Deep Learning-Based Bioactive Therapeutic Peptide Generation and Screening

Novel bioactive peptides from ginger rhizome: Integrating in silico and in vitro analysis with mechanistic insights through molecular docking

Ginger (Zingiber officinale) is widely recognised for its functional benefits, primarily attributed to its diverse phytochemicals. However, its proteome remains largely unexplored. This study hypothesised that isolated peptides may exhibit different bioactivities or more targeted mechanisms of action and could be investigated at a molecular level. Proteins were enzymatically hydrolysed under five conditions, and peptides were identified using LC-MS/MS. In silico screening suggested antioxidant, ACE-inhibitory, and antibacterial properties, further assessed through molecular docking and in vitro validation. 41 potentially bioactive peptides were identified. In vitro assays confirmed these properties for selected peptides, P1 (GSPVWIIPEPT), P2 (FASYPVKK), P3 (GPEKIFYDGPYL), and P4 (IAISPSYPIK). Notably, P4 exhibited potent mixed-type ACE-inhibition and bacteriostatic effects. Molecular docking provided mechanistic insights into these interactions. These findings highlight ginger as a promising source of bioactive peptides while underscoring the need to complement AI tools with in vitro and in vivo validations due to observed discrepancies.

Production of bioactive peptides by high-voltage pulsed electric field: Protein extraction, mechanism, research status and collaborative application

Bioactive peptides exhibit a variety of potential applications in the fields of medicine, food and cosmetics. However, studies have shown that the traditional preparation is characterized by low efficiency, substantial pollution, limited activities and poor purity, which constrains their further application. High-voltage pulsed electric field (HPEF) technology, as a physical non-thermal processing method, shows unique advantages in bioactive peptide preparation. Through comprehensive analysis, this paper reveals the main principle of HPEF technology, the extraction of proteins (break up cellular tissue), the structural changes of proteins, enzymes and bioactive peptides after treatment, the improvement of bioactive peptides' functional properties and the potential in promoting bioactive peptides' large-scale production. Besides, this paper introduces the application of other non-thermal processing technologies, artificial intelligence and nanotechnology, providing new ways of thinking for the efficient preparation and application of bioactive peptides and establishes a theoretical foundation for the application and promotion of HPEF technology.

A fast and efficient virtual screening and identification strategy for helix peptide binders based on finDr webserver: A case study of bovine serum albumin (BSA)

Peptides offer unique advantages, including strong specificity, rapid action, and low side effects, making them a prominent focus in the development of new drugs and functional materials. However, the rapid and efficient screening and identification of high-affinity peptides for specific targets remains a significant challenge. In this study, we successfully screened 12-helix candidate peptides using bovine serum albumin (BSA) as the target protein, employing the computer-aided peptide virtual screening webserver finDr. Among the top five candidate peptides, we identified E4-TP2 (GVATVVARLFLL) as the peptide capable of binding BSA with high affinity constant (KD = 39.4 nM), confirmed through an in vitro molecular interaction instrument. The interaction mode of the peptide-BSA complex was analyzed using Ligplot software, revealing that the primary interactions involved hydrophobic forces and hydrogen bonds. Additionally, molecular dynamics simulations further elucidated the molecular mechanisms underlying the high-affinity peptide interactions, the results demonstrated that the complex exhibited good conformational stability and strong binding free energy (MM/PBSA: -21.075 ± 5.471 kJ/mol). In conclusion, the finDr virtual screening strategy and the molecular interaction identification method employed in this study provide a robust technical approach for the rapid and efficient acquisition of high-affinity binding peptides for target proteins of interest.

