Prediction of Adolescents' Fluid Intelligence Scores based on Deep Learning with Reconstruction Regularization.

Objective: The aim of this study was to develop a predictive model for uncorrected/actual fluid intelligence scores in 9-10 year old children using magnetic resonance T1-weighted imaging. Explore the predictive performance of an autoencoder model based on reconstruction regularization for fluid intelligence in adolescents. Methods: We collected actual fluid intelligence scores and T1-weighted MRIs of 11,534 adolescents who completed baseline tasks from ABCD Data Release 3.0. A total of 148 ROIs were selected and 604 features were proposed by FreeSurfer segmentation. The training and testing sets were divided in a ratio of 7:3. To predict fluid intelligence scores, we used AE, MLP and classic machine learning models, and compared their performance on the test set. In addition, we explored their performance across gender subpopulations. Moreover, we evaluated the importance of features using the SHapley Additive Explain method. Results: The proposed model achieves optimal performance on the test set for predicting actual fluid intelligence scores (PCC = 0.209 ± 0.02, MSE = 105.212 ± 2.53). Results show that autoencoders with refactoring regularization are significantly more effective than MLPs and classical machine learning models. In addition, all models performed better on female adolescents than on male adolescents. Further analysis of relevant characteristics in different populations revealed that this may be related to gender differences in underlying fluid intelligence mechanisms. Conclusions: We construct a weak but stable correlation between brain structural features and raw fluid intelligence using autoencoders. Future research may need to explore ensemble regression strategies utilizing multiple machine learning algorithms on multimodal data in order to improve the predictive performance of fluid intelligence based on neuroimaging features.

Ultrafast Dual-Shock Chemistry Synthesis of Ordered/Disordered Hybrid Carbon Anodes: High-Rate Performance of Li-Ion Batteries.

Graphite exhibits crystal anisotropy, which impedes the mass transfer of ion intercalation and extraction processes in Li-ion batteries. Herein, a dual-shock chemical strategy has been developed to synthesize the carbon anode. This approach comprised two key phases: (1) a thermal shock utilizing ultrahigh temperature (3228 K) can thermodynamically facilitate graphitization; (2) a mechanical shock (21.64 MPa) disrupting the π-π interactions in the aromatic chains of carbon can result in hybrid-structured carbon composed of crystalline and amorphous carbon. The optimized carbon (DSC-200-0.3) demonstrates a capacity of 208.61 mAh/g at a 10C rate, with a significant enhancement comparing with 15 mAh/g of the original graphite. Impressively, it maintains 81.06% capacity even after 3000 charge-discharge cycles. Dynamic process analysis reveals that this superior rate performance is attributed to a larger interlayer spacing facilitating ion transport comparing with the original graphite, disordered amorphous carbon for additional lithium storage sites, and crystallized carbon for enhanced charge transfer. The dual-shock chemical approach offers a cost-effective and efficient method to rapidly produce hybrid-structured carbon anodes, enabling 10C fast charging capabilities in lithium-ion batteries.

Approaching Ultimate Synthesis Reaction Rate of Ni-Rich Layered Cathodes for Lithium-Ion Batteries.

Nickel-rich layered oxide LiNixCoyMnzO2 (NCM, x + y + z = 1) is the most promising cathode material for high-energy lithium-ion batteries. However, conventional synthesis methods are limited by the slow heating rate, sluggish reaction dynamics, high energy consumption, and long reaction time. To overcome these challenges, we first employed a high-temperature shock (HTS) strategy for fast synthesis of the NCM, and the approaching ultimate reaction rate of solid phase transition is deeply investigated for the first time. In the HTS process, ultrafast average reaction rate of phase transition from Ni0.6Co0.2Mn0.2(OH)2 to Li- containing oxides is 66.7 (% s-1), that is, taking only 1.5 s. An ultrahigh heating rate leads to fast reaction kinetics, which induces the rapid phase transition of NCM cathodes. The HTS-synthesized nickel-rich layered oxides perform good cycling performances (94% for NCM523, 94% for NCM622, and 80% for NCM811 after 200 cycles at 4.3 V). These findings might also assist to pave the way for preparing effectively Ni-rich layered oxides for lithium-ion batteries.

