m6Aexpress-enet: Predicting the regulatory expression m6A sites by an enet-regularization negative binomial regression model.

As the most abundant mRNA modification, m6A controls and influences many aspects of mRNA metabolism including the mRNA stability and degradation. However, the role of specific m6A sites in regulating gene expression still remains unclear. In additional, the multicollinearity problem caused by the correlation of methylation level of multiple m6A sites in each gene could influence the prediction performance. To address the above challenges, we propose an elastic-net regularized negative binomial regression model (called m6Aexpress-enet) to predict which m6A site could potentially regulate its gene expression. Comprehensive evaluations on simulated datasets demonstrate that m6Aexpress-enet could achieve the top prediction performance. Applying m6Aexpress-enet on real MeRIP-seq data from human lymphoblastoid cell lines, we have uncovered the complex regulatory pattern of predicted m6A sites and their unique enrichment pathway of the constructed co-methylation modules. m6Aexpress-enet proves itself as a powerful tool to enable biologists to discover the mechanism of m6A regulatory gene expression. Furthermore, the source code and the step-by-step implementation of m6Aexpress-enet is freely accessed at https://github.com/tengzhangs/m6Aexpress-enet.

Diagnosis of Alzheimer's disease by joining dual attention CNN and MLP based on structural MRIs, clinical and genetic data.

Alzheimer's disease (AD) is an irreversible central nervous degenerative disease, while mild cognitive impairment (MCI) is a precursor state of AD. Accurate early diagnosis of AD is conducive to the prevention and early intervention treatment of AD. Although some computational methods have been developed for AD diagnosis, most employ only neuroimaging, ignoring other data (e.g., genetic, clinical) that may have potential disease information. In addition, the results of some methods lack interpretability. In this work, we proposed a novel method (called DANMLP) of joining dual attention convolutional neural network (CNN) and multilayer perceptron (MLP) for computer-aided AD diagnosis by integrating multi-modality data of the structural magnetic resonance imaging (sMRI), clinical data (i.e., demographics, neuropsychology), and APOE genetic data. Our DANMLP consists of four primary components: (1) the Patch-CNN for extracting the image characteristics from each local patch, (2) the position self-attention block for capturing the dependencies between features within a patch, (3) the channel self-attention block for capturing dependencies of inter-patch features, (4) two MLP networks for extracting the clinical features and outputting the AD classification results, respectively. Compared with other state-of-the-art methods in the 5CV test, DANMLP achieves 93% and 82.4% classification accuracy for the AD vs. MCI and MCI vs. NC tasks on the ADNI database, which is 0.2%∼15.2% and 3.4%∼26.8% higher than that of other five methods, respectively. The individualized visualization of focal areas can also help clinicians in the early diagnosis of AD. These results indicate that DANMLP can be effectively used for diagnosing AD and MCI patients.

A novel cross-layer dual encoding-shared decoding network framework with spatial self-attention mechanism for hippocampus segmentation.

Accurate segmentation of the hippocampus from the brain magnetic resonance images (MRIs) is a crucial task in the neuroimaging research, since its structural integrity is strongly related to several neurodegenerative disorders, such as Alzheimer's disease (AD). Automatic segmentation of the hippocampus structures is challenging due to the small volume, complex shape, low contrast and discontinuous boundaries of hippocampus. Although some methods have been developed for the hippocampus segmentation, most of them paid too much attention to the hippocampus shape and volume instead of considering the spatial information. Additionally, the extracted features are independent of each other, ignoring the correlation between the global and local information. In view of this, here we proposed a novel cross-layer dual Encoding-Shared Decoding network framework with Spatial self-Attention mechanism (called ESDSA) for hippocampus segmentation in human brains. Considering that the hippocampus is a relatively small part in MRI, we introduced the spatial self-attention mechanism in ESDSA to capture the spatial information of hippocampus for improving the segmentation accuracy. We also designed a cross-layer dual encoding-shared decoding network to effectively extract the global information of MRIs and the spatial information of hippocampus. The spatial features of hippocampus and the features extracted from the MRIs were combined to realize the hippocampus segmentation. Results on the baseline T1-weighted structural MRI data show that the performance of our ESDSA is superior to other state-of-the-art methods, and the dice similarity coefficient of ESDSA achieves 89.37%. In addition, the dice similarity coefficient of the Spatial Self-Attention mechanism (SSA) strategy and the dual Encoding-Shared Decoding (ESD) strategy is 9.47%, 5.35% higher than that of the baseline U-net, respectively, indicating that the strategies of SSA and ESD can effectively enhance the segmentation accuracy of human brain hippocampus.

