MOTIVATION: The mutations of cancers can encode the seeds of their own destruction, in the form of T-cell recognizable immunogenic peptides, also known as neoantigens. It is computationally challenging, however, to accurately prioritize the potential neoantigen candidates according to their ability of activating the T-cell immunoresponse, especially when the somatic mutations are abundant. Although a few neoantigen prioritization methods have been proposed to address this issue, advanced machine learning model that is specifically designed to tackle this problem is still lacking. Moreover, none of the existing methods considers the original DNA loci of the neoantigens in the perspective of 3D genome which may provide key information for inferring neoantigens' immunogenicity. RESULTS: In this study, we discovered that DNA loci of the immunopositive and immunonegative MHC-I neoantigens have distinct spatial distribution patterns across the genome. We therefore used the 3D genome information along with an ensemble pMHC-I coding strategy, and developed a group feature selection-based deep sparse neural network model (DNN-GFS) that is optimized for neoantigen prioritization. DNN-GFS demonstrated increased neoantigen prioritization power comparing to existing sequence-based approaches. We also developed a webserver named deepAntigen (http://yishi.sjtu.edu.cn/deepAntigen) that implements the DNN-GFS as well as other machine learning methods. We believe that this work provides a new perspective toward more accurate neoantigen prediction which eventually contribute to personalized cancer immunotherapy. AVAILABILITY AND IMPLEMENTATION: Data and implementation are available on webserver: http://yishi.sjtu.edu.cn/deepAntigen. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Single-cell transcriptomic data are commonly accompanied by extremely high technical noise due to the low RNA concentrations from individual cells. Precise identification of differentially expressed genes and cell populations are heavily dependent on the effective reduction of technical noise, e.g. by gene filtering. However, there is still no well-established standard in the current approaches of gene filtering. Investigators usually filter out genes based on single fixed threshold, which commonly leads to both over- and under-stringent errors. RESULTS: In this study, we propose a novel algorithm, termed as Optimal Gene Filtering for Single-Cell data, to construct a thresholding curve based on gene expression levels and the corresponding variances. We validated our method on multiple single-cell RNA-seq datasets, including simulated and published experimental datasets. The results show that the known signal and known noise are reliably discriminated in the simulated datasets. In addition, the results of seven experimental datasets demonstrate that these cells of the same annotated types are more sharply clustered using our method. Interestingly, when we re-analyze the dataset from an aging research recently published in Science, we find a list of regulated genes which is different from that reported in the original study, because of using different filtering methods. However, the knowledge based on our findings better matches the progression of immunosenescence. In summary, we here provide an alternative opportunity to probe into the true level of technical noise in single-cell transcriptomic data. AVAILABILITY AND IMPLEMENTATION: https://github.com/XZouProjects/OGFSC.git. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

BACKGROUND: With the developments of DNA sequencing technology, large amounts of sequencing data have become available in recent years and provide unprecedented opportunities for advanced association studies between somatic point mutations and cancer types/subtypes, which may contribute to more accurate somatic point mutation based cancer classification (SMCC). However in existing SMCC methods, issues like high data sparsity, small volume of sample size, and the application of simple linear classifiers, are major obstacles in improving the classification performance. RESULTS: To address the obstacles in existing SMCC studies, we propose DeepGene, an advanced deep neural network (DNN) based classifier, that consists of three steps: firstly, the clustered gene filtering (CGF) concentrates the gene data by mutation occurrence frequency, filtering out the majority of irrelevant genes; secondly, the indexed sparsity reduction (ISR) converts the gene data into indexes of its non-zero elements, thereby significantly suppressing the impact of data sparsity; finally, the data after CGF and ISR is fed into a DNN classifier, which extracts high-level features for accurate classification. Experimental results on our curated TCGA-DeepGene dataset, which is a reformulated subset of the TCGA dataset containing 12 selected types of cancer, show that CGF, ISR and DNN all contribute in improving the overall classification performance. We further compare DeepGene with three widely adopted classifiers and demonstrate that DeepGene has at least 24% performance improvement in terms of testing accuracy. CONCLUSIONS: Based on deep learning and somatic point mutation data, we devise DeepGene, an advanced cancer type classifier, which addresses the obstacles in existing SMCC studies. Experiments indicate that DeepGene outperforms three widely adopted existing classifiers, which is mainly attributed to its deep learning module that is able to extract the high level features between combinatorial somatic point mutations and cancer types.