Methicillin-resistant S. aureus (MRSA) has prominently emerged among the recognized causes of community-acquired and hospital infections. We proposed a novel computational approach, iMRSA-Fuse, based on a multi-view feature fusion strategy for fast and accurate anti-MRSA peptide identification. In iMRSA-Fuse, we explored and integrated 12 different sequence-based feature descriptors from multiple perspectives, in conjunction with 12 popular machine learning (ML) algorithms, to construct multi-view features that were able to fully capture the useful information of anti-MRSA peptides. Additionally, we applied our customized genetic algorithm to determine a set of multi-view features to enhance its discriminative ability. Based on a series of comparative results, our multi-view features exhibited the most discriminative ability compared to several conventional feature descriptors. Moreover, concerning the independent test dataset, iMRSA-Fuse achieved the best balanced accuracy (BACC) and Matthew's correlation coefficient (MCC) of 0.997 and 0.981, respectively with an increase of 3.93 and 7.78%, respectively. Finally, to facilitate the large-scale identification of candidate anti-MRSA peptides, a user-friendly web server of the iMRSA-Fuse model is constructed and is freely accessible at https://pmlabqsar.pythonanywhere.com/iMRSA-Fuse. We anticipate that this new computational approach will be effectively applied to screen and prioritize candidate peptides that might exhibit the great anti-MRSA activities.

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 .

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.

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.

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 desirable. 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 an 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 8.0% accuracy and 16.0% 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. AVAILABILITYAND IMPLEMENTATION: 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.

BACKGROUND: Few studies have investigated prognostic biomarkers of distant metastases of lung cancer. One of the central difficulties in identifying biomarkers from microarray data is the availability of only a small number of samples, which results overtraining. Recently obtained evidence reveals that epithelial-mesenchymal transition (EMT) of tumor cells causes metastasis, which is detrimental to patients' survival. RESULTS: This work proposes a novel optimization approach to discovering EMT-related prognostic biomarkers to predict the distant metastasis of lung cancer using both microarray and survival data. This weighted objective function maximizes both the accuracy of prediction of distant metastasis and the area between the disease-free survival curves of the non-distant and distant metastases. Seventy-eight patients with lung cancer and a follow-up time of 120 months are used to identify a set of gene markers and an independent cohort of 26 patients is used to evaluate the identified biomarkers. The medical records of the 78 patients show a significant difference between the disease-free survival times of the 37 non-distant- and the 41 distant-metastasis patients. The experimental results thus obtained are as follows. 1) The use of disease-free survival curves can compensate for the shortcoming of insufficient samples and greatly increase the test accuracy by 11.10%; and 2) the support vector machine with a set of 17 transcripts, such as CCL16 and CDKN2AIP, can yield a leave-one-out cross-validation accuracy of 93.59%, a test accuracy of 76.92%, a large disease-free survival area of 74.81%, and a mean survival prediction error of 3.99 months. The identified putative biomarkers are examined using related studies and signaling pathways to reveal the potential effectiveness of the biomarkers in prospective confirmatory studies. CONCLUSIONS: The proposed new optimization approach to identifying prognostic biomarkers by combining multiple sources of data (microarray and survival) can facilitate the accurate selection of biomarkers that are most relevant to the disease while solving the problem of insufficient samples.