PhenoDriver: interpretable framework for studying personalized phenotype-associated driver genes in breast cancer.

Identifying personalized cancer driver genes and further revealing their oncogenic mechanisms is critical for understanding the mechanisms of cell transformation and aiding clinical diagnosis. Almost all existing methods primarily focus on identifying driver genes at the cohort or individual level but fail to further uncover their underlying oncogenic mechanisms. To fill this gap, we present an interpretable framework, PhenoDriver, to identify personalized cancer driver genes, elucidate their roles in cancer development and uncover the association between driver genes and clinical phenotypic alterations. By analyzing 988 breast cancer patients, we demonstrate the outstanding performance of PhenoDriver in identifying breast cancer driver genes at the cohort level compared to other state-of-the-art methods. Otherwise, our PhenoDriver can also effectively identify driver genes with both recurrent and rare mutations in individual patients. We further explore and reveal the oncogenic mechanisms of some known and unknown breast cancer driver genes (e.g. TP53, MAP3K1, HTT, etc.) identified by PhenoDriver, and construct their subnetworks for regulating clinical abnormal phenotypes. Notably, most of our findings are consistent with existing biological knowledge. Based on the personalized driver profiles, we discover two existing and one unreported breast cancer subtypes and uncover their molecular mechanisms. These results intensify our understanding for breast cancer mechanisms, guide therapeutic decisions and assist in the development of targeted anticancer therapies.

ncRPI-LGAT: Prediction of ncRNA-protein interactions with line graph attention network framework.

Identification of ncRNA-protein interactions (ncRPIs) through wet experiments is still time-consuming and highly-costly. Although several computational approaches have been developed to predict ncRPIs using the structure and sequence information of ncRNAs and proteins, the prediction accuracy needs to be improved, and the results lack interpretability. In this work, we proposed a novel computational method (called ncRPI-LGAT) to predict the ncRNA-Protein Interactions by transforming the link prediction (i.e., subgraph classification) task into a node classification task in the line network, and introducing a Line Graph ATtention network framework. ncRPI-LGAT first extracts the ncRNA/protein attributes using node2vec, and then generates the local enclosing subgraph of a target ncRNA-protein pair with SEAL. Because using the pooling operations in local enclosing subgraphs to learn a fixed-size feature vector for representing ncRNAs/proteins will cause the information loss, ncRPI-LGAT converts the local enclosing subgraphs into their corresponding line graphs, in which the node corresponds to the edge (i.e., ncRNA-protein pair) of the local enclosing subgraphs. Then, the attention mechanism-based graph neural network GATv2 is used on these line graphs to efficiently learn the embedding features of the target nodes (i.e., ncRNA-protein pairs) by focusing on learning the significance of one ncRNA-protein pair to another ncRNA-protein pair. These embedding features of one ncRNA-protein pair obtained from multi-head attention are concatenated in series and then fed them into a fully connected network to predict ncRPIs. Compared with other state-of-the-art methods in the 5CV test, ncRPI-LGAT shows superior performance on three benchmark datasets, demonstrating the effectiveness of our ncRPI-LGAT method in predicting ncRNA-protein interactions.

Few-Shot Drug Synergy Prediction With a Prior-Guided Hypernetwork Architecture.

