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

Interpretable molecular encodings and representations for machine learning tasks

Molecular encodings and their usage in machine learning models have demonstrated significant breakthroughs in biomedical applications, particularly in the classification of peptides and proteins. To this end, we propose a new encoding method: Interpretable Carbon-based Array of Neighborhoods (iCAN). Designed to address machine learning models' need for more structured and less flexible input, it captures the neighborhoods of carbon atoms in a counting array and improves the utility of the resulting encodings for machine learning models. The iCAN method provides interpretable molecular encodings and representations, enabling the comparison of molecular neighborhoods, identification of repeating patterns, and visualization of relevance heat maps for a given data set. When reproducing a large biomedical peptide classification study, it outperforms its predecessor encoding. When extended to proteins, it outperforms a lead structure-based encoding on 71% of the data sets. Our method offers interpretable encodings that can be applied to all organic molecules, including exotic amino acids, cyclic peptides, and larger proteins, making it highly versatile across various domains and data sets. This work establishes a promising new direction for machine learning in peptide and protein classification in biomedicine and healthcare, potentially accelerating advances in drug discovery and disease diagnosis.

Structural and Biochemical Characterization of Three Antimicrobial Peptides from Capsicum annuum L. var. annuum Leaves for Anti-Candida Use

The emergence of resistant microorganisms has reduced the effectiveness of currently available antimicrobials, necessitating the development of new strategies. Plant antimicrobial peptides (AMPs) are promising candidates for novel drug development. In this study, we aimed to isolate, characterize, and evaluate the antimicrobial activities of AMPs isolated from Capsicum annuum. The antifungal potential was tested against Candida species. Three AMPs from C. annuum leaves were isolated and characterized: a protease inhibitor, a defensin-like protein, and a lipid transporter protein, respectively named CaCPin-II, CaCDef-like, and CaCLTP2. All three peptides had a molecular mass between 3.5 and 6.5 kDa and caused morphological and physiological changes in four different species of the genus Candida, such as pseudohyphae formation, cell swelling and agglutination, growth inhibition, reduced cell viability, oxidative stress, membrane permeabilization, and metacaspase activation. Except for CaCPin-II, the peptides showed low or no hemolytic activity at the concentrations used in the yeast assays. CaCPin-II inhibited α-amylase activity. Together, these results suggest that these peptides have the potential as antimicrobial agents against species of the genus Candida and can serve as scaffolds for the development of synthetic peptides for this purpose.

An active machine learning discovery platform for membrane-disrupting and pore-forming peptides

Membrane-disrupting and pore-forming peptides (PFPs) play a substantial role in bionanotechnology and can determine the life and death of cells. The control of chemical and ion transport through cell membranes is essential to maintaining concentration gradients. Likewise, the delivery of drugs and intracellular proteins aided by pore-forming agents is of interest in treating malfunctioning cells. Known PFPs tend to be up to 50 residues in length, which is commensurate with the thickness of a lipid bilayer. Accordingly, few short PFPs are known. Here we show that the discovery of PFPs can be accelerated via an active machine learning approach. The approach identified 71 potential PFPs from the 25.6 billion octapeptide sequence space; 13 sequences were tested experimentally, and all were found to have the predicted membrane-disrupting ability, with 1 forming highly stable pores. Experimental verification of the predicted pore-forming ability demonstrated that a range of short peptides can form pores in membranes, while the positioning and characteristics of residues that favour pore-forming behaviour were identified. This approach identified more ultrashort (8-residues, unmodified, non-cyclic) PFPs than previously known. We anticipate our findings and methodology will be useful in discovering new pore-forming and membrane-disrupting peptides for a range of applications from nanoreactors to therapeutics.

TriplEP-CPP: Algorithm for Predicting the Properties of Peptide Sequences

Advancements in medicine and pharmacology have led to the development of systems that deliver biologically active molecules inside cells, increasing drug concentrations at target sites. This improves effectiveness and duration of action and reduces side effects on healthy tissues. Cell-penetrating peptides (CPPs) show promise in this area. While traditional medicinal chemistry methods have been used to develop CPPs, machine learning techniques can speed up and reduce costs in the search for new peptides. A predictive algorithm based on machine learning models was created to identify novel CPP sequences using molecular descriptors using a combination of algorithms like k-nearest neighbors, gradient boosting, and random forest. Some potential CPPs were found and tested for cytotoxicity and penetrating ability. A new low-toxicity CPP was discovered from the Rhopilema esculentum venom proteome through this study.

Peptide-based drug discovery through artificial intelligence: towards an autonomous design of therapeutic peptides

With their diverse biological activities, peptides are promising candidates for therapeutic applications, showing antimicrobial, antitumour and hormonal signalling capabilities. Despite their advantages, therapeutic peptides face challenges such as short half-life, limited oral bioavailability and susceptibility to plasma degradation. The rise of computational tools and artificial intelligence (AI) in peptide research has spurred the development of advanced methodologies and databases that are pivotal in the exploration of these complex macromolecules. This perspective delves into integrating AI in peptide development, encompassing classifier methods, predictive systems and the avant-garde design facilitated by deep-generative models like generative adversarial networks and variational autoencoders. There are still challenges, such as the need for processing optimization and careful validation of predictive models. This work outlines traditional strategies for machine learning model construction and training techniques and proposes a comprehensive AI-assisted peptide design and validation pipeline. The evolving landscape of peptide design using AI is emphasized, showcasing the practicality of these methods in expediting the development and discovery of novel peptides within the context of peptide-based drug discovery.

Uptake pathways of cell-penetrating peptides in the context of drug delivery, gene therapy, and vaccine development

Cell-penetrating peptides have been extensively utilized for the purpose of facilitating the intracellular delivery of cargo that is impermeable to the cell membrane. The researchers have exhibited proficient delivery capabilities for oligonucleotides, thereby establishing cell-penetrating peptides as a potent instrument in the field of gene therapy. Furthermore, they have demonstrated a high level of efficiency in delivering several additional payloads. Cell penetrating peptides (CPPs) possess the capability to efficiently transport therapeutic molecules to specific cells, hence offering potential remedies for many illnesses. Hence, their utilization is imperative for the improvement of therapeutic vaccines. In contemporary studies, a plethora of cell-penetrating peptides have been unveiled, each characterized by its own distinct structural attributes and associated mechanisms. Although it is widely acknowledged that there are multiple pathways through which particles might be internalized, a comprehensive understanding of the specific mechanisms by which these particles enter cells has to be fully elucidated. The absorption of cell-penetrating peptides can occur through either direct translocation or endocytosis. However, it is worth noting that categories of cell-penetrating peptides are not commonly linked to specific entrance mechanisms. Furthermore, research has demonstrated that cell-penetrating peptides (CPPs) possess the capacity to enhance antigen uptake by cells and facilitate the traversal of various biological barriers. The primary objective of this work is to examine the mechanisms by which cell-penetrating peptides are internalized by cells and their significance in facilitating the administration of drugs, particularly in the context of gene therapy and vaccine development. The current study investigates the immunostimulatory properties of numerous vaccine components administered using different cell-penetrating peptides (CPPs). This study encompassed a comprehensive discussion on various topics, including the uptake pathways and mechanisms of cell-penetrating peptides (CPPs), the utilization of CPPs as innovative vectors for gene therapy, the role of CPPs in vaccine development, and the potential of CPPs for antigen delivery in the context of vaccine development.

