DeepVF: a deep learning-based hybrid framework for identifying virulence factors using the stacking strategy

Stack-HDAC3i: A high-precision identification of HDAC3 inhibitors by exploiting a stacked ensemble-learning framework

Epigenetics involves reversible modifications in gene expression without altering the genetic code itself. Among these modifications, histone deacetylases (HDACs) play a key role by removing acetyl groups from lysine residues on histones. Overexpression of HDACs is linked to the proliferation and survival of tumor cells. To combat this, HDAC inhibitors (HDACi) are commonly used in cancer treatments. However, pan-HDAC inhibition can lead to numerous side effects. Therefore, isoform-selective HDAC inhibitors, such as HDAC3i, could be advantageous for treating various medical conditions while minimizing off-target effects. To date, computational approaches that use only the SMILES notation without any experimental evidence have become increasingly popular and necessary for the initial discovery of novel potential therapeutic drugs. In this study, we develop an innovative and high-precision stacked-ensemble framework, called Stack-HDAC3i, which can directly identify HDAC3i using only the SMILES notation. Using an up-to-date benchmark dataset, we first employed both molecular descriptors and Mol2Vec embeddings to generate feature representations that cover multi-view information embedded in HDAC3i, such as structural and contextual information. Subsequently, these feature representations were used to train baseline models using nine popular ML algorithms. Finally, the probabilistic features derived from the selected baseline models were fused to construct the final stacked model. Both cross-validation and independent tests showed that Stack-HDAC3i is a high-accuracy prediction model with great generalization ability for identifying HDAC3i. Furthermore, in the independent test, Stack-HDAC3i achieved an accuracy of 0.926 and Matthew's correlation coefficient of 0.850, which are 0.44-6.11% and 0.83-11.90% higher than its constituent baseline models, respectively.

DTVF: A User-Friendly Tool for Virulence Factor Prediction Based on ProtT5 and Deep Transfer Learning Models

Virulencefactors (VFs) are key molecules that enable pathogens to evade the immune systems of the host. These factors are crucial for revealing the pathogenic processes of microbes and drug discovery. Identification of virulence factors in microbes become an important problem in the field of bioinformatics. To address this problem, this study proposes a novel model DTVF (Deep Transfer Learning for Virulence Factor Prediction), which integrates the ProtT5 protein sequence extraction model with a dual-channel deep learning model. In the dual-channel deep learning model, we innovatively integrate long short-term memory (LSTM) with convolutional neural networks (CNNs), creating a novel integrated architecture. Furthermore, by incorporating the attention mechanism, the accuracy of VF detection was significantly enhanced. We evaluated the DTVF model against other excellent-performing models in the field. DTVF demonstrates superior performance, achieving an accuracy rate of 84.55% and an AUROC of 92.08% on the benchmark dataset. DTVF shows state-of-the-art performance in this field, surpassing the existing models in nearly all metrics. To facilitate the use of biologists, we have also developed an interactive web-based user interface version of DTVF based on Gradio.

Computational prediction of phosphorylation sites of SARS-CoV-2 infection using feature fusion and optimization strategies

SARS-CoV-2's global spread has instigated a critical health and economic emergency, impacting countless individuals. Understanding the virus's phosphorylation sites is vital to unravel the molecular intricacies of the infection and subsequent changes in host cellular processes. Several computational methods have been proposed to identify phosphorylation sites, typically focusing on specific residue (S/T) or Y phosphorylation sites. Unfortunately, current predictive tools perform best on these specific residues and may not extend their efficacy to other residues, emphasizing the urgent need for enhanced methodologies. In this study, we developed a novel predictor that integrated all the residues (STY) phosphorylation sites information. We extracted ten different feature descriptors, primarily derived from composition, evolutionary, and position-specific information, and assessed their discriminative power through five classifiers. Our results indicated that Light Gradient Boosting (LGB) showed superior performance, and five descriptors displayed excellent discriminative capabilities. Subsequently, we identified the top two integrated features have high discriminative capability and trained with LGB to develop the final prediction model, LGB-IPs. The proposed approach shows an excellent performance on 10-fold cross-validation with an ACC, MCC, and AUC values of 0.831, 0.662, 0.907, respectively. Notably, these performances are replicated in the independent evaluation. Consequently, our approach may provide valuable insights into the phosphorylation mechanisms in SARS-CoV-2 infection for biomedical researchers.

A deep learning method to predict bacterial ADP-ribosyltransferase toxins

MOTIVATION

ADP-ribosylation is a critical modification involved in regulating diverse cellular processes, including chromatin structure regulation, RNA transcription, and cell death. Bacterial ADP-ribosyltransferase toxins (bARTTs) serve as potent virulence factors that orchestrate the manipulation of host cell functions to facilitate bacterial pathogenesis. Despite their pivotal role, the bioinformatic identification of novel bARTTs poses a formidable challenge due to limited verified data and the inherent sequence diversity among bARTT members.

RESULTS

We proposed a deep learning-based model, ARTNet, specifically engineered to predict bARTTs from bacterial genomes. Initially, we introduced an effective data augmentation method to address the issue of data scarcity in training ARTNet. Subsequently, we employed a data optimization strategy by utilizing ART-related domain subsequences instead of the primary full sequences, thereby significantly enhancing the performance of ARTNet. ARTNet achieved a Matthew's correlation coefficient (MCC) of 0.9351 and an F1-score (macro) of 0.9666 on repeated independent test datasets, outperforming three other deep learning models and six traditional machine learning models in terms of time efficiency and accuracy. Furthermore, we empirically demonstrated the ability of ARTNet to predict novel bARTTs across domain superfamilies without sequence similarity. We anticipate that ARTNet will greatly facilitate the screening and identification of novel bARTTs from bacterial genomes.

AVAILABILITY AND IMPLEMENTATION

ARTNet is publicly accessible at http://www.mgc.ac.cn/ARTNet/. The source code of ARTNet is freely available at https://github.com/zhengdd0422/ARTNet/.

SEP-AlgPro: An efficient allergen prediction tool utilizing traditional machine learning and deep learning techniques with protein language model features

Allergy is a hypersensitive condition in which individuals develop objective symptoms when exposed to harmless substances at a dose that would cause no harm to a "normal" person. Most current computational methods for allergen identification rely on homology or conventional machine learning using limited set of feature descriptors or validation on specific datasets, making them inefficient and inaccurate. Here, we propose SEP-AlgPro for the accurate identification of allergen protein from sequence information. We analyzed 10 conventional protein-based features and 14 different features derived from protein language models to gauge their effectiveness in differentiating allergens from non-allergens using 15 different classifiers. However, the final optimized model employs top 10 feature descriptors with top seven machine learning classifiers. Results show that the features derived from protein language models exhibit superior discriminative capabilities compared to traditional feature sets. This enabled us to select the most discriminatory baseline models, whose predicted outputs were aggregated and used as input to a deep neural network for the final allergen prediction. Extensive case studies showed that SEP-AlgPro outperforms state-of-the-art predictors in accurately identifying allergens. A user-friendly web server was developed and made freely available at https://balalab-skku.org/SEP-AlgPro/, making it a powerful tool for identifying potential allergens.

