IBPred: A sequence-based predictor for identifying ion binding protein in phage

Machine learning: Python tools for studying biomolecules and drug design

The increasing adoption of computational methods and artificial intelligence in scientific research has led to a growing interest in versatile tools like Python. In the fields of medical chemistry, biochemistry, and bioinformatics, Python has emerged as a key language for tackling complex challenges. It is used to solve various tasks, such as drug discovery, high-throughput and virtual screening, protein and genome analysis, and predicting drug efficacy. This review presents a list of tools for these tasks, including scripts, libraries, and ready-made programs, and serves as a starting point for scientists wishing to apply automation or optimization to routine tasks in medical chemistry and bioinformatics.

TCellPredX: A Novel Approach for Accurate Prediction of Hepatitis C Virus Linear T Cell Epitopes

Hepatitis C Virus (HCV) is a bloodborne RNA virus that leads to severe liver diseases, and currently, no effective prophylactic biologics are available to prevent its transmission. The prevention of HCV is closely related to the major histocompatibility complex (MHC). Linear antigenic peptides of HCV, known as T cell epitopes (TCEs), are crucial in the presentation process by MHC molecules to T cells, playing a key role in immune responses. Therefore, the rapid and accurate identification of these TCE-HCVs is essential for advancing vaccine development. Herein, we propose TCellPredX, a novel integrated predictor for TCE-HCV identification. TCellPredX leverages five distinct feature encoding schemes, including local and global sequence encodings, composition-transition-distribution descriptors, physicochemical properties, and embeddings from two protein language models, which are processed through 12 machine learning algorithms. Our results indicate that feature fusion significantly enhances predictive accuracy. Moreover, the maximal relevance minimal redundancy feature selection method is particularly effective in isolating informative features, ensuring the model's use of the most informative data. Additionally, ensemble models, especially when combined with an averaged voting strategy, demonstrate superior stability and accuracy compared to individual classifiers, effectively reducing noise and enhancing model robustness. TCellPredX achieves notable accuracies of 0.900 and 0.897 in 10-fold cross-validation and independent test, respectively. Furthermore, TCellPredX's high accuracy is validated on experimentally verified peptide sequences documented for their potential benefits in vaccine development. Overall, TCellPredX can offer a robust tool for the precise identification of TCE-HCV, potentially serving as a cornerstone for future epitope research and advancing HCV vaccines development.

An explainable stacking-based approach for accelerating the prediction of antidiabetic peptides

Diabetes is a chronic disease that is characterized by high blood sugar levels and can have several harmful outcomes. Hyperglycemia, which is defined by persistently elevated blood sugar, is one of the primary concerns. People can improve their overall well-being and get optimal health outcomes by prioritizing diabetes control. Although the use of experimental approaches in diabetes treatment is cost-effective, it necessitates the development of many strategies for evaluating the efficacy of therapies. Researchers can quickly create new strategies for managing diabetes and get vital insights by enabling virtual screening with computational tools and procedures. In this study, we suggest a predictor named STADIP (STacking-based predictor for AntiDiabetic Peptides), a new method to predict antidiabetic peptides (ADPs) utilizing a stacked-based ensemble approach. It uses 12 different feature encodings and seven machine-learning techniques to construct 84 baseline models. The impacts of various baseline models on ADP prediction were then thoroughly examined. A two-step feature selection method, eXtreme Gradient Boosting with Sequential Forward Selection (XGB-SFS), was employed to determine the optimal number, out of 84 PFs to enhance predictive performance. Subsequently, utilizing the meta-predictor approach, 45 selected PFs were integrated into an XGB classifier to formulate the final hybrid model. The proposed method demonstrated superior predictive capabilities compared to constituent baseline models, as evidenced by evaluations on both cross-validation and independent tests. During extensive independent testing, STADIP achieved promising performance with accuracy and mathew's correlation coefficient of 0.954 and 0.877, respectively. It is anticipated that it will be useful tool in helping the scientific community to identify new antidiabetic proteins.

ac4C-AFL: A high-precision identification of human mRNA N4-acetylcytidine sites based on adaptive feature representation learning

