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.

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.

Spatial-MGCN: a novel multi-view graph convolutional network for identifying spatial domains with attention mechanism.

MOTIVATION: Recent advances in spatial transcriptomics technologies have enabled gene expression profiles while preserving spatial context. Accurately identifying spatial domains is crucial for downstream analysis and it requires the effective integration of gene expression profiles and spatial information. While increasingly computational methods have been developed for spatial domain detection, most of them cannot adaptively learn the complex relationship between gene expression and spatial information, leading to sub-optimal performance. RESULTS: To overcome these challenges, we propose a novel deep learning method named Spatial-MGCN for identifying spatial domains, which is a Multi-view Graph Convolutional Network (GCN) with attention mechanism. We first construct two neighbor graphs using gene expression profiles and spatial information, respectively. Then, a multi-view GCN encoder is designed to extract unique embeddings from both the feature and spatial graphs, as well as their shared embeddings by combining both graphs. Finally, a zero-inflated negative binomial decoder is used to reconstruct the original expression matrix by capturing the global probability distribution of gene expression profiles. Moreover, Spatial-MGCN incorporates a spatial regularization constraint into the features learning to preserve spatial neighbor information in an end-to-end manner. The experimental results show that Spatial-MGCN outperforms state-of-the-art methods consistently in several tasks, including spatial clustering and trajectory inference.

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.

A survey of circular RNAs in complex diseases: databases, tools and computational methods.

Circular RNAs (circRNAs) are a category of novelty discovered competing endogenous non-coding RNAs that have been proved to implicate many human complex diseases. A large number of circRNAs have been confirmed to be involved in cancer progression and are expected to become promising biomarkers for tumor diagnosis and targeted therapy. Deciphering the underlying relationships between circRNAs and diseases may provide new insights for us to understand the pathogenesis of complex diseases and further characterize the biological functions of circRNAs. As traditional experimental methods are usually time-consuming and laborious, computational models have made significant progress in systematically exploring potential circRNA-disease associations, which not only creates new opportunities for investigating pathogenic mechanisms at the level of circRNAs, but also helps to significantly improve the efficiency of clinical trials. In this review, we first summarize the functions and characteristics of circRNAs and introduce some representative circRNAs related to tumorigenesis. Then, we mainly investigate the available databases and tools dedicated to circRNA and disease studies. Next, we present a comprehensive review of computational methods for predicting circRNA-disease associations and classify them into five categories, including network propagating-based, path-based, matrix factorization-based, deep learning-based and other machine learning methods. Finally, we further discuss the challenges and future researches in this field.

A knowledge-driven network for fine-grained relationship detection between miRNA and disease.

Increasing biological evidence indicated that microRNAs (miRNAs) play a vital role in exploring the pathogenesis of various human diseases (especially in tumors). Mining disease-related miRNAs is of great significance for the clinical diagnosis and treatment of diseases. Compared with the traditional experimental methods with the significant limitations of high cost, long cycle and small scale, the methods based on computing have the advantages of being cost-effective. However, although the current methods based on computational biology can accurately predict the correlation between miRNAs and disease, they can not predict the detailed association information at a fine level. We propose a knowledge-driven approach to the fine-grained prediction of disease-related miRNAs (KDFGMDA). Different from the previous methods, this method can finely predict the clear associations between miRNA and disease, such as upregulation, downregulation or dysregulation. Specifically, KDFGMDA extracts triple information from massive experimental data and existing datasets to construct a knowledge graph and then trains a depth graph representation learning model based on knowledge graph to complete fine-grained prediction tasks. Experimental results show that KDFGMDA can predict the relationship between miRNA and disease accurately, which is of far-reaching significance for medical clinical research and early diagnosis, prevention and treatment of diseases. Additionally, the results of case studies on three types of cancers, Kaplan-Meier survival analysis and expression difference analysis further provide the effectiveness and feasibility of KDFGMDA to detect potential candidate miRNAs. Availability: Our work can be downloaded from https://github.com/ShengPengYu/KDFGMDA.

scGCL: an imputation method for scRNA-seq data based on graph contrastive learning.