Investigating the Impact of Pineapple-Whey Protein Fermentation Products on Cefixime-Induced Intestinal Flora Dysbiosis in Mice Using 16S Sequencing and Untargeted Metabolomics Techniques.

In our previous study, a new fermented food (PWF) created by utilizing pineapple by-products and whey proteins as a matrix via co-fermentation with lactic acid bacteria and yeast was developed, and, in the current study, we examined the impact of a pineapple-whey protein fermentation product on a cefixime-induced dysbiosis model in mice using 16S sequencing and untargeted metabolomics techniques. The results indicated that the pineapple-whey protein fermentation product played a positive role in restoring the intestinal flora. In this study, cefixime reduced the overall abundance of intestinal flora and decreased the relative abundance of probiotics in the gut, while also inhibiting amino acid metabolism. The addition of PWF normalized the intestinal flora to a steady state, significantly increasing the populations of Weissella, Lactococcus, Faecalibaculum, and Bacteroides acidophilus, while decreasing the numbers of Akkermansia and Escherichia-Shigella. Additionally, PWF modulated microbial metabolites, such as L-glutamate and L-threonine, and upregulated amino-acid-related metabolic pathways, including those involving glycine, serine, and threonine. In conclusion, PWF can alleviate intestinal flora dysbiosis and metabolic disturbances induced by antibiotic interventions. It is suggested that PWF could be a potential dietary strategy for patients with antibiotic-associated diarrhea.

Neural network enabled fringe projection through scattering media.

The projection of fringes plays an essential role in many applications, such as fringe projection profilometry and structured illumination microscopy. However, these capabilities are significantly constrained in environments affected by optical scattering. Although recent developments in wavefront shaping have effectively generated high-fidelity focal points and relatively simple structured images amidst scattering, the ability to project fringes that cover half of the projection area has not yet been achieved. To address this limitation, this study presents a fringe projector enabled by a neural network, capable of projecting fringes with variable periodicities and orientation angles through scattering media. We tested this projector on two types of scattering media: ground glass diffusers and multimode fibers. For these scattering media, the average Pearson's correlation coefficients between the projected fringes and their designed configurations are 86.9% and 79.7%, respectively. These results demonstrate the effectiveness of the proposed neural network enabled fringe projector. This advancement is expected to broaden the scope of fringe-based imaging techniques, making it feasible to employ them in conditions previously hindered by scattering effects.

Brain-Controlled Hand Exoskeleton Based on Augmented Reality-Fused Stimulus Paradigm.

Advancements in brain-machine interfaces (BMIs) have led to the development of novel rehabilitation training methods for people with impaired hand function. However, contemporary hand exoskeleton systems predominantly adopt passive control methods, leading to low system performance. In this work, an active brain-controlled hand exoskeleton system is proposed that uses a novel augmented reality-fused stimulus (AR-FS) paradigm as a human-machine interface, which enables users to actively control their fingers to move. Considering that the proposed AR-FS paradigm generates movement artifacts during hand movements, an enhanced decoding algorithm is designed to improve the decoding accuracy and robustness of the system. In online experiments, participants performed online control tasks using the proposed system, with an average task time cost of 16.27 s, an average output latency of 1.54 s, and an average correlation instantaneous rate (CIR) of 0.0321. The proposed system shows 35.37% better efficiency, 8.03% reduced system delay, and 35.28% better stability than the traditional system. This study not only provides an efficient rehabilitation solution for people with impaired hand function but also expands the application prospects of brain-control technology in areas such as human augmentation, patient monitoring, and remote robotic interaction. The video in Graphical Abstract Video demonstrates the user's process of operating the proposed brain-controlled hand exoskeleton system.

Lightweight and robust cellulose/MXene/polyurethane composite aerogels as personal protective wearable devices for electromagnetic interference shielding.

