Search

Aim: Lung cancer is the leading cause of cancer-related deaths worldwide. Non-small cell lung cancer (NSCLC) is the most common subtype. Despite recent advancements in diagnostics and therapies, only a small percentage of patients benefit from immunotherapies. This underscores the urgent need to identify prognostic biomarkers for accurately assessing outcomes and providing treatment recommendations for NSCLC patients. Single-cell RNA sequencing (scRNA-seq) has revealed the heterogeneity of tumor-associated macrophages. Macrophages consist of M0, M1, and M2 subsets. M1 macrophages are often associated with improved clinical outcomes in various malignancies. However, there are no systematic studies on risk biomarkers for prognosticating NSCLC. Methods: CIBERSORT was used to calculate the macrophage subset infiltration percentage in bulk RNA-seq data from TCGA and GEO. The M1-related module was identified using the WGCNA algorithm. Potential M1 macrophage prognosis-associated genes were defined as the overlapping genes between marker genes in the M1 subpopulation from scRNA-seq data and prognosis-associated genes in M1 infiltrating cells. Results: Four risk genes (ADAM19, ICAM3, WIPF1, and LAP3) were identified through LASSO and multivariate Cox regression analysis. Forest plots demonstrated that the scoring model was an independent risk factor. A nomogram was provided to predict the prognosis of NSCLC patients. Finally, we validated the four risk genes at the protein expression levels and for copy number variations. Conclusions: In summary, our studies identified four risk genes related to M1 macrophages and presented a risk-scoring system to predict the outcomes of patients with NSCLC by integrating bulk and single-cell data.

Abstract The ongoing COVID-19 pandemic, caused by the SARS-CoV-2 virus, represents one of the most significant global health crises in recent history. Despite extensive research into the immune mechanisms and therapeutic options for COVID-19, there remains a paucity of studies focusing on plasma cells. In this study, we utilized the DESeq2 package to identify differentially expressed genes (DEGs) between COVID-19 patients and controls using datasets GSE157103 and GSE152641. We employed the xCell algorithm to perform immune infiltration analyses, revealing notably elevated levels of plasma cells in COVID-19 patients compared to healthy individuals. Subsequently, we applied the Weighted Gene Co-expression Network Analysis (WGCNA) algorithm to identify COVID-19 related plasma cell module genes. Further, positive cluster biomarker genes for plasma cells were extracted from single-cell RNA sequencing data (GSE171524), leading to the identification of 122 shared genes implicated in critical biological processes such as cell cycle regulation and viral infection pathways. We constructed a robust protein-protein interaction (PPI) network comprising 89 genes using Cytoscape, and identified 20 hub genes through cytoHubba. These genes were validated in external datasets (GSE152418 and GSE179627). Additionally, we identified three potential small molecules (GSK-1070916, BRD-K89997465, and idarubicin) that target key hub genes in the network, suggesting a novel therapeutic approach. These compounds were characterized by their ability to down-regulate AURKB, KIF11, and TOP2A effectively, as evidenced by their low free binding energies determined through computational analyses using cMAP and AutoDock. This study marks the first comprehensive exploration of plasma cells’ role in COVID-19, offering new insights and potential therapeutic targets. It underscores the importance of a systematic approach to understanding and treating COVID-19, expanding the current body of knowledge and providing a foundation for future research.

Abstract Proteins and nucleic-acids are essential components of living organisms that interact in critical cellular processes. Accurate prediction of nucleic acid-binding residues in proteins can contribute to a better understanding of protein function. However, the discrepancy between protein sequence information and obtained structural and functional data renders most current computational models ineffective. Therefore, it is vital to design computational models based on protein sequence information to identify nucleic acid binding sites in proteins. Here, we implement an ensemble deep learning model-based nucleic-acid-binding residues on proteins identification method, called SOFB, which characterizes protein sequences by learning the semantics of biological dynamics contexts, and then develop an ensemble deep learning-based sequence network to learn feature representation and classification by explicitly modeling dynamic semantic information. Among them, the language learning model, which is constructed from natural language to biological language, captures the underlying relationships of protein sequences, and the ensemble deep learning-based sequence network consisting of different convolutional layers together with Bi-LSTM refines various features for optimal performance. Meanwhile, to address the imbalanced issue, we adopt ensemble learning to train multiple models and then incorporate them. Our experimental results on several DNA/RNA nucleic-acid-binding residue datasets demonstrate that our proposed model outperforms other state-of-the-art methods. In addition, we conduct an interpretability analysis of the identified nucleic acid binding residue sequences based on the attention weights of the language learning model, revealing novel insights into the dynamic semantic information that supports the identified nucleic acid binding residues. SOFB is available at https://github.com/Encryptional/SOFB and https://figshare.com/articles/online_resource/SOFB_figshare_rar/25499452 .

