scHiCStackL: a stacking ensemble learning-based method for single-cell Hi-C classification using cell embedding

Construction of machine learning diagnostic models for cardiovascular pan-disease based on blood routine and biochemical detection data

BACKGROUND

Cardiovascular disease, also known as circulation system disease, remains the leading cause of morbidity and mortality worldwide. Traditional methods for diagnosing cardiovascular disease are often expensive and time-consuming. So the purpose of this study is to construct machine learning models for the diagnosis of cardiovascular diseases using easily accessible blood routine and biochemical detection data and explore the unique hematologic features of cardiovascular diseases, including some metabolic indicators.

METHODS

After the data preprocessing, 25,794 healthy people and 32,822 circulation system disease patients with the blood routine and biochemical detection data were utilized for our study. We selected logistic regression, random forest, support vector machine, eXtreme Gradient Boosting (XGBoost), and deep neural network to construct models. Finally, the SHAP algorithm was used to interpret models.

RESULTS

The circulation system disease prediction model constructed by XGBoost possessed the best performance (AUC: 0.9921 (0.9911-0.9930); Acc: 0.9618 (0.9588-0.9645); Sn: 0.9690 (0.9655-0.9723); Sp: 0.9526 (0.9477-0.9572); PPV: 0.9631 (0.9592-0.9668); NPV: 0.9600 (0.9556-0.9644); MCC: 0.9224 (0.9165-0.9279); F1 score: 0.9661 (0.9634-0.9686)). Most models of distinguishing various circulation system diseases also had good performance, the model performance of distinguishing dilated cardiomyopathy from other circulation system diseases was the best (AUC: 0.9267 (0.8663-0.9752)). The model interpretation by the SHAP algorithm indicated features from biochemical detection made major contributions to predicting circulation system disease, such as potassium (K), total protein (TP), albumin (ALB), and indirect bilirubin (NBIL). But for models of distinguishing various circulation system diseases, we found that red blood cell count (RBC), K, direct bilirubin (DBIL), and glucose (GLU) were the top 4 features subdividing various circulation system diseases.

CONCLUSIONS

The present study constructed multiple models using 50 features from the blood routine and biochemical detection data for the diagnosis of various circulation system diseases. At the same time, the unique hematologic features of various circulation system diseases, including some metabolic-related indicators, were also explored. This cost-effective work will benefit more people and help diagnose and prevent circulation system diseases.

Integration of scHi-C and scRNA-seq data defines distinct 3D-regulated and biological-context dependent cell subpopulations

An integration of 3D chromatin structure and gene expression at single-cell resolution has yet been demonstrated. Here, we develop a computational method, a multiomic data integration (MUDI) algorithm, which integrates scHi-C and scRNA-seq data to precisely define the 3D-regulated and biological-context dependent cell subpopulations or topologically integrated subpopulations (TISPs). We demonstrate its algorithmic utility on the publicly available and newly generated scHi-C and scRNA-seq data. We then test and apply MUDI in a breast cancer cell model system to demonstrate its biological-context dependent utility. We find the newly defined topologically conserved associating domain (CAD) is the characteristic single-cell 3D chromatin structure and better characterizes chromatin domains in single-cell resolution. We further identify 20 TISPs uniquely characterizing 3D-regulated breast cancer cellular states. We reveal two of TISPs are remarkably resemble to high cycling breast cancer persister cells and chromatin modifying enzymes might be functional regulators to drive the alteration of the 3D chromatin structures. Our comprehensive integration of scHi-C and scRNA-seq data in cancer cells at single-cell resolution provides mechanistic insights into 3D-regulated heterogeneity of developing drug-tolerant cancer cells.

scHiCyclePred: a deep learning framework for predicting cell cycle phases from single-cell Hi-C data using multi-scale interaction information

