Search

Abstract In protein identification, researchers increasingly aim to achieve efficient classification using fewer features. While many feature selection methods effectively reduce the number of model features, they often cause information loss caused by merely selecting or discarding features, which limits classifier performance. To address this issue, we present Rore, an algorithm based on a feature-dimensionality reduction strategy. By mapping the original features to a latent space, Rore retains all relevant feature information while using fewer representations of the latent features. This approach significantly preserves the original information and overcomes the information loss problem associated with previous feature selection. Through extensive experimental validation and analysis, Rore demonstrated excellent performance on an antioxidant protein dataset, achieving an accuracy of 95.88% and MCC of 91.78%, using vectors including only 15 features. The Rore algorithm is available online at http://112.124.26.17:8021/Rore .

Abstract Background Due to the ability of circRNA to bind with corresponding RBPs and play a critical role in gene regulation and disease prevention, numerous identification algorithms have been developed. Nevertheless, most of the current mainstream methods primarily capture one-dimensional sequence features through various descriptors, while neglecting the effective extraction of secondary structure features. Moreover, as the number of introduced descriptors increases, the issues of sparsity and ineffective representation also rise, causing a significant burden on computational models and leaving room for improvement in predictive performance. Results Based on this, we focused on capturing the features of secondary structure in sequences and developed a new architecture called CRBPSA, which is based on a sequence-structure attention mechanism. Firstly, a base-pairing matrix is generated by calculating the matching probability between each base, with a Gaussian function introduced as a weight to construct the secondary structure. Then, a Structure_Transformer is employed to extract base-pairing information and spatial positional dependencies, enabling the identification of binding sites through deeper feature extraction. Experimental results using the same set of hyperparameters on 37 circRNA datasets, totaling 671,952 samples, show that the CRBPSA algorithm achieves an average AUC of 99.93%, surpassing all existing prediction methods. Conclusions CRBPSA is a lightweight and efficient prediction tool for circRNA-RBP, which can capture structural features of sequences with minimal computational resources and accurately predict protein-binding sites. This tool facilitates a deeper understanding of the biological processes and mechanisms underlying circRNA and protein interactions.

Abstract Background The type IV secretion system is widely present in various bacteria, such as Salmonella, Escherichia coli, and Helicobacter pylori. These bacteria use the type IV secretion system to secrete type IV secretion effectors, infect host cells, and disrupt or modulate the communication pathways. In this study, type III and type VI secretion effectors were used as negative samples to train a robust model. Results The area under the curve of T4Seeker on the validation and independent test sets were 0.947 and 0.970, respectively, demonstrating the strong predictive capacity and robustness of T4Seeker. After comparing with the classic and state-of-the-art T4SE identification models, we found that T4Seeker, which is based on traditional features and large language model features, had a higher predictive ability. Conclusion The T4Seeker proposed in this study demonstrates superior performance in the field of T4SEs prediction. By integrating features at multiple levels, it achieves higher predictive accuracy and strong generalization capability, providing an effective tool for future T4SE research.

Abstract Biomedical network learning offers fresh prospects for expediting drug repositioning. However, traditional network architectures struggle to quantify the relationship between micro-scale drug spatial structures and corresponding macro-scale biomedical networks, limiting their ability to capture key pharmacological properties and complex biomedical information crucial for drug screening and therapeutic discovery. Moreover, challenges such as difficulty in capturing long-range dependencies hinder current network-based approaches. To address these limitations, we introduce the Spatial Hierarchical Network, modeling molecular 3D structures and biological associations into a unified network. We propose an end-to-end framework, SpHN-VDA, integrating spatial hierarchical information through triple attention mechanisms to enhance machine understanding of molecular functionality and improve the accuracy of virus-drug association identification. SpHN-VDA outperforms leading models across three datasets, particularly excelling in out-of-distribution and cold-start scenarios. It also exhibits enhanced robustness against data perturbation, ranging from 20% to 40%. It accurately identifies critical motifs for binding sites, even without protein residue annotations. Leveraging reliability of SpHN-VDA, we have identified 25 potential candidate drugs through gene expression analysis and CMap. Molecular docking experiments with the SARS-CoV-2 spike protein further corroborate the predictions. This research highlights the broad potential of SpHN-VDA to enhance drug repositioning and identify effective treatments for various diseases.

Abstract Background Drug-drug interactions (DDIs) can result in unexpected pharmacological outcomes, including adverse drug events, which are crucial for drug discovery. Graph neural networks have substantially advanced our ability to model molecular representations; however, the precise identification of key local structures and the capture of long-distance structural correlations for better DDI prediction and interpretation remain significant challenges. Results Here, we present DrugDAGT, a dual-attention graph transformer framework with contrastive learning for predicting multiple DDI types. The dual-attention graph transformer incorporates attention mechanisms at both the bond and atomic levels, thereby enabling the integration of short and long-range dependencies within drug molecules to pinpoint key local structures essential for DDI discovery. Moreover, DrugDAGT further implements graph contrastive learning to maximize the similarity of representations across different views for better discrimination of molecular structures. Experiments in both warm-start and cold-start scenarios demonstrate that DrugDAGT outperforms state-of-the-art baseline models, achieving superior overall performance. Furthermore, visualization of the learned representations of drug pairs and the attention map provides interpretable insights instead of black-box results. Conclusions DrugDAGT provides an effective tool for accurately predicting multiple DDI types by identifying key local chemical structures, offering valuable insights for prescribing medications, and guiding drug development. All data and code of our DrugDAGT can be found at https://github.com/codejiajia/DrugDAGT .

Abstract Drug repurposing is a promising approach in the field of drug discovery owing to its efficiency and cost-effectiveness. Most current drug repurposing models rely on specific datasets for training, which limits their predictive accuracy and scope. The number of both market-approved and experimental drugs is vast, forming an extensive molecular space. Due to limitations in parameter size and data volume, traditional drug-target interaction (DTI) prediction models struggle to generalize well within such a broad space. In contrast, large language models (LLMs), with their vast parameter sizes and extensive training data, demonstrate certain advantages in drug repurposing tasks. In our research, we introduce a novel drug repurposing framework, DrugReAlign, based on LLMs and multi-source prompt techniques, designed to fully exploit the potential of existing drugs efficiently. Leveraging LLMs, the DrugReAlign framework acquires general knowledge about targets and drugs from extensive human knowledge bases, overcoming the data availability limitations of traditional approaches. Furthermore, we collected target summaries and target-drug space interaction data from databases as multi-source prompts, substantially improving LLM performance in drug repurposing. We validated the efficiency and reliability of the proposed framework through molecular docking and DTI datasets. Significantly, our findings suggest a direct correlation between the accuracy of LLMs' target analysis and the quality of prediction outcomes. These findings signify that the proposed framework holds the promise of inaugurating a new paradigm in drug repurposing.