Abstract Structure-based generative chemistry is essential in computer-aided drug discovery by exploring a vast chemical space to design ligands with high binding affinity for targets. However, traditional in silico methods are limited by computational inefficiency, while machine learning approaches face bottlenecks due to auto-regressive sampling. To address these concerns, we have developed a conditional deep generative model, PMDM, for 3D molecule generation fitting specified targets. PMDM consists of a conditional equivariant diffusion model with both local and global molecular dynamics, enabling PMDM to consider the conditioned protein information to generate molecules efficiently. The comprehensive experiments indicate that PMDM outperforms baseline models across multiple evaluation metrics. To evaluate the applications of PMDM under real drug design scenarios, we conduct lead compound optimization for SARS-CoV-2 main protease (Mpro) and Cyclin-dependent Kinase 2 (CDK2), respectively. The selected lead optimization molecules are synthesized and evaluated for their in-vitro activities against CDK2, displaying improved CDK2 activity.

Summary: Current studies in early cancer detection based on liquid biopsy data often rely on off-the-shelf models and face challenges with heterogeneous data, as well as manually designed data preprocessing pipelines with different parameter settings. To address those challenges, we present AutoCancer, an automated, multimodal, and interpretable transformer-based framework. This framework integrates feature selection, neural architecture search, and hyperparameter optimization into a unified optimization problem with Bayesian optimization. Comprehensive experiments demonstrate that AutoCancer achieves accurate performance in specific cancer types and pan-cancer analysis, outperforming existing methods across three cohorts. We further demonstrated the interpretability of AutoCancer by identifying key gene mutations associated with non-small cell lung cancer to pinpoint crucial factors at different stages and subtypes. The robustness of AutoCancer, coupled with its strong interpretability, underscores its potential for clinical applications in early cancer detection.

Abstract Single‐cell RNA sequencing (scRNA‐seq) is a robust method for studying gene expression at the single‐cell level, but accurately quantifying genetic material is often hindered by limited mRNA capture, resulting in many missing expression values. Existing imputation methods rely on strict data assumptions, limiting their broader application, and lack reliable supervision, leading to biased signal recovery. To address these challenges, authors developed Bis, a distribution‐agnostic deep learning model for accurately recovering missing sing‐cell gene expression from multiple platforms. Bis is an optimal transport‐based autoencoder model that can capture the intricate distribution of scRNA‐seq data while addressing the characteristic sparsity by regularizing the cellular embedding space. Additionally, they propose a module using bulk RNA‐seq data to guide reconstruction and ensure expression consistency. Experimental results show Bis outperforms other models across simulated and real datasets, showcasing superiority in various downstream analyses including batch effect removal, clustering, differential expression analysis, and trajectory inference. Moreover, Bis successfully restores gene expression levels in rare cell subsets in a tumor‐matched peripheral blood dataset, revealing developmental characteristics of cytokine‐induced natural killer cells within a head and neck squamous cell carcinoma microenvironment.

Summary: Gene regulatory networks (GRNs) involve complex and multi-layer regulatory interactions between regulators and their target genes. Precise knowledge of GRNs is important in understanding cellular processes and molecular functions. Recent breakthroughs in single-cell sequencing technology made it possible to infer GRNs at single-cell level. Existing methods, however, are limited by expensive computations, and sometimes simplistic assumptions. To overcome these obstacles, we propose scGREAT, a framework to infer GRN using gene embeddings and transformer from single-cell transcriptomics. scGREAT starts by constructing gene expression and gene biotext dictionaries from scRNA-seq data and gene text information. The representation of TF gene pairs is learned through optimizing embedding space by transformer-based engine. Results illustrated scGREAT outperformed other contemporary methods on benchmarks. Besides, gene representations from scGREAT provide valuable gene regulation insights, and external validation on spatial transcriptomics illuminated the mechanism behind scGREAT annotation. Moreover, scGREAT identified several TF target regulations corroborated in studies.

Abstract RNA-binding proteins play crucial roles in the regulation of gene expression, and understanding the interactions between RNAs and RBPs in distinct cellular conditions forms the basis for comprehending the underlying RNA function. However, current computational methods pose challenges to the cross-prediction of RNA-protein binding events across diverse cell lines and tissue contexts. Here, we develop HDRNet, an end-to-end deep learning-based framework to precisely predict dynamic RBP binding events under diverse cellular conditions. Our results demonstrate that HDRNet can accurately and efficiently identify binding sites, particularly for dynamic prediction, outperforming other state-of-the-art models on 261 linear RNA datasets from both eCLIP and CLIP-seq, supplemented with additional tissue data. Moreover, we conduct motif and interpretation analyses to provide fresh insights into the pathological mechanisms underlying RNA-RBP interactions from various perspectives. Our functional genomic analysis further explores the gene-human disease associations, uncovering previously uncharacterized observations for a broad range of genetic disorders.

Abstract Single‐cell Hi‐C (scHi‐C) has made it possible to analyze chromatin organization at the single‐cell level. However, scHi‐C experiments generate inherently sparse data, which poses a challenge for loop calling methods. The existing approach performs significance tests across the imputed dense contact maps, leading to substantial computational overhead and loss of information at the single‐cell level. To overcome this limitation, a lightweight framework called scGSLoop is proposed, which sets a new paradigm for scHi‐C loop calling by adapting the training and inferencing strategies of graph‐based deep learning to leverage the sequence features and 1D positional information of genomic loci. With this framework, sparsity is no longer a challenge, but rather an advantage that the model leverages to achieve unprecedented computational efficiency. Compared to existing methods, scGSLoop makes more accurate predictions and is able to identify more loops that have the potential to play regulatory roles in genome functioning. Moreover, scGSLoop preserves single‐cell information by identifying a distinct group of loops for each individual cell, which not only enables an understanding of the variability of chromatin looping states between cells, but also allows scGSLoop to be extended for the investigation of multi‐connected hubs and their underlying mechanisms.

