De novo design of anticancer peptides by ensemble artificial neural networks

Recent advances and applications of peptide-agent conjugates for targeting tumor cells

BACKGROUND

Cancer, being a complex disease, presents a major challenge for the scientific and medical communities. Peptide therapeutics have played a significant role in different medical practices, including cancer treatment.

METHOD

This review provides an overview of the current situation and potential development prospects of anticancer peptides (ACPs), with a particular focus on peptide vaccines and peptide-drug conjugates for cancer treatment.

RESULTS

ACPs can be used directly as cytotoxic agents (molecularly targeted peptides) or can act as carriers (guiding missile) of chemotherapeutic agents and radionuclides by specifically targeting cancer cells. More than 60 natural and synthetic cationic peptides are approved in the USA and other major markets for the treatment of cancer and other diseases. Compared to traditional cancer treatments, peptides exhibit anticancer activity with high specificity and the ability to rapidly kill target cancer cells. ACP's target and kill cancer cells via different mechanisms, including membrane disruption, pore formation, induction of apoptosis, necrosis, autophagy, and regulation of the immune system. Modified peptides have been developed as carriers for drugs, vaccines, and peptide-drug conjugates, which have been evaluated in various phases of clinical trials for the treatment of different types of solid and leukemia cancer.

CONCLUSIONS

This review highlights the potential of ACPs as a promising therapeutic option for cancer treatment, particularly through the use of peptide vaccines and peptide-drug conjugates. Despite the limitations of peptides, such as poor metabolic stability and low bioavailability, modified peptides show promise in addressing these challenges. Various mechanism of action of anticancer peptides. Modes of action against cancer cells including: inducing apoptosis by cytochrome c release, direct cell membrane lysis (necrosis), inhibiting angiogenesis, inducing autophagy-mediated cell death and immune cell regulation.

A novel portable immuno-device for the recognition of lymphatic vessel endothelial hyaluronan receptor-1 biomarker using GQD-AgNPrs conductive ink stabilized on the surface of cellulose

Lymphatic vessel endothelium expresses various lymphatic marker molecules. LYVE-1, the lymphatic vessel endothelial hyaluronan (HA) receptor, a 322-residue protein belonging to the integral membrane glycoproteins which is found on lymph vessel wall and is completely absent from blood vessels. LYVE-1 is very effective in the passage of lymphocytes and tumor cells into the lymphatics. As regards cancer metastasis, in vitro studies indicate LYVE-1 to be involved in tumor cell adhesion. Researches show that, in neoplastic tissue, LYVE-1 is limited to the lymphovascular and could well be proper for studies of tumor lymphangiogenesis. So, the monitoring of LYVE-1 level in human biofluids has provided a valuable approach for research into tumor lymphangiogenesis. For the first time, an innovative paper-based electrochemical immune-platform was developed for recognition of LYVE-1. For this purpose, graphene quantum dots decorated silver nanoparticles nano-ink was synthesized and designed directly by writing pen-on paper technology on the surface of photographic paper. This nano-ink has a great surface area for biomarker immobilization. The prepared paper-based biosensor was so small and cheap and also has high stability and sensitivity. For the first time, biotinylated antibody of biomarker (LYVE-1) was immobilized on the surface of working electrode and utilized for the monitoring of specific antigen by simple immune-assay strategy. The designed biosensor showed two separated linear ranges in the range of 20-320 pg ml-1 and 0.625-10 pg ml-1, with the acceptable limit of detection (LOD) of 0.312 pg ml-1. Additionally, engineered immunosensor revealed excellent selectivity that promises its use in complex biological samples and assistance for biomarker-related disease screening in clinical studies.

