Machine Learning in Antibacterial Drug Design

Addressing docking pose selection with structure-based deep learning: Recent advances, challenges and opportunities

Molecular docking is a widely used technique in drug discovery to predict the binding mode of a given ligand to its target. However, the identification of the near-native binding pose in docking experiments still represents a challenging task as the scoring functions currently employed by docking programs are parametrized to predict the binding affinity, and, therefore, they often fail to correctly identify the ligand native binding conformation. Selecting the correct binding mode is crucial to obtaining meaningful results and to conveniently optimizing new hit compounds. Deep learning (DL) algorithms have been an area of a growing interest in this sense for their capability to extract the relevant information directly from the protein-ligand structure. Our review aims to present the recent advances regarding the development of DL-based pose selection approaches, discussing limitations and possible future directions. Moreover, a comparison between the performances of some classical scoring functions and DL-based methods concerning their ability to select the correct binding mode is reported. In this regard, two novel DL-based pose selectors developed by us are presented.

Current Treatments, Emerging Therapeutics, and Natural Remedies for Inflammatory Bowel Disease

Inflammatory bowel disease (IBD) is a chronic, lifelong disorder characterized by inflammation of the gastrointestinal (GI) tract. The exact etiology of IBD remains incompletely understood due to its multifaceted nature, which includes genetic predisposition, environmental factors, and host immune response dysfunction. Currently, there is no cure for IBD. This review discusses the available treatment options and the challenges they present. Importantly, we examine emerging therapeutics, such as biologics and immunomodulators, that offer targeted treatment strategies for IBD. While many IBD patients do not respond adequately to most biologics, recent clinical trials combining biologics with small-molecule drugs (SMDs) have provided new insights into improving the IBD treatment landscape. Furthermore, numerous novel and specific therapeutic targets have been identified. The high cost of IBD drugs poses a significant barrier to treatment, but this challenge may be alleviated with the development of more affordable biosimilars. Additionally, emerging point-of-care protein biomarkers from serum and plasma are showing potential for enhancing the precision of IBD diagnosis and prognosis. Several natural products (NPs), including crude extracts, small molecules, and peptides, have demonstrated promising anti-inflammatory activity in high-throughput screening (HTS) systems and advanced artificial intelligence (AI)-assisted platforms, such as molecular docking and ADMET prediction. These platforms are advancing the search for alternative IBD therapies derived from natural sources, potentially leading to more affordable and safer treatment options with fewer side effects.

De novo synthetic antimicrobial peptide design with a recurrent neural network

Antibiotic resistance is recognized as an imminent and growing global health threat. New antimicrobial drugs are urgently needed due to the decreasing effectiveness of conventional small-molecule antibiotics. Antimicrobial peptides (AMPs), a class of host defense peptides, are emerging as promising candidates to address this need. The potential sequence space of amino acids is combinatorially vast, making it possible to extend the current arsenal of antimicrobial agents with a practically infinite number of new peptide-based candidates. However, mining naturally occurring AMPs, whether directly by wet lab screening methods or aided by bioinformatics prediction tools, has its theoretical limit regarding the number of samples or genomic/transcriptomic resources researchers have access to. Further, manually designing novel synthetic AMPs requires prior field knowledge, restricting its throughput. In silico sequence generation methods are gaining interest as a high-throughput solution to the problem. Here, we introduce AMPd-Up, a recurrent neural network based tool for de novo AMP design, and demonstrate its utility over existing methods. Validation of candidates designed by AMPd-Up through antimicrobial susceptibility testing revealed that 40 of the 58 generated sequences possessed antimicrobial activity against Escherichia coli and/or Staphylococcus aureus. These results illustrate that AMPd-Up can be used to design novel synthetic AMPs with potent activities.

