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.

Advances in methylation analysis of liquid biopsy in early cancer detection of colorectal and lung cancer.

Methylation patterns in cell-free DNA (cfDNA) have emerged as a promising genomic feature for detecting the presence of cancer and determining its origin. The purpose of this study was to evaluate the diagnostic performance of methylation-sensitive restriction enzyme digestion followed by sequencing (MRE-Seq) using cfDNA, and to investigate the cancer signal origin (CSO) of the cancer using a deep neural network (DNN) analyses for liquid biopsy of colorectal and lung cancer. We developed a selective MRE-Seq method with DNN learning-based prediction model using demethylated-sequence-depth patterns from 63,266 CpG sites using SacII enzyme digestion. A total of 191 patients with stage I-IV cancers (95 lung cancers and 96 colorectal cancers) and 126 noncancer participants were enrolled in this study. Our study showed an area under the receiver operating characteristic curve (AUC) of 0.978 with a sensitivity of 78.1% for colorectal cancer, and an AUC of 0.956 with a sensitivity of 66.3% for lung cancer, both at a specificity of 99.2%. For colorectal cancer, sensitivities for stages I-IV ranged from 76.2 to 83.3% while for lung cancer, sensitivities for stages I-IV ranged from 44.4 to 78.9%, both again at a specificity of 99.2%. The CSO model's true-positive rates were 94.4% and 89.9% for colorectal and lung cancers, respectively. The MRE-Seq was found to be a useful method for detecting global hypomethylation patterns in liquid biopsy samples and accurately diagnosing colorectal and lung cancers, as well as determining CSO of the cancer using DNN analysis.Trial registration: This trial was registered at ClinicalTrials.gov (registration number: NCT04253509) for lung cancer on 5 February 2020, https://clinicaltrials.gov/ct2/show/NCT04253509 . Colorectal cancer samples were retrospectively registered at CRIS (Clinical Research Information Service, registration number: KCT0008037) on 23 December 2022, https://cris.nih.go.kr , https://who.init/ictrp . Healthy control samples were retrospectively registered.

Clinical Implications of Quantitative JAK2 V617F Analysis using Droplet Digital PCR in Myeloproliferative Neoplasms.

BACKGROUND: JAK2 V617F is the most common mutation in myeloproliferative neoplasms (MPNs) and is a major diagnostic criterion. Mutation quantification is useful for classifying patients with MPN into subgroups and for prognostic prediction. Droplet digital PCR (ddPCR) can provide accurate and reproducible quantitative analysis of DNA. This study was designed to verify the correlation of ddPCR with pyrosequencing results in the diagnosis of MPN and to investigate clinical implications of the mutational burden. METHODS: Peripheral blood or bone marrow samples were obtained from 56 patients newly diagnosed with MPN or previously diagnosed with MPN but not yet indicated for JAK2 inhibitor treatment between 2012 and 2016. The JAK2 V617F mutation was detected by pyrosequencing as a diagnostic work-up. The same samples were used for ddPCR to determine the correlation between assays and establish a detection sensitivity cut-off. Clinical and hematologic aspects were reviewed. RESULTS: Forty-two (75%) and 46 (82.1%) patients were positive for JAK2 V617F by pyrosequencing and ddPCR, respectively. The mean mutated allele frequency at diagnosis was 37.5±30.1% and was 40.7±31.2% with ddPCR, representing a strong correlation (r=0.9712, P<0.001). Follow-up samples were available for 12 patients, including eight that were JAK2 V617F-positive. Of these, mutational burden reduction after treatment was observed in six patients (75%), consistent with trends of hematologic improvement. CONCLUSIONS: Quantitative analysis of the JAK2 V617F mutation using ddPCR was highly correlated with pyrosequencing data and may reflect the clinical response to treatment.

Chromothripsis in Treatment Resistance in Multiple Myeloma.

Multiple myeloma (MM) is a malignant disease caused by an abnormal proliferation of plasma cells, of which the prognostic factors include chromosomal abnormality, ß-2 microglobulin, and albumin. Recently, the term chromothripsis has emerged, which is the massive but highly localized chromosomal rearrangement in response to a one-step catastrophic event. Many studies have shown an association of chromothripsis with the prognosis in several cancers; however, few studies have investigated it in MM. Here, we studied the association between chromothripsis-like patterns and treatment resistance or prognosis. First, we analyzed nine MM cell lines (U266, MM.1S, RPMI8226, KMS-11, KMS-12-BM, KMS-12-PE, KMS-28-BM, KMS-28-PE, and NCI-H929) and bone marrow samples of four patients who were diagnosed with MM by next-generation sequencing-based copy number variation analysis. The frequency of the chromothripsis-like pattern was observed in seven cell lines. We analyzed the treatment-induced chromothripsis-like patterns in KMS-12-BM and KMS-12-PE cells. As a result, breakpoints and chromothripsis-like patterns were increased after drug treatment in the relatively resistant KMS-12-BM. We further analyzed the patients' results according to the therapeutic response, which was divided into sensitive and resistant, as suggested by the International Myeloma Working Group. The chromothripsis-like pattern was more frequently observed in the resistant group. In the sensitive group, the frequency of the chromothripsis-like pattern decreased after treatment, whereas the resistant group showed increased chromothripsis-like patterns after the treatment. These results suggest that the chromothripsis-like pattern is associated with treatment response in MM.

Tumor-derived IL-18 induces PD-1 expression on immunosuppressive NK cells in triple-negative breast cancer.

PURPOSE: While the inflammatory cytokine interleukin-18 (IL-18) is known to activate natural killer (NK) cells, its precise role in cancer is controversial. In this study, we investigated the role of tumor-derived IL-18 on peripheral blood NK cells in breast cancer patients. RESULTS: In breast cancer cell lines, IL-18 was expressed and secreted in the triple-negative breast cancer (TNBC) cell lines MDA-MB-231 and HCC-70 but not in MCF-7 cells. The immature and non-cytotoxic CD56dimCD16dim/- NK cell fraction was increased following co-culture with MDA-MB-231 cells, and this increase was not observed with tumor cells transfected with siRNA for IL-18 or in MCF-7 cells. In addition, tumor-derived IL-18 increased PD-1 expression on CD56dimCD16dim/- NK cells, although no effect on PD-L1 expression in tumor cells was observed. Among EBC patients, serum IL-18 levels were significantly increased in those with a TNBC subtype compared to levels from patients with other subtypes, and the IL-18 levels were strongly associated with poor survival. Similarly, serum IL-18 and CD56dimCD16dim/- NK cells were also increased in patients with metastatic TNBC who had progressive disease following cytotoxic chemotherapy. EXPERIMENTAL DESIGN: We performed in vitro experiments in breast cancer cell lines, measured cytokine levels by RT-qPCR, western blot, and ELISA, and analyzed NK cell subsets by flow cytometry. For clinical validation, we collected and analyzed blood sample from patients with early breast cancer (EBC, N = 545) and metastatic breast cancer (MBC, N = 42). CONCLUSIONS: Our data revealed that tumor-derived IL-18 is associated with bad prognosis in patients with TNBC. Tumor-derived IL-18 increased the immunosuppressive CD56dimCD16dim/- NK cell fraction and induced PD-1 expression on these NK cells.