The emergence of single-cell Hi-C (scHi-C) technology has provided unprecedented opportunities for investigating the intricate relationship between cell cycle phases and the three-dimensional (3D) structure of chromatin. However, accurately predicting cell cycle phases based on scHi-C data remains a formidable challenge. Here, we present scHiCyclePred, a prediction model that integrates multiple feature sets to leverage scHi-C data for predicting cell cycle phases. scHiCyclePred extracts 3D chromatin structure features by incorporating multi-scale interaction information. The comparative analysis illustrates that scHiCyclePred surpasses existing methods such as Nagano_method and CIRCLET across various metrics including accuracy (ACC), F1 score, Precision, Recall, and balanced accuracy (BACC). In addition, we evaluate scHiCyclePred against the previously published CIRCLET using the dataset of complex tissues (Liu_dataset). Experimental results reveal significant improvements with scHiCyclePred exhibiting improvements of 0.39, 0.52, 0.52, and 0.39 over the CIRCLET in terms of ACC, F1 score, Precision, and Recall metrics, respectively. Furthermore, we conduct analyses on three-dimensional chromatin dynamics and gene features during the cell cycle, providing a more comprehensive understanding of cell cycle dynamics through chromatin structure. scHiCyclePred not only offers insights into cell biology but also holds promise for catalyzing breakthroughs in disease research. Access scHiCyclePred on GitHub at https:// github.com/HaoWuLab-Bioinformatics/ scHiCyclePred .

Single-cell omics: experimental workflow, data analyses and applications

Cells are the fundamental units of biological systems and exhibit unique development trajectories and molecular features. Our exploration of how the genomes orchestrate the formation and maintenance of each cell, and control the cellular phenotypes of various organismsis, is both captivating and intricate. Since the inception of the first single-cell RNA technology, technologies related to single-cell sequencing have experienced rapid advancements in recent years. These technologies have expanded horizontally to include single-cell genome, epigenome, proteome, and metabolome, while vertically, they have progressed to integrate multiple omics data and incorporate additional information such as spatial scRNA-seq and CRISPR screening. Single-cell omics represent a groundbreaking advancement in the biomedical field, offering profound insights into the understanding of complex diseases, including cancers. Here, we comprehensively summarize recent advances in single-cell omics technologies, with a specific focus on the methodology section. This overview aims to guide researchers in selecting appropriate methods for single-cell sequencing and related data analysis.

CTPredictor: A comprehensive and robust framework for predicting cell types by integrating multi-scale features from single-cell Hi-C data

Single-cell Hi-C (scHi-C) has emerged as a powerful technology for deciphering cell-to-cell variability in three-dimensional (3D) chromatin organization, providing insights into genome-wide chromatin interactions and their correlation with cellular functions. Nevertheless, the accurate identification of cell types across different datasets remains a formidable challenge, hindering comprehensive investigations into genome structure. In response, we introduce CTPredictor, an innovative computational method that integrates multi-scale features to accurately predict cell types in various datasets. CTPredictor strategically incorporates three distinct feature sets, namely, small intra-domain contact probability (SICP), smoothed small intra-domain contact probability (SSICP), and smoothed bin contact probability (SBCP). The resulting fusion classification model significantly enhances the accuracy of cell type prediction based on single-cell Hi-C data (scHi-C). Rigorous benchmarking against established methods and three conventional machine learning approaches demonstrates the robust performance of CTPredictor, positioning it as an advanced tool for cell type prediction within scHi-C data. Beyond its prediction capabilities, CTPredictor holds promise in illuminating 3D genome structures and their functional significance across a wide array of biological processes.

PseUpred-ELPSO Is an Ensemble Learning Predictor with Particle Swarm Optimizer for Improving the Prediction of RNA Pseudouridine Sites

RNA pseudouridine modification exists in different RNA types of many species, and it has a significant role in regulating the expression of biological processes. To understand the functional mechanisms for RNA pseudouridine sites, the accurate identification of pseudouridine sites in RNA sequences is essential. Although several fast and inexpensive computational methods have been proposed, the challenge of improving recognition accuracy and generalization still exists. This study proposed a novel ensemble predictor called PseUpred-ELPSO for improved RNA pseudouridine site prediction. After analyzing the nucleotide composition preferences between RNA pseudouridine site sequences, two feature representations were determined and fed into the stacking ensemble framework. Then, using five tree-based machine learning classifiers as base classifiers, 30-dimensional RNA profiles are constructed to represent RNA sequences, and using the PSO algorithm, the weights of the RNA profiles were searched to further enhance the representation. A logistic regression classifier was used as a meta-classifier to complete the final predictions. Compared to the most advanced predictors, the performance of PseUpred-ELPSO is superior in both cross-validation and the independent test. Based on the PseUpred-ELPSO predictor, a free and easy-to-operate web server has been established, which will be a powerful tool for pseudouridine site identification.