PyAMPA: a high-throughput prediction and optimization tool for antimicrobial peptides

The alarming rise of antibiotic-resistant bacterial infections is driving efforts to develop alternatives to conventional antibiotics. In this context, antimicrobial peptides (AMPs) have emerged as promising candidates for their ability to target a broad range of microorganisms. However, the development of AMPs with optimal potency, selectivity, and/or stability profiles remains a challenge. To address it, computational tools for predicting AMP properties and designing novel peptides have gained increasing attention. PyAMPA is a novel platform for AMP discovery. It consists of five modules, namely AMPScreen, AMPValidate, AMPSolve, AMPMutate, and AMPOptimize, that allow high-throughput proteome inspection, candidate screening, and optimization through point-mutation and genetic algorithms. The platform also offers additional tools for predicting and evaluating AMP properties, including antimicrobial and cytotoxic activity, and peptide half-life. By providing innovative and accessible inroads into AMP motifs in proteomes, PyAMPA will enable advances in AMP development and potential translation into clinically useful molecules. PyAMPA is available at: https://github.com/SysBioUAB/PyAMPA.

IMPORTANCE

This paper introduces PyAMPA, a new bioinformatics platform designed for the discovery and optimization of antimicrobial peptides (AMPs). It addresses the urgent need for new antimicrobials due to the rise of antibiotic-resistant infections. PyAMPA, with its five predictive modules -AMPScreen, AMPValidate, AMPSolve, AMPMutate and AMPOptimize, enables high-throughput screening of proteomes to identify potential AMP motifs and optimize them for clinical use. Its unique approach, combining prediction, design, and optimization tools, makes PyAMPA a robust solution for developing new AMP-based therapies, offering a significant advance in combatting antibiotic resistance.

Investigating the synergistic effects of apple vinegar and deep eutectic solvent as natural antibiotics: an experimental and COSMO-RS analysis

The present investigation examines the antimicrobial and antifungal characteristics of natural deep eutectic solvents (NADES) and apple vinegar in relation to a diverse array of bacterial and fungal strains. The clinical bacterial strains, including gram-negative and gram-positive, and the fungal pathogen Candida albicans, were subjected to solid medium diffusion to determine the inhibitory effects of these compounds. The results show that NADES has superior antimicrobial and antifungal action compared to apple vinegar. The observed inhibitory zones for apple vinegar and NADES varied in length from 16.5 to 24.2 and 16 to 52.5 mm, respectively. The results obtained indicate that no synergy is observed for this mixture (50% AV + 50% NADES). The range of values for bactericidal concentrations (MBC) and minimal inhibitory concentrations (MIC) was 0.0125 to 0.2 and 0.0125 to 0.4 µl/ml, respectively. Antibacterial and antifungal chemicals may be found in apple vinegar and NADES, with NADES offering environmentally safe substitutes for traditional antibiotics. Additional investigation is suggested to refine these compounds for a wide range of bacteria, which could create antimicrobial solutions that are both highly effective and specifically targeted, thereby offering extensive potential in medicine and the environment.

Implications of Artificial Intelligence in Addressing Antimicrobial Resistance: Innovations, Global Challenges, and Healthcare's Future

Antibiotic resistance poses a significant threat to global public health due to complex interactions between bacterial genetic factors and external influences such as antibiotic misuse. Artificial intelligence (AI) offers innovative strategies to address this crisis. For example, AI can analyze genomic data to detect resistance markers early on, enabling early interventions. In addition, AI-powered decision support systems can optimize antibiotic use by recommending the most effective treatments based on patient data and local resistance patterns. AI can accelerate drug discovery by predicting the efficacy of new compounds and identifying potential antibacterial agents. Although progress has been made, challenges persist, including data quality, model interpretability, and real-world implementation. A multidisciplinary approach that integrates AI with other emerging technologies, such as synthetic biology and nanomedicine, could pave the way for effective prevention and mitigation of antimicrobial resistance, preserving the efficacy of antibiotics for future generations.