Predicting drug synergy is critical to tailoring feasible drug combination treatment regimens for cancer patients. However, most of the existing computational methods only focus on data-rich cell lines, and hardly work on data-poor cell lines. To this end, here we proposed a novel few-shot drug synergy prediction method (called HyperSynergy) for data-poor cell lines by designing a prior-guided Hypernetwork architecture, in which the meta-generative network based on the task embedding of each cell line generates cell line dependent parameters for the drug synergy prediction network. In HyperSynergy model, we designed a deep Bayesian variational inference model to infer the prior distribution over the task embedding to quickly update the task embedding with a few labeled drug synergy samples, and presented a three-stage learning strategy to train HyperSynergy for quickly updating the prior distribution by a few labeled drug synergy samples of each data-poor cell line. Moreover, we proved theoretically that HyperSynergy aims to maximize the lower bound of log-likelihood of the marginal distribution over each data-poor cell line. The experimental results show that our HyperSynergy outperforms other state-of-the-art methods not only on data-poor cell lines with a few samples (e.g., 10, 5, 0), but also on data-rich cell lines.

A novel heterophilic graph diffusion convolutional network for identifying cancer driver genes.

Identifying cancer driver genes plays a curial role in the development of precision oncology and cancer therapeutics. Although a plethora of methods have been developed to tackle this problem, the complex cancer mechanisms and intricate interactions between genes still make the identification of cancer driver genes challenging. In this work, we propose a novel machine learning method of heterophilic graph diffusion convolutional networks (called HGDCs) to boost cancer-driver gene identification. Specifically, HGDC first introduces graph diffusion to generate an auxiliary network for capturing the structurally similar nodes in a biomolecular network. Then, HGDC designs an improved message aggregation and propagation scheme to adapt to the heterophilic setting of biomolecular networks, alleviating the problem of driver gene features being smoothed by its neighboring dissimilar genes. Finally, HGDC uses a layer-wise attention classifier to predict the probability of one gene being a cancer driver gene. In the comparison experiments with other existing state-of-the-art methods, our HGDC achieves outstanding performance in identifying cancer driver genes. The experimental results demonstrate that HGDC not only effectively identifies well-known driver genes on different networks but also novel candidate cancer genes. Moreover, HGDC can effectively prioritize cancer driver genes for individual patients. Particularly, HGDC can identify patient-specific additional driver genes, which work together with the well-known driver genes to cooperatively promote tumorigenesis.

Defining the separation landscape of topological domains for decoding consensus domain organization of the 3D genome.

Topologically associating domains (TADs) have emerged as basic structural and functional units of genome organization and have been determined by many computational methods from Hi-C contact maps. However, the TADs obtained by different methods vary greatly, which makes the accurate determination of TADs a challenging issue and hinders subsequent biological analyses about their organization and functions. Obvious inconsistencies among the TADs identified by different methods indeed make the statistical and biological properties of TADs overly depend on the chosen method rather than on the data. To this end, we use the consensus structural information captured by these methods to define the TAD separation landscape for decoding the consensus domain organization of the 3D genome. We show that the TAD separation landscape could be used to compare domain boundaries across multiple cell types for discovering conserved and divergent topological structures, decipher three types of boundary regions with diverse biological features, and identify consensus TADs (ConsTADs). We illustrate that these analyses could deepen our understanding of the relationships between the topological domains and chromatin states, gene expression, and DNA replication timing.

A social theory-enhanced graph representation learning framework for multitask prediction of drug-drug interactions.

Current machine learning-based methods have achieved inspiring predictions in the scenarios of mono-type and multi-type drug-drug interactions (DDIs), but they all ignore enhancive and depressive pharmacological changes triggered by DDIs. In addition, these pharmacological changes are asymmetric since the roles of two drugs in an interaction are different. More importantly, these pharmacological changes imply significant topological patterns among DDIs. To address the above issues, we first leverage Balance theory and Status theory in social networks to reveal the topological patterns among directed pharmacological DDIs, which are modeled as a signed and directed network. Then, we design a novel graph representation learning model named SGRL-DDI (social theory-enhanced graph representation learning for DDI) to realize the multitask prediction of DDIs. SGRL-DDI model can capture the task-joint information by integrating relation graph convolutional networks with Balance and Status patterns. Moreover, we utilize task-specific deep neural networks to perform two tasks, including the prediction of enhancive/depressive DDIs and the prediction of directed DDIs. Based on DDI entries collected from DrugBank, the superiority of our model is demonstrated by the comparison with other state-of-the-art methods. Furthermore, the ablation study verifies that Balance and Status patterns help characterize directed pharmacological DDIs, and that the joint of two tasks provides better DDI representations than individual tasks. Last, we demonstrate the practical effectiveness of our model by a version-dependent test, where 88.47 and 81.38% DDI out of newly added entries provided by the latest release of DrugBank are validated in two predicting tasks respectively.

scHi-CSim: a flexible simulator that generates high-fidelity single-cell Hi-C data for benchmarking.

