Search

The identification of interactions between compounds and proteins plays an important role in network pharmacology and drug discovery. However, experimentally identifying compound-protein interactions (CPIs) is generally expensive and time-consuming, computational approaches are thus introduced. Among these, machine-learning based methods have achieved a considerable success. However, due to the nonlinear and imbalanced nature of biological data, many machine learning approaches have their own limitations. Recently, deep learning techniques show advantages over many state-of-the-art machine learning methods in some applications. In this study, we aim at improving the performance of CPI prediction based on deep learning, and propose a method called DL-CPI (the abbreviation of D eep L earning for C ompound- P rotein I nteractions prediction), which employs deep neural network (DNN) to effectively learn the representations of compound-protein pairs. Extensive experiments show that DL-CPI can learn useful features of compound-protein pairs by a layerwise abstraction, and thus achieves better prediction performance than existing methods on both balanced and imbalanced datasets. [ABSTRACT FROM AUTHOR]

Sea surface temperature (SST) plays an important role in various oceanic applications, including climate prediction, ocean environment monitoring and marine disaster warning. Although many approaches have been developed for predicting SST, most of them conduct the prediction only based on historical SST data. However, SST is essentially affected by many external factors, e.g. , the short-wave radiation from the sun and the long-wave radiation from the atmosphere and ground, which are ignored by existing approaches. In this work, we proposed a Multi-source Spatio-Temporal data fusion model (MUST) to fuse multi-source data, including SST data and external factors, to improve the accuracy of short-term SST prediction. Concretely, MUST first introduces Bicubic Convolutional Interpolation (BCI) to address the issue of inconsistent spatial resolutions of multi-source data, then employs the Spatio-Temporal Dilated ConvLSTM (ST-DC) to learn the spatio-temporal features of SST and external factors, and finally fuses the learned features from multi-source data to predict SST with a Cross Data Fusion (CDF) component. As validated on two real datasets, MUST achieves much better performance than existing SST prediction approaches. • Multiple sources of data improve the prediction of short-term SST. • A MUST model was proposed to predict the SST for future seven days. • A case study was conducted in the regions of Nino3.4 and East China Sea. • The proposed MUST model outperforms CNN, LeNet and ConvLSTM. [ABSTRACT FROM AUTHOR]

The high-throughput technologies have led to vast amounts of protein–protein interaction (PPI) data, and a number of approaches based on PPI networks have been proposed for protein function prediction. However, these approaches do not work well if annotated or labeled proteins are scarce in the networks. To address this issue, we propose an active learning based approach that uses graph-based centrality metrics to select proper candidates for labeling. We first cluster a PPI network by using the spectral clustering algorithm and select some informative candidates for labeling within each cluster according to a certain centrality metric, and then apply a collective classification algorithm to predict protein function based on these labeled proteins. Experiments over two real datasets demonstrate that the active learning based approach achieves a better prediction performance by choosing more informative proteins for labeling. Experimental results also validate that betweenness centrality is more effective than degree centrality and closeness centrality in most cases. [ABSTRACT FROM AUTHOR]

Nucleosome positioning plays an essential role in cellular processes by modulating accessibility of DNA to proteins. Many computational models have been developed to predict genome-wide nucleosome positions from DNA sequences. Comparative analysis of predicted and experimental nucleosome positioning maps facilitates understanding the regulatory mechanisms of transcription and DNA replication. Therefore, a comprehensive evaluation of existing computational methods is important and useful for biologists to choose appropriate ones in their research. In this article, we carried out a performance comparison among eight widely used computational methods on four species including yeast, fruitfly, mouse and human. In particular, we compared these methods on different regions of each species such as gene sequences, promoters and 5′UTR exons. The experimental results show that the performances of the two latest versions of the thermodynamic model are relatively steadier than the other four methods. Moreover, these methods are workable on four species, but their performances decrease gradually from yeast to human, indicating that the fundamental mechanism of nucleosome positioning is conserved through the evolution process, but more and more factors participate in the determination of nucleosome positions, which leads to sophisticated regulation mechanisms. [ABSTRACT FROM PUBLISHER]

Abstract: We propose a deterministic weighted scale-free small-world model for considering pseudofractal web with the co-evolution of topology and weight. Considering the fluctuations in traffic flow constitute a main reason for congestion of packet delivery and poor performance of communication networks, we suggest a recursive algorithm to generate the network, which restricts the traffic fluctuations on it effectively during the evolutionary process. We provide a relatively complete view of topological structure and weight dynamics characteristics of the networks such as weight and strength distribution, degree correlations, average clustering coefficient and degree-cluster correlations as well as the diameter. [Copyright &y& Elsevier]

Abstract: Many real systems possess accelerating statistics where the total number of edges grows faster than the network size. In this paper, we propose a simple weighted network model with accelerating growth. We derive analytical expressions for the evolutions and distributions for strength, degree, and weight, which are relevant to accelerating growth. We also find that accelerating growth determines the clustering coefficient of the networks. Interestingly, the distributions for strength, degree, and weight display a transition from scale-free to exponential form when the parameter with respect to accelerating growth increases from a small to large value. All the theoretical predictions are successfully contrasted with numerical simulations. [Copyright &y& Elsevier]

Abstract: Chinese is spoken by the largest number of people in the world, and it is regarded as one of the most important languages. In this paper, we explore the statistical properties of Chinese language networks (CLNs) within the framework of complex network theory. Based on one of the largest Chinese corpora, i.e. People’s Daily Corpus, we construct two networks (CLN1 and CLN2) from two different respects, with Chinese words as nodes. In CLN1, a link between two nodes exists if they appear next to each other in at least one sentence; in CLN2, a link represents that two nodes appear simultaneously in a sentence. We show that both networks exhibit small-world effect, scale-free structure, hierarchical organization and disassortative mixing. These results indicate that in many topological aspects Chinese language shapes complex networks with organizing principles similar to other previously studied language systems, which shows that different languages may have some common characteristics in their evolution processes. We believe that our research may shed some new light into the Chinese language and find some potentially significant implications. [Copyright &y& Elsevier]