Finding potential lncRNA-disease associations using a boosting-based ensemble learning model

Introduction: Long non-coding RNAs (lncRNAs) have been in the clinical use as potential prognostic biomarkers of various types of cancer. Identifying associations between lncRNAs and diseases helps capture the potential biomarkers and design efficient therapeutic options for diseases. Wet experiments for identifying these associations are costly and laborious. Methods: We developed LDA-SABC, a novel boosting-based framework for lncRNA-disease association (LDA) prediction. LDA-SABC extracts LDA features based on singular value decomposition (SVD) and classifies lncRNA-disease pairs (LDPs) by incorporating LightGBM and AdaBoost into the convolutional neural network. Results: The LDA-SABC performance was evaluated under five-fold cross validations (CVs) on lncRNAs, diseases, and LDPs. It obviously outperformed four other classical LDA inference methods (SDLDA, LDNFSGB, LDASR, and IPCAF) through precision, recall, accuracy, F1 score, AUC, and AUPR. Based on the accurate LDA prediction performance of LDA-SABC, we used it to find potential lncRNA biomarkers for lung cancer. The results elucidated that 7SK and HULC could have a relationship with non-small-cell lung cancer (NSCLC) and lung adenocarcinoma (LUAD), respectively. Conclusion: We hope that our proposed LDA-SABC method can help improve the LDA identification.

Identifying potential ligand-receptor interactions based on gradient boosted neural network and interpretable boosting machine for intercellular communication analysis

Cell-cell communication is essential to many key biological processes. Intercellular communication is generally mediated by ligand-receptor interactions (LRIs). Thus, building a comprehensive and high-quality LRI resource can significantly improve intercellular communication analysis. Meantime, due to lack of a "gold standard" dataset, it remains a challenge to evaluate LRI-mediated intercellular communication results. Here, we introduce CellGiQ, a high-confident LRI prediction framework for intercellular communication analysis. Highly confident LRIs are first inferred by LRI feature extraction with BioTriangle, LRI selection using LightGBM, and LRI classification based on ensemble of gradient boosted neural network and interpretable boosting machine. Subsequently, known and identified high-confident LRIs are filtered by combining single-cell RNA sequencing (scRNA-seq) data and further applied to intercellular communication inference through a quartile scoring strategy. To validation the predictions, CellGiQ exploited several evaluation strategies: using AUC and AUPR, it surpassed six competing LRI prediction models on four LRI datasets; through Venn diagrams and molecular docking, its predicted LRIs were validated by five other popular intercellular communication inference methods; based on the overlapping LRIs, it computed high Jaccard index with six other state-of-the-art intercellular communication prediction tools within human HNSCC tissues; by comparing with classical models and literature retrieve, its inferred HNSCC-related intercellular communication results was further validated. The novelty of this study is to identify high-confident LRIs based on machine learning as well as design several LRI validation ways, providing reference for computational LRI prediction. CellGiQ provides an open-source and useful tool to decompose LRI-mediated intercellular communication at single cell resolution. CellGiQ is freely available at https://github.com/plhhnu/CellGiQ.

Predicting Anti-inflammatory Peptides by Ensemble Machine Learning and Deep Learning

Inflammation is a biological response to harmful stimuli, aiding in the maintenance of tissue homeostasis. However, excessive or persistent inflammation can precipitate a myriad of pathological conditions. Although current treatments such as NSAIDs, corticosteroids, and immunosuppressants are effective, they can have side effects and resistance issues. In this backdrop, anti-inflammatory peptides (AIPs) have emerged as a promising therapeutic approach against inflammation. Leveraging machine learning methods, we have the opportunity to accelerate the discovery and investigation of these AIPs more effectively. In this study, we proposed an advanced framework by ensemble machine learning and deep learning for AIP prediction. Initially, we constructed three individual models with extremely randomized trees (ET), gated recurrent unit (GRU), and convolutional neural networks (CNNs) with attention mechanism and then used stacking architecture to build the final predictor. By utilizing various sequence encodings and combining the strengths of different algorithms, our predictor demonstrated exemplary performance. On our independent test set, our model achieved an accuracy, MCC, and F1-score of 0.757, 0.500, and 0.707, respectively, clearly outperforming other contemporary AIP prediction methods. Additionally, our model offers profound insights into the feature interpretation of AIPs, establishing a valuable knowledge foundation for the design and development of future anti-inflammatory strategies.