Exhaled volatolomics profiling facilitates personalized screening for gastric cancer

Gastric cancer (GC) is one of the most fatal cancers, characterized by non-specific early symptoms and difficulty in detection. However, there are no valid non-invasive screening tools available for GC. Here we establish a non-invasive method that employs exhaled volatolomics and ensemble learning to detect GC. We developed a comprehensive mass spectrometry-based procedure and determined of a wide range of volatolomics from 314 breath samples. The discovery, identification and verification research screened a biomarker panel to distinguish GC from controls. This panel has achieved 0.90 (0.87-0.94, 95%CI) accuracy, with an area under curve (AUC) of 0.92 (0.89-0.94, 95%CI) in discovery cohort and 0.88 (0.83-0.91, 95%CI) accuracy with an AUC of 0.91 (0.87-0.93, 95%CI) in replication cohort, which outperformed traditional serum markers. Single-cell sequencing and gene set enrichment analysis revealed that these exhaled markers originated from aldehyde oxidation and pyruvate metabolism. Our approach advances the design of exhaled analysis for GC detection and holds promise as a non-invasive method to the clinic.

Identifying virulence factors using graph transformer autoencoder with ESMFold-predicted structures

With the increasing resistance of bacterial pathogens to conventional antibiotics, antivirulence strategies targeting virulence factors (VFs) have become an effective new therapy for the treatment of pathogenic bacterial infections. Therefore, the identification and prediction of VFs can provide ideal candidate targets for the implementation of antivirulence strategies in treating infections caused by pathogenic bacteria. Currently, the existing computational models predominantly rely on the amino acid sequences of virulence proteins while overlooking structural information. Here, we propose a novel graph transformer autoencoder for VF identification (GTAE-VF), which utilizes ESMFold-predicted 3D structures and converts the VF identification problem into a graph-level prediction task. In an encoder-decoder framework, GTAE-VF adaptively learns both local and global information by integrating a graph convolutional network and a transformer to implement all-pair message passing, which can better capture long-range correlations and potential relationships. Extensive experiments on an independent test dataset demonstrate that GTAE-VF achieves reliable and robust prediction accuracy with an AUC of 0.963, which is consistently better than that of other structure-based and sequence-based approaches. We believe that GTAE-VF has the potential to emerge as a valuable tool for assessing VFs and devising antivirulence strategies.

Leveraging a meta-learning approach to advance the accuracy of Nav blocking peptides prediction

The voltage-gated sodium (Nav) channel is a crucial molecular component responsible for initiating and propagating action potentials. While the α subunit, forming the channel pore, plays a central role in this function, the complete physiological function of Nav channels relies on crucial interactions between the α subunit and auxiliary proteins, known as protein-protein interactions (PPI). Nav blocking peptides (NaBPs) have been recognized as a promising and alternative therapeutic agent for pain and itch. Although traditional experimental methods can precisely determine the effect and activity of NaBPs, they remain time-consuming and costly. Hence, machine learning (ML)-based methods that are capable of accurately contributing in silico prediction of NaBPs are highly desirable. In this study, we develop an innovative meta-learning-based NaBP prediction method (MetaNaBP). MetaNaBP generates new feature representations by employing a wide range of sequence-based feature descriptors that cover multiple perspectives, in combination with powerful ML algorithms. Then, these feature representations were optimized to identify informative features using a two-step feature selection method. Finally, the selected informative features were applied to develop the final meta-predictor. To the best of our knowledge, MetaNaBP is the first meta-predictor for NaBP prediction. Experimental results demonstrated that MetaNaBP achieved an accuracy of 0.948 and a Matthews correlation coefficient of 0.898 over the independent test dataset, which were 5.79% and 11.76% higher than the existing method. In addition, the discriminative power of our feature representations surpassed that of conventional feature descriptors over both the training and independent test datasets. We anticipate that MetaNaBP will be exploited for the large-scale prediction and analysis of NaBPs to narrow down the potential NaBPs.

VF-Pred: Predicting virulence factor using sequence alignment percentage and ensemble learning models

This study introduces VF-Pred, a novel framework developed for the purpose of detecting virulence factors (VFs) through the analysis of genomic data. VFs are crucial for pathogens to successfully infect host tissue and evade the immune system, leading to the onset of infectious diseases. Identifying VFs accurately is of utmost importance in the quest for developing potent drugs and vaccines to counter these diseases. To accomplish this, VF-Pred combines various feature engineering techniques to generate inputs for distinct machine learning classification models. The collective predictions of these models are then consolidated by a final downstream model using an innovative ensembling approach. One notable aspect of VF-Pred is the inclusion of a novel Seq-Alignment feature, which significantly enhances the accuracy of the employed machine learning algorithms. The framework was meticulously trained on 982 features obtained from extensive feature engineering, utilizing a comprehensive ensemble of 25 models. The new downstream ensembling technique adopted by VF-Pred surpasses existing stacking strategies and other ensembling methods, delivering superior performance in VF detection. There have been similar studies done earlier, VF-Pred stands out in comparison showing higher accuracy (83.5 %), higher sensitivity (87 %) towards identification of VFs. Accessible through a user-friendly web page, VF-Pred can be accessed by providing the identifier and protein sequence, enabling the prediction of high or low likelihoods of VFs. Overall, VF-Pred showcases a highly promising methodology for the identification of VFs, potentially paving the way for the development of more effective strategies in the battle against infectious diseases.

