Positive-unlabeled learning in bioinformatics and computational biology: a brief review

Autoencoder-based drug-virus association prediction with reliable negative sample selection: A case study with COVID-19

Emergence of viruses cause unprecedented challenges and thus leading to wide-ranging consequences today. The world has faced massive disruptions like COVID-19 and continues to suffer in terms of public health and world economy. Fighting with this emergence of viruses and its reemergence plays a critical role in the health care industry. Identification of novel virus-drug associations is a vital step in drug discovery. Prediction and prioritization of novel virus-drug associations through computational approaches is an alternative and best choice considering the cost and risk of biological experiments. This study proposes a method, KR-AEVDA that relies on k-nearest neighbor based reliable negative sample selection and autoencoder based feature extraction to explore promising virus-drug associations for further experimental validation. The method analyzes complex relationships among drugs and viruses by investigating similarity and association data between drugs and viruses. It generates feature vectors from the similarity data, and reliable negative samples are extracted through an effective distance-based algorithm from the unlabeled samples in the dataset. Then high level features are extracted via an autoencoder and is fed to an ensemble classifier for inferring novel associations. Experimental results on three different datasets showed that KR-AEVDA reliably attained better performance than other state-of-the-art methods. Molecular docking is carried out between the top-predicted drugs and the crystal structure of the SARS-CoV-2's main protease to further validate the predictions. Case studies for SARS-CoV-2 illustrate the effectiveness of KR-AEVDA in identifying potential virus-drug associations.

Identification of potential riboswitch elements in Homo sapiens mRNA 5'UTR sequences using positive-unlabeled machine learning

Riboswitches are a class of noncoding RNA structures that interact with target ligands to cause a conformational change that can then execute some regulatory purpose within the cell. Riboswitches are ubiquitous and well characterized in bacteria and prokaryotes, with additional examples also being found in fungi, plants, and yeast. To date, no purely RNA-small molecule riboswitch has been discovered in Homo Sapiens. Several analogous riboswitch-like mechanisms have been described within the H. Sapiens translatome within the past decade, prompting the question: Is there a H. Sapiens riboswitch dependent on only small molecule ligands? In this work, we set out to train positive unlabeled machine learning classifiers on known riboswitch sequences and apply the classifiers to H. Sapiens mRNA 5'UTR sequences found in the 5'UTR database, UTRdb, in the hope of identifying a set of mRNAs to investigate for riboswitch functionality. 67,683 riboswitch sequences were obtained from RNAcentral and sorted for ligand type and used as positive examples and 48,031 5'UTR sequences were used as unlabeled, unknown examples. Positive examples were sorted by ligand, and 20 positive-unlabeled classifiers were trained on sequence and secondary structure features while withholding one or two ligand classes. Cross validation was then performed on the withheld ligand sets to obtain a validation accuracy range of 75%-99%. The joint sets of 5'UTRs identified as potential riboswitches by the 20 classifiers were then analyzed. 1533 sequences were identified as a riboswitch by one or more classifier(s) and 436 of the H. Sapiens 5'UTRs were labeled as harboring potential riboswitch elements by all 20 classifiers. These 436 sequences were mapped back to the most similar riboswitches within the positive data and examined. An online database of identified and ranked 5'UTRs, their features, and their most similar matches to known riboswitches, is provided to guide future experimental efforts to identify H. Sapiens riboswitches.

KG2ML: Integrating Knowledge Graphs and Positive Unlabeled Learning for Identifying Disease-Associated Genes

Background

Biomedical knowledge graphs (KGs), such as the Data Distillery Knowledge Graph (DDKG), capture known relationships among entities (e.g., genes, diseases, proteins), providing valuable insights for research. However, these relationships are typically derived from prior studies, leaving potential unknown associations unexplored. Identifying such unknown associations, including previously unknown disease-associated genes, remains a critical challenge in bioinformatics and is crucial for advancing biomedical knowledge. Traditional methods, such as linkage analysis and genome-wide association studies (GWAS), can be time-consuming and resource-intensive. This highlights the need for efficient computational approaches to identify or predict new genes using known disease-gene associations. Recently, network-based methods and KGs, enhanced by advances in machine learning (ML) frameworks, have emerged as promising tools for inferring these unexplored associations. Given the technical limitations of the Neo4j Graph Data Science (GDS) machine learning pipeline, we developed a novel machine learning pipeline called KG2ML (Knowledge Graph to Machine Learning). This pipeline utilizes our Positive and Unlabeled (PU) learning algorithm, PULSNAR (Positive Unlabeled Learning Selected Not At Random), and incorporates path-based feature extraction from ProteinGraphML.

Results

KG2ML was applied to 12 diseases, including Bipolar Disorder, Coronary Artery Disease, and Parkinson's Disease, to infer disease-associated genes not explicitly recorded in DDKG. For several of these diseases, 14 out of the 15 top-ranked genes lacked prior explicit associations in the DDKG but were supported by literature and TINX (Target Importance and Novelty Explorer) evidence. Incorporating PULSNAR-imputed genes as positives enhanced XGBoost classification, demonstrating the potential of PU learning in identifying hidden gene-disease relationships.