MOTIVATION: Single-cell RNA-sequencing (scRNA-seq) is widely used to reveal cellular heterogeneity, complex disease mechanisms and cell differentiation processes. Due to high sparsity and complex gene expression patterns, scRNA-seq data present a large number of dropout events, affecting downstream tasks such as cell clustering and pseudo-time analysis. Restoring the expression levels of genes is essential for reducing technical noise and facilitating downstream analysis. However, existing scRNA-seq data imputation methods ignore the topological structure information of scRNA-seq data and cannot comprehensively utilize the relationships between cells. RESULTS: Here, we propose a single-cell Graph Contrastive Learning method for scRNA-seq data imputation, named scGCL, which integrates graph contrastive learning and Zero-inflated Negative Binomial (ZINB) distribution to estimate dropout values. scGCL summarizes global and local semantic information through contrastive learning and selects positive samples to enhance the representation of target nodes. To capture the global probability distribution, scGCL introduces an autoencoder based on the ZINB distribution, which reconstructs the scRNA-seq data based on the prior distribution. Through extensive experiments, we verify that scGCL outperforms existing state-of-the-art imputation methods in clustering performance and gene imputation on 14 scRNA-seq datasets. Further, we find that scGCL can enhance the expression patterns of specific genes in Alzheimer's disease datasets. AVAILABILITY AND IMPLEMENTATION: The code and data of scGCL are available on Github: https://github.com/zehaoxiong123/scGCL. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

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.

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.

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.

Interisland-Distance-Mediated Growth of Centimeter-Scale Two-Dimensional Magnetic Fe3O4 Arrays with Unidirectional Domain Orientations.

Two-dimensional (2D) nanosheet arrays with unidirectional orientations are of great significance for synthesizing wafer-scale single crystals. Although great efforts have been devoted, the growth of atomically thin magnetic nanosheet arrays and single crystals is still unaddressed. Here we design an interisland-distance-mediated chemical vapor deposition strategy to synthesize centimeter-scale atomically thin Fe3O4 arrays with unidirectional orientations on mica. The unidirectional alignment of nearly all the Fe3O4 nanosheets is driven by a dual-coupling-guided growth mechanism. The Fe3O4/mica interlayer interaction induces two preferred antiparallel orientations, whereas the interisland interaction of Fe3O4 breaks the energy degeneracy of antiparallel orientations. The room-temperature long-range ferrimagnetic order and thickness-tunable magnetic domain evolution are uncovered in atomically thin Fe3O4. This strategy to tune the orientations of nanosheets through the an interisland interaction can guide the synthesis of other 2D transition-metal oxides, thereby laying a solid foundation for future spintronic device applications at the integration level.

BMI trajectories in late middle age, genetic risk, and the incident diabetes in older adults: evidence from a 26-year longitudinal study.

This study investigated the association between BMI trajectories in late middle age and incident diabetes in later years. A total of 11,441 participants aged 50-60 years from the Health and Retirement Study with at least two self-reported BMI records were included. Individual BMI trajectories representing average BMI changes per year were generated using multilevel modeling. Adjusted risk ratios (ARRs) and 95% confidence intervals (95% CIs) were calculated. Associations between BMI trajectories and diabetes risk in participants with different genetic risks were estimated for 5720 participants of European ancestry. BMI trajectories were significantly associated with diabetes risk in older age (slowly increasing vs. stable: ARR 1.31, 95% CI 1.12-1.54; rapidly increasing vs. stable: ARR 1.5, 95% CI 1.25-1.79). This association was strongest for normal-initial-BMI participants (slowly increasing: ARR 1.34, 95% CI 0.96-1.88; rapidly increasing: ARR 2.06, 95% CI 1.37-3.11). Participants with a higher genetic liability to diabetes and a rapidly increasing BMI trajectory had the highest risk for diabetes (ARR 2.15, 95% CI 1.67-2.76). These findings confirmed that BMI is the leading risk factor for diabetes and that although the normal BMI group has the lowest incidence rate for diabetes, people with normal BMI are most sensitive to changes in BMI.