Abstract DNA methylation plays a critical role in gene regulation by modulating the DNA binding of transcription factors (TFs). This study integrates TFs’ ChIP-seq profiles with WGBS profiles to investigate how DNA methylation affects protein interactions. Statistical methods and a 5-letter DNA motif calling model have been developed to characterize DNA sequences bound by proteins, while considering the effects of DNA modifications. By employing these methods, 79 significant universal “stripe” TFs and cofactors (USFs), 2360 co-binding protein pairs, and distinct protein modules associated with various DNA methylation states have been identified. The USFs hint a regulatory hierarchy within these protein interactions. Proteins preferentially bind to non-CpG sites in methylated regions, indicating binding affinity is not solely CpG-dependent. Proteins involved in methylation-specific USFs and cobinding pairs play essential roles in promoting and sustaining DNA methylation through interacting with DNMTs or inhibiting TET binding. These findings underscore the interplay between protein binding and methylation, offering insights into epigenetic regulation in cellular biology.

Abstract Background Ductal carcinoma in situ (DCIS) of the breast is an early stage of breast cancer, and preventing its progression to invasive ductal carcinoma (IDC) is crucial for the early detection and treatment of breast cancer. Although single-cell transcriptome analysis technology has been widely used in breast cancer research, the biological mechanisms underlying the transition from DCIS to IDC remain poorly understood. Results We identified eight cell types through cell annotation, finding significant differences in T cell proportions between DCIS and IDC. Using this as a basis, we performed pseudotime analysis on T cell subpopulations, revealing that differentially expressed genes primarily regulate immune cell migration and modulation. By intersecting WGCNA results of T cells highly correlated with the subtypes and the differentially expressed genes, we identified six key genes: FGFBP2, GNLY, KLRD1, TYROBP, PRF1, and NKG7. Excluding PRF1, the other five genes were significantly associated with overall survival in breast cancer, highlighting their potential as prognostic biomarkers. Conclusions We identified immune cells that may play a role in the progression from DCIS to IDC and uncovered five key genes that can serve as prognostic markers for breast cancer. These findings provide insights into the mechanisms underlying the transition from DCIS to IDC, offering valuable perspectives for future research. Additionally, our results contribute to a better understanding of the biological processes involved in breast cancer progression.

Abstract The realisation of fast position tracking control and strong robust control of the chain‐type rotary shell magazine in the complex systems such as the large calibre howitzer has been the focus and challenge of research. The predictive control strategies can achieve a fast dynamic response, but it relies on the system model. By integrating the generalised predictive control method with sliding mode theory, a novel robust generalised predictive position control method is proposed. Firstly, a non‐cascade position tracking controller is designed based on the continuous‐time model of the systems; then, a sliding mode compensation structure is introduced to address the degradation of control performance due to load variations and external disturbances. The scheme utilises the sliding mode switching term to overcome the effects caused by the disturbances while preserving the fast dynamic response characteristics of the original predictive control. Moreover, the disturbance observer is designed to further enhance the robustness by producing corresponding compensation according to the perturbation quantity. The proposed controller has been validated in a shell magazine test bench, indicating its superior position control performance of the shell magazine under different load conditions.

Abstract Background Drug-target interaction (DTI) prediction plays a pivotal role in drug discovery and drug repositioning, enabling the identification of potential drug candidates. However, most previous approaches often do not fully utilize the complementary relationships among multiple biological networks, which limits their ability to learn more consistent representations. Additionally, the selection strategy of negative samples significantly affects the performance of contrastive learning methods. Results In this study, we propose CCL-ASPS, a novel deep learning model that incorporates Collaborative Contrastive Learning (CCL) and Adaptive Self-Paced Sampling strategy (ASPS) for drug-target interaction prediction. CCL-ASPS leverages multiple networks to learn the fused embeddings of drugs and targets, ensuring their consistent representations from individual networks. Furthermore, ASPS dynamically selects more informative negative sample pairs for contrastive learning. Experiment results on the established dataset demonstrate that CCL-ASPS achieves significant improvements compared to current state-of-the-art methods. Moreover, ablation experiments confirm the contributions of the proposed CCL and ASPS strategies. Conclusions By integrating Collaborative Contrastive Learning and Adaptive Self-Paced Sampling, the proposed CCL-ASPS effectively addresses the limitations of previous methods. This study demonstrates that CCL-ASPS achieves notable improvements in DTI predictive performance compared to current state-of-the-art approaches. The case study and cold start experiments further illustrate the capability of CCL-ASPS to effectively predict previously unknown DTI, potentially facilitating the identification of new drug-target interactions.

Based on the system dynamic model, a full system dynamics estimation method is proposed for a chain shell magazine driven by a permanent magnet synchronous motor (PMSM). An adaptive extended state observer (AESO) is proposed to estimate the unmeasured states and disturbance, in which the model parameters are adjusted in real time. Theoretical analysis shows that the estimation errors of the disturbances and unmeasured states converge exponentially to zero, and the parameter estimation error can be obtained from the extended state. Then, based on the extended state of the AESO, a novel parameter estimation law is designed. Due to the convergence of AESO, the novel parameter estimation law is insensitive to controllers and excitation signal. Under persistent excitation (PE) condition, the estimated parameters will converge to a compact set around the actual parameter value. Without PE signal, the estimated parameters will converge to zero for the extended state. Simulation and experimental results show that the proposed method can accurately estimate the unmeasured states and disturbance of the chain shell magazine, and the estimated parameters will converge to the actual value without strictly continuous PE signals.

The high-temperature gas-cooled reactor (HTGR) with spherical fuel elements contains complex pebble flow. The flow behavior of pebbles is influenced by various factors, such as pebble density, friction coefficient, wall structure, and discharge port size. Using a GPU-DEM numerical model, the effects of the friction coefficient on the cyclic loading and unloading of pebbles in the full-scale HTR-PM are studied. Numerical simulations with up to 420,000 spherical pebbles are conducted. Four sets of friction coefficient values are determined for comparative analysis based on experimental measurements. Discharging speed, residence time, stress, porosity, and velocity distribution are quantitatively analyzed. In addition, a comparison with the CT-PFD experiment is carried out to validate the numerical model. The results show that near-wall retention phenomena are observed in the reactor core only when using large friction coefficients. However, using friction coefficient values closer to the measured experimental values, the pebble bed in HTR-PM exhibited good flow characteristics. Furthermore, the friction coefficient also influences the porosity and velocity distribution of the pebble bed, with lower friction coefficients resulting in lower overall stress in the bed. The discharge outlet's influence varies with different friction coefficient values. In summary, this study demonstrates that the value of the friction coefficient has a complex influence on the pebble flow in HTR-PM, which provides important insights for future numerical and experimental studies in this field.

