Machine learning models-based on integration of next-generation sequencing testing and tumor cell sizes improve subtype classification of mature B-cell neoplasms.

Background: Next-generation sequencing (NGS) panels for mature B-cell neoplasms (MBNs) are widely applied clinically but have yet to be routinely used in a manner that is suitable for subtype differential diagnosis. This study retrospectively investigated newly diagnosed cases of MBNs from our laboratory to investigate mutation landscapes in Chinese patients with MBNs and to combine mutational information and machine learning (ML) into clinical applications for MBNs, especially for subtype classification. Methods: Samples from the Catalogue Of Somatic Mutations In Cancer (COSMIC) database were collected for ML model construction and cases from our laboratory were used for ML model validation. Five repeats of 10-fold cross-validation Random Forest algorithm was used for ML model construction. Mutation detection was performed by NGS and tumor cell size was confirmed by cell morphology and/or flow cytometry in our laboratory. Results: Totally 849 newly diagnosed MBN cases from our laboratory were retrospectively identified and included in mutational landscape analyses. Patterns of gene mutations in a variety of MBN subtypes were found, important to investigate tumorigenesis in MBNs. A long list of novel mutations was revealed, valuable to both functional studies and clinical applications. By combining gene mutation information revealed by NGS and ML, we established ML models that provide valuable information for MBN subtype classification. In total, 8895 cases of 8 subtypes of MBNs in the COSMIC database were collected and utilized for ML model construction, and the models were validated on the 849 MBN cases from our laboratory. A series of ML models was constructed in this study, and the most efficient model, with an accuracy of 0.87, was based on integration of NGS testing and tumor cell sizes. Conclusions: The ML models were of great significance in the differential diagnosis of all cases and different MBN subtypes. Additionally, using NGS results to assist in subtype classification of MBNs by method of ML has positive clinical potential.

MYD88-Mutated Chronic Lymphocytic Leukaemia/Small Lymphocytic Lymphoma as a Distinctive Molecular Subgroup Is Associated with Atypical Immunophenotypes in Chinese Patients.

Chronic lymphocytic leukaemia/small lymphocytic lymphoma (CLL/SLL) is a heterogeneous disease in Western and Chinese populations, and it is still not well characterized in Chinese patients. Based on a large cohort of newly diagnosed CLL/SLL patients from China, we investigated immunophenotypes, genetic abnormalities, and their correlations. Eighty-four percent of the CLL/SLL patients showed typical immunophenotypes with scores of 4 or 5 points in the Royal Marsden Hospital (RMH) scoring system (classic group), and the remaining 16% of patients were atypical with scores lower than 4 points (atypical group). Trisomy 12 and variants of TP53, NOTCH1, SF3B1, ATM, and MYD88 were the most recurrent genetic aberrations. Additionally, unsupervised genomic analysis based on molecular genetics revealed distinctive characteristics of MYD88 variants in CLL/SLL. By overlapping different correlation grouping analysis from genetics to immunophenotypes, the results showed MYD88 variants to be highly related to atypical CLL/SLL immunophenotypes. Furthermore, compared with mantle cell lymphoma (MCL), the genetic landscape showed potential value in clinical differential diagnosis of atypical CLL/SLL and MCL patients. These results reveal immunophenotypic and genetic features, and may provide insights into the tumorigenesis and clinical management of Chinese CLL/SLL patients.

High expression of N-type calcium channel indicates a favorable prognosis in gliomas.

For the diagnosis and prognosis of glioma, the development of prognostic biomarkers is critical. The N-type calcium channel, whose predominant subunit is encoded by calcium voltage-gated channel subunit alpha1 B (CACNA1B), is mostly found in the nervous system and is closely associated with neurosensory functions. However, the link between the expression of CACNA1B and glioma remains unknown. We used ONCOMINE to explore the differences in CACNA1B expression among different cancers. We then conducted survival analysis and COX analysis using TCGA_LGG and TCGA_GBM datasets, which were divided into CACNA1Bhigh and CACNA1Blow based on the median. We examined the differences in other favorable prognostic markers or clinical characteristics between CACNA1Bhigh and CACNA1Blow using t tests. Differentially expressed genes were identified, and KEGG pathway enrichment was performed. We compared the expression of methyltransferases and analyzed the differentially methylated regions. Immunohistochemistry results were retrieved from the Human Protein Atlas database for validation purposes. CACNA1B was expressed at lower levels in gliomas, and, for the first time, we found that high expression of CACNA1B in gliomas predicts a good prognosis. Other favorable prognostic markers, such as isocitrate dehydrogenase mutation, 1p/19q codeletion, and O6-methylguanine-DNA methyltransferase promoter methylation, were increased in tandem with high expression of CACNA1B. Differentially expressed genes were enriched in multiple pathways related to cancer progression and aberrant epigenetic alterations were significantly associated with CACNA1B. High expression of N-type calcium channels indicates a favorable prognosis for gliomas. This study provides a better understanding of the link between gliomas and N-type calcium channels and may offer guidance for the future treatment of gliomas.