Single-cell Hi-C technology provides an unprecedented opportunity to reveal chromatin structure in individual cells. However, high sequencing cost impedes the generation of biological Hi-C data with high sequencing depths and multiple replicates for downstream analysis. Here, we developed a single-cell Hi-C simulator (scHi-CSim) that generates high-fidelity data for benchmarking. scHi-CSim merges neighboring cells to overcome the sparseness of data, samples interactions in distance-stratified chromosomes to maintain the heterogeneity of single cells, and estimates the empirical distribution of restriction fragments to generate simulated data. We demonstrated that scHi-CSim can generate high-fidelity data by comparing the performance of single-cell clustering and detection of chromosomal high-order structures with raw data. Furthermore, scHi-CSim is flexible to change sequencing depth and the number of simulated replicates. We showed that increasing sequencing depth could improve the accuracy of detecting topologically associating domains. We also used scHi-CSim to generate a series of simulated datasets with different sequencing depths to benchmark scHi-C clustering methods.

DGMP: Identifying Cancer Driver Genes by Jointing DGCN and MLP from Multi-omics Genomic Data.

Identification of cancer driver genes plays an important role in precision oncology research, which is helpful to understand cancer initiation and progression. However, most existing computational methods mainly used the protein-protein interaction (PPI) networks, or treated the directed gene regulatory networks (GRNs) as the undirected gene-gene association networks to identify the cancer driver genes, which will lose the unique structure regulatory information in the directed GRNs, and then affect the outcome of the cancer driver gene identification. Here, based on the multi-omics pan-cancer data (i.e., gene expression, mutation, copy number variation, and DNA methylation), we propose a novel method (called DGMP) to identify cancer driver genes by jointing directed graph convolutional network (DGCN) and multilayer perceptron (MLP). DGMP learns the multi-omics features of genes as well as the topological structure features in GRN with the DGCN model and uses MLP to weigh more on gene features for mitigating the bias toward the graph topological features in the DGCN learning process. The results on three GRNs show that DGMP outperforms other existing state-of-the-art methods. The ablation experimental results on the DawnNet network indicate that introducing MLP into DGCN can offset the performance degradation of DGCN, and jointing MLP and DGCN can effectively improve the performance of identifying cancer driver genes. DGMP can identify not only the highly mutated cancer driver genes but also the driver genes harboring other kinds of alterations (e.g., differential expression and aberrant DNA methylation) or genes involved in GRNs with other cancer genes. The source code of DGMP can be freely downloaded from https://github.com/NWPU-903PR/DGMP.

Prioritization of cancer driver gene with prize-collecting steiner tree by introducing an edge weighted strategy in the personalized gene interaction network.

BACKGROUND: Cancer is a heterogeneous disease in which tumor genes cooperate as well as adapt and evolve to the changing conditions for individual patients. It is a meaningful task to discover the personalized cancer driver genes that can provide diagnosis and target drug for individual patients. However, most of existing methods mainly ranks potential personalized cancer driver genes by considering the patient-specific nodes information on the gene/protein interaction network. These methods ignore the personalized edge weight information in gene interaction network, leading to false positive results. RESULTS: In this work, we presented a novel algorithm (called PDGPCS) to predict the Personalized cancer Driver Genes based on the Prize-Collecting Steiner tree model by considering the personalized edge weight information. PDGPCS first constructs the personalized weighted gene interaction network by integrating the personalized gene expression data and prior known gene/protein interaction network knowledge. Then the gene mutation data and pathway data are integrated to quantify the impact of each mutant gene on every dysregulated pathway with the prize-collecting Steiner tree model. Finally, according to the mutant gene's aggregated impact score on all dysregulated pathways, the mutant genes are ranked for prioritizing the personalized cancer driver genes. Experimental results on four TCGA cancer datasets show that PDGPCS has better performance than other personalized driver gene prediction methods. In addition, we verified that the personalized edge weight of gene interaction network can improve the prediction performance. CONCLUSIONS: PDGPCS can more accurately identify the personalized driver genes and takes a step further toward personalized medicine and treatment. The source code of PDGPCS can be freely downloaded from https://github.com/NWPU-903PR/PDGPCS .

m 6 Aexpress-BHM: predicting m6A regulation of gene expression in multiple-groups context by a Bayesian hierarchical mixture model.

