Search

Abstract The most widely practiced strategy for constructing the deep learning (DL) prediction model for drug resistance of Mycobacterium tuberculosis (MTB) involves the adoption of ready-made and state-of-the-art architectures usually proposed for non-biological problems. However, the ultimate goal is to construct a customized model for predicting the drug resistance of MTB and eventually for the biological phenotypes based on genotypes. Here, we constructed a DL training framework to standardize and modularize each step during the training process using the latest tensorflow 2 API. A systematic and comprehensive evaluation of each module in the three currently representative models, including Convolutional Neural Network, Denoising Autoencoder, and Wide & Deep, which were adopted by CNNGWP, DeepAMR, and WDNN, respectively, was performed in this framework regarding module contributions in order to assemble a novel model with proper dedicated modules. Based on the whole-genome level mutations, a de novo learning method was developed to overcome the intrinsic limitations of previous models that rely on known drug resistance-associated loci. A customized DL model with the multilayer perceptron architecture was constructed and achieved a competitive performance (the mean sensitivity and specificity were 0.90 and 0.87, respectively) compared to previous ones. The new model developed was applied in an end-to-end user-friendly graphical tool named TB-DROP (TuBerculosis Drug Resistance Optimal Prediction: https://github.com/nottwy/TB-DROP ), in which users only provide sequencing data and TB-DROP will complete analysis within several minutes for one sample. Our study contributes to both a new strategy of model construction and clinical application of deep learning-based drug-resistance prediction methods.

Abstract Single-cell sequencing has shed light on previously inaccessible biological questions from different fields of research, including organism development, immune function, and disease progression. The number of single-cell-based studies increased dramatically over the past decade. Several new methods and tools have been continuously developed, making it extremely tricky to navigate this research landscape and develop an up-to-date workflow to analyze single-cell sequencing data, particularly for researchers seeking to enter this field without computational experience. Moreover, choosing appropriate tools and optimal parameters to meet the demands of researchers represents a major challenge in processing single-cell sequencing data. However, a specific resource for easy access to detailed information on single-cell sequencing methods and data processing pipelines is still lacking. In the present study, an online resource called SingleScan was developed to curate all up-to-date single-cell transcriptome/genome analyzing tools and pipelines. All the available tools were categorized according to their main tasks, and several typical workflows for single-cell data analysis were summarized. In addition, spatial transcriptomics, which is a breakthrough molecular analysis method that enables researchers to measure all gene activity in tissue samples and map the site of activity, was included along with a portion of single-cell and spatial analysis solutions. For each processing step, the available tools and specific parameters used in published articles are provided and how these parameters affect the results is shown in the resource. All information used in the resource was manually extracted from related literature. An interactive website was designed for data retrieval, visualization, and download. By analyzing the included tools and literature, users can gain insights into the trends of single-cell studies and easily grasp the specific usage of a specific tool. SingleScan will facilitate the analysis of single-cell sequencing data and promote the development of new tools to meet the growing and diverse needs of the research community. The SingleScan database is publicly accessible via the website at http://cailab.labshare.cn/SingleScan .

Abstract Background High oncogene expression in cancer cells is a major cause of rapid tumor progression and drug resistance. Recent cancer genome research has shown that oncogenes as well as regulatory elements can be amplified in the form of extrachromosomal DNA (ecDNA) or subsequently integrated into chromosomes as homogeneously staining regions (HSRs). These genome-level variants lead to the overexpression of the corresponding oncogenes, resulting in poor prognosis. Most existing detection methods identify ecDNA using whole genome sequencing (WGS) data. However, these techniques usually detect many false positive regions owing to chromosomal DNA interference. Results In the present study, an algorithm called “ATACAmp” that can identify ecDNA/HSRs in tumor genomes using ATAC-seq data has been described. High chromatin accessibility, one of the characteristics of ecDNA, makes ATAC-seq naturally enriched in ecDNA and reduces chromosomal DNA interference. The algorithm was validated using ATAC-seq data from cell lines that have been experimentally determined to contain ecDNA regions. ATACAmp accurately identified the majority of validated ecDNA regions. AmpliconArchitect, the widely used ecDNA detecting tool, was used to detect ecDNA regions based on the WGS data of the same cell lines. Additionally, the Circle-finder software, another tool that utilizes ATAC-seq data, was assessed. The results showed that ATACAmp exhibited higher accuracy than AmpliconArchitect and Circle-finder. Moreover, ATACAmp supported the analysis of single-cell ATAC-seq data, which linked ecDNA to specific cells. Conclusions ATACAmp, written in Python, is freely available on GitHub under the MIT license: https://github.com/chsmiss/ATAC-amp . Using ATAC-seq data, ATACAmp offers a novel analytical approach that is distinct from the conventional use of WGS data. Thus, this method has the potential to reduce the cost and technical complexity associated ecDNA analysis.