Umami-BERT: An interpretable BERT-based model for umami peptides prediction

Umami peptides have received extensive attention due to their ability to enhance flavors and provide nutritional benefits. The increasing demand for novel umami peptides and the vast number of peptides present in food call for more efficient methods to screen umami peptides, and further exploration is necessary. Therefore, the purpose of this study is to develop deep learning (DL) model to realize rapid screening of umami peptides. The Umami-BERT model was devised utilizing a novel two-stage training strategy with Bidirectional Encoder Representations from Transformers (BERT) and the inception network. In the pre-training stage, attention mechanisms were implemented on a large amount of bioactive peptides sequences to acquire high-dimensional generalized features. In the re-training stage, umami peptide prediction was carried out on UMP789 dataset, which is developed through the latest research. The model achieved the performance with an accuracy (ACC) of 93.23% and MCC of 0.78 on the balanced dataset, as well as an ACC of 95.00% and MCC of 0.85 on the unbalanced dataset. The results demonstrated that Umami-BERT could predict umami peptides directly from their amino acid sequences and exceeded the performance of other models. Furthermore, Umami-BERT enabled the analysis of attention pattern learned by Umami-BERT model. The amino acids Alanine (A), Cysteine (C), Aspartate (D), and Glutamicacid (E) were found to be the most significant contributors to umami peptides. Additionally, the patterns of summarized umami peptides involving A, C, D, and E were analyzed based on the learned attention weights. Consequently, Umami-BERT exhibited great potential in the large-scale screening of candidate peptides and offers novel insight for the further exploration of umami peptides.

Nanoparticle-mediated cancer cell therapy: basic science to clinical applications

Every sixth person in the world dies due to cancer, making it the second leading severe cause of death after cardiovascular diseases. According to WHO, cancer claimed nearly 10 million deaths in 2020. The most common types of cancers reported have been breast (lung, colon and rectum, prostate cases), skin (non-melanoma) and stomach. In addition to surgery, the most widely used traditional types of anti-cancer treatment are radio- and chemotherapy. However, these do not distinguish between normal and malignant cells. Additional treatment methods have evolved over time for early detection and targeted therapy of cancer. However, each method has its limitations and the associated treatment costs are quite high with adverse effects on the quality of life of patients. Use of individual atoms or a cluster of atoms (nanoparticles) can cause a paradigm shift by virtue of providing point of sight sensing and diagnosis of cancer. Nanoparticles (1-100 nm in size) are 1000 times smaller in size than the human cell and endowed with safer relocation capability to attack mechanically and chemically at a precise location which is one avenue that can be used to destroy cancer cells precisely. This review summarises the extant understanding and the work done in this area to pave the way for physicians to accelerate the use of hybrid mode of treatments by leveraging the use of various nanoparticles.

General structure-activity/selectivity relationship patterns for the inhibitors of the chemokine receptors (CCR1/CCR2/CCR4/CCR5) with application for virtual screening of PubChem database

CC chemokine receptors (CCRs) form a crucial subfamily of G protein-linked receptors that play a distinct role in the onset and progression of various life-threatening diseases. The main aim of this research is to derive general structure-activity relationship (SAR) patterns to describe the selectivity and activity of CCR inhibitors. To this end, a total of 7332 molecules related to the inhibition of CCR1, CCR2, CCR4, and CCR5 were collected from the Binding Database and analyzed using machine learning techniques. A diverse set of 450 molecular descriptors was calculated for each molecule, and the molecules were classified based on their therapeutic targets and activities. The variable importance in the projection (VIP) approach was used to select discriminatory molecular features, and classification models were developed using supervised Kohonen networks (SKN) and counter-propagation artificial neural networks (CPANN). The reliability and predictability of the models were estimated using 10-fold cross-validation, an external validation set, and an applicability domain approach. We were able to identify different sets of molecular descriptors for discriminating between active and inactive molecules and model the selectivity of inhibitors towards different CCRs. The sensitivities of the predictions for the external test set for the SKN models ranged from 0.827-0.873. Finally, the developed classification models were used to screen approximately 2 million random molecules from the PubChem database, with average values for areas under the receiver operating characteristic curves ranging from 0.78-0.96 for SKN models and 0.75-0.89 for CPANN models.Communicated by Ramaswamy H. Sarma.

Current therapeutic approaches and promising perspectives of using bioengineered peptides in fighting chemoresistance in triple-negative breast cancer

Breast cancer is a collation of malignancies that manifest in the mammary glands at the early stages. Among breast cancer subtypes, triple-negative breast cancer (TNBC) shows the most aggressive behavior, with apparent stemness features. Owing to the lack of response to hormone therapy and specific targeted therapies, chemotherapy remains the first line of the TNBC treatment. However, the acquisition of resistance to chemotherapeutic agents increase therapy failure, and promotes cancer recurrence and distant metastasis. Invasive primary tumors are the birthplace of cancer burden, though metastasis is a key attribute of TNBC-associated morbidity and mortality. Targeting the chemoresistant metastases-initiating cells via specific therapeutic agents with affinity to the upregulated molecular targets is a promising step in the TNBC clinical management. Exploring the capacity of peptides as biocompatible entities with the specificity of action, low immunogenicity, and robust efficacy provides a principle for designing peptide-based drugs capable of increasing the efficacy of current chemotherapy agents for selective targeting of the drug-tolerant TNBC cells. Here, we first focus on the resistance mechanisms that TNBC cells acquire to evade the effect of chemotherapeutic agents. Next, the novel therapeutic approaches employing tumor-targeting peptides to exploit the mechanisms of drug resistance in chemorefractory TNBC are described.

