Infrared molecular fingerprinting of blood-based liquid biopsies for the detection of cancer

Abstract

Recent omics analyses of human biofluids provide opportunities to probe selected species of biomolecules for disease diagnostics. Fourier-transform infrared (FTIR) spectroscopy investigates the full repertoire of molecular species within a sample at once. Here, we present a multi-institutional study in which we analysed infrared fingerprints of plasma and serum samples from 1639 individuals with different solid tumours and carefully matched symptomatic and non-symptomatic reference individuals. Focusing on breast, bladder, prostate, and lung cancer, we find that infrared molecular fingerprinting is capable of detecting cancer: training a support vector machine algorithm allowed us to obtain binary classification performance in the range of 0.78–0.89 (area under the receiver operating characteristic curve [AUC]), with a clear correlation between AUC and tumour load. Intriguingly, we find that the spectral signatures differ between different cancer types. This study lays the foundation for high-throughput onco-IR-phenotyping of four common cancers, providing a cost-effective, complementary analytical tool for disease recognition.

Machine learning diagnosis by immunoglobulinN‐glycan signatures for precision diagnosis of urological diseases

“…Several N-glycan signatures, such as sialylation, fucosylation, bisecting GlcNAcylation, and branching, are regulated by various glycosyltransferase activities, and their synthetic pathways could influence each other. Although discriminating three or more diseases by discriminant analysis using N-glycan signatures has been limited, an ML approach combined with omics data has been used for early detection of diseases, including cancer [16][17][18][19] and seems to be suitable for extraction of disease-specific N-glycan features and precise discrimination between benign and malignant conditions.…”

“…Statistical analyses to extract disease‐specific N ‐glycan signatures from vast amounts of N ‐glycomics data on complex N ‐glycan structures and their synthetic pathways are limited. Therefore, ML approaches could be an important tool for these analyses 16–19 . We aimed to simultaneously detect nine urological diseases including five cancers (RCC, BCa, UTUC, PC, and GCT) and three benign diseases (BPH, US, and UTI) using a diagnostic modeling ML approach with Ig N ‐glycan signature data.…”

“…Therefore, ML approaches could be an important tool for these analyses. [16][17][18][19] We aimed to simultaneously detect nine urological diseases including five cancers (RCC, BCa, UTUC, PC, and GCT) and three benign diseases (BPH, US, and UTI) using a diagnostic modeling ML approach with Ig N-glycan signature data. Thirty-seven patients were excluded because the presence or absence of disease could not be determined from medical records.…”

Fast and Deep Diagnosis Using Blood-Based ATR-FTIR Spectroscopy for Digestive Tract Cancers

“…The average of the correctness of the ten results is used as an estimate of the accuracy of the algorithm. This approach aims to identify the signals of cancer from a known patient cohort to develop a trained classification model and then use this information to predict the presence of cancer in an unknown population [ 41 , 42 ].…”

Liquid biopsy in lung cancer: significance in diagnostics, prediction, and treatment monitoring

“…Additionally, during cisplatin-induced drug resistance, the expression of mir-146a-5p in NSCLC cell lines or exosomes decreased gradually, while overexpression of mir-146a-5p was shown to reverse DDP resistance in A549 cells. These findings suggested that inhibition of exosome formation and release may be a potential new strategy for the treatment of lung cancer [ 50 ].…”