A systems-biology approach connects aging mechanisms with Alzheimer's disease pathogenesis.

Age is the strongest risk factor for developing Alzheimer's disease, the most common neurodegenerative disorder. However, the mechanisms connecting advancing age to neurodegeneration in Alzheimer's disease are incompletely understood. We conducted an unbiased, genome-scale, forward genetic screen for age-associated neurodegeneration in Drosophila to identify the underlying biological processes required for maintenance of aging neurons. To connect genetic screen hits to Alzheimer's disease pathways, we measured proteomics, phosphoproteomics, and metabolomics in Drosophila models of Alzheimer's disease. We further identified Alzheimer's disease human genetic variants that modify expression in disease-vulnerable neurons. Through multi-omic, multi-species network integration of these data, we identified relationships between screen hits and tau-mediated neurotoxicity. Furthermore, we computationally and experimentally identified relationships between screen hits and DNA damage in Drosophila and human iPSC-derived neural progenitor cells. Our work identifies candidate pathways that could be targeted to attenuate the effects of age on neurodegeneration and Alzheimer's disease.

Whole-genome DNA methylation profiling of intrahepatic cholangiocarcinoma reveals prognostic subtypes with distinct biological drivers.

Intrahepatic cholangiocarcinoma (iCCA) is the second most prevalent primary liver cancer. While the genetic characterization of iCCA has led to targeted therapies for treating tumors with FGFR2 alterations and IDH1/2 mutations, only a limited number of patients can benefit from these strategies. Epigenomic profiles have emerged as potential diagnostic and prognostic biomarkers for improving treatment of cancers. In this study, we conducted whole-genome bisulfite sequencing on 331 iCCAs integrated with genetic, transcriptomic, and proteomic analyses, demonstrating the existence of four DNA methylation subtypes of iCCAs (S1-S4) that exhibited unique post-operative clinical outcomes. The S1 group was an IDH1/2-mutation-specific subtype with moderate survival. The S2 subtype was characterized by the lowest methylation level and the highest mutational burden among the four subtypes and displayed upregulation of a gene expression pattern associated with cell cycle/DNA replication. The S3 group was distinguished by high inter-patient heterogeneity of tumor immunity, a gene expression pattern associated with carbohydrate metabolism, and an enrichment of KRAS alterations. Patients with the S2 and S3 subtypes had the shortest survival among the four subtypes. Tumors in the S4 subtype, which had the best prognosis, showed global methylation levels comparable to normal controls, increased FGFR2 fusions/BAP1 mutations, and the highest copy number variant burdens. Further integrative and functional analyses identified GBP4 demethylation, which is highly prevalent in the S2 and S3 groups, as an epigenetic oncogenic factor that regulates iCCA proliferation, migration, and invasion. Together, this study identifies prognostic methylome alterations and epigenetic drivers in iCCA.

postGWAS: A web server for deciphering the causality post the genome-wide association studies.

While genome-wide association studies (GWAS) have unequivocally identified vast disease susceptibility variants, a majority of them are situated in non-coding regions and are in high linkage disequilibrium (LD). To pave the way of translating GWAS signals to clinical drug targets, it is essential to identify the underlying causal variants and further causal genes. To this end, a myriad of post-GWAS methods have been devised, each grounded in distinct principles including fine-mapping, co-localization, and transcriptome-wide association study (TWAS) techniques. Yet, no platform currently exists that seamlessly integrates these diverse post-GWAS methodologies. In this work, we present a user-friendly web server for post-GWAS analysis, that seamlessly integrates 9 distinct methods with 12 models, categorized by fine-mapping, colocalization, and TWAS. The server mainly helps users decipher the causality hindered by complex GWAS signals, including casual variants and casual genes, without the burden of computational skills and complex environment configuration, and provides a convenient platform for post-GWAS analysis, result visualization, facilitating the understanding and interpretation of the genome-wide association studies. The postGWAS server is available at http://g2g.biographml.com/.

An improved hierarchical variational autoencoder for cell-cell communication estimation using single-cell RNA-seq data.