Summary: By soaking microRNAs (miRNAs), long non-coding RNAs (lncRNAs) have the potential to regulate gene expression. Few methods have been created based on this mechanism to anticipate the lncRNA-gene relationship prediction. Hence, we present lncRNA-Top to forecast potential lncRNA-gene regulation relationships. Specifically, we constructed controlled deep-learning methods using 12417 lncRNAs and 16127 genes. We have provided retrospective and innovative views among negative sampling, random seeds, cross-validation, metrics, and independent datasets. The AUC, AUPR, and our defined precision@k were leveraged to evaluate performance. In-depth case studies demonstrate that 47 out of 100 projected top unknown pairings were recorded in publications, supporting the predictive power. Our additional software can annotate the scores with target candidates. The lncRNA-Top will be a helpful tool to uncover prospective lncRNA targets and better comprehend the regulatory processes of lncRNAs.

Cancer has received extensive recognition for its high mortality rate, with metastatic cancer being the top cause of cancer-related deaths. Metastatic cancer involves the spread of the primary tumor to other body organs. As much as the early detection of cancer is essential, the timely detection of metastasis, the identification of biomarkers, and treatment choice are valuable for improving the quality of life for metastatic cancer patients. This study reviews the existing studies on classical machine learning (ML) and deep learning (DL) in metastatic cancer research. Since the majority of metastatic cancer research data are collected in the formats of PET/CT and MRI image data, deep learning techniques are heavily involved. However, its black-box nature and expensive computational cost are notable concerns. Furthermore, existing models could be overestimated for their generality due to the non-diverse population in clinical trial datasets. Therefore, research gaps are itemized; follow-up studies should be carried out on metastatic cancer using machine learning and deep learning tools with data in a symmetric manner.

A major challenge in analyzing scRNA-seq data arises from challenges related to dimensionality and the prevalence of dropout events. Here the authors develop a deep graph learning method called scMGCA based on a graph-embedding autoencoder that simultaneously learns cell-cell topology representation and cluster assignments, outperforming other state-of-the-art models across multiple platforms.

An ensemble deep learning model (EDLM)-based protein-protein interaction (PPI) site identification method (EDLMPPI) accurately predicts PPIs through protein language models and outperforms state-of-the-art methods on multiple benchmark sets.

Abstract Unsupervised clustering is an essential step in identifying cell types from single‐cell RNA sequencing (scRNA‐seq) data. However, a common issue with unsupervised clustering models is that the optimization direction of the objective function and the final generated clustering labels in the absence of supervised information may be inconsistent or even arbitrary. To address this challenge, a dynamic ensemble pruning framework (DEPF) is proposed to identify and interpret single‐cell molecular heterogeneity. In particular, a silhouette coefficient‐based indicator is developed to determine the optimization direction of the bi‐objective function. In addition, a hierarchical autoencoder is employed to project the high‐dimensional data onto multiple low‐dimensional latent space sets, and then a clustering ensemble is produced in the latent space by the basic clustering algorithm. Following that, a bi‐objective fruit fly optimization algorithm is designed to prune dynamically the low‐quality basic clustering in the ensemble. Multiple experiments are conducted on 28 real scRNA‐seq datasets and one large real scRNA‐seq dataset from diverse platforms and species to validate the effectiveness of the DEPF. In addition, biological interpretability and transcriptional and post‐transcriptional regulatory are conducted to explore biological patterns from the cell types identified, which could provide novel insights into characterizing the mechanisms.

Abstract The single‐cell RNA sequencing (scRNA‐seq) quantifies the gene expression of individual cells, while the bulk RNA sequencing (bulk RNA‐seq) characterizes the mixed transcriptome of cells. The inference of drug sensitivities for individual cells can provide new insights to understand the mechanism of anti‐cancer response heterogeneity and drug resistance at the cellular resolution. However, pharmacogenomic information related to their corresponding scRNA‐Seq is often limited. Therefore, a transfer learning model is proposed to infer the drug sensitivities at single‐cell level. This framework learns bulk transcriptome profiles and pharmacogenomics information from population cell lines in a large public dataset and transfers the knowledge to infer drug efficacy of individual cells. The results suggest that it is suitable to learn knowledge from pre‐clinical cell lines to infer pre‐existing cell subpopulations with different drug sensitivities prior to drug exposure. In addition, the model offers a new perspective on drug combinations. It is observed that drug‐resistant subpopulation can be sensitive to other drugs (e.g., a subset of JHU006 is Vorinostat‐resistant while Gefitinib‐sensitive); such finding corroborates the previously reported drug combination (Gefitinib + Vorinostat) strategy in several cancer types. The identified drug sensitivity biomarkers reveal insights into the tumor heterogeneity and treatment at cellular resolution.