Abstract: We propose a growing model which interpolates between one-dimensional regular lattice and small-world networks. The model undergoes an interesting phase transition from large to small worlds. We investigate the structural properties by both theoretical predictions and numerical simulations. Our growing model is a complementarity for the important static Watts–Strogatz network model. [Copyright &y& Elsevier]

Abstract: We propose an extended local-world evolving network model including a triad formation (TF) step. In the process of network evolution, random fluctuation in the number of new edges is involved. We derive analytical expressions for degree distribution, clustering coefficient and average path length. Our model can unify the generic properties of real-life networks: scale-free degree distribution, high clustering and small inter-node separation. Moreover, in our model, the clustering coefficient is tunable simply by changing the expected number of TF steps after a single local preferential attachment step. [Copyright &y& Elsevier]

Privacy preserving is a paramount concern in publishing datasets that contain sensitive information. Preventing privacy disclosure and providing useful information to legitimate users for data analyzing/mining are conflicting goals. Randomized response is a class of techniques that perturbs each sensitive value in a certain way, so that personal privacy is protected while the large-trend of the entire dataset is still recoverable. However, existing randomized response techniques do not allow to flexibly configure the level of privacy protection, support only a few types of aggregate queries, and cannot achieve the best answer accuracy from perturbed data. These drawbacks impair the effectiveness of those techniques. This paper proposes a general framework based on randomized response techniques, which has good flexibility and extensibility, and can improve the effectiveness of randomized response methods. Our approach is validated by extensive experiments and comparison with existing randomized response and generalization methods. • A general framework for data publication is proposed based on randomized response techniques, which, by utilizing matrix decomposition method and properties of Kronecker product, can reduce the computational complexity of reconstructing unbiased estimate answers from exponential correlation to linear correlation. • A general approach for constructing a recovery matrix from arbitrary perturbation matrix is proposed, which can minimize the variance of unbiased estimate answers. • Perturbation and reconstruction algorithms for boolean and categorical attributes are developed, which can be extended to numerical attributes. • Both theoretical analysis and experimental results are given, which validate the proposed approach. [ABSTRACT FROM AUTHOR]

Causal partitioning is an effective approach for causal discovery based on the divide-and-conquer strategy. Up to now, various heuristic methods based on conditional independence (CI) tests have been proposed for causal partitioning. However, most of these methods fail to achieve satisfactory partitioning without violating d-separation, leading to poor inference performance. In this work, we transform causal partitioning into an alternative problem that can be more easily solved. Concretely, we first construct a superstructure G of the true causal graph G T by performing a set of low-order CI tests on the observed data D. Then, we leverage point-line duality to obtain a graph G A adjoint to G. We show that the solution of minimizing edge-cut ratio on G A can lead to a valid causal partitioning with smaller causal-cut ratio on G and without violating d-separation. We design an efficient algorithm to solve this problem. Extensive experiments show that the proposed method can achieve significantly better causal partitioning without violating d-separation than the existing methods. The source code and data are available at https://github.com/hzsiat/CPA.

In the past decade, Artificial Intelligence (AI) driven drug design and discovery has been a hot research topic in the AI area, where an important branch is molecule generation by generative models, from GAN-based models and VAE-based models to the latest diffusion-based models. However, most existing models pursue mainly the basic properties like validity and uniqueness of the generated molecules, a few go further to explicitly optimize one single important molecular property (e.g., QED or PlogP), which makes most generated molecules little usefulness in practice. In this paper, we present a novel approach to generating molecules with desirable properties, which expands the diffusion model framework with multiple innovative designs. The novelty is two-fold. On the one hand, considering that the structures of molecules are complex and diverse, and molecular properties are usually determined by some substructures (e.g., pharmacophores), we propose to perform diffusion on two structural levels: molecules and molecular fragments respectively, with which a mixed Gaussian distribution is obtained for the reverse diffusion process. To get desirable molecular fragments, we develop a novel electronic effect based fragmentation method. On the other hand, we introduce two ways to explicitly optimize multiple molecular properties under the diffusion model framework. First, as potential drug molecules must be chemically valid, we optimize molecular validity by an energy-guidance function. Second, since potential drug molecules should be desirable in various properties, we employ a multi-objective mechanism to optimize multiple molecular properties simultaneously. Extensive experiments with two benchmark datasets QM9 and ZINC250k show that the molecules generated by our proposed method have better validity, uniqueness, novelty, Fr´echet ChemNet Distance (FCD), QED, and PlogP than those generated by current SOTA models. The Code of D2L-OMP is available at https://github.com/bz99bz/D2L-OMP.

The discovery of cancer biomarkers helps to advance medical diagnosis and plays an important role in biomedical applications. Most of the existing data-driven methods identify biomarkers by ranking-based strategies, which generally return a subset or superset of the actual biomarkers, while some other causal-wise feature selection methods are based on Markov Blanket (MB) learning, facing the challenges of high-dimensionality & low-sample. In this work, we propose a novel hybrid causal feature selection method (called CAFES) to support large-scale cancer biomarker discovery from real RNA-seq data. Concretely, CAFES first uses minimal-redundancy & maximal-relevance strategy for dimensionality reduction that returns a set of candidate features. CAFES then learns the causal skeleton w.r.t. those features by CI tests and further obtains an appropriate superset of the MB of the target variable. Finally, CAFES learns the causal structure of this superset by the DAG-GNN algorithm and then obtains the MB of the target variable, which can be treated as the cancer biomarkers. We conduct experiments to evaluate the proposed method on two real well-known RNA-seq datasets that covering both binary and multi-class cases. We compare our method CAFES with seven recent methods including Semi-HITON-MB, STMB, BAMB, FBED, LCS-FS, EEMB, and EAMB. The results show that CAFES can identify dozens of cancer biomarkers, and 1/6  ∼ 1/2 of the discovered biomarkers can be verified by existing works that they are really directly related to the corresponding disease. An advantage of CAFES is that its Recall is significantly higher than those of all the counterparts, indicating that the continuous optimization (DAG-GNN) with the returned causal skeleton after feature selection (that can be treated as a conditional independence-based constraint to the optimization problem) is effective in cancer biomarkers identification under high-dimensional and low-sample RNA-seq data. The source code of CAFES is available at https://github.com/Milkteaww/CFS.

