Prediction of rifampicin resistance beyond the RRDR using structure-based machine learning approaches

Implications of drug resistance in leprosy: disease course, reactions and the use of novel drugs

Leprosy remains a significant neglected tropical disease despite the goal of elimination having been achieved in various endemic nations over the past two decades. Reactional episodes complicate the disease course, resulting in deformities and disability. The main aim of treatment is to kill Mycobacterium leprae and decrease the bacterial load, which could help prevent further bacilli transmission. A major concern in breaking the chain of transmission and possibly for recurrent reactions is the role of drug-resistant bacilli. Though some data is available on the background prevalence of drug resistance in leprosy, there is a paucity of studies that look for resistance specifically in leprosy reactions. Administration of long-term steroids or immunosuppressants for chronic and recurrent responses in the presence of drug resistance has the twin effect of perpetuating the multiplication of resistant bacilli and encouraging the dissemination of leprosy. The increasing trend of prescribing second-line drugs for leprosy or type 2 reactions without prior assessment of drug resistance can potentially precipitate a severe public health problem as this can promote the development of resistance to second-line drugs as well. A comprehensive multicenter study, including drug resistance surveillance testing in cases of reactions, is necessary, along with the current measures to stop the spread of leprosy. Here, we have detailed the history of drug resistance in leprosy, given pointers on when to suspect drug resistance, described the role of resistance in reactions, methods of resistance testing, and the management of resistant cases with second-line therapy.

From Data to Decisions: Leveraging Artificial Intelligence and Machine Learning in Combating Antimicrobial Resistance - a Comprehensive Review

The emergence of drug-resistant bacteria poses a significant challenge to modern medicine. In response, Artificial Intelligence (AI) and Machine Learning (ML) algorithms have emerged as powerful tools for combating antimicrobial resistance (AMR). This review aims to explore the role of AI/ML in AMR management, with a focus on identifying pathogens, understanding resistance patterns, predicting treatment outcomes, and discovering new antibiotic agents. Recent advancements in AI/ML have enabled the efficient analysis of large datasets, facilitating the reliable prediction of AMR trends and treatment responses with minimal human intervention. ML algorithms can analyze genomic data to identify genetic markers associated with antibiotic resistance, enabling the development of targeted treatment strategies. Additionally, AI/ML techniques show promise in optimizing drug administration and developing alternatives to traditional antibiotics. By analyzing patient data and clinical outcomes, these technologies can assist healthcare providers in diagnosing infections, evaluating their severity, and selecting appropriate antimicrobial therapies. While integration of AI/ML in clinical settings is still in its infancy, advancements in data quality and algorithm development suggest that widespread clinical adoption is forthcoming. In conclusion, AI/ML holds significant promise for improving AMR management and treatment outcome.

Engineering G protein-coupled receptors for stabilization

G protein-coupled receptors (GPCRs) are one of the most important families of targets for drug discovery. One of the limiting steps in the study of GPCRs has been their stability, with significant and time-consuming protein engineering often used to stabilize GPCRs for structural characterization and drug screening. Unfortunately, computational methods developed using globular soluble proteins have translated poorly to the rational engineering of GPCRs. To fill this gap, we propose GPCR-tm, a novel and personalized structurally driven web-based machine learning tool to study the impacts of mutations on GPCR stability. We show that GPCR-tm performs as well as or better than alternative methods, and that it can accurately rank the stability changes of a wide range of mutations occurring in various types of class A GPCRs. GPCR-tm achieved Pearson's correlation coefficients of 0.74 and 0.46 on 10-fold cross-validation and blind test sets, respectively. We observed that the (structural) graph-based signatures were the most important set of features for predicting destabilizing mutations, which points out that these signatures properly describe the changes in the environment where the mutations occur. More specifically, GPCR-tm was able to accurately rank mutations based on their effect on protein stability, guiding their rational stabilization. GPCR-tm is available through a user-friendly web server at https://biosig.lab.uq.edu.au/gpcr_tm/.

