Application of deep learning methods in biological networks

Jointly constrained group sparse connectivity representation improves early diagnosis of Alzheimer's disease on routinely acquired T1-weighted imaging-based brain network

Background

Radiomics-based morphological brain networks (radMBN) constructed from routinely acquired structural MRI (sMRI) data have gained attention in Alzheimer's disease (AD). However, the radMBN suffers from limited characterization of AD because sMRI only characterizes anatomical changes and is not a direct measure of neuronal pathology or brain activity.

Purpose

To establish a group sparse representation of the radMBN under a joint constraint of group-level white matter fiber connectivity and individual-level sMRI regional similarity (JCGS-radMBN).

Methods

Two publicly available datasets were adopted, including 120 subjects from ADNI with both T1-weighted image (T1WI) and diffusion MRI (dMRI) for JCGS-radMBN construction, 818 subjects from ADNI and 200 subjects solely with T1WI from AIBL for validation in early AD diagnosis. Specifically, the JCGS-radMBN was conducted by jointly estimating non-zero connections among subjects, with the regularization term constrained by group-level white matter fiber connectivity and individual-level sMRI regional similarity. Then, a triplet graph convolutional network was adopted for early AD diagnosis. The discriminative brain connections were identified using a two-sample t-test, and the neurobiological interpretation was validated by correlating the discriminative brain connections with cognitive scores.

Results

The JCGS-radMBN exhibited superior classification performance over five brain network construction methods. For the typical NC vs. AD classification, the JCGS-radMBN increased by 1-30% in accuracy over the alternatives on ADNI and AIBL. The discriminative brain connections exhibited a strong connectivity to hippocampus, parahippocampal gyrus, and basal ganglia, and had significant correlation with MMSE scores.

Conclusion

The proposed JCGS-radMBN facilitated the AD characterization of brain network established on routinely acquired imaging modality of sMRI.

Supplementary Information

The online version of this article (10.1007/s13755-023-00269-0) contains supplementary material, which is available to authorized users.

Novel Alzheimer's disease subtypes based on functional brain connectivity in human connectome project

The pathogenesis of Alzheimer's disease (AD) remains unclear, but revealing individual differences in functional connectivity (FC) may provide insights and improve diagnostic precision. A hierarchical clustering-based autoencoder with functional connectivity was proposed to categorize 82 AD patients from the Alzheimer's Disease Neuroimaging Initiative. Compared to directly performing clustering, using an autoencoder to reduce the dimensionality of the matrix can effectively eliminate noise and redundant information in the data, extract key features, and optimize clustering performance. Subsequently, subtype differences in clinical and graph theoretical metrics were assessed. Results indicate a significant inter-subject heterogeneity in the degree of FC disruption among AD patients. We have identified two neurophysiological subtypes: subtype I exhibits widespread functional impairment across the entire brain, while subtype II shows mild impairment in the Limbic System region. What is worth noting is that we also observed significant differences between subtypes in terms of neurocognitive assessment scores associations with network functionality, and graph theory metrics. Our method can accurately identify different functional disruptions in subtypes of AD, facilitating personalized treatment and early diagnosis, ultimately improving patient outcomes.

From biological data to oscillator models using SINDy

Periodic changes in the concentration or activity of different molecules regulate vital cellular processes such as cell division and circadian rhythms. Developing mathematical models is essential to better understand the mechanisms underlying these oscillations. Recent data-driven methods like SINDy have fundamentally changed model identification, yet their application to experimental biological data remains limited. This study investigates SINDy's constraints by directly applying it to biological oscillatory data. We identify insufficient resolution, noise, dimensionality, and limited prior knowledge as primary limitations. Using various generic oscillator models of different complexity and/or dimensionality, we systematically analyze these factors. We then propose a comprehensive guide for inferring models from biological data, addressing these challenges step by step. Our approach is validated using glycolytic oscillation data from yeast.

scGREAT: Transformer-based deep-language model for gene regulatory network inference from single-cell transcriptomics

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.

sscNOVA: a semi-supervised convolutional neural network for predicting functional regulatory variants in autoimmune diseases

Genome-wide association studies (GWAS) have identified thousands of variants in the human genome with autoimmune diseases. However, identifying functional regulatory variants associated with autoimmune diseases remains challenging, largely because of insufficient experimental validation data. We adopt the concept of semi-supervised learning by combining labeled and unlabeled data to develop a deep learning-based algorithm framework, sscNOVA, to predict functional regulatory variants in autoimmune diseases and analyze the functional characteristics of these regulatory variants. Compared to traditional supervised learning methods, our approach leverages more variants' data to explore the relationship between functional regulatory variants and autoimmune diseases. Based on the experimentally curated testing dataset and evaluation metrics, we find that sscNOVA outperforms other state-of-the-art methods. Furthermore, we illustrate that sscNOVA can help to improve the prioritization of functional regulatory variants from lead single-nucleotide polymorphisms and the proxy variants in autoimmune GWAS data.

DeepPPThermo: A Deep Learning Framework for Predicting Protein Thermostability Combining Protein-Level and Amino Acid-Level Features

Using wet experimental methods to discover new thermophilic proteins or improve protein thermostability is time-consuming and expensive. Machine learning methods have shown powerful performance in the study of protein thermostability in recent years. However, how to make full use of multiview sequence information to predict thermostability effectively is still a challenge. In this study, we proposed a deep learning-based classifier named DeepPPThermo that fuses features of classical sequence features and deep learning representation features for classifying thermophilic and mesophilic proteins. In this model, deep neural network (DNN) and bi-long short-term memory (Bi-LSTM) are used to mine hidden features. Furthermore, local attention and global attention mechanisms give different importance to multiview features. The fused features are fed to a fully connected network classifier to distinguish thermophilic and mesophilic proteins. Our model is comprehensively compared with advanced machine learning algorithms and deep learning algorithms, proving that our model performs better. We further compare the effects of removing different features on the classification results, demonstrating the importance of each feature and the robustness of the model. Our DeepPPThermo model can be further used to explore protein diversity, identify new thermophilic proteins, and guide directed mutations of mesophilic proteins.