ALA-A2 Is a Novel Anticancer Peptide Inspired by Alpha-Lactalbumin: A Discovery from a Computational Peptide Library, In Silico Anticancer Peptide Screening and In Vitro Experimental Validation

Anticancer peptides (ACPs) are rising as a new strategy for cancer therapy. However, traditional laboratory screening to find and identify novel ACPs from hundreds to thousands of peptides is costly and time consuming. Here, a sequential procedure is applied to identify candidate ACPs from a computer-generated peptide library inspired by alpha-lactalbumin, a milk protein with known anticancer properties. A total of 2688 distinct peptides, 5-25 amino acids in length, are generated from alpha-lactalbumin. In silico ACP screening using the physicochemical and structural filters and three machine learning models lead to the top candidate peptides ALA-A1 and ALA-A2. In vitro screening against five human cancer cell lines supports ALA-A2 as the positive hit. ALA-A2 selectively kills A549 lung cancer cells in a dose-dependent manner, with no hemolytic side effects, and acts as a cell penetrating peptide without membranolytic effects. Sequential window acquisition of all theorical fragment ions-proteomics and functional validation reveal that ALA-A2 induces autophagy to mediate lung cancer cell death. This approach to identify ALA-A2 is time and cost-effective. Further investigations are warranted to elucidate the exact intracellular targets of ALA-A2. Moreover, these findings support the use of larger computational peptide libraries built upon multiple proteins to further advance ACP research and development.

De Novo Drug Design Using Reinforcement Learning with Graph-Based Deep Generative Models

Machine learning provides effective computational tools for exploring the chemical space via deep generative models. Here, we propose a new reinforcement learning scheme to fine-tune graph-based deep generative models for de novo molecular design tasks. We show how our computational framework can successfully guide a pretrained generative model toward the generation of molecules with a specific property profile, even when such molecules are not present in the training set and unlikely to be generated by the pretrained model. We explored the following tasks: generating molecules of decreasing/increasing size, increasing drug-likeness, and increasing bioactivity. Using the proposed approach, we achieve a model which generates diverse compounds with predicted DRD2 activity for 95% of sampled molecules, outperforming previously reported methods on this metric.

Accelerating the discovery of anticancer peptides targeting lung and breast cancers with the Wasserstein autoencoder model and PSO algorithm

In the development of targeted drugs, anticancer peptides (ACPs) have attracted great attention because of their high selectivity, low toxicity and minimal non-specificity. In this work, we report a framework of ACPs generation, which combines Wasserstein autoencoder (WAE) generative model and Particle Swarm Optimization (PSO) forward search algorithm guided by attribute predictive model to generate ACPs with desired properties. It is well known that generative models based on Variational AutoEncoder (VAE) and Generative Adversarial Networks (GAN) are difficult to be used for de novo design due to the problems of posterior collapse and difficult convergence of training. Our WAE-based generative model trains more successfully (lower perplexity and reconstruction loss) than both VAE and GAN-based generative models, and the semantic connections in the latent space of WAE accelerate the process of forward controlled generation of PSO, while VAE fails to capture this feature. Finally, we validated our pipeline on breast cancer targets (HIF-1) and lung cancer targets (VEGR, ErbB2), respectively. By peptide-protein docking, we found candidate compounds with the same binding sites as the peptides carried in the crystal structure but with higher binding affinity and novel structures, which may be potent antagonists that interfere with these target-mediated signaling.

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.

Design of Protein Segments and Peptides for Binding to Protein Targets

Recent years have witnessed a rise in methods for accurate prediction of structure and design of novel functional proteins. Design of functional protein fragments and peptides occupy a small, albeit unique, space within the general field of protein design. While the smaller size of these peptides allows for more exhaustive computational methods, flexibility in their structure and sparsity of data compared to proteins, as well as presence of noncanonical building blocks, add additional challenges to their design. This review summarizes the current advances in the design of protein fragments and peptides for binding to targets and discusses the challenges in the field, with an eye toward future directions.