Abstract Background Antioxidant proteins are involved in several biological processes and can protect DNA and cells from the damage of free radicals. These proteins regulate the body's oxidative stress and perform a significant role in many antioxidant-based drugs. The current invitro-based medications are costly, time-consuming, and unable to efficiently screen and identify the targeted motif of antioxidant proteins. Methods In this model, we proposed an accurate prediction method to discriminate antioxidant proteins namely StackedEnC-AOP. The training sequences are formulation encoded via incorporating a discrete wavelet transform (DWT) into the evolutionary matrix to decompose the PSSM-based images via two levels of DWT to form a Pseudo position-specific scoring matrix (PsePSSM-DWT) based embedded vector. Additionally, the Evolutionary difference formula and composite physiochemical properties methods are also employed to collect the structural and sequential descriptors. Then the combined vector of sequential features, evolutionary descriptors, and physiochemical properties is produced to cover the flaws of individual encoding schemes. To reduce the computational cost of the combined features vector, the optimal features are chosen using Minimum redundancy and maximum relevance (mRMR). The optimal feature vector is trained using a stacking-based ensemble meta-model. Results Our developed StackedEnC-AOP method reported a prediction accuracy of 98.40% and an AUC of 0.99 via training sequences. To evaluate model validation, the StackedEnC-AOP training model using an independent set achieved an accuracy of 96.92% and an AUC of 0.98. Conclusion Our proposed StackedEnC-AOP strategy performed significantly better than current computational models with a ~ 5% and ~ 3% improved accuracy via training and independent sets, respectively. The efficacy and consistency of our proposed StackedEnC-AOP make it a valuable tool for data scientists and can execute a key role in research academia and drug design.

Abstract Background Metabolite-associated cell communications play critical roles in maintaining human biological function. However, most existing tools and resources focus only on ligand-receptor interaction pairs where both partners are proteinaceous, neglecting other non-protein molecules. To address this gap, we introduce the MRCLinkdb database and algorithm, which aggregates and organizes data related to non-protein L-R interactions in cell-cell communication, providing a valuable resource for predicting intercellular communication based on metabolite-related ligand-receptor interactions. Results Here, we manually curated the metabolite-ligand-receptor (ML-R) interactions from the literature and known databases, ultimately collecting over 790 human and 670 mouse ML-R interactions. Additionally, we compiled information on over 1900 enzymes and 260 transporter entries associated with these metabolites. We developed Metabolite-Receptor based Cell Link Database (MRCLinkdb) to store these ML-R interactions data. Meanwhile, the platform also offers extensive information for presenting ML-R interactions, including fundamental metabolite information and the overall expression landscape of metabolite-associated gene sets (such as receptor, enzymes, and transporter proteins) based on single-cell transcriptomics sequencing (covering 35 human and 26 mouse tissues, 52 human and 44 mouse cell types) and bulk RNA-seq/microarray data (encompassing 62 human and 39 mouse tissues). Furthermore, MRCLinkdb introduces a web server dedicated to the analysis of intercellular communication based on ML-R interactions. MRCLinkdb is freely available at https://www.cellknowledge.com.cn/mrclinkdb/ . Conclusions In addition to supplementing ligand-receptor databases, MRCLinkdb may provide new perspectives for decoding the intercellular communication and advancing related prediction tools based on ML-R interactions.

Objectives: This study aimed to investigate the factors associated with the spontaneous clearance of Chlamydia trachomatis, a phenomenon that, despite a growing body of literature, remains understudied in the context of women in China. Methods: Spontaneous clearance was defined as the transition from a positive to negative Chlamydia status over time without the use of antichlamydial therapy. Data from 5935 women aged 18 years and older who participated in the Clinical-Based Health Check program were analyzed. Eligible participants had no history of Neisseria gonorrhoeae infection, pelvic inflammatory disease, recent antibiotic use, or pregnancy and had an interval between the screening and follow-up visits of more than 3 days. Logistic regression was used to identify factors influencing spontaneous clearance. Results: Spontaneous clearance occurred in 23.9% (50/209) of the participants, typically with a median interval of 27 days. Significant factors included an interval >45 days, an age >35 years, the use of an intrauterine device (IUD), and the presence of clue cells. Conclusion: Spontaneous clearance of C. trachomatis is significantly affected by age, the interval between two tests, IUD use, and the presence of clue cells. Screening strategies should prioritize women under 35 years of age who do not use IUDs and test negative for clue cells for more effective chlamydia prevention and management.

Protein phosphorylation is essential in various signal transduction and cellular processes. To date, most tools are designed for model organisms, but only a handful of methods are suitable for predicting task in fungal species, and their performance still leaves much to be desired. In this study, a novel tool called MFPSP is developed for phosphorylation site prediction in multi-fungal species. The amino acids sequence features were derived from physicochemical and distributed information, and an offspring competition-based genetic algorithm was applied for choosing the most effective feature subset. The comparison results shown that MFPSP achieves a more advanced and balanced performance to several state-of-the-art available toolkits. Feature contribution and interaction exploration indicating the proposed model is efficient in uncovering concealed patterns within sequence. We anticipate MFPSP to serve as a valuable bioinformatics tool and benefiting practical experiments by pre-screening potential phosphorylation sites and enhancing our functional understanding of phosphorylation modifications in fungi. The source code and datasets are accessible at https://github.com/AI4HKB/MFPSP/.

Abstract Background A promoter is a specific sequence in DNA that has transcriptional regulatory functions, playing a role in initiating gene expression. Identifying promoters and their strengths can provide valuable information related to human diseases. In recent years, computational methods have gained prominence as an effective means for identifying promoter, offering a more efficient alternative to labor-intensive biological approaches. Results In this study, a two-stage integrated predictor called “msBERT-Promoter” is proposed for identifying promoters and predicting their strengths. The model incorporates multi-scale sequence information through a tokenization strategy and fine-tunes the DNABERT model. Soft voting is then used to fuse the multi-scale information, effectively addressing the issue of insufficient DNA sequence information extraction in traditional models. To the best of our knowledge, this is the first time an integrated approach has been used in the DNABERT model for promoter identification and strength prediction. Our model achieves accuracy rates of 96.2% for promoter identification and 79.8% for promoter strength prediction, significantly outperforming existing methods. Furthermore, through attention mechanism analysis, we demonstrate that our model can effectively combine local and global sequence information, enhancing its interpretability. Conclusions msBERT-Promoter provides an effective tool that successfully captures sequence-related attributes of DNA promoters and can accurately identify promoters and predict their strengths. This work paves a new path for the application of artificial intelligence in traditional biology.

IntroductionThe hair follicle (HF) is a micro-organ capable of regeneration. A HF cycle consists of an anagen, catagen and telogen. Abnormalities in the HF cycle can lead to many hair disorders such as hair loss. The pig is a good biomedical model, but there are few data on their HF cycle. The aim of this study was to classify the pig HF cycle and determine the feasibility of the pig as an animal model for human HF cycle.MethodsSkin samples from 10 different postnatal (P) days Yorkshire pigs was collected to determine the key time points of the first HF cycle in pig by H&E staining, immunofluorescence staining, q-PCR and western-blot.ResultsBy morphological observation and detection of markers at different stages, pig HF cycle was classified into three main periods - the first anagen until P45, catagen (P45–P85), telogen (P85–P100), and next anagen (>P100). In addition, we examined the expression of important genes AE15, CD34, Versican, Ki67 et al. related to the HF cycle at different stages of pig HF, indicating that pig and human share similarities in morphology and marker gene expression patterns of HF cycle.DiscussionOur findings will facilitate the study of HF cycle and offer researchers a suitable model for human hair research.

