Cells Induces Proliferation and Alters Subtype Signatures Determined by Multi-Omics Analysis,” Cancers (Basel), vol. 14, no. 8, p. 1968, 2022, doi: 10.3390/cancers14081968.

[10] Y. Wang et al., “Prognostic Biomarkers for Pancreatic Ductal Adenocarcinoma: An Umbrella Review,” Front. Oncol., vol. 10, no. September, pp. 1–12, 2020, doi: 10.3389/fonc.2020.01466.

[11] Y. Cao et al., “Potential Metabolite Biomarkers for Early Detection of Stage-I Pancreatic Ductal Adenocarcinoma,” Front. Oncol., vol. 11, no. January, pp. 1–10, 2022, doi: 10.3389/fonc.2021.744667.

[12] C. Dalvit, E. Ardini, M. Flocco, G. P. Fogliatto, N. Mongelli, and M. Veronesit, “A General NMR Method for Rapid, Efficient, and Reliable Biochemical Screening,” J. Am. Chem. Soc., vol. 125, no. 47, pp. 14620–14625, 2003, doi: 10.1021/ja038128e.

[13] I. T. Jollife and J. Cadima, “Principal component analysis: A review and recent developments,” Philos. Trans. R. Soc. A Math. Phys. Eng. Sci., vol. 374, no. 2065, 2016, doi: 10.1098/rsta.2015.0202.

[14] R. D. Ledesma, P. Valero-Mora, and G. Macbeth, “The Scree Test and the Number of Factors: a Dynamic Graphics Approach,” Span. J. Psychol., vol. 18, no. June, p. E11, 2015, doi: 10.1017/sjp.2015.13.

[15] P. Larrañaga et al., “Machine learning in bioinformatics,” Brief. Bioinform., vol. 7, no. 1, pp. 86–112, 2006, doi: 10.1093/bib/bbk007.

[16] H. Ahmadi, P. Pichappan, and E. Ariwa, Communications in Computer and Information Science: Preface, vol. 241 CCIS. 2011.

[17] C. Y. J. Peng, K. L. Lee, and G. M. Ingersoll, “An introduction to logistic regression analysis and reporting,” J. Educ. Res., vol. 96, no. 1, pp. 3–14, 2002, doi: 10.1080/00220670209598786.

[18] A. Primajaya and B. N. Sari, “Random Forest Algorithm for Prediction of Precipitation,” Indones. J. Artif. Intell. Data Min., vol. 1, no. 1, p. 27, 2018, doi: 10.24014/ijaidm.v1i1.4903.

[19] F. Dhimas Syahfitra, R. Syahputra, and K. Trinanda Putra, “Implementation of Backpropagation Artificial Neural Network as a Forecasting System of Power Transformer Peak Load at Bumiayu Substation,” J. Electr. Technol. UMY, vol. 1, no. 3, pp. 118–125, 2017, doi: 10.18196/jet.1316.

[20] D. Visa Sofia, “Confusion Matrix-based Feature Selection Sofia Visa,” ConfusionMatrix-based Featur. Sel. Sofia, vol. 710, no. January, p. 8, 2011.

[21] K. Hajian-Tilaki, “Receiver operating characteristic (ROC) curve analysis for medical diagnostic test evaluation,” Casp. J. Intern. Med., vol. 4, no. 2, pp. 627–635, 2013.

[22] J. Luo, “KRAS mutation in pancreatic cancer,” Semin. Oncol., vol. 48, no. 1, pp. 10–18, 2021, doi: 10.1053/j.seminoncol.2021.02.003.

[23] I. A. Voutsadakis, “Mutations of p53 associated with pancreatic cancer and therapeutic implications,” Ann. Hepato-Biliary-Pancreatic Surg., vol. 25, no. 3, pp. 315–327, 2021, doi: 10.14701/ahbps.2021.25.3.315.

[24] Y. Tabach et al., “Amplification of the 20q chromosomal arm occurs early in tumorigenic transformation and may initiate cancer,” PLoS One, vol. 6, no. 1, 2011, doi: 10.1371/journal.pone.0014632.