Conclusion

The observed improvement in classification performance after the inclusion of PULSNAR-imputed genes as positive examples, along with the subject matter experts' (SME) evaluations of the top 15 imputed genes for 12 diseases, suggests that PU learning can effectively uncover disease-gene associations missing from existing knowledge graphs (KGs). By integrating KG data with ML-based inference, our KG2ML pipeline provides a scalable and interpretable framework to advance biomedical research while addressing the inherent limitations of current KGs.

CLMT: graph contrastive learning model for microbe-drug associations prediction with transformer

Accurate prediction of microbe-drug associations is essential for drug development and disease diagnosis. However, existing methods often struggle to capture complex nonlinear relationships, effectively model long-range dependencies, and distinguish subtle similarities between microbes and drugs. To address these challenges, this paper introduces a new model for microbe-drug association prediction, CLMT. The proposed model differs from previous approaches in three key ways. Firstly, unlike conventional GCN-based models, CLMT leverages a Graph Transformer network with an attention mechanism to model high-order dependencies in the microbe-drug interaction graph, enhancing its ability to capture long-range associations. Then, we introduce graph contrastive learning, generating multiple augmented views through node perturbation and edge dropout. By optimizing a contrastive loss, CLMT distinguishes subtle structural variations, making the learned embeddings more robust and generalizable. By integrating multi-view contrastive learning and Transformer-based encoding, CLMT effectively mitigates data sparsity issues, significantly outperforming existing methods. Experimental results on three publicly available datasets demonstrate that CLMT achieves state-of-the-art performance, particularly in handling sparse data and nonlinear microbe-drug interactions, confirming its effectiveness for real-world biomedical applications. On the MDAD, aBiofilm, and Drug Virus datasets, CLMT outperforms the previously best model in terms of Accuracy by 4.3%, 3.5%, and 2.8%, respectively.

NPI-HGNN: A Heterogeneous Graph Neural Network-Based Approach for Predicting ncRNA-Protein Interactions

Accurate identification of ncRNA-protein interactions (NPIs) is critical for understanding various cellular activities and biological functions of ncRNAs and proteins. Many sequence- and/or structure- and graph-based computational approaches have been developed to identify NPIs from large-scale ncRNA and protein data in a high-throughput manner. However, many sequence- and/or structure- and graph-based computational approaches often ignore either the topological information in NPIs or the influence of other molecule networks on NPI prediction. In this work, we propose NPI-HGNN, an end-to-end graph neural network (GNN)-based approach for the identification of NPIs from a large heterogeneous network, consisting of the ncRNA-protein interaction network, the ncRNA-ncRNA similarity network, and the protein-protein interaction network. To our knowledge, NPI-HGNN is the first GNN-based predictor that integrates related heterogeneous networks for NPI prediction. Experiments on five benchmarking datasets demonstrate that NPI-HGNN outperformed several state-of-the-art sequence- and/or structure- and graph-based predictors. In addition, we showcased the prediction power of NPI-HGNN by identifying 12 interacting ncRNAs of the pre-mRNA 3' end processing protein, which indicates the effectiveness of the proposed model. The source code of NPI-HGNN is freely available for academic purposes at https://github.com/zhangxin11111/NPI-HGNN .

Sequencing and characterizing human mitochondrial genomes in the biobank-based genomic research paradigm

Human mitochondrial DNA (mtDNA) harbors essential mutations linked to aging, neurodegenerative diseases, and complex muscle disorders. Due to its uniparental and haploid inheritance, mtDNA captures matrilineal evolutionary trajectories, playing a crucial role in population and medical genetics. However, critical questions about the genomic diversity patterns, inheritance models, and evolutionary and medical functions of mtDNA remain unresolved or underexplored, particularly in the transition from traditional genotyping to large-scale genomic analyses. This review summarizes recent advancements in data-driven genomic research and technological innovations that address these questions and clarify the biological impact of nuclear-mitochondrial segments (NUMTs) and mtDNA variants on human health, disease, and evolution. We propose a streamlined pipeline to comprehensively identify mtDNA and NUMT genomic diversity using advanced sequencing and computational technologies. Haplotype-resolved mtDNA sequencing and assembly can distinguish authentic mtDNA variants from NUMTs, reduce diagnostic inaccuracies, and provide clearer insights into heteroplasmy patterns and the authenticity of paternal inheritance. This review emphasizes the need for integrative multi-omics approaches and emerging long-read sequencing technologies to gain new insights into mutation mechanisms, the influence of heteroplasmy and paternal inheritance on mtDNA diversity and disease susceptibility, and the detailed functions of NUMTs.