POSEIDON: Peptidic Objects SEquence-based Interaction with cellular DOmaiNs: a new database and predictor

Cell-penetrating peptides (CPPs) are short chains of amino acids that have shown remarkable potential to cross the cell membrane and deliver coupled therapeutic cargoes into cells. Designing and testing different CPPs to target specific cells or tissues is crucial to ensure high delivery efficiency and reduced toxicity. However, in vivo/in vitro testing of various CPPs can be both time-consuming and costly, which has led to interest in computational methodologies, such as Machine Learning (ML) approaches, as faster and cheaper methods for CPP design and uptake prediction. However, most ML models developed to date focus on classification rather than regression techniques, because of the lack of informative quantitative uptake values. To address these challenges, we developed POSEIDON, an open-access and up-to-date curated database that provides experimental quantitative uptake values for over 2,300 entries and physicochemical properties of 1,315 peptides. POSEIDON also offers physicochemical properties, such as cell line, cargo, and sequence, among others. By leveraging this database along with cell line genomic features, we processed a dataset of over 1,200 entries to develop an ML regression CPP uptake predictor. Our results demonstrated that POSEIDON accurately predicted peptide cell line uptake, achieving a Pearson correlation of 0.87, Spearman correlation of 0.88, and r2 score of 0.76, on an independent test set. With its comprehensive and novel dataset, along with its potent predictive capabilities, the POSEIDON database and its associated ML predictor signify a significant leap forward in CPP research and development. The POSEIDON database and ML Predictor are available for free and with a user-friendly interface at https://moreiralab.com/resources/poseidon/ , making them valuable resources for advancing research on CPP-related topics. Scientific Contribution Statement: Our research addresses the critical need for more efficient and cost-effective methodologies in Cell-Penetrating Peptide (CPP) research. We introduced POSEIDON, a comprehensive and freely accessible database that delivers quantitative uptake values for over 2,300 entries, along with detailed physicochemical profiles for 1,315 peptides. Recognizing the limitations of current Machine Learning (ML) models for CPP design, our work leveraged the rich dataset provided by POSEIDON to develop a highly accurate ML regression model for predicting CPP uptake.

Immunomodulatory Peptides as Vaccine Adjuvants and Antimicrobial Agents

The underdevelopment of adjuvant discovery and diversity, compared to core vaccine technology, is evident. On the other hand, antibiotic resistance is on the list of the top ten threats to global health. Immunomodulatory peptides that target a pathogen and modulate the immune system simultaneously are promising for the development of preventive and therapeutic molecules. Since investigating innate immunity in insects has led to prominent achievements in human immunology, such as toll-like receptor (TLR) discovery, we used the capacity of the immunomodulatory peptides of arthropods with concomitant antimicrobial or antitumor activity. An SVM-based machine learning classifier identified short immunomodulatory sequences encrypted in 643 antimicrobial peptides from 55 foe-to-friend arthropods. The critical features involved in efficacy and safety were calculated. Finally, 76 safe immunomodulators were identified. Then, molecular docking and simulation studies defined the target of the most optimal peptide ligands among all human cell-surface TLRs. SPalf2-453 from a crab is a cell-penetrating immunoadjuvant with antiviral properties. The peptide interacts with the TLR1/2 heterodimer. SBsib-711 from a blackfly is a TLR4/MD2 ligand used as a cancer vaccine immunoadjuvant. In addition, SBsib-711 binds CD47 and PD-L1 on tumor cells, which is applicable in cancer immunotherapy as a checkpoint inhibitor. MRh4-679 from a shrimp is a broad-spectrum or universal immunoadjuvant with a putative Th1/Th2-balanced response. We also implemented a pathway enrichment analysis to define fingerprints or immunological signatures for further in vitro and in vivo immunogenicity and reactogenicity measurements. Conclusively, combinatorial machine learning, molecular docking, and simulation studies, as well as systems biology, open a new opportunity for the discovery and development of multifunctional prophylactic and therapeutic lead peptides.

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).

Designing Cell Delivery Peptides and SARS-CoV-2-Targeting Small Interfering RNAs: A Comprehensive Bioinformatics Study with Generative Adversarial Network-Based Peptide Design and In Vitro Assays

Nucleic acid technologies with designed intracellular delivery systems are some of the most promising therapies of the future. Small interfering (si)RNAs inhibit gene expression and protein synthesis and may complement current vaccines with faster design and production. Although successful delivery remains an issue, delivery peptides may help to fill this gap. Here, we address this issue by applying bioinformatic approaches to design new putative cell delivery peptides and siRNAs for COVID-19 variants and other related viral diseases. Of the 29,880 RNA sequences analyzed, 62 were identified in silico as able to target the virus mRNA sequence, and from the 9,984 peptide sequences analyzed, 10 were selected as delivery peptides. From the latter, we further performed in vitro studies of the two best-ranked peptides and compared them with the broadly used TAT delivery peptide. One of them, seq5, displayed better internalization results with about double intensity signal compared to TAT after a 1 h incubation time in GFP-HeLa cells. This peptide has, thus, the features of a delivery peptide and could be used for cargo intracellular delivery.

Purification and characterization of a novel immunoregulatory peptide from Sipunculus nudus L. protein

This study aimed to purify and characterize immunoregulatory peptides from Sipunculus nudus L. and to explore the underlying mechanisms. Ultrafiltration, gel filtration chromatography, and reverse phase high-performance liquid chromatography (RP-HPLC) were used to purify the peptide following enzymatic hydrolysis. Rates of lymphocyte proliferation and phagocytosis as well as nitric oxide (NO) production levels were used as indicators of immunoregulatory activity to screen the fractions. The amino acid sequence of the peptide, designated as SNLP, was identified as Arg-Val-Lys-Gly-Lys-Ile-Leu-Ala-Lys-Arg-Leu-Asn (RVKGKILAKRLN) by liquid chromatography-tandem mass spectrometry (LC-MS/MS). Treatment with the synthetic SNLP increased the proliferation and phagocytosis of RAW 264.7 macrophages and promoted the secretion of tumor necrosis factor-ɑ (TNF-α), interleukin-6 (IL-6), interleukin-1β (IL-1β), and NO levels. The mRNA levels of these cytokines and iNOS were also increased by SNLP. Our results provide preliminary evidence suggesting that SNLP acts as a dual immunomodulatory peptide with immunostimulatory and anti-inflammatory activities. In summary, SNLP derived from Sipunculus nudus L. is a potent immunoregulatory peptide and represents a potential functional food or immunoregulatory drug.

Artificial intelligence: Machine learning approach for screening large database and drug discovery

Recent research in drug discovery dealing with many faces difficulties, including development of new drugs during disease outbreak and drug resistance due to rapidly accumulating mutations. Virtual screening is the most widely used method in computer aided drug discovery. It has a prominent ability in screening drug targets from large molecular databases. Recently, a number of web servers have developed for quickly screening publicly accessible chemical databases. In a nutshell, deep learning algorithms and artificial neural networks have modernised the field. Several drug discovery processes have used machine learning and deep learning algorithms, including peptide synthesis, structure-based virtual screening, ligand-based virtual screening, toxicity prediction, drug monitoring and release, pharmacophore modelling, quantitative structure-activity relationship, drug repositioning, polypharmacology, and physiochemical activity. Although there are presently a wide variety of data-driven AI/ML tools available, the majority of these tools have, up to this point, been developed in the context of non-communicable diseases like cancer, and a number of obstacles have prevented the translation of these tools to the discovery of treatments against infectious diseases. In this review various aspects of AI and ML in virtual screening of large databases were discussed. Here, with an emphasis on antivirals as well as other disease, offers a perspective on the advantages, drawbacks, and hazards of AI/ML techniques in the search for innovative treatments.

