Ying Cui

When classifying breeds of dogs, the accuracy of classification significantly affects breed identification and dog research. Using images to classify dog breeds can improve classification efficiency; however, it is increasingly challenging due to the diversities and similarities among dog breeds. Traditional image classification methods primarily rely on extracting simple geometric features, while current convolutional neural networks (CNNs) are capable of learning high-level semantic features. However, the diversity of dog breeds continues to pose a challenge to classification accuracy. To address this, we developed a model that integrates multiple CNNs with a machine learning method, significantly improving the accuracy of dog images classification. We used the Stanford Dog Dataset, combined image features from four CNN models, filtered the features using principal component analysis (PCA) and gray wolf optimization algorithm (GWO), and then classified the features with support vector machine (SVM). The classification accuracy rate reached 95.24% for 120 breeds and 99.34% for 76 selected breeds, respectively, demonstrating a significant improvement over existing methods using the same Stanford Dog Dataset. It is expected that our proposed method will further serve as a fundamental framework for the accurate classification of a wider range of species.

Immune checkpoint blockades (ICBs) have revolutionized cancer therapy by inducing durable clinical responses, but only a small percentage of patients can benefit from ICB treatments. Many studies have established various biomarkers to predict ICB responses. However, different biomarkers were found with diverse performances in practice, and a timely and unbiased assessment has yet to be conducted due to the complexity of ICB-related studies and trials. In this study, we manually curated 29 published datasets with matched transcriptome and clinical data from more than 1400 patients, and uniformly preprocessed these datasets for further analyses. In addition, we collected 39 sets of transcriptomic biomarkers, and based on the nature of the corresponding computational methods, we categorized them into the gene-set-like group (with the self-contained design and the competitive design, respectively) and the deconvolution-like group. Next, we investigated the correlations and patterns of these biomarkers and utilized a standardized workflow to systematically evaluate their performance in predicting ICB responses and survival statuses across different datasets, cancer types, antibodies, biopsy times, and combinatory treatments. In our benchmark, most biomarkers showed poor performance in terms of stability and robustness across different datasets. Two scores (TIDE and CYT) had a competitive performance for ICB response prediction, and two others (PASS-ON and EIGS_ssGSEA) showed the best association with clinical outcome. Finally, we developed ICB-Portal to host the datasets, biomarkers, and benchmark results and to implement the computational methods for researchers to test their custom biomarkers. Our work provided valuable resources and a one-stop solution to facilitate ICB-related research.

Convolutional neural network (CNN) has been widely used for fine-grained image classification, which has proven to be an effective approach for the classification and identification of specific species. For breed classification of dog, there are several proposed methods based on dog images, however, the highest accuracy rate for dogs (about 93%) is still below expectations compared to other animals or plants (more than 95% on birds and more than 97% on flowers). In this study, we used the Stanford Dog Dataset, combined image features from four CNN models, filtered the features using principal component analysis (PCA) and gray wolf optimization algorithm (GWO), and then classified the features with support vector machine (SVM). Eventually, the classification accuracy rate reached 95.24% for 120 breeds and 99.34% for 76 selected breeds, respectively, demonstrating a significant improvement over existing methods using the same Stanford Dog Dataset. It is expected that our proposed method will further serve as a fundamental framework for accurate classification of a wider range of species.

Learning outcome modeling is a technical underpinning for the successful evaluation of learners' learning outcomes through computer-based assessments. In recent years, collaborative filtering approaches have gained popularity as a technique to model learners' item responses. However, how to model the temporal dependencies between item responses using a collaborative filtering approach for learning outcome modeling is still under investigation. Leveraging the advantages of deep learning, this study proposes a novel deep learning-based collaborative filtering approach for learning outcome modeling. Unlike conventional collaborative filtering approaches, the proposed model, utilizing recurrent neural networks, is capable of sequentially predicting learners' future learning outcomes based on their history learning records. Moreover, the proposed model has the capacity to discover item-skill associations from the scratch without expert input based on attentive modeling. The experimental results demonstrate that the proposed model outperforms a popular deep-learning approach and can be successfully used to discover item-skill associations for both real-world and synthetic datasets.