Identification of potential riboswitch elements inHomo SapiensmRNA 5'UTR sequences using Positive-Unlabeled machine learning

Riboswitches are a class of noncoding RNA structures that interact with target ligands to cause a conformational change that can then execute some regulatory purpose within the cell. Riboswitches are ubiquitous and well characterized in bacteria and prokaryotes, with additional examples also being found in fungi, plants, and yeast. To date, no purely RNA-small molecule riboswitch has been discovered in Homo Sapiens. Several analogous riboswitch-like mechanisms have been described within the H. Sapiens translatome within the past decade, prompting the question: Is there a H. Sapiens riboswitch dependent on only small molecule ligands? In this work, we set out to train positive unlabeled machine learning classifiers on known riboswitch sequences and apply the classifiers to H. Sapiens mRNA 5'UTR sequences found in the 5'UTR database, UTRdb, in the hope of identifying a set of mRNAs to investigate for riboswitch functionality. 67,683 riboswitch sequences were obtained from RNAcentral and sorted for ligand type and used as positive examples and 48,031 5'UTR sequences were used as unlabeled, unknown examples. Positive examples were sorted by ligand, and 20 positive-unlabeled classifiers were trained on sequence and secondary structure features while withholding one or two ligand classes. Cross validation was then performed on the withheld ligand sets to obtain a validation accuracy range of 75%-99%. The joint sets of 5'UTRs identified as potential riboswitches by the 20 classifiers were then analyzed. 15333 sequences were identified as a riboswitch by one or more classifier(s) and 436 of the H. Sapiens 5'UTRs were labeled as harboring potential riboswitch elements by all 20 classifiers. These 436 sequences were mapped back to the most similar riboswitches within the positive data and examined. An online database of identified and ranked 5'UTRs, their features, and their most similar matches to known riboswitches, is provided to guide future experimental efforts to identify H. Sapiens riboswitches.

B cell epitope prediction by capturing spatial clustering property of the epitopes using graph attention network

Knowledge of B cell epitopes is critical to vaccine design, diagnostics, and therapeutics. As experimental validation for epitopes is time-consuming and costly, many in silico tools have been developed to computationally predict the B cell epitopes. While most methods show poor performance, deep learning methods in recent years have shown promising results. We developed a method called EpiGraph that outperformed previous methods, including those that showed a significant improvement in performance in recent years. Our model's performance can be attributed to the following factors: (1) a combination of structure and sequence feature embeddings obtained from pretrained ESM-IF1 and ESM-2 models could capture the structural and evolutionary features of B cell epitopes, (2) a graph attention network could learn the spatial proximity of B cell epitopes with high graph homophily, and (3) residual connections in the model framework mitigate the over-smoothing problem in the graph neural network. Our model achieved the highest performance on an independent benchmark dataset. The results were also consistent on a different dataset. The datasets and source codes are available at https://github.com/sj584/EpiGraph . A user-friendly web server is freely available at http://epigraph.kaist.ac.kr .

Current computational tools for protein lysine acylation site prediction

As a main subtype of post-translational modification (PTM), protein lysine acylations (PLAs) play crucial roles in regulating diverse functions of proteins. With recent advancements in proteomics technology, the identification of PTM is becoming a data-rich field. A large amount of experimentally verified data is urgently required to be translated into valuable biological insights. With computational approaches, PLA can be accurately detected across the whole proteome, even for organisms with small-scale datasets. Herein, a comprehensive summary of 166 in silico PLA prediction methods is presented, including a single type of PLA site and multiple types of PLA sites. This recapitulation covers important aspects that are critical for the development of a robust predictor, including data collection and preparation, sample selection, feature representation, classification algorithm design, model evaluation, and method availability. Notably, we discuss the application of protein language models and transfer learning to solve the small-sample learning issue. We also highlight the prediction methods developed for functionally relevant PLA sites and species/substrate/cell-type-specific PLA sites. In conclusion, this systematic review could potentially facilitate the development of novel PLA predictors and offer useful insights to researchers from various disciplines.

Positive-Unlabelled learning for identifying new candidate Dietary Restriction-related genes among ageing-related genes

Dietary Restriction (DR) is one of the most popular anti-ageing interventions; recently, Machine Learning (ML) has been explored to identify potential DR-related genes among ageing-related genes, aiming to minimize costly wet lab experiments needed to expand our knowledge on DR. However, to train a model from positive (DR-related) and negative (non-DR-related) examples, the existing ML approach naively labels genes without known DR relation as negative examples, assuming that lack of DR-related annotation for a gene represents evidence of absence of DR-relatedness, rather than absence of evidence. This hinders the reliability of the negative examples (non-DR-related genes) and the method's ability to identify novel DR-related genes. This work introduces a novel gene prioritization method based on the two-step Positive-Unlabelled (PU) Learning paradigm: using a similarity-based, KNN-inspired approach, our method first selects reliable negative examples among the genes without known DR associations. Then, these reliable negatives and all known positives are used to train a classifier that effectively differentiates DR-related and non-DR-related genes, which is finally employed to generate a more reliable ranking of promising genes for novel DR-relatedness. Our method significantly outperforms (p<0.05) the existing state-of-the-art approach in three predictive accuracy metrics with up to ∼40% lower computational cost in the best case, and we identify 4 new promising DR-related genes (PRKAB1, PRKAB2, IRS2, PRKAG1), all with evidence from the existing literature supporting their potential DR-related role.

