Tae Hwan Shin

MLACP: machine-learning-based prediction of anticancer peptides

Cancer is the second leading cause of death globally, and use of therapeutic peptides to target and kill cancer cells has received considerable attention in recent years. Identification of anticancer peptides (ACPs) through wet-lab experimentation is expensive and often time consuming; therefore, development of an efficient computational method is essential to identify potential ACP candidates prior to in vitro experimentation. In this study, we developed support vector machine- and random forest-based machine-learning methods for the prediction of ACPs using the features calculated from the amino acid sequence, including amino acid composition, dipeptide composition, atomic composition, and physicochemical properties. We trained our methods using the Tyagi-B dataset and determined the machine parameters by 10-fold cross-validation. Furthermore, we evaluated the performance of our methods on two benchmarking datasets, with our results showing that the random forest-based method outperformed the existing methods with an average accuracy and Matthews correlation coefficient value of 88.7% and 0.78, respectively. To assist the scientific community, we also developed a publicly accessible web server at www.thegleelab.org/MLACP.html.

Machine-Learning-Based Prediction of Cell-Penetrating Peptides and Their Uptake Efficiency with Improved Accuracy

Cell-penetrating peptides (CPPs) can enter cells as a variety of biologically active conjugates and have various biomedical applications. To offset the cost and effort of designing novel CPPs in laboratories, computational methods are necessitated to identify candidate CPPs before in vitro experimental studies. We developed a two-layer prediction framework called machine-learning-based prediction of cell-penetrating peptides (MLCPPs). The first-layer predicts whether a given peptide is a CPP or non-CPP, whereas the second-layer predicts the uptake efficiency of the predicted CPPs. To construct a two-layer prediction framework, we employed four different machine-learning methods and five different compositions including amino acid composition (AAC), dipeptide composition, amino acid index, composition-transition-distribution, and physicochemical properties (PCPs). In the first layer, hybrid features (combination of AAC and PCP) and extremely randomized tree outperformed state-of-the-art predictors in CPP prediction with an accuracy of 0.896 when tested on independent data sets, whereas in the second layer, hybrid features obtained through feature selection protocol and random forest produced an accuracy of 0.725 that is better than state-of-the-art predictors. We anticipate that our method MLCPP will become a valuable tool for predicting CPPs and their uptake efficiency and might facilitate hypothesis-driven experimental design. The MLCPP server interface along with the benchmarking and independent data sets are freely accessible at www.thegleelab.org/MLCPP .

Quality and freshness of human bone marrow-derived mesenchymal stem cells decrease over time after trypsinization and storage in phosphate-buffered saline

Human bone marrow-derived mesenchymal stem cells (hBM-MSCs) have been studied for their therapeutic potential. However, evaluating the quality of hBM-MSCs before transplantation remains a challenge. We addressed this issue in the present study by investigating deformation, the expression of genes related to reactive oxygen species (ROS) generation, changes in amino acid profiles, and membrane fluidity in hBM-MSCs. Deformability and cell size were decreased after storage for 6 and 12 h, respectively, in phosphate-buffered saline. Intracellular ROS levels also increased over time, which was associated with altered expression of genes related to ROS generation and amino acid metabolism. Membrane fluidity measurements revealed higher Laurdan generalized polarization values at 6 and 12 h; however, this effect was reversed by N-acetyl-l-cysteine-treatment. These findings indicate that the quality and freshness of hBM-MSCs is lost over time after dissociation from the culture dish for transplantation, highlighting the importance of using freshly trypsinized cells in clinical applications.

Integration of metabolomics and transcriptomics in nanotoxicity studies

Biomedical research involving nanoparticles has produced useful products with medical applications. However, the potential toxicity of nanoparticles in biofluids, cells, tissues, and organisms is a major challenge. The ‘-omics’ analyses provide molecular profiles of multifactorial biological systems instead of focusing on a single molecule. The ‘omics’ approaches are necessary to evaluate nanotoxicity because classical methods for the detection of nanotoxicity have limited ability in detecting miniscule variations within a cell and do not accurately reflect the actual levels of nanotoxicity. In addition, the ‘omics’ approaches allow analyses of in-depth changes and compensate for the differences associated with high-throughput technologies between actual nanotoxicity and results from traditional cytotoxic evaluations. However, compared with a single omics approach, integrated omics provides precise and sensitive information by integrating complex biological conditions. Thus, these technologies contribute to extended safety evaluations of nanotoxicity and allow the accurate diagnoses of diseases far earlier than was once possible in the nanotechnology era. Here, we review a novel approach for evaluating nanotoxicity by integrating metabolomics with metabolomic profiling and transcriptomics, which is termed “metabotranscriptomics”.