Analysis of cell-cell communication (CCC) in the tumor micro-environment helps decipher the underlying mechanism of cancer progression and drug tolerance. Currently, single-cell RNA-Seq data are available on a large scale, providing an unprecedented opportunity to predict cellular communications. There have been many achievements and applications in inferring cell-cell communication based on the known interactions between molecules, such as ligands, receptors and extracellular matrix. However, the prior information is not quite adequate and only involves a fraction of cellular communications, producing many false-positive or false-negative results. To this end, we propose an improved hierarchical variational autoencoder (HiVAE) based model to fully use single-cell RNA-seq data for automatically estimating CCC. Specifically, the HiVAE model is used to learn the potential representation of cells on known ligand-receptor genes and all genes in single-cell RNA-seq data, respectively, which are then utilized for cascade integration. Subsequently, transfer entropy is employed to measure the transmission of information flow between two cells based on the learned representations, which are regarded as directed communication relationships. Experiments are conducted on single-cell RNA-seq data of the human skin disease dataset and the melanoma dataset, respectively. Results show that the HiVAE model is effective in learning cell representations, and transfer entropy could be used to estimate the communication scores between cell types.

Machine Learning in Bioelectrocatalysis.

At present, the global energy crisis and environmental pollution coexist, and the demand for sustainable clean energy has been highly concerned. Bioelectrocatalysis that combines the benefits of biocatalysis and electrocatalysis produces high-value chemicals, clean biofuel, and biodegradable new materials. It has been applied in biosensors, biofuel cells, and bioelectrosynthesis. However, there are certain flaws in the application process of bioelectrocatalysis, such as low accuracy/efficiency, poor stability, and limited experimental conditions. These issues can possibly be solved using machine learning (ML) in recent reports although the combination of them is still not mature. To summarize the progress of ML in bioelectrocatalysis, this paper first introduces the modeling process of ML, then focuses on the reports of ML in bioelectrocatalysis, and ultimately makes a summary and outlook about current issues and future directions. It is believed that there is plenty of scope for this interdisciplinary research direction.

Predicting cell-type specific disease genes of diabetes with the biological network.

Type 2 diabetes (T2D) is a chronic condition that can lead to significant harm, such as heart disease, kidney disease, nerve damage, and blindness. Although T2D-related genes have been identified through Genome-wide association studies (GWAS) and various computational methods, the biological mechanism of T2D at the cell type level remains unclear. Exploring cell type-specific genes related to T2D is essential to understand the cellular mechanisms underlying the disease. To address this issue, we introduce DiGCellNet (predicting Disease Genes with Cell type specificity based on biological Networks), a model that integrates graph convolutional network (GCN) and multi-task learning (MTL) to predict T2D-associated cell type-specific genes based on the biological network. Our work represents the first attempt to predict cell type-specific disease genes using GCN and MTL. We evaluate our approach by predicting genes specific to four cell types and demonstrate that the proposed DiGCellNet outperforms other models that combine node embeddings with traditional machine learning algorithms. Moreover, DiGCellNet successfully identifies CALM1 as a gene specific to beta cell type in T2D cases, and this association is confirmed using an independent dataset. The code is available at https://github.com/23AIBox/23AIBox-DiGCellNet.

scMultiGAN: cell-specific imputation for single-cell transcriptomes with multiple deep generative adversarial networks.

The emergence of single-cell RNA sequencing (scRNA-seq) technology has revolutionized the identification of cell types and the study of cellular states at a single-cell level. Despite its significant potential, scRNA-seq data analysis is plagued by the issue of missing values. Many existing imputation methods rely on simplistic data distribution assumptions while ignoring the intrinsic gene expression distribution specific to cells. This work presents a novel deep-learning model, named scMultiGAN, for scRNA-seq imputation, which utilizes multiple collaborative generative adversarial networks (GAN). Unlike traditional GAN-based imputation methods that generate missing values based on random noises, scMultiGAN employs a two-stage training process and utilizes multiple GANs to achieve cell-specific imputation. Experimental results show the efficacy of scMultiGAN in imputation accuracy, cell clustering, differential gene expression analysis and trajectory analysis, significantly outperforming existing state-of-the-art techniques. Additionally, scMultiGAN is scalable to large scRNA-seq datasets and consistently performs well across sequencing platforms. The scMultiGAN code is freely available at https://github.com/Galaxy8172/scMultiGAN.