StackER: a novel SMILES-based stacked approach for the accelerated and efficient discovery of ERα and ERβ antagonists

The role of estrogen receptors (ERs) in breast cancer is of great importance in both clinical practice and scientific exploration. However, around 15-30% of those affected do not see benefits from the usual treatments owing to the innate resistance mechanisms, while 30-40% will gain resistance through treatments. In order to address this problem and facilitate community-wide efforts, machine learning (ML)-based approaches are considered one of the most cost-effective and large-scale identification methods. Herein, we propose a new SMILES-based stacked approach, termed StackER, for the accelerated and efficient identification of ERα and ERβ inhibitors. In StackER, we first established an up-to-date dataset consisting of 1,996 and 1,207 compounds for ERα and ERβ, respectively. Using the up-to-date dataset, StackER explored a wide range of different SMILES-based feature descriptors and ML algorithms in order to generate probabilistic features (PFs). Finally, the selected PFs derived from the two-step feature selection strategy were used for the development of an efficient stacked model. Both cross-validation and independent tests showed that StackER surpassed several conventional ML classifiers and the existing method in precisely predicting ERα and ERβ inhibitors. Remarkably, StackER achieved MCC values of 0.829-0.847 and 0.712-0.786 in terms of the cross-validation and independent tests, respectively, which were 5.92-8.29 and 1.59-3.45% higher than the existing method. In addition, StackER was applied to determine useful features for being ERα and ERβ inhibitors and identify FDA-approved drugs as potential ERα inhibitors in efforts to facilitate drug repurposing. This innovative stacked method is anticipated to facilitate community-wide efforts in efficiently narrowing down ER inhibitor screening.

RVFScan predicts virulence factor genes and hypervirulence of the clinical metagenome

Bacterial infections often involve virulence factors that play a crucial role in the pathogenicity of bacteria. Accurate detection of virulence factor genes (VFGs) is essential for precise treatment and prognostic management of hypervirulent bacterial infections. However, there is a lack of rapid and accurate methods for VFG identification from the metagenomic data of clinical samples. Here, we developed a Reads-based Virulence Factors Scanner (RVFScan), an innovative user-friendly online tool that integrates a comprehensive VFG database with similarity matrix-based criteria for VFG prediction and annotation using metagenomic data without the need for assembly. RVFScan demonstrated superior performance compared to previous assembly-based and read-based VFG predictors, achieving a sensitivity of 97%, specificity of 98% and accuracy of 98%. We also conducted a large-scale analysis of 2425 clinical metagenomic datasets to investigate the utility of RVFScan, the species-specific VFG profiles and associations between VFGs and virulence phenotypes for 24 important pathogens were analyzed. By combining genomic comparisons and network analysis, we identified 53 VFGs with significantly higher abundances in hypervirulent Klebsiella pneumoniae (hvKp) than in classical K. pneumoniae. Furthermore, a cohort of 1256 samples suspected of K. pneumoniae infection demonstrated that RVFScan could identify hvKp with a sensitivity of 90%, specificity of 100% and accuracy of 98.73%, with 90% of hvKp samples consistent with clinical diagnosis (Cohen's kappa, 0.94). RVFScan has the potential to detect VFGs in low-biomass and high-complexity clinical samples using metagenomic reads without assembly. This capability facilitates the rapid identification and targeted treatment of hvKp infections and holds promise for application to other hypervirulent pathogens.

TIPred: a novel stacked ensemble approach for the accelerated discovery of tyrosinase inhibitory peptides

BACKGROUND

Tyrosinase is an enzyme involved in melanin production in the skin. Several hyperpigmentation disorders involve the overproduction of melanin and instability of tyrosinase activity resulting in darker, discolored patches on the skin. Therefore, discovering tyrosinase inhibitory peptides (TIPs) is of great significance for basic research and clinical treatments. However, the identification of TIPs using experimental methods is generally cost-ineffective and time-consuming.

RESULTS

Herein, a stacked ensemble learning approach, called TIPred, is proposed for the accurate and quick identification of TIPs by using sequence information. TIPred explored a comprehensive set of various baseline models derived from well-known machine learning (ML) algorithms and heterogeneous feature encoding schemes from multiple perspectives, such as chemical structure properties, physicochemical properties, and composition information. Subsequently, 130 baseline models were trained and optimized to create new probabilistic features. Finally, the feature selection approach was utilized to determine the optimal feature vector for developing TIPred. Both tenfold cross-validation and independent test methods were employed to assess the predictive capability of TIPred by using the stacking strategy. Experimental results showed that TIPred significantly outperformed the state-of-the-art method in terms of the independent test, with an accuracy of 0.923, MCC of 0.757 and an AUC of 0.977.

CONCLUSIONS

The proposed TIPred approach could be a valuable tool for rapidly discovering novel TIPs and effectively identifying potential TIP candidates for follow-up experimental validation. Moreover, an online webserver of TIPred is publicly available at http://pmlabstack.pythonanywhere.com/TIPred .

PredLLPS_PSSM: a novel predictor for liquid-liquid protein separation identification based on evolutionary information and a deep neural network

The formation of biomolecular condensates by liquid-liquid phase separation (LLPS) has become a universal mechanism for spatiotemporal coordination of biological activities in cells and has been widely observed to directly regulate the key cellular processes involved in cancer cell pathology. However, the complexity of protein sequences and the diversity of conformations are inherently disordered, which poses great challenges for LLPS protein calculations and experimental research. Herein, we proposed a novel predictor named PredLLPS_PSSM for LLPS protein identification based only on sequence evolution information. Because finding real and reliable samples is the cornerstone of building predictors, we collected anew and collated the LLPS proteins from the latest versions of three databases. By comparing the performance of the position-specific score matrix (PSSM) and word embedding, PredLLPS_PSSM combined PSSM-based information and two deep learning frameworks. Independent tests using three existing independent test datasets and two newly constructed independent test datasets demonstrated the superiority of PredLLPS_PSSM compared with state-of-the-art methods. Furthermore, we tested PredLLPS_PSSM on nine experimentally identified LLPS proteins from three insects that were not included in any of the databases. In addition, the powerful Shapley Additive exPlanation algorithm and heatmap were applied to find the most critical amino acids relevant to LLPS.

Empirical comparison and analysis of machine learning-based approaches for druggable protein identification

Efficiently and precisely identifying drug targets is crucial for developing and discovering potential medications. While conventional experimental approaches can accurately pinpoint these targets, they suffer from time constraints and are not easily adaptable to high-throughput processes. On the other hand, computational approaches, particularly those utilizing machine learning (ML), offer an efficient means to accelerate the prediction of druggable proteins based solely on their primary sequences. Recently, several state-of-the-art computational methods have been developed for predicting and analyzing druggable proteins. These computational methods showed high diversity in terms of benchmark datasets, feature extraction schemes, ML algorithms, evaluation strategies and webserver/software usability. Thus, our objective is to reexamine these computational approaches and conduct a comprehensive assessment of their strengths and weaknesses across multiple aspects. In this study, we deliver the first comprehensive survey regarding the state-of-the-art computational approaches for in silico prediction of druggable proteins. First, we provided information regarding the existing benchmark datasets and the types of ML methods employed. Second, we investigated the effectiveness of these computational methods in druggable protein identification for each benchmark dataset. Third, we summarized the important features used in this field and the existing webserver/software. Finally, we addressed the present constraints of the existing methods and offer valuable guidance to the scientific community in designing and developing novel prediction models. We anticipate that this comprehensive review will provide crucial information for the development of more accurate and efficient druggable protein predictors.