BACKGROUND: Protein-protein interactions (PPIs) are involved in various biological processes, and underlying mechanism of the interactions plays a crucial role in therapeutics and protein engineering. Most machine learning approaches have been developed for predicting the binding affinity of protein-protein complexes based on structure and functional information. This work aims to predict the binding affinity of heterodimeric protein complexes from sequences only. RESULTS: This work proposes a support vector machine (SVM) based binding affinity classifier, called SVM-BAC, to classify heterodimeric protein complexes based on the prediction of their binding affinity. SVM-BAC identified 14 of 580 sequence descriptors (physicochemical, energetic and conformational properties of the 20 amino acids) to classify 216 heterodimeric protein complexes into low and high binding affinity. SVM-BAC yielded the training accuracy, sensitivity, specificity, AUC and test accuracy of 85.80%, 0.89, 0.83, 0.86 and 83.33%, respectively, better than existing machine learning algorithms. The 14 features and support vector regression were further used to estimate the binding affinities (Pkd) of 200 heterodimeric protein complexes. Prediction performance of a Jackknife test was the correlation coefficient of 0.34 and mean absolute error of 1.4. We further analyze three informative physicochemical properties according to their contribution to prediction performance. Results reveal that the following properties are effective in predicting the binding affinity of heterodimeric protein complexes: apparent partition energy based on buried molar fractions, relations between chemical structure and biological activity in principal component analysis IV, and normalized frequency of beta turn. CONCLUSIONS: The proposed sequence-based prediction method SVM-BAC uses an optimal feature selection method to identify 14 informative features to classify and predict binding affinity of heterodimeric protein complexes. The characterization analysis revealed that the average numbers of beta turns and hydrogen bonds at protein-protein interfaces in high binding affinity complexes are more than those in low binding affinity complexes.

BACKGROUND: Photosynthetic proteins (PSPs) greatly differ in their structure and function as they are involved in numerous subprocesses that take place inside an organelle called a chloroplast. Few studies predict PSPs from sequences due to their high variety of sequences and structues. This work aims to predict and characterize PSPs by establishing the datasets of PSP and non-PSP sequences and developing prediction methods. RESULTS: A novel bioinformatics method of predicting and characterizing PSPs based on scoring card method (SCMPSP) was used. First, a dataset consisting of 649 PSPs was established by using a Gene Ontology term GO:0015979 and 649 non-PSPs from the SwissProt database with sequence identity <= 25%.- Several prediction methods are presented based on support vector machine (SVM), decision tree J48, Bayes, BLAST, and SCM. The SVM method using dipeptide features-performed well and yielded - a test accuracy of 72.31%. The SCMPSP method uses the estimated propensity scores of 400 dipeptides - as PSPs and has a test accuracy of 71.54%, which is comparable to that of the SVM method. The derived propensity scores of 20 amino acids were further used to identify informative physicochemical properties for characterizing PSPs. The analytical results reveal the following four characteristics of PSPs: 1) PSPs favour hydrophobic side chain amino acids; 2) PSPs are composed of the amino acids prone to form helices in membrane environments; 3) PSPs have low interaction with water; and 4) PSPs prefer to be composed of the amino acids of electron-reactive side chains. CONCLUSIONS: The SCMPSP method not only estimates the propensity of a sequence to be PSPs, it also discovers characteristics that further improve understanding of PSPs. The SCMPSP source code and the datasets used in this study are available at http://iclab.life.nctu.edu.tw/SCMPSP/.

BACKGROUND: Heme binding proteins (HBPs) are metalloproteins that contain a heme ligand (an iron-porphyrin complex) as the prosthetic group. Several computational methods have been proposed to predict heme binding residues and thereby to understand the interactions between heme and its host proteins. However, few in silico methods for identifying HBPs have been proposed. RESULTS: This work proposes a scoring card method (SCM) based method (named SCMHBP) for predicting and analyzing HBPs from sequences. A balanced dataset of 747 HBPs (selected using a Gene Ontology term GO:0020037) and 747 non-HBPs (selected from 91,414 putative non-HBPs) with an identity of 25% was firstly established. Consequently, a set of scores that quantified the propensity of amino acids and dipeptides to be HBPs is estimated using SCM to maximize the predictive accuracy of SCMHBP. Finally, the informative physicochemical properties of 20 amino acids are identified by utilizing the estimated propensity scores to be used to categorize HBPs. The training and mean test accuracies of SCMHBP applied to three independent test datasets are 85.90% and 71.57%, respectively. SCMHBP performs well relative to comparison with such methods as support vector machine (SVM), decision tree J48, and Bayes classifiers. The putative non-HBPs with high sequence propensity scores are potential HBPs, which can be further validated by experimental confirmation. The propensity scores of individual amino acids and dipeptides are examined to elucidate the interactions between heme and its host proteins. The following characteristics of HBPs are derived from the propensity scores: 1) aromatic side chains are important to the effectiveness of specific HBP functions; 2) a hydrophobic environment is important in the interaction between heme and binding sites; and 3) the whole HBP has low flexibility whereas the heme binding residues are relatively flexible. CONCLUSIONS: SCMHBP yields knowledge that improves our understanding of HBPs rather than merely improves the prediction accuracy in predicting HBPs.