Abstract Background Cancer molecular subtyping plays a critical role in individualized patient treatment. In previous studies, high-throughput gene expression signature-based methods have been proposed to identify cancer subtypes. Unfortunately, the existing ones suffer from the curse of dimensionality, data sparsity, and computational deficiency. Methods To address those problems, we propose a computational framework for colorectal cancer subtyping without any exploitation in model complexity and generality. A supervised learning framework based on deep learning (DeepCSD) is proposed to identify cancer subtypes. Specifically, based on the differentially expressed genes under cancer consensus molecular subtyping, we design a minimalist feed-forward neural network to capture the distinct molecular features in different cancer subtypes. To mitigate the overfitting phenomenon of deep learning as much as possible, L 1 and L 2 regularization and dropout layers are added. Results For demonstrating the effectiveness of DeepCSD, we compared it with other methods including Random Forest (RF), Deep forest (gcForest), support vector machine (SVM), XGBoost, and DeepCC on eight independent colorectal cancer datasets. The results reflect that DeepCSD can achieve superior performance over other algorithms. In addition, gene ontology enrichment and pathology analysis are conducted to reveal novel insights into the cancer subtype identification and characterization mechanisms. Conclusions DeepCSD considers all subtype-specific genes as input, which is pathologically necessary for its completeness. At the same time, DeepCSD shows remarkable robustness in handling cross-platform gene expression data, achieving similar performance on both training and test data without significant model overfitting or exploitation of model complexity.

With the development of next-generation sequencing technologies, single-cell RNA sequencing (scRNA-seq) has become one indispensable tool to reveal the wide heterogeneity between cells. Clustering is a fundamental task in this analysis to disclose the transcriptomic profiles of single cells and is one of the key computational problems that has received widespread attention. Recently, many clustering algorithms have been developed for the scRNA-seq data. Nevertheless, the computational models often suffer from realistic restrictions such as numerical instability, high dimensionality and computational scalability. Moreover, the accumulating cell numbers and high dropout rates bring a huge computational challenge to the analysis. To address these limitations, we first provide a systematic and extensive performance evaluation of four feature selection methods and nine scRNA-seq clustering algorithms on fourteen real single-cell RNA-seq datasets. Based on this, we then propose an accurate single-cell data analysis via Ensemble Feature Selection based Clustering, called scEFSC. Indeed, the algorithm employs several unsupervised feature selections to remove genes that do not contribute significantly to the scRNA-seq data. After that, different single-cell RNA-seq clustering algorithms are proposed to cluster the data filtered by multiple unsupervised feature selections, and then the clustering results are combined using weighted-based meta-clustering. We applied scEFSC to the fourteen real single-cell RNA-seq datasets and the experimental results demonstrated that our proposed scEFSC outperformed the other scRNA-seq clustering algorithms with several evaluation metrics. In addition, we established the biological interpretability of scEFSC by carrying out differential gene expression analysis, gene ontology enrichment and KEGG analysis. scEFSC is available at https://github.com/Conan-Bian/scEFSC.

Post-translational modifications (PTMs) are closely linked to numerous diseases, playing a significant role in regulating protein structures, activities, and functions. Therefore, the identification of PTMs is crucial for understanding the mechanisms of cell biology and diseases therapy. Compared to traditional machine learning methods, the deep learning approaches for PTM prediction provide accurate and rapid screening, guiding the downstream wet experiments to leverage the screened information for focused studies. In this paper, we reviewed the recent works in deep learning to identify phosphorylation, acetylation, ubiquitination, and other PTM types. In addition, we summarized PTM databases and discussed future directions with critical insights.

Enhancers are short non-coding DNA sequences outside of the target promoter regions that can be bound by specific proteins to increase a gene's transcriptional activity, which has a crucial role in the spatiotemporal and quantitative regulation of gene expression. However, enhancers do not have a specific sequence motifs or structures, and their scattered distribution in the genome makes the identification of enhancers from human cell lines particularly challenging. Here we present a novel, stacked multivariate fusion framework called SMFM, which enables a comprehensive identification and analysis of enhancers from regulatory DNA sequences as well as their interpretation. Specifically, to characterize the hierarchical relationships of enhancer sequences, multi-source biological information and dynamic semantic information are fused to represent regulatory DNA enhancer sequences. Then, we implement a deep learning-based sequence network to learn the feature representation of the enhancer sequences comprehensively and to extract the implicit relationships in the dynamic semantic information. Ultimately, an ensemble machine learning classifier is trained based on the refined multi-source features and dynamic implicit relations obtained from the deep learning-based sequence network. Benchmarking experiments demonstrated that SMFM significantly outperforms other existing methods using several evaluation metrics. In addition, an independent test set was used to validate the generalization performance of SMFM by comparing it to other state-of-the-art enhancer identification methods. Moreover, we performed motif analysis based on the contribution scores of different bases of enhancer sequences to the final identification results. Besides, we conducted interpretability analysis of the identified enhancer sequences based on attention weights of EnhancerBERT, a fine-tuned BERT model that provides new insights into exploring the gene semantic information likely to underlie the discovered enhancers in an interpretable manner. Finally, in a human placenta study with 4,562 active distal gene regulatory enhancers, SMFM successfully exposed tissue-related placental development and the differential mechanism, demonstrating the generalizability and stability of our proposed framework.