Motivation: Molecular property prediction (MPP) is a fundamental but challenging task in the computer-aided drug discovery process. More and more recent works employ different graph-based models for MPP, which have achieved considerable progress in improving prediction performance. However, current models often ignore relationships between molecules, which could be also helpful for MPP., Results: For this sake, in this article we propose a graph structure learning (GSL) based MPP approach, called GSL-MPP. Specifically, we first apply graph neural network (GNN) over molecular graphs to extract molecular representations. Then, with molecular fingerprints, we construct a molecule similarity graph (MSG). Following that, we conduct GSL on the MSG, i.e. molecule-level GSL, to get the final molecular embeddings, which are the results of fuzing both GNN encoded molecular representations and the relationships among molecules. That is, combining both intra-molecule and inter-molecule information. Finally, we use these molecular embeddings to perform MPP. Extensive experiments on 10 various benchmark datasets show that our method could achieve state-of-the-art performance in most cases, especially on classification tasks. Further visualization studies also demonstrate the good molecular representations of our method., Availability and Implementation: Source code is available at https://github.com/zby961104/GSL-MPP., (© The Author(s) 2024. Published by Oxford University Press.)

Background: The rapid devolvement of single cell RNA sequencing (scRNA-seq) technology leads to huge amounts of scRNA-seq data, which greatly advance the research of many biomedical fields involving tissue heterogeneity, pathogenesis of disease and drug resistance etc. One major task in scRNA-seq data analysis is to cluster cells in terms of their expression characteristics. Up to now, a number of methods have been proposed to infer cell clusters, yet there is still much space to improve their performance., Results: In this paper, we develop a new two-step clustering approach to effectively cluster scRNA-seq data, which is called TSC - the abbreviation of Two-Step Clustering. Particularly, by dividing all cells into two types: core cells (those possibly lying around the centers of clusters) and non-core cells (those locating in the boundary areas of clusters), we first clusters the core cells by hierarchical clustering (the first step) and then assigns the non-core cells to the corresponding nearest clusters (the second step). Extensive experiments on 12 real scRNA-seq datasets show that TSC outperforms the state of the art methods., Conclusion: TSC is an effective clustering method due to its two-steps clustering strategy, and it is a useful tool for scRNA-seq data analysis., (© 2023. The Author(s).)

A fundamental principle of biology is that proteins tend to form complexes to play important roles in the core functions of cells. For a complete understanding of human cellular functions, it is crucial to have a comprehensive atlas of human protein complexes. Unfortunately, we still lack such a comprehensive atlas of experimentally validated protein complexes, which prevents us from gaining a complete understanding of the compositions and functions of human protein complexes, as well as the underlying biological mechanisms. To fill this gap, we built Human Protein Complexes Atlas (HPC-Atlas), as far as we know, the most accurate and comprehensive atlas of human protein complexes available to date. We integrated two latest protein interaction networks, and developed a novel computational method to identify nearly 9000 protein complexes, including many previously uncharacterized complexes. Compared with the existing methods, our method achieved outstanding performance on both testing and independent datasets. Furthermore, with HPC-Atlas we identified 751 severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2)-affected human protein complexes, and 456 multifunctional proteins that contain many potential moonlighting proteins. These results suggest that HPC-Atlas can serve as not only a computing framework to effectively identify biologically meaningful protein complexes by integrating multiple protein data sources, but also a valuable resource for exploring new biological findings. The HPC-Atlas webserver is freely available at http://www.yulpan.top/HPC-Atlas., (Copyright © 2023 Beijing Institute of Genomics, Chinese Academy of Sciences and Genetics Society of China. Published by Elsevier B.V. All rights reserved.)

Molecular property prediction (MPP) is a crucial and fundamental task for AI-aided drug discovery (AIDD). Recent studies have shown great promise of applying self-supervised learning (SSL) to producing molecular representations to cope with the widely-concerned data scarcity problem in AIDD. As some specific substructures of molecules play important roles in determining molecular properties, molecular representations learned by deep learning models are expected to attach more importance to such substructures implicitly or explicitly to achieve better predictive performance. However, few SSL pre-trained models for MPP in the literature have ever focused on such substructures. To challenge this situation, this paper presents a Chemistry-Aware Fragmentation for Effective MPP (CAFE-MPP in short) under the self-supervised contrastive learning framework. First, a novel fragment-based molecular graph (FMG) is designed to represent the topological relationship between chemistry-aware substructures that constitute a molecule. Then, with well-designed hard negative pairs, a is pre-trained on fragment-level by contrastive learning to extract representations for the nodes in FMGs. Finally, a Graphormer model is leveraged to produce molecular representations for MPP based on the embeddings of fragments. Experiments on 11 benchmark datasets show that the proposed CAFE-MPP method achieves state-of-the-art performance on 7 of the 11 datasets and the second-best performance on 3 datasets, compared with six remarkable self-supervised methods. Further investigations also demonstrate that CAFE-MPP can learn to embed molecules into representations implicitly containing the information of fragments highly correlated to molecular properties, and can alleviate the over-smoothing problem of graph neural networks., (© The Author(s) 2023. Published by Oxford University Press. All rights reserved. For Permissions, please email: journals.permissions@oup.com.)

Motivation: Contrastive learning has been widely used as pretext tasks for self-supervised pre-trained molecular representation learning models in AI-aided drug design and discovery. However, existing methods that generate molecular views by noise-adding operations for contrastive learning may face the semantic inconsistency problem, which leads to false positive pairs and consequently poor prediction performance., Results: To address this problem, in this article, we first propose a semantic-invariant view generation method by properly breaking molecular graphs into fragment pairs. Then, we develop a Fragment-based Semantic-Invariant Contrastive Learning (FraSICL) model based on this view generation method for molecular property prediction. The FraSICL model consists of two branches to generate representations of views for contrastive learning, meanwhile a multi-view fusion and an auxiliary similarity loss are introduced to make better use of the information contained in different fragment-pair views. Extensive experiments on various benchmark datasets show that with the least number of pre-training samples, FraSICL can achieve state-of-the-art performance, compared with major existing counterpart models., Availability and Implementation: The code is publicly available at https://github.com/ZiqiaoZhang/FraSICL., (© The Author(s) 2023. Published by Oxford University Press.)