Predicting human microbe-disease associations via graph attention networks with inductive matrix completion.

MOTIVATION: human microbes play a critical role in an extensive range of complex human diseases and become a new target in precision medicine. In silico methods of identifying microbe-disease associations not only can provide a deep insight into understanding the pathogenic mechanism of complex human diseases but also assist pharmacologists to screen candidate targets for drug development. However, the majority of existing approaches are based on linear models or label propagation, which suffers from limitations in capturing nonlinear associations between microbes and diseases. Besides, it is still a great challenge for most previous methods to make predictions for new diseases (or new microbes) with few or without any observed associations. RESULTS: in this work, we construct features for microbes and diseases by fully exploiting multiply sources of biomedical data, and then propose a novel deep learning framework of graph attention networks with inductive matrix completion for human microbe-disease association prediction, named GATMDA. To our knowledge, this is the first attempt to leverage graph attention networks for this important task. In particular, we develop an optimized graph attention network with talking-heads to learn representations for nodes (i.e. microbes and diseases). To focus on more important neighbours and filter out noises, we further design a bi-interaction aggregator to enforce representation aggregation of similar neighbours. In addition, we combine inductive matrix completion to reconstruct microbe-disease associations to capture the complicated associations between diseases and microbes. Comprehensive experiments on two data sets (i.e. HMDAD and Disbiome) demonstrated that our proposed model consistently outperformed baseline methods. Case studies on two diseases, i.e. asthma and inflammatory bowel disease, further confirmed the effectiveness of our proposed model of GATMDA. AVAILABILITY: python codes and data set are available at: https://github.com/yahuilong/GATMDA. CONTACT: luojiawei@hnu.edu.cn.

SG-LSTM-FRAME: a computational frame using sequence and geometrical information via LSTM to predict miRNA-gene associations.

MOTIVATION: MircroRNAs (miRNAs) regulate target genes and are responsible for lethal diseases such as cancers. Accurately recognizing and identifying miRNA and gene pairs could be helpful in deciphering the mechanism by which miRNA affects and regulates the development of cancers. Embedding methods and deep learning methods have shown their excellent performance in traditional classification tasks in many scenarios. But not so many attempts have adapted and merged these two methods into miRNA-gene relationship prediction. Hence, we proposed a novel computational framework. We first generated representational features for miRNAs and genes using both sequence and geometrical information and then leveraged a deep learning method for the associations' prediction. RESULTS: We used long short-term memory (LSTM) to predict potential relationships and proved that our method outperformed other state-of-the-art methods. Results showed that our framework SG-LSTM got an area under curve of 0.94 and was superior to other methods. In the case study, we predicted the top 10 miRNA-gene relationships and recommended the top 10 potential genes for hsa-miR-335-5p for SG-LSTM-core. We also tested our model using a larger dataset, from which 14 668 698 miRNA-gene pairs were predicted. The top 10 unknown pairs were also listed. AVAILABILITY: Our work can be download in https://github.com/Xshelton/SG_LSTM. CONTACT: luojiawei@hnu.edu.cn. SUPPLEMENTARY INFORMATION: Supplementary data are available at Briefings in Bioinformatics online.

Multi-view Multichannel Attention Graph Convolutional Network for miRNA-disease association prediction.