Molecular Modelling in Bioactive Peptide Discovery and Characterisation

Molecular modelling is a vital tool in the discovery and characterisation of bioactive peptides, providing insights into their structural properties and interactions with biological targets. Many models predicting bioactive peptide function or structure rely on their intrinsic properties, including the influence of amino acid composition, sequence, and chain length, which impact stability, folding, aggregation, and target interaction. Homology modelling predicts peptide structures based on known templates. Peptide-protein interactions can be explored using molecular docking techniques, but there are challenges related to the inherent flexibility of peptides, which can be addressed by more computationally intensive approaches that consider their movement over time, called molecular dynamics (MD). Virtual screening of many peptides, usually against a single target, enables rapid identification of potential bioactive peptides from large libraries, typically using docking approaches. The integration of artificial intelligence (AI) has transformed peptide discovery by leveraging large amounts of data. AlphaFold is a general protein structure prediction tool based on deep learning that has greatly improved the predictions of peptide conformations and interactions, in addition to providing estimates of model accuracy at each residue which greatly guide interpretation. Peptide function and structure prediction are being further enhanced using Protein Language Models (PLMs), which are large deep-learning-derived statistical models that learn computer representations useful to identify fundamental patterns of proteins. Recent methodological developments are discussed in the context of canonical peptides, as well as those with modifications and cyclisations. In designing potential peptide therapeutics, the main outstanding challenge for these methods is the incorporation of diverse non-canonical amino acids and cyclisations.

Ensemble learning based on bi-directional gated recurrent unit and convolutional neural network with word embedding module for bioactive peptide prediction

Bioactive peptides, as small protein fragments, are essential mediators of diverse physiological activities, such as antimicrobial, anti-inflammatory, anticancer, antioxidant, and immunomodulatory functions. Despite their substantial potential in pharmaceuticals and the food industry, conventional methods for peptide classification and activity prediction are limited by high costs, time-intensive procedures, and extensive data processing requirements. Here, we present BioPepPred-DLEmb, a novel computational model integrating Convolutional Neural Networks (CNNs) and Bidirectional Gated Recurrent Units (BiGRUs), augmented with natural language processing to encode amino acids into information-dense vectors. Evaluated across nine bioactive peptide datasets, BioPepPred-DLEmb demonstrates superior predictive accuracy (0.909) and sensitivity (0.911) compared to traditional methods. Through UMAP visualization and Kplogo analysis, the model effectively differentiates peptide activity states and identifies key biomarkers. The predicted antimicrobial peptides (Pred-AMPs) exhibit potent efficacy in vitro, achieving low micromolar inhibitory concentrations (2-16 μmol/L) against pathogens such as Escherichia coli and Acinetobacter baumannii. These findings establish a robust foundation for bioactive peptide development, with implications for advancements in precision medicine, personalized therapies, and functional food innovations.

Advance in peptide-based drug development: delivery platforms, therapeutics and vaccines

The successful approval of peptide-based drugs can be attributed to a collaborative effort across multiple disciplines. The integration of novel drug design and synthesis techniques, display library technology, delivery systems, bioengineering advancements, and artificial intelligence have significantly expedited the development of groundbreaking peptide-based drugs, effectively addressing the obstacles associated with their character, such as the rapid clearance and degradation, necessitating subcutaneous injection leading to increasing patient discomfort, and ultimately advancing translational research efforts. Peptides are presently employed in the management and diagnosis of a diverse array of medical conditions, such as diabetes mellitus, weight loss, oncology, and rare diseases, and are additionally garnering interest in facilitating targeted drug delivery platforms and the advancement of peptide-based vaccines. This paper provides an overview of the present market and clinical trial progress of peptide-based therapeutics, delivery platforms, and vaccines. It examines the key areas of research in peptide-based drug development through a literature analysis and emphasizes the structural modification principles of peptide-based drugs, as well as the recent advancements in screening, design, and delivery technologies. The accelerated advancement in the development of novel peptide-based therapeutics, including peptide-drug complexes, new peptide-based vaccines, and innovative peptide-based diagnostic reagents, has the potential to promote the era of precise customization of disease therapeutic schedule.

Single amino acid substitution analogs of marine antioxidant peptides with membrane permeability exert a marked protective effect against ultraviolet-B induced damage

