MyeloDB: a multi-omics resource for multiple myeloma.

Multiple myeloma (MM) is a common type of blood cancer affecting plasma cells originating from the lymphoid B-cell lineage. It accounts for about 10% of all hematological malignancies and can cause significant end-organ damage. The emergence of genomic technologies such as next-generation sequencing and gene expression analysis has opened new possibilities for early detection of multiple myeloma and identification of personalized treatment options. However, there remain significant challenges to overcome in MM research, including integrating multi-omics data, achieving a comprehensive understanding of the disease, and developing targeted therapies and biomarkers. The extensive data generated by these technologies presents another challenge for data analysis and interpretation. To bridge this gap, we have developed a multi-omics open-access database called MyeloDB. It includes gene expression profiling, high-throughput CRISPR-Cas9 screens, drug sensitivity resources profile, and biomarkers. MyeloDB contains 47 expression profiles, 3 methylation profiles comprising a total of 5630 patient samples and 25 biomarkers which were reported in previous studies. In addition to this, MyeloDB can provide significant insight of gene mutations in MM on drug sensitivity. Furthermore, users can download the datasets and conduct their own analyses. Utilizing this database, we have identified five novel genes, i.e., CBFB, MANF, MBNL1, SEPHS2, and UFM1 as potential drug targets for MM. We hope MyeloDB will serve as a comprehensive platform for researchers and foster novel discoveries in MM. MyeloDB Database URL: https://project.iith.ac.in/cgntlab/myelodb/ .

Deep learning-based classifier of diffuse large B-cell lymphoma cell-of-origin with clinical outcome.

Diffuse large B-cell lymphoma (DLBCL) is an aggressive form of non-Hodgkin lymphoma with poor response to R-CHOP therapy due to remarkable heterogeneity. Based on gene expression, DLBCL cases were divided into two subtypes, i.e. ABC and GCB, where ABC subtype is associated with poor outcomes. Due to its association with clinical outcome, this classification, also known as cell-of-origin (COO), is an efficient way to predict the response to R-CHOP therapy. Previous COO classification methods have some shortcomings, e.g. limited number of samples in the training dataset. These shortcomings challenge the robustness of methods and make it difficult to implicate these methods at clinical level. To overcome the shortcomings of previous methods, we developed a deep learning-based classifier model on a cohort of 381 DLBCL patients using expression data of 20 genes. We implemented multilayer perceptron (MLP) to train deep learning-based classifier, named MLP-COO. MLP-COO achieved accuracy of 99.70% and 94.70% on training and testing datasets, respectively, with 10-fold cross-validation. We also assessed its performance on an independent dataset of 294 DLBCL patients. On independent dataset, we achieved an accuracy of 95.90% with MCC of 0.917. To show its broader applicability, we used this classifier to predict the clinical outcome using survival data from two large cohorts of DLBCL patients. In survival analysis, MLP-COO recapitulates the survival probabilities of DLBCL patients based on their COO in both cohorts. We anticipate that MLP-COO model developed in this study will benefit in the accurate COO prediction of DLBCL patients and their clinical outcomes.