Summary: Graph and image are two common representations of Hi-C cis-contact maps. Existing computational tools have only adopted Hi-C data modeled as unitary data structures but neglected the potential advantages of synergizing the information of different views. Here we propose GILoop, a dual-branch neural network that learns from both representations to identify genome-wide CTCF-mediated loops. With GILoop, we explore the combined strength of integrating the two view representations of Hi-C data and corroborate the complementary relationship between the views. In particular, the model outperforms the state-of-the-art loop calling framework and is also more robust against low-quality Hi-C libraries. We also uncover distinct preferences for matrix density by graph-based and image-based models, revealing interesting insights into Hi-C data elucidation. Finally, along with multiple transfer-learning case studies, we demonstrate that GILoop can accurately model the organizational and functional patterns of CTCF-mediated looping across different cell lines.

Abstract Background Coronavirus Disease 2019 (COVID-19) led to pandemic that affected almost all countries in the world. Many countries have implemented border restriction as a public health measure to limit local outbreak. However, there is inadequate scientific data to support such a practice, especially in the presence of an established local transmission of the disease. Objective To apply a metapopulation Susceptible-Exposed-Infectious-Recovered (SEIR) model with inspected migration to investigate the effect of border restriction as a public health measure to limit outbreak of coronavirus disease 2019. Methods We apply a modified metapopulation SEIR model with inspected migration with simulating population migration, and incorporating parameters such as efficiency of custom inspection in blocking infected travelers in the model. The population sizes were retrieved from government reports, while the number of COVID-19 patients were retrieved from Hong Kong Department of Health and China Centre for Disease Control (CDC) data. The R 0 was obtained from previous clinical studies. Results Complete border closure can help to reduce the cumulative COVID-19 case number and mortality in Hong Kong by 13.99% and 13.98% respectively. To prevent full occupancy of isolation facilities in Hong Kong; effective public health measures to reduce local R 0 to below 1.6 was necessary, apart from having complete border closure. Conclusions Early complete travel restriction is effective in reducing cumulative cases and mortality. However, additional anti-COVID-19 measures to reduce local R 0 to below 1.6 are necessary to prevent COVID-19 cases from overwhelming hospital isolation facilities.

Summary: Human disease prediction from microbiome data has broad implications in metagenomics. It is rare for the existing methods to consider abundance profiles from both known and unknown microbial organisms, or capture the taxonomic relationships among microbial taxa, leading to significant information loss. On the other hand, deep learning has shown unprecedented advantages in classification tasks for its feature-learning ability. However, it encounters the opposite situation in metagenome-based disease prediction since high-dimensional low-sample-size metagenomic datasets can lead to severe overfitting; and black-box model fails in providing biological explanations. To circumvent the related problems, we developed MetaDR, a comprehensive machine learning-based framework that integrates various information and deep learning to predict human diseases. Experimental results indicate that MetaDR achieves competitive prediction performance with a reduction in running time, and effectively discovers the informative features with biological insights.

Predicting products of organic chemical reactions is useful in chemical sciences, especially when one or more reactants are new organics. However, the performance of traditional learning models heavily relies on high-quality labeled data. In this work, to utilize unlabeled data for better prediction performance, we propose a method that combines semi-supervised learning with graph convolutional neural networks for chemical reaction prediction. First, we propose a Mean Teacher Weisfeiler–Lehman Network to find the reaction centers. Then, we construct the candidate product set. Finally, we use an Improved Weisfeiler–Lehman Difference Network to rank candidate products. Experimental results demonstrate that, with 400k labeled data, our framework can improve the top-5 accuracy by 0.7% using 35k unlabeled data. When the proportion of unlabeled data increases, the performance gain can be larger. For example, with 80k labeled data and 35k unlabeled data, the performance gain with our framework can be 1.8%.

Summary: The early detection of cancers has the potential to save many lives. A recent attempt has been demonstrated successful. However, we note several critical limitations. Given the central importance and broad impact of early cancer detection, we aspire to address those limitations. We explore different supervised learning approaches for multiple cancer type detection and observe significant improvements; for instance, one of our approaches (i.e., CancerA1DE) can double the existing sensitivity from 38% to 77% for the earliest cancer detection (i.e., Stage I) at the 99% specificity level. For Stage II, it can even reach up to about 90% across multiple cancer types. In addition, CancerA1DE can also double the existing sensitivity from 30% to 70% for detecting breast cancers at the 99% specificity level. Data and model analysis are conducted to reveal the underlying reasons. A website is built at http://cancer.cs.cityu.edu.hk/. : Biological Sciences; Cancer Systems Biology; Cancer; Algorithms; Bioinformatics Subject Areas: Biological Sciences, Cancer Systems Biology, Cancer, Algorithms, Bioinformatics

Cancer gene expression data is of great importance in cancer subtype diagnosis and drug discovery. Many computational methods have been proposed to classify subtypes using those data. However, most of the previous computational methods suffer from poor interpretability, experimental noises, and low diagnostic quality. To address those problems, multiobjective ensemble cuckoo search based on decomposition (MOECSA) is proposed to optimize those four objectives simultaneously including the number of features, the accuracy, and two entropy-based measures: the relevance and the redundancy, classifying the cancer gene expression data with high predictive power for different cardinality levels under multiple objectives. A novel binary encoding is proposed to choose gene subsets from the cancer gene expression data for calculating four objective functions. Furthermore, an effective ensemble mechanism blended in the cuckoo search algorithm framework is applied to balance the convergence speed and population diversity in MOECSA. To demonstrate the effectiveness and efficiency of the proposed algorithm, experiments on thirty-five benchmark cancer gene expression datasets, four independent disease datasets, and one sequencing-based dataset are carried out to compare MOECSA with the six state-of-the-art multiobjective evolutionary algorithms and seven traditional classification algorithms. The experimental results in different perspectives demonstrate that MOECSA has better diagnosis performance than others at multiple levels.