The increasing electromagnetic pollution is urgently needed as an electromagnetic interference shielding protection device for wearable devices. Two-dimensional transition metal carbides and nitrides (MXene), due to their interesting layered structure and high electrical conductivity, are ideal candidates for constructing efficient conductive networks in electromagnetic interference shielding materials. In this work, lightweight and robust cellulose/MXene/polyurethane composite aerogels were prepared by mixing cellulose nanofiber (CNF) suspensions with MXene, followed by freeze-drying and coating with polyurethane. In this process, CNF effectively assembled MXene nanosheets into a conductive network by enhancing the interactions between MXene nanosheets. The prepared aerogel exhibited the shielding effectiveness of 48.59 dB in the X-band and an electrical conductivity of 0.34 S·cm-1. Meanwhile, the composite aerogel also possessed excellent thermal insulation, infrared stealth, mechanical and hydrophobic properties, and can be used as a wearable protective device to protect the human body from injuries in different scenarios while providing electromagnetic interference shielding protection.

Coupling Antisite Defect and Lattice Tensile Stimulates Facile Isotropic Li-Ion Diffusion.

Despite widely used as a commercial cathode, the anisotropic 1D channel hopping of lithium ions along the [010] direction in LiFePO4 prevents its application in fast charging conditions. Herein, an ultrafast nonequilibrium high-temperature shock technology is employed to controllably introduce the Li-Fe antisite defects and tensile strain into the lattice of LiFePO4. This design makes the study of the effect of the strain field on the performance further extended from the theoretical calculation to the experimental perspective. The existence of Li-Fe antisite defects makes it feasible for Li+ to move from the 4a site of the edge-sharing octahedra across the ab plane to 4c site of corner-sharing octahedra, producing a new diffusion channel different from [010]. Meanwhile, the presence of a tensile strain field reduces the energy barrier of the new 2D diffusion path. In the combination of electrochemical experiments and first-principles calculations, the unique multiscale coupling structure of Li-Fe antisite defects and lattice strain promotes isotropic 2D interchannel Li+ hopping, leading to excellent fast charging performance and cycling stability (high-capacity retention of 84.4% after 2000 cycles at 10 C). The new mechanism of Li+ diffusion kinetics accelerated by multiscale coupling can guide the design of high-rate electrodes.

Paediatric off-label use of drugs in Gansu, China: a multicentre cross-sectional study.

OBJECTIVE: To examine the current prevalence and cost of paediatric off-label drug prescriptions in Gansu, China, and the potential influencing factors. DESIGN: The prevalence of off-label prescriptions in paediatrics was evaluated according to the National Medical Products Administration drug instructions in the China Pharmaceutical Reference (China Pharmaceutical Reference, MCDEX) database. The evidence of the prescription was determined by existing clinical practice guidelines and the Thomson Grade in the Micromedex 2021 compendium. We used logistic regression to investigate the characteristics that influence paediatric off-label drug use after single-factor regression analysis. SETTING: A multicentre cross-sectional study of outpatient paediatric prescriptions in 196 secondary and tertiary hospitals in Gansu Province, China, in March and September 2020. RESULTS: We retrieved 104 029 paediatric prescriptions, of which 39 480 (38.0%) contained off-label use. The most common diseases treated by off-label drugs were respiratory system diseases (n=15 831, 40.1%). A quarter of off-label prescriptions had adequate evidence basis (n=10 130, 25.6%). Unapproved indications were the most common type of off-label drug use (n=25 891, 65.6%). A total of 1177 different drugs were prescribed off-label, with multienzyme tablets being the most common drug (n=1790, 3.5%). The total cost of the prescribed off-label drugs was ¥106 116/day. Off-label prescriptions were less frequent in tertiary than in secondary hospitals. Topical preparations were more commonly prescribed off-label than other types of drugs. Senior-level clinicians prescribed drugs off-label more often than intermediate and junior clinicians. CONCLUSION: Off-label drug use is widespread in paediatric practice in China. Three-quarters of the prescriptions may potentially include inappropriate medication use, resulting in a daily economic burden of about ¥81 000 in 2020 in Gansu Province with 25 million inhabitants. The management of off-label drug use in paediatrics in China needs improvement.

A Dual-mode platform for the rapid detection of Escherichia coli O157:H7 based on CRISPR/Cas12a and RPA.

