Integrated models of blood protein and metabolite enhance the diagnostic accuracy for Non-Small Cell Lung Cancer

Abstract

Background For early screening and diagnosis of non-small cell lung cancer (NSCLC), a robust model based on plasma proteomics and metabolomics is required for accurate and accessible non-invasive detection. Here we aim to combine TMT-LC-MS/MS and machine-learning algorithms to establish models with high specificity and sensitivity, and summarize a generalized model building scheme. Methods TMT-LC-MS/MS was used to discover the differentially expressed proteins (DEPs) in the plasma of NSCLC patients. Plasma proteomics-guided metabolites were selected for clinical evaluation in 110 NSCLC patients who were going to receive therapies, 108 benign pulmonary diseases (BPD) patients, and 100 healthy controls (HC). The data were randomly split into training set and test set in a ratio of 80:20. Three supervised learning algorithms were applied to the training set for models fitting. The best performance models were evaluated with the test data set. Results Differential plasma proteomics and metabolic pathways analyses revealed that the majority of DEPs in NSCLC were enriched in the pathways of complement and coagulation cascades, cholesterol and bile acids metabolism. Moreover, 10 DEPs, 14 amino acids, 15 bile acids, as well as 6 classic tumor biomarkers in blood were quantified using clinically validated assays. Finally, we obtained a high-performance screening model using logistic regression algorithm with AUC of 0.96, sensitivity of 92%, and specificity of 89%, and a diagnostic model with AUC of 0.871, sensitivity of 86%, and specificity of 78%. In the test set, the screening model achieved accuracy of 90%, sensitivity of 91%, and specificity of 90%, and the diagnostic model achieved accuracy of 82%, sensitivity of 77%, and specificity of 86%. Conclusions Integrated analysis of DEPs, amino acid, and bile acid features based on plasma proteomics-guided metabolite profiling, together with classical tumor biomarkers, provided a much more accurate detection model for screening and differential diagnosis of NSCLC. In addition, this new mathematical modeling based on plasma proteomics-guided metabolite profiling will be used for evaluation of therapeutic efficacy and long-term recurrence prediction of NSCLC.

Integrative Analysis of Multi-Omic Data for the Characteristics of Endometrial Cancer

“…The whole flowchart of this study is shown in Figure . We first collected the RNA-seq data of EC from the TCGA database and prepared the expression data and clinical information for the further associated analysis. − To provide enough data for the model validation, we also divided the whole RNA-seq data set into two equal subsets: the training and the testing data set. The differentially expressed genes (DEGs) between the normal and cancer samples were combined with the prognostic genes screened out by univariate Cox regression for the selection of the genes whose expression is positively correlated with the hazard ratio by the least absolute shrinkage and selection operator (LASSO) regression for biomarker discovery.…”

Decision-Making on the Diagnosis of Oncological Diseases Using Cost-Sensitive SVM Classifiers Based on Datasets with a Variety of Features of Different Natures

“…Currently, especially in 2022-2023, there is a significant increase in the number of studies addressing aspects of the use of ML and DL technologies in the context of solving the problem of early diagnosis of cancer [3][4][5][6][7][11][12][13][14]20,26,37,38,[60][61][62][63][64][65][66]. At the same time, many of them are aimed at solving the problem of diagnosing ODs on the basis of biomarkers, including blood protein markers [13,14,[20][21][22][23][24]27,28,37,38,60]. However, most research solves the problem of binary classification with the identification of one specific disease, for example, breast [22], liver [12] or lung [37] cancer.…”

“…At the same time, many of them are aimed at solving the problem of diagnosing ODs on the basis of biomarkers, including blood protein markers [13,14,[20][21][22][23][24]27,28,37,38,60]. However, most research solves the problem of binary classification with the identification of one specific disease, for example, breast [22], liver [12] or lung [37] cancer. It is obvious that the problem of multiclass classification is, on the one hand, more complex, but, on the other hand, the data used in its solution contain more complex dependencies, the restoration of which should help the rapid diagnosis of oncological diseases [13,14,20].…”

“…The problem of working with data accommodating information on blood protein markers is addressed in a number of scientific papers [13,[21][22][23][24][25]37,38]. In particular, in [13], the so-called CancerSEEK test based on the logistic classifier (LC) is considered.…”

Integrative multi-omics analysis unravels the host response landscape and reveals a serum protein panel for early prognosis prediction for ARDS

“…The integration of multi-omics approaches, particularly the combination of proteomics and metabolomics, elucidates the interactions across different biological system layers, as demonstrated in studies on cardiomyopathy [ 7 ], non‑small cell lung cancer [ 8 ], hepatitis C infection [ 9 ], etc. Previous studies have utilized serum proteins or metabolites to investigate infectious diseases.…”