Ultraviolet-B (UVB) causes oxidative stress, which is implicated in skin damage and photoaging. Antioxidant peptides exhibit protective effects against UVB-induced oxidative stress and are thus regarded as potential competitors compared to synthetic antioxidants for cosmetics. In the present study, we provided a discovery pipeline for screening and modifying marine-derived antioxidant peptides, and successfully identified and characterized three novel modified peptides (WP5, LW5 and YY6) with strong antioxidant abilities. Their scavenging activities on 2,2'-azinobis-(3-ethylbenzthiazoline-6-sulphonate) radical (ABTS·) and hydroxyl radical (·OH) were higher than those of glutathione (GSH) (ABTS·: 71.12 ± 3.58 %, 67.63 ± 1.65 % and 68.51 ± 0.54 % by WP5, LW5 and YY6, respectively, vs 61.51 ± 1.02 % by GSH; ·OH: 52.15 ± 1.99 %, 51.25 ± 1.29 % and 53.06 ± 2.23 % by WP5, LW5 and YY6, respectively, vs 42.69 ± 1.18 % by GSH). The modified peptides can effectively penetrate cell membrane and significantly enhance cell viability against UVB-induced oxidative stress in human keratinocyte (HaCaT) cells by reducing the levels of reactive oxygen species and malondialdehyde and increasing the activity of intracellular antioxidant enzymes, including superoxide dismutase and glutathione peroxidase. Additionally, the modified peptides decreased the expression of tumor necrosis factor-α, interleukin-6 and interleukin-1β in UVB-induced cell inflammatory response, exhibiting a potent anti-inflammatory activity. Further investigation into the molecular mechanism revealed that the modified peptides not only decreased cell apoptosis by down-regulating the apoptosis factors Bax/Bcl-2 and c-PARP, but also increased the antioxidant capacity of HaCaT cells by interrupting the interaction between Kelch-like ECH associated protein 1 (Keap1) and nuclear factor erythroid 2-related factor 2 (Nrf2), and ultimately promoting Nrf2 activation. The findings suggest a promising strategy for accelerating the discovery of antioxidant peptides and cell-penetrating peptides, providing valuable insights for pharmaceutical and cosmetic industries.

Advances of deep Neural Networks (DNNs) in the development of peptide drugs

Peptides are able to bind to difficult disease targets with high potency and specificity, providing great opportunities to meet unmet medical requirements. Nevertheless, the unique features of peptides, such as their small size, high structural flexibility, and scarce data availability, bring extra challenges to the design process. Firstly, this review sums up the application of peptide drugs in treating diseases. Then, the review probes into the advantages of Deep Neural Networks (DNNs) in predicting and designing peptide structures. DNNs have demonstrated remarkable capabilities in structural prediction, enabling accurate three-dimensional modeling of peptide drugs through models like AlphaFold and its successors. Finally, the review deliberates on the challenges and coping strategies of DNNs in the development of peptide drugs, along with future research directions. Future research directions focus on further improving the accuracy and efficiency of DNN-based peptide drug design, exploring novel applications of peptide drugs, and accelerating their clinical translation. With continuous advancements in technology and data accumulation, DNNs are poised to play an increasingly crucial role in the field of peptide drug development.

A review on the screening methods for the discovery of natural antimicrobial peptides

Natural antimicrobial peptides (AMPs) are promising candidates for the development of a new generation of antimicrobials to combat antibiotic-resistant pathogens. They have found extensive applications in the fields of medicine, food, and agriculture. However, efficiently screening AMPs from natural sources poses several challenges, including low efficiency and high antibiotic resistance. This review focuses on the action mechanisms of AMPs, both through membrane and non-membrane routes. We thoroughly examine various highly efficient AMP screening methods, including whole-bacterial adsorption binding, cell membrane chromatography (CMC), phospholipid membrane chromatography binding, membrane-mediated capillary electrophoresis (CE), colorimetric assays, thin layer chromatography (TLC), fluorescence-based screening, genetic sequencing-based analysis, computational mining of AMP databases, and virtual screening methods. Additionally, we discuss potential developmental applications for enhancing the efficiency of AMP discovery. This review provides a comprehensive framework for identifying AMPs within complex natural product systems.

Therapeutic peptide development revolutionized: Harnessing the power of artificial intelligence for drug discovery

Due to the spread of antibiotic resistance, global attention is focused on its inhibition and the expansion of effective medicinal compounds. The novel functional properties of peptides have opened up new horizons in personalized medicine. With artificial intelligence methods combined with therapeutic peptide products, pharmaceuticals and biotechnology advance drug development rapidly and reduce costs. Short-chain peptides inhibit a wide range of pathogens and have great potential for targeting diseases. To address the challenges of synthesis and sustainability, artificial intelligence methods, namely machine learning, must be integrated into their production. Learning methods can use complicated computations to select the active and toxic compounds of the drug and its metabolic activity. Through this comprehensive review, we investigated the artificial intelligence method as a potential tool for finding peptide-based drugs and providing a more accurate analysis of peptides through the introduction of predictable databases for effective selection and development.