Phylogenetic Analysis and Comparative Genomics of Brucella abortus and Brucella melitensis Strains in Egypt

Brucellosis is a notifiable disease induced by a facultative intracellular Brucella pathogen. In this study, eight Brucella abortus and eighteen Brucella melitensis strains from Egypt were annotated and compared with RB51 and REV1 vaccines respectively. RAST toolkit in the BV-BRC server was used for annotation, revealing genome length of 3,250,377 bp and 3,285,803 bp, 3289 and 3323 CDS, 48 and 49 tRNA genes, the same number of rRNA (3) genes, 583 and 586 hypothetical proteins, 2697 and 2726 functional proteins for B. abortus and B. melitensis respectively. B. abortus strains exhibit a similar number of candidate genes, while B. melitensis strains showed some differences, especially in the SRR19520422 Faiyum strain. Also, B. melitensis clarified differences in antimicrobial resistance genes (KatG, FabL, MtrA, MtrB, OxyR, and VanO-type) in SRR19520319 Faiyum and (Erm C and Tet K) in SRR19520422 Faiyum strain. Additionally, the whole genome phylogeny analysis proved that all B. abortus strains were related to vaccinated animals and all B. melitensis strains of Menoufia clustered together and closely related to Gharbia, Dameitta, and Kafr Elshiek. The Bowtie2 tool identified 338 (eight B. abortus) and 4271 (eighteen B. melitensis) single nucleotide polymorphisms (SNPs) along the genomes. These variants had been annotated according to type and impact. Moreover, thirty candidate genes were predicted and submitted at GenBank (24 in B. abortus) and (6 in B. melitensis). This study contributes significant insights into genetic variation, virulence factors, and vaccine-related associations of Brucella pathogens, enhancing our knowledge of brucellosis epidemiology and evolution in Egypt.

Staphylococcus aureus response and adaptation to vancomycin

Antibiotic resistance is an increasing challenge for the human pathogen Staphylococcus aureus. Methicillin-resistant S. aureus (MRSA) clones have spread globally, and a growing number display decreased susceptibility to vancomycin, the favoured antibiotic for treatment of MRSA infections. These vancomycin-intermediate S. aureus (VISA) or heterogeneous vancomycin-intermediate S. aureus (hVISA) strains arise from accumulation of a variety of point mutations, leading to cell wall thickening and reduced vancomycin binding to the cell wall building block, Lipid II, at the septum. They display only minor changes in vancomycin susceptibility, with varying tolerance between cells in a population, and therefore, they can be difficult to detect. In this review, we summarize current knowledge of VISA and hVISA. We discuss the role of genetic strain background or epistasis for VISA development and the possibility of strains being 'transient' VISA with gene expression changes mediated by, for example, VraTSR, GraXSR, or WalRK signal transduction systems, leading to temporary vancomycin tolerance. Additionally, we address collateral susceptibility to other antibiotics than vancomycin. Specifically, we estimate how mutations in rpoB, encoding the β-subunit of the RNA polymerase, affect overall protein structure and compare changes with rifampicin resistance. Ultimately, such in-depth analysis of VISA and hVISA strains in terms of genetic and transcriptional changes, as well as changes in protein structures, may pave the way for improved detection and guide antibiotic therapy by revealing strains at risk of VISA development. Such tools will be valuable for keeping vancomycin an asset also in the future.

Tackling the Antimicrobial Resistance "Pandemic" with Machine Learning Tools: A Summary of Available Evidence

Antimicrobial resistance is recognised as one of the top threats healthcare is bound to face in the future. There have been various attempts to preserve the efficacy of existing antimicrobials, develop new and efficient antimicrobials, manage infections with multi-drug resistant strains, and improve patient outcomes, resulting in a growing mass of routinely available data, including electronic health records and microbiological information that can be employed to develop individualised antimicrobial stewardship. Machine learning methods have been developed to predict antimicrobial resistance from whole-genome sequencing data, forecast medication susceptibility, recognise epidemic patterns for surveillance purposes, or propose new antibacterial treatments and accelerate scientific discovery. Unfortunately, there is an evident gap between the number of machine learning applications in science and the effective implementation of these systems. This narrative review highlights some of the outstanding opportunities that machine learning offers when applied in research related to antimicrobial resistance. In the future, machine learning tools may prove to be superbugs' kryptonite. This review aims to provide an overview of available publications to aid researchers that are looking to expand their work with new approaches and to acquaint them with the current application of machine learning techniques in this field.

Prediction of pyrazinamide resistance in Mycobacterium tuberculosis using structure-based machine-learning approaches

Background

Pyrazinamide is one of four first-line antibiotics used to treat tuberculosis; however, antibiotic susceptibility testing for pyrazinamide is challenging. Resistance to pyrazinamide is primarily driven by genetic variation in pncA, encoding an enzyme that converts pyrazinamide into its active form.