Finding the molecular features causes the halophilicity in the halostable organisms is helpful to understand the halophilic adaption. In this study, we proposed a prediction method for halophilic proteins by using a machine learning method. The stages of this study are six-fold. First, we establish a non-redundant dataset of the halophilic proteins, collected from NCBI, Uniprotkb and EMBL-EBI databases. The dataset consists of 245 positive and negative proteins with sequence identity <;25%. Second, the protein sequences are represented by three types of feature vector sets which include amino acid composition, dipeptide composition, and physicochemical properties. Third, we propose three classifiers based on support vector machine (SVM) to classify the halophilic proteins and non-halophilic proteins. Fourth, the independent test accuracies of the three efficient classifiers are larger than 83%. Fifth, an inheritable biobjective combinatory genetic algorithm is utilized to select a set of 11 physicochemical properties (PCPs). Sixth, these abundant amino acids, high different dipeptides (amino acid pair) and 11 informative PCPs can support to analyze the halophilic and non-halophilic proteins.

Many computational methods have been developed to predict protein crystallization. Most methods use amino acid and dipeptide compositions as part of the informative features. To advance the prediction accuracy, the support vector machine (SVM) based classifiers and ensemble approaches were effective and commonly-used techniques. However, these techniques suffer from the low interpretation ability of insight into crystallization. In this study, we utilize a newly-developed scoring card method (SCM) with a dipeptide composition feature to predict protein crystallization. This SCM classifier obtains prediction results 74%, 0.55 and 0.83 for accuracy, sensitivity and specificity, respectively, which is comparable to the SVM classifier using the same benchmarks. The experimental results show that the SCM classifier has advantages of simplicity, high interpretability, and high accuracy in predicting protein crystallization, compared with existing SVM-basedensemble classifiers.

BACKGROUND: High-content screening (HCS) has become a powerful tool for drug discovery. However, the discovery of drugs targeting neurons is still hampered by the inability to accurately identify and quantify the phenotypic changes of multiple neurons in a single image (named multi-neuron image) of a high-content screen. Therefore, it is desirable to develop an automated image analysis method for analyzing multi-neuron images. RESULTS: We propose an automated analysis method with novel descriptors of neuromorphology features for analyzing HCS-based multi-neuron images, called HCS-neurons. To observe multiple phenotypic changes of neurons, we propose two kinds of descriptors which are neuron feature descriptor (NFD) of 13 neuromorphology features, e.g., neurite length, and generic feature descriptors (GFDs), e.g., Haralick texture. HCS-neurons can 1) automatically extract all quantitative phenotype features in both NFD and GFDs, 2) identify statistically significant phenotypic changes upon drug treatments using ANOVA and regression analysis, and 3) generate an accurate classifier to group neurons treated by different drug concentrations using support vector machine and an intelligent feature selection method. To evaluate HCS-neurons, we treated P19 neurons with nocodazole (a microtubule depolymerizing drug which has been shown to impair neurite development) at six concentrations ranging from 0 to 1000 ng/mL. The experimental results show that all the 13 features of NFD have statistically significant difference with respect to changes in various levels of nocodazole drug concentrations (NDC) and the phenotypic changes of neurites were consistent to the known effect of nocodazole in promoting neurite retraction. Three identified features, total neurite length, average neurite length, and average neurite area were able to achieve an independent test accuracy of 90.28% for the six-dosage classification problem. This NFD module and neuron image datasets are provided as a freely downloadable MatLab project at http://iclab.life.nctu.edu.tw/HCS-Neurons. CONCLUSIONS: Few automatic methods focus on analyzing multi-neuron images collected from HCS used in drug discovery. We provided an automatic HCS-based method for generating accurate classifiers to classify neurons based on their phenotypic changes upon drug treatments. The proposed HCS-neurons method is helpful in identifying and classifying chemical or biological molecules that alter the morphology of a group of neurons in HCS.