Construction of PANoptosis signature: Novel target discovery for prostate cancer immunotherapy.

PANoptosis pathway gene sets encompassing pyroptosis, apoptosis, and necroptosis were identified from the MSigDB database. We analyzed the perturbations and crosstalk in the PANoptosis pathway in prostate adenocarcinoma (PRAD), including gene mutation, transcription, methylation, and clinical features. By constructing a PANoptosis signature, we accurately predicted the prognosis and immunotherapeutic response of PRAD patients. We further explored the molecular features and immunological roles of the signature, dividing patients into high- and low-score groups. Notably, the high-score group correlated with better survival outcomes and immunotherapeutic responses, as well as a higher mutation frequency and enrichment score in the PANoptosis and HALLMARK pathways. The PANoptosis signature also enhanced overall antitumor immunity, promoted immune cell infiltration, upregulated immune checkpoint regulators, and revealed the cold tumor characteristics of PRAD. We also identified potential drug targets based on the PANoptosis signature. These findings lead the way in identifying novel prognostic markers and therapeutic targets for patients with PRAD.

Collaborative deep learning improves disease-related circRNA prediction based on multi-source functional information.

Emerging studies have shown that circular RNAs (circRNAs) are involved in a variety of biological processes and play a key role in disease diagnosing, treating and inferring. Although many methods, including traditional machine learning and deep learning, have been developed to predict associations between circRNAs and diseases, the biological function of circRNAs has not been fully exploited. Some methods have explored disease-related circRNAs based on different views, but how to efficiently use the multi-view data about circRNA is still not well studied. Therefore, we propose a computational model to predict potential circRNA-disease associations based on collaborative learning with circRNA multi-view functional annotations. First, we extract circRNA multi-view functional annotations and build circRNA association networks, respectively, to enable effective network fusion. Then, a collaborative deep learning framework for multi-view information is designed to get circRNA multi-source information features, which can make full use of the internal relationship among circRNA multi-view information. We build a network consisting of circRNAs and diseases by their functional similarity and extract the consistency description information of circRNAs and diseases. Last, we predict potential associations between circRNAs and diseases based on graph auto encoder. Our computational model has better performance in predicting candidate disease-related circRNAs than the existing ones. Furthermore, it shows the high practicability of the method that we use several common diseases as case studies to find some unknown circRNAs related to them. The experiments show that CLCDA can efficiently predict disease-related circRNAs and are helpful for the diagnosis and treatment of human disease.

A benchmark for automatic medical consultation system: frameworks, tasks and datasets.

MOTIVATION: In recent years, interest has arisen in using machine learning to improve the efficiency of automatic medical consultation and enhance patient experience. In this article, we propose two frameworks to support automatic medical consultation, namely doctor-patient dialogue understanding and task-oriented interaction. We create a new large medical dialogue dataset with multi-level fine-grained annotations and establish five independent tasks, including named entity recognition, dialogue act classification, symptom label inference, medical report generation and diagnosis-oriented dialogue policy. RESULTS: We report a set of benchmark results for each task, which shows the usability of the dataset and sets a baseline for future studies. AVAILABILITY AND IMPLEMENTATION: Both code and data are available from https://github.com/lemuria-wchen/imcs21. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

DxFormer: a decoupled automatic diagnostic system based on decoder-encoder transformer with dense symptom representations.