Methods

We curated a dataset of 664 non-redundant, missense amino acid mutations in PncA with associated high-confidence phenotypes from published studies and then trained three different machine-learning models to predict pyrazinamide resistance. All models had access to a range of protein structural-, chemical- and sequence-based features.

Results

The best model, a gradient-boosted decision tree, achieved a sensitivity of 80.2% and a specificity of 76.9% on the hold-out test dataset. The clinical performance of the models was then estimated by predicting the binary pyrazinamide resistance phenotype of 4027 samples harbouring 367 unique missense mutations in pncA derived from 24 231 clinical isolates.

Conclusions

This work demonstrates how machine learning can enhance the sensitivity/specificity of pyrazinamide resistance prediction in genetics-based clinical microbiology workflows, highlights novel mutations for future biochemical investigation, and is a proof of concept for using this approach in other drugs.

Environmental and genetic influence on the rate and spectrum of spontaneous mutations in Escherichia coli

Spontaneous mutations are the ultimate source of novel genetic variation on which evolution operates. Although mutation rate is often discussed as a single parameter in evolution, it comprises multiple distinct types of changes at the level of DNA. Moreover, the rates of these distinct changes can be independently influenced by genomic background and environmental conditions. Using fluctuation tests, we characterized the spectrum of spontaneous mutations in Escherichia coli grown in low and high glucose environments. These conditions are known to affect the rate of spontaneous mutation in wild-type MG1655, but not in a ΔluxS deletant strain - a gene with roles in both quorum sensing and the recycling of methylation products used in E. coli's DNA repair process. We find an increase in AT>GC transitions in the low glucose environment, suggesting that processes relating to the production or repair of this mutation could drive the response of overall mutation rate to glucose concentration. Interestingly, this increase in AT>GC transitions is maintained by the glucose non-responsive ΔluxS deletant. Instead, an elevated rate of GC>TA transversions, more common in a high glucose environment, leads to a net non-responsiveness of overall mutation rate for this strain. Our results show how relatively subtle changes, such as the concentration of a carbon substrate or loss of a regulatory gene, can substantially influence the amount and nature of genetic variation available to selection.

The potential role of artificial intelligence in the clinical management of Hansen's disease (leprosy)

Missed and delayed diagnoses of Hansen's disease (HD) are making the battle against it even more complex, increasing its transmission and significantly impacting those affected and their families. This strains public health systems and raises the risk of lifelong impairments and disabilities. Worryingly, the three countries most affected by HD witnessed a growth in new cases in 2022, jeopardizing the World Health Organization's targets to interrupt transmission. Artificial intelligence (AI) can help address these challenges by offering the potential for rapid case detection, customized treatment, and solutions for accessibility challenges-especially in regions with a shortage of trained healthcare professionals. This perspective article explores how AI can significantly impact the clinical management of HD, focusing on therapeutic strategies. AI can help classify cases, ensure multidrug therapy compliance, monitor geographical treatment coverage, and detect adverse drug reactions and antimicrobial resistance. In addition, AI can assist in the early detection of nerve damage, which aids in disability prevention and planning rehabilitation. Incorporating AI into mental health counseling is also a promising contribution to combating the stigma associated with HD. By revolutionizing therapeutic approaches, AI offers a holistic solution to reduce the burden of HD and improve patient outcomes.

Overcoming antibiotic resistance: non-thermal plasma and antibiotics combination inhibits important pathogens

Antibiotic resistance (ATBR) is increasing every year as the overuse of antibiotics (ATBs) and the lack of newly emerging antimicrobial agents lead to an efficient pathogen escape from ATBs action. This trend is alarming and the World Health Organization warned in 2021 that ATBR could become the leading cause of death worldwide by 2050. The development of novel ATBs is not fast enough considering the situation, and alternative strategies are therefore urgently required. One such alternative may be the use of non-thermal plasma (NTP), a well-established antimicrobial agent actively used in a growing number of medical fields. Despite its efficiency, NTP alone is not always sufficient to completely eliminate pathogens. However, NTP combined with ATBs is more potent and evidence has been emerging over the last few years proving this is a robust and highly effective strategy to fight resistant pathogens. This minireview summarizes experimental research addressing the potential of the NTP-ATBs combination, particularly for inhibiting planktonic and biofilm growth and treating infections in mouse models caused by methicillin-resistant Staphylococcus aureus or Pseudomonas aeruginosa. The published studies highlight this combination as a promising solution to emerging ATBR, and further research is therefore highly desirable.