Breast and Lung Anticancer Peptides Classification Using N-Grams and Ensemble Learning Techniques

Anticancer peptides (ACPs) are short protein sequences; they perform functions like some hormones and enzymes inside the body. The role of any protein or peptide is related to its structure and the sequence of amino acids that make up it. There are 20 types of amino acids in humans, and each of them has a particular characteristic according to its chemical structure. Current machine and deep learning models have been used to classify ACPs problems. However, these models have neglected Amino Acid Repeats (AARs) that play an essential role in the function and structure of peptides. Therefore, in this paper, ACPs offer a promising route for novel anticancer peptides by extracting AARs based on N-Grams and k-mers using two peptides’ datasets. These datasets pointed to breast and lung cancer cells assembled and curated manually from the Cancer Peptide and Protein Database (CancerPPD). Every dataset consists of a sequence of peptides and their synthesis and anticancer activity on breast and lung cancer cell lines. Five different feature selection methods were used in this paper to improve classification performance and reduce the experimental costs. After that, ACPs were classified using four classifiers, namely AdaBoost, Random Forest Tree (RFT), Multi-class Support Vector Machine (SVM), and Multi-Layer Perceptron (MLP). These classifiers were evaluated by applying five well-known evaluation metrics. Experimental results showed that the breast and lung ACPs classification process provided an accurate performance that reached 89.25% and 92.56%, respectively. In terms of AUC, it reached 95.35% and 96.92% for both breast and lung ACPs, respectively. The proposed classifiers performed competently somewhat equally in AUC, accuracy, precision, F-measures, and recall, except for Multi-class SVM-based feature selection, which showed superior performance. As a result, this paper significantly improved the predictive performance that can effectively distinguish ACPs as virtual inactive, experimental inactive, moderately active, and very active.

A novel kernel based approach to arbitrary length symbolic data with application to type 2 diabetes risk

Predictive modeling of clinical data is fraught with challenges arising from the manner in which events are recorded. Patients typically fall ill at irregular intervals and experience dissimilar intervention trajectories. This results in irregularly sampled and uneven length data which poses a problem for standard multivariate tools. The alternative of feature extraction into equal-length vectors via methods like Bag-of-Words (BoW) potentially discards useful information. We propose an approach based on a kernel framework in which data is maintained in its native form: discrete sequences of symbols. Kernel functions derived from the edit distance between pairs of sequences may then be utilized in conjunction with support vector machines to classify the data. Our method is evaluated in the context of the prediction task of determining patients likely to develop type 2 diabetes following an earlier episode of elevated blood pressure of 130/80 mmHg. Kernels combined via multi kernel learning achieved an F1-score of 0.96, outperforming classification with SVM 0.63, logistic regression 0.63, Long Short Term Memory 0.61 and Multi-Layer Perceptron 0.54 applied to a BoW representation of the data. We achieved an F1-score of 0.97 on MKL on external dataset. The proposed approach is consequently able to overcome limitations associated with feature-based classification in the context of clinical data.

Recent advancement in functional properties and toxicity assessment of plant-derived bioactive peptides using bioinformatic approaches

Nowadays, biopeptides have gained considerable interest by the food industries, given their potent biological effect on health. BPs, when released from the sequence of their precursors by proteolytic enzymes, improved the various physiological functions of the body. Diabetic and hypertension are the two most common life-threatening diseases linked to dietary patterns. Angiotensin-converting enzyme (ACE) (hypertension-responsible glycoprotein) and dipeptidyl peptidase IV (DPP-IV) (proline-specific dimeric aminopeptidase) have been widely used as molecular target sites of action of bioactive compounds possessing antihypertensive and antidiabetic effects. Although, BPs possess considerable biological properties (antioxidant, antimicrobial, antiviral, immunomodulating, antiproliferative, antidiabetic, and antihypertensive effects), most of them possess inherent lacunae such as toxicity, allergenicity, bitterness, and lack of detailed mechanistic investigation, limiting their commercial application. The present review provides an overview on various sources of bioactive peptides, conventional and modern methods of extraction, and challenges that need to be addressed before its commercial application. In addition, bioinformatics' role in exploring the functional properties of biopeptides (ACE and DPP-IV inhibitory effects) toxicity, the target site of action with special reference to plant-based peptides, and recent burgeoning proficiencies in biopeptide research have been discussed.