DiCleave: a deep learning model for predicting human Dicer cleavage sites

BACKGROUND

MicroRNAs (miRNAs) are a class of non-coding RNAs that play a pivotal role as gene expression regulators. These miRNAs are typically approximately 20 to 25 nucleotides long. The maturation of miRNAs requires Dicer cleavage at specific sites within the precursor miRNAs (pre-miRNAs). Recent advances in machine learning-based approaches for cleavage site prediction, such as PHDcleav and LBSizeCleav, have been reported. ReCGBM, a gradient boosting-based model, demonstrates superior performance compared with existing methods. Nonetheless, ReCGBM operates solely as a binary classifier despite the presence of two cleavage sites in a typical pre-miRNA. Previous approaches have focused on utilizing only a fraction of the structural information in pre-miRNAs, often overlooking comprehensive secondary structure information. There is a compelling need for the development of a novel model to address these limitations.

RESULTS

In this study, we developed a deep learning model for predicting the presence of a Dicer cleavage site within a pre-miRNA segment. This model was enhanced by an autoencoder that learned the secondary structure embeddings of pre-miRNA. Benchmarking experiments demonstrated that the performance of our model was comparable to that of ReCGBM in the binary classification tasks. In addition, our model excelled in multi-class classification tasks, making it a more versatile and practical solution than ReCGBM.

CONCLUSIONS

Our proposed model exhibited superior performance compared with the current state-of-the-art model, underscoring the effectiveness of a deep learning approach in predicting Dicer cleavage sites. Furthermore, our model could be trained using only sequence and secondary structure information. Its capacity to accommodate multi-class classification tasks has enhanced the practical utility of our model.

Graph Neural Networks in Cancer and Oncology Research: Emerging and Future Trends

Next-generation cancer and oncology research needs to take full advantage of the multimodal structured, or graph, information, with the graph data types ranging from molecular structures to spatially resolved imaging and digital pathology, biological networks, and knowledge graphs. Graph Neural Networks (GNNs) efficiently combine the graph structure representations with the high predictive performance of deep learning, especially on large multimodal datasets. In this review article, we survey the landscape of recent (2020-present) GNN applications in the context of cancer and oncology research, and delineate six currently predominant research areas. We then identify the most promising directions for future research. We compare GNNs with graphical models and "non-structured" deep learning, and devise guidelines for cancer and oncology researchers or physician-scientists, asking the question of whether they should adopt the GNN methodology in their research pipelines.

Systems Biology in Cancer Diagnosis Integrating Omics Technologies and Artificial Intelligence to Support Physician Decision Making

Cancer is the second major cause of disease-related death worldwide, and its accurate early diagnosis and therapeutic intervention are fundamental for saving the patient's life. Cancer, as a complex and heterogeneous disorder, results from the disruption and alteration of a wide variety of biological entities, including genes, proteins, mRNAs, miRNAs, and metabolites, that eventually emerge as clinical symptoms. Traditionally, diagnosis is based on clinical examination, blood tests for biomarkers, the histopathology of a biopsy, and imaging (MRI, CT, PET, and US). Additionally, omics biotechnologies help to further characterize the genome, metabolome, microbiome traits of the patient that could have an impact on the prognosis and patient's response to the therapy. The integration of all these data relies on gathering of several experts and may require considerable time, and, unfortunately, it is not without the risk of error in the interpretation and therefore in the decision. Systems biology algorithms exploit Artificial Intelligence (AI) combined with omics technologies to perform a rapid and accurate analysis and integration of patient's big data, and support the physician in making diagnosis and tailoring the most appropriate therapeutic intervention. However, AI is not free from possible diagnostic and prognostic errors in the interpretation of images or biochemical-clinical data. Here, we first describe the methods used by systems biology for combining AI with omics and then discuss the potential, challenges, limitations, and critical issues in using AI in cancer research.

NRTPredictor: identifying rice root cell state in single-cell RNA-seq via ensemble learning

BACKGROUND

Single-cell RNA sequencing (scRNA-seq) measurements of gene expression show great promise for studying the cellular heterogeneity of rice roots. How precisely annotating cell identity is a major unresolved problem in plant scRNA-seq analysis due to the inherent high dimensionality and sparsity.

RESULTS

To address this challenge, we present NRTPredictor, an ensemble-learning system, to predict rice root cell stage and mine biomarkers through complete model interpretability. The performance of NRTPredictor was evaluated using a test dataset, with 98.01% accuracy and 95.45% recall. With the power of interpretability provided by NRTPredictor, our model recognizes 110 marker genes partially involved in phenylpropanoid biosynthesis. Expression patterns of rice root could be mapped by the above-mentioned candidate genes, showing the superiority of NRTPredictor. Integrated analysis of scRNA and bulk RNA-seq data revealed aberrant expression of Epidermis cell subpopulations in flooding, Pi, and salt stresses.

CONCLUSION

Taken together, our results demonstrate that NRTPredictor is a useful tool for automated prediction of rice root cell stage and provides a valuable resource for deciphering the rice root cellular heterogeneity and the molecular mechanisms of flooding, Pi, and salt stresses. Based on the proposed model, a free webserver has been established, which is available at https://www.cgris.net/nrtp .

Predicting GPR40 Agonists with A Deep Learning-Based Ensemble Model

Recent studies have identified G protein-coupled receptor 40 (GPR40) as a promising target for treating type 2 diabetes mellitus, and GPR40 agonists have several superior effects over other hypoglycemic drugs, including cardiovascular protection and suppression of glucagon levels. In this study, we constructed an up-to-date GPR40 ligand dataset for training models and performed a systematic optimization of the ensemble model, resulting in a powerful ensemble model (ROC AUC: 0.9496) for distinguishing GPR40 agonists and non-agonists. The ensemble model is divided into three layers, and the optimization process is carried out in each layer. We believe that these results will prove helpful for both the development of GPR40 agonists and ensemble models. All the data and models are available on GitHub. (https://github.com/Jiamin-Yang/ensemble_model).

