In Silico Screening and Optimization of Cell-Penetrating Peptides Using Deep Learning Methods

Strategies for the design of biomimetic cell-penetrating peptides using AI-driven in silico tools for drug delivery

Cell-penetrating peptides (CPP) have gained rapid attention over the last 25 years; this is attributed to their versatility, customisation, and 'Trojan horse' delivery that evades the immune system. However, the current CPP rational design process is limited, as it requires several rounds of peptide synthesis, prediction and wet-lab validation, which is expensive, time-consuming and requires extensive knowledge in peptide chemistry. Artificial intelligence (AI) has emerged as a promising alternative which can augment the design process, for example by determining physiochemical characteristics, secondary structure, solvent accessibility, disorder and flexibility, as well as predicting in vivo behaviour such as toxicity and peptidase degradation. Other more recent tools utilise supervised machine learning (ML) to predict the penetrative ability of an amino acid sequence. The use of AI in the CPP design process has the potential to reduce development costs and increase the chances of success with respect to delivery. This review provides a survey of in silico tools and AI platforms which can be utilised in the design process, and the key features that should be taken into consideration when designing next generation CPPs.

Peptide classification landscape: An in-depth systematic literature review on peptide types, databases, datasets, predictors architectures and performance

Peptides are gaining significant attention in diverse fields such as the pharmaceutical market has seen a steady rise in peptide-based therapeutics over the past six decades. Peptides have been utilized in the development of distinct applications including inhibitors of SARS-COV-2 and treatments for conditions like cancer and diabetes. Distinct types of peptides possess unique characteristics, and development of peptide-specific applications require the discrimination of one peptide type from others. To the best of our knowledge, approximately 230 Artificial Intelligence (AI) driven applications have been developed for 22 distinct types of peptides, yet there remains significant room for development of new predictors. A Comprehensive review addresses the critical gap by providing a consolidated platform for the development of AI-driven peptide classification applications. This paper offers several key contributions, including presenting the biological foundations of 22 unique peptide types and categorizes them into four main classes: Regulatory, Therapeutic, Nutritional, and Delivery Peptides. It offers an in-depth overview of 47 databases that have been used to develop peptide classification benchmark datasets. It summarizes details of 288 benchmark datasets that are used in development of diverse types AI-driven peptide classification applications. It provides a detailed summary of 197 sequence representation learning methods and 94 classifiers that have been used to develop 230 distinct AI-driven peptide classification applications. Across 22 distinct types peptide classification tasks related to 288 benchmark datasets, it demonstrates performance values of 230 AI-driven peptide classification applications. It summarizes experimental settings and various evaluation measures that have been employed to assess the performance of AI-driven peptide classification applications. The primary focus of this manuscript is to consolidate scattered information into a single comprehensive platform. This resource will greatly assist researchers who are interested in developing new AI-driven peptide classification applications.

A bird's-eye view of the biological mechanism and machine learning prediction approaches for cell-penetrating peptides

Cell-penetrating peptides (CPPs) are highly effective at passing through eukaryotic membranes with various cargo molecules, like drugs, proteins, nucleic acids, and nanoparticles, without causing significant harm. Creating drug delivery systems with CPP is associated with cancer, genetic disorders, and diabetes due to their unique chemical properties. Wet lab experiments in drug discovery methodologies are time-consuming and expensive. Machine learning (ML) techniques can enhance and accelerate the drug discovery process with accurate and intricate data quality. ML classifiers, such as support vector machine (SVM), random forest (RF), gradient-boosted decision trees (GBDT), and different types of artificial neural networks (ANN), are commonly used for CPP prediction with cross-validation performance evaluation. Functional CPP prediction is improved by using these ML strategies by using CPP datasets produced by high-throughput sequencing and computational methods. This review focuses on several ML-based CPP prediction tools. We discussed the CPP mechanism to understand the basic functioning of CPPs through cells. A comparative analysis of diverse CPP prediction methods was conducted based on their algorithms, dataset size, feature encoding, software utilities, assessment metrics, and prediction scores. The performance of the CPP prediction was evaluated based on accuracy, sensitivity, specificity, and Matthews correlation coefficient (MCC) on independent datasets. In conclusion, this review will encourage the use of ML algorithms for finding effective CPPs, which will have a positive impact on future research on drug delivery and therapeutics.