An ensemble machine learning model to uncover potential sites of hazardous waste illegal dumping based on limited supervision experience

With the soaring generation of hazardous waste (HW) during industrialization and urbanization, HW illegal dumping continues to be an intractable global issue. Particularly in developing regions with lax regulations, it has become a major source of soil and groundwater contamination. One dominant challenge for HW illegal dumping supervision is the invisibility of dumping sites, which makes HW illegal dumping difficult to be found, thereby causing a long-term adverse impact on the environment. How to utilize the limited historic supervision records to screen the potential dumping sites in the whole region is a key challenge to be addressed. In this study, a novel machine learning model based on the positive-unlabeled (PU) learning algorithm was proposed to resolve this problem through the ensemble method which could iteratively mine the features of limited historic cases. Validation of the random forest-based PU model showed that the predicted top 30% of high-risk areas could cover 68.1% of newly reported cases in the studied region, indicating the reliability of the model prediction. This novel framework will also be promising in other environmental management scenarios to deal with numerous unknown samples based on limited prior experience.

Leveraging permutation testing to assess confidence in positive-unlabeled learning applied to high-dimensional biological datasets

BACKGROUND

Compared to traditional supervised machine learning approaches employing fully labeled samples, positive-unlabeled (PU) learning techniques aim to classify "unlabeled" samples based on a smaller proportion of known positive examples. This more challenging modeling goal reflects many real-world scenarios in which negative examples are not available-posing direct challenges to defining prediction accuracy and robustness. While several studies have evaluated predictions learned from only definitive positive examples, few have investigated whether correct classification of a high proportion of known positives (KP) samples from among unlabeled samples can act as a surrogate to indicate model quality.

RESULTS

In this study, we report a novel methodology combining multiple established PU learning-based strategies with permutation testing to evaluate the potential of KP samples to accurately classify unlabeled samples without using "ground truth" positive and negative labels for validation. Multivariate synthetic and real-world high-dimensional benchmark datasets were employed to demonstrate the suitability of the proposed pipeline to provide evidence of model robustness across varied underlying ground truth class label compositions among the unlabeled set and with different proportions of KP examples. Comparisons between model performance with actual and permuted labels could be used to distinguish reliable from unreliable models.

CONCLUSIONS

As in fully supervised machine learning, permutation testing offers a means to set a baseline "no-information rate" benchmark in the context of semi-supervised PU learning inference tasks-providing a standard against which model performance can be compared.

LCASPMDA: a computational model for predicting potential microbe-drug associations based on learnable graph convolutional attention networks and self-paced iterative sampling ensemble

Introduction

Numerous studies show that microbes in the human body are very closely linked to the human host and can affect the human host by modulating the efficacy and toxicity of drugs. However, discovering potential microbe-drug associations through traditional wet labs is expensive and time-consuming, hence, it is important and necessary to develop effective computational models to detect possible microbe-drug associations.

Methods

In this manuscript, we proposed a new prediction model named LCASPMDA by combining the learnable graph convolutional attention network and the self-paced iterative sampling ensemble strategy to infer latent microbe-drug associations. In LCASPMDA, we first constructed a heterogeneous network based on newly downloaded known microbe-drug associations. Then, we adopted the learnable graph convolutional attention network to learn the hidden features of nodes in the heterogeneous network. After that, we utilized the self-paced iterative sampling ensemble strategy to select the most informative negative samples to train the Multi-Layer Perceptron classifier and put the newly-extracted hidden features into the trained MLP classifier to infer possible microbe-drug associations.

Results and discussion

Intensive experimental results on two different public databases including the MDAD and the aBiofilm showed that LCASPMDA could achieve better performance than state-of-the-art baseline methods in microbe-drug association prediction.

Learning peptide properties with positive examples only

Deep learning can create accurate predictive models by exploiting existing large-scale experimental data, and guide the design of molecules. However, a major barrier is the requirement of both positive and negative examples in the classical supervised learning frameworks. Notably, most peptide databases come with missing information and low number of observations on negative examples, as such sequences are hard to obtain using high-throughput screening methods. To address this challenge, we solely exploit the limited known positive examples in a semi-supervised setting, and discover peptide sequences that are likely to map to certain antimicrobial properties via positive-unlabeled learning (PU). In particular, we use the two learning strategies of adapting base classifier and reliable negative identification to build deep learning models for inferring solubility, hemolysis, binding against SHP-2, and non-fouling activity of peptides, given their sequence. We evaluate the predictive performance of our PU learning method and show that by only using the positive data, it can achieve competitive performance when compared with the classical positive-negative (PN) classification approach, where there is access to both positive and negative examples.

A Novel Classification Method: Neighborhood-Based Positive Unlabeled Learning Using Decision Tree (NPULUD)

In a standard binary supervised classification task, the existence of both negative and positive samples in the training dataset are required to construct a classification model. However, this condition is not met in certain applications where only one class of samples is obtainable. To overcome this problem, a different classification method, which learns from positive and unlabeled (PU) data, must be incorporated. In this study, a novel method is presented: neighborhood-based positive unlabeled learning using decision tree (NPULUD). First, NPULUD uses the nearest neighborhood approach for the PU strategy and then employs a decision tree algorithm for the classification task by utilizing the entropy measure. Entropy played a pivotal role in assessing the level of uncertainty in the training dataset, as a decision tree was developed with the purpose of classification. Through experiments, we validated our method over 24 real-world datasets. The proposed method attained an average accuracy of 87.24%, while the traditional supervised learning approach obtained an average accuracy of 83.99% on the datasets. Additionally, it is also demonstrated that our method obtained a statistically notable enhancement (7.74%), with respect to state-of-the-art peers, on average.