Modeling of Effectiveness of N3-Substituted Amidrazone Derivatives as Potential Agents against Gram-Positive Bacteria

Prediction of the antibacterial activity of new chemical compounds is an important task, due to the growing problem of bacterial drug resistance. Generalized linear models (GLMs) were created using 85 amidrazone derivatives based on the results of antimicrobial activity tests, determined as the minimum inhibitory concentration (MIC) against Gram-positive bacteria: Staphylococcus aureus, Enterococcus faecalis, Micrococcus luteus, Nocardia corallina, and Mycobacterium smegmatis. For the analysis of compounds characterized by experimentally measured MIC values, we included physicochemical properties (e.g., molecular weight, number of hydrogen donors and acceptors, topological polar surface area, compound percentages of carbon, nitrogen, and oxygen, melting points, and lipophilicity) as potential predictors. The presence of R1 and R2 substituents, as well as interactions between melting temperature and R1 or R2 substituents, were also considered. The set of potential predictors also included possible biological effects (e.g., antibacterial, antituberculotic) of tested compounds calculated with the PASS (Prediction of Activity Spectra for Substances) program. Using GLMs with least absolute shrinkage and selection (LASSO), least-angle regression, and stepwise selection, statistically significant models with the optimal value of the adjusted determination coefficient and of seven fit criteria were chosen, e.g., Akaike's information criterion. The most often selected variables were as follows: molecular weight, PASS_antieczematic, PASS_anti-inflam, squared melting temperature, PASS_antitumor, and experimental lipophilicity. Additionally, relevant to the bacterial strain, the interactions between melting temperature and R1 or R2 substituents were selected, indicating that the relationship between MIC and melting temperature depends on the type of R1 or R2 substituent.

The Future of Material Scientists in an Age of Artificial Intelligence

Material science has historically evolved in tandem with advancements in technologies for characterization, synthesis, and computation. Another type of technology to add to this mix is machine learning (ML) and artificial intelligence (AI). Now increasingly sophisticated AI-models are seen that can solve progressively harder problems across a variety of fields. From a material science perspective, it is indisputable that machine learning and artificial intelligence offer a potent toolkit with the potential to substantially accelerate research efforts in areas such as the development and discovery of new functional materials. Less clear is how to best harness this development, what new skill sets will be required, and how it may affect established research practices. In this paper, those question are explored with respect to increasingly more sophisticated ML/AI-approaches. To structure the discussion, a conceptual framework of an AI-ladder is introduced. This AI-ladder ranges from basic data-fitting techniques to more advanced functionalities such as semi-autonomous experimentation, experimental design, knowledge generation, hypothesis formulation, and the orchestration of specialized AI modules as stepping-stones toward general artificial intelligence. This ladder metaphor provides a hierarchical framework for contemplating the opportunities, challenges, and evolving skill sets required to stay competitive in the age of artificial intelligence.

In Silico Design of Potential Small-Molecule Antibiotic Adjuvants against Salmonella typhimurium Ortho Acetyl Sulphydrylase Synthase to Address Antimicrobial Resistance

The inhibition of O-acetyl sulphydrylase synthase isoforms has been reported to represent a promising approach for the development of antibiotic adjuvants. This occurs via the organism developing an unpaired oxidative stress response, causing a reduction in antibiotic resistance in vegetative and swarm cell populations. This consequently increases the effectiveness of conventional antibiotics at lower doses. This study aimed to predict potential inhibitors of Salmonella typhimurium ortho acetyl sulphydrylase synthase (StOASS), which has lower binding energy than the cocrystalized ligand pyridoxal 5 phosphate (PLP), using a computer-aided drug design approach including pharmacophore modeling, virtual screening, and in silico ADMET (Absorption, Distribution, Metabolism, Excretion, and Toxicity) evaluation. The screening and molecular docking of 4254 compounds obtained from the PubChem database were carried out using AutoDock vina, while a post-screening analysis was carried out using Discovery Studio. The best three hits were compounds with the PubChem IDs 118614633, 135715279, and 155773276, possessing binding affinities of -9.1, -8.9, and -8.8 kcal/mol, respectively. The in silico ADMET prediction showed that the pharmacokinetic properties of the best hits were relatively good. The optimization of the best three hits via scaffold hopping gave rise to 187 compounds, and they were docked against StOASS; this revealed that lead compound 1 had the lowest binding energy (-9.3 kcal/mol) and performed better than its parent compound 155773276. Lead compound 1, with the best binding affinity, has a hydroxyl group in its structure and a change in the core heterocycle of its parent compound to benzimidazole, and pyrimidine introduces a synergistic effect and consequently increases the binding energy. The stability of the best hit and optimized compound at the StOASS active site was determined using RMSD, RMSF, radius of gyration, and SASA plots generated from a molecular dynamics simulation. The MD simulation results were also used to monitor how the introduction of new functional groups of optimized compounds contributes to the stability of ligands at the target active site. The improved binding affinity of these compounds compared to PLP and their toxicity profile, which is predicted to be mild, highlights them as good inhibitors of StOASS, and hence, possible antimicrobial adjuvants.