MOTIVATION: Symptom-based automatic diagnostic system queries the patient's potential symptoms through continuous interaction with the patient and makes predictions about possible diseases. A few studies use reinforcement learning (RL) to learn the optimal policy from the joint action space of symptoms and diseases. However, existing RL (or Non-RL) methods focus on disease diagnosis while ignoring the importance of symptom inquiry. Although these systems have achieved considerable diagnostic accuracy, they are still far below its performance upper bound due to few turns of interaction with patients and insufficient performance of symptom inquiry. To address this problem, we propose a new automatic diagnostic framework called DxFormer, which decouples symptom inquiry and disease diagnosis, so that these two modules can be independently optimized. The transition from symptom inquiry to disease diagnosis is parametrically determined by the stopping criteria. In DxFormer, we treat each symptom as a token, and formalize the symptom inquiry and disease diagnosis to a language generation model and a sequence classification model, respectively. We use the inverted version of Transformer, i.e. the decoder-encoder structure, to learn the representation of symptoms by jointly optimizing the reinforce reward and cross-entropy loss. RESULTS: We conduct experiments on three real-world medical dialogue datasets, and the experimental results verify the feasibility of increasing diagnostic accuracy by improving symptom recall. Our model overcomes the shortcomings of previous RL-based methods. By decoupling symptom query from the process of diagnosis, DxFormer greatly improves the symptom recall and achieves the state-of-the-art diagnostic accuracy. AVAILABILITY AND IMPLEMENTATION: Both code and data are available at https://github.com/lemuria-wchen/DxFormer. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

DFinder: a novel end-to-end graph embedding-based method to identify drug-food interactions.

MOTIVATION: Drug-food interactions (DFIs) occur when some constituents of food affect the bioaccessibility or efficacy of the drug by involving in drug pharmacodynamic and/or pharmacokinetic processes. Many computational methods have achieved remarkable results in link prediction tasks between biological entities, which show the potential of computational methods in discovering novel DFIs. However, there are few computational approaches that pay attention to DFI identification. This is mainly due to the lack of DFI data. In addition, food is generally made up of a variety of chemical substances. The complexity of food makes it difficult to generate accurate feature representations for food. Therefore, it is urgent to develop effective computational approaches for learning the food feature representation and predicting DFIs. RESULTS: In this article, we first collect DFI data from DrugBank and PubMed, respectively, to construct two datasets, named DrugBank-DFI and PubMed-DFI. Based on these two datasets, two DFI networks are constructed. Then, we propose a novel end-to-end graph embedding-based method named DFinder to identify DFIs. DFinder combines node attribute features and topological structure features to learn the representations of drugs and food constituents. In topology space, we adopt a simplified graph convolution network-based method to learn the topological structure features. In feature space, we use a deep neural network to extract attribute features from the original node attributes. The evaluation results indicate that DFinder performs better than other baseline methods. AVAILABILITY AND IMPLEMENTATION: The source code is available at https://github.com/23AIBox/23AIBox-DFinder. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Predicting drug-target binding affinity with cross-scale graph contrastive learning.

Identifying the binding affinity between a drug and its target is essential in drug discovery and repurposing. Numerous computational approaches have been proposed for understanding these interactions. However, most existing methods only utilize either the molecular structure information of drugs and targets or the interaction information of drug-target bipartite networks. They may fail to combine the molecule-scale and network-scale features to obtain high-quality representations. In this study, we propose CSCo-DTA, a novel cross-scale graph contrastive learning approach for drug-target binding affinity prediction. The proposed model combines features learned from the molecular scale and the network scale to capture information from both local and global perspectives. We conducted experiments on two benchmark datasets, and the proposed model outperformed existing state-of-art methods. The ablation experiment demonstrated the significance and efficacy of multi-scale features and cross-scale contrastive learning modules in improving the prediction performance. Moreover, we applied the CSCo-DTA to predict the novel potential targets for Erlotinib and validated the predicted targets with the molecular docking analysis.

Anterior cervical discectomy and fusion without plate (ACDFWP) versus anterior cervical disc arthroplasty (ACDA) for cervical spondylosis: A meta-analysis and literature review.