TG-CDDPM: text-guided antimicrobial peptides generation based on conditional denoising diffusion probabilistic model

Antimicrobial peptides (AMPs) have emerged as a promising substitution to antibiotics thanks to their boarder range of activities, less likelihood of drug resistance, and low toxicity. Traditional biochemical methods for AMP discovery are costly and inefficient. Deep generative models, including the long-short term memory model, variational autoencoder model, and generative adversarial model, have been widely introduced to expedite AMP discovery. However, these models tend to suffer from the lack of diversity in generating AMPs. The denoising diffusion probabilistic model serves as a good candidate for solving this issue. We proposed a three-stage Text-Guided Conditional Denoising Diffusion Probabilistic Model (TG-CDDPM) to generate novel and homologous AMPs. In the first two stages, contrastive learning and inferring models are crafted to create better conditions for guiding AMP generation, respectively. In the last stage, a pre-trained conditional denoising diffusion probabilistic model is leveraged to enrich the peptide knowledge and fine-tuned to learn feature representation in downstream. TG-CDDPM was compared to the state-of-the-art generative models for AMP generation, and it demonstrated competitive or better performance with the assistance of text description as supervised information. The membrane penetration capabilities of the identified candidate AMPs by TG-CDDPM were also validated through molecular weight dynamics experiments.

Molecular hybridization modification improves the stability and immunomodulatory activity of TP5 peptide

Thymopentin (TP5) plays an important role in host immunomodulation, yet its bioavailability is significantly limited by its short half-life. YW12D is a peptide with strong stability but relatively weak immunoactivity. Tuning the physicochemical properties of such molecules may yield synthetic molecules displaying optimal stability, safety and enhanced immunological activity. Here, natural peptides were modified to improve their activity by hybridization strategies. A hybrid peptide YW12D-TP5 (YTP) that combines TP5 and YW12D is designed. The half-life of YTP in plasma is significantly longer than that of YW12D and TP5. YTP also displays an improved ability to protect the host from CTX-induced weight loss and thymus and spleen indices decrease than YW12D and TP5. In addition, YTP promotes dendritic cell maturation and increases the expression of cytokines IL-1β, IL-6, TNF-α and immunoglobulins IgA, IgG, and IgM. A combination of antibody-specific blocking assay, SPR, molecular dynamics simulations and western blotting suggest that the immunomodulatory effect of YTP is associated with its activation of the TLR2-NF-кB signaling axis. In sum, we demonstrate that peptide hybridization is an effective strategy for redirecting biological activity to generate novel bioactive molecules with desired properties.

Discovery of Highly Bioactive Peptides through Hierarchical Structural Information and Molecular Dynamics Simulations

Peptide drugs play an essential role in modern therapeutics, but the computational design of these molecules is hindered by several challenges. Traditional methods like molecular docking and molecular dynamics (MD) simulation, as well as recent deep learning approaches, often face limitations related to computational resource demands, complex binding affinity assessments, extensive data requirements, and poor model interpretability. Here, we introduce PepHiRe, an innovative methodology that utilizes the hierarchical structural information in peptide sequences and employs a novel strategy called Ladderpath, rooted in algorithmic information theory, to rapidly generate and enhance the efficiency and clarity of novel peptide design. We applied PepHiRe to develop BH3-like peptide inhibitors targeting myeloid cell leukemia-1, a protein associated with various cancers. By analyzing just eight known bioactive BH3 peptide sequences, PepHiRe effectively derived a hierarchy of subsequences used to create new BH3-like peptides. These peptides underwent screening through MD simulations, leading to the selection of five candidates for synthesis and subsequent in vitro testing. Experimental results demonstrated that these five peptides possess high inhibitory activity, with IC50 values ranging from 28.13 ± 7.93 to 167.42 ± 22.15 nM. Our study explores a white-box model driven technique and a structured screening pipeline for identifying and generating novel peptides with potential bioactivity.