A Capture-Recapture-based Ascertainment Probability Weighting Method for Effect Estimation With Under-ascertained Outcomes

Outcome under-ascertainment, characterized by the incomplete identification or reporting of cases, poses a substantial challenge in epidemiologic research. While capture-recapture methods can estimate unknown case numbers, their role in estimating exposure effects in observational studies is not well established. This paper presents an ascertainment probability weighting framework that integrates capture-recapture and propensity score weighting. We propose a nonparametric estimator of effects on binary outcomes that combines exposure propensity scores with data from two conditionally independent outcome measurements to simultaneously adjust for confounding and under-ascertainment. Demonstrating its practical application, we apply the method to estimate the relationship between health care work and coronavirus disease 2019 testing in a Swedish region. We find that ascertainment probability weighting greatly influences the estimated association compared to conventional inverse probability weighting, underscoring the importance of accounting for under-ascertainment in studies with limited outcome data coverage. We conclude with practical guidelines for the method's implementation, discussing its strengths, limitations, and suitable scenarios for application.

MGCNSS: miRNA-disease association prediction with multi-layer graph convolution and distance-based negative sample selection strategy

Identifying disease-associated microRNAs (miRNAs) could help understand the deep mechanism of diseases, which promotes the development of new medicine. Recently, network-based approaches have been widely proposed for inferring the potential associations between miRNAs and diseases. However, these approaches ignore the importance of different relations in meta-paths when learning the embeddings of miRNAs and diseases. Besides, they pay little attention to screening out reliable negative samples which is crucial for improving the prediction accuracy. In this study, we propose a novel approach named MGCNSS with the multi-layer graph convolution and high-quality negative sample selection strategy. Specifically, MGCNSS first constructs a comprehensive heterogeneous network by integrating miRNA and disease similarity networks coupled with their known association relationships. Then, we employ the multi-layer graph convolution to automatically capture the meta-path relations with different lengths in the heterogeneous network and learn the discriminative representations of miRNAs and diseases. After that, MGCNSS establishes a highly reliable negative sample set from the unlabeled sample set with the negative distance-based sample selection strategy. Finally, we train MGCNSS under an unsupervised learning manner and predict the potential associations between miRNAs and diseases. The experimental results fully demonstrate that MGCNSS outperforms all baseline methods on both balanced and imbalanced datasets. More importantly, we conduct case studies on colon neoplasms and esophageal neoplasms, further confirming the ability of MGCNSS to detect potential candidate miRNAs. The source code is publicly available on GitHub https://github.com/15136943622/MGCNSS/tree/master.

DiscoTope-3.0: improved B-cell epitope prediction using inverse folding latent representations

Accurate computational identification of B-cell epitopes is crucial for the development of vaccines, therapies, and diagnostic tools. However, current structure-based prediction methods face limitations due to the dependency on experimentally solved structures. Here, we introduce DiscoTope-3.0, a markedly improved B-cell epitope prediction tool that innovatively employs inverse folding structure representations and a positive-unlabelled learning strategy, and is adapted for both solved and predicted structures. Our tool demonstrates a considerable improvement in performance over existing methods, accurately predicting linear and conformational epitopes across multiple independent datasets. Most notably, DiscoTope-3.0 maintains high predictive performance across solved, relaxed and predicted structures, alleviating the need for experimental structures and extending the general applicability of accurate B-cell epitope prediction by 3 orders of magnitude. DiscoTope-3.0 is made widely accessible on two web servers, processing over 100 structures per submission, and as a downloadable package. In addition, the servers interface with RCSB and AlphaFoldDB, facilitating large-scale prediction across over 200 million cataloged proteins. DiscoTope-3.0 is available at: https://services.healthtech.dtu.dk/service.php?DiscoTope-3.0.

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.

Learning Peptide Properties with Positive Examples Only

Deep learning can create accurate predictive models by exploiting existing large-scale experimental data, and guide the design of molecules. However, a major barrier is the requirement of both positive and negative examples in the classical supervised learning frameworks. Notably, most peptide databases come with missing information and low number of observations on negative examples, as such sequences are hard to obtain using high-throughput screening methods. To address this challenge, we solely exploit the limited known positive examples in a semi-supervised setting, and discover peptide sequences that are likely to map to certain antimicrobial properties via positive-unlabeled learning (PU). In particular, we use the two learning strategies of adapting base classifier and reliable negative identification to build deep learning models for inferring solubility, hemolysis, binding against SHP-2, and non-fouling activity of peptides, given their sequence. We evaluate the predictive performance of our PU learning method and show that by only using the positive data, it can achieve competitive performance when compared with the classical positive-negative (PN) classification approach, where there is access to both positive and negative examples.