Exploring the Chemical Features and Biomedical Relevance of Cell-Penetrating Peptides

Cell-penetrating peptides (CPPs) are a diverse group of peptides, typically composed of 4 to 40 amino acids, known for their unique ability to transport a wide range of substances-such as small molecules, plasmid DNA, small interfering RNA, proteins, viruses, and nanoparticles-across cellular membranes while preserving the integrity of the cargo. CPPs exhibit passive and non-selective behavior, often requiring functionalization or chemical modification to enhance their specificity and efficacy. The precise mechanisms governing the cellular uptake of CPPs remain ambiguous; however, electrostatic interactions between positively charged amino acids and negatively charged glycosaminoglycans on the membrane, particularly heparan sulfate proteoglycans, are considered the initial crucial step for CPP uptake. Clinical trials have highlighted the potential of CPPs in diagnosing and treating various diseases, including cancer, central nervous system disorders, eye disorders, and diabetes. This review provides a comprehensive overview of CPP classifications, potential applications, transduction mechanisms, and the most relevant algorithms to improve the accuracy and reliability of predictions in CPP development.

EnDM-CPP: A Multi-view Explainable Framework Based on Deep Learning and Machine Learning for Identifying Cell-Penetrating Peptides with Transformers and Analyzing Sequence Information

Cell-Penetrating Peptides (CPPs) are a crucial carrier for drug delivery. Since the process of synthesizing new CPPs in the laboratory is both time- and resource-consuming, computational methods to predict potential CPPs can be used to find CPPs to enhance the development of CPPs in therapy. In this study, EnDM-CPP is proposed, which combines machine learning algorithms (SVM and CatBoost) with convolutional neural networks (CNN and TextCNN). For dataset construction, three previous CPP benchmark datasets, including CPPsite 2.0, MLCPP 2.0, and CPP924, are merged to improve the diversity and reduce homology. For feature generation, two language model-based features obtained from the Transformer architecture, including ProtT5 and ESM-2, are employed in CNN and TextCNN. Additionally, sequence features, such as CPRS, Hybrid PseAAC, KSC, etc., are input to SVM and CatBoost. Based on the result of each predictor, Logistic Regression (LR) is built to predict the final decision. The experiment results indicate that ProtT5 and ESM-2 fusion features significantly contribute to predicting CPP and that combining employed features and models demonstrates better association. On an independent test dataset comparison, EnDM-CPP achieved an accuracy of 0.9495 and a Matthews correlation coefficient of 0.9008 with an improvement of 2.23%-9.48% and 4.32%-19.02%, respectively, compared with other state-of-the-art methods. Code and data are available at https://github.com/tudou1231/EnDM-CPP.git .

Cycle-ESM: Generation-assisted classification of antifungal peptides using ESM protein language model

The rising prevalence of invasive fungal infections and the emergence of antifungal resistance highlight the urgent need for new antifungal medications. Antifungal peptides have emerged as promising alternatives to traditional antimicrobial agents. The identification of natural or synthetic antifungal peptides is crucial for advancing antifungal drug development. Typically, the availability of antifungal samples is limited, and significant sequence diversity exists among antifungal peptides, posing challenges for high-throughput screening. To address the identification challenge of antifungal peptides with limited sample availability, this study introduces the Cycle ESM method. Initially, the method utilises the ESM protein language model to generate additional data on antifungal peptides, serving as a data augmentation technique to enhance model training effectiveness. Subsequently, the ESM is employed in conjunction with a textCNN model to construct a classifier for peptide prediction, with a comprehensive exploration of peptide characteristics to improve prediction accuracy. Experimental results demonstrate that the performance of the Cycle ESM method surpasses that of existing methods across three distinct antifungal peptide datasets. This study presents a novel approach to antifungal peptide prediction and offers innovative insights for addressing classification problems with limited sample availability.

A high hydrophobic moment arginine-rich peptide screened by a machine learning algorithm enhanced ADC antitumor activity