MOTIVATION: In recent years, a growing number of studies have proved that microRNAs (miRNAs) play significant roles in the development of human complex diseases. Discovering the associations between miRNAs and diseases has become an important part of the discovery and treatment of disease. Since uncovering associations via traditional experimental methods is complicated and time-consuming, many computational methods have been proposed to identify the potential associations. However, there are still challenges in accurately determining potential associations between miRNA and disease by using multisource data. RESULTS: In this study, we develop a Multi-view Multichannel Attention Graph Convolutional Network (MMGCN) to predict potential miRNA-disease associations. Different from simple multisource information integration, MMGCN employs GCN encoder to obtain the features of miRNA and disease in different similarity views, respectively. Moreover, our MMGCN can enhance the learned latent representations for association prediction by utilizing multichannel attention, which adaptively learns the importance of different features. Empirical results on two datasets demonstrate that MMGCN model can achieve superior performance compared with nine state-of-the-art methods on most of the metrics. Furthermore, we prove the effectiveness of multichannel attention mechanism and the validity of multisource data in miRNA and disease association prediction. Case studies also indicate the ability of the method for discovering new associations.

Adaptive multi-source multi-view latent feature learning for inferring potential disease-associated miRNAs.

Accumulating evidence has shown that microRNAs (miRNAs) play crucial roles in different biological processes, and their mutations and dysregulations have been proved to contribute to tumorigenesis. In silico identification of disease-associated miRNAs is a cost-effective strategy to discover those most promising biomarkers for disease diagnosis and treatment. The increasing available omics data sources provide unprecedented opportunities to decipher the underlying relationships between miRNAs and diseases by computational models. However, most existing methods are biased towards a single representation of miRNAs or diseases and are also not capable of discovering unobserved associations for new miRNAs or diseases without association information. In this study, we present a novel computational method with adaptive multi-source multi-view latent feature learning (M2LFL) to infer potential disease-associated miRNAs. First, we adopt multiple data sources to obtain similarity profiles and capture different latent features according to the geometric characteristic of miRNA and disease spaces. Then, the multi-modal latent features are projected to a common subspace to discover unobserved miRNA-disease associations in both miRNA and disease views, and an adaptive joint graph regularization term is developed to preserve the intrinsic manifold structures of multiple similarity profiles. Meanwhile, the Lp,q-norms are imposed into the projection matrices to ensure the sparsity and improve interpretability. The experimental results confirm the superior performance of our proposed method in screening reliable candidate disease miRNAs, which suggests that M2LFL could be an efficient tool to discover diagnostic biomarkers for guiding laborious clinical trials.

NSL2CD: identifying potential circRNA-disease associations based on network embedding and subspace learning.

Many studies have evidenced that circular RNAs (circRNAs) are important regulators in various pathological processes and play vital roles in many human diseases, which could serve as promising biomarkers for disease diagnosis, treatment and prognosis. However, the functions of most of circRNAs remain to be unraveled, and it is time-consuming and costly to uncover those relationships between circRNAs and diseases by conventional experimental methods. Thus, identifying candidate circRNAs for human diseases offers new opportunities to understand the functional properties of circRNAs and the pathogenesis of diseases. In this study, we propose a novel network embedding-based adaptive subspace learning method (NSL2CD) for predicting potential circRNA-disease associations and discovering those disease-related circRNA candidates. The proposed method first calculates disease similarities and circRNA similarities by fully utilizing different data sources and learns low-dimensional node representations with network embedding methods. Then, we adopt an adaptive subspace learning model to discover potential associations between circRNAs and diseases. Meanwhile, an integrated weighted graph regularization term is imposed to preserve local geometric structures of data spaces, and L1,2-norm constraint is also incorporated into the model to realize the smoothness and sparsity of projection matrices. The experiment results show that NSL2CD achieves comparable performance under different evaluation metrics, and case studies further confirm its ability to discover potential candidate circRNAs for human diseases.

scSemiGAN: a single-cell semi-supervised annotation and dimensionality reduction framework based on generative adversarial network.