Predicting microbe-drug associations with structure-enhanced contrastive learning and self-paced negative sampling strategy

MOTIVATION

Predicting the associations between human microbes and drugs (MDAs) is one critical step in drug development and precision medicine areas. Since discovering these associations through wet experiments is time-consuming and labor-intensive, computational methods have already been an effective way to tackle this problem. Recently, graph contrastive learning (GCL) approaches have shown great advantages in learning the embeddings of nodes from heterogeneous biological graphs (HBGs). However, most GCL-based approaches don't fully capture the rich structure information in HBGs. Besides, fewer MDA prediction methods could screen out the most informative negative samples for effectively training the classifier. Therefore, it still needs to improve the accuracy of MDA predictions.

RESULTS

In this study, we propose a novel approach that employs the Structure-enhanced Contrastive learning and Self-paced negative sampling strategy for Microbe-Drug Association predictions (SCSMDA). Firstly, SCSMDA constructs the similarity networks of microbes and drugs, as well as their different meta-path-induced networks. Then SCSMDA employs the representations of microbes and drugs learned from meta-path-induced networks to enhance their embeddings learned from the similarity networks by the contrastive learning strategy. After that, we adopt the self-paced negative sampling strategy to select the most informative negative samples to train the MLP classifier. Lastly, SCSMDA predicts the potential microbe-drug associations with the trained MLP classifier. The embeddings of microbes and drugs learning from the similarity networks are enhanced with the contrastive learning strategy, which could obtain their discriminative representations. Extensive results on three public datasets indicate that SCSMDA significantly outperforms other baseline methods on the MDA prediction task. Case studies for two common drugs could further demonstrate the effectiveness of SCSMDA in finding novel MDA associations.

AVAILABILITY

The source code is publicly available on GitHub https://github.com/Yue-Yuu/SCSMDA-master.

MGREL: A multi-graph representation learning-based ensemble learning method for gene-disease association prediction

The identification of gene-disease associations plays an important role in the exploration of pathogenic mechanisms and therapeutic targets. Computational methods have been regarded as an effective way to discover the potential gene-disease associations in recent years. However, most of them ignored the combination of abundant genetic, therapeutic information, and gene-disease network topology. To this end, we re-organized the current gene-disease association benchmark dataset by extracting the newest gene-disease associations from the OMIM database. Then, we developed a multi-graph representation learning-based ensemble model, named MGREL to predict gene-disease associations. MGREL integrated two feature generation channels to extract gene and disease features, including a knowledge extraction channel which learned high-order representations from genetic and therapeutic information, and a graph learning channel which acquired network topological representations through multiple advanced graph representation learning methods. Then, an ensemble learning method with 5 machine learning models was used as the classifier to predict the gene-disease association. Comprehensive experiments have demonstrated the significant performance achieved by MGREL compared to 5 state-of-the-art methods. For the major measurements (AUC = 0.925, AUPR = 0.935), the relative improvements of MGREL compared to the suboptimal methods are 3.24%, and 2.75%, respectively. MGREL also achieved impressive improvements in the challenging tasks of predicting potential associations for unknown genes/diseases. In addition, case studies implied potential applications for MGREL in the discovery of potential therapeutic targets.

Transformer-based deep learning for predicting protein properties in the life sciences

Recent developments in deep learning, coupled with an increasing number of sequenced proteins, have led to a breakthrough in life science applications, in particular in protein property prediction. There is hope that deep learning can close the gap between the number of sequenced proteins and proteins with known properties based on lab experiments. Language models from the field of natural language processing have gained popularity for protein property predictions and have led to a new computational revolution in biology, where old prediction results are being improved regularly. Such models can learn useful multipurpose representations of proteins from large open repositories of protein sequences and can be used, for instance, to predict protein properties. The field of natural language processing is growing quickly because of developments in a class of models based on a particular model-the Transformer model. We review recent developments and the use of large-scale Transformer models in applications for predicting protein characteristics and how such models can be used to predict, for example, post-translational modifications. We review shortcomings of other deep learning models and explain how the Transformer models have quickly proven to be a very promising way to unravel information hidden in the sequences of amino acids.

Predicting Pseudouridine Sites with Porpoise

Pseudouridine is a ubiquitous RNA modification and plays a crucial role in many biological processes. However, it remains a challenging task to identify pseudouridine sites using expensive and time-consuming experimental research. To this end, we present Porpoise, a computational approach to identify pseudouridine sites from RNA sequence data. Porpoise builds on a stacking ensemble learning framework with several informative features and achieves competitive performance compared with state-of-the-art approaches. This protocol elaborates on step-by-step use and execution of the local stand-alone version and the webserver of Porpoise. In addition, we also provide a general machine learning framework that can help identify the optimal stacking ensemble learning model using different combinations of feature-based features. This general machine learning framework can facilitate users to build their pseudouridine predictors using their in-house datasets.