Graph neural networks (GNNs) with feature propagation have demonstrated their power in handling unstructured data. However, feature propagation is also a smooth process that tends to make all node representations similar as the number of propagation increases. To address this problem, we propose a novel Block-Based Adaptive Decoupling (BBAD) Framework to produce effective deep GNNs by utilizing backbone networks. In this framework, each block contains a shallow GNN with feature propagation and transformation decoupled. We also introduce layer regularizations and flexible receptive fields to automatically adjust the propagation depth and to provide different aggregation hops for each node, respectively. We prove that the traditional coupled GNNs are more likely to suffer from over-smoothing when they become deep. We also demonstrate the diversity of outputs from different blocks of our framework. In the experiments, we conduct semi-supervised and fully supervised node classifications on benchmark datasets, and the results verify that our method can not only improve the performance of various backbone networks, but also is superior to existing deep graph neural networks with less parameters.

Abstract Background Identification of miRNA-disease associations has attracted much attention recently due to the functional roles of miRNAs implicated in various biological and pathological processes. Great efforts have been made to discover the potential associations between miRNAs and diseases both experimentally and computationally. Although reliable, the experimental methods are in general time-consuming and labor-intensive. In comparison, computational methods are more efficient and applicable to large-scale datasets. Methods In this paper, we propose a novel semi-supervised model to predict miRNA-disease associations via $$\ell_{1}$$ ℓ1 -norm graph. Specifically, we first recalculate the miRNA functional similarities as well as the disease semantic similarities based on the latest version of MeSH descriptors and HMDD. We then update the similarity matrices and association matrix iteratively in both miRNA space and disease space. The optimized association matrices from each space are combined together as the final output. Results Compared with four state-of-the-art prediction methods, our method achieved favorable performance with AUCs of 0.943 and 0.946 in both global LOOCV and local LOOCV, respectively. In addition, we carried out three types of case studies on five common human diseases, and most of the top 50 predicted miRNAs were confirmed to be associated with the investigated diseases by four databases dbDEMC, PheomiR, miR2Disease and miRwayDB. Specifically, our results provided potential evidence that miRNAs within the same family or cluster were likely to play functional roles together in given diseases. Conclusions Taken together, the experimental results clearly demonstrated the utility of the proposed method. We anticipated that our method could serve as a reliable and efficient tool for miRNA-disease association prediction.

Abstract The off‐target effects induced by guide RNAs in the CRISPR/Cas9 gene‐editing system have raised substantial concerns in recent years. Many in silico predictive models have been developed for predicting the off‐target activities; however, few are capable of predicting the off‐target activities with insertions or deletions between guide RNA and target DNA sequence pair. In order to fill this gap, a recurrent convolutional network named CRISPR‐Net is developed for scoring the gRNA‐target pairs with mismatches and indels; and a machine‐learning based model named CRISPR‐Net‐Aggregate is also developed for aggregating the scores as the consensus off‐target score for each potential guide RNA. It is demonstrated that CRISPR‐Net achieves competitive performance on CIRCLE‐Seq and GUIDE‐seq datasets with indels and mismatches, outperforming the state‐of‐the‐art off‐target prediction methods on two independent mismatch‐only datasets. The CRISPR‐Net‐Aggregate also surpasses a competing method on the aggregation task. Moreover, a two‐stage sensitivity analysis is introduced to visualize the CRISPR‐Net prediction on the gRNA‐target pair of interest, demonstrating how implicit knowledge encoded in CRISPR‐Net contributes to the accurate off‐target activity quantification. Finally, the source code is made available at the Code Ocean repository (https://codeocean.com/capsule/9553651/tree/v1).

Summary: Although the existing works on DNA motif discovery on DNA sequences are plethoric, mechanistic knowledge to infer DNA motifs from protein sequences across multiple DNA-binding domain families without conducting any wet-lab experiments is still lacking. Therefore, the k-spectrum recognition modeling is proposed to address the issues at the highest possible resolutions. The k-spectrum model can capture DNA motif patterns from protein sequences at the resolution in which local sequence context and nucleotide dependency can be taken into account completely. Multiple evaluation metrics are adopted and measured on millions of k-mer binding intensities from 92 proteins across 5 DNA-binding families (i.e., bHLH, bZIP, ETS, Forkhead, and Homeodomain), demonstrating its competitive edges. In addition, it not only can contribute to DNA motif recognition modeling but also can help prioritize the observed or even unobserved binding of single nucleotide variants on transcription factor binding sites in a genome-wide manner. : Genetics; Quantitative Genetics; Bioinformatics; Computational Biology; DNA Motifs Subject Areas: Genetics, Quantitative Genetics, Bioinformatics, Computational Biology, DNA Motifs