Characterizing and predicting ccRCC-causing missense mutations in Von Hippel-Lindau disease

BACKGROUND

Mutations within the Von Hippel-Lindau (VHL) tumor suppressor gene are known to cause VHL disease, which is characterized by the formation of cysts and tumors in multiple organs of the body, particularly clear cell renal cell carcinoma (ccRCC). A major challenge in clinical practice is determining tumor risk from a given mutation in the VHL gene. Previous efforts have been hindered by limited available clinical data and technological constraints.

METHODS

To overcome this, we initially manually curated the largest set of clinically validated VHL mutations to date, enabling a robust assessment of existing predictive tools on an independent test set. Additionally, we comprehensively characterized the effects of mutations within VHL using in silico biophysical tools describing changes in protein stability, dynamics and affinity to binding partners to provide insights into the structure-phenotype relationship. These descriptive properties were used as molecular features for the construction of a machine learning model, designed to predict the risk of ccRCC development as a result of a VHL missense mutation.

RESULTS

Analysis of our model showed an accuracy of 0.81 in the identification of ccRCC-causing missense mutations, and a Matthew's Correlation Coefficient of 0.44 on a non-redundant blind test, a significant improvement in comparison to the previous available approaches.

CONCLUSION

This work highlights the power of using protein 3D structure to fully explore the range of molecular and functional consequences of genomic variants. We believe this optimized model will better enable its clinical implementation and assist guiding patient risk stratification and management.

Exploring the effects of missense mutations on protein thermodynamics through structure-based approaches: findings from the CAGI6 challenges

Missense mutations are known contributors to diverse genetic disorders, due to their subtle, single amino acid changes imparted on the resultant protein. Because of this, understanding the impact of these mutations on protein stability and function is crucial for unravelling disease mechanisms and developing targeted therapies. The Critical Assessment of Genome Interpretation (CAGI) provides a valuable platform for benchmarking state-of-the-art computational methods in predicting the impact of disease-related mutations on protein thermodynamics. Here we report the performance of our comprehensive platform of structure-based computational approaches to evaluate mutations impacting protein structure and function on 3 challenges from CAGI6: Calmodulin, MAPK1 and MAPK3. Our stability predictors have achieved correlations of up to 0.74 and AUCs of 1 when predicting changes in ΔΔG for MAPK1 and MAPK3, respectively, and AUC of up to 0.75 in the Calmodulin challenge. Overall, our study highlights the importance of structure-based approaches in understanding the effects of missense mutations on protein thermodynamics. The results obtained from the CAGI6 challenges contribute to the ongoing efforts to enhance our understanding of disease mechanisms and facilitate the development of personalised medicine approaches.

Quantitative measurement of antibiotic resistance in Mycobacterium tuberculosis reveals genetic determinants of resistance and susceptibility in a target gene approach

The World Health Organization has a goal of universal drug susceptibility testing for patients with tuberculosis. However, molecular diagnostics to date have focused largely on first-line drugs and predicting susceptibilities in a binary manner (classifying strains as either susceptible or resistant). Here, we used a multivariable linear mixed model alongside whole genome sequencing and a quantitative microtiter plate assay to relate genomic mutations to minimum inhibitory concentration (MIC) in 15,211 Mycobacterium tuberculosis clinical isolates from 23 countries across five continents. We identified 492 unique MIC-elevating variants across 13 drugs, as well as 91 mutations likely linked to hypersensitivity. Our results advance genetics-based diagnostics for tuberculosis and serve as a curated training/testing dataset for development of drug resistance prediction algorithms.

Evaluation of mycobacteria infection prevalence and optimization of the identification process in North Sardinia, Italy

IMPORTANCE

Mycobacterial infection is a major threat to public health worldwide. Accurate identification of infected species and drug resistance detection are critical factors in treatment. We focused on shortening the turn-around time of identifying mycobacteria species and antibiotic resistance tests.