Design and characterization of a novel tumor-homing cell-penetrating peptide for drug delivery in TGFBR3 high-expressing tumors

Targeted therapy has attracted more and more attention in cancer treatment in recent years. However, due to the diversity of tumor types and the mutation of target sites on the tumor surface, some existing targets are no longer suitable for tumor therapy. In addition, the long-term administration of a single targeted drug can also lead to drug resistance and attenuate drug potency, so it is important to develop new targets for tumor therapy. The expression of Type III transforming growth factor β receptor (TGFBR3) is upregulated in colon, breast, and prostate cancer cells, and plays an important role in the occurrence and development of these cancers, so TGFBR3 may be developed as a novel target for tumor therapy, but so far there is no report on this research. In this study, the structure of bone morphogenetic protein 4 (BMP4), one of the ligands of TGFBR3 was analyzed through the docking analysis with TGFBR3 and sequence charge characteristic analysis, and a functional tumor-targeting penetrating peptide T3BP was identified. The results of fluorescent labeling experiments showed that T3BP could target and efficiently enter tumor cells with high expression of TGFBR3, especially A549 cells. When the expression of TGFBR3 on the surface of tumor cells (HeLa) was knocked down by RNA interference, the high delivery efficiency of T3BP was correspondingly reduced by 40%, indicating that the delivery was TGFBR3-dependent. Trichosanthin (TCS, a plant-derived ribosome inactivating protein) fused with T3BP can enhance the inhibitory activity of the fusion protein on A549 cells by more than 200 times that of TCS alone. These results indicated that T3BP, as a novel targeting peptide that can efficiently bind TGFBR3 and be used for targeted therapy of tumors with high expression of TGFBR3. This study enriches the supply of tumor-targeting peptides and provides a new potential application option for the treatment of tumors with high expression of TGFBR3.

Cell-penetrating peptides predictors: A comparative analysis of methods and datasets

Cell-Penetrating Peptides (CPP) are emerging as an alternative to small-molecule drugs to expand the range of biomolecules that can be targeted for therapeutic purposes. Due to the importance of identifying and designing new CPP, a great variety of predictors have been developed to achieve these goals. To establish a ranking for these predictors, a couple of recent studies compared their performances on specific datasets, yet their conclusions cannot determine if the ranking obtained is due to the model, the set of descriptors or the datasets used to test the predictors. We present a systematic study of the influence of the peptide sequence's similarity of the datasets on the predictors' performance. The analysis reveals that the datasets used for training have a stronger influence on the predictors performance than the model or descriptors employed. We show that datasets with low sequence similarity between the positive and negative examples can be easily separated, and the tested classifiers showed good performance on them. On the other hand, a dataset with high sequence similarity between CPP and non-CPP will be a hard dataset, and it should be the one to be used for assessing the performance of new predictors.

A prediction model for blood-brain barrier penetrating peptides based on masked peptide transformers with dynamic routing

Blood-brain barrier penetrating peptides (BBBPs) are short peptide sequences that possess the ability to traverse the selective blood-brain interface, making them valuable drug candidates or carriers for various payloads. However, the in vivo or in vitro validation of BBBPs is resource-intensive and time-consuming, driving the need for accurate in silico prediction methods. Unfortunately, the scarcity of experimentally validated BBBPs hinders the efficacy of current machine-learning approaches in generating reliable predictions. In this paper, we present DeepB3P3, a novel framework for BBBPs prediction. Our contribution encompasses four key aspects. Firstly, we propose a novel deep learning model consisting of a transformer encoder layer, a convolutional network backbone, and a capsule network classification head. This integrated architecture effectively learns representative features from peptide sequences. Secondly, we introduce masked peptides as a powerful data augmentation technique to compensate for small training set sizes in BBBP prediction. Thirdly, we develop a novel threshold-tuning method to handle imbalanced data by approximating the optimal decision threshold using the training set. Lastly, DeepB3P3 provides an accurate estimation of the uncertainty level associated with each prediction. Through extensive experiments, we demonstrate that DeepB3P3 achieves state-of-the-art accuracy of up to 98.31% on a benchmarking dataset, solidifying its potential as a promising computational tool for the prediction and discovery of BBBPs.

Cell penetrating peptides: Highlighting points in cancer therapy

Cell-penetrating peptides (CPPs), first identified in HIV a few decades ago, deserved great attention in the last two decades; especially to support the penetration of anticancer drug means. In the drug delivery discipline, they have been involved in various approaches from mixing with hydrophobic drugs to the use of genetically conjugated proteins. The early classification as cationic and amphipathic CPPs has been extended to a few more classes such as hydrophobic and cyclic CPPs so far. Developing potential sequences utilized almost all methods of modern science: choosing high-efficiency peptides from natural protein sequences, sequence-based comparison, amino acid substitution, obtaining chemical and/or genetic conjugations, in silico approaches, in vitro analysis, animal experiments, etc. The bottleneck effect in this discipline reveals the complications that modern science faces in drug delivery research. Most CPP-based drug delivery systems (DDSs) efficiently inhibited tumor volume and weight in mice, but only in rare cases reduced their levels and continued further processes. The integration of chemical synthesis into the development of CPPs made a significant contribution and even reached the clinical stage as a diagnostic tool. But constrained efforts still face serious problems in overcoming biobarriers to reach further achievements. In this work, we reviewed the roles of CPPs in anticancer drug delivery, focusing on their amino acid composition and sequences. As the most suitable point, we relied on significant changes in tumor volume in mice resulting from CPPs. We provide a review of individual CPPs and/or their derivatives in a separate subsection.

AMP-EBiLSTM: employing novel deep learning strategies for the accurate prediction of antimicrobial peptides

Antimicrobial peptides are present ubiquitously in intra- and extra-biological environments and display considerable antibacterial and antifungal activities. Clinically, it has shown good antibacterial effect in the treatment of diabetic foot and its complications. However, the discovery and screening of antimicrobial peptides primarily rely on wet lab experiments, which are inefficient. This study endeavors to create a precise and efficient method of predicting antimicrobial peptides by incorporating novel machine learning technologies. We proposed a deep learning strategy named AMP-EBiLSTM to accurately predict them, and compared its performance with ensemble learning and baseline models. We utilized Binary Profile Feature (BPF) and Pseudo Amino Acid Composition (PSEAAC) for effective local sequence capture and amino acid information extraction, respectively, in deep learning and ensemble learning. Each model was cross-validated and externally tested independently. The results demonstrate that the Enhanced Bi-directional Long Short-Term Memory (EBiLSTM) deep learning model outperformed others with an accuracy of 92.39% and AUC value of 0.9771 on the test set. On the other hand, the ensemble learning models demonstrated cost-effectiveness in terms of training time on a T4 server equipped with 16 GB of GPU memory and 8 vCPUs, with training durations varying from 0 to 30 s. Therefore, the strategy we propose is expected to predict antimicrobial peptides more accurately in the future.