Automatic recognition of schizophrenia from brain-network features using graph convolutional neural network

Schizophrenia is a severe mental illness that imposes considerable economic burden on families and society. However, its clinical diagnosis primarily relies on scales and doctors' clinical experience and lacks an objective and accurate diagnostic approach. In recent years, graph convolutional neural networks (GCN) have been used to assist in psychiatric diagnosis owing to their ability to learn spatial-association information. Therefore, this study proposes a schizophrenia automatic recognition model based on graph convolutional neural network. Herein, the resting-state electroencephalography (EEG) data of 103 first-episode schizophrenia patients and 92 normal controls (NCs) were obtained. The automatic recognition model was trained with a nodal feature matrix that comprised the time and frequency-domain features of the EEG signals and local features of the brain network. The most significant regions that contributed to the model classification were identified, and the correlation between the node topological features of each significant region and clinical evaluation metrics was explored. Experiments were conducted to evaluate the performance of the model using 10-fold cross-validation. The best performance in the theta frequency band with a 6 s epoch length and phase-locked value. The recognition accuracy was 90.01%. The most significant region for identifying with first-episode schizophrenia patients and NCs was located in the parietal lobe. The results of this study verify the applicability of the proposed novel method for the identification and diagnosis of schizophrenia.

Pretreatment ultrasound-based deep learning radiomics model for the early prediction of pathologic response to neoadjuvant chemotherapy in breast cancer

OBJECTIVES

To investigate the predictive performance of the deep learning radiomics (DLR) model integrating pretreatment ultrasound imaging features and clinical characteristics for evaluating therapeutic response after neoadjuvant chemotherapy (NAC) in patients with breast cancer.

METHODS

A total of 603 patients who underwent NAC were retrospectively included between January 2018 and June 2021 from three different institutions. Four different deep convolutional neural networks (DCNNs) were trained by pretreatment ultrasound images using annotated training dataset (n = 420) and validated in a testing cohort (n = 183). Comparing the predictive performance of these models, the best one was selected for image-only model structure. Furthermore, the integrated DLR model was constructed based on the image-only model combined with independent clinical-pathologic variables. Areas under the curve (AUCs) of these models and two radiologists were compared by using the DeLong method.

RESULTS

As the optimal basic model, Resnet50 achieved an AUC and accuracy of 0.879 and 82.5% in the validation set. The integrated DLR model, yielding the highest classification performance in predicting response to NAC (AUC 0.962 and 0.939 in the training and validation cohort), outperformed the image-only model and the clinical model and also performed better than two radiologists' prediction (all p < 0.05). In addition, predictive efficacy of the radiologists was improved under the assistance of the DLR model significantly.

CONCLUSION

The pretreatment US-based DLR model could hold promise as a clinical guidance for predicting NAC response of patients with breast cancer, thereby providing benefit of timely treatment strategy adjustment to potential poor NAC responders.

KEY POINTS

• Multicenter retrospective study showed that deep learning radiomics (DLR) model based on pretreatment ultrasound image and clinical parameter achieved satisfactory prediction of tumor response to neoadjuvant chemotherapy (NAC) in breast cancer. • The integrated DLR model could become an effective tool to guide clinicians in identifying potential poor pathological responders before chemotherapy. • The predictive efficacy of the radiologists was improved under the assistance of the DLR model.

Automating the design-build-test-learn cycle towards next-generation bacterial cell factories

Automation is playing an increasingly significant role in synthetic biology. Groundbreaking technologies, developed over the past 20 years, have enormously accelerated the construction of efficient microbial cell factories. Integrating state-of-the-art tools (e.g. for genome engineering and analytical techniques) into the design-build-test-learn cycle (DBTLc) will shift the metabolic engineering paradigm from an almost artisanal labor towards a fully automated workflow. Here, we provide a perspective on how a fully automated DBTLc could be harnessed to construct the next-generation bacterial cell factories in a fast, high-throughput fashion. Innovative toolsets and approaches that pushed the boundaries in each segment of the cycle are reviewed to this end. We also present the most recent efforts on automation of the DBTLc, which heralds a fully autonomous pipeline for synthetic biology in the near future.

Multi-modality attribute learning-based method for drug-protein interaction prediction based on deep neural network

Identification of active candidate compounds for target proteins, also called drug-protein interaction (DPI) prediction, is an essential but time-consuming and expensive step, which leads to fostering the development of drug discovery. In recent years, deep network-based learning methods were frequently proposed in DPIs due to their powerful capability of feature representation. However, the performance of existing DPI methods is still limited by insufficiently labeled pharmacological data and neglected intermolecular information. Therefore, overcoming these difficulties to perfect the performance of DPIs is an urgent challenge for researchers. In this article, we designed an innovative 'multi-modality attributes' learning-based framework for DPIs with molecular transformer and graph convolutional networks, termed, multi-modality attributes (MMA)-DPI. Specifically, intermolecular sub-structural information and chemical semantic representations were extracted through an augmented transformer module from biomedical data. A tri-layer graph convolutional neural network module was applied to associate the neighbor topology information and learn the condensed dimensional features by aggregating a heterogeneous network that contains multiple biological representations of drugs, proteins, diseases and side effects. Then, the learned representations were taken as the input of a fully connected neural network module to further integrate them in molecular and topological space. Finally, the attribute representations were fused with adaptive learning weights to calculate the interaction score for the DPIs tasks. MMA-DPI was evaluated in different experimental conditions and the results demonstrate that the proposed method achieved higher performance than existing state-of-the-art frameworks.

PreTP-Stack: Prediction of Therapeutic Peptides Based on the Stacked Ensemble Learing

Therapeutic peptide prediction is critical for drug development and therapeutic therapy. Researchers have developed several computational methods to identify different therapeutic peptide types. However, most computational methods focus on identifying the specific type of therapeutic peptides and fail to accurately predict all types of therapeutic peptides. Moreover, it is still challenging to utilize different properties features to predict the therapeutic peptides. In this study, a novel stacking framework PreTP-Stack is proposed for predicting different types of therapeutic peptide. PreTP-Stack is constructed based on ten different features and four predictors (Random Forest, Linear Discriminant Analysis, XGBoost and Support Vector Machine). Then the proposed method constructs an auto-weighted multi-view learning model as a final meta-classifier to enhance the performance of the basic models. Experimental results showed that the proposed method achieved better or highly comparable performance with the state-of-the-art methods for predicting eight types of therapeutic peptides A user-friendly web-server predictor is available at http://bliulab.net/PreTP-Stack.