Non-synonymous single nucleotide polymorphisms (nsSNPs) may result in pathogenic changes that are associated with human diseases. Accurate prediction of these deleterious nsSNPs is in high demand. The existing predictors of deleterious nsSNPs secure modest levels of predictive performance, leaving room for improvements. We propose a new sequence-based predictor, DMBS, which addresses the need to improve the predictive quality. The design of DMBS relies on the observation that the deleterious mutations are likely to occur at the highly conserved and functionally important positions in the protein sequence. Correspondingly, we introduce two innovative components. First, we improve the estimates of the conservation computed from the multiple sequence profiles based on two complementary databases and two complementary alignment algorithms. Second, we utilize putative annotations of functional/binding residues produced by two state-of-the-art sequence-based methods. These inputs are processed by a random forests model that provides favorable predictive performance when empirically compared against five other machine-learning algorithms. Empirical results on four benchmark datasets reveal that DMBS achieves AUC > 0.94, outperforming current methods, including protein structure-based approaches. In particular, DMBS secures AUC = 0.97 for the SNPdbe and ExoVar datasets, compared to AUC = 0.70 and 0.88, respectively, that were obtained by the best available methods. Further tests on the independent HumVar dataset shows that our method significantly outperforms the state-of-the-art method SNPdryad. We conclude that DMBS provides accurate predictions that can effectively guide wet-lab experiments in a high-throughput manner.

With the advances of liquid biopsy technology, there is increasing evidence that body fluid such as blood, urine, and saliva could harbor the potential biomarkers associated with tumor origin. Traditional correlation analysis methods are no longer sufficient to capture the high-resolution complex relationships between biomarkers and cancer subtype heterogeneity. To address the challenge, researchers proposed machine learning techniques with liquid biopsy data to explore the essence of tumor origin together. In this survey, we review the machine learning protocols and provide corresponding code demos for the approaches mentioned. We discuss algorithmic principles and frameworks extensively developed to reveal cancer mechanisms and consider the future prospects in biomarker exploration and cancer diagnostics.

Genistein and icariin are flavonoid compounds that exhibit estrogen-like properties in inducing bone formation and reducing bone loss associated with estrogen deficiency in both preclinical and clinical studies. However, the mechanisms that are involved in mediating their estrogenic actions in bone cells are far from clear. The present study aimed to study the signaling pathways that mediate the estrogenic actions of genistein and icariin in osteoblastic cells. The effects of genistein and icariin on the activation of estrogen receptor (ER) and the downstream mitogen-activated protein kinase (MAPK) and phosphatidylinositol 3-kinase (PI3K)/Akt signaling pathway in murine osteoblastic MC3T3-E1 cells and rat osteoblastic UMR-106 cells were studied. As expected, genistein displayed higher binding affinity toward ERβ than ERα and significantly induced estrogen response element (ERE)-dependent transcription in UMR-106 cells in a dose-dependent manner. In contrast, icariin failed to bind to ERα or ERβ and did not induce ERE-dependent transcription in UMR-106 cells at 10-10 to 10-7 M. The effects of genistein (10 nM) and icariin (0.1 μM) on cell proliferation and differentiation in osteoblastic UMR-106 cells were abolished in the presence of ER antagonist ICI 182,780 (1 μM), MAPK inhibitor U0126 (10 μM), and PI3K inhibitor LY294002 (10 μM). Genistein at 10 nM rapidly induced ERK1/2 phosphorylation at 5–10 min in UMR-106 cells and the phosphorylation of ERα at both Ser118 and Ser167 in both MC3T3-E1 and transfected UMR-106 cells whereas icariin at 0.1 μM rapidly activated both ERK1/2 and Akt phosphorylation in UMR-106 cells and subsequent ERα phosphorylation at both Ser118 and Ser167 in MC3T3-E1 and transfected UMR-106 cells. Confocal imaging studies confirmed that the phosphorylation of ERα at Ser 118 and Ser 167 by genistein and icariin in MC3T3-E1 cells was mediated via MAPK- and PI3K-dependent pathway, respectively. Furthermore, our studies showed that icariin exerted stronger anti-apoptotic effects than genistein and 17β-estradiol (E2) and inhibited the cleavage of downstream caspase-3 in MC3T3-E1 cells induced by a potent PI3K inhibitor, PI828 (at 2 μM). These results indicated that the mechanisms that mediate the estrogenic actions of icariin in osteoblastic cells are different from those of genistein.

The analysis of animal movement from telemetry data provides insights into how and why animals move. While traditional approaches to such analysis mostly focus on predicting animal states during movement, we describe an approach that allows us to identify representative movement patterns of different animal groups. To do this, we propose a carefully designed recurrent neural network and combine it with telemetry data for automatic feature extraction and identification of non-predefined representative patterns. In the experiment, we consider a particular marine predator species, the southern elephant seal, as an example. With our approach, we identify that the male seals in our data set share similar movement patterns when they are close to land. We identify this pattern recurring in a number of distant locations, consistent with alternative approaches from previous research.