Delivery of Oleanolic Acid with Improved Antifibrosis Efficacy by a Cell Penetrating Peptide P10

Oleanolic acid (OA), a common pentacyclic triterpenoid found in plants, has several therapeutic uses, including the treatment of hepatopathy disorders. However, due to OA's weak permeability and limited bioavailability, its therapeutic advantages are limited. Here, we showed that a short peptide known as p10 not only binds to OA but also rapidly enhances OA delivery into cultured hepatic stellate cells (HSCs), lowers their synthesis of fibrogenic proteins, and further reduces the HSC migration capacity. Our findings show that noncovalently conjugating short peptides to OA improves its pharmacological efficacy and permeability.

In-Cell Penetration Selection-Mass Spectrometry Produces Noncanonical Peptides for Antisense Delivery

Peptide-mediated delivery of macromolecules in cells has significant potential therapeutic benefits, but no therapy employing cell-penetrating peptides (CPPs) has reached the market after 30 years of investigation due to challenges in the discovery of new, more efficient sequences. Here, we demonstrate a method for in-cell penetration selection-mass spectrometry (in-cell PS-MS) to discover peptides from a synthetic library capable of delivering macromolecule cargo to the cytosol. This method was inspired by recent in vivo selection approaches for cell-surface screening, with an added spatial dimension resulting from subcellular fractionation. A representative peptide discovered in the cytosolic extract, Cyto1a, is nearly 100-fold more active toward antisense phosphorodiamidate morpholino oligomer (PMO) delivery compared to a sequence identified from a whole cell extract, which includes endosomes. Cyto1a is composed of d-residues and two non-α-amino acids, is more stable than its all-l isoform, and is less toxic than known CPPs with comparable activity. Pulse-chase and microscopy experiments revealed that while the PMO-Cyto1a conjugate is likely taken up by endosomes, it can escape to localize to the nucleus without nonspecifically releasing other endosomal components. In-cell PS-MS introduces a means to empirically discover unnatural synthetic peptides for subcellular delivery of therapeutically relevant cargo.

Unsupervised encoding selection through ensemble pruning for biomedical classification

BACKGROUND

Owing to the rising levels of multi-resistant pathogens, antimicrobial peptides, an alternative strategy to classic antibiotics, got more attention. A crucial part is thereby the costly identification and validation. With the ever-growing amount of annotated peptides, researchers leverage artificial intelligence to circumvent the cumbersome, wet-lab-based identification and automate the detection of promising candidates. However, the prediction of a peptide's function is not limited to antimicrobial efficiency. To date, multiple studies successfully classified additional properties, e.g., antiviral or cell-penetrating effects. In this light, ensemble classifiers are employed aiming to further improve the prediction. Although we recently presented a workflow to significantly diminish the initial encoding choice, an entire unsupervised encoding selection, considering various machine learning models, is still lacking.

RESULTS

We developed a workflow, automatically selecting encodings and generating classifier ensembles by employing sophisticated pruning methods. We observed that the Pareto frontier pruning is a good method to create encoding ensembles for the datasets at hand. In addition, encodings combined with the Decision Tree classifier as the base model are often superior. However, our results also demonstrate that none of the ensemble building techniques is outstanding for all datasets.

CONCLUSION

The workflow conducts multiple pruning methods to evaluate ensemble classifiers composed from a wide range of peptide encodings and base models. Consequently, researchers can use the workflow for unsupervised encoding selection and ensemble creation. Ultimately, the extensible workflow can be used as a plugin for the PEPTIDE REACToR, further establishing it as a versatile tool in the domain.

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

Cell-penetrating peptides (CPPs) have great potential to deliver bioactive agents into cells. Although there have been many recent advances in CPP-related research, it is still important to develop more efficient CPPs. The development of CPPs by in silico methods is a very useful addition to experimental methods, but in many cases it can lead to a large number of false-positive results. In this study, we developed a deep-learning-based CPP prediction method, AiCPP, to develop novel CPPs. AiCPP uses a large number of peptide sequences derived from human-reference proteins as a negative set to reduce false-positive predictions and adopts a method to learn small-length peptide sequence motifs that may have CPP tendencies. Using AiCPP, we found that short peptide sequences derived from amyloid precursor proteins are efficient new CPPs, and experimentally confirmed that these CPP sequences can be further optimized.

Bacteriophage P22 Capsid as a Pluripotent Nanotechnology Tool

The Salmonella enterica bacteriophage P22 is one of the most promising models for the development of virus-like particle (VLP) nanocages. It possesses an icosahedral T = 7 capsid, assembled by the combination of two structural proteins: the coat protein (gp5) and the scaffold protein (gp8). The P22 capsid has the remarkable capability of undergoing structural transition into three morphologies with differing diameters and wall-pore sizes. These varied morphologies can be explored for the design of nanoplatforms, such as for the development of cargo internalization strategies. The capsid proteic nature allows for the extensive modification of its structure, enabling the addition of non-native structures to alter the VLP properties or confer them to diverse ends. Various molecules were added to the P22 VLP through genetic, chemical, and other means to both the capsid and the scaffold protein, permitting the encapsulation or the presentation of cargo. This allows the particle to be exploited for numerous purposes-for example, as a nanocarrier, nanoreactor, and vaccine model, among other applications. Therefore, the present review intends to give an overview of the literature on this amazing particle.

SiameseCPP: a sequence-based Siamese network to predict cell-penetrating peptides by contrastive learning

BACKGROUND

Cell-penetrating peptides (CPPs) have received considerable attention as a means of transporting pharmacologically active molecules into living cells without damaging the cell membrane, and thus hold great promise as future therapeutics. Recently, several machine learning-based algorithms have been proposed for predicting CPPs. However, most existing predictive methods do not consider the agreement (disagreement) between similar (dissimilar) CPPs and depend heavily on expert knowledge-based handcrafted features.

RESULTS

In this study, we present SiameseCPP, a novel deep learning framework for automated CPPs prediction. SiameseCPP learns discriminative representations of CPPs based on a well-pretrained model and a Siamese neural network consisting of a transformer and gated recurrent units. Contrastive learning is used for the first time to build a CPP predictive model. Comprehensive experiments demonstrate that our proposed SiameseCPP is superior to existing baseline models for predicting CPPs. Moreover, SiameseCPP also achieves good performance on other functional peptide datasets, exhibiting satisfactory generalization ability.

A systematic review on the state-of-the-art strategies for protein representation

The study of drug-target protein interaction is a key step in drug research. In recent years, machine learning techniques have become attractive for research, including drug research, due to their automated nature, predictive power, and expected efficiency. Protein representation is a key step in the study of drug-target protein interaction by machine learning, which plays a fundamental role in the ultimate accomplishment of accurate research. With the progress of machine learning, protein representation methods have gradually attracted attention and have consequently developed rapidly. Therefore, in this review, we systematically classify current protein representation methods, comprehensively review them, and discuss the latest advances of interest. According to the information extraction methods and information sources, these representation methods are generally divided into structure and sequence-based representation methods. Each primary class can be further divided into specific subcategories. As for the particular representation methods involve both traditional and the latest approaches. This review contains a comprehensive assessment of the various methods which researchers can use as a reference for their specific protein-related research requirements, including drug research.