A review of methods for predicting DNA N6-methyladenine sites

Deoxyribonucleic acid(DNA) N6-methyladenine plays a vital role in various biological processes, and the accurate identification of its site can provide a more comprehensive understanding of its biological effects. There are several methods for 6mA site prediction. With the continuous development of technology, traditional techniques with the high costs and low efficiencies are gradually being replaced by computer methods. Computer methods that are widely used can be divided into two categories: traditional machine learning and deep learning methods. We first list some existing experimental methods for predicting the 6mA site, then analyze the general process from sequence input to results in computer methods and review existing model architectures. Finally, the results were summarized and compared to facilitate subsequent researchers in choosing the most suitable method for their work.

Matrix reconstruction with reliable neighbors for predicting potential MiRNA-disease associations

Numerous experimental studies have indicated that alteration and dysregulation in mircroRNAs (miRNAs) are associated with serious diseases. Identifying disease-related miRNAs is therefore an essential and challenging task in bioinformatics research. Computational methods are an efficient and economical alternative to conventional biomedical studies and can reveal underlying miRNA-disease associations for subsequent experimental confirmation with reasonable confidence. Despite the success of existing computational approaches, most of them only rely on the known miRNA-disease associations to predict associations without adding other data to increase the prediction accuracy, and they are affected by issues of data sparsity. In this paper, we present MRRN, a model that combines matrix reconstruction with node reliability to predict probable miRNA-disease associations. In MRRN, the most reliable neighbors of miRNA and disease are used to update the original miRNA-disease association matrix, which significantly reduces data sparsity. Unknown miRNA-disease associations are reconstructed by aggregating the most reliable first-order neighbors to increase prediction accuracy by representing the local and global structure of the heterogeneous network. Five-fold cross-validation of MRRN produced an area under the curve (AUC) of 0.9355 and area under the precision-recall curve (AUPR) of 0.2646, values that were greater than those produced by comparable models. Two different types of case studies using three diseases were conducted to demonstrate the accuracy of MRRN, and all top 30 predicted miRNAs were verified.

Identification of adaptor proteins by incorporating deep learning and PSSM profiles

Adaptor proteins, also known as signal transduction adaptor proteins, are important proteins in signal transduction pathways, and play a role in connecting signal proteins for signal transduction between cells. Studies have shown that adaptor proteins are closely related to some diseases, such as tumors and diabetes. Therefore, it is very meaningful to construct a relevant model to accurately identify adaptor proteins. In recent years, many studies have used a position-specific scoring matrix (PSSM) and neural network methods to identify adaptor proteins. However, ordinary neural network models cannot correlate the contextual information in PSSM profiles well, so these studies usually process 20×N (N > 20) PSSM into 20×20 dimensions, which results in the loss of a large amount of protein information; This research proposes an efficient method that combines one-dimensional convolution (1-D CNN) and a bidirectional long short-term memory network (biLSTM) to identify adaptor proteins. The complete PSSM profiles are the input of the model, and the complete information of the protein is retained during the training process. We perform cross-validation during model training and test the performance of the model on an independent test set; in the data set with 1224 adaptor proteins and 11,078 non-adaptor proteins, five indicators including specificity, sensitivity, accuracy, area under the receiver operating characteristic curve (AUC) metric and Matthews correlation coefficient (MCC), were employed to evaluate model performance. On the independent test set, the specificity, sensitivity, accuracy and MCC were 0.817, 0.865, 0.823 and 0.465, respectively. Those results show that our method is better than the state-of-the art methods. This study is committed to improve the accuracy of adaptor protein identification, and laid a foundation for further research on diseases related to adaptor protein. This research provided a new idea for the application of deep learning related models in bioinformatics and computational biology.

iDRBP-EL: Identifying DNA- and RNA- Binding Proteins Based on Hierarchical Ensemble Learning

Identification of DNA-binding proteins (DBPs) and RNA-binding proteins (RBPs) from the primary sequences is essential for further exploring protein-nucleic acid interactions. Previous studies have shown that machine-learning-based methods can efficiently identify DBPs or RBPs. However, the information used in these methods is slightly unitary, and most of them only can predict DBPs or RBPs. In this study, we proposed a computational predictor iDRBP-EL to identify DNA- and RNA- binding proteins, and introduced hierarchical ensemble learning to integrate three level information. The method can integrate the information of different features, machine learning algorithms and data into one multi-label model. The ablation experiment showed that the fusion of different information can improve the prediction performance and overcome the cross-prediction problem. Experimental results on the independent datasets showed that iDRBP-EL outperformed all the other competing methods. Moreover, we established a user-friendly webserver iDRBP-EL (http://bliulab.net/iDRBP-EL), which can predict both DBPs and RBPs only based on protein sequences.

A Method for Predicting DNA Motif Length Based On Deep Learning

A DNA motif is a sequence pattern shared by the DNA sequence segments that bind to a specific protein. Discovering motifs in a given DNA sequence dataset plays a vital role in studying gene expression regulation. As an important attribute of the DNA motif, the motif length directly affects the quality of the discovered motifs. How to determine the motif length more accurately remains a difficult challenge to be solved. We propose a new motif length prediction scheme named MotifLen by using supervised machine learning. First, a method of constructing sample data for predicting the motif length is proposed. Secondly, a deep learning model for motif length prediction is constructed based on the convolutional neural network. Then, the methods of applying the proposed prediction model based on a motif found by an existing motif discovery algorithm are given. The experimental results show that i) the prediction accuracy of MotifLen is more than 90% on the validation set and is significantly higher than that of the compared methods on real datasets, ii) MotifLen can successfully optimize the motifs found by the existing motif discovery algorithms, and iii) it can effectively improve the time performance of some existing motif discovery algorithms.