MOTIVATION: Cell-type annotation plays a crucial role in single-cell RNA-seq (scRNA-seq) data analysis. As more and more well-annotated scRNA-seq reference data are publicly available, automatical label transference algorithms are gaining popularity over manual marker gene-based annotation methods. However, most existing methods fail to unify cell-type annotation with dimensionality reduction and are unable to generate deep latent representation from the perspective of data generation. RESULTS: In this article, we propose scSemiGAN, a single-cell semi-supervised cell-type annotation and dimensionality reduction framework based on a generative adversarial network, to overcome these challenges, modeling scRNA-seq data from the aspect of data generation. Our proposed scSemiGAN is capable of performing deep latent representation learning and cell-type label prediction simultaneously. Through extensive comparison with four state-of-the-art annotation methods on diverse simulated and real scRNA-seq datasets, scSemiGAN achieves competitive or superior performance in multiple downstream tasks including cell-type annotation, latent representation visualization, confounding factor removal and enrichment analysis. AVAILABILITY AND IMPLEMENTATION: The code and data of scSemiGAN are available on GitHub: https://github.com/rafa-nadal/scSemiGAN. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Pre-training graph neural networks for link prediction in biomedical networks.

MOTIVATION: Graphs or networks are widely utilized to model the interactions between different entities (e.g. proteins, drugs, etc.) for biomedical applications. Predicting potential interactions/links in biomedical networks is important for understanding the pathological mechanisms of various complex human diseases, as well as screening compound targets for drug discovery. Graph neural networks (GNNs) have been utilized for link prediction in various biomedical networks, which rely on the node features extracted from different data sources, e.g. sequence, structure and network data. However, it is challenging to effectively integrate these data sources and automatically extract features for different link prediction tasks. RESULTS: In this article, we propose a novel Pre-Training Graph Neural Networks-based framework named PT-GNN to integrate different data sources for link prediction in biomedical networks. First, we design expressive deep learning methods [e.g. convolutional neural network and graph convolutional network (GCN)] to learn features for individual nodes from sequence and structure data. Second, we further propose a GCN-based encoder to effectively refine the node features by modelling the dependencies among nodes in the network. Third, the node features are pre-trained based on graph reconstruction tasks. The pre-trained features can be used for model initialization in downstream tasks. Extensive experiments have been conducted on two critical link prediction tasks, i.e. synthetic lethality (SL) prediction and drug-target interaction (DTI) prediction. Experimental results demonstrate PT-GNN outperforms the state-of-the-art methods for SL prediction and DTI prediction. In addition, the pre-trained features benefit improving the performance and reduce the training time of existing models. AVAILABILITY AND IMPLEMENTATION: Python codes and dataset are available at: https://github.com/longyahui/PT-GNN. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Optical focusing inside scattering media with iterative time-reversed ultrasonically encoded near-infrared light.

Focusing light inside scattering media is a long-sought goal in optics. Time-reversed ultrasonically encoded (TRUE) focusing, which combines the advantages of biological transparency of the ultrasound and the high efficiency of digital optical phase conjugation (DOPC) based wavefront shaping, has been proposed to tackle this problem. By invoking repeated acousto-optic interactions, iterative TRUE (iTRUE) focusing can further break the resolution barrier imposed by the acoustic diffraction limit, showing great potential for deep-tissue biomedical applications. However, stringent requirements on system alignment prohibit the practical use of iTRUE focusing, especially for biomedical applications at the near-infrared spectral window. In this work, we fill this blank by developing an alignment protocol that is suitable for iTRUE focusing with a near-infrared light source. This protocol mainly contains three steps, including rough alignment with manual adjustment, fine-tuning with a high-precision motorized stage, and digital compensation through Zernike polynomials. Using this protocol, an optical focus with a peak-to-background ratio (PBR) of up to 70% of the theoretical value can be achieved. By using a 5-MHz ultrasonic transducer, we demonstrated the first iTRUE focusing using near-infrared light at 1053 nm, enabling the formation of an optical focus inside a scattering medium composed of stacked scattering films and a mirror. Quantitatively, the size of the focus decreased from roughly 1 mm to 160 µm within a few consecutive iterations and a PBR up to 70 was finally achieved. We anticipate that the capability of focusing near-infrared light inside scattering media, along with the reported alignment protocol, can be beneficial to a variety of applications in biomedical optics.