Cell-penetrating peptides (CPPs) with better biomolecule delivery properties will expand their clinical applications. Using the MLCPP2.0 machine algorithm, we screened multiple candidate sequences with potential cellular uptake ability from the nuclear localization signal/nuclear export signal database and verified them through cell-penetrating fluorescent tracing experiments. A peptide (NCR) derived from the Rev protein of the caprine arthritis-encephalitis virus exhibited efficient cell-penetrating activity, delivering over four times more EGFP than the classical CPP TAT, allowing it to accumulate in lysosomes. Structural and property analysis revealed that a high hydrophobic moment and an appropriate hydrophobic region contribute to the high delivery activity of NCR. Trastuzumab emtansine (T-DM1), a HER2-targeted antibody-drug conjugate, could improve its anti-tumor activity by enhancing targeted delivery efficiency and increasing lysosomal drug delivery. This study designed a new NCR vector to non-covalently bind T-DM1 by fusing domain Z, which can specifically bind to the Fc region of immunoglobulin G and effectively deliver T-DM1 to lysosomes. MTT results showed that the domain Z-NCR vector significantly enhanced the cytotoxicity of T-DM1 against HER2-positive tumor cells while maintaining drug specificity. Our results make a useful attempt to explore the potential application of CPP as a lysosome-targeted delivery tool.

Peptidomimetics design and characterization: Bridging experimental and computer-based approaches

Peptidomimetics, designed to mimic peptide biological activity with more drug-like properties, are increasingly pivotal in medicinal chemistry. They offer enhanced systemic delivery, cell penetration, target specificity, and protection against peptidases when compared to their native peptide counterparts. Already utilized in treating diverse diseases like neurodegenerative disorders, cancer and infectious diseases, their future in medicine seems bright, with many peptidomimetics in clinical trials or development stages. Peptidomimetics are well-suited for addressing disturbed protein-protein interactions (PPIs), which often underlie various pathologies. Structural biology and computational methods like molecular dynamics simulations facilitate rational design, whereas machine learning algorithms accelerate protein structure prediction, enabling efficient drug development. Experimental validation via various spectroscopic, biophysical, and biochemical assays confirms computational predictions and guides further optimization. Peptidomimetics, with their tailored constrained structures, represent a frontier in drug design focused on targeting PPIs. In this overview, we present a comprehensive landscape of peptidomimetics, encompassing perspectives on involvement in pathologies, chemical strategies, and methodologies for their characterization, spanning in silico, in vitro and in cell approaches. With increasing interest from pharmaceutical sectors, peptidomimetics hold promise for revolutionizing therapeutic approaches, marking a new era of precision drug discovery.

Investigating molecular descriptors in cell-penetrating peptides prediction with deep learning: Employing N, O, and hydrophobicity according to the Eisenberg scale

Cell-penetrating peptides comprise a group of molecules that can naturally cross the lipid bilayer membrane that protects cells, sharing physicochemical and structural properties, and having several pharmaceutical applications, particularly in drug delivery. Investigations of molecular descriptors have provided not only an improvement in the performance of classifiers but also less computational complexity and an enhanced understanding of membrane permeability. Furthermore, the employment of new technologies, such as the construction of deep learning models using overfitting treatment, promotes advantages in tackling this problem. In this study, the descriptors nitrogen, oxygen, and hydrophobicity on the Eisenberg scale were investigated, using the proposed ConvBoost-CPP composed of an improved convolutional neural network with overfitting treatment and an XGBoost model with adjusted hyperparameters. The results revealed favorable to the use of ConvBoost-CPP, having as input nitrogen, oxygen, and hydrophobicity together with ten other descriptors previously investigated in this research line, showing an increase in accuracy from 88% to 91.2% in cross-validation and 82.6% to 91.3% in independent test.

Virtual Screening of Peptide Libraries: The Search for Peptide-Based Therapeutics Using Computational Tools

Over the last few decades, we have witnessed growing interest from both academic and industrial laboratories in peptides as possible therapeutics. Bioactive peptides have a high potential to treat various diseases with specificity and biological safety. Compared to small molecules, peptides represent better candidates as inhibitors (or general modulators) of key protein-protein interactions. In fact, undruggable proteins containing large and smooth surfaces can be more easily targeted with the conformational plasticity of peptides. The discovery of bioactive peptides, working against disease-relevant protein targets, generally requires the high-throughput screening of large libraries, and in silico approaches are highly exploited for their low-cost incidence and efficiency. The present review reports on the potential challenges linked to the employment of peptides as therapeutics and describes computational approaches, mainly structure-based virtual screening (SBVS), to support the identification of novel peptides for therapeutic implementations. Cutting-edge SBVS strategies are reviewed along with examples of applications focused on diverse classes of bioactive peptides (i.e., anticancer, antimicrobial/antiviral peptides, peptides blocking amyloid fiber formation).

Advances in Drug Design and Development for Human Therapeutics Using Artificial Intelligence-II

Building on our 2021-2022 Special Issue, "Advances in Drug Design and Development for Human Therapeutics Using Artificial Intelligence [...].