Cell-Permeable PROTAC Degraders against KEAP1 Efficiently Suppress Hepatic Stellate Cell Activation through the Antioxidant and Anti-Inflammatory Pathway

Accumulating evidence indicates that oxidative stress and inflammation are involved in the physiopathology of liver fibrogenesis. Nuclear factor erythroid 2-related factor 2 (Nrf2) is a key transcription factor, which regulates the expression of redox regulators to establish cellular redox homeostasis. The Nrf2 modulator can serve as a primary cellular defense against the cytotoxic effects of oxidative stress. We designed a chimeric Keap1-Keap1 peptide (KKP1) based on the proteolysis-targeting chimera technology. The KKP1 peptide not only can efficiently penetrate into the rat hepatic stellate cell line (HSC-T6) cells but also can induce Keap1 protein degradation by the ubiquitination-proteasome degradation pathway, which releases Nrf2 and promotes the transcriptional activity of the Nrf2/antioxidant response element pathway. It then activates the protein expression of the downstream antioxidant factors, the glutamate-cysteine ligase catalytic subunit and heme oxygenase-1 (HO-1). Finally, Keap1 protein degradation inhibits the nuclear factor-kappaB inflammatory signal pathway, the downstream inflammatory factor tumor necrosis factor alpha, and the interleukin-1beta protein expression and further inhibits the expression of the fibrosis biomarker gene. The current research suggests that our designed KKP1 may provide a new avenue for the future treatment of liver fibrosis.

Polypharmacological Cell-Penetrating Peptides from Venomous Marine Animals Based on Immunomodulating, Antimicrobial, and Anticancer Properties

Complex pathological diseases, such as cancer, infection, and Alzheimer's, need to be targeted by multipronged curative. Various omics technologies, with a high rate of data generation, demand artificial intelligence to translate these data into druggable targets. In this study, 82 marine venomous animal species were retrieved, and 3505 cryptic cell-penetrating peptides (CPPs) were identified in their toxins. A total of 279 safe peptides were further analyzed for antimicrobial, anticancer, and immunomodulatory characteristics. Protease-resistant CPPs with endosomal-escape ability in Hydrophis hardwickii, nuclear-localizing peptides in Scorpaena plumieri, and mitochondrial-targeting peptides from Synanceia horrida were suitable for compartmental drug delivery. A broad-spectrum S. horrida-derived antimicrobial peptide with a high binding-affinity to bacterial membranes was an antigen-presenting cell (APC) stimulator that primes cytokine release and naïve T-cell maturation simultaneously. While antibiofilm and wound-healing peptides were detected in Synanceia verrucosa, APC epitopes as universal adjuvants for antiviral vaccination were in Pterois volitans and Conus monile. Conus pennaceus-derived anticancer peptides showed antiangiogenic and IL-2-inducing properties with moderate BBB-permeation and were defined to be a tumor-homing peptide (THP) with the ability to inhibit programmed death ligand-1 (PDL-1). Isoforms of RGD-containing peptides with innate antiangiogenic characteristics were in Conus tessulatus for tumor targeting. Inhibitors of neuropilin-1 in C. pennaceus are proposed for imaging probes or therapeutic delivery. A Conus betulinus cryptic peptide, with BBB-permeation, mitochondrial-targeting, and antioxidant capacity, was a stimulator of anti-inflammatory cytokines and non-inducer of proinflammation proposed for Alzheimer's. Conclusively, we have considered the dynamic interaction of cells, their microenvironment, and proportional-orchestrating-host- immune pathways by multi-target-directed CPPs resembling single-molecule polypharmacology. This strategy might fill the therapeutic gap in complex resistant disorders and increase the candidates' clinical-translation chance.

Could artificial intelligence revolutionize the development of nanovectors for gene therapy and mRNA vaccines?

Gene therapy enables the introduction of nucleic acids like DNA and RNA into host cells, and is expected to revolutionize the treatment of a wide range of diseases. This growth has been further accelerated by the discovery of CRISPR/Cas technology, which allows accurate genomic editing in a broad range of cells and organisms in vitro and in vivo. Despite many advances in gene delivery and the development of various viral and non-viral gene delivery vectors, the lack of highly efficient non-viral systems with low cellular toxicity remains a challenge. The application of cutting-edge technologies such as artificial intelligence (AI) has great potential to find new paradigms to solve this issue. Herein, we review AI and its major subfields including machine learning (ML), neural networks (NNs), expert systems, deep learning (DL), computer vision and robotics. We discuss the potential of AI-based models and algorithms in the design of targeted gene delivery vehicles capable of crossing extracellular and intracellular barriers by viral mimicry strategies. We finally discuss the role of AI in improving the function of CRISPR/Cas systems, developing novel nanobots, and mRNA vaccine carriers.

Disrupting Cu trafficking as a potential therapy for cancer

Copper ions play a crucial role in various cellular biological processes. However, these copper ions can also lead to toxicity when their concentration is not controlled by a sophisticated copper-trafficking system. Copper dys-homeostasis has been linked to a variety of diseases, including neurodegeneration and cancer. Therefore, manipulating Cu-trafficking to trigger selective cancer cell death may be a viable strategy with therapeutic benefit. By exploiting combined in silico and experimental strategies, we identified small peptides able to bind Atox1 and metal-binding domains 3-4 of ATP7B proteins. We found that these peptides reduced the proliferation of cancer cells owing to increased cellular copper ions concentration. These outcomes support the idea of harming copper trafficking as an opportunity for devising novel anti-cancer therapies.

Designed Multifunctional Peptides for Intracellular Targets

Nature’s way for bioactive peptides is to provide them with several related functions and the ability to cooperate in performing their job. Natural cell-penetrating peptides (CPP), such as penetratins, inspired the design of multifunctional constructs with CPP ability. This review focuses on known and novel peptides that can easily reach intracellular targets with little or no toxicity to mammalian cells. All peptide candidates were evaluated and ranked according to the predictions of low toxicity to mammalian cells and broad-spectrum activity. The final set of the 20 best peptide candidates contains the peptides optimized for cell-penetrating, antimicrobial, anticancer, antiviral, antifungal, and anti-inflammatory activity. Their predicted features are intrinsic disorder and the ability to acquire an amphipathic structure upon contact with membranes or nucleic acids. In conclusion, the review argues for exploring wide-spectrum multifunctionality for novel nontoxic hybrids with cell-penetrating peptides.

Antimicrobial peptides with cell-penetrating activity as prophylactic and treatment drugs

Health is fundamental for the development of individuals and evolution of species. In that sense, for human societies is relevant to understand how the human body has developed molecular strategies to maintain health. In the present review, we summarize diverse evidence that support the role of peptides in this endeavor. Of particular interest to the present review are antimicrobial peptides (AMP) and cell-penetrating peptides (CPP). Different experimental evidence indicates that AMP/CPP are able to regulate autophagy, which in turn regulates the immune system response. AMP also assists in the establishment of the microbiota, which in turn is critical for different behavioral and health aspects of humans. Thus, AMP and CPP are multifunctional peptides that regulate two aspects of our bodies that are fundamental to our health: autophagy and microbiota. While it is now clear the multifunctional nature of these peptides, we are still in the early stages of the development of computational strategies aimed to assist experimentalists in identifying selective multifunctional AMP/CPP to control nonhealthy conditions. For instance, both AMP and CPP are computationally characterized as amphipatic and cationic, yet none of these features are relevant to differentiate these peptides from non-AMP or non-CPP. The present review aims to highlight current knowledge that may facilitate the development of AMP’s design tools for preventing or treating illness.