Motivation: Protein complexes are groups of polypeptide chains linked by non-covalent protein-protein interactions, which play important roles in biological systems and perform numerous functions, including DNA transcription, mRNA translation, and signal transduction. In the past decade, a number of computational methods have been developed to identify protein complexes from protein interaction networks by mining dense subnetworks or subgraphs., Results: In this article, different from the existing works, we propose a novel approach for this task based on generative adversarial networks, which is called PCGAN, meaning identifying Protein Complexes by GAN. With the help of some real complexes as training samples, our method can learn a model to generate new complexes from a protein interaction network. To effectively support model training and testing, we construct two more comprehensive and reliable protein interaction networks and a larger gold standard complex set by merging existing ones of the same organism (including human and yeast). Extensive comparison studies indicate that our method is superior to existing protein complex identification methods in terms of various performance metrics. Furthermore, functional enrichment analysis shows that the identified complexes are of high biological significance, which indicates that these generated protein complexes are very possibly real complexes., Availability and Implementation: https://github.com/yul-pan/PCGAN., (© The Author(s) 2023. Published by Oxford University Press.)

Motivation: Predicting molecular properties is one of the fundamental problems in drug design and discovery. In recent years, self-supervised learning (SSL) has shown its promising performance in image recognition, natural language processing, and single-cell data analysis. Contrastive learning (CL) is a typical SSL method used to learn the features of data so that the trained model can more effectively distinguish the data. One important issue of CL is how to select positive samples for each training example, which will significantly impact the performance of CL., Results: In this article, we propose a new method for molecular property prediction (MPP) by Contrastive Learning with Attention-guided Positive-sample Selection (CLAPS). First, we generate positive samples for each training example based on an attention-guided selection scheme. Second, we employ a Transformer encoder to extract latent feature vectors and compute the contrastive loss aiming to distinguish positive and negative sample pairs. Finally, we use the trained encoder for predicting molecular properties. Experiments on various benchmark datasets show that our approach outperforms the state-of-the-art (SOTA) methods in most cases., Availability and Implementation: The code is publicly available at https://github.com/wangjx22/CLAPS., (© The Author(s) 2023. Published by Oxford University Press.)

With the development of biomedical techniques in the past decades, causal gene identification has become one of the most promising applications in human genome-based business, which can help doctors to evaluate the risk of certain genetic diseases and provide further treatment recommendations for potential patients. When no controlled experiments can be applied, machine learning techniques like causal inference-based methods are generally used to identify causal genes. Unfortunately, most of the existing methods detect disease-related genes by ranking-based strategies or feature selection techniques, which generally return a superset of the corresponding real causal genes. There are also some causal inference-based methods that can identify a part of real causal genes from those supersets, but they are just able to return a few causal genes. This is contrary to our knowledge, as many results from controlled experiments have demonstrated that a certain disease, especially cancer, is usually related to dozens or hundreds of genes. In this work, we present an effective approach for identifying causal genes from gene expression data by using a new search strategy based on non-linear regression-based independence tests, which is able to greatly reduce the search space, and simultaneously establish the causal relationships from the candidate genes to the disease variable. Extensive experiments on real-world cancer datasets show that our method is superior to the existing causal inference-based methods in three aspects: 1) our method can identify dozens of causal genes, and 1/3  ∼ 1/2 of the discovered causal genes can be verified by existing works that they are really directly related to the corresponding disease; 2) The discovered causal genes are able to distinguish the status or disease subtype of the target patient; 3) Most of the discovered causal genes are closely relevant to the disease variable.

Clustering analysis has been widely used in analyzing single-cell RNA-sequencing (scRNA-seq) data to study various biological problems at cellular level. Although a number of scRNA-seq data clustering methods have been developed, most of them evaluate the similarity of pairwise cells while ignoring the global relationships among cells, which sometimes cannot effectively capture the latent structure of cells. In this paper, we propose a new clustering method SPARC for scRNA-seq data. The most important feature of SPARC is a novel similarity metric that uses the sparse representation coefficients of each cell in terms of the other cells to measure the relationships among cells. In addition, we develop an outlier detection method to help parameter selection in SPARC. We compare SPARC with nine existing scRNA-seq data clustering methods on twelve real datasets. Experimental results show that SPARC achieves the state of the art performance. By further analyzing the cell similarity data derived from sparse representations, we find that SPARC is much more effective in mining high quality clusters of scRNA-seq data than two traditional similarity metrics. In conclusion, this study provides a new way to effectively cluster scRNA-seq data and achieves more accurate clustering results than the state of art methods.

Cellular programs often exhibit strong heterogeneity and asynchrony in the timing of program execution. Single-cell RNA-seq technology has provided an unprecedented opportunity for characterizing these cellular processes by simultaneously quantifying many parameters at single-cell resolution. Robust trajectory inference is a critical step in the analysis of dynamic temporal gene expression, which can shed light on the mechanisms of normal development and diseases. Here, we present TiC2D, a novel algorithm for cell trajectory inference from single-cell RNA-seq data, which adopts a consensus clustering strategy to precisely cluster cells. To evaluate the power of TiC2D, we compare it with three state-of-the-art methods on four independent single-cell RNA-seq datasets. The results show that TiC2D can accurately infer developmental trajectories from single-cell transcriptome. Furthermore, the reconstructed trajectories enable us to identify key genes involved in cell fate determination and to obtain new insights about their roles at different developmental stages.