AI-Driven Enhancements in Drug Screening and Optimization

The greatest challenge in drug discovery remains the high rate of attrition across the different phases of the process, which cost the industry billions of dollars every year. While all phases remain crucial to ensure pharmaceutical-level safety, quality, and efficacy of the end product, streamlining these efforts toward compounds with success potential is pivotal for a more efficient and cost-effective process. The use of artificial intelligence (AI) within the pharmaceutical industry aims at just this, and has applications in preclinical screening for biological activity, optimization of pharmacokinetic properties for improved drug formulation, early toxicity prediction which reduces attrition, and pre-emptively screening for genetic changes in the biological target to improve therapeutic longevity. Here, we present a series of in silico tools that address these applications in small molecule development and describe how they can be embedded within the current pharmaceutical development pipeline.

A computational method for predicting the most likely evolutionary trajectories in the stepwise accumulation of resistance mutations

Pathogen evolution of drug resistance often occurs in a stepwise manner via the accumulation of multiple mutations that in combination have a non-additive impact on fitness, a phenomenon known as epistasis. The evolution of resistance via the accumulation of point mutations in the DHFR genes of Plasmodium falciparum (Pf) and Plasmodium vivax (Pv) has been studied extensively and multiple studies have shown epistatic interactions between these mutations determine the accessible evolutionary trajectories to highly resistant multiple mutations. Here, we simulated these evolutionary trajectories using a model of molecular evolution, parameterised using Rosetta Flex ddG predictions, where selection acts to reduce the target-drug binding affinity. We observe strong agreement with pathways determined using experimentally measured IC50 values of pyrimethamine binding, which suggests binding affinity is strongly predictive of resistance and epistasis in binding affinity strongly influences the order of fixation of resistance mutations. We also infer pathways directly from the frequency of mutations found in isolate data, and observe remarkable agreement with the most likely pathways predicted by our mechanistic model, as well as those determined experimentally. This suggests mutation frequency data can be used to intuitively infer evolutionary pathways, provided sufficient sampling of the population.

Characterization on the oncogenic effect of the missense mutations of p53 via machine learning

Dysfunctions caused by missense mutations in the tumour suppressor p53 have been extensively shown to be a leading driver of many cancers. Unfortunately, it is time-consuming and labour-intensive to experimentally elucidate the effects of all possible missense variants. Recent works presented a comprehensive dataset and machine learning model to predict the functional outcome of mutations in p53. Despite the well-established dataset and precise predictions, this tool was trained on a complicated model with limited predictions on p53 mutations. In this work, we first used computational biophysical tools to investigate the functional consequences of missense mutations in p53, informing a bias of deleterious mutations with destabilizing effects. Combining these insights with experimental assays, we present two interpretable machine learning models leveraging both experimental assays and in silico biophysical measurements to accurately predict the functional consequences on p53 and validate their robustness on clinical data. Our final model based on nine features obtained comparable predictive performance with the state-of-the-art p53 specific method and outperformed other generalized, widely used predictors. Interpreting our models revealed that information on residue p53 activity, polar atom distances and changes in p53 stability were instrumental in the decisions, consistent with a bias of the properties of deleterious mutations. Our predictions have been computed for all possible missense mutations in p53, offering clinical diagnostic utility, which is crucial for patient monitoring and the development of personalized cancer treatment.

Quantitative measurement of antibiotic resistance in Mycobacterium tuberculosis reveals genetic determinants of resistance and susceptibility in a target gene approach

The World Health Organization has a goal of universal drug susceptibility testing for patients with tuberculosis; however, molecular diagnostics to date have focused largely on first-line drugs and predicting binary susceptibilities. We used a multivariable linear mixed model alongside whole genome sequencing and a quantitative microtiter plate assay to relate genomic mutations to minimum inhibitory concentration in 15,211 Mycobacterium tuberculosis patient isolates from 23 countries across five continents. This identified 492 unique MIC-elevating variants across thirteen drugs, as well as 91 mutations likely linked to hypersensitivity. Our results advance genetics-based diagnostics for tuberculosis and serve as a curated training/testing dataset for development of drug resistance prediction algorithms.