PIP-EL: A New Ensemble Learning Method for Improved Proinflammatory Peptide Predictions

Proinflammatory cytokines have the capacity to increase inflammatory reaction and play a central role in first line of defence against invading pathogens. Proinflammatory inducing peptides (PIPs) have been used as an antineoplastic agent, an antibacterial agent and a vaccine in immunization therapies. Due to the advancement in sequence technologies that resulted an avalanche of protein sequence data. Therefore, it is necessary to develop an automated computational method to enable fast and accurate identification of novel PIPs within the vast number of candidate proteins and peptides. To address this, we proposed a new predictor, PIP-EL, for predicting PIPs using the strategy of ensemble learning (EL). Our benchmarking dataset is imbalanced. Thus, we applied a random under-sampling technique to generate 10 balanced models for each composition. Technically, PIP-EL is the fusion of 50 independent random forest (RF) models, where each of the five different compositions, including amino acid, dipeptide, composition–transition–distribution, physicochemical properties, and amino acid index contains 10 RF models. PIP-EL achieves the Matthews’ correlation coefficient (MCC) of 0.435 in a 5-fold cross-validation test, which is ~2–5% higher than that of the individual classifiers and hybrid feature-based classifier. Furthermore, we evaluate the performance of PIP-EL on the independent dataset, showing that our method outperforms the existing method and two different machine learning methods developed in this study, with an MCC of 0.454. These results indicate that PIP-EL will be a useful tool for predicting PIPs and for researchers working in the field of peptide therapeutics and immunotherapy. The user-friendly web server, PIP-EL, is freely accessible.1

iBCE-EL: A New Ensemble Learning Framework for Improved Linear B-Cell Epitope Prediction

Identification of B-cell epitopes (BCEs) is a fundamental step for epitope-based vaccine development, antibody production, and disease prevention and diagnosis. Due to the avalanche of protein sequence data discovered in postgenomic age, it is essential to develop an automated computational method to enable fast and accurate identification of novel BCEs within vast number of candidate proteins and peptides. Although several computational methods have been developed, their accuracy is unreliable. Thus, developing a reliable model with significant prediction improvements is highly desirable. In this study, we first constructed a non-redundant data set of 5,550 experimentally validated BCEs and 6,893 non-BCEs from the Immune Epitope Database. We then developed a novel ensemble learning framework for improved linear BCE predictor called iBCE-EL, a fusion of two independent predictors, namely, extremely randomized tree (ERT) and gradient boosting (GB) classifiers, which, respectively, uses a combination of physicochemical properties (PCP) and amino acid composition and a combination of dipeptide and PCP as input features. Cross-validation analysis on a benchmarking data set showed that iBCE-EL performed better than individual classifiers (ERT and GB), with a Matthews correlation coefficient (MCC) of 0.454. Furthermore, we evaluated the performance of iBCE-EL on the independent data set. Results show that iBCE-EL significantly outperformed the state-of-the-art method with an MCC of 0.463. To the best of our knowledge, iBCE-EL is the first ensemble method for linear BCEs prediction. iBCE-EL was implemented in a web-based platform, which is available at http://thegleelab.org/iBCE-EL. iBCE-EL contains two prediction modes. The first one identifying peptide sequences as BCEs or non-BCEs, while later one is aimed at providing users with the option of mining potential BCEs from protein sequences.

Polyamine patterns in plasma of patients with systemic lupus erythematosus and fever

Systemic lupus erythematosus (SLE) is a systemic autoimmune disease with various clinical manifestations and serologic markers. In this study, we analyzed nine polyamine (PA) profiles of plasma from patients with SLE and healthy controls (HCs), and the relationship between the PA profiles and disease activity. PA alterations in plasma of 44 patients with SLE and fever were investigated using gas chromatography mass spectrometry (GC-MS) in selected ion monitoring mode using N-ethoxycarbonyl/N-pentafluoropropionyl derivatives, and compared with those of 43 HCs. Patients with SLE and HCs showed differences in five of nine PA profiles. Among five changed PA levels, four PAs, namely N1-acetylcadaverine, spermidine, N1-acetylspermidine, and spermine, were dramatically decreased. However, the level of cadaverine was increased in patients with SLE. In the partial correlation with PA profiles and disease activity markers of SLE, several disease activity markers and nutritional markers were correlated with cadaverine, spermidine, and N 8 -acetylspermidine. Thus, our results provide a comprehensive understanding of the relationship between PA metabolomics and disease activity markers in patients with SLE.