This article addresses two important issues of causal inference in the high-dimensional situation. One is how to reduce redundant conditional independence (CI) tests, which heavily impact the efficiency and accuracy of existing constraint-based methods. Another is how to construct the true causal graph from a set of Markov equivalence classes returned by these methods. For the first issue, we design a recursive decomposition approach where the original data (a set of variables) are first decomposed into two small subsets, each of which is then recursively decomposed into two smaller subsets until none of these subsets can be decomposed further. Redundant CI tests can be reduced by inferring causalities from these subsets. The advantage of this decomposition scheme lies in two aspects: 1) it requires only low-order CI tests and 2) it does not violate d -separation. The complete causality can be reconstructed by merging all the partial results of the subsets. For the second issue, we employ regression-based CI tests to check CIs in linear non-Gaussian additive noise cases, which can identify more causal directions by [Formula: see text] (or [Formula: see text]). Consequently, causal direction learning is no longer limited by the number of returned V -structures and consistent propagation. Extensive experiments show that the proposed method can not only substantially reduce redundant CI tests but also effectively distinguish the equivalence classes.

Link weight prediction is an important subject in network science and machine learning. Its applications to social network analysis, network modeling, and bioinformatics are ubiquitous. Although this subject has attracted considerable attention recently, the performance and interpretability of existing prediction models have not been well balanced. This article focuses on an unsupervised mixed strategy for link weight prediction. Here, the target attribute is the link weight, which represents the correlation or strength of the interaction between a pair of nodes. The input of the model is the weighted adjacency matrix without any preprocessing, as widely adopted in the existing models. Extensive observations on a large number of networks show that the new scheme is competitive to the state-of-the-art algorithms concerning both root-mean-square error and Pearson correlation coefficient metrics. Analytic and simulation results suggest that combining the weight consistency of the network and the link weight-associated latent factors of the nodes is a very effective way to solve the link weight prediction problem.

Over the past decades, massive amounts of protein-protein interaction (PPI) data have been accumulated due to the advancement of high-throughput technologies, and but data quality issues (noise or incompleteness) of PPI have been still affecting protein function prediction accuracy based on PPI networks. Although two main strategies of network reconstruction and edge enrichment have been reported on the effectiveness of boosting the prediction performance in numerous literature studies, there still lack comparative studies of the performance differences between network reconstruction and edge enrichment . Inspired by the question, this study first uses three protein similarity metrics (local, global and sequence) for network reconstruction and edge enrichment in PPI networks, and then evaluates the performance differences of network reconstruction, edge enrichment and the original networks on two real PPI datasets. The experimental results demonstrate that edge enrichment work better than both network reconstruction and original networks. Moreover, for the edge enrichment of PPI networks, the sequence similarity outperformes both local and global similarity. In summary, our study can help biologists select suitable pre-processing schemes and achieve better protein function prediction for PPI networks., Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (Copyright © 2021 Zhou, Xiong, Wang and Guan.)

Motivation: Molecular property prediction is a hot topic in recent years. Existing graph-based models ignore the hierarchical structures of molecules. According to the knowledge of chemistry and pharmacy, the functional groups of molecules are closely related to its physio-chemical properties and binding affinities. So, it should be helpful to represent molecular graphs by fragments that contain functional groups for molecular property prediction., Results: In this article, to boost the performance of molecule property prediction, we first propose a definition of molecule graph fragments that may be or contain functional groups, which are relevant to molecular properties, then develop a fragment-oriented multi-scale graph attention network for molecular property prediction, which is called FraGAT. Experiments on several widely used benchmarks are conducted to evaluate FraGAT. Experimental results show that FraGAT achieves state-of-the-art predictive performance in most cases. Furthermore, our case studies show that when the fragments used to represent the molecule graphs contain functional groups, the model can make better predictions. This conforms to our expectation and demonstrates the interpretability of the proposed model., Availability and Implementation: The code and data underlying this work are available in GitHub, at https://github.com/ZiqiaoZhang/FraGAT., Supplementary Information: Supplementary data are available at Bioinformatics online., (© The Author(s) 2021. Published by Oxford University Press.)

Background: The rapid development of single-cell RNA sequencing (scRNA-seq) enables the exploration of cell heterogeneity, which is usually done by scRNA-seq data clustering. The essence of scRNA-seq data clustering is to group cells by measuring the similarities among genes/transcripts of cells. And the selection of features for cell similarity evaluation is of great importance, which will significantly impact clustering effectiveness and efficiency., Results: In this paper, we propose a novel method called CaFew to select genes based on cluster-aware feature weighting. By optimizing the clustering objective function, CaFew obtains a feature weight matrix, which is further used for feature selection. The genes have large weights in at least one cluster or the genes whose weights vary greatly in different clusters are selected. Experiments on 8 real scRNA-seq datasets show that CaFew can obviously improve the clustering performance of existing scRNA-seq data clustering methods. Particularly, the combination of CaFew with SC3 achieves the state-of-art performance. Furthermore, CaFew also benefits the visualization of scRNA-seq data., Conclusion: CaFew is an effective scRNA-seq data clustering method due to its gene selection mechanism based on cluster-aware feature weighting, and it is a useful tool for scRNA-seq data analysis.

Clustering analysis has been widely applied to single-cell RNA-sequencing (scRNA-seq) data to discover cell types and cell states. Algorithms developed in recent years have greatly helped the understanding of cellular heterogeneity and the underlying mechanisms of biological processes. However, these algorithms often use different techniques, were evaluated on different datasets and compared with some of their counterparts usually using different performance metrics. Consequently, there lacks an accurate and complete picture of their merits and demerits, which makes it difficult for users to select proper algorithms for analyzing their data. To fill this gap, we first do a review on the major existing scRNA-seq data clustering methods, and then conduct a comprehensive performance comparison among them from multiple perspectives. We consider 13 state of the art scRNA-seq data clustering algorithms, and collect 12 publicly available real scRNA-seq datasets from the existing works to evaluate and compare these algorithms. Our comparative study shows that the existing methods are very diverse in performance. Even the top-performance algorithms do not perform well on all datasets, especially those with complex structures. This suggests that further research is required to explore more stable, accurate, and efficient clustering algorithms for scRNA-seq data.