Bioinformatics toolbox for exploring target mutation-induced drug resistance

Drug resistance is increasingly among the main issues affecting human health and threatening agriculture and food security. In particular, developing approaches to overcome target mutation-induced drug resistance has long been an essential part of biological research. During the past decade, many bioinformatics tools have been developed to explore this type of drug resistance, and they have become popular for elucidating drug resistance mechanisms in a low cost, fast and effective way. However, these resources are scattered and underutilized, and their strengths and limitations have not been systematically analyzed and compared. Here, we systematically surveyed 59 freely available bioinformatics tools for exploring target mutation-induced drug resistance. We analyzed and summarized these resources based on their functionality, data volume, data source, operating principle, performance, etc. And we concisely discussed the strengths, limitations and application examples of these tools. Specifically, we tested some predictive tools and offered some thoughts from the clinician's perspective. Hopefully, this work will provide a useful toolbox for researchers working in the biomedical, pesticide, bioinformatics and pharmaceutical engineering fields, and a good platform for non-specialists to quickly understand drug resistance prediction.

Mutually beneficial confluence of structure-based modeling of protein dynamics and machine learning methods

Proteins sample an ensemble of conformers under physiological conditions, having access to a spectrum of modes of motions, also called intrinsic dynamics. These motions ensure the adaptation to various interactions in the cell, and largely assist in, if not determine, viable mechanisms of biological function. In recent years, machine learning frameworks have proven uniquely useful in structural biology, and recent studies further provide evidence to the utility and/or necessity of considering intrinsic dynamics for increasing their predictive ability. Efficient quantification of dynamics-based attributes by recently developed physics-based theories and models such as elastic network models provides a unique opportunity to generate data on dynamics for training ML models towards inferring mechanisms of protein function, assessing pathogenicity, or estimating binding affinities.

The mutation rate of rpoB gene showed an upward trend with the increase of MIRU10, MIRU39 and QUB4156 repetitive number

BACKGROUND

Mycobacterial interspersed repetitive unit-variable number tandem repeat (MIRU-VNTR) is a frequently used typing method for identifying the Beijing genotype of Mycobacterium tuberculosis (Mtb), which is easily transformed into rifampicin (RIF) resistance. The RIF resistance of Mtb is considered to be highly related with the mutation of rpoB gene. Therefore, this study aimed to analyze the relationship between the repetitive number of MIRU loci and the mutation of rpoB gene.

METHODS

An open-source whole-genome sequencing data of Mtb was used to detect the mutation of rpoB gene and the repetitive number of MIRU loci by bioinformatics methods. Cochran-Armitage analysis was performed to analyze the trend of the rpoB gene mutation rate and the repetitive number of MIRU loci.

RESULTS

Among 357 rifampicin-resistant tuberculosis (RR-TB), 304 strains with mutated rpoB genes were detected, and 6 of 67 rifampicin susceptible strains were detected mutations. The rpoB gene mutational rate showed an upward trend with the increase of MIRU10, MIRU39, QUB4156 and MIRU16 repetitive number, but only the repetitive number of MIRU10, MRIU39 and QUB4156 were risk factors for rpoB gene mutation. The Hunter-Gaston discriminatory index (HGDI) of MIRU10 (0.65) and QUB4156 (0.62) was high in the overall sample, while MIRU39 (0.39) and MIRU16 (0.43) showed a moderate discriminatory Power.

CONCLUSION

The mutation rate of rpoB gene increases with the addition of repetitive numbers of MIRU10, QUB4156 and MIRU39 loci.

Using Graph-Based Signatures to Guide Rational Antibody Engineering

Antibodies are essential experimental and diagnostic tools and as biotherapeutics have significantly advanced our ability to treat a range of diseases. With recent innovations in computational tools to guide protein engineering, we can now rationally design better antibodies with improved efficacy, stability, and pharmacokinetics. Here, we describe the use of the mCSM web-based in silico suite, which uses graph-based signatures to rapidly identify the structural and functional consequences of mutations, to guide rational antibody engineering to improve stability, affinity, and specificity.

Identifying the molecular drivers of ALS-implicated missense mutations

BACKGROUND

Amyotrophic lateral sclerosis (ALS) is a progressively fatal, neurodegenerative disease associated with both motor and non-motor symptoms, including frontotemporal dementia. Approximately 10% of cases are genetically inherited (familial ALS), while the majority are sporadic. Mutations across a wide range of genes have been associated; however, the underlying molecular effects of these mutations and their relation to phenotypes remain poorly explored.

METHODS

We initially curated an extensive list (n=1343) of missense mutations identified in the clinical literature, which spanned across 111 unique genes. Of these, mutations in genes SOD1, FUS and TDP43 were analysed using in silico biophysical tools, which characterised changes in protein stability, interactions, localisation and function. The effects of pathogenic and non-pathogenic mutations within these genes were statistically compared to highlight underlying molecular drivers.