EVlncRNA-Dpred: improved prediction of experimentally validated lncRNAs by deep learning

Long non-coding RNAs (lncRNAs) played essential roles in nearly every biological process and disease. Many algorithms were developed to distinguish lncRNAs from mRNAs in transcriptomic data and facilitated discoveries of more than 600 000 of lncRNAs. However, only a tiny fraction (<1%) of lncRNA transcripts (~4000) were further validated by low-throughput experiments (EVlncRNAs). Given the cost and labor-intensive nature of experimental validations, it is necessary to develop computational tools to prioritize those potentially functional lncRNAs because many lncRNAs from high-throughput sequencing (HTlncRNAs) could be resulted from transcriptional noises. Here, we employed deep learning algorithms to separate EVlncRNAs from HTlncRNAs and mRNAs. For overcoming the challenge of small datasets, we employed a three-layer deep-learning neural network (DNN) with a K-mer feature as the input and a small convolutional neural network (CNN) with one-hot encoding as the input. Three separate models were trained for human (h), mouse (m) and plant (p), respectively. The final concatenated models (EVlncRNA-Dpred (h), EVlncRNA-Dpred (m) and EVlncRNA-Dpred (p)) provided substantial improvement over a previous model based on support-vector-machines (EVlncRNA-pred). For example, EVlncRNA-Dpred (h) achieved 0.896 for the area under receiver-operating characteristic curve, compared with 0.582 given by sequence-based EVlncRNA-pred model. The models developed here should be useful for screening lncRNA transcripts for experimental validations. EVlncRNA-Dpred is available as a web server at https://www.sdklab-biophysics-dzu.net/EVlncRNA-Dpred/index.html, and the data and source code can be freely available along with the web server.

Intersection of network medicine and machine learning towards investigating the key biomarkers and pathways underlying amyotrophic lateral sclerosis: a systematic review

BACKGROUND

Network medicine is an emerging area of research that focuses on delving into the molecular complexity of the disease, leading to the discovery of network biomarkers and therapeutic target discovery. Amyotrophic lateral sclerosis (ALS) is a complicated rare disease with unknown pathogenesis and no available treatment. In ALS, network properties appear to be potential biomarkers that can be beneficial in disease-related applications when explored independently or in tandem with machine learning (ML) techniques.

OBJECTIVE

This systematic literature review explores recent trends in network medicine and implementations of network-based ML algorithms in ALS. We aim to provide an overview of the identified primary studies and gather details on identifying the potential biomarkers and delineated pathways.

METHODS

The current study consists of searching for and investigating primary studies from PubMed and Dimensions.ai, published between 2018 and 2022 that reported network medicine perspectives and the coupling of ML techniques. Each abstract and full-text study was individually evaluated, and the relevant studies were finally included in the review for discussion once they met the inclusion and exclusion criteria.

RESULTS

We identified 109 eligible publications from primary studies representing this systematic review. The data coalesced into two themes: application of network science to identify disease modules and promising biomarkers in ALS, along with network-based ML approaches. Conclusion This systematic review gives an overview of the network medicine approaches and implementations of network-based ML algorithms in ALS to determine new disease genes, and identify critical pathways and therapeutic target discovery for personalized treatment.

Deep learning and social network analysis elucidate drivers of HIV transmission in a high-incidence cohort of people who inject drugs

Globally, people who inject drugs (PWID) experience some of the fastest-growing HIV epidemics. Network-based approaches represent a powerful tool for understanding and combating these epidemics; however, detailed social network studies are limited and pose analytical challenges. We collected longitudinal social (injection partners) and spatial (injection venues) network information from 2512 PWID in New Delhi, India. We leveraged network analysis and graph neural networks (GNNs) to uncover factors associated with HIV transmission and identify optimal intervention delivery points. Longitudinal HIV incidence was 21.3 per 100 person-years. Overlapping community detection using GNNs revealed seven communities, with HIV incidence concentrated within one community. The injection venue most strongly associated with incidence was found to overlap six of the seven communities, suggesting that an intervention deployed at this one location could reach the majority of the sample. These findings highlight the utility of network analysis and deep learning in HIV program design.

Multistrategy Improved Sparrow Search Algorithm Optimized Deep Neural Network for Esophageal Cancer

Deep neural network is a complex pattern recognition network system. It is widely favored by scholars for its strong nonlinear fitting ability. However, training deep neural network models on small datasets typically realizes worse performance than shallow neural network. In this study, a strategy to improve the sparrow search algorithm based on the iterative map, iterative perturbation, and Gaussian mutation is developed. This optimized strategy improved the sparrow search algorithm validated by fourteen benchmark functions, and the algorithm has the best search accuracy and the fastest convergence speed. An algorithm based on the iterative map, iterative perturbation, and Gaussian mutation improved sparrow search algorithm is designed to optimize deep neural networks. The modified sparrow algorithm is exploited to search for the optimal connection weights of deep neural network. This algorithm is implemented for the esophageal cancer dataset along with the other six algorithms. The proposed model is able to achieve 0.92 under all the eight scoring criteria, which is better than the performance of the other six algorithms. Therefore, an optimized deep neural network based on an improved sparrow search algorithm with iterative map, iterative perturbation, and Gaussian mutation is an effective approach to predict the survival rate of esophageal cancer.

Identification of DNA-binding proteins via Multi-view LSSVM with independence criterion

DNA-binding proteins actively participate in life activities such as DNA replication, recombination, gene expression and regulation and play a prominent role in these processes. As DNA-binding proteins continue to be discovered and increase, it is imperative to design an efficient and accurate identification tool. Considering the time-consuming and expensive traditional experimental technology and the insufficient number of samples in the biological computing method based on structural information, we proposed a machine learning algorithm based on sequence information to identify DNA binding proteins, named multi-view Least Squares Support Vector Machine via Hilbert-Schmidt Independence Criterion (multi-view LSSVM via HSIC). This method took 6 feature sets as multi-view input and trains a single view through the LSSVM algorithm. Then, we integrated HSIC into LSSVM as a regular term to reduce the dependence between views and explored the complementary information of multiple views. Subsequently, we trained and coordinated the submodels and finally combined the submodels in the form of weights to obtain the final prediction model. On training set PDB1075, the prediction results of our model were better than those of most existing methods. Independent tests are conducted on the datasets PDB186 and PDB2272. The accuracy of the prediction results was 85.5% and 79.36%, respectively. This result exceeded the current state-of-the-art methods, which showed that the multi-view LSSVM via HSIC can be used as an efficient predictor.