RNA N4-acetylcytidine (ac4C) is a highly conserved RNA modification that plays a crucial role in controlling mRNA stability, processing, and translation. Consequently, accurate identification of ac4C sites across the genome is critical for understanding gene expression regulation mechanisms. In this study, we have developed ac4C-AFL, a bioinformatics tool that precisely identifies ac4C sites from primary RNA sequences. In ac4C-AFL, we identified the optimal sequence length for model building and implemented an adaptive feature representation strategy that is capable of extracting the most representative features from RNA. To identify the most relevant features, we proposed a novel ensemble feature importance scoring strategy to rank features effectively. We then used this information to conduct the sequential forward search, which individually determine the optimal feature set from the 16 sequence-derived feature descriptors. Utilizing these optimal feature descriptors, we constructed 176 baseline models using 11 popular classifiers. The most efficient baseline models were identified using the two-step feature selection approach, whose predicted scores were integrated and trained with the appropriate classifier to develop the final prediction model. Our rigorous cross-validations and independent tests demonstrate that ac4C-AFL surpasses contemporary tools in predicting ac4C sites. Moreover, we have developed a publicly accessible web server at https://balalab-skku.org/ac4C-AFL/.

ASPTF: A computational tool to predict abiotic stress-responsive transcription factors in plants by employing machine learning algorithms

BACKGROUND

Abiotic stresses pose serious threat to the growth and yield of crop plants. Several studies suggest that in plants, transcription factors (TFs) are important regulators of gene expression, especially when it comes to coping with abiotic stresses. Therefore, it is crucial to identify TFs associated with abiotic stress response for breeding of abiotic stress tolerant crop cultivars.

METHODS

Based on a machine learning framework, a computational model was envisaged to predict TFs associated with abiotic stress response in plants. To numerically encode TF sequences, four distinct sequence derived features were generated. The prediction was performed using ten shallow learning and four deep learning algorithms. For prediction using more pertinent and informative features, feature selection techniques were also employed.

RESULTS

Using the features chosen by the light-gradient boosting machine-variable importance measure (LGBM-VIM), the LGBM achieved the highest cross-validation performance metrics (accuracy: 86.81%, auROC: 92.98%, and auPRC: 94.03%). Further evaluation of the proposed model (LGBM prediction method + LGBM-VIM selected features) was also done using an independent test dataset, where the accuracy, auROC and auPRC were observed 81.98%, 90.65% and 91.30%, respectively.

CONCLUSIONS

To facilitate the adoption of the proposed strategy by users, the approach was implemented as a prediction server called ASPTF, accessible at https://iasri-sg.icar.gov.in/asptf/. The developed approach and the corresponding web application are anticipated to supplement experimental methods in the identification of transcription factors (TFs) responsive to abiotic stress in plants.

An ensemble computational model for prediction of clathrin protein by coupling machine learning with discrete cosine transform

Clathrin protein (CP) plays a pivotal role in numerous cellular processes, including endocytosis, signal transduction, and neuronal function. Dysregulation of CP has been associated with a spectrum of diseases. Given its involvement in various cellular functions, CP has garnered significant attention for its potential applications in drug design and medicine, ranging from targeted drug delivery to addressing viral infections, neurological disorders, and cancer. The accurate identification of CP is crucial for unraveling its function and devising novel therapeutic strategies. Computational methods offer a rapid, cost-effective, and less labor-intensive alternative to traditional identification methods, making them especially appealing for high-throughput screening. This paper introduces CL-Pred, a novel computational method for CP identification. CL-Pred leverages three feature descriptors: Dipeptide Deviation from Expected Mean (DDE), Bigram Position Specific Scoring Matrix (BiPSSM), and Position Specific Scoring Matrix-Tetra Slice-Discrete Cosine Transform (PSSM-TS-DCT). The model is trained using three classifiers: Support Vector Machine (SVM), Extremely Randomized Tree (ERT), and Light eXtreme Gradient Boosting (LiXGB). Notably, the LiXGB-based model achieves outstanding performance, demonstrating accuracies of 94.63% and 93.65% on the training and testing datasets, respectively. The proposed CL-Pred method is poised to significantly advance our comprehension of clathrin-mediated endocytosis, cellular physiology, and disease pathogenesis. Furthermore, it holds promise for identifying potential drug targets across a spectrum of diseases.