TROLLOPE: A novel sequence-based stacked approach for the accelerated discovery of linear T-cell epitopes of hepatitis C virus

Hepatitis C virus (HCV) infection is a concerning health issue that causes chronic liver diseases. Despite many successful therapeutic outcomes, no effective HCV vaccines are currently available. Focusing on T cell activity, the primary effector for HCV clearance, T cell epitopes of HCV (TCE-HCV) are considered promising elements to accelerate HCV vaccine efficacy. Thus, accurate and rapid identification of TCE-HCVs is recommended to obtain more efficient therapy for chronic HCV infection. In this study, a novel sequence-based stacked approach, termed TROLLOPE, is proposed to accurately identify TCE-HCVs from sequence information. Specifically, we employed 12 different sequence-based feature descriptors from heterogeneous perspectives, such as physicochemical properties, composition-transition-distribution information and composition information. These descriptors were used in cooperation with 12 popular machine learning (ML) algorithms to create 144 base-classifiers. To maximize the utility of these base-classifiers, we used a feature selection strategy to determine a collection of potential base-classifiers and integrated them to develop the meta-classifier. Comprehensive experiments based on both cross-validation and independent tests demonstrated the superior predictive performance of TROLLOPE compared with conventional ML classifiers, with cross-validation and independent test accuracies of 0.745 and 0.747, respectively. Finally, a user-friendly online web server of TROLLOPE (http://pmlabqsar.pythonanywhere.com/TROLLOPE) has been developed to serve research efforts in the large-scale identification of potential TCE-HCVs for follow-up experimental verification.

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

BACKGROUND

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

RESULTS

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

CONCLUSIONS

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

StackDPP: Stacking-Based Explainable Classifier for Depression Prediction and Finding the Risk Factors among Clinicians

Mental health is a major concern for all classes of people, but especially physicians in the present world. A challenging task is to identify the significant risk factors that are responsible for depression among physicians. To address this issue, the study aimed to build a machine learning-based predictive model that will be capable of predicting depression levels and finding associated risk factors. A raw dataset was collected to conduct this study and preprocessed as necessary. Then, the dataset was divided into 10 sub-datasets to determine the best possible set of attributes to predict depression. Seven different classification algorithms, KNN, DT, LGBM, GB, RF, ETC, and StackDPP, were applied to all the sub-datasets. StackDPP is a stacking-based ensemble classifier, which is proposed in this study. It was found that StackDPP outperformed on all the datasets. The findings indicate that the StackDPP with the sub-dataset with all the attributes gained the highest accuracy (0.962581), and the top 20 attributes were enough to gain 0.96129 accuracy by StackDPP, which was close to the performance of the dataset with all the attributes. In addition, risk factors were analyzed in this study to reveal the most significant risk factors that are responsible for depression among physicians. The findings of the study indicate that the proposed model is highly capable of predicting the level of depression, along with finding the most significant risk factors. The study will enable mental health professionals and psychiatrists to decide on treatment and therapy for physicians by analyzing the depression level and finding the most significant risk factors.

PSRTTCA: A new approach for improving the prediction and characterization of tumor T cell antigens using propensity score representation learning

Despite the arsenal of existing cancer therapies, the ongoing recurrence and new cases of cancer pose a serious health concern that necessitates the development of new and effective treatments. Cancer immunotherapy, which uses the body's immune system to combat cancer, is a promising treatment option. As a result, in silico methods for identifying and characterizing tumor T cell antigens (TTCAs) would be useful for better understanding their functional mechanisms. Although few computational methods for TTCA identification have been developed, their lack of model interpretability is a major drawback. Thus, developing computational methods for the effective identification and characterization of TTCAs is a critical endeavor. PSRTTCA, a new machine learning (ML)-based approach for improving the identification and characterization of TTCAs based on their primary sequences, is proposed in this study. Specifically, we introduce a new propensity score representation learning algorithm that allows one to generate various sets of propensity scores of amino acids, dipeptides, and g-gap dipeptides to be TTCAs. To enhance the predictive performance, optimal sets of variant propensity scores were determined and fed into the final meta-predictor (PSRTTCA). Benchmarking results revealed that PSRTTCA was a more precise and promising tool for the identification and characterization of TTCAs than conventional ML classifiers and existing methods. Furthermore, PSR-derived propensities of amino acids in becoming TTCAs are used to reveal the relationship between TTCAs and their informative physicochemical properties in order to provide insights into TTCA characteristics. Finally, a user-friendly online computational platform of PSRTTCA is publicly available at http://pmlabstack.pythonanywhere.com/PSRTTCA. The PSRTTCA predictor is anticipated to facilitate community-wide efforts in accelerating the discovery of novel TTCAs for cancer immunotherapy and other clinical applications.

StackPR is a new computational approach for large-scale identification of progesterone receptor antagonists using the stacking strategy

Progesterone receptors (PRs) are implicated in various cancers since their presence/absence can determine clinical outcomes. The overstimulation of progesterone can facilitate oncogenesis and thus, its modulation through PR inhibition is urgently needed. To address this issue, a novel stacked ensemble learning approach (termed StackPR) is presented for fast, accurate, and large-scale identification of PR antagonists using only SMILES notation without the need for 3D structural information. We employed six popular machine learning (ML) algorithms (i.e., logistic regression, partial least squares, k-nearest neighbor, support vector machine, extremely randomized trees, and random forest) coupled with twelve conventional molecular descriptors to create 72 baseline models. Then, a genetic algorithm in conjunction with the self-assessment-report approach was utilized to determine m out of the 72 baseline models as means of developing the final meta-predictor using the stacking strategy and tenfold cross-validation test. Experimental results on the independent test dataset show that StackPR achieved impressive predictive performance with an accuracy of 0.966 and Matthew's coefficient correlation of 0.925. In addition, analysis based on the SHapley Additive exPlanation algorithm and molecular docking indicates that aliphatic hydrocarbons and nitrogen-containing substructures were the most important features for having PR antagonist activity. Finally, we implemented an online webserver using StackPR, which is freely accessible at http://pmlabstack.pythonanywhere.com/StackPR . StackPR is anticipated to be a powerful computational tool for the large-scale identification of unknown PR antagonist candidates for follow-up experimental validation.