Antimicrobial peptides: An alternative to traditional antibiotics

As antibiotic-resistant bacteria and genes continue to emerge, the identification of effective alternatives to traditional antibiotics has become a pressing issue. Antimicrobial peptides are favored for their safety, low residue, and low resistance properties, and their unique antimicrobial mechanisms show significant potential in combating antibiotic resistance. However, the high production cost and weak activity of antimicrobial peptides limit their application. Moreover, traditional laboratory methods for identifying and designing new antimicrobial peptides are time-consuming and labor-intensive, hindering their development. Currently, novel technologies, such as artificial intelligence (AI) are being employed to develop and design new antimicrobial peptide resources, offering new opportunities for the advancement of antimicrobial peptides. This article summarizes the basic characteristics and antimicrobial mechanisms of antimicrobial peptides, as well as their advantages and limitations, and explores the application of AI in antimicrobial peptides prediction amd design. This highlights the crucial role of AI in enhancing the efficiency of antimicrobial peptide research and provides a reference for antimicrobial drug development.

The role and potential of computer-aided drug discovery strategies in the discovery of novel antimicrobials

Antimicrobial resistance (AMR) has become more of a concern in recent decades, particularly in infections associated with global public health threats. The development of new antibiotics is crucial to ensuring infection control and eradicating AMR. Although drug discovery and development are essential processes in the transformation of a drug candidate from the laboratory to the bedside, they are often very complicated, expensive, and time-consuming. The pharmaceutical sector is continuously innovating strategies to reduce research costs and accelerate the development of new drug candidates. Computer-aided drug discovery (CADD) has emerged as a powerful and promising technology that renews the hope of researchers for the faster identification, design, and development of cheaper, less resource-intensive, and more efficient drug candidates. In this review, we discuss an overview of AMR, the potential, and limitations of CADD in AMR drug discovery, and case studies of the successful application of this technique in the rapid identification of various drug candidates. This review will aid in achieving a better understanding of available CADD techniques in the discovery of novel drug candidates against resistant pathogens and other infectious agents.

Explainable artificial intelligence and machine learning: novel approaches to face infectious diseases challenges

Artificial intelligence (AI) and machine learning (ML) are revolutionizing human activities in various fields, with medicine and infectious diseases being not exempt from their rapid and exponential growth. Furthermore, the field of explainable AI and ML has gained particular relevance and is attracting increasing interest. Infectious diseases have already started to benefit from explainable AI/ML models. For example, they have been employed or proposed to better understand complex models aimed at improving the diagnosis and management of coronavirus disease 2019, in the field of antimicrobial resistance prediction and in quantum vaccine algorithms. Although some issues concerning the dichotomy between explainability and interpretability still require careful attention, an in-depth understanding of how complex AI/ML models arrive at their predictions or recommendations is becoming increasingly essential to properly face the growing challenges of infectious diseases in the present century.