DeepCPPred: A Deep Learning Framework for the Discrimination of Cell-Penetrating Peptides and Their Uptake Efficiencies

Cell-penetrating peptides (CPPs) are special peptides capable of carrying a variety of bioactive molecules, such as genetic materials, short interfering RNAs and nanoparticles, into cells. Recently, research on CPP has gained substantial interest from researchers, and the biological mechanisms of CPPS have been assessed in the context of safe drug delivery agents and therapeutic applications. Correct identification and synthesis of CPPs using traditional biochemical methods is an extremely slow, expensive and laborious task particularly due to the large volume of unannotated peptide sequences accumulating in the World Bank repository. Hence, a powerful bioinformatics predictor that rapidly identifies CPPs with a high recognition rate is urgently needed. To date, numerous computational methods have been developed for CPP prediction. However, the available machine-learning (ML) tools are unable to distinguish both the CPPs and their uptake efficiencies. This study aimed to develop a two-layer deep learning framework named DeepCPPred to identify both CPPs in the first phase and peptide uptake efficiency in the second phase. The DeepCPPred predictor first uses four types of descriptors that cover evolutionary, energy estimation, reduced sequence and amino-acid contact information. Then, the extracted features are optimized through the elastic net algorithm and fed into a cascade deep forest algorithm to build the final CPP model. The proposed method achieved 99.45 percent overall accuracy with the CPP924 benchmark dataset in the first layer and 95.43 percent accuracy in the second layer with the CPPSite3 dataset using a 5-fold cross-validation test. Thus, our proposed bioinformatics tool surpassed all the existing state-of-the-art sequence-based CPP approaches.

C10Pred: A First Machine Learning Based Tool to Predict C10 Family Cysteine Peptidases Using Sequence-Derived Features

Streptococcus pyogenes, or group A Streptococcus (GAS), a gram-positive bacterium, is implicated in a wide range of clinical manifestations and life-threatening diseases. One of the key virulence factors of GAS is streptopain, a C10 family cysteine peptidase. Since its discovery, various homologs of streptopain have been reported from other bacterial species. With the increased affordability of sequencing, a significant increase in the number of potential C10 family-like sequences in the public databases is anticipated, posing a challenge in classifying such sequences. Sequence-similarity-based tools are the methods of choice to identify such streptopain-like sequences. However, these methods depend on some level of sequence similarity between the existing C10 family and the target sequences. Therefore, in this work, we propose a novel predictor, C10Pred, for the prediction of C10 peptidases using sequence-derived optimal features. C10Pred is a support vector machine (SVM) based model which is efficient in predicting C10 enzymes with an overall accuracy of 92.7% and Matthews’ correlation coefficient (MCC) value of 0.855 when tested on an independent dataset. We anticipate that C10Pred will serve as a handy tool to classify novel streptopain-like proteins belonging to the C10 family and offer essential information.

Development of an RHEB-Targeting Peptide To Inhibit mTORC1 Kinase Activity

In cancer, the mechanistic/mammalian target of rapamycin complex-1 (mTORC1) is hyperactivated to promote survival under adverse conditions. The kinase activity of mTORC1 is activated by small-GTPase RHEB-GTP. Therefore, a new modality to inhibit mTORC1 activity has emerged, through intercepting RHEB. However, due to the relatively large contact area involved in the interaction between RHEB and mTORC1, facilitating this inhibition through small molecules has been challenging. Here, we report the development of a peptide that can inhibit the RHEB-mTORC1 interaction. The peptide, P1_WT, was designed based on the α-helix (aa 101-115) of the N-heat domain of mTOR to interact with switch II of RHEB. P1_WT bound to RHEB (K _D = 0.14 μM) and inhibited RHEB-mTOR^N-heat interaction (IC₅₀ = 0.33 μM) in vitro. Consequently, P1_WT inhibited mTORC1 activity at a sub-micromolar level (IC₅₀ ∼ 0.3 μM). P1_WT was predicted to be cell-permeable due to the rich content of arginine (23%), enhancing the intracellular translocation. These results show that P1_WT is a potential compound to further develop inhibitors for mTORC1 by intercepting RHEB from mTORC1.

In silico and experimental validation of a new modified arginine-rich cell penetrating peptide for plasmid DNA delivery

Cell-penetrating peptides (CPPs) attracted great attention because of the capability to deliver various types of cargo molecules across into the cells. In this study, we presented a new arginine rich CPP, named MR, for efficient transporting plasmid DNA. We used a combined bioinformatic-based approach to improve the speed and accuracy of CPP evaluation. MR protein properties, structural models, interaction with DNA, as well as cell localization and membrane interaction were evaluated through multiple servers. Importantly, analysis using different algorithms showed the high CPP prediction confidence of MR. Experimental results also revealed the capacity of this gene delivery system in vitro for efficient plasmid DNA transfection. Additionally, in vitro mechanistically studies together with bioinformatic investigation suggested that MR peptide may internalize into the cell through endocytosis pathways. Moreover, in silico safety analysis such as immunogenicity, allergenicity, toxicity, and hemolysis activity as well as MTT assay also confirmed the safety of MR peptide. This study illustrated that MR peptide could be presented as remarkable potential gene delivery system for promising transport of plasmid DNA towards the therapeutic applications.

Sequential Properties Representation Scheme for Recurrent Neural Network-Based Prediction of Therapeutic Peptides

The discovery of therapeutic peptides is often accelerated by means of virtual screening supported by machine learning-based predictive models. The predictive performance of such models is sensitive to the choice of data and its representation scheme. While the peptide physicochemical and compositional representations fail to distinguish sequence permutations, the amino acid arrangement within the sequence lacks the important information contained in physicochemical, conformational, topological, and geometrical properties. In this paper, we propose a solution to the identified information gap by implementing a hybrid scheme that complements the best traits from both approaches with the aim of predicting antimicrobial and antiviral activities based on experimental data from DRAMP 2.0, AVPdb, and Uniprot data repositories. Using the Friedman test of statistical significance, we compared our hybrid, sequential properties approach to peptide properties, one-hot vector encoding, and word embedding schemes in the 10-fold cross-validation setting, with respect to the F1 score, Matthews correlation coefficient, geometric mean, recall, and precision evaluation metrics. Moreover, the sequence modeling neural network was employed to gain insight into the synergic effect of both properties- and amino acid order-based predictions. The results suggest that sequential properties significantly (P < 0.01) surpasses the aforementioned state-of-the-art representation schemes. This makes it a strong candidate for increasing the predictive power of screening methods based on machine learning, applicable to any category of peptides.

The role of cell-penetrating peptides in potential anti-cancer therapy

Due to the complex physiological structure, microenvironment and multiple physiological barriers, traditional anti-cancer drugs are severely restricted from reaching the tumour site. Cell-penetrating peptides (CPPs) are typically made up of 5-30 amino acids, and can be utilised as molecular transporters to facilitate the passage of therapeutic drugs across physiological barriers. Up to now, CPPs have widely been used in many anti-cancer treatment strategies, serving as an excellent potential choice for oncology treatment. However, their drawbacks, such as the lack of cell specificity, short duration of action, poor stability in vivo, compatibility problems (i.e. immunogenicity), poor therapeutic efficacy and formation of unwanted metabolites, have limited their further application in cancer treatment. The cellular uptake mechanisms of CPPs involve mainly endocytosis and direct penetration, but still remain highly controversial in academia. The CPPs-based drug delivery strategy could be improved by clever design or chemical modifications to develop the next-generation CPPs with enhanced cell penetration capability, stability and selectivity. In addition, some recent advances in targeted cell penetration that involve CPPs provide some new ideas to optimise CPPs.