LDA-VGHB: identifying potential lncRNA-disease associations with singular value decomposition, variational graph auto-encoder and heterogeneous Newton boosting machine

Long noncoding RNAs (lncRNAs) participate in various biological processes and have close linkages with diseases. In vivo and in vitro experiments have validated many associations between lncRNAs and diseases. However, biological experiments are time-consuming and expensive. Here, we introduce LDA-VGHB, an lncRNA-disease association (LDA) identification framework, by incorporating feature extraction based on singular value decomposition and variational graph autoencoder and LDA classification based on heterogeneous Newton boosting machine. LDA-VGHB was compared with four classical LDA prediction methods (i.e. SDLDA, LDNFSGB, IPCARF and LDASR) and four popular boosting models (XGBoost, AdaBoost, CatBoost and LightGBM) under 5-fold cross-validations on lncRNAs, diseases, lncRNA-disease pairs and independent lncRNAs and independent diseases, respectively. It greatly outperformed the other methods with its prominent performance under four different cross-validations on the lncRNADisease and MNDR databases. We further investigated potential lncRNAs for lung cancer, breast cancer, colorectal cancer and kidney neoplasms and inferred the top 20 lncRNAs associated with them among all their unobserved lncRNAs. The results showed that most of the predicted top 20 lncRNAs have been verified by biomedical experiments provided by the Lnc2Cancer 3.0, lncRNADisease v2.0 and RNADisease databases as well as publications. We found that HAR1A, KCNQ1DN, ZFAT-AS1 and HAR1B could associate with lung cancer, breast cancer, colorectal cancer and kidney neoplasms, respectively. The results need further biological experimental validation. We foresee that LDA-VGHB was capable of identifying possible lncRNAs for complex diseases. LDA-VGHB is publicly available at https://github.com/plhhnu/LDA-VGHB.

Integration of scHi-C and scRNA-seq data defines distinct 3D-regulated and biological-context dependent cell subpopulations

An integration of 3D chromatin structure and gene expression at single-cell resolution has yet been demonstrated. Here, we develop a computational method, a multiomic data integration (MUDI) algorithm, which integrates scHi-C and scRNA-seq data to precisely define the 3D-regulated and biological-context dependent cell subpopulations or topologically integrated subpopulations (TISPs). We demonstrate its algorithmic utility on the publicly available and newly generated scHi-C and scRNA-seq data. We then test and apply MUDI in a breast cancer cell model system to demonstrate its biological-context dependent utility. We found the newly defined topologically conserved associating domain (CAD) is the characteristic single-cell 3D chromatin structure and better characterizes chromatin domains in single-cell resolution. We further identify 20 TISPs uniquely characterizing 3D-regulated breast cancer cellular states. We reveal two of TISPs are remarkably resemble to high cycling breast cancer persister cells and chromatin modifying enzymes might be functional regulators to drive the alteration of the 3D chromatin structures. Our comprehensive integration of scHi-C and scRNA-seq data in cancer cells at single-cell resolution provides mechanistic insights into 3D-regulated heterogeneity of developing drug-tolerant cancer cells.

Predicting potential microbe-disease associations with graph attention autoencoder, positive-unlabeled learning, and deep neural network

Background

Microbes have dense linkages with human diseases. Balanced microorganisms protect human body against physiological disorders while unbalanced ones may cause diseases. Thus, identification of potential associations between microbes and diseases can contribute to the diagnosis and therapy of various complex diseases. Biological experiments for microbe-disease association (MDA) prediction are expensive, time-consuming, and labor-intensive.