Generative β-hairpin design using a residue-based physicochemical property landscape

De novo peptide design is a new frontier that has broad application potential in the biological and biomedical fields. Most existing models for de novo peptide design are largely based on sequence homology that can be restricted based on evolutionarily derived protein sequences and lack the physicochemical context essential in protein folding. Generative machine learning for de novo peptide design is a promising way to synthesize theoretical data that are based on, but unique from, the observable universe. In this study, we created and tested a custom peptide generative adversarial network intended to design peptide sequences that can fold into the β-hairpin secondary structure. This deep neural network model is designed to establish a preliminary foundation of the generative approach based on physicochemical and conformational properties of 20 canonical amino acids, for example, hydrophobicity and residue volume, using extant structure-specific sequence data from the PDB. The beta generative adversarial network model robustly distinguishes secondary structures of β hairpin from α helix and intrinsically disordered peptides with an accuracy of up to 96% and generates artificial β-hairpin peptide sequences with minimum sequence identities around 31% and 50% when compared against the current NCBI PDB and nonredundant databases, respectively. These results highlight the potential of generative models specifically anchored by physicochemical and conformational property features of amino acids to expand the sequence-to-structure landscape of proteins beyond evolutionary limits.

Bibliometric analysis of artificial intelligence in healthcare research: Trends and future directions

Objective

The presence of artificial intelligence (AI) in healthcare is a powerful and game-changing force that is completely transforming the industry as a whole. Using sophisticated algorithms and data analytics, AI has unparalleled prospects for improving patient care, streamlining operational efficiency, and fostering innovation across the healthcare ecosystem. This study conducts a comprehensive bibliometric analysis of research on AI in healthcare, utilising the SCOPUS database as the primary data source.

Methods

Preliminary findings from 2013 identified 153 publications on AI and healthcare. Between 2019 and 2023, the number of publications increased exponentially, indicating significant growth and development in the field. The analysis employs various bibliometric indicators to assess research production performance, science mapping techniques, and thematic mapping analysis.

Results

The study reveals insights into research hotspots, thematic focus, and emerging trends in AI and healthcare research. Based on an extensive examination of the Scopus database provides a brief overview and suggests potential avenues for further investigation.

Conclusion

This article provides valuable contributions to understanding the current landscape of AI in healthcare, offering insights for future research directions and informing strategic decision making in the field.

Reinforcement learning-driven exploration of peptide space: accelerating generation of drug-like peptides

Using amino acid residues in peptide generation has solved several key problems, including precise control of amino acid sequence order, customized peptides for property modification, and large-scale peptide synthesis. Proteins contain unknown amino acid residues. Extracting them for the synthesis of drug-like peptides can create novel structures with unique properties, driving drug development. Computer-aided design of novel peptide drug molecules can solve the high-cost and low-efficiency problems in the traditional drug discovery process. Previous studies faced limitations in enhancing the bioactivity and drug-likeness of polypeptide drugs due to less emphasis on the connection relationships in amino acid structures. Thus, we proposed a reinforcement learning-driven generation model based on graph attention mechanisms for peptide generation. By harnessing the advantages of graph attention mechanisms, this model effectively captured the connectivity structures between amino acid residues in peptides. Simultaneously, leveraging reinforcement learning's strength in guiding optimal sequence searches provided a novel approach to peptide design and optimization. This model introduces an actor-critic framework with real-time feedback loops to achieve dynamic balance between attributes, which can customize the generation of multiple peptides for specific targets and enhance the affinity between peptides and targets. Experimental results demonstrate that the generated drug-like peptides meet specified absorption, distribution, metabolism, excretion, and toxicity properties and bioactivity with a success rate of over 90$\%$, thereby significantly accelerating the process of drug-like peptide generation.

Advancing Peptide-Based Cancer Therapy with AI: In-Depth Analysis of State-of-the-Art AI Models

Anticancer peptides (ACPs) play a vital role in selectively targeting and eliminating cancer cells. Evaluating and comparing predictions from various machine learning (ML) and deep learning (DL) techniques is challenging but crucial for anticancer drug research. We conducted a comprehensive analysis of 15 ML and 10 DL models, including the models released after 2022, and found that support vector machines (SVMs) with feature combination and selection significantly enhance overall performance. DL models, especially convolutional neural networks (CNNs) with light gradient boosting machine (LGBM) based feature selection approaches, demonstrate improved characterization. Assessment using a new test data set (ACP10) identifies ACPred, MLACP 2.0, AI4ACP, mACPred, and AntiCP2.0_AAC as successive optimal predictors, showcasing robust performance. Our review underscores current prediction tool limitations and advocates for an omnidirectional ACP prediction framework to propel ongoing research.