Correlation between the secondary structure and surface activity of β-sheet forming cationic amphiphilic peptides and their anticancer activity

Cancer is one of the main causes of death worldwide. The current cancer treatment strategies often lack selectivity for cancer cells resulting in dose-limiting adverse effects and reduced quality of life. Recently, anticancer peptides (ACPs) have emerged as an alternative treatment with higher selectivity, less adverse effects, and lower propensity for drug resistance. However, most of the current studies on the ACPs are focused on α-helical ACPs and there is lack of systematic studies on β-sheet forming ACPs. Herein we report the development of a new series of rationally designed short cationic amphiphilic β-sheet forming ACPs and their structure activity relationship. The peptides had the general formula (XY₁XY₂)₃, with X representing hydrophobic amino acids (isoleucine (I) or leucine (L)), Y₁ and Y₂ representing cationic amino acids (arginine (R) or lysine (K)). The cytotoxicity of the designed ACPs in HCT 116 colorectal cancer, HeLa cervical cancer and human dermal fibroblast (HDF) cells was assessed by MTT test. The physicochemical properties of the peptides were characterized by various techniques including RP-HPLC, LC-MS, and Circular Dichroism (CD) spectroscopy. The surface activity of the peptides at the air-water interface and their interaction with the lipid monolayers as models for cell membranes were studied by Langmuir trough. The peptides consisting of I with R and K had selective anticancer activity while the combination of L and R diminished the anticancer activity of the peptides but rendered them more toxic to HDFs. The anticancer activity of the peptides was directed by their surface activity (amphiphilicity) and their secondary structure in hydrophobic surfaces including cancer cell membranes. The selectivity of the peptides for cancer cells was a result of their higher penetration into cancer cell membranes compared to normal cell membranes. The peptides exerted their anticancer activity by disrupting the mitochondrial membranes and eventually apoptosis. The results presented in this study provide an insight into the structure-activity relationship of this class of ACPs which can be employed as guidance to design new ACPs with improved anticancer activity and lower toxicity against normal cells.

Anti-cancer Peptide Recognition Based on Grouped Sequence and Spatial Dimension Integrated Networks

The diversification of the characteristic sequences of anti-cancer peptides has imposed difficulties on research. To effectively predict new anti-cancer peptides, this paper proposes a more suitable feature grouping sequence and spatial dimension-integrated network algorithm for anti-cancer peptide sequence prediction called GRCI-Net. The main process is as follows: First, we implemented the fusion reduction of binary structure features and K-mer sparse matrix features through principal component analysis and generated a set of new features; second, we constructed a new bidirectional long- and short-term memory network. We used traditional convolution and dilated convolution to acquire features in the spatial dimension using the memory network's grouping sequence model, which is designed to better handle the diversification of anti-cancer peptide feature sequences and to fully learn the contextual information between features. Finally, we achieved the fusion of grouping sequence features and spatial dimensional integration features through two sets of dense network layers, achieved the prediction of anti-cancer peptides through the sigmoid function, and verified the approach with two public datasets, ACP740 (accuracy reached 0.8230) and ACP240 (accuracy reached 0.8750). The following is a link to the model code and datasets mentioned in this article: https://github.com/ YouHongfeng101/ACP-DL.

GenUI: interactive and extensible open source software platform for de novo molecular generation and cheminformatics

Many contemporary cheminformatics methods, including computer-aided de novo drug design, hold promise to significantly accelerate and reduce the cost of drug discovery. Thanks to this attractive outlook, the field has thrived and in the past few years has seen an especially significant growth, mainly due to the emergence of novel methods based on deep neural networks. This growth is also apparent in the development of novel de novo drug design methods with many new generative algorithms now available. However, widespread adoption of new generative techniques in the fields like medicinal chemistry or chemical biology is still lagging behind the most recent developments. Upon taking a closer look, this fact is not surprising since in order to successfully integrate the most recent de novo drug design methods in existing processes and pipelines, a close collaboration between diverse groups of experimental and theoretical scientists needs to be established. Therefore, to accelerate the adoption of both modern and traditional de novo molecular generators, we developed Generator User Interface (GenUI), a software platform that makes it possible to integrate molecular generators within a feature-rich graphical user interface that is easy to use by experts of diverse backgrounds. GenUI is implemented as a web service and its interfaces offer access to cheminformatics tools for data preprocessing, model building, molecule generation, and interactive chemical space visualization. Moreover, the platform is easy to extend with customizable frontend React.js components and backend Python extensions. GenUI is open source and a recently developed de novo molecular generator, DrugEx, was integrated as a proof of principle. In this work, we present the architecture and implementation details of GenUI and discuss how it can facilitate collaboration in the disparate communities interested in de novo molecular generation and computer-aided drug discovery.