Face detection for security cameras monitoring large and crowded areas is very important for public safety. However, it is much more difficult than traditional face detection tasks. One reason is, in large areas like squares, stations and stadiums, faces captured by cameras are usually at a low resolution and thus miss many facial details. In this paper, we improve popular cascade algorithms by proposing a novel multi-resolution framework that utilizes parallel convolutional neural network cascades for detecting faces in large scene. This framework utilizes the face and head-with-shoulder information together to deal with the large area surveillance images. Comparing with popular cascade algorithms, our method outperforms them by a large margin.

The present study was designed to characterize the bone protective effects of (−)-epiafzelechin (EAF), a flavan-3-ol, in mature ovariectomized mice model and its ability to stimulate osteoblastic activity and inhibit osteoclastic activity. Mature C57BL/6 mice (three to four months old) were either ovariectomised (OVX) or sham-operated and subjected to treatment (vehicle, 17β-oestradiol (E2, 200 μg/kg/day) or EAF (500 μg/kg/day) orally for six weeks. EAF and E2 significantly reduced urinary calcium (Ca) excretion, serum osteocalcin (OCN), and urinary deoxy-pyridinoline (DPD); increased bone mineral density (BMD); and improved micro-architectural properties in OVX mice. EAF significantly increased cell viability, alkaline phosphatise (ALP) activity, and collagen content, as well as runt-related transcriptional factor 2 (Runx2) mRNA expression in murine osteoblastic MC3T3-E1 cells. In addition, EAF significantly reduced the viability of osteoclast precursor murine leukemia monocyte RAW 264.7 cells and tartrate-resistant acid phosphatase (TRAP) activities in mature osteoclastic RAW 264.7 cells. EAF is a bioactive flavan-3-ol that protects estrogen deficiency-induced bone loss in OVX mice and exerts direct modulating effects in bone cells in vitro.

Rhizoma Drynariae (RD), as one of the most common clinically used folk medicines, has been reported to exert potent anti-osteoporotic activity. The bioactive ingredients and mechanisms that account for its bone protective effects are under active investigation. Here we adopt a novel in silico target fishing method to reveal the target profile of RD. Cathepsin K (Ctsk) is one of the cysteine proteases that is over-expressed in osteoclasts and accounts for the increase in bone resorption in metabolic bone disorders such as postmenopausal osteoporosis. It has been the focus of target based drug discovery in recent years. We have identified two components in RD, Kushennol F and Sophoraflavanone G, that can potentially interact with Ctsk. Biological studies were performed to verify the effects of these compounds on Ctsk and its related bone resorption process, which include the use of in vitro fluorescence-based Ctsk enzyme assay, bone resorption pit formation assay, as well as Receptor Activator of Nuclear factor κB (NF-κB) ligand (RANKL)-induced osteoclastogenesis using murine RAW264.7 cells. Finally, the binding mode and stability of these two compounds that interact with Ctsk were determined by molecular docking and dynamics methods. The results showed that the in silico target fishing method could successfully identify two components from RD that show inhibitory effects on the bone resorption process related to protease Ctsk.

With rapid advances in the development of DNA sequencing technologies, a plethora of high-throughput genome and proteome data from a diverse spectrum of organisms have been generated. The functional annotation and evolutionary history of proteins are usually inferred from domains predicted from the genome sequences. Traditional database-based domain prediction methods cannot identify novel domains, however, and alignment-based methods, which look for recurring segments in the proteome, are computationally demanding. Here, we propose a novel genome-wide domain prediction method, SECOM. Instead of conducting all-against-all sequence alignment, SECOM first indexes all the proteins in the genome by using a hash seed function. Local similarity can thus be detected and encoded into a graph structure, in which each node represents a protein sequence and each edge weight represents the shared hash seeds between the two nodes. SECOM then formulates the domain prediction problem as an overlapping community-finding problem in this graph. A backward graph percolation algorithm that efficiently identifies the domains is proposed. We tested SECOM on five recently sequenced genomes of aquatic animals. Our tests demonstrated that SECOM was able to identify most of the known domains identified by InterProScan. When compared with the alignment-based method, SECOM showed higher sensitivity in detecting putative novel domains, while it was also three orders of magnitude faster. For example, SECOM was able to predict a novel sponge-specific domain in nucleoside-triphosphatase (NTPases). Furthermore, SECOM discovered two novel domains, likely of bacterial origin, that are taxonomically restricted to sea anemone and hydra. SECOM is an open-source program and available at http://sfb.kaust.edu.sa/Pages/Software.aspx.

We analyze the passengers' traffic pattern for 1.58 million taxi trips of Shanghai, China. By employing the non-negative matrix factorization and optimization methods, we find that, people travel on workdays mainly for three purposes: commuting between home and workplace, traveling from workplace to workplace, and others such as leisure activities. Therefore, traffic flow in one area or between any pair of locations can be approximated by a linear combination of three basis flows, corresponding to the three purposes respectively. We name the coefficients in the linear combination as traffic powers, each of which indicates the strength of each basis flow. The traffic powers on different days are typically different even for the same location, due to the uncertainty of the human motion. Therefore, we provide a probability distribution function for the relative deviation of the traffic power. This distribution function is in terms of a series of functions for normalized binomial distributions. It can be well explained by statistical theories and is verified by empirical data. These findings are applicable in predicting the road traffic, tracing the traffic pattern and diagnosing the traffic related abnormal events. These results can also be used to infer land uses of urban area quite parsimoniously.