Humans have the ability to constantly learn new knowledge. However, for artificial intelligence, trying to continuously learn new knowledge usually results in catastrophic forgetting, the existing regularization-based and dynamic structure-based approaches have shown great potential for alleviating. Nevertheless, these approaches have certain limitations. They usually do not fully consider the problem of incompatible feature embeddings. Instead, they tend to focus only on the features of new or previous classes and fail to comprehensively consider the entire model. Therefore, we propose a two-stage learning paradigm to solve feature embedding incompatibility problems. Specifically, we retain the previous model and freeze all its parameters in the first stage while dynamically expanding a new module to alleviate feature embedding incompatibility questions. In the second stage, a fusion knowledge distillation approach is used to compress the redundant feature dimensions. Moreover, we propose weight pruning and consolidation approaches to improve the efficiency of the model. Our experimental results obtained on the CIFAR-100, ImageNet-100 and ImageNet-1000 benchmark datasets show that the proposed approaches achieve the best performance among all the compared approaches. For example, on the ImageNet-100 dataset, the maximal accuracy improvement is 5.08%. Code is available at https://github.com/ybyangjing/CIL-FCE.

This research delves into the exploration of the potential of tocopherol-based nanoemulsion as a therapeutic agent for cardiovascular diseases (CVD) through an in-depth molecular docking analysis. The study focuses on elucidating the molecular interactions between tocopherol and seven key proteins (1O8a, 4YAY, 4DLI, 1HW9, 2YCW, 1BO9 and 1CX2) that play pivotal roles in CVD development. Through rigorous in silico docking investigations, assessment was conducted on the binding affinities, inhibitory potentials and interaction patterns of tocopherol with these target proteins. The findings revealed significant interactions, particularly with 4YAY, displaying a robust binding energy of -6.39 kcal/mol and a promising Ki value of 20.84 μM. Notable interactions were also observed with 1HW9, 4DLI, 2YCW and 1CX2, further indicating tocopherol\'s potential therapeutic relevance. In contrast, no interaction was observed with 1BO9. Furthermore, an examination of the common residues of 4YAY bound to tocopherol was carried out, highlighting key intermolecular hydrophobic bonds that contribute to the interaction\'s stability. Tocopherol complies with pharmacokinetics (Lipinski\'s and Veber\'s) rules for oral bioavailability and proves safety non-toxic and non-carcinogenic. Thus, deep learning-based protein language models ESM1-b and ProtT5 were leveraged for input encodings to predict interaction sites between the 4YAY protein and tocopherol. Hence, highly accurate predictions of these critical protein-ligand interactions were achieved. This study not only advances the understanding of these interactions but also highlights deep learning\'s immense potential in molecular biology and drug discovery. It underscores tocopherol\'s promise as a cardiovascular disease management candidate, shedding light on its molecular interactions and compatibility with biomolecule-like characteristics.

DNA N6-methyladenine (6mA) is one of the most common and abundant modifications, which plays essential roles in various biological processes and cellular functions. Therefore, the accurate identification of DNA 6mA sites is of great importance for a better understanding of its regulatory mechanisms and biological functions. Although significant progress has been made, there still has room for further improvement in 6mA site prediction in DNA sequences. In this study, we report a smart but accurate 6mA predictor, termed as SNN6mA, using Siamese network. To be specific, DNA segments are firstly encoded into feature vectors using the one-hot encoding scheme; then, these original feature vectors are mapped to a low-dimensional embedding space derived from Siamese network to capture more discriminative features; finally, the obtained low-dimensional features are fed to a fully connected neural network to perform final prediction. Stringent benchmarking tests on the datasets of two species demonstrated that the proposed SNN6mA is superior to the state-of-the-art 6mA predictors. Detailed data analyses show that the major advantage of SNN6mA lies in the utilization of Siamese network, which can map the original features into a low-dimensional embedding space with more discriminative capability. In summary, the proposed SNN6mA is the first attempt to use Siamese network for 6mA site prediction and could be easily extended to predict other types of modifications. The codes and datasets used in the study are freely available at https://github.com/YuXuan-Glasgow/SNN6mA for academic use.