Rationally designed short cationic α-helical peptides with selective anticancer activity

HYPOTHESIS

Naturally derived or synthetic anticancer peptides (ACPs) have emerged as a new generation of anticancer agents with higher selectivity for cancer cells and less propensity for drug resistance. Despite the structural diversity of ACPs, α-helix is the most common secondary structure among them. Herein we report the development of a new library of short cationic amphiphilic α-helical ACPs with selective cytotoxicity against colorectal and cervical cancer.

EXPERIMENTS

The peptides had a general formula C(XXYY)₃ with C representing amino acid cysteine (providing a -SH group for molecular conjugation), X representing hydrophobic amino acids (isoleucine (I) or leucine (L)), and Y representing cationic amino acids (arginine (R) or lysine (K)). Two variants of the peptides were synthesized by adding additional Isoleucine residues to the C-terminal and replacing the N-terminal cysteine with LC-propargylglycine (LC-G) to investigate the effect of N-terminal and C-terminal variation on the anticancer activity. The structure and physicochemical properties of the peptides were determined by RP-HPLC, LC-MS and CD spectroscopy. The cytotoxicity of the peptides in different cell lines was assessed by MTT test, cell proliferation assay and mitochondrial damage assay. The mechanism of cell selectivity of the peptides was investigated by studying their interfacial behaviour at the air/water and lipid/water interface using Langmuir trough.

FINDINGS

The peptides consisting of K residues in their hydrophilic domains exhibited more selective anticancer activity whereas the peptides containing R exhibited strong toxicity in normal cells. The anticancer activity of the peptides was a function of their helical content and their hydrophobicity. Therefore, the addition of two I residues at C-terminal enhanced the anticancer activity of the peptides by increasing their hydrophobicity and their helical content. These two variants also exhibited strong anticancer activity against colorectal cancer multicellular tumour spheroids (MCTS). The higher toxicity of the peptides in cancer cells compared to normal cells was the result of higher penetration into the negatively charged cancer cell membranes, leading to higher cellular uptake, and their cytotoxic effect was mainly exerted by damaging the mitochondrial membranes leading to apoptosis. The results from this study provide a basis for rational design of new α-helical ACPs with enhanced anticancer activity and selectivity.

Accelerating antibiotic discovery through artificial intelligence

By targeting invasive organisms, antibiotics insert themselves into the ancient struggle of the host-pathogen evolutionary arms race. As pathogens evolve tactics for evading antibiotics, therapies decline in efficacy and must be replaced, distinguishing antibiotics from most other forms of drug development. Together with a slow and expensive antibiotic development pipeline, the proliferation of drug-resistant pathogens drives urgent interest in computational methods that promise to expedite candidate discovery. Strides in artificial intelligence (AI) have encouraged its application to multiple dimensions of computer-aided drug design, with increasing application to antibiotic discovery. This review describes AI-facilitated advances in the discovery of both small molecule antibiotics and antimicrobial peptides. Beyond the essential prediction of antimicrobial activity, emphasis is also given to antimicrobial compound representation, determination of drug-likeness traits, antimicrobial resistance, and de novo molecular design. Given the urgency of the antimicrobial resistance crisis, we analyze uptake of open science best practices in AI-driven antibiotic discovery and argue for openness and reproducibility as a means of accelerating preclinical research. Finally, trends in the literature and areas for future inquiry are discussed, as artificially intelligent enhancements to drug discovery at large offer many opportunities for future applications in antibiotic development.

xDeep-AcPEP: Deep Learning Method for Anticancer Peptide Activity Prediction Based on Convolutional Neural Network and Multitask Learning