Spatial transcriptome technology can parse transcriptomic data at the spatial level to detect high-throughput gene expression and preserve information regarding the spatial structure of tissues. Identifying spatial domains, that is identifying regions with similarities in gene expression and histology, is the most basic and critical aspect of spatial transcriptome data analysis. Most current methods identify spatial domains only through a single view, which may obscure certain important information and thus fail to make full use of the information embedded in spatial transcriptome data. Therefore, we propose an unsupervised clustering framework based on multiview graph convolutional networks (MVST) to achieve accurate spatial domain recognition by the learning graph embedding features of neighborhood graphs constructed from gene expression information, spatial location information, and histopathological image information through multiview graph convolutional networks. By exploring spatial transcriptomes from multiple views, MVST enables data from all parts of the spatial transcriptome to be comprehensively and fully utilized to obtain more accurate spatial expression patterns. We verified the effectiveness of MVST on real spatial transcriptome datasets, the robustness of MVST on some simulated datasets, and the reasonableness of the framework structure of MVST in ablation experiments, and from the experimental results, it is clear that MVST can achieve a more accurate spatial domain identification compared with the current more advanced methods. In conclusion, MVST is a powerful tool for spatial transcriptome research with improved spatial domain recognition.

Single-cell RNA sequencing (scRNA-seq) has emerged as a powerful tool in genomics research, enabling the analysis of gene expression at the individual cell level. However, scRNA-seq data often suffer from a high rate of dropouts, where certain genes fail to be detected in specific cells due to technical limitations. This missing data can introduce biases and hinder downstream analysis. To overcome this challenge, the development of effective imputation methods has become crucial in the field of scRNA-seq data analysis. Here, we propose an imputation method based on robust and non-negative matrix factorization (scRNMF). Instead of other matrix factorization algorithms, scRNMF integrates two loss functions: L2 loss and C-loss. The L2 loss function is highly sensitive to outliers, which can introduce substantial errors. We utilize the C-loss function when dealing with zero values in the raw data. The primary advantage of the C-loss function is that it imposes a smaller punishment for larger errors, which results in more robust factorization when handling outliers. Various datasets of different sizes and zero rates are used to evaluate the performance of scRNMF against other state-of-the-art methods. Our method demonstrates its power and stability as a tool for imputation of scRNA-seq data.

Abstract Organelles do not act as autonomous discrete units but rather as interconnected hubs that engage in extensive communication by forming close contacts called “membrane contact sites (MCSs)”. And many proteins have been identified as residing in MCS and playing important roles in maintaining and fulfilling specific functions within these microdomains. However, a comprehensive compilation of these MCS proteins is still lacking. Therefore, we developed MCSdb, a manually curated resource of MCS proteins and complexes from publications. MCSdb documents 7010 MCS protein entries and 263 complexes, involving 24 organelles and 44 MCSs across 11 species. Additionally, MCSdb orchestrates all data into different categories with multitudinous information for presenting MCS proteins. In summary, MCSdb provides a valuable resource for accelerating MCS functional interpretation and interorganelle communication deciphering.

Abstract Background Viral infections have been the main health issue in the last decade. Antiviral peptides (AVPs) are a subclass of antimicrobial peptides (AMPs) with substantial potential to protect the human body against various viral diseases. However, there has been significant production of antiviral vaccines and medications. Recently, the development of AVPs as an antiviral agent suggests an effective way to treat virus-affected cells. Recently, the involvement of intelligent machine learning techniques for developing peptide-based therapeutic agents is becoming an increasing interest due to its significant outcomes. The existing wet-laboratory-based drugs are expensive, time-consuming, and cannot effectively perform in screening and predicting the targeted motif of antiviral peptides. Methods In this paper, we proposed a novel computational model called Deepstacked-AVPs to discriminate AVPs accurately. The training sequences are numerically encoded using a novel Tri-segmentation-based position-specific scoring matrix (PSSM-TS) and word2vec-based semantic features. Composition/Transition/Distribution-Transition (CTDT) is also employed to represent the physiochemical properties based on structural features. Apart from these, the fused vector is formed using PSSM-TS features, semantic information, and CTDT descriptors to compensate for the limitations of single encoding methods. Information gain (IG) is applied to choose the optimal feature set. The selected features are trained using a stacked-ensemble classifier. Results The proposed Deepstacked-AVPs model achieved a predictive accuracy of 96.60%%, an area under the curve (AUC) of 0.98, and a precision-recall (PR) value of 0.97 using training samples. In the case of the independent samples, our model obtained an accuracy of 95.15%, an AUC of 0.97, and a PR value of 0.97. Conclusion Our Deepstacked-AVPs model outperformed existing models with a ~ 4% and ~ 2% higher accuracy using training and independent samples, respectively. The reliability and efficacy of the proposed Deepstacked-AVPs model make it a valuable tool for scientists and may perform a beneficial role in pharmaceutical design and research academia.

Abstract Background Circular RNAs (circRNAs) can regulate microRNA activity and are related to various diseases, such as cancer. Functional research on circRNAs is the focus of scientific research. Accurate identification of circRNAs is important for gaining insight into their functions. Although several circRNA prediction models have been developed, their prediction accuracy is still unsatisfactory. Therefore, providing a more accurate computational framework to predict circRNAs and analyse their looping characteristics is crucial for systematic annotation. Results We developed a novel framework, CircDC, for classifying circRNAs from other lncRNAs. CircDC uses four different feature encoding schemes and adopts a multilayer convolutional neural network and bidirectional long short-term memory network to learn high-order feature representation and make circRNA predictions. The results demonstrate that the proposed CircDC model is more accurate than existing models. In addition, an interpretable analysis of the features affecting the model is performed, and the computational framework is applied to the extended application of circRNA identification. Conclusions CircDC is suitable for the prediction of circRNA. The identification of circRNA helps to understand and delve into the related biological processes and functions. Feature importance analysis increases model interpretability and uncovers significant biological properties. The relevant code and data in this article can be accessed for free at https://github.com/nmt315320/CircDC.git .

Single-pixel imaging is an advanced computational imaging technique based on compressive sensing that offers higher signal-to-noise ratio and broader application scope compared to traditional imaging techniques. However, conventional reconstruction algorithms suffer from issues such as long processing time and low reconstruction accuracy during the sampling and reconstruction processes. Deep learning-based compressed reconstruction networks can circumvent the complex iterative computations of traditional algorithms and achieve fast, high-quality reconstruction. In this paper, we propose a Variational Multi-Scale Error Compensation Network (VMSE) based on variational autoencoders. VMSE designs an error compensation network to enhance the feature representation capability of the sampling reconstruction network. We employ multiple latent variables to generate error features at different scales in the intermediate layers of the error compensation network, compensating the reconstructed image. Additionally, we design a module that simultaneously learns in the spatial and frequency domains, which is used for upsampling and complementing the missing high-frequency information in the frequency domain. On the MNIST dataset, when the sampling rate is 0.025, VMSE achieved higher Peak Signal-to-Noise Ratio(PSNR) and Structural Similarity Index(SSIM) scores, especially with an SSIM score of 0.963, significantly surpassing Reconnet and DR2Net's scores of 0.930 and 0.920, respectively. This was further corroborated by practical experiments, where at low sampling rates, VMSE could reconstruct outlines more clearly compared to TVAL3.