Escherichia coli O157:H7 (E. coli O157:H7) is a foodborne pathogenic microorganism that is commonly found in the environment and poses a significant threat to human health, public safety, and economic stability worldwide. Thus, early detection is essential for E. coli O157:H7 control. In recent years, a series of E. coli O157:H7 detection methods have been developed, but the sensitivity and portability of the methods still need improvement. Therefore, in this study, a rapid and efficient testing platform based on the CRISPR/Cas12a cleavage reaction was constructed. Through the integration of recombinant polymerase amplification and lateral flow chromatography, we established a dual-interpretation-mode detection platform based on CRISPR/Cas12a-derived fluorescence and lateral flow chromatography for the detection of E. coli O157:H7. For the fluorescence detection method, the limits of detection (LODs) of genomic DNA and E. coli O157:H7 were 1.8 fg/µL and 2.4 CFU/mL, respectively, within 40 min. Conversely, for the lateral flow detection method, LODs of 1.8 fg/µL and 2.4 × 102 CFU/mL were achieved for genomic DNA and E. coli O157:H7, respectively, within 45 min. This detection strategy offered higher sensitivity and lower equipment requirements than industry standards. In conclusion, the established platform showed excellent specificity and strong universality. Modifying the target gene and its primers can broaden the platform's applicability to detect various other foodborne pathogens.

Curvature-enhanced graph convolutional network for biomolecular interaction prediction.

Geometric deep learning has demonstrated a great potential in non-Euclidean data analysis. The incorporation of geometric insights into learning architecture is vital to its success. Here we propose a curvature-enhanced graph convolutional network (CGCN) for biomolecular interaction prediction. Our CGCN employs Ollivier-Ricci curvature (ORC) to characterize network local geometric properties and enhance the learning capability of GCNs. More specifically, ORCs are evaluated based on the local topology from node neighborhoods, and further incorporated into the weight function for the feature aggregation in message-passing procedure. Our CGCN model is extensively validated on fourteen real-world bimolecular interaction networks and analyzed in details using a series of well-designed simulated data. It has been found that our CGCN can achieve the state-of-the-art results. It outperforms all existing models, as far as we know, in thirteen out of the fourteen real-world datasets and ranks as the second in the rest one. The results from the simulated data show that our CGCN model is superior to the traditional GCN models regardless of the positive-to-negative-curvature ratios, network densities, and network sizes (when larger than 500).

Dynamics of nutrients, sensory quality and microbial communities and their interactions during co-fermentation of pineapple by-products and whey protein.

In this study, a new fermented food was developed using pineapple by-products and whey protein (2.6%) as raw materials through the co-fermentation of autochthonous lactic acid bacteria and yeast. To better understand the fermentation mechanism and the impact of microorganisms on the entire fermentation system, we tracked the changes in carbohydrate and amino acid profiles, organoleptic quality and microbial community during the fermentation process. Compared with unfermented samples, dietary fiber and free amino acids increased significantly as fermentation proceeded. The fermented samples were significantly lower in astringency and bitterness and significantly higher in sourness, umami and richness. The fermented products were richer in volatile compounds with floral, cheesy, fruity and other flavors. Relevant analyses showed that the core microbial community was highly correlated with the quality attributes of the fermented products. Microorganisms such as Lactococcus, Weissella, Hanseniaspora, Saccharomyces and Lachancea contributed significantly to the fermented products.

Sd-net: a semi-supervised double-cooperative network for liver segmentation from computed tomography (CT) images.