Cancer is one of the leading causes of death worldwide. Conventional cancer treatment relies on radiotherapy and chemotherapy, but both methods bring severe side effects to patients, as these therapies not only attack cancer cells but also damage normal cells. Anticancer peptides (ACPs) are a promising alternative as therapeutic agents that are efficient and selective against tumor cells. Here, we propose a deep learning method based on convolutional neural networks to predict biological activity (EC50, LC50, IC50, and LD50) against six tumor cells, including breast, colon, cervix, lung, skin, and prostate. We show that models derived with multitask learning achieve better performance than conventional single-task models. In repeated 5-fold cross validation using the CancerPPD data set, the best models with the applicability domain defined obtain an average mean squared error of 0.1758, Pearson's correlation coefficient of 0.8086, and Kendall's correlation coefficient of 0.6156. As a step toward model interpretability, we infer the contribution of each residue in the sequence to the predicted activity by means of feature importance weights derived from the convolutional layers of the model. The present method, referred to as xDeep-AcPEP, will help to identify effective ACPs in rational peptide design for therapeutic purposes. The data, script files for reproducing the experiments, and the final prediction models can be downloaded from http://github.com/chen709847237/xDeep-AcPEP. The web server to directly access this prediction method is at https://app.cbbio.online/acpep/home.

Prediction of Anticancer Peptides with High Efficacy and Low Toxicity by Hybrid Model Based on 3D Structure of Peptides

Recently, anticancer peptides (ACPs) have emerged as unique and promising therapeutic agents for cancer treatment compared with antibody and small molecule drugs. In addition to experimental methods of ACPs discovery, it is also necessary to develop accurate machine learning models for ACP prediction. In this study, features were extracted from the three-dimensional (3D) structure of peptides to develop the model, compared to most of the previous computational models, which are based on sequence information. In order to develop ACPs with more potency, more selectivity and less toxicity, the model for predicting ACPs, hemolytic peptides and toxic peptides were established by peptides 3D structure separately. Multiple datasets were collected according to whether the peptide sequence was chemically modified. After feature extraction and screening, diverse algorithms were used to build the model. Twelve models with excellent performance (Acc > 90%) in the ACPs mixed datasets were used to form a hybrid model to predict the candidate ACPs, and then the optimal model of hemolytic peptides (Acc = 73.68%) and toxic peptides (Acc = 85.5%) was used for safety prediction. Novel ACPs were found by using those models, and five peptides were randomly selected to determine their anticancer activity and toxic side effects in vitro experiments.

Artificial intelligence in oncology: From bench to clinic

In the past few years, Artificial Intelligence (AI) techniques have been applied to almost every facet of oncology, from basic research to drug development and clinical care. In the clinical arena where AI has perhaps received the most attention, AI is showing promise in enhancing and automating image-based diagnostic approaches in fields such as radiology and pathology. Robust AI applications, which retain high performance and reproducibility over multiple datasets, extend from predicting indications for drug development to improving clinical decision support using electronic health record data. In this article, we review some of these advances. We also introduce common concepts and fundamentals of AI and its various uses, along with its caveats, to provide an overview of the opportunities and challenges in the field of oncology. Leveraging AI techniques productively to provide better care throughout a patient's medical journey can fuel the predictive promise of precision medicine.

Recent Progress Using De Novo Design to Study Protein Structure, Design and Binding Interactions

De novo protein design is a powerful methodology used to study natural functions in an artificial-protein context. Since its inception, it has been used to reproduce a plethora of reactions and uncover biophysical principles that are often difficult to extract from direct studies of natural proteins. Natural proteins are capable of assuming a variety of different structures and subsequently binding ligands at impressively high levels of both specificity and affinity. Here, we will review recent examples of de novo design studies on binding reactions for small molecules, nucleic acids, and the formation of protein-protein interactions. We will then discuss some new structural advances in the field. Finally, we will discuss some advancements in computational modeling and design approaches and provide an overview of some modern algorithmic tools being used to design these proteins.

Use of anticancer peptides as an alternative approach for targeted therapy in breast cancer: a review

Breast cancer is the most common cancer in women worldwide. Traditional therapies are expensive and cause severe side effects. Targeted therapy is a powerful method to circumvent the problems of other therapies. It also allows drugs to localize at predefined targets in a selective manner. Currently, there are several monoclonal antibodies which target breast cancer cell surface markers. However, using antibodies has some limitations. In the last two decades, many investigators have discovered peptides that may be useful to target breast cancer cells. In this article, we provide an overview on anti-breast cancer peptides, their sources and biological activities. We further discuss the pros and cons of using anticancer peptides with further emphasis on how to improve their effectiveness in cancer therapy.