Bioinformatics approaches for unveiling virus-host interactions

The coronavirus disease-2019 (COVID-19) pandemic has elucidated major limitations in the capacity of medical and research institutions to appropriately manage emerging infectious diseases. We can improve our understanding of infectious diseases by unveiling virus-host interactions through host range prediction and protein-protein interaction prediction. Although many algorithms have been developed to predict virus-host interactions, numerous issues remain to be solved, and the entire network remains veiled. In this review, we comprehensively surveyed algorithms used to predict virus-host interactions. We also discuss the current challenges, such as dataset biases toward highly pathogenic viruses, and the potential solutions. The complete prediction of virus-host interactions remains difficult; however, bioinformatics can contribute to progress in research on infectious diseases and human health.

Function Prediction of Peptide Toxins with Sequence-Based Multi-Tasking PU Learning Method

Peptide toxins generally have extreme pharmacological activities and provide a rich source for the discovery of drug leads. However, determining the optimal activity of a new peptide can be a long and expensive process. In this study, peptide toxins were retrieved from Uniprot; three positive-unlabeled (PU) learning schemes, adaptive basis classifier, two-step method, and PU bagging were adopted to develop models for predicting the biological function of new peptide toxins. All three schemes were embedded with 14 machine learning classifiers. The prediction results of the adaptive base classifier and the two-step method were highly consistent. The models with top comprehensive performances were further optimized by feature selection and hyperparameter tuning, and the models were validated by making predictions for 61 three-finger toxins or the external HemoPI dataset. Biological functions that can be identified by these models include cardiotoxicity, vasoactivity, lipid binding, hemolysis, neurotoxicity, postsynaptic neurotoxicity, hypotension, and cytolysis, with relatively weak predictions for hemostasis and presynaptic neurotoxicity. These models are discovery-prediction tools for active peptide toxins and are expected to accelerate the development of peptide toxins as drugs.

Predicting multiple types of miRNA-disease associations using adaptive weighted nonnegative tensor factorization with self-paced learning and hypergraph regularization

More and more evidence indicates that the dysregulations of microRNAs (miRNAs) lead to diseases through various kinds of underlying mechanisms. Identifying the multiple types of disease-related miRNAs plays an important role in studying the molecular mechanism of miRNAs in diseases. Moreover, compared with traditional biological experiments, computational models are time-saving and cost-minimized. However, most tensor-based computational models still face three main challenges: (i) easy to fall into bad local minima; (ii) preservation of high-order relations; (iii) false-negative samples. To this end, we propose a novel tensor completion framework integrating self-paced learning, hypergraph regularization and adaptive weight tensor into nonnegative tensor factorization, called SPLDHyperAWNTF, for the discovery of potential multiple types of miRNA-disease associations. We first combine self-paced learning with nonnegative tensor factorization to effectively alleviate the model from falling into bad local minima. Then, hypergraphs for miRNAs and diseases are constructed, and hypergraph regularization is used to preserve the high-order complex relations of these hypergraphs. Finally, we innovatively introduce adaptive weight tensor, which can effectively alleviate the impact of false-negative samples on the prediction performance. The average results of 5-fold and 10-fold cross-validation on four datasets show that SPLDHyperAWNTF can achieve better prediction performance than baseline models in terms of Top-1 precision, Top-1 recall and Top-1 F1. Furthermore, we implement case studies to further evaluate the accuracy of SPLDHyperAWNTF. As a result, 98 (MDAv2.0) and 98 (MDAv2.0-2) of top-100 are confirmed by HMDDv3.2 dataset. Moreover, the results of enrichment analysis illustrate that unconfirmed potential associations have biological significance.

iPseU-TWSVM: Identification of RNA pseudouridine sites based on TWSVM

Biological sequence analysis is an important basic research work in the field of bioinformatics. With the explosive growth of data, machine learning methods play an increasingly important role in biological sequence analysis. By constructing a classifier for prediction, the input sequence feature vector is predicted and evaluated, and the knowledge of gene structure, function and evolution is obtained from a large amount of sequence information, which lays a foundation for researchers to carry out in-depth research. At present, many machine learning methods have been applied to biological sequence analysis such as RNA gene recognition and protein secondary structure prediction. As a biological sequence, RNA plays an important biological role in the encoding, decoding, regulation and expression of genes. The analysis of RNA data is currently carried out from the aspects of structure and function, including secondary structure prediction, non-coding RNA identification and functional site prediction. Pseudouridine (У) is the most widespread and rich RNA modification and has been discovered in a variety of RNAs. It is highly essential for the study of related functional mechanisms and disease diagnosis to accurately identify У sites in RNA sequences. At present, several computational approaches have been suggested as an alternative to experimental methods to detect У sites, but there is still potential for improvement in their performance. In this study, we present a model based on twin support vector machine (TWSVM) for У site identification. The model combines a variety of feature representation techniques and uses the max-relevance and min-redundancy methods to obtain the optimum feature subset for training. The independent testing accuracy is improved by 3.4% in comparison to current advanced У site predictors. The outcomes demonstrate that our model has better generalization performance and improves the accuracy of У site identification. iPseU-TWSVM can be a helpful tool to identify У sites.