Development of Anticancer Peptides Using Artificial Intelligence and Combinational Therapy for Cancer Therapeutics

Cancer is a group of diseases causing abnormal cell growth, altering the genome, and invading or spreading to other parts of the body. Among therapeutic peptide drugs, anticancer peptides (ACPs) have been considered to target and kill cancer cells because cancer cells have unique characteristics such as a high negative charge and abundance of microvilli in the cell membrane when compared to a normal cell. ACPs have several advantages, such as high specificity, cost-effectiveness, low immunogenicity, minimal toxicity, and high tolerance under normal physiological conditions. However, the development and identification of ACPs are time-consuming and expensive in traditional wet-lab-based approaches. Thus, the application of artificial intelligence on the approaches can save time and reduce the cost to identify candidate ACPs. Recently, machine learning (ML), deep learning (DL), and hybrid learning (ML combined DL) have emerged into the development of ACPs without experimental analysis, owing to advances in computer power and big data from the power system. Additionally, we suggest that combination therapy with classical approaches and ACPs might be one of the impactful approaches to increase the efficiency of cancer therapy.

Humanizing plant-derived snakins and their encrypted antimicrobial peptides

Due to safety restrictions, plant-derived antimicrobial peptides (AMPs) need optimization to be consumed beyond preservatives. Herein, 175 GASA-domain-containing snakins were analyzed. Factors including charge, hydrophobicity, helicity, hydrophobic moment (μH), folding enthalpy, folding heat capacity, folding free energy, therapeutic index, allergenicity, and bitterness were considered. The most optimal snakins for oral consumption as preservatives were from Cajanus cajan, Cucumis melo, Durio zibethinus, Glycine soja, Herrania umbratica, and Ziziphus jujuba. Virtual digestion of snakins predicted ACE1 and DPPIV inhibitory as dominant effects upon oral use with antihypertensive and antidiabetic properties. To be applied as a therapeutic in parenteral administration, snakins were browsed for short 20-mer encrypted fragments that were non-toxic or with eliminated toxicity using directed mutagenesis yet retaining the AMP property. The most promising 20-mer AMPs were Mr-SNK2-1a in Morella rubra with BBB permeation, Na-SNK2-2a(C¹⁸W), and Na-SNK2-2b(C¹⁶F) from Nicotiana attenuata. These AMPs were cell-penetrating peptides (CPPs), with a charge of +6, a μH of about 0.40, and a Boman-index higher than 2.48 Kcalmol^-1. Na-SNK2-2a(C¹⁸W) had putative activity against gram-negative bacteria with MIC lower than 25 μgml^-1, and Na-SNK2-2b(C¹⁶F) was a potential anti-HIV with an IC₅₀ of 3.04 μM. Other 20-mer AMPs, such as Cc-SNK1-2a from Cajanus cajan displayed an anti-HCV property with an IC₅₀ of 13.91 μM. While Si-SNK2-3a(C¹⁷P) from Sesamum indicum was a cationic anti-angiogenic CPP targeting the acidic microenvironment of tumors, Cme-SNK2-1a(C¹¹F) from Cucumis melo was an immunomodulator CPP applicable as a vaccine adjuvant. Because of combined mechanisms, investigating cysteine-rich peptides can nominate effective biotherapeutics.

Biological Membrane-Penetrating Peptides: Computational Prediction and Applications

Peptides comprise a versatile class of biomolecules that present a unique chemical space with diverse physicochemical and structural properties. Some classes of peptides are able to naturally cross the biological membranes, such as cell membrane and blood-brain barrier (BBB). Cell-penetrating peptides (CPPs) and blood-brain barrier-penetrating peptides (B3PPs) have been explored by the biotechnological and pharmaceutical industries to develop new therapeutic molecules and carrier systems. The computational prediction of peptides’ penetration into biological membranes has been emerged as an interesting strategy due to their high throughput and low-cost screening of large chemical libraries. Structure- and sequence-based information of peptides, as well as atomistic biophysical models, have been explored in computer-assisted discovery strategies to classify and identify new structures with pharmacokinetic properties related to the translocation through biomembranes. Computational strategies to predict the permeability into biomembranes include cheminformatic filters, molecular dynamics simulations, artificial intelligence algorithms, and statistical models, and the choice of the most adequate method depends on the purposes of the computational investigation. Here, we exhibit and discuss some principles and applications of these computational methods widely used to predict the permeability of peptides into biomembranes, exhibiting some of their pharmaceutical and biotechnological applications.

Viral Prefusion Targeting Using Entry Inhibitor Peptides: The Case of SARS-CoV-2 and Influenza A virus

In this study, peptide entry inhibitors against the fusion processes of severe acute respiratory syndrome coronavirus-2 (SCV2) and influenza A virus (IAV) were designed and evaluated. Fusion inhibitor peptides targeting the conformational shift of the viral fusion protein were designed based on the relatively conserved sequence of HR2 from SCV2 spike protein and the conserved fusion peptide from hemagglutinin (HA) of IAV. Helical HR2 peptides bind more efficiently to HR1 trimer, while helical amphipathic anti-IAV peptides have higher cell penetration and endosomal uptake. The initial sequences were mutated by increasing the amphipathicity, using helix favoring residues, and residues likely to form salt- and disulfide-bridges. After docking against their targets, all anti-SCV2 designed peptides bonded with the HR1 3-helical bundle's hydrophobic crevice, while AntiSCV2P1, AntiSCV2P3, AntiSCV2P7, and AntiSCV2P8 expected to form coiled coils with at least one of the HR1 strands. Four of the designed anti-IAV peptides were cell-penetrating (AntiIAVP2, AntiIAVP3, AntiIAVP4, AntiIAVP7). All of them interacted with the fusion peptide of HA and some of the residues in the conserved hydrophobic pocket of HA2 in H1N1, H3N1, and H5N1 subtypes of IAV. AntiIAVP3 and AntiIAVP4 peptides had the best binding to HA2 conserved hydrophobic pocket, while, AntiIAVP2 and AntiIAVP6 showed the best binding to the fusion peptide region. According to analyses for in-vivo administration, AntiSCV2P1, AntiSCV2P7, AntiIAVP2, and AntiIAVP7 were the best candidates. AntiSCV2 and AntiIAV peptides were also conjugated using an in vivo cleavable linker sensitive to TMPRSS2 applicable as a single therapeutic in coinfections or uncertain diagnosis.

Machine learning models for prognosis prediction in endodontic microsurgery

OBJECTIVES

This study aimed to establish and validate machine learning models for prognosis prediction in endodontic microsurgery, avoiding treatment failure and supporting clinical decision-making.

METHODS

A total of 234 teeth from 178 patients were included in this study. We developed gradient boosting machine (GBM) and random forest (RF) models. For each model, 80% of the data were randomly selected for the training set and the remaining 20% were used as the test set. A stratified 5-fold cross-validation approach was used in model training and testing. Correlation analysis and importance ranking were conducted for feature selection. The predictive accuracy, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), F1 score, and the area under the curve (AUC) of receiver operating characteristic (ROC) curves were calculated to evaluate the predictive performance.

RESULTS

There were eight important predictors, including tooth type, lesion size, type of bone defect, root filling density, root filling length, apical extension of post, age, and sex. For the GBM model, the predictive accuracy was 0.80, with a sensitivity of 0.92, specificity of 0.71, PPV of 0.71, NPV of 0.92, F1 of 0.80/0.80, and AUC of 0.88. For the RF model, the accuracy was 0.80, with a sensitivity of 0.85, specificity of 0.76, PPV of 0.73, NPV of 0.87, F1 of 0.79/0.81, and AUC of 0.83.