Generating Ampicillin-Level Antimicrobial Peptides with Activity-Aware Generative Adversarial Networks

Antimicrobial peptides are a potential solution to the threat of multidrug-resistant bacterial pathogens. Recently, deep generative models including generative adversarial networks (GANs) have been shown to be capable of designing new antimicrobial peptides. Intuitively, a GAN controls the probability distribution of generated sequences to cover active peptides as much as possible. This paper presents a peptide-specialized model called PepGAN that takes the balance between covering active peptides and dodging nonactive peptides. As a result, PepGAN has superior statistical fidelity with respect to physicochemical descriptors including charge, hydrophobicity, and weight. Top six peptides were synthesized, and one of them was confirmed to be highly antimicrobial. The minimum inhibitory concentration was 3.1 μg/mL, indicating that the peptide is twice as strong as ampicillin.

Prediction of Amphiphilic Cell-Penetrating Peptide Building Blocks from Protein-Derived Amino Acid Sequences for Engineering of Drug Delivery Nanoassemblies

Amphiphilic molecules, forming self-assembled nanoarchitectures, are typically composed of hydrophobic and hydrophilic domains. Peptide amphiphiles can be designed from two, three, or four building blocks imparting novel structural and functional properties and affinities for interaction with cellular membranes or intracellular organelles. Here we present a combined numerical approach to design amphiphilic peptide scaffolds that are derived from the human nuclear K_i-67 protein. K_i-67 acts, like a biosurfactant, as a steric and electrostatic charge barrier against the collapse of mitotic chromosomes. The proposed predictive design of new K_i-67 protein-derived amphiphilic amino acid sequences exploits the computational outcomes of a set of web-accessible predictors, which are based on machine learning methods. The ensemble of such artificial intelligence algorithms, involving support vector machine (SVM), random forest (RF) classifiers, and neural networks (NN), enables the nanoengineering of a broad range of innovative peptide materials for therapeutic delivery in various applications. Amphiphilic cell-penetrating peptides (CPP), derived from natural protein sequences, may spontaneously form self-assembled nanocarriers characterized by enhanced cellular uptake. Thanks to their inherent low immunogenicity, they may enable the safe delivery of therapeutic molecules across the biological barriers.

Populating Chemical Space with Peptides Using a Genetic Algorithm

In drug discovery, one uses chemical space as a concept to organize molecules according to their structures and properties. One often would like to generate new possible molecules at a specific location in the chemical space marked by a molecule of interest. Herein, we report the peptide design genetic algorithm (PDGA, code available at https://github.com/reymond-group/PeptideDesignGA ), a computational tool capable of producing peptide sequences of various topologies (linear, cyclic/polycyclic, or dendritic) in proximity of any molecule of interest in a chemical space defined by macromolecule extended atom-pair fingerprint (MXFP), an atom-pair fingerprint describing molecular shape and pharmacophores. We show that the PDGA generates high-similarity analogues of bioactive peptides with diverse peptide chain topologies and of nonpeptide target molecules. We illustrate the chemical space accessible by the PDGA with an interactive 3D map of the MXFP property space available at http://faerun.gdb.tools/ . The PDGA should be generally useful to generate peptides at any location in the chemical space.

Prediction of the Health Effects of Food Peptides and Elucidation of the Mode-of-action Using Multi-task Graph Convolutional Neural Network

Food proteins work not only as nutrients but also modulators for the physiological functions of the human body. The physiological functions of food proteins are basically regulated by peptides encrypted in food protein sequences (food peptides). In this study, we propose a novel deep learning-based method to predict the health effects of food peptides and elucidate the mode-of-action. In the algorithm, we estimate potential target proteins of food peptides using a multi-task graph convolutional neural network, and predict its health effects using information about therapeutic targets for diseases. We constructed predictive models based on 21,103 peptide-protein interactions involving 10,950 peptides and 2,533 proteins, and applied the models to food peptides (e. g., lactotripeptide, isoleucyltyrosine and sardine peptide) defined in food for specified health use. The models suggested potential effects such as blood-pressure lowering effects, blood glucose level lowering effects, and anti-cancer effects for several food peptides. The interactions of food peptides with target proteins were confirmed by docking simulations.