Machine Learning Accelerates De Novo Design of Antimicrobial Peptides

Efficient and precise design of antimicrobial peptides (AMPs) is of great importance in the field of AMP development. Computing provides opportunities for peptide de novo design. In the present investigation, a new machine learning-based AMP prediction model, AP_Sin, was trained using 1160 AMP sequences and 1160 non-AMP sequences. The results showed that AP_Sin correctly classified 94.61% of AMPs on a comprehensive dataset, outperforming the mainstream and open-source models (Antimicrobial Peptide Scanner vr.2, iAMPpred and AMPlify) and being effective in identifying AMPs. In addition, a peptide sequence generator, AP_Gen, was devised based on the concept of recombining dominant amino acids and dipeptide compositions. After inputting the parameters of the 71 tridecapeptides from antimicrobial peptides database (APD3) into AP_Gen, a tridecapeptide bank consisting of de novo designed 17,496 tridecapeptide sequences were randomly generated, from which 2675 candidate AMP sequences were identified by AP_Sin. Chemical synthesis was performed on 180 randomly selected candidate AMP sequences, of which 18 showed high antimicrobial activities against a wide range of the tested pathogenic microorganisms, and 16 of which had a minimal inhibitory concentration of less than 10 μg/mL against at least one of the tested pathogenic microorganisms. The method established in this research accelerates the discovery of valuable candidate AMPs and provides a novel approach for de novo design of antimicrobial peptides.

A deep learning based multi-model approach for predicting drug-like chemical compound's toxicity

Ensuring the safety and efficacy of chemical compounds is crucial in small-molecule drug development. In the later stages of drug development, toxic compounds pose a significant challenge, losing valuable resources and time. Early and accurate prediction of compound toxicity using deep learning models offers a promising solution to mitigate these risks during drug discovery. In this study, we present the development of several deep-learning models aimed at evaluating different types of compound toxicity, including acute toxicity, carcinogenicity, hERG_cardiotoxicity (the human ether-a-go-go related gene caused cardiotoxicity), hepatotoxicity, and mutagenicity. To address the inherent variations in data size, label type, and distribution across different types of toxicity, we employed diverse training strategies. Our first approach involved utilizing a graph convolutional network (GCN) regression model to predict acute toxicity, which achieved notable performance with Pearson R 0.76, 0.74, and 0.65 for intraperitoneal, intravenous, and oral administration routes, respectively. Furthermore, we trained multiple GCN binary classification models, each tailored to a specific type of toxicity. These models exhibited high area under the curve (AUC) scores, with an impressive AUC of 0.69, 0.77, 0.88, and 0.79 for predicting carcinogenicity, hERG_cardiotoxicity, mutagenicity, and hepatotoxicity, respectively. Additionally, we have used the approved drug dataset to determine the appropriate threshold value for the prediction score in model usage. We integrated these models into a virtual screening pipeline to assess their effectiveness in identifying potential low-toxicity drug candidates. Our findings indicate that this deep learning approach has the potential to significantly reduce the cost and risk associated with drug development by expediting the selection of compounds with low toxicity profiles. Therefore, the models developed in this study hold promise as critical tools for early drug candidate screening and selection.

Computational peptide discovery with a genetic programming approach

The development of peptides for therapeutic targets or biomarkers for disease diagnosis is a challenging task in protein engineering. Current approaches are tedious, often time-consuming and require complex laboratory data due to the vast search spaces that need to be considered. In silico methods can accelerate research and substantially reduce costs. Evolutionary algorithms are a promising approach for exploring large search spaces and can facilitate the discovery of new peptides. This study presents the development and use of a new variant of the genetic-programming-based POET algorithm, called POETRegex , where individuals are represented by a list of regular expressions. This algorithm was trained on a small curated dataset and employed to generate new peptides improving the sensitivity of peptides in magnetic resonance imaging with chemical exchange saturation transfer (CEST). The resulting model achieves a performance gain of 20% over the initial POET models and is able to predict a candidate peptide with a 58% performance increase compared to the gold-standard peptide. By combining the power of genetic programming with the flexibility of regular expressions, new peptide targets were identified that improve the sensitivity of detection by CEST. This approach provides a promising research direction for the efficient identification of peptides with therapeutic or diagnostic potential.