DLm6Am: A Deep-Learning-Based Tool for Identifying N6,2′-O-Dimethyladenosine Sites in RNA Sequences

N6,2′-O-dimethyladenosine (m⁶Am) is a post-transcriptional modification that may be associated with regulatory roles in the control of cellular functions. Therefore, it is crucial to accurately identify transcriptome-wide m⁶Am sites to understand underlying m⁶Am-dependent mRNA regulation mechanisms and biological functions. Here, we used three sequence-based feature-encoding schemes, including one-hot, nucleotide chemical property (NCP), and nucleotide density (ND), to represent RNA sequence samples. Additionally, we proposed an ensemble deep learning framework, named DLm6Am, to identify m⁶Am sites. DLm6Am consists of three similar base classifiers, each of which contains a multi-head attention module, an embedding module with two parallel deep learning sub-modules, a convolutional neural network (CNN) and a Bi-directional long short-term memory (BiLSTM), and a prediction module. To demonstrate the superior performance of our model’s architecture, we compared multiple model frameworks with our method by analyzing the training data and independent testing data. Additionally, we compared our model with the existing state-of-the-art computational methods, m6AmPred and MultiRM. The accuracy (ACC) for the DLm6Am model was improved by 6.45% and 8.42% compared to that of m6AmPred and MultiRM on independent testing data, respectively, while the area under receiver operating characteristic curve (AUROC) for the DLm6Am model was increased by 4.28% and 5.75%, respectively. All the results indicate that DLm6Am achieved the best prediction performance in terms of ACC, Matthews correlation coefficient (MCC), AUROC, and the area under precision and recall curves (AUPR). To further assess the generalization performance of our proposed model, we implemented chromosome-level leave-out cross-validation, and found that the obtained AUROC values were greater than 0.83, indicating that our proposed method is robust and can accurately predict m⁶Am sites.

Computational prediction and interpretation of druggable proteins using a stacked ensemble-learning framework

Discovery of potential drugs requires rapid and precise identification of drug targets. Although traditional experimental methodologies can accurately identify drug targets, they are time-consuming and inappropriate for high-throughput screening. Computational approaches based on machine learning (ML) algorithms can expedite the prediction of druggable proteins; however, the performance of the existing computational methods remains unsatisfactory. This study proposes a computational tool, SPIDER, to enhance the accurate prediction of druggable proteins. SPIDER employs various feature descriptors pertaining to several aspects, including physicochemical properties, compositional information, and composition-transition-distribution information, coupled with well-known ML algorithms to facilitate the construction of the final meta-predictor. The experimental results showed that SPIDER enabled more precise and robust prediction of druggable proteins than the baseline models and current existing methods in terms of the independent test dataset. An online web server was established and made freely available online.

SCMRSA: a New Approach for Identifying and Analyzing Anti-MRSA Peptides Using Estimated Propensity Scores of Dipeptides

Staphylococcus aureus is deemed to be one of the major causes of hospital and community-acquired infections, especially in methicillin-resistant S. aureus (MRSA) strains. Because antimicrobial peptides have captured attention as novel drug candidates due to their rapid and broad-spectrum antimicrobial activity, anti-MRSA peptides have emerged as potential therapeutics for the treatment of bacterial infections. Although experimental approaches can precisely identify anti-MRSA peptides, they are usually cost-ineffective and labor-intensive. Therefore, computational approaches that are able to identify and characterize anti-MRSA peptides by using sequence information are highly desirable. In this study, we present the first computational approach (termed SCMRSA) for identifying and characterizing anti-MRSA peptides by using sequence information without the use of 3D structural information. In SCMRSA, we employed an interpretable scoring card method (SCM) coupled with the estimated propensity scores of 400 dipeptides. Comparative experiments indicated that SCMRSA was more effective and could outperform several machine learning-based classifiers with an accuracy of 0.960 and Matthews correlation coefficient of 0.848 on the independent test data set. In addition, we employed the SCMRSA-derived propensity scores to provide a more in-depth explanation regarding the functional mechanisms of anti-MRSA peptides. Finally, in order to serve community-wide use of the proposed SCMRSA, we established a user-friendly webserver which can be accessed online at http://pmlabstack.pythonanywhere.com/SCMRSA. SCMRSA is anticipated to be an open-source and useful tool for screening and identifying novel anti-MRSA peptides for follow-up experimental studies.

SPREAD: An ensemble predictor based on DNA autoencoder framework for discriminating promoters in Pseudomonas aeruginosa

Regulatory elements in DNA sequences, such as promoters, enhancers, terminators and so on, are essential for gene expression in physiological and pathological processes. A promoter is the specific DNA sequence that is located upstream of the coding gene and acts as the "switch" for gene transcriptional regulation. Lots of promoter predictors have been developed for different bacterial species, but only a few are designed for Pseudomonas aeruginosa, a widespread Gram-negative conditional pathogen in nature. In this work, an ensemble model named SPREAD is proposed for the recognition of promoters in Pseudomonas aeruginosa. In SPREAD, the DNA sequence autoencoder model LSTM is employed to extract potential sequence information, and the mean output probability value of CNN and RF is applied as the final prediction. Compared with G4PromFinder, the only state-of-the-art classifier for promoters in Pseudomonas aeruginosa, SPREAD improves the prediction performance significantly, with an accuracy of 0.98, recall of 0.98, precision of 0.98, specificity of 0.97 and F1-score of 0.98.

Functional Annotation of Hypothetical Proteins From the Enterobacter cloacae B13 Strain and Its Association With Pathogenicity

Enterobacter cloacae B13 strain is a rod-shaped gram-negative bacterium that belongs to the Enterobacteriaceae family. It can cause respiratory and urinary tract infections, and is responsible for several outbreaks in hospitals. E. cloacae has become an important pathogen and an emerging global threat because of its opportunistic and multidrug resistant ability. However, little knowledge is present about a large portion of its proteins and functions. Therefore, functional annotation of the hypothetical proteins (HPs) can provide an improved understanding of this organism and its virulence activity. The workflow in the study included several bioinformatic tools which were utilized to characterize functions, family and domains, subcellular localization, physiochemical properties, and protein-protein interactions. The E. cloacae B13 strain has overall 604 HPs, among which 78 were functionally annotated with high confidence. Several proteins were identified as enzymes, regulatory, binding, and transmembrane proteins with essential functions. Furthermore, 23 HPs were predicted to be virulent factors. These virulent proteins are linked to pathogenesis with their contribution to biofilm formation, quorum sensing, 2-component signal transduction or secretion. Better knowledge about the HPs’ characteristics and functions will provide a greater overview of the proteome. Moreover, it will help against E. cloacae in neonatal intensive care unit (NICU) outbreaks and nosocomial infections.