INTRODUCTION: The automatic segmentation of the liver is a crucial step in obtaining quantitative biomarkers for accurate clinical diagnosis and computer-aided decision support systems. This task is challenging due to the frequent presence of noise and sampling artifacts in computerized tomography (CT) images, as well as the complex background, variable shapes, and blurry boundaries of the liver. Standard segmentation of medical images based on full-supervised convolutional networks demands accurate dense annotations. Such a learning framework is built on laborious manual annotation with strict requirements for expertise, leading to insufficient high-quality labels. METHODS: To overcome such limitation and exploit massive weakly labeled data, we relaxed the rigid labeling requirement and developed a semi-supervised double-cooperative network (SD- Net). SD-Net is trained to segment the complete liver volume from preoperative abdominal CT images by using limited labeled datasets and large-scale unlabeled datasets. Specifically, to enrich the diversity of unsupervised information, we construct SD-Net consisting of two collaborative network models. Within the supervised training module, we introduce an adaptive mask refinement approach. First, each of the two network models predicts the labeled dataset, after which adaptive mask refinement of the difference predictions is implemented to obtain more accurate liver segmentation results. In the unsupervised training module, a dynamic pseudo-label generation strategy is proposed. First each of the two models predicts unlabeled data and the better prediction is considered as pseudo-labeling before training. RESULTS AND DISCUSSION: Based on the experimental findings, the proposed method achieves a dice score exceeding 94%, indicating its high level of accuracy and its suitability for everyday clinical use.

Comprehensive analysis of the miRNA-mRNA regulatory network involved in spontaneous recovery of an H2O2-induced zebrafish cataract model.

OBJECTIVE: To identify the hub miRNAs and mRNAs contributing to the spontaneous recovery of an H2O2-induced zebrafish cataract model. METHODS: Zebrafishes were divided into three groups, i.e., Group A, which included normal control fish (day 0), and Groups B and C, where fish were injected with 2.5% hydrogen peroxide into the anterior chamber and reared for 14 and 30 days, respectively. Fish eyes were examined by stereomicroscope photography and optical coherence tomography (OCT). RNA profiles of fish lenses were detected by RNA sequencing. Differentially expressed genes (DEGs) and differentially expressed miRNAs (DEmiRs) were identified among three groups. The DEGs and DEmiRs, which changed in opposite positions between "B vs. A" and "C vs. B" were defined as ODGs (opposite positions changed DEGs) and ODmiRs (opposite positions changed DEmiRs). Gene Ontology (GO) analysis and Kyoto Encyclopedia of Genes and Genomes pathway (KEGG) analysis were carried out by R language. The protein-protein interaction network (PPI) was constructed using STRING. Potential targets of miRNAs were obtained using miRanda. miRNA-mRNA networks were constructed by Cytoscape. RESULTS: The fish lens opacity formed on day 14 and recovered to transparent on day 30 after injection. Compared to group B, 1366 DEGs and 54 DEmiRs were identified in group C. "C vs. B" DEGs were enriched in gene clusters related to development and oxidative phosphorylation. Target genes of DEmiRs were enriched in clusters such as development and cysteine metabolism. Among three groups, 786 ODGs and 27 ODmiRs were identified, and 480 ODGs were predicted as targets of ODmiRs. Target ODGs were enriched in pathways related to methionine metabolism, ubiquitin, sensory system development, and structural constituents of the eye lens. In addition, we established an ODmiRs-ODGs regulation network. CONCLUSION: We identified several hub mRNAs and altered miRNAs in the formation and reversal of zebrafish cataracts. These hub miRNAs/mRNAs could be potential targets for the non-surgical treatment of ARC.

Node-adaptive graph Transformer with structural encoding for accurate and robust lncRNA-disease association prediction.

BACKGROUND: Long noncoding RNAs (lncRNAs) are integral to a plethora of critical cellular biological processes, including the regulation of gene expression, cell differentiation, and the development of tumors and cancers. Predicting the relationships between lncRNAs and diseases can contribute to a better understanding of the pathogenic mechanisms of disease and provide strong support for the development of advanced treatment methods. RESULTS: Therefore, we present an innovative Node-Adaptive Graph Transformer model for predicting unknown LncRNA-Disease Associations, named NAGTLDA. First, we utilize the node-adaptive feature smoothing (NAFS) method to learn the local feature information of nodes and encode the structural information of the fusion similarity network of diseases and lncRNAs using Structural Deep Network Embedding (SDNE). Next, the Transformer module is used to capture potential association information between the network nodes. Finally, we employ a Transformer module with two multi-headed attention layers for learning global-level embedding fusion. Network structure coding is added as the structural inductive bias of the network to compensate for the missing message-passing mechanism in Transformer. NAGTLDA achieved an average AUC of 0.9531 and AUPR of 0.9537 significantly higher than state-of-the-art methods in 5-fold cross validation. We perform case studies on 4 diseases; 55 out of 60 associations between lncRNAs and diseases have been validated in the literatures. The results demonstrate the enormous potential of the graph Transformer structure to incorporate graph structural information for uncovering lncRNA-disease unknown correlations. CONCLUSIONS: Our proposed NAGTLDA model can serve as a highly efficient computational method for predicting biological information associations.