Recent Progress in Phage-Based Nanoplatforms for Tumor Therapy

Nanodrug delivery systems have demonstrated a great potential for tumor therapy with the development of nanotechnology. Nonetheless, traditional drug delivery systems are faced with issues such as complex synthetic procedures, low reproducibility, nonspecific distribution, impenetrability of biological barrier, systemic toxicity, etc. In recent years, phage-based nanoplatforms have attracted increasing attention in tumor treatment for their regular structure, fantastic carrying property, high transduction efficiency and biosafety. Notably, therapeutic or targeting peptides can be expressed on the surface of the phages through phage display technology, enabling the phage vectors to possess multifunctions. As a result, the drug delivery efficiency on tumor will be vastly improved, thereby enhancing the therapeutic efficacy while reducing the side effects on normal tissues. Moreover, phages can overcome the hindrance of biofilm barrier to elicit antitumor effects, which exhibit great advantages compared with traditional synthetic drug delivery systems. Herein, this review not only summarizes the structure and biology of the phages, but also presents their potential as prominent nanoplatforms against tumor in different pathways to inspire the development of effective nanomedicine.

NCSP-PLM: An ensemble learning framework for predicting non-classical secreted proteins based on protein language models and deep learning

Non-classical secreted proteins (NCSPs) refer to a group of proteins that are located in the extracellular environment despite the absence of signal peptides and motifs. They usually play different roles in intercellular communication. Therefore, the accurate prediction of NCSPs is a critical step to understanding in depth their associated secretion mechanisms. Since the experimental recognition of NCSPs is often costly and time-consuming, computational methods are desired. In this study, we proposed an ensemble learning framework, termed NCSP-PLM, for the identification of NCSPs by extracting feature embeddings from pre-trained protein language models (PLMs) as input to several fine-tuned deep learning models. First, we compared the performance of nine PLM embeddings by training three neural networks: Multi-layer perceptron (MLP), attention mechanism and bidirectional long short-term memory network (BiLSTM) and selected the best network model for each PLM embedding. Then, four models were excluded due to their below-average accuracies, and the remaining five models were integrated to perform the prediction of NCSPs based on the weighted voting. Finally, the 5-fold cross validation and the independent test were conducted to evaluate the performance of NCSP-PLM on the benchmark datasets. Based on the same independent dataset, the sensitivity and specificity of NCSP-PLM were 91.18% and 97.06%, respectively. Particularly, the overall accuracy of our model achieved 94.12%, which was 7~16% higher than that of the existing state-of-the-art predictors. It indicated that NCSP-PLM could serve as a useful tool for the annotation of NCSPs.

Accurately identifying hemagglutinin using sequence information and machine learning methods

Introduction

Hemagglutinin (HA) is responsible for facilitating viral entry and infection by promoting the fusion between the host membrane and the virus. Given its significance in the process of influenza virus infestation, HA has garnered attention as a target for influenza drug and vaccine development. Thus, accurately identifying HA is crucial for the development of targeted vaccine drugs. However, the identification of HA using in-silico methods is still lacking. This study aims to design a computational model to identify HA.

Methods

In this study, a benchmark dataset comprising 106 HA and 106 non-HA sequences were obtained from UniProt. Various sequence-based features were used to formulate samples. By perform feature optimization and inputting them four kinds of machine learning methods, we constructed an integrated classifier model using the stacking algorithm.

Results and discussion

The model achieved an accuracy of 95.85% and with an area under the receiver operating characteristic (ROC) curve of 0.9863 in the 5-fold cross-validation. In the independent test, the model exhibited an accuracy of 93.18% and with an area under the ROC curve of 0.9793. The code can be found from https://github.com/Zouxidan/HA_predict.git. The proposed model has excellent prediction performance. The model will provide convenience for biochemical scholars for the study of HA.