Identifying protein complexes is an important issue in computational biology, as it benefits the understanding of cellular functions and the design of drugs. In the past decades, many computational methods have been proposed by mining dense subgraphs in Protein-Protein Interaction Networks (PINs). However, the high rate of false positive/negative interactions in PINs prevents accurately detecting complexes directly from the raw PINs. In this paper, we propose a denoising approach for protein complex detection by using variational graph auto-encoder. First, we embed a PIN to vector space by a stacked graph convolutional network (GCN), then decide which interactions in the PIN are credible. If the probability of an interaction being credible is less than a threshold, we delete the interaction. In such a way, we reconstruct a reliable PIN. Following that, we detect protein complexes in the reconstructed PIN by using several typical detection methods, including CPM, Coach, DPClus, GraphEntropy, IPCA and MCODE, and compare the results with those obtained directly from the original PIN. We conduct the empirical evaluation on four yeast PPI datasets (Gavin, Krogan, DIP and Wiphi) and two human PPI datasets (Reactome and Reactomekb), against two yeast complex benchmarks (CYC2008 and MIPS) and three human complex benchmarks (REACT, REACT_uniprotkb and CORE_COMPLEX_human), respectively. Experimental results show that with the reconstructed PINs obtained by our denoising approach, complex detection performance can get obviously boosted, in most cases by over 5%, sometimes even by 200%. Furthermore, we compare our approach with two existing denoising methods (RWS and RedNemo) while varying different matching rates on separate complex distributions. Our results show that in most cases (over 2/3), the proposed approach outperforms the existing methods.

Identifying protein complexes is helpful for understanding cellular functions and designing drugs. In the last decades, many computational methods have been proposed based on detecting dense subgraphs or subnetworks in Protein-Protein Interaction Networks (PINs). However, the high rate of false positive/negative interactions in PINs prevents from the achievement of satisfactory detection results directly from PINs, because most of such existing methods exploit mainly topological information to do network partitioning. In this paper, we propose a new approach for protein complex detection by merging topological information of PINs and functional information of proteins. We first split proteins to a number of protein groups from the perspective of protein functions by using FunCat data. Then, for each of the resulting protein groups, we calculate two protein-protein similarity matrices: one is computed by using graph embedding over a PIN, the other is by using GO terms, and combine these two matrices to get an integrated similarity matrix. Following that, we cluster the proteins in each group based on the corresponding integrated similarity matrix, and obtain a number of small protein clusters. We map these clusters of proteins onto the PIN, and get a number of connected subgraphs. After a round of merging of overlapping subgraphs, finally we get the detected complexes. We conduct empirical evaluation on four PPI datasets (Collins, Gavin, Krogan, and Wiphi) with two complex benchmarks (CYC2008 and MIPS). Experimental results show that our method performs better than the state-of-the-art methods.

Background: Super-enhancers (SEs) are clusters of transcriptional active enhancers, which dictate the expression of genes defining cell identity and play an important role in the development and progression of tumors and other diseases. Many key cancer oncogenes are driven by super-enhancers, and the mutations associated with common diseases such as Alzheimer's disease are significantly enriched with super-enhancers. Super-enhancers have shown great potential for the identification of key oncogenes and the discovery of disease-associated mutational sites., Results: In this paper, we propose a new computational method called DEEPSEN for predicting super-enhancers based on convolutional neural network. The proposed method integrates 36 kinds of features. Compared with existing approaches, our method performs better and can be used for genome-wide prediction of super-enhancers. Besides, we screen important features for predicting super-enhancers., Conclusion: Convolutional neural network is effective in boosting the performance of super-enhancer prediction.

Essential proteins are critical to the development and survival of cells. Identification of essential proteins is helpful for understanding the minimal set of required genes in a living cell and for designing new drugs. To detect essential proteins, various computational methods have been proposed based on protein-protein interaction (PPI) networks. However, protein interaction data obtained by high-throughput experiments usually contain high false positives, which negatively impacts the accuracy of essential protein detection. Moreover, most existing studies focused on the local information of proteins in PPI networks, while ignoring the influence of indirect protein interactions on essentiality. In this paper, we propose a novel method, called Essentiality Ranking (EssRank in short), to boost the accuracy of essential protein detection. To deal with the inaccuracy of PPI data, confidence scores of interactions are evaluated by integrating various biological information. Weighted edge clustering coefficient (WECC), considering both interaction confidence scores and network topology, is proposed to calculate edge weights in PPI networks. The weight of each node is evaluated by the sum of WECC values of its linking edges. A random walk method, making use of both direct and indirect protein interactions, is then employed to calculate protein essentiality iteratively. Experimental results on the yeast PPI network show that EssRank outperforms most existing methods, including the most commonly-used centrality measures (SC, DC, BC, CC, IC, and EC), topology based methods (DMNC and NC) and the data integrating method IEW.

Background: The default mode network (DMN) in resting state has been increasingly used in disease diagnosis since it was found in 2001. Prior work has mainly focused on extracting a single DMN with various techniques. However, by using seeding-based analysis with more than one desirable seed, we can obtain multiple DMNs, which are likely to have complementary information, and thus are more promising for disease diagnosis. In the study, we used 18 early mild cognitive impairment (EMCI) participants and 18 late mild cognitive impairment (LMCI) participants of Alzheimer's disease (AD). First, we used seeding-based analysis with four seeds to extract four DMNs for each subject. Then, we conducted fusion analysis for all different combinations of the four DMNs. Finally, we carried out nonlinear support vector machine classification based on the mixing coefficients from the fusion analysis., Results: We found that (1) the four DMNs corresponding to the four different seeds indeed capture different functional regions of each subject; (2) Maps of the four DMNs in the most different joint source from fusion analysis are centered at the regions of the corresponding seeds; (3) Classification results reveal the effectiveness of using multiple seeds to extract DMNs. When using a single seed, the regions of posterior cingulate cortex (PCC) extractions of EMCI and LMCI show the largest difference. For multiple-seed cases, the regions of PCC extraction and right lateral parietal cortex (RLP) extraction provide complementary information for each other in fusion, which improves the classification accuracy. Furthermore, the regions of left lateral parietal cortex (LLP) extraction and RLP extraction also have complementary effect in fusion. In summary, AD diagnosis can be improved by exploiting complementary information of DMNs extracted with multiple seeds., Conclusions: In this study, we applied fusion analysis to the DMNs extracted by using different seeds for exploiting the complementary information hidden among the separately extracted DMNs, and the results supported our expectation that using the complementary information can improve classification accuracy.