Methods

We developed a computational MDA prediction method called GPUDMDA by combining graph attention autoencoder, positive-unlabeled learning, and deep neural network. First, GPUDMDA computes disease similarity and microbe similarity matrices by integrating their functional similarity and Gaussian association profile kernel similarity, respectively. Next, it learns the feature representation of each microbe-disease pair using graph attention autoencoder based on the obtained disease similarity and microbe similarity matrices. Third, it selects a few reliable negative MDAs based on positive-unlabeled learning. Finally, it takes the learned MDA features and the selected negative MDAs as inputs and designed a deep neural network to predict potential MDAs.

Results

GPUDMDA was compared with four state-of-the-art MDA identification models (i.e., MNNMDA, GATMDA, LRLSHMDA, and NTSHMDA) on the HMDAD and Disbiome databases under five-fold cross validations on microbes, diseases, and microbe-disease pairs. Under the three five-fold cross validations, GPUDMDA computed the best AUCs of 0.7121, 0.9454, and 0.9501 on the HMDAD database and 0.8372, 0.8908, and 0.8948 on the Disbiome database, respectively, outperforming the other four MDA prediction methods. Asthma is the most common chronic respiratory condition and affects ~339 million people worldwide. Inflammatory bowel disease is a class of globally chronic intestinal disease widely existed in the gut and gastrointestinal tract and extraintestinal organs of patients. Particularly, inflammatory bowel disease severely affects the growth and development of children. We used the proposed GPUDMDA method and found that Enterobacter hormaechei had potential associations with both asthma and inflammatory bowel disease and need further biological experimental validation.

Conclusion

The proposed GPUDMDA demonstrated the powerful MDA prediction ability. We anticipate that GPUDMDA helps screen the therapeutic clues for microbe-related diseases.

Deciphering ligand-receptor-mediated intercellular communication based on ensemble deep learning and the joint scoring strategy from single-cell transcriptomic data

BACKGROUND

Cell-cell communication in a tumor microenvironment is vital to tumorigenesis, tumor progression and therapy. Intercellular communication inference helps understand molecular mechanisms of tumor growth, progression and metastasis.

METHODS

Focusing on ligand-receptor co-expressions, in this study, we developed an ensemble deep learning framework, CellComNet, to decipher ligand-receptor-mediated cell-cell communication from single-cell transcriptomic data. First, credible LRIs are captured by integrating data arrangement, feature extraction, dimension reduction, and LRI classification based on an ensemble of heterogeneous Newton boosting machine and deep neural network. Next, known and identified LRIs are screened based on single-cell RNA sequencing (scRNA-seq) data in certain tissues. Finally, cell-cell communication is inferred by incorporating scRNA-seq data, the screened LRIs, a joint scoring strategy that combines expression thresholding and expression product of ligands and receptors.

RESULTS

The proposed CellComNet framework was compared with four competing protein-protein interaction prediction models (PIPR, XGBoost, DNNXGB, and OR-RCNN) and obtained the best AUCs and AUPRs on four LRI datasets, elucidating the optimal LRI classification ability. CellComNet was further applied to analyze intercellular communication in human melanoma and head and neck squamous cell carcinoma (HNSCC) tissues. The results demonstrate that cancer-associated fibroblasts highly communicate with melanoma cells and endothelial cells strong communicate with HNSCC cells.

CONCLUSIONS

The proposed CellComNet framework efficiently identified credible LRIs and significantly improved cell-cell communication inference performance. We anticipate that CellComNet can contribute to anticancer drug design and tumor-targeted therapy.

StackTTCA: a stacking ensemble learning-based framework for accurate and high-throughput identification of tumor T cell antigens

BACKGROUND

The identification of tumor T cell antigens (TTCAs) is crucial for providing insights into their functional mechanisms and utilizing their potential in anticancer vaccines development. In this context, TTCAs are highly promising. Meanwhile, experimental technologies for discovering and characterizing new TTCAs are expensive and time-consuming. Although many machine learning (ML)-based models have been proposed for identifying new TTCAs, there is still a need to develop a robust model that can achieve higher rates of accuracy and precision.

RESULTS

In this study, we propose a new stacking ensemble learning-based framework, termed StackTTCA, for accurate and large-scale identification of TTCAs. Firstly, we constructed 156 different baseline models by using 12 different feature encoding schemes and 13 popular ML algorithms. Secondly, these baseline models were trained and employed to create a new probabilistic feature vector. Finally, the optimal probabilistic feature vector was determined based the feature selection strategy and then used for the construction of our stacked model. Comparative benchmarking experiments indicated that StackTTCA clearly outperformed several ML classifiers and the existing methods in terms of the independent test, with an accuracy of 0.932 and Matthew's correlation coefficient of 0.866.