As the most abundant RNA modification, N6-methyladenosine (m6A) plays an important role in various RNA activities including gene expression and translation. With the rapid application of MeRIP-seq technology, samples of multiple groups, such as the involved multiple viral/ bacterial infection or distinct cell differentiation stages, are extracted from same experimental unit. However, our current knowledge about how the dynamic m6A regulating gene expression and the role in certain biological processes (e.g. immune response in this complex context) is largely elusive due to lack of effective tools. To address this issue, we proposed a Bayesian hierarchical mixture model (called m6Aexpress-BHM) to predict m6A regulation of gene expression (m6A-reg-exp) in multiple groups of MeRIP-seq experiment with limited samples. Comprehensive evaluations of m6Aexpress-BHM on the simulated data demonstrate its high predicting precision and robustness. Applying m6Aexpress-BHM on three real-world datasets (i.e. Flaviviridae infection, infected time-points of bacteria and differentiation stages of dendritic cells), we predicted more m6A-reg-exp genes with positive regulatory mode that significantly participate in innate immune or adaptive immune pathways, revealing the underlying mechanism of the regulatory function of m6A during immune response. In addition, we also found that m6A may influence the expression of PD-1/PD-L1 via regulating its interacted genes. These results demonstrate the power of m6Aexpress-BHM, helping us understand the m6A regulatory function in immune system.

Prediction of Drug-Drug Interaction Using an Attention-Based Graph Neural Network on Drug Molecular Graphs.

The treatment of complex diseases by using multiple drugs has become popular. However, drug-drug interactions (DDI) may give rise to the risk of unanticipated adverse effects and even unknown toxicity. Therefore, for polypharmacy safety it is crucial to identify DDIs and explore their underlying mechanisms. The detection of DDI in the wet lab is expensive and time-consuming, due to the need for experimental research over a large volume of drug combinations. Although many computational methods have been developed to predict DDIs, most of these are incapable of predicting potential DDIs between drugs within the DDI network and new drugs from outside the DDI network. In addition, they are not designed to explore the underlying mechanisms of DDIs and lack interpretative capacity. Thus, here we propose a novel method of GNN-DDI to predict potential DDIs by constructing a five-layer graph attention network to identify k-hops low-dimensional feature representations for each drug from its chemical molecular graph, concatenating all identified features of each drug pair, and inputting them into a MLP predictor to obtain the final DDI prediction score. The experimental results demonstrate that our GNN-DDI is suitable for each of two DDI predicting scenarios, namely the potential DDIs among known drugs in the DDI network and those between drugs within the DDI network and new drugs from outside DDI network. The case study indicates that our method can explore the specific drug substructures that lead to the potential DDIs, which helps to improve interpretability and discover the underlying interaction mechanisms of drug pairs.

kngMap: Sensitive and Fast Mapping Algorithm for Noisy Long Reads Based on the K-Mer Neighborhood Graph.

With the rapid development of single molecular sequencing (SMS) technologies such as PacBio single-molecule real-time and Oxford Nanopore sequencing, the output read length is continuously increasing, which has dramatical potentials on cutting-edge genomic applications. Mapping these reads to a reference genome is often the most fundamental and computing-intensive step for downstream analysis. However, these long reads contain higher sequencing errors and could more frequently span the breakpoints of structural variants (SVs) than those of shorter reads, leading to many unaligned reads or reads that are partially aligned for most state-of-the-art mappers. As a result, these methods usually focus on producing local mapping results for the query read rather than obtaining the whole end-to-end alignment. We introduce kngMap, a novel k-mer neighborhood graph-based mapper that is specifically designed to align long noisy SMS reads to a reference sequence. By benchmarking exhaustive experiments on both simulated and real-life SMS datasets to assess the performance of kngMap with ten other popular SMS mapping tools (e.g., BLASR, BWA-MEM, and minimap2), we demonstrated that kngMap has higher sensitivity that can align more reads and bases to the reference genome; meanwhile, kngMap can produce consecutive alignments for the whole read and span different categories of SVs in the reads. kngMap is implemented in C++ and supports multi-threading; the source code of kngMap can be downloaded for free at: https://github.com/zhang134/kngMap for academic usage.