The Impact of Data on Structure-Based Binding Affinity Predictions Using Deep Neural Networks

Artificial intelligence (AI) has gained significant traction in the field of drug discovery, with deep learning (DL) algorithms playing a crucial role in predicting protein-ligand binding affinities. Despite advancements in neural network architectures, system representation, and training techniques, the performance of DL affinity prediction has reached a plateau, prompting the question of whether it is truly solved or if the current performance is overly optimistic and reliant on biased, easily predictable data. Like other DL-related problems, this issue seems to stem from the training and test sets used when building the models. In this work, we investigate the impact of several parameters related to the input data on the performance of neural network affinity prediction models. Notably, we identify the size of the binding pocket as a critical factor influencing the performance of our statistical models; furthermore, it is more important to train a model with as much data as possible than to restrict the training to only high-quality datasets. Finally, we also confirm the bias in the typically used current test sets. Therefore, several types of evaluation and benchmarking are required to understand models' decision-making processes and accurately compare the performance of models.

Changes in the Ultrastructure of Staphylococcus aureus Cells Make It Possible to Identify and Analyze the Injuring Effects of Ciprofloxacin, Polycationic Amphiphile and Their Hybrid

The purposeful development of synthetic antibacterial compounds requires an understanding of the relationship between effects of compounds and their chemical structure. This knowledge can be obtained by studying changes in bacteria ultrastructure under the action of antibacterial compounds of a certain chemical structure. Our study was aimed at examination of ultrastructural changes in S. aureus cells caused by polycationic amphiphile based on 1,4‒diazabicyclo[2.2.2]octane (DL412), ciprofloxacin and their hybrid (DL5Cip6); the samples were incubated for 15 and 45 min. DL412 first directly interacted with bacterial cell wall, damaging it, then penetrated into the cell and disrupted cytoplasm. Ciprofloxacin penetrated into cell without visually damaging the cell wall, but altered the cell membrane and cytoplasm, and inhibited the division of bacteria. The ultrastructural characteristics of S. aureus cells damaged by the hybrid clearly differed from those under ciprofloxacin or DL412 action. Signs associated with ciprofloxacin predominated in cell damage patterns from the hybrid. We studied the effect of ciprofloxacin, DL412 and their hybrid on S. aureus biofilm morphology using paraffin sections. Clear differences in compound effects on S. aureus biofilm (45 min incubation) were observed. The results obtained allow us to recommend this simple and cheap approach for the initial assessment of antibiofilm properties of synthesized compounds.

Advances in computational frameworks in the fight against TB: The way forward

Around 1.6 million people lost their life to Tuberculosis in 2021 according to WHO estimates. Although an intensive treatment plan exists against the causal agent, Mycobacterium Tuberculosis, evolution of multi-drug resistant strains of the pathogen puts a large number of global populations at risk. Vaccine which can induce long-term protection is still in the making with many candidates currently in different phases of clinical trials. The COVID-19 pandemic has further aggravated the adversities by affecting early TB diagnosis and treatment. Yet, WHO remains adamant on its "End TB" strategy and aims to substantially reduce TB incidence and deaths by the year 2035. Such an ambitious goal would require a multi-sectoral approach which would greatly benefit from the latest computational advancements. To highlight the progress of these tools against TB, through this review, we summarize recent studies which have used advanced computational tools and algorithms for-early TB diagnosis, anti-mycobacterium drug discovery and in the designing of the next-generation of TB vaccines. At the end, we give an insight on other computational tools and Machine Learning approaches which have successfully been applied in biomedical research and discuss their prospects and applications against TB.

Synergistic Effects of Baicalin and Levofloxacin Against Hypervirulent Klebsiella pneumoniae Biofilm In Vitro

Hypervirulent Klebsiella pneumoniae (hvKp) strains that form biofilms have recently emerged worldwide; however, the mechanisms underlying biofilm formation and disruption remain elusive. In this study, we established a hvKp biofilm model, investigated its in vitro formation pattern, and determined the mechanism of biofilm destruction by baicalin (BA) and levofloxacin (LEV). Our results revealed that hvKp exhibited a strong biofilm-forming ability, forming early and mature biofilms after 3 and 5 d, respectively. Early biofilm and bacterial burden were significantly reduced by BA + LEV and EM + LEV treatments, which destroyed the 3D structure of early biofilms. Conversely, these treatments were less effective against mature biofilm. The expression of both AcrA and wbbM was significantly downregulated in the BA + LEV group. These findings indicated that BA + LEV might inhibit the formation of hvKp biofilm by altering the expression of genes regulating efflux pumps and lipopolysaccharide biosynthesis.