Prediction of compound-protein interactions (CPIs) is to find new compound-protein pairs where a protein is targeted by at least a compound, which is a crucial step in new drug design. Currently, a number of machine learning based methods have been developed to predict new CPIs in the literature. However, as there is not yet any publicly available set of validated negative CPIs, most existing machine learning based approaches use the unknown interactions (not validated CPIs) selected randomly as the negative examples to train classifiers for predicting new CPIs. Obviously, this is not quite reasonable and unavoidably impacts the CPI prediction performance. In this paper, we simply take the unknown CPIs as unlabeled examples, and propose a new method called PUCPI (the abbreviation of PU learning for Compound-Protein Interaction identification) that employs biased-SVM (Support Vector Machine) to predict CPIs using only positive and unlabeled examples. PU learning is a class of learning methods that leans from positive and unlabeled (PU) samples. To the best of our knowledge, this is the first work that identifies CPIs using only positive and unlabeled examples. We first collect known CPIs as positive examples and then randomly select compound-protein pairs not in the positive set as unlabeled examples. For each CPI/compound-protein pair, we extract protein domains as protein features and compound substructures as chemical features, then take the tensor product of the corresponding compound features and protein features as the feature vector of the CPI/compound-protein pair. After that, biased-SVM is employed to train classifiers on different datasets of CPIs and compound-protein pairs. Experiments over various datasets show that our method outperforms six typical classifiers, including random forest, L1- and L2-regularized logistic regression, naive Bayes, SVM and k-nearest neighbor (kNN), and three types of existing CPI prediction models. More information can be found at http://admis.fudan.edu.cn/projects/pucpi.html.

Interactions between chromatin segments play a large role in functional genomic assays and developments in genomic interaction detection methods have shown interacting topological domains within the genome. Among these methods, Hi-C plays a key role. Here, we present the Genome Interaction Tools and Resources (GITAR), a software to perform a comprehensive Hi-C data analysis, including data preprocessing, normalization, and visualization, as well as analysis of topologically-associated domains (TADs). GITAR is composed of two main modules: (1) HiCtool, a Python library to process and visualize Hi-C data, including TAD analysis; and (2) processed data library, a large collection of human and mouse datasets processed using HiCtool. HiCtool leads the user step-by-step through a pipeline, which goes from the raw Hi-C data to the computation, visualization, and optimized storage of intra-chromosomal contact matrices and TAD coordinates. A large collection of standardized processed data allows the users to compare different datasets in a consistent way, while saving time to obtain data for visualization or additional analyses. More importantly, GITAR enables users without any programming or bioinformatic expertise to work with Hi-C data. GITAR is publicly available at http://genomegitar.org as an open-source software., (Copyright © 2018 The Authors. Production and hosting by Elsevier B.V. All rights reserved.)

Background: Effectively predicting protein complexes not only helps to understand the structures and functions of proteins and their complexes, but also is useful for diagnosing disease and developing new drugs. Up to now, many methods have been developed to detect complexes by mining dense subgraphs from static protein-protein interaction (PPI) networks, while ignoring the value of other biological information and the dynamic properties of cellular systems., Results: In this paper, based on our previous works CPredictor and CPredictor2.0, we present a new method for predicting complexes from PPI networks with both gene expression data and protein functional annotations, which is called CPredictor3.0. This new method follows the viewpoint that proteins in the same complex should roughly have similar functions and are active at the same time and place in cellular systems. We first detect active proteins by using gene express data of different time points and cluster proteins by using gene ontology (GO) functional annotations, respectively. Then, for each time point, we do set intersections with one set corresponding to active proteins generated from expression data and the other set corresponding to a protein cluster generated from functional annotations. Each resulting unique set indicates a cluster of proteins that have similar function(s) and are active at that time point. Following that, we map each cluster of active proteins of similar function onto a static PPI network, and get a series of induced connected subgraphs. We treat these subgraphs as candidate complexes. Finally, by expanding and merging these candidate complexes, the predicted complexes are obtained. We evaluate CPredictor3.0 and compare it with a number of existing methods on several PPI networks and benchmarking complex datasets. The experimental results show that CPredictor3.0 achieves the highest F1-measure, which indicates that CPredictor3.0 outperforms these existing method in overall., Conclusion: CPredictor3.0 can serve as a promising tool of protein complex prediction.

In social gaming networks, previous studies extensively investigated the influence of a variety of strategies on reciprocal behaviors in the prisoner's dilemma game. The studied frameworks range from the case that an individual uniformly cooperates or defects with all social contacts, to the recently reported divide-and-conquer games, where an individual can choose a particular move to play with each neighbor. In this paper, we investigate a divide-and-conquer tournament among 14 well-known strategies on social gaming networks. In the tournament, an individual's fitness is measured by accumulated and average payoff aggregated for a certain number of rounds. On the base of their fitness, the evolution of the population follows a local learning mechanism. Our observation indicates that the distribution of individuals adopting a strategy in degree ranking fundamentally changes the frequency of the strategy. In the divide-and-conquer gaming networks, our result suggests that the connectivity in social networks and strategy are two key factors that govern the evolution of the population.

Background: Predicting protein complexes from protein-protein interaction (PPI) networks has been studied for decade. Various methods have been proposed to address some challenging issues of this problem, including overlapping clusters, high false positive/negative rates of PPI data and diverse complex structures. It is well known that most current methods can detect effectively only complexes of size ≥3, which account for only about half of the total existing complexes. Recently, a method was proposed specifically for finding small complexes (size = 2 and 3) from PPI networks. However, up to now there is no effective approach that can predict both small (size ≤ 3) and large (size >3) complexes from PPI networks., Results: In this paper, we propose a novel method, called CPredictor2.0, that can detect both small and large complexes under a unified framework. Concretely, we first group proteins of similar functions. Then, the Markov clustering algorithm is employed to discover clusters in each group. Finally, we merge all discovered clusters that overlap with each other to a certain degree, and the merged clusters as well as the remaining clusters constitute the set of detected complexes. Extensive experiments have shown that the new method can more effectively predict both small and large complexes, in comparison with the state-of-the-art methods., Conclusions: The proposed method, CPredictor2.0, can be applied to accurately predict both small and large protein complexes.