Bidirectional Transcriptome Analysis of Rat Bone Marrow-Derived Mesenchymal Stem Cells and Activated Microglia in an In Vitro Coculture System

Microglia contribute to the regulation of neuroinflammation and play an important role in the pathogenesis of brain diseases. Thus, regulation of neuroinflammation triggered by activated microglia in brain diseases has become a promising curative strategy. Bone marrow-derived mesenchymal stem cells (BM-MSCs) have been shown to have therapeutic effects, resulting from the regulation of inflammatory conditions in the brain. In this study, we investigated differential gene expression in rat BM-MSCs (rBM-MSCs) that were cocultured with lipopolysaccharide- (LPS-) stimulated primary rat microglia using microarray analysis and evaluated the functional relationships through Ingenuity Pathway Analysis (IPA). We also evaluated the effects of rBM-MSC on LPS-stimulated microglia using a reverse coculture system and the same conditions of the transcriptomic analysis. In the transcriptome of rBM-MSCs, 67 genes were differentially expressed, which were highly related with migration of cells, compared to control. The prediction of the gene network using IPA and experimental validation showed that LPS-stimulated primary rat microglia increase the migration of rBM-MSCs. Reversely, expression patterns of the transcriptome in LPS-stimulated primary rat microglia were changed when cocultured with rBM-MSCs. Our results showed that 65 genes were changed, which were highly related with inflammatory response, compared to absence of rBM-MSCs. In the same way with the aforementioned, the prediction of the gene network and experimental validation showed that rBM-MSCs decrease the inflammatory response of LPS-stimulated primary rat microglia. Our data indicate that LPS-stimulated microglia increase the migration of rBM-MSCs and that rBM-MSCs reduce the inflammatory activity in LPS-stimulated microglia. The results of this study show complex mechanisms underlying the interaction between rBM-MSCs and activated microglia and may be helpful for the development of stem cell-based strategies for brain diseases.

Analysis of the free fatty acid metabolome in the plasma of patients with systemic lupus erythematosus and fever

IntroductionSystemic lupus erythematosus (SLE) is a multifactorial autoimmune disease with heterogeneous clinical manifestations mediated by immune dysregulation.ObjectivesWe aimed to analyze the metabolomic differences in free fatty acids (FFAs) between patients with SLE and healthy controls (HCs).MethodsIn this study, the levels of 24 FFAs, as their tert-butyldimethylsilyl derivatives, in the plasma of 41 patients with SLE and 41 HCs, were investigated using gas chromatography with mass spectrometry in selected-ion monitoring mode.ResultsThe results showed that patients with SLE and HCs had significantly different levels of 13 of the 24 FFAs. The levels of myristic, palmitoleic, oleic, and eicosenoic acids were significantly higher, whereas the levels of caproic, caprylic, linoleic, stearic, arachidonic, eicosanoic, behenic, lignoceric, and hexacosanoic acids were significantly lower in patients with SLE, than in the HCs. In the partial-correlation analysis of the FFA profiles and markers of disease activity of SLE, several metabolic markers correlated with SLE disease activity.ConclusionsOur results provide a comprehensive understanding of the relationship between FFAs and markers of SLE disease activity. Thus, this approach has promising potential for the discovery of metabolic biomarkers of SLE.

iGHBP: Computational Identification of Growth Hormone Binding Proteins from Sequences using Extremely Randomised tree

A soluble carrier growth hormone binding protein (GHBP) that can selectively and non-covalently interact with growth hormone, thereby acting as a modulator or inhibitor of growth hormone signalling. Accurate identification of the GHBP from a given protein sequence also provides important clues for understanding cell growth and cellular mechanisms. In the postgenomic era, there has been an abundance of protein sequence data garnered, hence it is crucial to develop an automated computational method which enables fast and accurate identification of putative GHBPs within a vast number of candidate proteins. In this study, we describe a novel machine-learning-based predictor called iGHBP for the identification of GHBP. In order to predict GHBP from a given protein sequence, we trained an extremely randomised tree with an optimal feature set that was obtained from a combination of dipeptide composition and amino acid index values by applying a two-step feature selection protocol. During cross-validation analysis, iGHBP achieved an accuracy of 84.9%, which was ~7% higher than the control extremely randomised tree predictor trained with all features, thus demonstrating the effectiveness of our feature selection protocol. Furthermore, when objectively evaluated on an independent data set, our proposed iGHBP method displayed superior performance compared to the existing method. Additionally, a user-friendly web server that implements the proposed iGHBP has been established and is available at http://thegleelab.org/iGHBP.