Ensemble Learning-Based Feature Selection for Phage Protein Prediction

Phage has high specificity for its host recognition. As a natural enemy of bacteria, it has been used to treat super bacteria many times. Identifying phage proteins from the original sequence is very important for understanding the relationship between phage and host bacteria and developing new antimicrobial agents. However, traditional experimental methods are both expensive and time-consuming. In this study, an ensemble learning-based feature selection method is proposed to find important features for phage protein identification. The method uses four types of protein sequence-derived features, quantifies the importance of each feature by adding perturbations to the features to influence the results, and finally splices the important features among the four types of features. In addition, we analyzed the selected features and their biological significance.

Identification of Vesicle Transport Proteins via Hypergraph Regularized K-Local Hyperplane Distance Nearest Neighbour Model

The prediction of protein function is a common topic in the field of bioinformatics. In recent years, advances in machine learning have inspired a growing number of algorithms for predicting protein function. A large number of parameters and fairly complex neural networks are often used to improve the prediction performance, an approach that is time-consuming and costly. In this study, we leveraged traditional features and machine learning classifiers to boost the performance of vesicle transport protein identification and make the prediction process faster. We adopt the pseudo position-specific scoring matrix (PsePSSM) feature and our proposed new classifier hypergraph regularized k-local hyperplane distance nearest neighbour (HG-HKNN) to classify vesicular transport proteins. We address dataset imbalances with random undersampling. The results show that our strategy has an area under the receiver operating characteristic curve (AUC) of 0.870 and a Matthews correlation coefficient (MCC) of 0.53 on the benchmark dataset, outperforming all state-of-the-art methods on the same dataset, and other metrics of our model are also comparable to existing methods.

Identification of MiRNA–Disease Associations Based on Information of Multi-Module and Meta-Path

Cumulative research reveals that microRNAs (miRNAs) are involved in many critical biological processes including cell proliferation, differentiation and apoptosis. It is of great significance to figure out the associations between miRNAs and human diseases that are the basis for finding biomarkers for diagnosis and targets for treatment. To overcome the time-consuming and labor-intensive problems faced by traditional experiments, a computational method was developed to identify potential associations between miRNAs and diseases based on the graph attention network (GAT) with different meta-path mode and support vector (SVM). Firstly, we constructed a multi-module heterogeneous network based on the meta-path and learned the latent features of different modules by GAT. Secondly, we found the average of the latent features with weight to obtain a final node representation. Finally, we characterized miRNA–disease-association pairs with the node representation and trained an SVM to recognize potential associations. Based on the five-fold cross-validation and benchmark datasets, the proposed method achieved an area under the precision–recall curve (AUPR) of 0.9379 and an area under the receiver–operating characteristic curve (AUC) of 0.9472. The results demonstrate that our method has an outstanding practical application performance and can provide a reference for the discovery of new biomarkers and therapeutic targets.

Analysis of Data Interaction Process Based on Data Mining and Neural Network Topology Visualization

This paper addresses data mining and neural network model construction and analysis to design a data interaction process model based on data mining and topology visualization. This paper performs preprocessing data operations such as data filtering and cleaning of the collected data. A typical multichannel convolutional neural network (MCNN) in deep learning techniques is applied to alert students' academic performance. In addition, the network topology of the CNN is optimized to improve the performance of the model. The CNN has many hyperparameters that need to be tuned to construct an optimal model that can effectively interact with the data. In this paper, we propose a method to visualize the network topology within unstable regions to address the current problem of lacking an effective way to layout the network topology into specified areas. The technique transforms the network topology layout problem within the unstable region into a circular topology diffusion problem within a convex polygon, ensuring a clear, logical topology connection, and dramatically reducing the gaps in the area, making the layout more uniform beautiful. This paper constructs a real-time data interaction model based on JSON format and database triggers using message queues for reliable delivery. A platform-based real-time data interaction solution is designed by combining the timer method with the original key. The solution designed in this paper considers the real-time accuracy, security and reliability of data interaction. It satisfies the platform's initial and newly discovered requirements for data interaction.

Weighted deep factorizing heterogeneous molecular network for genome-phenome association prediction

Genome-phenome association (GPA) prediction can promote the understanding of biological mechanisms about complex pathology of phenotypes (i.e., traits and diseases). Traditional heterogeneous network-based GPA approaches overwhelmingly need to project heterogeneous data toward homogeneous network for data fusion and prediction, such projections result in the loss of heterogeneous network structure information. Matrix factorization based data fusion can avoid such projection by integrating multi-type data in a coherent way, but they typically perform linear factorization and cannot mine the nonlinear relationships between molecules, which compromise the accuracy of GPA analysis. Furthermore, most of them can not selectively synergy network topology and node attribution information in a principle way. In this paper, we propose a weighted deep matrix factorization based solution (WDGPA) to predict GPAs by selectively and differentially fusing heterogeneous molecular network and diverse attributes of nodes. WDGPA firstly assigns weights to inter/intra-relational data matrices and attribute data matrices, and performs deep matrix factorization on these matrices of heterogeneous network in a cooperative manner to obtain the nonlinear representations of different nodes. In addition, it performs low-rank representation learning on the attribute data with the shared nonlinear representations. In this way, both the network topology and node attributes are jointly mined to explore the representations of molecules and complex interplays between molecules and phenotypes. WDGPA then uses the representational vectors of gene and phenotype nodes to predict GPAs. Experimental results on maize and human datasets confirm that WDGPA outperforms competitive methods by a large margin under different evaluation protocols.