Abstract Background The yak is a species of livestock which is crucial for local communities of the Qinghai-Tibet Plateau and adjacent regions and naturally owns one more thoracic vertebra than cattle. Recently, a sub-population of yak termed as the Jinchuan yak has been identified with over half its members own a thoracolumbar vertebral formula of T15L5 instead of the natural T14L5 arrangement. The novel T15L5 positioning is a preferred genetic trait leading to enhanced meat and milk production. Selective breeding of this trait would have great agricultural value and exploration of the molecular mechanisms underlying this trait would both accelerate this process and provide us insight into the development and regulation of somitogenesis. Results Here we investigated the genetic background of the Jinchuan yak through resequencing fifteen individuals, comprising five T15L5 individuals and ten T14L5 individuals with an average sequencing depth of > 10X, whose thoracolumbar vertebral formulae were confirmed by anatomical observation. Principal component analysis, linkage disequilibrium analysis, phylogenetic analysis, and selective sweep analysis were carried out to explore Jinchuan yak’s genetic background. Three hundred and thirty candidate markers were identified as associated with the additional thoracic vertebrae and target sequencing was used to validate seven carefully selected markers in an additional 51 Jinchuan yaks. The accuracies of predicting 15 thoracic vertebrae and 20 thoracolumbar vertebrae with these 7 markers were 100.00 and 33.33% despite they both could only represent 20% of all possible genetic diversity. Two genes, PPP2R2B and TBLR1, were found to harbour the most candidate markers associated with the trait and likely contribute to the unique somitic number and identity according to their reported roles in the mechanism of somitogenesis. Conclusions Our findings provide a clear depiction of the Jinchuan yak’s genetic background and a solid foundation for marker-assistant selection. Further exploitation of this unique population and trait could be promoted with the aid of our genomic resource.

Abstract Background The integration of DNA methylation and copy number alteration data promises to provide valuable insight into the underlying molecular mechanisms responsible for cancer initiation and progression. However, the generation and processing of these datasets are costly and time-consuming if carried out separately. The Illumina Infinium HumanMethylation450 BeadChip, initially designed for the evaluation of DNA methylation levels, allows copy number variant calling using bioinformatics tools. Results A substantial amount of Infinium HumanMethylation450 data across various cancer types has been accumulated in recent years and is a valuable resource for large-scale data analysis. Here we present MethCNA, a comprehensive database for genomic and epigenomic data integration in human cancer. In the current release, MethCNA contains about 10,000 tumor samples representing 37 cancer types. All raw array data were collected from The Cancer Genome Atlas and NCBI Gene Expression Omnibus database and analyzed using a pipeline that integrated multiple computational resources and tools. The normalized copy number aberration data and DNA methylation alterations were obtained. We provide a user-friendly web-interface for data mining and visualization. Conclusions The Illumina Infinium HumanMethylation450 BeadChip enables the interrogation and integration of both genomic and epigenomic data from exactly the same DNA specimen, and thus can aid in distinguishing driver from passenger mutations in cancer. We expect MethCNA will enable researchers to explore DNA methylation and copy number alteration patterns, identify key oncogenic drivers in cancer, and assist in the development of targeted therapies. MethCNA is publicly available online at http://cgma.scu.edu.cn/MethCNA.