Single-pixel imaging (SPI), an imaging technique based on the theory of compressed sensing, is limited in real-time imaging and high-resolution images due to its relatively slow imaging speed. In recent years, deep unfolding network compressed sensing reconstruction algorithms based on deep learning have proven to be an effective solution for faster and higher quality image reconstruction. However, existing deep unfolding networks mainly rely on a single piece of a priori information and may ignore other intrinsic structures of the image. Therefore, in this paper, we propose a deep unfolding network (MPDU-Net) that incorporates multiple prior information. To effectively fuse multiple prior information, we propose three different fusion strategies in the deep reconstruction sub-network. An unbiased convolutional layer is used to simulate the sampling reconstruction process to achieve joint reconstruction for effective removal of block artifacts. The sampling matrix is input into the deep reconstruction sub-network as a learnable parameter to achieve joint optimization of sampling reconstruction. Simulation and practical experimental results show that the proposed network outperforms existing compressed sensing reconstruction algorithms based on deep unfolding networks.

Abstract Background Circular RNAs (circRNAs) have been confirmed to play a vital role in the occurrence and development of diseases. Exploring the relationship between circRNAs and diseases is of far-reaching significance for studying etiopathogenesis and treating diseases. To this end, based on the graph Markov neural network algorithm (GMNN) constructed in our previous work GMNN2CD, we further considered the multisource biological data that affects the association between circRNA and disease and developed an updated web server CircDA and based on the human hepatocellular carcinoma (HCC) tissue data to verify the prediction results of CircDA. Results CircDA is built on a Tumarkov-based deep learning framework. The algorithm regards biomolecules as nodes and the interactions between molecules as edges, reasonably abstracts multiomics data, and models them as a heterogeneous biomolecular association network, which can reflect the complex relationship between different biomolecules. Case studies using literature data from HCC, cervical, and gastric cancers demonstrate that the CircDA predictor can identify missing associations between known circRNAs and diseases, and using the quantitative real-time PCR (RT-qPCR) experiment of HCC in human tissue samples, it was found that five circRNAs were significantly differentially expressed, which proved that CircDA can predict diseases related to new circRNAs. Conclusions This efficient computational prediction and case analysis with sufficient feedback allows us to identify circRNA-associated diseases and disease-associated circRNAs. Our work provides a method to predict circRNA-associated diseases and can provide guidance for the association of diseases with certain circRNAs. For ease of use, an online prediction server ( http://server.malab.cn/CircDA ) is provided, and the code is open-sourced ( https://github.com/nmt315320/CircDA.git ) for the convenience of algorithm improvement.

Auxin is the first plant hormone found to play a dominant role in fruit growth, from fruit set to fruit ripening. Strawberry plants represent a suitable model for studying auxin’s biosynthesis, sensing, and signaling machinery. Aux/IAA genes are a classical rapid auxin-responsive family. However, the Aux/IAA gene family in Fragaria genus is poorly understood. In this study, a total of 287 Aux/IAA genes were identified in the eight strawberry genomes. Their physicochemical properties, domain structure, and cis-regulatory elements revealed the functional multiplicity of the strawberry Aux/IAAs. We used a phylogenetic analysis to classify these genes into 12 classes. In addition, based on synteny analysis, gene duplications, and calculation of the Ka/Ks ratio, we found that segmental duplications promote the evolution of Aux/IAAs in Fragaria species, which is followed by purifying selection. Furthermore, the expression pattern and protein–protein interaction network of these genes in Fragaria vesca revealed various tissue-specific expressions and probable regulatory functions. Taken together, these results provide basic genomic information and a functional analysis of these genes, which will serve to expand our understanding of the direction in which the Aux/IAA gene family is evolving in Fragaria species.

Long non-coding RNAs (lncRNAs) are important factors involved in biological regulatory networks. Accurately predicting lncRNA-protein interactions (LPIs) is vital for clarifying lncRNA’s functions and pathogenic mechanisms. Existing deep learning models have yet to yield satisfactory results in LPI prediction. Recently, graph autoencoders (GAEs) have seen rapid development, excelling in tasks like link prediction and node classification. We employed GAE technology for LPI prediction, devising the FMSRT-LPI model based on path masking and degree regression strategies and thereby achieving satisfactory outcomes. This represents the first known integration of path masking and degree regression strategies into the GAE framework for potential LPI inference. The effectiveness of our FMSRT-LPI model primarily relies on four key aspects. First, within the GAE framework, our model integrates multi-source relationships of lncRNAs and proteins with LPN’s topological data. Second, the implemented masking strategy efficiently identifies LPN’s key paths, reconstructs the network, and reduces the impact of redundant or incorrect data. Third, the integrated degree decoder balances degree and structural information, enhancing node representation. Fourth, the PolyLoss function we introduced is more appropriate for LPI prediction tasks. The results on multiple public datasets further demonstrate our model’s potential in LPI prediction.

Abstract The dermis and epidermis, crucial structural layers of the skin, encompass appendages, hair follicles (HFs), and intricate cellular heterogeneity. However, an integrated spatiotemporal transcriptomic atlas of embryonic skin has not yet been described and would be invaluable for studying skin‐related diseases in humans. Here, single‐cell and spatial transcriptomic analyses are performed on skin samples of normal and hairless fetal pigs across four developmental periods. The cross‐species comparison of skin cells illustrated that the pig epidermis is more representative of the human epidermis than mice epidermis. Moreover, Phenome‐wide association study analysis revealed that the conserved genes between pigs and humans are strongly associated with human skin‐related diseases. In the epidermis, two lineage differentiation trajectories describe hair follicle (HF) morphogenesis and epidermal development. By comparing normal and hairless fetal pigs, it is found that the hair placode (Pc), the most characteristic initial structure in HFs, arises from progenitor‐like OGN+/UCHL1+ cells. These progenitors appear earlier in development than the previously described early Pc cells and exhibit abnormal proliferation and migration during differentiation in hairless pigs. The study provides a valuable resource for in‐depth insights into HF development, which may serve as a key reference atlas for studying human skin disease etiology using porcine models.

Accurate multiple sequence alignment (MSA) is imperative for the comprehensive analysis of biological sequences. However, a notable challenge arises as no single MSA tool consistently outperforms its counterparts across diverse datasets. Users often have to try multiple MSA tools to achieve optimal alignment results, which can be time-consuming and memory-intensive. While the overall accuracy of certain MSA results may be lower, there could be local regions with the highest alignment scores, prompting researchers to seek a tool capable of merging these locally optimal results from multiple initial alignments into a globally optimal alignment. In this study, we introduce Two Pointers Meta-Alignment (TPMA), a novel tool designed for the integration of nucleic acid sequence alignments. TPMA employs two pointers to partition the initial alignments into blocks containing identical sequence fragments. It selects blocks with the high sum of pairs (SP) scores to concatenate them into an alignment with an overall SP score superior to that of the initial alignments. Through tests on simulated and real datasets, the experimental results consistently demonstrate that TPMA outperforms M-Coffee in terms of aSP, Q, and total column (TC) scores across most datasets. Even in cases where TPMA's scores are comparable to M-Coffee, TPMA exhibits significantly lower running time and memory consumption. Furthermore, we comprehensively assessed all the MSA tools used in the experiments, considering accuracy, time, and memory consumption. We propose accurate and fast combination strategies for small and large datasets, which streamline the user tool selection process and facilitate large-scale dataset integration. The dataset and source code of TPMA are available on GitHub (https://github.com/malabz/TPMA).