Origin and early divergence of tandem duplicated sorbitol transporter genes in Rosaceae: insights from evolutionary analysis of the SOT gene family in angiosperms.

Sorbitol is a critical photosynthate and storage substance in the Rosaceae family. Sorbitol transporters (SOTs) play a vital role in facilitating sorbitol allocation from source to sink organs and sugar accumulation in sink organs. While prior research has addressed gene duplications within the SOT gene family in Rosaceae, the precise origin and evolutionary dynamics of these duplications remain unclear, largely due to the complicated interplay of whole genome duplications and tandem duplications. Here, we investigated the synteny relationships among all identified Polyol/Monosaccharide Transporter (PLT) genes in 61 angiosperm genomes and SOT genes in representative genomes within the Rosaceae family. By integrating phylogenetic analyses, we elucidated the lineage-specific expansion and syntenic conservation of PLTs and SOTs across diverse plant lineages. We found that Rosaceae SOTs, as PLT family members, originated from a pair of tandemly duplicated PLT genes within Class III-A. Furthermore, our investigation highlights the role of lineage-specific and synergistic duplications in Amygdaloideae in contributing to the expansion of SOTs in Rosaceae plants. Collectively, our findings provide insights into the genomic origins, duplication events, and subsequent divergence of SOT gene family members. Such insights lay a crucial foundation for comprehensive functional characterizations in future studies.

An extracellular matrix-mimicking magnetic microrobot for targeted elimination of circulating cancer cells.

Cancer cells disseminate through the bloodstream, leading to metastasis in distant sites within the body. One promising strategy to prevent metastasis is to eliminate circulating tumor cells. However, this remains challenging due to the lack of an active and targeted biomedical tool for efficient cancer cell elimination. Here, we developed a magnetic microrobot by using natural materials derived from the extracellular matrix (ECM) to mimic the ligand-receptor interaction between cancer cells and the ECM, offering targeted elimination of cancer cells. The ECM-mimicking microrobot is designed with a biodegradable hydrogel matrix, incorporating a cancer cell ligand and magnetic microparticles for cancer cell capture and active locomotion. This microrobot was fabricated based on an interface-shearing method, enabling controllable magnetic response and size scalability (30 µm-500 µm). The presented ECM-mimicking microrobot can actively approach and capture single cancer cells and cell clusters under the control of specific magnetic fields. The experiment was conducted in a blood vessel-mimicking simulator. The microrobot demonstrates an outstanding elimination efficacy of 92.3% on MDA-MB-231 cancer cells and a stable transport capability of the captured cells over long distances to a designed recycling site, inhibiting cell metastasis. This magnetic ECM-mimicking microrobot based on a bioinspired binding mechanism represents a promising candidate for the efficient elimination of cancer cells and other biological waste in the blood.

Single-Cell Transcriptional Analysis of Lamina Propria Lymphocytes in the Jejunum Reveals Innate Lymphoid Cell-like Cells in Pigs.