SAPPHIRE: A stacking-based ensemble learning framework for accurate prediction of thermophilic proteins

Thermophilic proteins (TPPs) are important in the field of protein biochemistry and development of new enzymes. Thus, computational methods must be urgently developed to accurately and rapidly identify TPPs. To date, several computational methods have been developed for TPP identification; however, few limitations in terms of performance and utility remain. In this study, we present a novel computational method, SAPPHIRE, to achieve more accurate identification of TPPs using only sequence information without any need for structural information. We combined twelve different feature encodings representing different perspectives and six popular machine learning algorithms to train 72 baseline models and extract the key information of TPPs. Subsequently, the informative predicted probabilities from the baseline models were mined and selected using a genetic algorithm in conjunction with a self-assessment-report approach. Finally, the final meta-predictor, SAPPHIRE, was built and optimized by applying an optimal feature set. The performance of SAPPHIRE in the 10-fold cross-validation test showed that a superior predictive performance compared with several baseline models could be achieved. Moreover, SAPPHIRE yielded an accuracy of 0.942 and Matthew's coefficient correlation of 0.884, which were 7.68 and 5.12% higher than those of the current existing methods, respectively, as indicated by the independent test. The proposed computational approach is anticipated to facilitate large-scale identification of TPPs and accelerate their applications in the food industry. The codes and datasets are available at https://github.com/plenoi/SAPPHIRE.

TACOS: a novel approach for accurate prediction of cell-specific long noncoding RNAs subcellular localization

Long noncoding RNAs (lncRNAs) are primarily regulated by their cellular localization, which is responsible for their molecular functions, including cell cycle regulation and genome rearrangements. Accurately identifying the subcellular location of lncRNAs from sequence information is crucial for a better understanding of their biological functions and mechanisms. In contrast to traditional experimental methods, bioinformatics or computational methods can be applied for the annotation of lncRNA subcellular locations in humans more effectively. In the past, several machine learning-based methods have been developed to identify lncRNA subcellular localization, but relevant work for identifying cell-specific localization of human lncRNA remains limited. In this study, we present the first application of the tree-based stacking approach, TACOS, which allows users to identify the subcellular localization of human lncRNA in 10 different cell types. Specifically, we conducted comprehensive evaluations of six tree-based classifiers with 10 different feature descriptors, using a newly constructed balanced training dataset for each cell type. Subsequently, the strengths of the AdaBoost baseline models were integrated via a stacking approach, with an appropriate tree-based classifier for the final prediction. TACOS displayed consistent performance in both the cross-validation and independent assessments compared with the other two approaches employed in this study. The user-friendly online TACOS web server can be accessed at https://balalab-skku.org/TACOS.

NEPTUNE: A novel computational approach for accurate and large-scale identification of tumor homing peptides

Tumor homing peptides (THPs) play a crucial role in recognizing and specifically binding to cancer cells. Although experimental approaches can facilitate the precise identification of THPs, they are usually time-consuming, labor-intensive, and not cost-effective. However, computational approaches can identify THPs by utilizing sequence information alone, thus highlighting their great potential for large-scale identification of THPs. Herein, we propose NEPTUNE, a novel computational approach for the accurate and large-scale identification of THPs from sequence information. Specifically, we constructed variant baseline models from multiple feature encoding schemes coupled with six popular machine learning algorithms. Subsequently, we comprehensively assessed and investigated the effects of these baseline models on THP prediction. Finally, the probabilistic information generated by the optimal baseline models is fed into a support vector machine-based classifier to construct the final meta-predictor (NEPTUNE). Cross-validation and independent tests demonstrated that NEPTUNE achieved superior performance for THP prediction compared with its constituent baseline models and the existing methods. Moreover, we employed the powerful SHapley additive exPlanations method to improve the interpretation of NEPTUNE and elucidate the most important features for identifying THPs. Finally, we implemented an online web server using NEPTUNE, which is available at http://pmlabstack.pythonanywhere.com/NEPTUNE. NEPTUNE could be beneficial for the large-scale identification of unknown THP candidates for follow-up experimental validation.

Empirical comparison and analysis of machine learning-based predictors for predicting and analyzing of thermophilic proteins

Thermophilic proteins (TPPs) are critical for basic research and in the food industry due to their ability to maintain a thermodynamically stable fold at extremely high temperatures. Thus, the expeditious identification of novel TPPs through computational models from protein sequences is very desirable. Over the last few decades, a number of computational methods, especially machine learning (ML)-based methods, for in silico prediction of TPPs have been developed. Therefore, it is desirable to revisit these methods and summarize their advantages and disadvantages in order to further develop new computational approaches to achieve more accurate and improved prediction of TPPs. With this goal in mind, we comprehensively investigate a large collection of fourteen state-of-the-art TPP predictors in terms of their dataset size, feature encoding schemes, feature selection strategies, ML algorithms, evaluation strategies and web server/software usability. To the best of our knowledge, this article represents the first comprehensive review on the development of ML-based methods for in silico prediction of TPPs. Among these TPP predictors, they can be classified into two groups according to the interpretability of ML algorithms employed (i.e., computational black-box methods and computational white-box methods). In order to perform the comparative analysis, we conducted a comparative study on several currently available TPP predictors based on two benchmark datasets. Finally, we provide future perspectives for the design and development of new computational models for TPP prediction. We hope that this comprehensive review will facilitate researchers in selecting an appropriate TPP predictor that is the most suitable one to deal with their purposes and provide useful perspectives for the development of more effective and accurate TPP predictors.

Deepm5C: A deep learning-based hybrid framework for identifying human RNA N5-methylcytosine sites using a stacking strategy

As one of the most prevalent post-transcriptional epigenetic modifications, N5-methylcytosine (m5C), plays an essential role in various cellular processes and disease pathogenesis. Therefore, it is important accurately identify m5C modifications in order to gain a deeper understanding of cellular processes and other possible functional mechanisms. Although a few computational methods have been proposed, their respective models have been developed using small training datasets. Hence, their practical application is quite limited in genome-wide detection. To overcome the existing limitations, we propose Deepm5C, a bioinformatics method to identify RNA m5C sites in the throughout human genome. To develop Deepm5C, we constructed a novel benchmarking dataset and investigated a mixture of three conventional feature encoding algorithms and a feature derived from word embedding approaches. Afterwards, four variants of deep learning classifiers and four commonly used conventional classifiers were employed and trained with the four encodings, ultimately obtaining 32 baseline models. A stacking strategy is effectively utilized by integrating the predicted output of the optimal baseline models and trained with a 1-D convolutional neural network. As a result, the Deepm5C predictor achieved excellent performance during cross-validation with a Matthews correlation coefficient and accuracy of 0.697 and 0.855, respectively. The corresponding metrics during the independent test were 0.691 and 0.852, respectively. Overall, Deepm5C achieved a more accurate and stable performance than the baseline models and significantly outperformed the existing predictors, demonstrating the effectiveness of our proposed hybrid framework. Furthermore, Deepm5C is expected to assist community-wide efforts in identifying putative m5Cs and formulate the novel testable biological hypothesis.