Detection of Alzheimer's disease using features of brain region-of-interest-based individual network constructed with the sMRI image.

Brain networks constructed with regions of interest (ROIs) from the structural magnetic resonance imaging (sMRI) image are widely investigated for detecting Alzheimer's disease (AD). However, the ROI is generally represented by spatial domain-based features, so attentions are hardly paid to constructing a brain network with the frequency domain-based feature. In order to accurately characterize the ROI in the frequency domain and then construct an individual network, in this study, a novel method, which can describe the ROI properly by directional subbands and capture correlations between those ROIs, is proposed to construct a shearlet subband energy feature-based individual network (SSBIN) for AD detection. Specifically, the SSBIN is constructed with 90 ROIs which are segmented from the pre-processed sMRI image based on the automated anatomical labeling atlas, the 90 ROIs are represented by directional subband-based energy feature vectors (SVs) formed by jointing energy features extracted from their directional subbands, and the weight values of the SSBIN are computed by Pearson's correlation coefficient (PCC). Subsequently, two network features are extracted from the SSBIN: the node feature vector (NV) is computed by averaging the 90 SVs; the low dimensional edge feature vector (LV) is obtained by kernel principal component analysis (KPCA). Following that the concatenation of NV and LV is used as a SSBIN-based feature for the sMRI image. Finally, we use support vector machine (SVM) with the radial basis function kernel as classifier to categorize 680 subjects selected from the AD Neuroimaging Initiative (ADNI) database. Experimental results validate that the ROI can be properly characterized by the NV, and correlations between ROIs captured by the LV play an important role in AD detection. Besides, a series of comparisons with four current state-of-the-art approaches demonstrate the higher AD detecting performance of the SSBIN method.

Prediction of the transcription factor binding sites with meta-learning.

With the accumulation of ChIP-seq data, convolution neural network (CNN)-based methods have been proposed for predicting transcription factor binding sites (TFBSs). However, biological experimental data are noisy, and are often treated as ground truth for both training and testing. Particularly, existing classification methods ignore the false positive and false negative which are caused by the error in the peak calling stage, and therefore, they can easily overfit to biased training data. It leads to inaccurate identification and inability to reveal the rules of governing protein-DNA binding. To address this issue, we proposed a meta learning-based CNN method (namely TFBS_MLCNN or MLCNN for short) for suppressing the influence of noisy labels data and accurately recognizing TFBSs from ChIP-seq data. Guided by a small amount of unbiased meta-data, MLCNN can adaptively learn an explicit weighting function from ChIP-seq data and update the parameter of classifier simultaneously. The weighting function overcomes the influence of biased training data on classifier by assigning a weight to each sample according to its training loss. The experimental results on 424 ChIP-seq datasets show that MLCNN not only outperforms other existing state-of-the-art CNN methods, but can also detect noisy samples which are given the small weights to suppress them. The suppression ability to the noisy samples can be revealed through the visualization of samples' weights. Several case studies demonstrate that MLCNN has superior performance to others.

m6Acancer-Net: Identification of m6A-mediated cancer driver genes from gene-site heterogeneous network.