Abstract Background Enhancers play a crucial role in gene regulation, and some active enhancers produce noncoding RNAs known as enhancer RNAs (eRNAs) bi-directionally. The most commonly used method for detecting eRNAs is CAGE-seq, but the instability of eRNAs in vivo leads to data noise in sequencing results. Unfortunately, there is currently a lack of research focused on the noise inherent in CAGE-seq data, and few approaches have been developed for predicting eRNAs. Bridging this gap and developing widely applicable eRNA prediction models is of utmost importance. Results In this study, we proposed a method to reduce false positives in the identification of eRNAs by adjusting the statistical distribution of expression levels. We also developed eRNA prediction models using joint gene expressions, DNA methylation, and histone modification. These models achieved impressive performance with an AUC value of approximately 0.95 for intra-cell prediction and 0.9 for cross-cell prediction. Conclusions Our method effectively attenuates the noise generated by stochastic RNA production, resulting in more accurate detection of eRNAs. Furthermore, our eRNA prediction model exhibited significant accuracy in both intra-cell and cross-cell validation, highlighting its robustness and potential application in various cellular contexts.

Abstract Automating retrosynthesis with artificial intelligence expedites organic chemistry research in digital laboratories. However, most existing deep-learning approaches are hard to explain, like a “black box” with few insights. Here, we propose RetroExplainer, formulizing the retrosynthesis task into a molecular assembly process, containing several retrosynthetic actions guided by deep learning. To guarantee a robust performance of our model, we propose three units: a multi-sense and multi-scale Graph Transformer, structure-aware contrastive learning, and dynamic adaptive multi-task learning. The results on 12 large-scale benchmark datasets demonstrate the effectiveness of RetroExplainer, which outperforms the state-of-the-art single-step retrosynthesis approaches. In addition, the molecular assembly process renders our model with good interpretability, allowing for transparent decision-making and quantitative attribution. When extended to multi-step retrosynthesis planning, RetroExplainer has identified 101 pathways, in which 86.9% of the single reactions correspond to those already reported in the literature. As a result, RetroExplainer is expected to offer valuable insights for reliable, high-throughput, and high-quality organic synthesis in drug development.

Detecting cracks during structural health monitoring is crucial for ensuring infrastructure safety and longevity. Using drones to obtain crack images and automate processing can improve the efficiency of crack detection. To address the challenges posed by the limited computing resources of edge devices in practical applications, we propose CrackScopeNet, a lightweight segmentation network model that simultaneously considers local and global crack features while being suitable for deployment on drone platforms with limited computational power and memory. This novel network features a multi-scale branch to improve sensitivity to cracks of varying sizes without substantial computational overhead along with a stripe-wise context attention mechanism to enhance the capture of long-range contextual information while mitigating the interference from complex backgrounds. Experimental results on the CrackSeg9k dataset demonstrate that our method leads to a significant improvement in prediction performance, with the highest mean intersection over union (mIoU) scores reaching 82.12%, and maintains a lightweight architecture with only 1.05 M parameters and 1.58 G floating point operations (FLOPs). In addition, the proposed model excels in inference speed on edge devices without a GPU thanks to its low FLOPs. CrackScopeNet contributes to the development of efficient and effective crack segmentation networks suitable for practical structural health monitoring applications using drone platforms.

Inferring small molecule-miRNA associations (MMAs) is crucial for revealing the intricacies of biological processes and disease mechanisms. Deep learning, renowned for its exceptional speed and accuracy, is extensively used for predicting MMAs. However, given their heavy reliance on data, inaccuracies during data collection can make these methods susceptible to noise interference. To address this challenge, we introduce the joint masking and self-supervised (JMSS)-MMA model. This model synergizes graph autoencoders with a probability distribution-based masking strategy, effectively countering the impact of noisy data and enabling precise predictions of unknown MMAs. Operating in a self-supervised manner, it deeply encodes the relationship data of small molecules and miRNA through the graph autoencoder, delving into its latent information. Our masking strategy has successfully reduced data noise, enhancing prediction accuracy. To our knowledge, this is the pioneering integration of a masking strategy with graph autoencoders for MMA prediction. Furthermore, the JMSS-MMA model incorporates a node-degree–based decoder, deepening the understanding of the network’s structure. Experiments on two mainstream datasets confirm the model’s efficiency and precision, and ablation studies further attest to its robustness. We firmly believe that this model will revolutionize drug development, personalized medicine, and biomedical research.

The impact of novel coronavirus (SARS-CoV-2) is very high; its mutant variants provide a higher transmission rate. Due to many mutations in the omicron-variant, it can evade previously available neutralizing antibodies. The inhibitory effect of the novel compound “Ignaciomycin” was investigated using various computational analyses against the RBD of the SARS-CoV-2 wild-type, Delta, and omicron-variants. Molecular docking revealed the potentially stable interaction of Ignaciomycin with an energy value of −8.65 kcal/mol for the omicron-variant. DFT and Hirshfeld surface calculations showed higher efficiency and reactivity with strong electrostatic potential values. In-silico toxicity studies revealed a significant drug-likeness score (7.5912) with non-toxic properties. MD simulation studies confirmed the stability of Ignaciomycin during ∼ 100 ns simulation. Covariance, PCA, and FEL analyses revealed significant fluctuations in residues and atom mobility in all variants based on the strong interaction of Ignaciomycin. Mutations in the Delta and omicron-variants increased the binding efficiency of the RBD of the SARS-CoV-2 S-glycoprotein with human ACE2. Ignaciomycin had high efficiency in interacting with mutated sites in the RBD, thereby blocking the interaction of the RBD with ACE2. Our findings provide a strong hypothesis for preclinical validation of Ignaciomycin as a potential drug against SARS-CoV-2 and its mutant variants.

Understanding protein corona composition is essential for evaluating their potential applications in biomedicine. Relative protein abundance (RPA), accounting for the total proteins in the corona, is an important parameter for describing the protein corona. For the first time, we comprehensively predicted the RPA of multiple proteins on the protein corona. First, we used multiple machine learning algorithms to predict whether a protein adsorbs to a nanoparticle, which is dichotomous prediction. Then, we selected the top 3 performing machine learning algorithms in dichotomous prediction to predict the specific value of RPA, which is regression prediction. Meanwhile, we analyzed the advantages and disadvantages of different machine learning algorithms for RPA prediction through interpretable analysis. Finally, we mined important features about the RPA prediction, which provided effective suggestions for the preliminary design of protein corona. The service for the prediction of RPA is available at http://www.bioai-lab.com/PC_ML.