SCORPION is a stacking-based ensemble learning framework for accurate prediction of phage virion proteins

Fast and accurate identification of phage virion proteins (PVPs) would greatly aid facilitation of antibacterial drug discovery and development. Although, several research efforts based on machine learning (ML) methods have been made for in silico identification of PVPs, these methods have certain limitations. Therefore, in this study, we propose a new computational approach, termed SCORPION, (StaCking-based Predictior fOR Phage VIrion PrOteiNs), to accurately identify PVPs using only protein primary sequences. Specifically, we explored comprehensive 13 different feature descriptors from different aspects (i.e., compositional information, composition-transition-distribution information, position-specific information and physicochemical properties) with 10 popular ML algorithms to construct a pool of optimal baseline models. These optimal baseline models were then used to generate probabilistic features (PFs) and considered as a new feature vector. Finally, we utilized a two-step feature selection strategy to determine the optimal PF feature vector and used this feature vector to develop a stacked model (SCORPION). Both tenfold cross-validation and independent test results indicate that SCORPION achieves superior predictive performance than its constitute baseline models and existing methods. We anticipate SCORPION will serve as a useful tool for the cost-effective and large-scale screening of new PVPs. The source codes and datasets for this work are available for downloading in the GitHub repository (https://github.com/saeed344/SCORPION).

Comparative analysis of machine learning-based approaches for identifying therapeutic peptides targeting SARS-CoV-2

Coronavirus disease 2019 (COVID-19) has impacted public health as well as societal and economic well-being. In the last two decades, various prediction algorithms and tools have been developed for predicting antiviral peptides (AVPs). The current COVID-19 pandemic has underscored the need to develop more efficient and accurate machine learning (ML)-based prediction algorithms for the rapid identification of therapeutic peptides against severe acute respiratory syndrome coronavirus-2 (SARS-CoV-2). Several peptide-based ML approaches, including anti-coronavirus peptides (ACVPs), IL-6 inducing epitopes and other epitopes targeting SARS-CoV-2, have been implemented in COVID-19 therapeutics. Owing to the growing interest in the COVID-19 field, it is crucial to systematically compare the existing ML algorithms based on their performances. Accordingly, we comprehensively evaluated the state-of-the-art IL-6 and AVP predictors against coronaviruses in terms of core algorithms, feature encoding schemes, performance evaluation metrics and software usability. A comprehensive performance assessment was then conducted to evaluate the robustness and scalability of the existing predictors using well-constructed independent validation datasets. Additionally, we discussed the advantages and disadvantages of the existing methods, providing useful insights into the development of novel computational tools for characterizing and identifying epitopes or ACVPs. The insights gained from this review are anticipated to provide critical guidance to the scientific community in the rapid design and development of accurate and efficient next-generation in silico tools against SARS-CoV-2.

StackDPPIV: A novel computational approach for accurate prediction of dipeptidyl peptidase IV (DPP-IV) inhibitory peptides

The development of efficient and effective bioinformatics tools and pipelines for identifying peptides with dipeptidyl peptidase IV (DPP-IV) inhibitory activities from large-scale protein datasets is of great importance for the discovery and development of potential and promising antidiabetic drugs. In this study, we present a novel stacking-based ensemble learning predictor (termed StackDPPIV) designed for identification of DPP-IV inhibitory peptides. Unlike the existing method, which is based on single-feature-based methods, we combined five popular machine learning algorithms in conjunction with ten different feature encodings from multiple perspectives to generate a pool of various baseline models. Subsequently, the probabilistic features derived from these baseline models were systematically integrated and deemed as new feature representations. Finally, in order to improve the predictive performance, the genetic algorithm based on the self-assessment-report was utilized to determine a set of informative probabilistic features and then used the optimal one for developing the final meta-predictor (StackDPPIV). Experiment results demonstrated that StackDPPIV could outperform its constituent baseline models on both the training and independent datasets. Furthermore, StackDPPIV achieved an accuracy of 0.891, MCC of 0.784 and AUC of 0.961, which were 9.4%, 19.0% and 11.4%, respectively, higher than that of the existing method on the independent test. Feature analysis demonstrated that our feature representations had more discriminative ability as compared to conventional feature descriptors, which highlights the combination of different features was essential for the performance improvement. In order to implement the proposed predictor, we had built a user-friendly online web server at http://pmlabstack.pythonanywhere.com/StackDPPIV.

UMPred-FRL: A New Approach for Accurate Prediction of Umami Peptides Using Feature Representation Learning

Umami ingredients have been identified as important factors in food seasoning and production. Traditional experimental methods for characterizing peptides exhibiting umami sensory properties (umami peptides) are time-consuming, laborious, and costly. As a result, it is preferable to develop computational tools for the large-scale identification of available sequences in order to identify novel peptides with umami sensory properties. Although a computational tool has been developed for this purpose, its predictive performance is still insufficient. In this study, we use a feature representation learning approach to create a novel machine-learning meta-predictor called UMPred-FRL for improved umami peptide identification. We combined six well-known machine learning algorithms (extremely randomized trees, k-nearest neighbor, logistic regression, partial least squares, random forest, and support vector machine) with seven different feature encodings (amino acid composition, amphiphilic pseudo-amino acid composition, dipeptide composition, composition-transition-distribution, and pseudo-amino acid composition) to develop the final meta-predictor. Extensive experimental results demonstrated that UMPred-FRL was effective and achieved more accurate performance on the benchmark dataset compared to its baseline models, and consistently outperformed the existing method on the independent test dataset. Finally, to aid in the high-throughput identification of umami peptides, the UMPred-FRL web server was established and made freely available online. It is expected that UMPred-FRL will be a powerful tool for the cost-effective large-scale screening of candidate peptides with potential umami sensory properties.