Artificial intelligence in cancer target identification and drug discovery

Artificial intelligence is an advanced method to identify novel anticancer targets and discover novel drugs from biology networks because the networks can effectively preserve and quantify the interaction between components of cell systems underlying human diseases such as cancer. Here, we review and discuss how to employ artificial intelligence approaches to identify novel anticancer targets and discover drugs. First, we describe the scope of artificial intelligence biology analysis for novel anticancer target investigations. Second, we review and discuss the basic principles and theory of commonly used network-based and machine learning-based artificial intelligence algorithms. Finally, we showcase the applications of artificial intelligence approaches in cancer target identification and drug discovery. Taken together, the artificial intelligence models have provided us with a quantitative framework to study the relationship between network characteristics and cancer, thereby leading to the identification of potential anticancer targets and the discovery of novel drug candidates.

A road map for happiness: The psychological factors related cell types in various parts of human body from single cell RNA-seq data analysis

Massive evidence from all sources including zoology, neurobiology and immunology has confirmed that psychological factors can raise remarkable physiological effects. Researchers have long been aware of the potential value of these effects and wanted to harness them in the development of new drugs and therapies, for which the mechanism study is a necessary prerequisite. However, most of these studies are restricted to neuroscience, or starts with blood sample and fall into the area of immunity. In this study, we choose to focus on the psychological factor of happiness, mining existing publicly available single cell RNA sequencing (scRNA-seq) data for the expression of happiness-related genes collected from various sources of literature in all types of cells in the samples, finding that the expression of these genes is not restricted within neuro-regulated cells or tissue-resident immune cells, on the opposite, cell types that are unique to tissue and organ without direct regulation from nervous system account for the majority to express the happiness-related genes. Our research is a preliminary exploration of where our body respond to our mind at cell level, and lays the foundation for more detailed mechanism research.

HKAM-MKM: A hybrid kernel alignment maximization-based multiple kernel model for identifying DNA-binding proteins

The identification of DNA-binding proteins (DBPs) has always been a hot issue in the field of sequence classification. However, considering that the experimental identification method is very resource-intensive, the construction of a computational prediction model is worthwhile. This study developed and evaluated a hybrid kernel alignment maximization-based multiple kernel model (HKAM-MKM) for predicting DBPs. First, we collected two datasets and performed feature extraction on the sequences to obtain six feature groups, and then constructed the corresponding kernels. To ensure the effective utilisation of the base kernel and avoid ignoring the difference between the sample and its neighbours, we proposed local kernel alignment to calculate the kernel between the sample and its neighbours, with each sample as the centre. We combined the global and local kernel alignments to develop a hybrid kernel alignment model, and balance the relationship between the two through parameters. By maximising the hybrid kernel alignment value, we obtained the weight of each kernel and then linearly combined the kernels in the form of weights. Finally, the fused kernel was input into a support vector machine for training and prediction. Finally, in the independent test sets PDB186 and PDB2272, we obtained the highest Matthew's correlation coefficient (MCC) (0.768 and 0.5962, respectively) and the highest accuracy (87.1% and 78.43%, respectively), which were superior to the other predictors. Therefore, HKAM-MKM is an efficient prediction tool for DBPs.

Roles of the Exosomes Derived From Myeloid-Derived Suppressor Cells in Tumor Immunity and Cancer Progression

Tumor immunity is involved in malignant tumor progression. Myeloid-derived suppressor cells (MDSCs) play an irreplaceable role in tumor immunity. MDSCs are composed of immature myeloid cells and exhibit obvious immunomodulatory functions. Exosomes released by MDSCs (MDSCs-Exos) have similar effects to parental MDSCs in regulating tumor immunity. In this review, we provided a comprehensive description of the characteristics, functions and mechanisms of exosomes. We analyzed the immunosuppressive, angiogenesis and metastatic effects of MDSCs-Exos in different tumors through multiple perspectives. Immunotherapy targeting MDSCs-Exos has demonstrated great potential in cancers and non-cancerous diseases.

GraphGONet: a self-explaining neural network encapsulating the Gene Ontology graph for phenotype prediction on gene expression

MOTIVATION

Medical care is becoming more and more specific to patients' needs due to the increased availability of omics data. The application to these data of sophisticated machine learning models, in particular deep learning, can improve the field of precision medicine. However, their use in clinics is limited as their predictions are not accompanied by an explanation. The production of accurate and intelligible predictions can benefit from the inclusion of domain knowledge. Therefore, knowledge-based deep learning models appear to be a promising solution.

RESULTS

In this paper, we propose GraphGONet, where the Gene Ontology is encapsulated in the hidden layers of a new self-explaining neural network. Each neuron in the layers represents a biological concept, combining the gene expression profile of a patient, and the information from its neighboring neurons. The experiments described in the paper confirm that our model not only performs as accurately as the state-of-the-art (non-explainable ones) but also automatically produces stable and intelligible explanations composed of the biological concepts with the highest contribution. This feature allows experts to use our tool in a medical setting.

AVAILABILITY

GraphGONet is freely available at https://forge.ibisc.univ-evry.fr/vbourgeais/GraphGONet.git.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Deep neural network prediction of genome-wide transcriptome signatures - beyond the Black-box

Prediction algorithms for protein or gene structures, including transcription factor binding from sequence information, have been transformative in understanding gene regulation. Here we ask whether human transcriptomic profiles can be predicted solely from the expression of transcription factors (TFs). We find that the expression of 1600 TFs can explain >95% of the variance in 25,000 genes. Using the light-up technique to inspect the trained NN, we find an over-representation of known TF-gene regulations. Furthermore, the learned prediction network has a hierarchical organization. A smaller set of around 125 core TFs could explain close to 80% of the variance. Interestingly, reducing the number of TFs below 500 induces a rapid decline in prediction performance. Next, we evaluated the prediction model using transcriptional data from 22 human diseases. The TFs were sufficient to predict the dysregulation of the target genes (rho = 0.61, P < 10⁻²¹⁶). By inspecting the model, key causative TFs could be extracted for subsequent validation using disease-associated genetic variants. We demonstrate a methodology for constructing an interpretable neural network predictor, where analyses of the predictors identified key TFs that were inducing transcriptional changes during disease.