BackgroundTo analyze vault effects of crystalline lens rise (CLR) and anterior chamber parameters (recorded by Pentacam) in highly myopic patients receiving implantable collamer lenses (ICLs), which may avoid subsequent complications such as glaucoma and cataract caused by the abnormal vault.MethodsWe collected clinical data of 137 patients with highly myopic vision, who were all subsequent recipients of V4c ICLs between June 2020 and January 2021. Horizontal ciliary sulcus-to-sulcus diameter (hSTS) and CLR were measured by ultrasonic biomicroscopy (UBM), and a Pentacam anterior segment analyzer was used to measure horizontal white-to-white diameter (hWTW), anterior chamber depth (ACD), anterior chamber angle (ACA), anterior chamber volume (ACV), CLR, and postoperative vault (Year 1 and Month 1). The lens thickness (LT) was determined by optical biometry (IOL Master instrument). The predictive model was generated through multiple linear regression analyses of influential factors, such as hSTS, CLR, hWTW, ACD, ACA, ACV, ICL size, and LT. The predictive performance of the multivariate model on vault after ICL was assessed using the receiver operating characteristic (ROC) curve with area under the curve (AUC) as well as the point of tangency.ResultsAverage CLR assessed by UBM was lower than the average value obtained by Pentacam (0.561 vs. 0.683). Bland-Altman analysis showed a good consistency in the two measurement methods and substantial correlation (r = 0.316; P = 0.000). The ROC curve of Model 1 (postoperative Year 1) displayed an AUC of 0.847 (95% confidence interval [CI]: 74.19-95.27), with optimal threshold of 0.581 (sensitivity, 0.857; specificity, 0.724). In addition, respective values for Model 2 (postoperative Month 1) were 0.783 (95% CI: 64.94-91.64) and 0.522 (sensitivity, 0.917; specificity, 0.605).ConclusionCLR and anterior chamber parameters are important determinants of postoperative vault after ICL placement. The multivariate regression model we constructed may serve in large part as a predictive gauge, effectively avoid postoperative complication.

The unique expression patterns of circRNAs linked to the advancement and prognosis of cancer underscore their considerable potential as valuable biomarkers. Repurposing existing drugs for new indications can significantly reduce the cost of cancer treatment. Computational prediction of circRNA-cancer and drug-cancer relationships is crucial for precise cancer therapy. However, prior computational methods fail to analyze the interaction between circRNAs, drugs, and cancer at the systematic level. It is essential to propose a method that uncover more valuable information for achieving cancer-centered multi-association prediction. In this paper, we present a novel computational method, AutoEdge-CCP, to unveil cancer-associated circRNAs and drugs. We abstract the complex relationships between circRNAs, drugs, and cancer into a multi-source heterogeneous network. In this network, each molecule is represented by two types information, one is the intrinsic attribute information of molecular features, and the other is the link information explicitly modeled by autoGNN, which searches information from both intra-layer and inter-layer of message passing neural network. The significant performance on multi-scenario applications and case studies establishes AutoEdge-CCP as a potent and promising association prediction tool.

Subcellular localization is crucial to the study of virus and diseases. Specifically, research on protein subcellular localization can help identify clues between virus and host cells that can aid in the design of targeted drugs. Research on RNA subcellular localization is significant for human diseases (such as Alzheimer’s disease, colon cancer, etc.). To date, only reviews addressing subcellular localization of proteins have been published, which are outdated for reference, and reviews of RNA subcellular localization are not comprehensive. Therefore, we collated (the most up-to-date) literature on protein and RNA subcellular localization to help researchers understand changes in the field of protein and RNA subcellular localization. Extensive and complete methods for constructing subcellular localization models have also been summarized, which can help readers understand the changes in application of biotechnology and computer science in subcellular localization research and explore how to use biological data to construct improved subcellular localization models. This paper is the first review to cover both protein subcellular localization and RNA subcellular localization. We urge researchers from biology and computational biology to jointly pay attention to transformation patterns, interrelationships, differences, and causality of protein subcellular localization and RNA subcellular localization.

Myocardial injury as one of the severe complications leads to the increasing morbidity and mortality in patients with sepsis. Recent studies reported that reactive oxygen species (ROS)-mediated ferroptosis plays a critical role in the development of heart diseases. Therefore, we hypothesized that anti-ferroptosis agent might be a novel potential therapeutic strategy for sepsis-induced cardiac injury. Herein, we demonstrated that a small biocompatible and MRI-visible melanin nanoparticles (MMPP) improves myocardial function by inhibiting ROS-related ferroptosis signaling pathway. In LPS-induced murine sepsis model, after a single dose intravenously injection of MMPP treatment, MMPP markedly alleviated the myocardial injury including cardiac function and heart structure disorder through suppressing iron-accumulation induced ferroptosis. In vitro, MMPP inhibited cardiomyocyte death by attenuating oxidative stress, inflammation and maintaining mitochondrial homeostasis. Collectively, our findings demonstrated that MMPP protected heart against sepsis-induced myocardial injury via inhibiting ferroptosis and inflammation, which might be a novel therapeutic approach in future.

Abstract Background RNA 5-methyluridine (m5U) modifications are obtained by methylation at the C5 position of uridine catalyzed by pyrimidine methylation transferase, which is related to the development of human diseases. Accurate identification of m5U modification sites from RNA sequences can contribute to the understanding of their biological functions and the pathogenesis of related diseases. Compared to traditional experimental methods, computational methods developed based on machine learning with ease of use can identify modification sites from RNA sequences in an efficient and time-saving manner. Despite the good performance of these computational methods, there are some drawbacks and limitations. Results In this study, we have developed a novel predictor, m5U-SVM, based on multi-view features and machine learning algorithms to construct predictive models for identifying m5U modification sites from RNA sequences. In this method, we used four traditional physicochemical features and distributed representation features. The optimized multi-view features were obtained from the four fused traditional physicochemical features by using the two-step LightGBM and IFS methods, and then the distributed representation features were fused with the optimized physicochemical features to obtain the new multi-view features. The best performing classifier, support vector machine, was identified by screening different machine learning algorithms. Compared with the results, the performance of the proposed model is better than that of the existing state-of-the-art tool. Conclusions m5U-SVM provides an effective tool that successfully captures sequence-related attributes of modifications and can accurately predict m5U modification sites from RNA sequences. The identification of m5U modification sites helps to understand and delve into the related biological processes and functions.

With the significant expansion of civil aviation, particularly in the low-altitude economy, there is a significant gap between the escalating demand for airworthiness certification of novel aircraft designs, such as electric vertical take-off and landing (eVTOL) vehicles, and the inefficiency of the current safety assessment process. This gap is partially attributed to safety assessors’ limited exposure to these innovative aircraft models in the safety assessment process, necessitating extensive efforts in identifying precedents and their handling strategies. Complicating matters further, pertinent case studies are scattered across diverse, unstandardized digital formats, obliging assessors to navigate voluminous electronic records while concurrently establishing links among fragmented information scattered across multiple files. This study introduces an advanced information integration methodology, comprising a multi-level path-based architecture and a self-updating algorithm. The proposed method not only furnishes safety assessors with pertinent knowledge featuring explicative interconnectedness automatically, but also dynamically enriches this knowledge corpus through operational usage. Additionally, we devise a suite of evaluative criteria to validate the capacity of our method in processing and consolidating relevant safety datasets. Experimental analyses affirm the efficacy of our proposed approach in streamlining and refreshing safety assessment data. The automation of the retrieval of analogous cases, which relieves the reliance on expert knowledge, enhances the efficiency of the overall safety appraisal procedure. Consequently, this research contributes a solution to enhancing the velocity and accuracy of aircraft certification processes.