RESULTS

Compared with previous ALS-dedicated databases, we have curated the most extensive missense mutation database to date and observed a twofold increase in unique implicated genes, and almost a threefold increase in the number of mutations. Our gene-specific analysis identified distinct molecular drivers across the different proteins, where SOD1 mutations primarily reduced protein stability and dimer formation, and those in FUS and TDP-43 were present within disordered regions, suggesting different mechanisms of aggregate formation.

CONCLUSION

Using our three genes as case studies, we identified distinct insights which can drive further research to better understand ALS. The information curated in our database can serve as a resource for similar gene-specific analyses, further improving the current understanding of disease, crucial for the development of treatment strategies.

JMM profile: rifampicin: a broad-spectrum antibiotic

Rifampicin (also known as rifampin) inhibits RNA synthesis, and is used to treat tuberculosis, leprosy, staphylococcal infections and legionnaires’ disease. It can also protect at-risk populations from Haemophilus influenzae type b and Neisseria meningitidis . It is a polyketide antibiotic and is on the World Health Organization (WHO) list of essential medicines due to its critical importance to human medicine. The adverse effect of liver toxicity is controlled by testing during prolonged treatment regimes. Rifampicin’s red–orange colour can result in the colouration of sweat, tears and urine. Resistance to rifampicin arises from mutation of the target RNA polymerase or ADP ribosylation of the antibiotic or efflux. Mycobacteria may become singularly resistant to rifampicin or as part of multidrug or extensive drug resistance.

Intra-host genetic population diversity: Role in emergence and persistence of drug resistance among Mycobacterium tuberculosis complex minor variants

Drug resistant tuberculosis (DR-TB) is an important public health issue in different parts of the world. Mycobacterium tuberculosis complex variants (MTBC vars) preferentially infect certain hosts, limiting their distribution to different ecosystems. However, MTBC vars can infect other hosts beyond their preferred target potentially contributing to persistence of drug resistance (DR) in other niches. Here, we performed a comprehensive intra-host genetic analysis for the identification of DR-related mutations among all MTBC minor vars whole genome sequences (8,095 strains) publicly available worldwide. High confidence drug-resistance mutations in katG (isoniazid), rpsL (streptomycin), pncA (pyrazinamide), rpoB (rifampicin) and gyrA (fluoroquinolones) genes were identified among intrahost minor sub-populations in 197 different strains (2.43%) belonging to vars africanum, bovis, caprae, microti, orygis and pinnipedii. In addition, a three-dimensional structure modeling analysis to assess the role of novel mutations was also performed. Our findings highlight the importance of detecting discrete intra-host populations carrying DR mutations.

Systematic evaluation of computational tools to predict the effects of mutations on protein stability in the absence of experimental structures

Changes in protein sequence can have dramatic effects on how proteins fold, their stability and dynamics. Over the last 20 years, pioneering methods have been developed to try to estimate the effects of missense mutations on protein stability, leveraging growing availability of protein 3D structures. These, however, have been developed and validated using experimentally derived structures and biophysical measurements. A large proportion of protein structures remain to be experimentally elucidated and, while many studies have based their conclusions on predictions made using homology models, there has been no systematic evaluation of the reliability of these tools in the absence of experimental structural data. We have, therefore, systematically investigated the performance and robustness of ten widely used structural methods when presented with homology models built using templates at a range of sequence identity levels (from 15% to 95%) and contrasted performance with sequence-based tools, as a baseline. We found there is indeed performance deterioration on homology models built using templates with sequence identity below 40%, where sequence-based tools might become preferable. This was most marked for mutations in solvent exposed residues and stabilizing mutations. As structure prediction tools improve, the reliability of these predictors is expected to follow, however we strongly suggest that these factors should be taken into consideration when interpreting results from structure-based predictors of mutation effects on protein stability.