Deep Learning and Antibiotic Resistance

Antibiotic resistance (AR) is a naturally occurring phenomenon with the capacity to render useless all known antibiotics in the fight against bacterial infections. Although bacterial resistance appeared before any human life form, this process has accelerated in the past years. Important causes of AR in modern times could be the over-prescription of antibiotics, the presence of faulty infection-prevention strategies, pollution in overcrowded areas, or the use of antibiotics in agriculture and farming, together with a decreased interest from the pharmaceutical industry in researching and testing new antibiotics. The last cause is primarily due to the high costs of developing antibiotics. The aim of the present review is to highlight the techniques that are being developed for the identification of new antibiotics to assist this lengthy process, using artificial intelligence (AI). AI can shorten the preclinical phase by rapidly generating many substances based on algorithms created by machine learning (ML) through techniques such as neural networks (NN) or deep learning (DL). Recently, a text mining system that incorporates DL algorithms was used to help and speed up the data curation process. Moreover, new and old methods are being used to identify new antibiotics, such as the combination of quantitative structure-activity relationship (QSAR) methods with ML or Raman spectroscopy and MALDI-TOF MS combined with NN, offering faster and easier interpretation of results. Thus, AI techniques are important additional tools for researchers and clinicians in the race for new methods of overcoming bacterial resistance.

Potent antibacterial activity of MXene-functionalized graphene nanocomposites

Two dimensional (2D) nanomaterials display properties with significant biological utility (e.g., antimicrobial activity). In this study, MXene-functionalized graphene (FG) nanocomposites with Ti3C2T x in varying ratios (FG : Ti3C2T x , 25 : 75%, 50 : 50%, and 75 : 25%) were prepared and characterized via scanning electron microscopy, scanning electron microscopy-energy dispersive X-ray (SEM-EDX), high-resolution transmission electron microscopy (HRTEM), and zeta potential analysis. Their cytotoxicity was assessed using immortalized human keratinocytes (HaCaT) cells at three different timepoints, and antibacterial activity was assessed using Gram-positive Methicillin resistant Staphylococcus aureus, MRSA, and Gram-negative neuro-pathogenic Escherichia coli K1 (E. coli K1) in vitro. The nanomaterials and composites displayed potent antibacterial effects against both types of bacteria and low cytotoxicity against HaCaT cells at 200 μg mL-1, which is promising for their utilization for biomedical applications.

Fluoroquinolones Hybrid Molecules as Promising Antibacterial Agents in the Fight against Antibacterial Resistance

The emergence of bacterial resistance has motivated researchers to discover new antibacterial agents. Nowadays, fluoroquinolones keep their status as one of the essential classes of antibacterial agents. The new generations of fluoroquinolones are valuable therapeutic tools with a spectrum of activity, including Gram-positive, Gram-negative, and atypical bacteria. This review article surveys the design of fluoroquinolone hybrids with other antibacterial agents or active compounds and underlines the new hybrids' antibacterial properties. Antibiotic fluoroquinolone hybrids have several advantages over combined antibiotic therapy. Thus, some challenges related to joining two different molecules are under study. Structurally, the obtained hybrids may contain a cleavable or non-cleavable linker, an essential element for their pharmacokinetic properties and mechanism of action. The design of hybrids seems to provide promising antibacterial agents helpful in the fight against more virulent and resistant strains. These hybrid structures have proven superior antibacterial activity and less susceptibility to bacterial resistance than the component molecules. In addition, fluoroquinolone hybrids have demonstrated other biological effects such as anti-HIV, antifungal, antiplasmodic/antimalarial, and antitumor activity. Many fluoroquinolone hybrids are in various phases of clinical trials, raising hopes that new antibacterial agents will be approved shortly.