BACKGROUND: Existing methods for predicting protein solubility on overexpression in Escherichia coli advance performance by using ensemble classifiers such as two-stage support vector machine (SVM) based classifiers and a number of feature types such as physicochemical properties, amino acid and dipeptide composition, accompanied with feature selection. It is desirable to develop a simple and easily interpretable method for predicting protein solubility, compared to existing complex SVM-based methods. RESULTS: This study proposes a novel scoring card method (SCM) by using dipeptide composition only to estimate solubility scores of sequences for predicting protein solubility. SCM calculates the propensities of 400 individual dipeptides to be soluble using statistic discrimination between soluble and insoluble proteins of a training data set. Consequently, the propensity scores of all dipeptides are further optimized using an intelligent genetic algorithm. The solubility score of a sequence is determined by the weighted sum of all propensity scores and dipeptide composition. To evaluate SCM by performance comparisons, four data sets with different sizes and variation degrees of experimental conditions were used. The results show that the simple method SCM with interpretable propensities of dipeptides has promising performance, compared with existing SVM-based ensemble methods with a number of feature types. Furthermore, the propensities of dipeptides and solubility scores of sequences can provide insights to protein solubility. For example, the analysis of dipeptide scores shows high propensity of α-helix structure and thermophilic proteins to be soluble. CONCLUSIONS: The propensities of individual dipeptides to be soluble are varied for proteins under altered experimental conditions. For accurately predicting protein solubility using SCM, it is better to customize the score card of dipeptide propensities by using a training data set under the same specified experimental conditions. The proposed method SCM with solubility scores and dipeptide propensities can be easily applied to the protein function prediction problems that dipeptide composition features play an important role. AVAILABILITY: The used datasets, source codes of SCM, and supplementary files are available at http://iclab.life.nctu.edu.tw/SCM/.

BACKGROUND: Automatic quantification of neuronal morphology from images of fluorescence microscopy plays an increasingly important role in high-content screenings. However, there exist very few freeware tools and methods which provide automatic neuronal morphology quantification for pharmacological discovery. RESULTS: This study proposes an effective quantification method, called NeurphologyJ, capable of automatically quantifying neuronal morphologies such as soma number and size, neurite length, and neurite branching complexity (which is highly related to the numbers of attachment points and ending points). NeurphologyJ is implemented as a plugin to ImageJ, an open-source Java-based image processing and analysis platform. The high performance of NeurphologyJ arises mainly from an elegant image enhancement method. Consequently, some morphology operations of image processing can be efficiently applied. We evaluated NeurphologyJ by comparing it with both the computer-aided manual tracing method NeuronJ and an existing ImageJ-based plugin method NeuriteTracer. Our results reveal that NeurphologyJ is comparable to NeuronJ, that the coefficient correlation between the estimated neurite lengths is as high as 0.992. NeurphologyJ can accurately measure neurite length, soma number, neurite attachment points, and neurite ending points from a single image. Furthermore, the quantification result of nocodazole perturbation is consistent with its known inhibitory effect on neurite outgrowth. We were also able to calculate the IC50 of nocodazole using NeurphologyJ. This reveals that NeurphologyJ is effective enough to be utilized in applications of pharmacological discoveries. CONCLUSIONS: This study proposes an automatic and fast neuronal quantification method NeurphologyJ. The ImageJ plugin with supports of batch processing is easily customized for dealing with high-content screening applications. The source codes of NeurphologyJ (interactive and high-throughput versions) and the images used for testing are freely available (see Availability).