The Characterization of Structure and Prediction for Aquaporin in Tumour Progression by Machine Learning

Recurrence and new cases of cancer constitute a challenging human health problem. Aquaporins (AQPs) can be expressed in many types of tumours, including the brain, breast, pancreas, colon, skin, ovaries, and lungs, and the histological grade of cancer is positively correlated with AQP expression. Therefore, the identification of aquaporins is an area to explore. Computational tools play an important role in aquaporin identification. In this research, we propose reliable, accurate and automated sequence predictor iAQPs-RF to identify AQPs. In this study, the feature extraction method was 188D (global protein sequence descriptor, GPSD). Six common classifiers, including random forest (RF), NaiveBayes (NB), support vector machine (SVM), XGBoost, logistic regression (LR) and decision tree (DT), were used for AQP classification. The classification results show that the random forest (RF) algorithm is the most suitable machine learning algorithm, and the accuracy was 97.689%. Analysis of Variance (ANOVA) was used to analyse these characteristics. Feature rank based on the ANOVA method and IFS strategy was applied to search for the optimal features. The classification results suggest that the 26th feature (neutral/hydrophobic) and 21st feature (hydrophobic) are the two most powerful and informative features that distinguish AQPs from non-AQPs. Previous studies reported that plasma membrane proteins have hydrophobic characteristics. Aquaporin subcellular localization prediction showed that all aquaporins were plasma membrane proteins with highly conserved transmembrane structures. In addition, the 3D structure of aquaporins was consistent with the localization results. Therefore, these studies confirmed that aquaporins possess hydrophobic properties. Although aquaporins are highly conserved transmembrane structures, the phylogenetic tree shows the diversity of aquaporins during evolution. The PCA showed that positive and negative samples were well separated by 54D features, indicating that the 54D feature can effectively classify aquaporins. The online prediction server is accessible at http://lab.malab.cn/∼acy/iAQP.

Maximal Information Coefficient-Based Testing to Identify Epistasis in Case-Control Association Studies

Interactions between genetic variants (epistasis) are ubiquitous in the model system and can significantly affect evolutionary adaptation, genetic mapping, and precision medical efforts. In this paper, we proposed a method for epistasis detection, called EpiMIC (epistasis detection through a maximal information coefficient (MIC)). MIC is a promising bivariate dependence measure explicitly designed for rapidly exploring various function types equally and for interpreting and comparing them on the same scale. Most epistasis detection approaches make assumptions about the form of the association between genetic variants, resulting in limited statistical performance. Based on the notion that if two SNPs do not interact, their joint distribution in all samples and in only cases should not be substantially different. We developed a statistic that utilizes the difference of MIC as a signal of epistasis and combined it with a permutation resampling strategy to estimate the empirical distribution of our statistic. Results of simulation and real-world data set showed that EpiMIC outperformed previous approaches for identifying epistasis at varying degrees of heredity.

A SNARE Protein Identification Method Based on iLearnPlus to Efficiently Solve the Data Imbalance Problem

Machine learning has been widely used to solve complex problems in engineering applications and scientific fields, and many machine learning-based methods have achieved good results in different fields. SNAREs are key elements of membrane fusion and required for the fusion process of stable intermediates. They are also associated with the formation of some psychiatric disorders. This study processes the original sequence data with the synthetic minority oversampling technique (SMOTE) to solve the problem of data imbalance and produces the most suitable machine learning model with the iLearnPlus platform for the identification of SNARE proteins. Ultimately, a sensitivity of 66.67%, specificity of 93.63%, accuracy of 91.33%, and MCC of 0.528 were obtained in the cross-validation dataset, and a sensitivity of 66.67%, specificity of 93.63%, accuracy of 91.33%, and MCC of 0.528 were obtained in the independent dataset (the adaptive skip dipeptide composition descriptor was used for feature extraction, and LightGBM with proper parameters was used as the classifier). These results demonstrate that this combination can perform well in the classification of SNARE proteins and is superior to other methods.

Identify DNA-Binding Proteins Through the Extreme Gradient Boosting Algorithm

The exploration of DNA-binding proteins (DBPs) is an important aspect of studying biological life activities. Research on life activities requires the support of scientific research results on DBPs. The decline in many life activities is closely related to DBPs. Generally, the detection method for identifying DBPs is achieved through biochemical experiments. This method is inefficient and requires considerable manpower, material resources and time. At present, several computational approaches have been developed to detect DBPs, among which machine learning (ML) algorithm-based computational techniques have shown excellent performance. In our experiments, our method uses fewer features and simpler recognition methods than other methods and simultaneously obtains satisfactory results. First, we use six feature extraction methods to extract sequence features from the same group of DBPs. Then, this feature information is spliced together, and the data are standardized. Finally, the extreme gradient boosting (XGBoost) model is used to construct an effective predictive model. Compared with other excellent methods, our proposed method has achieved better results. The accuracy achieved by our method is 78.26% for PDB2272 and 85.48% for PDB186. The accuracy of the experimental results achieved by our strategy is similar to that of previous detection methods.

VTP-Identifier: Vesicular Transport Proteins Identification Based on PSSM Profiles and XGBoost

Vesicular transport proteins are related to many human diseases, and they threaten human health when they undergo pathological changes. Protein function prediction has been one of the most in-depth topics in bioinformatics. In this work, we developed a useful tool to identify vesicular transport proteins. Our strategy is to extract transition probability composition, autocovariance transformation and other information from the position-specific scoring matrix as feature vectors. EditedNearesNeighbours (ENN) is used to address the imbalance of the data set, and the Max-Relevance-Max-Distance (MRMD) algorithm is adopted to reduce the dimension of the feature vector. We used 5-fold cross-validation and independent test sets to evaluate our model. On the test set, VTP-Identifier presented a higher performance compared with GRU. The accuracy, Matthew's correlation coefficient (MCC) and area under the ROC curve (AUC) were 83.6%, 0.531 and 0.873, respectively.