Pigs are the most suitable model to study various therapeutic strategies and drugs for human beings, although knowledge about cell type-specific transcriptomes and heterogeneity is poorly available. Through single-cell RNA sequencing and flow cytometry analysis of the types in the jejunum of pigs, we found that innate lymphoid cells (ILCs) existed in the lamina propria lymphocytes (LPLs) of the jejunum. Then, through flow sorting of live/dead-lineage (Lin)-CD45+ cells and single-cell RNA sequencing, we found that ILCs in the porcine jejunum were mainly ILC3s, with a small number of NK cells, ILC1s, and ILC2s. ILCs coexpressed IL-7Rα, ID2, and other genes and differentially expressed RORC, GATA3, and other genes but did not express the CD3 gene. ILC3s can be divided into four subgroups, and genes such as CXCL8, CXCL2, IL-22, IL-17, and NCR2 are differentially expressed. To further detect and identify ILC3s, we verified the classification of ILCs in the porcine jejunum subgroup and the expression of related hallmark genes at the protein level by flow cytometry. For systematically characterizing ILCs in the porcine intestines, we combined our pig ILC dataset with publicly available human and mice ILC data and identified that the human and pig ILCs shared more common features than did those mouse ILCs in gene signatures and cell states. Our results showed in detail for the first time (to our knowledge) the gene expression of porcine jejunal ILCs, the subtype classification of ILCs, and the markers of various ILCs, which provide a basis for an in-depth exploration of porcine intestinal mucosal immunity.

DeepWalk-aware graph attention networks with CNN for circRNA-drug sensitivity association identification.

Circular RNAs (circRNAs) are a class of noncoding RNA molecules that are widely found in cells. Recent studies have revealed the significant role played by circRNAs in human health and disease treatment. Several restrictions are encountered because forecasting prospective circRNAs and medication sensitivity connections through biological research is not only time-consuming and expensive but also incredibly ineffective. Consequently, the development of a novel computational method that enhances both the efficiency and accuracy of predicting the associations between circRNAs and drug sensitivities is urgently needed. Here, we present DGATCCDA, a computational method based on deep learning, for circRNA-drug sensitivity association identification. In DGATCCDA, we first construct multimodal networks from the original feature information of circRNAs and drugs. After that, we adopt DeepWalk-aware graph attention networks to sufficiently extract feature information from the multimodal networks to obtain the embedding representation of nodes. Specifically, we combine DeepWalk and graph attention network to form DeepWalk-aware graph attention networks, which can effectively capture the global and local information of graph structures. The features extracted from the multimodal networks are fused by layer attention, and eventually, the inner product approach is used to construct the association matrix of circRNAs and drugs for prediction. The ultimate experimental results obtained under 5-fold cross-validation settings show that the average area under the receiver operating characteristic curve value of DGATCCDA reaches 91.18%, which is better than those of the five current state-of-the-art calculation methods. We further guide a case study, and the excellent obtained results also show that DGATCCDA is an effective computational method for exploring latent circRNA-drug sensitivity associations.

MNCLCDA: predicting circRNA-drug sensitivity associations by using mixed neighbourhood information and contrastive learning.

BACKGROUND: circRNAs play an important role in drug resistance and cancer development. Recently, many studies have shown that the expressions of circRNAs in human cells can affect the sensitivity of cells to therapeutic drugs, thus significantly influencing the therapeutic effects of these drugs. Traditional biomedical experiments required to verify this sensitivity relationship are not only time-consuming but also expensive. Hence, the development of an efficient computational approach that can accurately predict the novel associations between drug sensitivities and circRNAs is a crucial and pressing need. METHODS: In this research, we present a novel computational framework called MNCLCDA, which aims to predict the potential associations between drug sensitivities and circRNAs to assist with medical research. First, MNCLCDA quantifies the similarity between the given drug and circRNA using drug structure information, circRNA gene sequence information, and GIP kernel information. Due to the existence of noise in similarity information, we employ a preprocessing approach based on random walk with restart for similarity networks to efficiently capture the useful features of circRNAs and drugs. Second, we use a mixed neighbourhood graph convolutional network to obtain the neighbourhood information of nodes. Then, a graph-based contrastive learning method is used to enhance the robustness of the model, and finally, a double Laplace-regularized least-squares method is used to predict potential circRNA-drug associations through the kernel matrices in the circRNA and drug spaces. RESULTS: Numerous experimental results show that MNCLCDA outperforms six other advanced methods. In addition, the excellent performance of our proposed model in case studies illustrates that MNCLCDA also has the ability to predict the associations between drug sensitivity and circRNA in practical situations. CONCLUSIONS: After a large number of experiments, it is illustrated that MNCLCDA is an efficient tool for predicting the potential associations between drug sensitivities and circRNAs, thereby can provide some guidance for clinical trials.