CONCLUSIONS

In summary, the proposed stacking ensemble learning-based framework of StackTTCA could help to precisely and rapidly identify true TTCAs for follow-up experimental verification. In addition, we developed an online web server ( http://2pmlab.camt.cmu.ac.th/StackTTCA ) to maximize user convenience for high-throughput screening of novel TTCAs.

EpiTEAmDNA: Sequence feature representation via transfer learning and ensemble learning for identifying multiple DNA epigenetic modification types across species

Methylation is a major DNA epigenetic modification for regulating the biological processes without altering the DNA sequence, and multiple types of DNA methylations have been discovered, including 6mA, 5hmC, and 4mC. Multiple computational approaches were developed to automatically identify the DNA methylation residues using machine learning or deep learning algorithms. The machine learning (ML) based methods are difficult to be transferred to the other predicting tasks of the DNA methylation sites using additional knowledge. Deep learning (DL) may facilitate the transfer learning of knowledge from similar tasks, but they are often ineffective on small datasets. This study proposes an integrated feature representation framework EpiTEAmDNA based on the strategies of transfer learning and ensemble learning, which is evaluated on multiple DNA methylation types across 15 species. EpiTEAmDNA integrates convolutional neural network (CNN) and conventional machine learning methods, and shows improved performances than the existing DL-based methods on small datasets when no additional knowledge is available. The experimental data suggests that the EpiTEAmDNA models may be further improved via transfer learning based on additional knowledge. The evaluation experiments on the independent test datasets also suggest that the proposed EpiTEAmDNA framework outperforms the existing models in most prediction tasks of the 3 DNA methylation types across 15 species. The source code, pre-trained global model, and the EpiTEAmDNA feature representation framework are freely available at http://www.healthinformaticslab.org/supp/.

3D genomics and its applications in precision medicine

Three-dimensional (3D) genomics is an emerging discipline that studies the three-dimensional structure of chromatin and the three-dimensional and functions of genomes. It mainly studies the three-dimensional conformation and functional regulation of intranuclear genomes, such as DNA replication, DNA recombination, genome folding, gene expression regulation, transcription factor regulation mechanism, and the maintenance of three-dimensional conformation of genomes. Self-chromosomal conformation capture (3C) technology has been developed, and 3D genomics and related fields have developed rapidly. In addition, chromatin interaction analysis techniques developed by 3C technologies, such as paired-end tag sequencing (ChIA-PET) and whole-genome chromosome conformation capture (Hi-C), enable scientists to further study the relationship between chromatin conformation and gene regulation in different species. Thus, the spatial conformation of plant, animal, and microbial genomes, transcriptional regulation mechanisms, interaction patterns of chromosomes, and the formation mechanism of spatiotemporal specificity of genomes are revealed. With the help of new experimental technologies, the identification of key genes and signal pathways related to life activities and diseases is sustaining the rapid development of life science, agriculture, and medicine. In this paper, the concept and development of 3D genomics and its application in agricultural science, life science, and medicine are introduced, which provides a theoretical basis for the study of biological life processes.

Mapping nucleosome and chromatin architectures: A survey of computational methods

With ever-growing genomic sequencing data, the data variabilities and the underlying biases of the sequencing technologies pose significant computational challenges ranging from the need for accurately detecting the nucleosome positioning or chromatin interaction to the need for developing normalization methods to eliminate systematic biases. This review mainly surveys the computational methods for mapping the higher-resolution nucleosome and higher-order chromatin architectures. While a detailed discussion of the underlying algorithms is beyond the scope of our survey, we have discussed the methods and tools that can detect the nucleosomes in the genome, then demonstrated the computational methods for identifying 3D chromatin domains and interactions. We further illustrated computational approaches for integrating multi-omics data with Hi-C data and the advance of single-cell (sc)Hi-C data analysis. Our survey provides a comprehensive and valuable resource for biomedical scientists interested in studying nucleosome organization and chromatin structures as well as for computational scientists who are interested in improving upon them.