A First Computational Frame for Recognizing Heparin-Binding Protein

Heparin-binding protein (HBP) is a cationic antibacterial protein derived from multinuclear neutrophils and an important biomarker of infectious diseases. The correct identification of HBP is of great significance to the study of infectious diseases. This work provides the first HBP recognition framework based on machine learning to accurately identify HBP. By using four sequence descriptors, HBP and non-HBP samples were represented by discrete numbers. By inputting these features into a support vector machine (SVM) and random forest (RF) algorithm and comparing the prediction performances of these methods on training data and independent test data, it is found that the SVM-based classifier has the greatest potential to identify HBP. The model could produce an auROC of 0.981 ± 0.028 on training data using 10-fold cross-validation and an overall accuracy of 95.0% on independent test data. As the first model for HBP recognition, it will provide some help for infectious diseases and stimulate further research in related fields.

AFP-SPTS: An Accurate Prediction of Antifreeze Proteins Using Sequential and Pseudo-Tri-Slicing Evolutionary Features with an Extremely Randomized Tree

The development of intracellular ice in the bodies of cold-blooded living organisms may cause them to die. These species yield antifreeze proteins (AFPs) to live in subzero temperature environments. Additionally, AFPs are implemented in biotechnological, industrial, agricultural, and medical fields. Machine learning-based predictors were presented for AFP identification. However, more accurate predictors are still highly desirable for boosting the AFP prediction. This work presents a novel approach, named AFP-SPTS, for the correct prediction of AFPs. We explored the discriminative features with four schemes, namely, dipeptide deviation from the expected mean (DDE), reduced amino acid alphabet (RAAA), grouped dipeptide composition (GDPC), and a novel representative method, called pseudo-position-specific scoring matrix tri-slicing (PseTS-PSSM). Considering the advantages of ensemble learning strategy, we fused each feature vector into different combinations and trained the models with five machine learning algorithms, i.e., multilayer perceptron (MLP), extremely randomized tree (ERT), decision tree (DT), random forest (RF), and AdaBoost. Among all models, PseTS-PSSM + RAAA with an extremely randomized tree attained the best outcomes. The proposed predictor (AFP-SPTS) boosted the accuracies of AFPs in the literature by 1.82 and 4.1%.

ToxMVA: An end-to-end multi-view deep autoencoder method for protein toxicity prediction

Effectively predicting protein toxicity plays an essential step in the early stage of protein-based drug discovery, which is of great help to speed up novel drug screening and reduce costs. Recently, several relevant datasets have been designed, and then machine learning-based methods have been proposed to predict the toxicity of the protein and have shown satisfactory performance. However, previous studies generally directly concatenate different protein features, which may introduce irrelevant information and decrease model performance. In this study, we present a novel end-to-end deep learning-based method called ToxMVA, to predict protein toxicity. To be specific, we first build comprehensive feature profiles of proteins based on primary sequences, including sequential, physicochemical, and contextual semantic information. Next, an autoencoder network is introduced to integrate the multi-view information for obtaining a more concise and accurate feature representation. Extensive experimental results on three datasets demonstrate that ToxMVA has superior performance for protein toxicity prediction and shows better robustness among three different datasets.

Antimicrobial Peptides Prediction method based on sequence multidimensional feature embedding

Antimicrobial peptides (AMPs) are alkaline substances with efficient bactericidal activity produced in living organisms. As the best substitute for antibiotics, they have been paid more and more attention in scientific research and clinical application. AMPs can be produced from almost all organisms and are capable of killing a wide variety of pathogenic microorganisms. In addition to being antibacterial, natural AMPs have many other therapeutically important activities, such as wound healing, antioxidant and immunomodulatory effects. To discover new AMPs, the use of wet experimental methods is expensive and difficult, and bioinformatics technology can effectively solve this problem. Recently, some deep learning methods have been applied to the prediction of AMPs and achieved good results. To further improve the prediction accuracy of AMPs, this paper designs a new deep learning method based on sequence multidimensional representation. By encoding and embedding sequence features, and then inputting the model to identify AMPs, high-precision classification of AMPs and Non-AMPs with lengths of 10-200 is achieved. The results show that our method improved accuracy by 1.05% compared to the most advanced model in independent data validation without decreasing other indicators.