Background: Studies have shown that enhancers are significant regulatory elements to play crucial roles in gene expression regulation. Since enhancers are unrelated to the orientation and distance to their target genes, it is a challenging mission for scholars and researchers to accurately predicting distal enhancers. In the past years, with the high-throughout ChiP-seq technologies development, several computational techniques emerge to predict enhancers using epigenetic or genomic features. Nevertheless, the inconsistency of computational models across different cell-lines and the unsatisfactory prediction performance call for further research in this area., Results: Here, we propose a new Deep Belief Network (DBN) based computational method for enhancer prediction, which is called EnhancerDBN. This method combines diverse features, composed of DNA sequence compositional features, DNA methylation and histone modifications. Our computational results indicate that 1) EnhancerDBN outperforms 13 existing methods in prediction, and 2) GC content and DNA methylation can serve as relevant features for enhancer prediction., Conclusion: Deep learning is effective in boosting the performance of enhancer prediction.

Background: Long non-coding RNA (lncRNA) plays important roles in many biological and pathological processes, including transcriptional regulation and gene regulation. As lncRNA interacts with multiple proteins, predicting lncRNA-protein interactions (lncRPIs) is an important way to study the functions of lncRNA. Up to now, there have been a few works that exploit protein-protein interactions (PPIs) to help the prediction of new lncRPIs., Results: In this paper, we propose to boost the prediction of lncRPIs by fusing multiple protein-protein similarity networks (PPSNs). Concretely, we first construct four PPSNs based on protein sequences, protein domains, protein GO terms and the STRING database respectively, then build a more informative PPSN by fusing these four constructed PPSNs. Finally, we predict new lncRPIs by a random walk method with the fused PPSN and known lncRPIs. Our experimental results show that the new approach outperforms the existing methods., Conclusion: Fusing multiple protein-protein similarity networks can effectively boost the performance of predicting lncRPIs.

Background: The identification of Protein-RNA Interactions (PRIs) is important to understanding cell activities. Recently, several machine learning-based methods have been developed for identifying PRIs. However, the performance of these methods is unsatisfactory. One major reason is that they usually use unreliable negative samples in the training process., Methods: For boosting the performance of PRI prediction, we propose a novel method to generate reliable negative samples. Concretely, we firstly collect the known PRIs as positive samples for generating positive sets. For each positive set, we construct two corresponding negative sets, one is by our method and the other by random method. Each positive set is combined with a negative set to form a dataset for model training and performance evaluation. Consequently, we get 18 datasets of different species and different ratios of negative samples to positive samples. Secondly, sequence-based features are extracted to represent each of PRIs and protein-RNA pairs in the datasets. A filter-based method is employed to cut down the dimensionality of feature vectors for reducing computational cost. Finally, the performance of support vector machine (SVM), random forest (RF) and naive Bayes (NB) is evaluated on the generated 18 datasets., Results: Extensive experiments show that comparing to using randomly-generated negative samples, all classifiers achieve substantial performance improvement by using negative samples selected by our method. The improvements on accuracy and geometric mean for the SVM classifier, the RF classifier and the NB classifier are as high as 204.5 and 68.7%, 174.5 and 53.9%, 80.9 and 54.3%, respectively., Conclusion: Our method is useful to the identification of PRIs.

Background: Differences in chromatin states are critical to the multiplicity of cell states. Recently genome-wide histone modification maps of diverse human developmental stages and tissues have been charted., Description: To facilitate the investigation of epigenetic dynamics and regulatory mechanisms in cellular differentiation processes, we developed iHMS, an integrated human histone modification database that incorporates massive histone modification maps spanning different developmental stages, lineages and tissues ( http://www.tongjidmb.com/human/index.html ). It also includes genome-wide expression data of different conditions, reference gene annotations, GC content and CpG island information. By providing an intuitive and user-friendly query interface, iHMS enables comprehensive query and comparative analysis based on gene names, genomic region locations, histone modification marks and cell types. Moreover, it offers an efficient browser that allows users to visualize and compare multiple genome-wide histone modification maps and related expression profiles across different developmental stages and tissues., Conclusion: iHMS is of great helpfulness to understand how global histone modification state transitions impact cellular phenotypes across different developmental stages and tissues in the human genome. This extensive catalog of histone modification states thus presents an important resource for epigenetic and developmental studies.

Background: One of the most challenging tasks in the exploration of anti-aging is to discover drugs that can promote longevity and delay the incidence of age-associated diseases of human. Up to date, a number of drugs, including some antioxidants, metabolites and synthetic compounds, have been found to effectively delay the aging of nematodes and insects., Results: We proposed a label propagation algorithm on drug-protein network to infer drugs that can extend the lifespan of C. elegans. We collected a set of drugs of which functions on lifespan extension of C. elegans have been reliably determined, and then built a large-scale drug-protein network by collecting a set of high-confidence drugprotein interactions. A label propagation algorithm was run on the drug-protein bipartite network to predict new drugs with lifespan-extending effect on C. elegans. We calibrated the performance of the proposed method by conducting performance comparison with two classical models, kNN and SVM. We also showed that the screened drugs significantly mediate in the aging-related pathways, and have higher chemical similarities to the effective drugs than ineffective drugs in promoting longevity of C. elegans. Moreover, we carried out wet-lab experiments to verify a screened drugs, 2- Bromo-4'-nitroacetophenone, and found that it can effectively extend the lifespan of C. elegans. These results showed that our method is effective in screening lifespanextending drugs in C. elegans., Conclusions: In this paper, we proposed a semi-supervised algorithm to predict drugs with lifespan-extending effects on C. elegans. In silico empirical evaluations and in vivo experiments in C. elegans have demonstrated that our method can effectively narrow down the scope of candidate drugs needed to be verified by wet lab experiments.