[25] K. Ando et al., “Discrimination of p53 immunohistochemistry-positive tumors by its staining pattern in gastric cancer,” Cancer Med., vol. 4, no. 1, pp. 75–83, 2015, doi: 10.1002/cam4.346.

[26] R. R. McWilliams et al., “Prevalence of CDKN2A mutations in pancreatic cancer patients: Implications for genetic counseling,” Eur. J. Hum. Genet., vol. 19, no. 4, pp. 472–478, 2011, doi: 10.1038/ejhg.2010.198.

[27] J. B. Greer and D. C. Whitcomb, “Role of BRCA1 and BRCA2 mutations in pancreatic cancer,” Gut, vol. 56, no. 5, pp. 601–605, 2007, doi: 10.1136/gut.2006.101220.

[28] Human Prostate Gene Database, “BRCA1 BRCA1 DNA repair associated [Homo sapiens (human)] - Gene - NCBI.” 2002, [Online]. Available: https://www.ncbi.nlm.nih.gov/gene/672, accessed on November 4th, 2022.

[29] F. Harish Lavu, MD, FACS, Harry B Lengel, BA, Naomi M Sell, BA, Joseph A Baiocco, BS, Eugene P Kennedy, MD, FACS, Theresa P Yeo, PhD, Sherry A Burrell, PhD*, Jordan M Winter, MD, FACS, Sarah Hegarty, MPhilˆ, Benjamin E. Leiby, PhDˆ, and Charles J Yeo, MD, “A Prospective randomized double blind placebo controlled trial on the efficacy of ethanol cellac Plexsus neurolysis in patients with operable panceratic and periampullary adenocarcinoma,” J Am Coll Surg, vol. 220, no. 4, pp. 497–508, 2015, doi: 10.1016/j.jamcollsurg.2014.12.013.

[30] B. Muz, P. de la Puente, F. Azab, and A. K. Azab, “The role of hypoxia in cancer progression, angiogenesis, metastasis, and resistance to therapy,” Hypoxia, p. 83, 2015, doi: 10.2147/hp.s93413.

[31] Y. Xiao et al., “Prognostic relevance of lactate dehydrogenase in advanced pancreatic ductal adenocarcinoma patients,” BMC Cancer, vol. 17, no. 1, pp. 1–7, 2017, doi: 10.1186/s12885-016-3012-8.

[32] M. E. Cameron, A. Yakovenko, and J. G. Trevino, “Glucose and Lactate Transport in Pancreatic Cancer: Glycolytic Metabolism Revisited,” J. Oncol., vol. 2018, 2018, doi: 10.1155/2018/6214838.

[33] S. K. Shukla et al., “Erratum to: Metabolic reprogramming induced by ketone bodies diminishes pancreatic cancer cachexia,” Cancer Metab., vol. 2, no. 1, pp. 1–19, 2014, doi: 10.1186/2049-3002-2-22.

[34] H. N. Luu et al., “The Association between Serum Serine and Glycine and Related-Metabolites with Pancreatic Cancer in a Prospective Cohort Study,” Cancers (Basel)., vol. 14, no. 9, 2022, doi: 10.3390/cancers14092199.

[35] N. Ron-Harel et al., “T Cell Activation Depends on Extracellular Alanine,” Cell Rep., vol. 28, no. 12, pp. 3011-3021.e4, 2019, doi: 10.1016/j.celrep.2019.08.034.

[36] G. Yang and X. Zhang, “TMAO promotes apoptosis and oxidative stress of pancreatic acinar cells by mediating IRE1α-XBP-1 pathway,” Saudi J. Gastroenterol., vol. 27, no. 6, pp. 361–369, 2021, doi: 10.4103/sjg.sjg_12_21.

[37] Z. Y. Liu et al., “Trimethylamine N-oxide, a gut microbiota-dependent metabolite of choline, is positively associated with the risk of primary liver cancer: A case-control study,” Nutr. Metab., vol. 15, no. 1, pp. 1–9, 2018, doi: 10.1186/s12986-018-0319-2.