Deep learning for advancing peptide drug development: Tools and methods in structure prediction and design

Peptides can bind challenging disease targets with high affinity and specificity, offering enormous opportunities for addressing unmet medical needs. However, peptides' unique features, including smaller size, increased structural flexibility, and limited data availability, pose additional challenges to the design process compared to proteins. This review explores the dynamic field of peptide therapeutics, leveraging deep learning to enhance structure prediction and design. Our exploration encompasses various facets of peptide research, ranging from dataset curation handling to model development. As deep learning technologies become more refined, we channel our efforts into peptide structure prediction and design, aligning with the fundamental principles of structure-activity relationships in drug development. To guide researchers in harnessing the potential of deep learning to advance peptide drug development, our insights comprehensively explore current challenges and future directions of peptide therapeutics.

Exploring the Potential of Bioactive Peptides: From Natural Sources to Therapeutics

Bioactive peptides, specific protein fragments with positive health effects, are gaining traction in drug development for advantages like enhanced penetration, low toxicity, and rapid clearance. This comprehensive review navigates the intricate landscape of peptide science, covering discovery to functional characterization. Beginning with a peptidomic exploration of natural sources, the review emphasizes the search for novel peptides. Extraction approaches, including enzymatic hydrolysis, microbial fermentation, and specialized methods for disulfide-linked peptides, are extensively covered. Mass spectrometric analysis techniques for data acquisition and identification, such as liquid chromatography, capillary electrophoresis, untargeted peptide analysis, and bioinformatics, are thoroughly outlined. The exploration of peptide bioactivity incorporates various methodologies, from in vitro assays to in silico techniques, including advanced approaches like phage display and cell-based assays. The review also discusses the structure-activity relationship in the context of antimicrobial peptides (AMPs), ACE-inhibitory peptides (ACEs), and antioxidative peptides (AOPs). Concluding with key findings and future research directions, this interdisciplinary review serves as a comprehensive reference, offering a holistic understanding of peptides and their potential therapeutic applications.

Geometric deep learning as a potential tool for antimicrobial peptide prediction

Antimicrobial peptides (AMPs) are components of natural immunity against invading pathogens. They are polymers that fold into a variety of three-dimensional structures, enabling their function, with an underlying sequence that is best represented in a non-flat space. The structural data of AMPs exhibits non-Euclidean characteristics, which means that certain properties, e.g., differential manifolds, common system of coordinates, vector space structure, or translation-equivariance, along with basic operations like convolution, in non-Euclidean space are not distinctly established. Geometric deep learning (GDL) refers to a category of machine learning methods that utilize deep neural models to process and analyze data in non-Euclidean settings, such as graphs and manifolds. This emerging field seeks to expand the use of structured models to these domains. This review provides a detailed summary of the latest developments in designing and predicting AMPs utilizing GDL techniques and also discusses both current research gaps and future directions in the field.

DeepBindGCN: Integrating Molecular Vector Representation with Graph Convolutional Neural Networks for Protein-Ligand Interaction Prediction

The core of large-scale drug virtual screening is to select the binders accurately and efficiently with high affinity from large libraries of small molecules in which non-binders are usually dominant. The binding affinity is significantly influenced by the protein pocket, ligand spatial information, and residue types/atom types. Here, we used the pocket residues or ligand atoms as the nodes and constructed edges with the neighboring information to comprehensively represent the protein pocket or ligand information. Moreover, the model with pre-trained molecular vectors performed better than the one-hot representation. The main advantage of DeepBindGCN is that it is independent of docking conformation, and concisely keeps the spatial information and physical-chemical features. Using TIPE3 and PD-L1 dimer as proof-of-concept examples, we proposed a screening pipeline integrating DeepBindGCN and other methods to identify strong-binding-affinity compounds. It is the first time a non-complex-dependent model has achieved a root mean square error (RMSE) value of 1.4190 and Pearson r value of 0.7584 in the PDBbind v.2016 core set, respectively, thereby showing a comparable prediction power with the state-of-the-art affinity prediction models that rely upon the 3D complex. DeepBindGCN provides a powerful tool to predict the protein-ligand interaction and can be used in many important large-scale virtual screening application scenarios.