STALLION: a stacking-based ensemble learning framework for prokaryotic lysine acetylation site prediction

Protein post-translational modification (PTM) is an important regulatory mechanism that plays a key role in both normal and disease states. Acetylation on lysine residues is one of the most potent PTMs owing to its critical role in cellular metabolism and regulatory processes. Identifying protein lysine acetylation (Kace) sites is a challenging task in bioinformatics. To date, several machine learning-based methods for the in silico identification of Kace sites have been developed. Of those, a few are prokaryotic species-specific. Despite their attractive advantages and performances, these methods have certain limitations. Therefore, this study proposes a novel predictor STALLION (STacking-based Predictor for ProkAryotic Lysine AcetyLatION), containing six prokaryotic species-specific models to identify Kace sites accurately. To extract crucial patterns around Kace sites, we employed 11 different encodings representing three different characteristics. Subsequently, a systematic and rigorous feature selection approach was employed to identify the optimal feature set independently for five tree-based ensemble algorithms and built their respective baseline model for each species. Finally, the predicted values from baseline models were utilized and trained with an appropriate classifier using the stacking strategy to develop STALLION. Comparative benchmarking experiments showed that STALLION significantly outperformed existing predictor on independent tests. To expedite direct accessibility to the STALLION models, a user-friendly online predictor was implemented, which is available at: http://thegleelab.org/STALLION.

StackIL6: a stacking ensemble model for improving the prediction of IL-6 inducing peptides

The release of interleukin (IL)-6 is stimulated by antigenic peptides from pathogens as well as by immune cells for activating aggressive inflammation. IL-6 inducing peptides are derived from pathogens and can be used as diagnostic biomarkers for predicting various stages of disease severity as well as being used as IL-6 inhibitors for the suppression of aggressive multi-signaling immune responses. Thus, the accurate identification of IL-6 inducing peptides is of great importance for investigating their mechanism of action as well as for developing diagnostic and immunotherapeutic applications. This study proposes a novel stacking ensemble model (termed StackIL6) for accurately identifying IL-6 inducing peptides. More specifically, StackIL6 was constructed from twelve different feature descriptors derived from three major groups of features (composition-based features, composition-transition-distribution-based features and physicochemical properties-based features) and five popular machine learning algorithms (extremely randomized trees, logistic regression, multi-layer perceptron, support vector machine and random forest). To enhance the utility of baseline models, they were effectively and systematically integrated through a stacking strategy to build the final meta-based model. Extensive benchmarking experiments demonstrated that StackIL6 could achieve significantly better performance than the existing method (IL6PRED) and outperformed its constituent baseline models on both training and independent test datasets, which thereby support its excellent discrimination and generalization abilities. To facilitate easy access to the StackIL6 model, it was established as a freely available web server accessible at http://camt.pythonanywhere.com/StackIL6. It is anticipated that StackIL6 can help to facilitate rapid screening of promising IL-6 inducing peptides for the development of diagnostic and immunotherapeutic applications in the future.

BERT4Bitter: a bidirectional encoder representations from transformers (BERT)-based model for improving the prediction of bitter peptides

MOTIVATION

The identification of bitter peptides through experimental approaches is an expensive and time-consuming endeavor. Due to the huge number of newly available peptide sequences in the post-genomic era, the development of automated computational models for the identification of novel bitter peptides is highly desira-ble.

RESULTS

In this work, we present BERT4Bitter, a bidirectional encoder representation from transformers (BERT)-based model for predicting bitter peptides directly from their amino acid sequence without using any structural information. To the best of our knowledge, this is the first time a BERT-based model has been employed to identify bitter peptides. Compared to widely used machine learning models, BERT4Bitter achieved the best performance with accuracy of 0.861 and 0.922 for cross-validation and independent tests, respectively. Furthermore, extensive empirical benchmarking experiments on the independent dataset demonstrated that BERT4Bitter clearly outperformed the existing method with improvements of > 8% accuracy and >16% Matthews coefficient correlation, highlighting the effectiveness and robustness of BERT4Bitter. We believe that the BERT4Bitter method proposed herein will be a useful tool for rapidly screening and identifying novel bitter peptides for drug development and nutritional research.

AVAILABILITY

The user-friendly web server of the proposed BERT4Bitter is freely accessible at: http://pmlab.pythonanywhere.com/BERT4Bitter.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Computational prediction of species-specific yeast DNA replication origin via iterative feature representation

Deoxyribonucleic acid replication is one of the most crucial tasks taking place in the cell, and it has to be precisely regulated. This process is initiated in the replication origins (ORIs), and thus it is essential to identify such sites for a deeper understanding of the cellular processes and functions related to the regulation of gene expression. Considering the important tasks performed by ORIs, several experimental and computational approaches have been developed in the prediction of such sites. However, existing computational predictors for ORIs have certain curbs, such as building only single-feature encoding models, limited systematic feature engineering efforts and failure to validate model robustness. Hence, we developed a novel species-specific yeast predictor called yORIpred that accurately identify ORIs in the yeast genomes. To develop yORIpred, we first constructed optimal 40 baseline models by exploring eight different sequence-based encodings and five different machine learning classifiers. Subsequently, the predicted probability of 40 models was considered as the novel feature vector and carried out iterative feature learning approach independently using five different classifiers. Our systematic analysis revealed that the feature representation learned by the support vector machine algorithm (yORIpred) could well discriminate the distribution characteristics between ORIs and non-ORIs when compared with the other four algorithms. Comprehensive benchmarking experiments showed that yORIpred achieved superior and stable performance when compared with the existing predictors on the same training datasets. Furthermore, independent evaluation showcased the best and accurate performance of yORIpred thus underscoring the significance of iterative feature representation. To facilitate the users in obtaining their desired results without undergoing any mathematical, statistical or computational hassles, we developed a web server for the yORIpred predictor, which is available at: http://thegleelab.org/yORIpred.

Computational prediction and interpretation of cell-specific replication origin sites from multiple eukaryotes by exploiting stacking framework

Origins of replication sites (ORIs), which refers to the initiative locations of genomic DNA replication, play essential roles in DNA replication process. Detection of ORIs' distribution in genome scale is one of key steps to in-depth understanding their regulation mechanisms. In this study, we presented a novel machine learning-based approach called Stack-ORI encompassing 10 cell-specific prediction models for identifying ORIs from four different eukaryotic species (Homo sapiens, Mus musculus, Drosophila melanogaster and Arabidopsis thaliana). For each cell-specific model, we employed 12 feature encoding schemes that cover nucleic acid composition, position-specific and physicochemical properties information. The optimal feature set was identified from each encoding individually and developed their respective baseline models using the eXtreme Gradient Boosting (XGBoost) classifier. Subsequently, the predicted scores of 12 baseline models are integrated as a novel feature vector to train XGBoost and develop the final model. Extensive experimental results show that Stack-ORI achieves significantly better performance as compared with their baseline models on both training and independent datasets. Interestingly, Stack-ORI consistently outperforms existing predictor in all cell-specific models, not only on training but also on independent test. Moreover, our novel approach provides necessary interpretations that help understanding model success by leveraging the powerful SHapley Additive exPlanation algorithm, thus underlining the most important feature encoding schemes significant for predicting cell-specific ORIs.