OBJECTIVE: Deep learning (DL) models have achieved state-of-the-art medical diagnosis classification accuracy. Current models are limited by discrete diagnosis labels, but could yield more information with diagnosis in a continuous scale. We developed a novel continuous severity scaling system for macular telangiectasia (MacTel) type 2 by combining a DL classification model with uniform manifold approximation and projection (UMAP).
METHODS: We used a DL network to learn a feature representation of MacTel severity from discrete severity labels and applied UMAP to embed this feature representation into 2 dimensions, thereby creating a continuous MacTel severity scale.
METHODS: A total of 2003 OCT volumes were analyzed from 1089 MacTel Project participants.
METHODS: We trained a multiview DL classifier using multiple B-scans from OCT volumes to learn a previously published discrete 7-step MacTel severity scale. The classifiers\' last feature layer was extracted as input for UMAP, which embedded these features into a continuous 2-dimensional manifold. The DL classifier was assessed in terms of test accuracy. Rank correlation for the continuous UMAP scale against the previously published scale was calculated. Additionally, the UMAP scale was assessed in the κ agreement against 5 clinical experts on 100 pairs of patient volumes. For each pair of patient volumes, clinical experts were asked to select the volume with more severe MacTel disease and to compare them against the UMAP scale.
METHODS: Classification accuracy for the DL classifier and κ agreement versus clinical experts for UMAP.
RESULTS: The multiview DL classifier achieved top 1 accuracy of 63.3% (186/294) on held-out test OCT volumes. The UMAP metric showed a clear continuous gradation of MacTel severity with a Spearman rank correlation of 0.84 with the previously published scale. Furthermore, the continuous UMAP metric achieved κ agreements of 0.56 to 0.63 with 5 clinical experts, which was comparable with interobserver κ values.
CONCLUSIONS: Our UMAP embedding generated a continuous MacTel severity scale, without requiring continuous training labels. This technique can be applied to other diseases and may lead to more accurate diagnosis, improved understanding of disease progression, and key imaging features for pathologic characteristics.
BACKGROUND: Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

Circular RNAs (circRNAs) are a class of noncoding RNA molecules featuring a closed circular structure. They have been proved to play a significant role in the reduction of many diseases. Besides, many researches in clinical diagnosis and treatment of disease have revealed that circRNA can be considered as a potential biomarker. Therefore, understanding the association of circRNA and diseases can help to forecast some disorders of life activities. However, traditional biological experimental methods are time-consuming. The most common method for circRNA-disease association prediction on the basis of machine learning can avoid this, which relies on diverse data. Nevertheless, topological information of circRNA and disease usually is not involved in these methods. Moreover, circRNAs can be associated with diseases through miRNAs. With these considerations, we proposed a novel method, named THGNCDA, to predict the association between circRNAs and diseases. Specifically, for a certain pair of circRNA and disease, we employ a graph neural network with attention to learn the importance of its each neighbor. In addition, we use a multilayer convolutional neural network to explore the relationship of a circRNA-disease pair based on their attributes. When calculating embeddings, we introduce the information of miRNAs. The results of experiments show that THGNCDA outperformed the SOTA methods. In addition, it can be observed that our method gives a better recall rate. To confirm the significance of attention, we conducted extensive ablation studies. Case studies on Urinary Bladder and Prostatic Neoplasms further show THGNCDA\'s ability in discovering known relationships between circRNA candidates and diseases.

Multi-label Zero-shot Learning (ZSL) is more reasonable and realistic than standard single-label ZSL because several objects can co-exist in a natural image in real scenarios. Intra-class feature entanglement is a significant factor influencing the alignment of visual and semantic features, resulting in the model\'s inability to recognize unseen samples comprehensively and completely. We observe that existing multi-label ZSL methods place a greater emphasis on attention-based refinement and decoupling of visual features, while ignoring the relationship between label semantics. Relying on label correlations to solve multi-label ZSL tasks has not been deeply studied. In this paper, we make full use of the co-occurrence relationship between category labels and build a directed weighted semantic graph based on statistics and prior knowledge, in which node features represent category semantics and weighted edges represent conditional probabilities of label co-occurrence. To guide the targeted extraction of visual features, node features and edge set weights are simultaneously updated and refined, and embedded into the visual feature extraction network from a global and local perspective. The proposed method\'s effectiveness was demonstrated by simulation results on two challenging multi-label ZSL benchmarks: NUS-WIDE and Open Images. In comparison to state-of-the-art models, our model achieves an absolute gain of 2.4% mAP on NUS-WIDE and 2.1% mAP on Open Images respectively.