Machine learning (ML) is one of the core driving forces for the next breeding stage, and Breeding 4.0. Genotype matrix based on single‐nucleotide polymorphisms (SNPs) is often used in ML for genome‐to‐phenotype prediction. Genotype matrix has an inherent defect, as the feature spaces it generates across different individuals or groups are inconsistent, and this hinders the application of ML. To overcome the challenge, a genome descriptor, Genic SNPs Composition Tool (GSCtool) is developed, which counts the number of SNPs in each gene of the genome so the dimension of the feature vectors equals the number of annotated genes in a species. Compared to using the genotype matrix, using GSCtool significantly decreases the model training time and has a higher accuracy of phenotype prediction. GSCtool also achieves good performance in variety identification, which is useful in crop variety protection. In general, GSCtool will help facilitate the application and study of genomic ML. The source code and test data of GSCtool are freely available at https://github.com/SZJhacker/GSCtool and https://gitee.com/shenzijie/GSCtool.

T cell proliferation regulators (Tcprs), which are positive regulators that promote T cell function, have made great contributions to the development of therapies to improve T cell function. CAR (chimeric antigen receptor) -T cell therapy, a type of adoptive cell transfer therapy that targets tumor cells and enhances immune lethality, has led to significant progress in the treatment of hematologic tumors. However, the applications of CAR-T in solid tumor treatment remain limited. Therefore, in this review, we focus on the development of Tcprs for solid tumor therapy and prognostic prediction. We summarize potential strategies for targeting different Tcprs to enhance T cell proliferation and activation and inhibition of cancer progression, thereby improving the antitumor activity and persistence of CAR-T. In summary, we propose means of enhancing CAR-T cells by expressing different Tcprs, which may lead to the development of a new generation of cell therapies.

The CRISPR/Cas9 system has significantly advanced the field of gene editing, yet its clinical application is constrained by the considerable challenge of off-target effects. Although numerous deep learning models for off-target prediction have been proposed, most struggle to effectively extract the nuanced features of guide RNA (gRNA) and DNA sequence pairs and to mitigate information loss during data transmission within the model. To address these limitations, we introduce a novel Hybrid Neural Network (HNN) model that employs a parallelized network structure to fully extract pertinent features from different positions and types of bases in the sequence to minimize information loss. Notably, this study marks the first application of word embedding techniques to extract information from sequence pairs that contain insertions and deletions (Indels). Comprehensive evaluation across diverse datasets indicates that our proposed model outperforms existing state-of-the-art prediction methods in off-target prediction. The datasets and source codes supporting this study can be found at https://github.com/Yang-k955/CRISPR-HW.

Abstract Background Drug-target interaction (DTI) prediction has become a crucial prerequisite in drug design and drug discovery. However, the traditional biological experiment is time-consuming and expensive, as there are abundant complex interactions present in the large size of genomic and chemical spaces. For alleviating this phenomenon, plenty of computational methods are conducted to effectively complement biological experiments and narrow the search spaces into a preferred candidate domain. Whereas, most of the previous approaches cannot fully consider association behavior semantic information based on several schemas to represent complex the structure of heterogeneous biological networks. Additionally, the prediction of DTI based on single modalities cannot satisfy the demand for prediction accuracy. Methods We propose a multi-modal representation framework of ‘DeepMPF’ based on meta-path semantic analysis, which effectively utilizes heterogeneous information to predict DTI. Specifically, we first construct protein–drug-disease heterogeneous networks composed of three entities. Then the feature information is obtained under three views, containing sequence modality, heterogeneous structure modality and similarity modality. We proposed six representative schemas of meta-path to preserve the high-order nonlinear structure and catch hidden structural information of the heterogeneous network. Finally, DeepMPF generates highly representative comprehensive feature descriptors and calculates the probability of interaction through joint learning. Results To evaluate the predictive performance of DeepMPF, comparison experiments are conducted on four gold datasets. Our method can obtain competitive performance in all datasets. We also explore the influence of the different feature embedding dimensions, learning strategies and classification methods. Meaningfully, the drug repositioning experiments on COVID-19 and HIV demonstrate DeepMPF can be applied to solve problems in reality and help drug discovery. The further analysis of molecular docking experiments enhances the credibility of the drug candidates predicted by DeepMPF. Conclusions All the results demonstrate the effectively predictive capability of DeepMPF for drug-target interactions. It can be utilized as a useful tool to prescreen the most potential drug candidates for the protein. The web server of the DeepMPF predictor is freely available at http://120.77.11.78/DeepMPF/ , which can help relevant researchers to further study.

Abstract Background 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. Results 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. Conclusions 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/ .

Abstract In this study, we propose iDNA-ABF, a multi-scale deep biological language learning model that enables the interpretable prediction of DNA methylations based on genomic sequences only. Benchmarking comparisons show that our iDNA-ABF outperforms state-of-the-art methods for different methylation predictions. Importantly, we show the power of deep language learning in capturing both sequential and functional semantics information from background genomes. Moreover, by integrating the interpretable analysis mechanism, we well explain what the model learns, helping us build the mapping from the discovery of important sequential determinants to the in-depth analysis of their biological functions.

Abstract Background Accurate precision approaches have far not been developed for modeling mortality risk in intensive care unit (ICU) patients. Conventional mortality risk prediction methods can hardly extract the information in longitudinal electronic medical records (EHRs) effectively, since they simply aggregate the heterogeneous variables in EHRs, ignoring the complex relationship and interactions between variables and the time dependence in longitudinal records. Recently deep learning approaches have been widely used in modeling longitudinal EHR data. However, most existing deep learning-based risk prediction approaches only use the information of a single disease, neglecting the interactions between multiple diseases and different conditions. Results In this paper, we address this unmet need by leveraging disease and treatment information in EHRs to develop a mortality risk prediction model based on deep learning (DeepMPM). DeepMPM utilizes a two-level attention mechanism, i.e. visit-level and variable-level attention, to derive the representation of patient risk status from patient’s multiple longitudinal medical records. Benefiting from using EHR of patients with multiple diseases and different conditions, DeepMPM can achieve state-of-the-art performances in mortality risk prediction. Conclusions Experiment results on MIMIC III database demonstrates that with the disease and treatment information DeepMPM can achieve a good performance in terms of Area Under ROC Curve (0.85). Moreover, DeepMPM can successfully model the complex interactions between diseases to achieve better representation learning of disease and treatment than other deep learning approaches, so as to improve the accuracy of mortality prediction. A case study also shows that DeepMPM offers the potential to provide users with insights into feature correlation in data as well as model behavior for each prediction.