Improving the accuracy of noninvasive prenatal testing through size-selection between fetal and maternal cfDNA.

OBJECTIVES: In general, fetal cfDNA is shorter than maternal cfDNA, and accuracy of noninvasive prenatal testing (NIPT) results can be improved by selecting shorter cfDNA fragments to enrich fetal-derived cfDNA. This study investigated potential improvements in the accuracy of NIPT by performing classification and analysis based on differences in cfDNA size. METHODS: We performed paired-end sequencing to identify size ranges of fetal and maternal cfDNA from 62,374 pregnant women. We then developed a size-selection method to isolate and analyze both fetal and maternal cfDNA, defining fetal-derived cfDNA as less than 150 bp and maternal-derived cfDNA as greater than 180 bp. RESULTS: By implementing size-selection method, the accuracy of NIPT was improved, resulting in an increase in the overall positive predictive value for all aneuploidies from 89.57% to 97.1%. This was achieved by enriching both fetal and maternal-derived cfDNA, which increased fetal DNA fraction while the number of false positives for all aneuploidies was reduced by more than 70%. CONCLUSIONS: We identified the differences in read length between fetal and maternal-derived cfDNA, and selectively enriched both shorter and longer cfDNA fragments for subsequent analysis. Our approach can increase the detection accuracy of NIPT for detecting fetal aneuploidies and reduce the number of false positives caused by maternal chromosomal abnormalities.

Enhancing Lung Cancer Classification through Integration of Liquid Biopsy Multi-Omics Data with Machine Learning Techniques.

Early detection of lung cancer is crucial for patient survival and treatment. Recent advancements in next-generation sequencing (NGS) analysis enable cell-free DNA (cfDNA) liquid biopsy to detect changes, like chromosomal rearrangements, somatic mutations, and copy number variations (CNVs), in cancer. Machine learning (ML) analysis using cancer markers is a highly promising tool for identifying patterns and anomalies in cancers, making the development of ML-based analysis methods essential. We collected blood samples from 92 lung cancer patients and 80 healthy individuals to analyze the distinction between them. The detection of lung cancer markers Cyfra21 and carcinoembryonic antigen (CEA) in blood revealed significant differences between patients and controls. We performed machine learning analysis to obtain AUC values via Adaptive Boosting (AdaBoost), Multi-Layer Perceptron (MLP), and Logistic Regression (LR) using cancer markers, cfDNA concentrations, and CNV screening. Furthermore, combining the analysis of all multi-omics data for ML showed higher AUC values compared with analyzing each element separately, suggesting the potential for a highly accurate diagnosis of cancer. Overall, our results from ML analysis using multi-omics data obtained from blood demonstrate a remarkable ability of the model to distinguish between lung cancer and healthy individuals, highlighting the potential for a diagnostic model against lung cancer.