N6-methyladenosine (m6A) is the most abundant eukaryotic modification internal mRNA, which plays the crucial roles in the occurrence and development of cancer. However, current knowledge about m6A-mediated functional circuit and key genes targeted by m6A methylation in cancer is mostly elusive. Thus, here we proposed a novel network-based approach (called m6Acancer-Net) to identify m6A-mediated driver genes and their associated network in specific type of cancer, such as acute myeloid leukemia. m6A-mediated cancer driver genes are defined as genes mediated by m6A methylation, significantly mutated, and functionally interacted in cancer. m6Acancer-Net identified the m6A-mediated cancer driver genes by combining gene functional interaction network with RNA methylation, gene expression and mutation information. A cancer-specific gene-site heterogeneous network was firstly constructed by connecting the m6A site co-methylation network with the functional interaction pruned gene co-expression network generated from large scale gene expression profile of specific cancer. Then, the functional m6A-mediated genes were identified by selecting the m6A regulators as seed genes to perform the random walk with restart algorithm on the gene-site heterogeneous network. Finally, m6A-mediated cancer driver gene subnetworks were constructed by performing the heat diffusion of mutation frequency for functional m6A-mediated genes in protein-protein interaction networks. The experimental results of m6Acancer-Net on the acute myeloid leukemia (AML) and glioblastoma multiforme (GBM) data from TCGA project show that the m6A-mediated caner driver genes identified by m6Acancer-Net are targeted by m6A regulators, and mediate significant cancer-related pathways. They play crucial roles in development and prognostic stratification of cancer. Moreover, 15 m6A-mediated cancer driver genes identified in AML are validated by literatures to mediate AML progress, and 14 m6A-mediated cancer driver genes identified in GBM are validated by literatures to participate in development of GBM. m6Acancer-Net is reliable to identify the functionally significant m6A-mediated driver genes in specific cancer, and it can effectively facilitate the understanding of regulatory and therapeutic mechanism of cancer driver genes in epitranscriptome layer.

deepMDDI: A deep graph convolutional network framework for multi-label prediction of drug-drug interactions.

It is crucial to identify DDIs and explore their underlying mechanism (e.g., DDIs types) for polypharmacy safety. However, the detection of DDIs in assays is still time-consuming and costly, due to the need for experimental search over a large space of drug combinations. Thus, many computational methods have been developed to predict DDIs, most of them focusing on whether a drug interacts with another or not. And a few deep learning-based methods address a more realistic screening task for identifying various DDI types, but they assume a DDI only triggers one pharmacological effect, while a DDI can trigger more types of pharmacological effects. Thus, here we proposed a novel end-to-end deep learning-based method (called deepMDDI) for the Multi-label prediction of Drug-Drug Interactions. deepMDDI contains an encoder derived from relational graph convolutional networks and a tensor-like decoder to uniformly model interactions. deepMDDI is not only efficient for DDI transductive prediction, but also inductive prediction. The experimental results show that our model is superior to other state-of-the-art deep learning-based methods. We also validated the power of deepMDDI in the DDIs multi-label prediction and found several new valid DDIs in the case study. In conclusion, deepMDDI is beneficial to uncover the mechanism and regularity of DDIs.

m6Aexpress-Reader: Prediction of m6A regulated expression genes by integrating m6A sites and reader binding information in specific- context.

N6-methyladenosine (m6A) is the most abundant form of mRNA modification and plays an important role in regulating gene expression. However, the mechanisms of m6A regulated gene expression in cell or condition specific, are still poorly understood. Even though, some methods are able to predict m6A regulated expression (m6A-reg-exp) genes in specific context, they don't introduce the m6A reader binding information, while this information can help to predict m6A-reg-exp genes and more clearly to explain the mechanisms of m6A-mediated gene expression process. Thus, by integrating m6A sites and reader binding information, we proposed a novel method (called m6Aexpress-Reader) to predict m6A-reg-exp genes from limited MeRIP-seq data in specific context. m6Aexpress-Reader adopts the reader binding signal strength to weight the posterior distribution of the estimated regulatory coefficients for enhancing the prediction power. By using m6Aexpress-Reader, we found the complex characteristic of m6A on gene expression regulation and the distinct regulated pattern of m6A-reg-exp genes with different reader binding. m6A readers, YTHDF2 or IGF2BP1/3 all play an important role in various cancers and the key cancer pathways. In addition, m6Aexpress-Reader reveals the distinct m6A regulated mode of reader targeted genes in cancer. m6Aexpress-Reader could be a useful tool for studying the m6A regulation on reader target genes in specific context and it can be freely accessible at: https://github.com/NWPU-903PR/m6AexpressReader.