This meta-analysis compared the clinical outcomes between two alternative surgeries for patients with cervical spondylosis, namely anterior cervical discectomy and fusion (ACDF) without plate (ACDFWP) vs. anterior cervical disc arthroplasty (ACDA). We searched databases, including PubMed, EMBASE, Cochrane Library, Google Scholar, and Web of Science (firstly available-2019). A standard meta-analysis was performed with the included studies. A Risk of Bias in Non-randomized Studies of Interventions (ROBINS-I) tool was used for the evaluation of the study quality of nonrandomized-controlled trials (nRCTs), while a Risk of Bias (RoB) battery was used for randomized controlled trials (RCTs). Eight studies involving 640 patients were included. No significant difference was found in the indices of Neck Disability Index (NDI) score, Visual Analog Score (VAS), Japanese Orthopaedic Association (JOA) score, operative time, blood loss, Swallowing Quality of Life Score (SWAL-QL), and complications. Cervical alignment was significantly better in the ACDFWP than in ACDA (mean difference (MD) = -0.67, 95% confidence interval (CI) [-1.11, -0.23], P = 0.003, I 2 = 20%). Although the alternative ACDFWP was slightly superior in terms of the index of cervical alignment, the limited research on this subject present insufficient evidence. Further well-designed studies are warranted in the future.

A review and performance evaluation of clustering frameworks for single-cell Hi-C data.

The three-dimensional genome structure plays a key role in cellular function and gene regulation. Single-cell Hi-C (high-resolution chromosome conformation capture) technology can capture genome structure information at the cell level, which provides the opportunity to study how genome structure varies among different cell types. Recently, a few methods are well designed for single-cell Hi-C clustering. In this manuscript, we perform an in-depth benchmark study of available single-cell Hi-C data clustering methods to implement an evaluation system for multiple clustering frameworks based on both human and mouse datasets. We compare eight methods in terms of visualization and clustering performance. Performance is evaluated using four benchmark metrics including adjusted rand index, normalized mutual information, homogeneity and Fowlkes-Mallows index. Furthermore, we also evaluate the eight methods for the task of separating cells at different stages of the cell cycle based on single-cell Hi-C data.

Identifying Non-Math Students from Brain MRIs with an Ensemble Classifier Based on Subspace-Enhanced Contrastive Learning.

In current research processes, mathematical learning has significantly impacted the brain's plasticity and cognitive functions. While biochemical changes in brain have been investigated by magnetic resonance spectroscopy, our study attempts to identify non-math students by using magnetic resonance imaging scans (MRIs). The proposed method crops the left middle front gyrus (MFG) region from the MRI, resulting in a multi-instance classification problem. Then, subspace enhanced contrastive learning is employed on all instances to learn robust deep features, followed by an ensemble classifier based on multiple-layer-perceptron models for student identification. The experiments were conducted on 123 MRIs taken from 72 math students and 51 non-math students. The proposed method arrived at an accuracy of 73.7% for image classification and 91.8% for student classification. Results show the proposed workflow successfully identifies the students who lack mathematical education by using MRI data. This study provides insights into the impact of mathematical education on brain development from structural imaging.

Hierarchical reinforcement learning for automatic disease diagnosis.

MOTIVATION: Disease diagnosis-oriented dialog system models the interactive consultation procedure as the Markov decision process, and reinforcement learning algorithms are used to solve the problem. Existing approaches usually employ a flat policy structure that treat all symptoms and diseases equally for action making. This strategy works well in a simple scenario when the action space is small; however, its efficiency will be challenged in the real environment. Inspired by the offline consultation process, we propose to integrate a hierarchical policy structure of two levels into the dialog system for policy learning. The high-level policy consists of a master model that is responsible for triggering a low-level model, the low-level policy consists of several symptom checkers and a disease classifier. The proposed policy structure is capable to deal with diagnosis problem including large number of diseases and symptoms. RESULTS: Experimental results on three real-world datasets and a synthetic dataset demonstrate that our hierarchical framework achieves higher accuracy and symptom recall in disease diagnosis compared with existing systems. We construct a benchmark including datasets and implementation of existing algorithms to encourage follow-up researches. AVAILABILITY AND IMPLEMENTATION: The code and data are available from https://github.com/FudanDISC/DISCOpen-MedBox-DialoDiagnosis. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.