Genomic epidemiology is important to study the COVID-19 pandemic, and more than two million severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) genomic sequences were deposited into public databases. However, the exponential increase of sequences invokes unprecedented bioinformatic challenges. Here, we present the Coronavirus GenBrowser (CGB) based on a highly efficient analysis framework and a node-picking rendering strategy. In total, 1,002,739 high-quality genomic sequences with the transmission-related metadata were analyzed and visualized. The size of the core data file is only 12.20 MB, highly efficient for clean data sharing. Quick visualization modules and rich interactive operations are provided to explore the annotated SARS-CoV-2 evolutionary tree. CGB binary nomenclature is proposed to name each internal lineage. The pre-analyzed data can be filtered out according to the user-defined criteria to explore the transmission of SARS-CoV-2. Different evolutionary analyses can also be easily performed, such as the detection of accelerated evolution and ongoing positive selection. Moreover, the 75 genomic spots conserved in SARS-CoV-2 but non-conserved in other coronaviruses were identified, which may indicate the functional elements specifically important for SARS-CoV-2. The CGB was written in Java and JavaScript. It not only enables users who have no programming skills to analyze millions of genomic sequences, but also offers a panoramic vision of the transmission and evolution of SARS-CoV-2.

On January 22, 2020, China National Center for Bioinformation (CNCB) released the 2019 Novel Coronavirus Resource (2019nCoVR), an open-access information resource for the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). 2019nCoVR features a comprehensive integration of sequence and clinical information for all publicly available SARS-CoV-2 isolates, which are manually curated with value-added annotations and quality evaluated by an automated in-house pipeline. Of particular note, 2019nCoVR offers systematic analyses to generate a dynamic landscape of SARS-CoV-2 genomic variations at a global scale. It provides all identified variants and their detailed statistics for each virus isolate, and congregates the quality score, functional annotation, and population frequency for each variant. Spatiotemporal change for each variant can be visualized and historical viral haplotype network maps for the course of the outbreak are also generated based on all complete and high-quality genomes available. Moreover, 2019nCoVR provides a full collection of SARS-CoV-2 relevant literature on the coronavirus disease 2019 (COVID-19), including published papers from PubMed as well as preprints from services such as bioRxiv and medRxiv through Europe PMC. Furthermore, by linking with relevant databases in CNCB, 2019nCoVR offers data submission services for raw sequence reads and assembled genomes, and data sharing with NCBI. Collectively, SARS-CoV-2 is updated daily to collect the latest information on genome sequences, variants, haplotypes, and literature for a timely reflection, making 2019nCoVR a valuable resource for the global research community. 2019nCoVR is accessible at https://bigd.big.ac.cn/ncov/.

On 22 January 2020, the National Genomics Data Center (NGDC), part of the China National Center for Bioinformation (CNCB), created the 2019 Novel Coronavirus Resource (2019nCoVR), an open-access SARS-CoV-2 information resource. 2019nCoVR features a comprehensive integration of sequence and clinical information for all publicly available SARS-CoV-2 isolates, which are manually curated with value-added annotations and quality evaluated by our in-house automated pipeline. Of particular note, 2019nCoVR performs systematic analyses to generate a dynamic landscape of SARS-CoV-2 genomic variations at a global scale. It provides all identified variants and detailed statistics for each virus isolate, and congregates the quality score, functional annotation, and population frequency for each variant. It also generates visualization of the spatiotemporal change for each variant and yields historical viral haplotype network maps for the course of the outbreak from all complete and high-quality genomes. Moreover, 2019nCoVR provides a full collection of SARS-CoV-2 relevant literature on COVID-19 (Coronavirus Disease 2019), including published papers from PubMed as well as preprints from services such as bioRxiv and medRxiv through Europe PMC. Furthermore, by linking with relevant databases in CNCB-NGDC, 2019nCoVR offers data submission services for raw sequence reads and assembled genomes, and data sharing with National Center for Biotechnology Information. Collectively, all SARS-CoV-2 genome sequences, variants, haplotypes and literature are updated daily to provide timely information, making 2019nCoVR a valuable resource for the global research community. 2019nCoVR is accessible at https://bigd.big.ac.cn/ncov/ .