High-performance Collective Biomarker from Liquid Biopsy for Diagnosis of Pancreatic Cancer Based on Mass Spectrometry and Machine Learning

Abstract

Background: Most pancreatic cancers are found at progressive stages when they cannot be surgically removed. Therefore, a highly accurate early detection method is urgently needed. Methods: This study analyzed serum from Japanese patients who suffered from pancreatic ductal adenocarcinoma (PDAC) and aimed to establish a PDAC-diagnostic system with metabolites in serum. Two groups of metabolites, primary metabolites (PM) and phospholipids (PL), were analyzed using liquid chromatography/electrospray ionization mass spectrometry. A support vector machine was employed to establish a machine learning-based diagnostic algorithm. Results: Integrating PM and PL databases improved cancer diagnostic accuracy and the area under the receiver operating characteristic curve. It was more effective than the algorithm based on either PM or PL database, or single metabolites as a biomarker. Subsequently, 36 statistically significant metabolites were fed into the algorithm as a collective biomarker, which improved results by accomplishing 97.4% and was further validated by additional serum. Interestingly, specific clusters of metabolites from patients with preoperative neoadjuvant chemotherapy (NAC) showed different patterns from those without NAC and were somewhat comparable to those of the control. Conclusion: We propose an efficient screening system for PDAC with high accuracy by liquid biopsy and potential biomarkers useful for assessing NAC performance.

Keywords: Liquid biopsy; Machine leargning; Metabolome; Neoadjuvant chemotherapy; Pancreatic ductal adenocarcinoma.

Figure 1

The analysis flow and diagnostic outcomes by machine learning. A The design and flow of this study. B-D Scatter plots of PLSR for PDAC and control by metabolome data. Orange and blue plots indicate PDAC and control, respectively. Three sets of a database composed of 91 PMs (B), 178 PLs (C), and a combination of both (D) were used. A variance of each principal component (Comp) is indicated on the ordinate and abscissa. E-H ROC curves were drawn with sensitivity on the ordinate false-positive fraction on the abscissa. Support vector machine was fed with the same database used for PLSR as shown in B-D. Validation of the independent cohort gave similar outcomes as shown in G. PM primary metabolites, PL phospholipids, PDAC pancreatic ductal adenocarcinoma, PLSR partial least square regression, ROC receiver operating characteristics, AUC area under the curve, SVM support vector machine.

Figure 2

The database based on the selected PM and PL (collective biomarker) gave the strongest prediction for PDAC than a single biomarker. A, B Boxplots of representative primary metabolites (A) and phospholipids (B) significantly changed in PDAC. Ion intensities were normalized by median and autoscaling with MetaboAnalyst 5.0. C, D ROC curves were drawn based on the database with selected 36 metabolites (C) from the training dataset or 36 metabolites from the validation dataset (D). E, F ROC curves were drawn for each primary metabolite (E) and phospholipid (F). AUC was calculated from the ROC curves. PM primary metabolites, PL phospholipids, PDAC pancreatic ductal adenocarcinoma, ROC receiver operating characteristics, AUC area under the curve.

Figure 3

NAC treatment affected the metabolic profiles of the patients' serum. A Scatterplots of PLSR of PDAC without NAC (non-NAC), with NAC (NAC), and control by metabolome data. Pink, green, and blue plots indicate non-NAC, NAC, and control, respectively. Database with integrated 269 PM and PL were used. The variance of each principal component (Comp) is indicated on the ordinate and abscissa. B Heatmap showing the normalized ion intensity of significantly differed metabolites for each group. Metabolites with similar ion intensity patterns were arbitrarily assembled into three clusters. C-E Boxplots of metabolites significantly representing each cluster are shown. Ion intensity of each spectrum was normalized with median and autoscaling by MetaboAnalyst 5.0. PDAC pancreatic ductal adenocarcinoma, NAC neoadjuvant chemotherapy, PLSR partial least square regression, PM primary metabolites, PL phospholipids. Statistical significance was assigned *p < 0.05, **p < 0.01, and ***p <0.001.