CONCLUSIONS

The trained models were developed by eight common variables, showing the potential ability to predict the prognosis of endodontic microsurgery. The GBM model outperformed the RF model slightly on our dataset.

CLINICAL SIGNIFICANCE

Clinicians can use machine learning models for preoperative analysis in endodontic microsurgery. The models are expected to improve the efficiency of clinical decision-making and assist in clinician-patient communication.

Systematic identification and characterization of repeat sequences in African swine fever virus genomes

African swine fever virus (ASFV) is a large DNA virus that infects domestic pigs with high morbidity and mortality rates. Repeat sequences, which are DNA sequence elements that are repeated more than twice in the genome, play an important role in the ASFV genome. The majority of repeat sequences, however, have not been identified and characterized in a systematic manner. In this study, three types of repeat sequences, including microsatellites, minisatellites and short interspersed nuclear elements (SINEs), were identified in the ASFV genome, and their distribution, structure, function, and evolutionary history were investigated. Most repeat sequences were observed in noncoding regions and at the 5' end of the genome. Noncoding repeat sequences tended to form enhancers, whereas coding repeat sequences had a lower ratio of alpha-helix and beta-sheet and a higher ratio of loop structure and surface amino acids than nonrepeat sequences. In addition, the repeat sequences tended to encode penetrating and antimicrobial peptides. Further analysis of the evolution of repeat sequences revealed that the pan-repeat sequences presented an open state, showing the diversity of repeat sequences. Finally, CpG islands were observed to be negatively correlated with repeat sequence occurrences, suggesting that they may affect the generation of repeat sequences. Overall, this study emphasizes the importance of repeat sequences in ASFVs, and these results can aid in understanding the virus's function and evolution.

SortPred: The first machine learning based predictor to identify bacterial sortases and their classes using sequence-derived information

Sortase enzymes are cysteine transpeptidases that embellish the surface of Gram-positive bacteria with various proteins thereby allowing these microorganisms to interact with their neighboring environment. It is known that several of their substrates can cause pathological implications, so researchers have focused on the development of sortase inhibitors. Currently, six different classes of sortases (A-F) are recognized. However, with the extensive application of bacterial genome sequencing projects, the number of potential sortases in the public databases has exploded, presenting considerable challenges in annotating these sequences. It is very laborious and time-consuming to characterize these sortase classes experimentally. Therefore, this study developed the first machine-learning-based two-layer predictor called SortPred, where the first layer predicts the sortase from the given sequence and the second layer predicts their class from the predicted sortase. To develop SortPred, we constructed an original benchmarking dataset and investigated 31 feature descriptors, primarily on five feature encoding algorithms. Afterward, each of these descriptors were trained using a random forest classifier and their robustness was evaluated with an independent dataset. Finally, we selected the final model independently for both layers depending on the performance consistency between cross-validation and independent evaluation. SortPred is expected to be an effective tool for identifying bacterial sortases, which in turn may aid in designing sortase inhibitors and exploring their functions. The SortPred webserver and a standalone version are freely accessible at: https://procarb.org/sortpred.

Computational Screening for the Anticancer Potential of Seed-Derived Antioxidant Peptides: A Cheminformatic Approach

Some seed-derived antioxidant peptides are known to regulate cellular modulators of ROS production, including those proposed to be promising targets of anticancer therapy. Nevertheless, research in this direction is relatively slow owing to the inevitable time-consuming nature of wet-lab experimentations. To help expedite such explorations, we performed structure-based virtual screening on seed-derived antioxidant peptides in the literature for anticancer potential. The ability of the peptides to interact with myeloperoxidase, xanthine oxidase, Keap1, and p47^phox was examined. We generated a virtual library of 677 peptides based on a database and literature search. Screening for anticancer potential, non-toxicity, non-allergenicity, non-hemolyticity narrowed down the collection to five candidates. Molecular docking found LYSPH as the most promising in targeting myeloperoxidase, xanthine oxidase, and Keap1, whereas PSYLNTPLL was the best candidate to bind stably to key residues in p47^phox. Stability of the four peptide-target complexes was supported by molecular dynamics simulation. LYSPH and PSYLNTPLL were predicted to have cell- and blood-brain barrier penetrating potential, although intolerant to gastrointestinal digestion. Computational alanine scanning found tyrosine residues in both peptides as crucial to stable binding to the targets. Overall, LYSPH and PSYLNTPLL are two potential anticancer peptides that deserve deeper exploration in future.

Improved Prediction Model of Protein Lysine Crotonylation Sites Using Bidirectional Recurrent Neural Networks

Histone lysine crotonylation (Kcr) is a post-translational modification of histone proteins that is involved in the regulation of gene transcription, acute and chronic kidney injury, spermatogenesis, depression, cancer, and so forth. The identification of Kcr sites in proteins is important for characterizing and regulating primary biological mechanisms. The use of computational approaches such as machine learning and deep learning algorithms have emerged in recent years as the traditional wet-lab experiments are time-consuming and costly. We propose as part of this study a deep learning model based on a recurrent neural network (RNN) termed as Sohoko-Kcr for the prediction of Kcr sites. Through the embedded encoding of the peptide sequences, we investigate the efficiency of RNN-based models such as long short-term memory (LSTM), bidirectional LSTM (BiLSTM), and bidirectional gated recurrent unit (BiGRU) networks using cross-validation and independent tests. We also established the comparison between Sohoko-Kcr and other published tools to verify the efficiency of our model based on 3-fold, 5-fold, and 10-fold cross-validations using independent set tests. The results then show that the BiGRU model has consistently displayed outstanding performance and computational efficiency. Based on the proposed model, a webserver called Sohoko-Kcr was deployed for free use and is accessible at https://sohoko-research-9uu23.ondigitalocean.app.

Deep Learning Enables Discovery of a Short Nuclear Targeting Peptide for Efficient Delivery of Antisense Oligomers

Therapeutic macromolecules such as proteins and oligonucleotides can be highly efficacious but are often limited to extracellular targets due to the cell's impermeable membrane. Cell-penetrating peptides (CPPs) are able to deliver such macromolecules into cells, but limited structure-activity relationships and inconsistent literature reports make it difficult to design effective CPPs for a given cargo. For example, polyarginine motifs are common in CPPs, promoting cell uptake at the expense of systemic toxicity. Machine learning may be able to address this challenge by bridging gaps between experimental data in order to discern sequence-activity relationships that evade our intuition. Our earlier data set and deep learning model led to the design of miniproteins (>40 amino acids) for antisense delivery. Here, we leveraged and expanded our model with data augmentation in the short CPP sequence space of the data set to extrapolate and discover short, low-arginine-content CPPs that would be easier to synthesize and amenable to rapid conjugation to desired cargo, and with minimal in vivo toxicity. The lead predicted peptide, termed P6, is as active as a polyarginine CPP for the delivery of an antisense oligomer, while having only one arginine side chain and 18 total residues. We determined the pentalysine motif and the C-terminal cysteine of P6 to be the main drivers of activity. The antisense conjugate was able to enhance corrective splicing in an animal model to produce functional eGFP in heart tissue in vivo while remaining nontoxic up to a dose of 60 mg/kg. In addition, P6 was able to deliver an enzyme to the cytosol of cells. Our findings suggest that, given a data set of long CPPs, we can discover by extrapolation short, active sequences that deliver antisense oligomers.