Doublets formed during single-cell RNA sequencing (scRNA-seq) severely affect downstream studies, such as differentially expressed gene analysis and cell trajectory inference, and limit the cellular throughput of scRNA-seq. Several doublet detection algorithms are currently available, but their generalization performance could be further improved due to the lack of effective feature-embedding strategies with suitable model architectures. Therefore, SoCube, a novel deep learning algorithm, was developed to precisely detect doublets in various types of scRNA-seq data. SoCube (i) proposed a novel 3D composite feature-embedding strategy that embedded latent gene information and (ii) constructed a multikernel, multichannel CNN-ensembled architecture in conjunction with the feature-embedding strategy. With its excellent performance on benchmark evaluation and several downstream tasks, it is expected to be a powerful algorithm to detect and remove doublets in scRNA-seq data. SoCube is freely provided as an end-to-end tool on the Python official package site PyPi (https://pypi.org/project/socube/) and open-source on GitHub (https://github.com/idrblab/socube/).

Protein solubility is a precondition for efficient heterologous protein expression at the basis of most industrial applications and for functional interpretation in basic research. However, recurrent formation of inclusion bodies is still an inevitable roadblock in protein science and industry, where only nearly a quarter of proteins can be successfully expressed in soluble form. Despite numerous solubility prediction models having been developed over time, their performance remains unsatisfactory in the context of the current strong increase in available protein sequences. Hence, it is imperative to develop novel and highly accurate predictors that enable the prioritization of highly soluble proteins to reduce the cost of actual experimental work.
In this study, we developed a novel tool, DeepSoluE, which predicts protein solubility using a long-short-term memory (LSTM) network with hybrid features composed of physicochemical patterns and distributed representation of amino acids. Comparison results showed that the proposed model achieved more accurate and balanced performance than existing tools. Furthermore, we explored specific features that have a dominant impact on the model performance as well as their interaction effects.
DeepSoluE is suitable for the prediction of protein solubility in E. coli; it serves as a bioinformatics tool for prescreening of potentially soluble targets to reduce the cost of wet-experimental studies. The publicly available webserver is freely accessible at http://lab.malab.cn/~wangchao/softs/DeepSoluE/ .

Antimicrobial peptides (AMPs) are alkaline substances with efficient bactericidal activity produced in living organisms. As the best substitute for antibiotics, they have been paid more and more attention in scientific research and clinical application. AMPs can be produced from almost all organisms and are capable of killing a wide variety of pathogenic microorganisms. In addition to being antibacterial, natural AMPs have many other therapeutically important activities, such as wound healing, antioxidant and immunomodulatory effects. To discover new AMPs, the use of wet experimental methods is expensive and difficult, and bioinformatics technology can effectively solve this problem. Recently, some deep learning methods have been applied to the prediction of AMPs and achieved good results. To further improve the prediction accuracy of AMPs, this paper designs a new deep learning method based on sequence multidimensional representation. By encoding and embedding sequence features, and then inputting the model to identify AMPs, high-precision classification of AMPs and Non-AMPs with lengths of 10-200 is achieved. The results show that our method improved accuracy by 1.05% compared to the most advanced model in independent data validation without decreasing other indicators.

BACKGROUND: Cancers are genetically heterogeneous, so anticancer drugs show varying degrees of effectiveness on patients due to their differing genetic profiles. Knowing patient\'s responses to numerous cancer drugs are needed for personalized treatment for cancer. By using molecular profiles of cancer cell lines available from Cancer Cell Line Encyclopedia (CCLE) and anticancer drug responses available in the Genomics of Drug Sensitivity in Cancer (GDSC), we will build computational models to predict anticancer drug responses from molecular features.
RESULTS: We propose a novel deep neural network model that integrates multi-omics data available as gene expressions, copy number variations, gene mutations, reverse phase protein array expressions, and metabolomics expressions, in order to predict cellular responses to known anti-cancer drugs. We employ a novel graph embedding layer that incorporates interactome data as prior information for prediction. Moreover, we propose a novel attention layer that effectively combines different omics features, taking their interactions into account. The network outperformed feedforward neural networks and reported 0.90 for [Formula: see text] values for prediction of drug responses from cancer cell lines data available in CCLE and GDSC.
CONCLUSIONS: The outstanding results of our experiments demonstrate that the proposed method is capable of capturing the interactions of genes and proteins, and integrating multi-omics features effectively. Furthermore, both the results of ablation studies and the investigations of the attention layer imply that gene mutation has a greater influence on the prediction of drug responses than other omics data types. Therefore, we conclude that our approach can not only predict the anti-cancer drug response precisely but also provides insights into reaction mechanisms of cancer cell lines and drugs as well.