Unsupervised and semi-supervised learning: the next frontier in machine learning for plant systems biology

Advances in high-throughput omics technologies are leading plant biology research into the era of big data. Machine learning (ML) performs an important role in plant systems biology because of its excellent performance and wide application in the analysis of big data. However, to achieve ideal performance, supervised ML algorithms require large numbers of labeled samples as training data. In some cases, it is impossible or prohibitively expensive to obtain enough labeled training data; here, the paradigms of unsupervised learning (UL) and semi-supervised learning (SSL) play an indispensable role. In this review, we first introduce the basic concepts of ML techniques, as well as some representative UL and SSL algorithms, including clustering, dimensionality reduction, self-supervised learning (self-SL), positive-unlabeled (PU) learning and transfer learning. We then review recent advances and applications of UL and SSL paradigms in both plant systems biology and plant phenotyping research. Finally, we discuss the limitations and highlight the significance and challenges of UL and SSL strategies in plant systems biology.

PCfun: a hybrid computational framework for systematic characterization of protein complex function

In molecular biology, it is a general assumption that the ensemble of expressed molecules, their activities and interactions determine biological function, cellular states and phenotypes. Stable protein complexes—or macromolecular machines—are, in turn, the key functional entities mediating and modulating most biological processes. Although identifying protein complexes and their subunit composition can now be done inexpensively and at scale, determining their function remains challenging and labor intensive. This study describes Protein Complex Function predictor (PCfun), the first computational framework for the systematic annotation of protein complex functions using Gene Ontology (GO) terms. PCfun is built upon a word embedding using natural language processing techniques based on 1 million open access PubMed Central articles. Specifically, PCfun leverages two approaches for accurately identifying protein complex function, including: (i) an unsupervised approach that obtains the nearest neighbor (NN) GO term word vectors for a protein complex query vector and (ii) a supervised approach using Random Forest (RF) models trained specifically for recovering the GO terms of protein complex queries described in the CORUM protein complex database. PCfun consolidates both approaches by performing a hypergeometric statistical test to enrich the top NN GO terms within the child terms of the GO terms predicted by the RF models. The documentation and implementation of the PCfun package are available at https://github.com/sharmavaruns/PCfun. We anticipate that PCfun will serve as a useful tool and novel paradigm for the large-scale characterization of protein complex function.

NNAN: Nearest Neighbor Attention Network to Predict Drug–Microbe Associations

Many drugs can be metabolized by human microbes; the drug metabolites would significantly alter pharmacological effects and result in low therapeutic efficacy for patients. Hence, it is crucial to identify potential drug–microbe associations (DMAs) before the drug administrations. Nevertheless, traditional DMA determination cannot be applied in a wide range due to the tremendous number of microbe species, high costs, and the fact that it is time-consuming. Thus, predicting possible DMAs in computer technology is an essential topic. Inspired by other issues addressed by deep learning, we designed a deep learning-based model named Nearest Neighbor Attention Network (NNAN). The proposed model consists of four components, namely, a similarity network constructor, a nearest-neighbor aggregator, a feature attention block, and a predictor. In brief, the similarity block contains a microbe similarity network and a drug similarity network. The nearest-neighbor aggregator generates the embedding representations of drug–microbe pairs by integrating drug neighbors and microbe neighbors of each drug–microbe pair in the network. The feature attention block evaluates the importance of each dimension of drug–microbe pair embedding by a set of ordinary multi-layer neural networks. The predictor is an ordinary fully-connected deep neural network that functions as a binary classifier to distinguish potential DMAs among unlabeled drug–microbe pairs. Several experiments on two benchmark databases are performed to evaluate the performance of NNAN. First, the comparison with state-of-the-art baseline approaches demonstrates the superiority of NNAN under cross-validation in terms of predicting performance. Moreover, the interpretability inspection reveals that a drug tends to associate with a microbe if it finds its top-l most similar neighbors that associate with the microbe.

Computational analysis and prediction of PE_PGRS proteins using machine learning

Mycobacterium tuberculosis genome comprises approximately 10% of two families of poorly characterised genes due to their high GC content and highly repetitive nature. The largest sub-group, the proline-glutamic acid polymorphic guanine-cytosine-rich sequence (PE_PGRS) family, is thought to be involved in host response and disease pathogenicity. Due to their high genetic variability and complexity of analysis, they are typically disregarded for further research in genomic studies. There are currently limited online resources and homology computational tools that can identify and analyse PE_PGRS proteins. In addition, they are computational-intensive and time-consuming, and lack sensitivity. Therefore, computational methods that can rapidly and accurately identify PE_PGRS proteins are valuable to facilitate the functional elucidation of the PE_PGRS family proteins. In this study, we developed the first machine learning-based bioinformatics approach, termed PEPPER, to allow users to identify PE_PGRS proteins rapidly and accurately. PEPPER was built upon a comprehensive evaluation of 13 popular machine learning algorithms with various sequence and physicochemical features. Empirical studies demonstrated that PEPPER achieved significantly better performance than alignment-based approaches, BLASTP and PHMMER, in both prediction accuracy and speed. PEPPER is anticipated to facilitate community-wide efforts to conduct high-throughput identification and analysis of PE_PGRS proteins.