cropCSM: designing safe and potent herbicides with graph-based signatures

Herbicides have revolutionised weed management, increased crop yields and improved profitability allowing for an increase in worldwide food security. Their widespread use, however, has also led to a rise in resistance and concerns about their environmental impact. Despite the need for potent and safe herbicidal molecules, no herbicide with a new mode of action has reached the market in 30 years. Although development of computational approaches has proven invaluable to guide rational drug discovery pipelines, leading to higher hit rates and lower attrition due to poor toxicity, little has been done in contrast for herbicide design. To fill this gap, we have developed cropCSM, a computational platform to help identify new, potent, nontoxic and environmentally safe herbicides. By using a knowledge-based approach, we identified physicochemical properties and substructures enriched in safe herbicides. By representing the small molecules as a graph, we leveraged these insights to guide the development of predictive models trained and tested on the largest collected data set of molecules with experimentally characterised herbicidal profiles to date (over 4500 compounds). In addition, we developed six new environmental and human toxicity predictors, spanning five different species to assist in molecule prioritisation. cropCSM was able to correctly identify 97% of herbicides currently available commercially, while predicting toxicity profiles with accuracies of up to 92%. We believe cropCSM will be an essential tool for the enrichment of screening libraries and to guide the development of potent and safe herbicides. We have made the method freely available through a user-friendly webserver at http://biosig.unimelb.edu.au/crop_csm.

Machine Learning Based Predictive Model for the Analysis of Sequence Activity Relationships Using Protein Spectra and Protein Descriptors

Accurately establishing the connection between a protein sequence and its function remains a focal point within the field of protein engineering, especially in the context of predicting the effects of mutations. From this, there has been a continued drive to build accurate and reliable predictive models via machine learning that allow for the virtual screening of many protein mutant sequences, measuring the relationship between sequence and 'fitness' or 'activity', commonly known as a Sequence-Activity-Relationship (SAR). An important preliminary stage in the building of these predictive models is the encoding of the chosen sequences. Evaluated in this work is a plethora of encoding strategies using the Amino Acid Index database, where the indices are transformed into their spectral form via Digital Signal Processing (DSP) techniques, as well as numerous protein structural and physiochemical descriptors. The encoding strategies are explored on a dataset curated to measure the thermostability of various mutants from a recombination library, designed from parental cytochrome P450s. In this work it was concluded that the implementation of protein spectra in concatenation with protein descriptors, together with the Partial Least Squares Regression (PLS) algorithm, gave the most noteworthy increase in the quality of the predictive models (as described in Encoding Strategy C), highlighting their utility in identifying an SAR. The accompanying software produced for this paper is termed pySAR (Python Sequence-Activity-Relationship), which allows for a user to find the optimal arrangement of structural and or physiochemical properties to encode their specific mutant library dataset; the source code is available at: https://github.com/amckenna41/pySAR.

The Structural Basis of Mycobacterium tuberculosis RpoB Drug-Resistant Clinical Mutations on Rifampicin Drug Binding

Tuberculosis (TB), caused by the Mycobacterium tuberculosis infection, continues to be a leading cause of morbidity and mortality in developing countries. Resistance to the first-line anti-TB drugs, isoniazid (INH) and rifampicin (RIF), is a major drawback to effective TB treatment. Genetic mutations in the β-subunit of the DNA-directed RNA polymerase (rpoB) are reported to be a major reason of RIF resistance. However, the structural basis and mechanisms of these resistant mutations are insufficiently understood. In the present study, thirty drug-resistant mutants of rpoB were initially modeled and screened against RIF via a comparative molecular docking analysis with the wild-type (WT) model. These analyses prioritized six mutants (Asp441Val, Ser456Trp, Ser456Gln, Arg454Gln, His451Gly, and His451Pro) that showed adverse binding affinities, molecular interactions, and RIF binding hinderance properties, with respect to the WT. These mutant models were subsequently analyzed by molecular dynamics (MD) simulations. One-hundred nanosecond all-atom MD simulations, binding free energy calculations, and a dynamic residue network analysis (DRN) were employed to exhaustively assess the impact of mutations on RIF binding dynamics. Considering the global structural motions and protein-ligand binding affinities, the Asp441Val, Ser456Gln, and His454Pro mutations generally yielded detrimental effects on RIF binding. Locally, we found that the electrostatic contributions to binding, particularly by Arg454 and Glu487, might be adjusted to counteract resistance. The DRN analysis revealed that all mutations mostly distorted the communication values of the critical hubs and may, therefore, confer conformational changes in rpoB to perturb RIF binding. In principle, the approach combined fundamental molecular modeling tools for robust "global" and "local" level analyses of structural dynamics, making it well suited for investigating other similar drug resistance cases.

mmCSM-NA: accurately predicting effects of single and multiple mutations on protein-nucleic acid binding affinity

While protein-nucleic acid interactions are pivotal for many crucial biological processes, limited experimental data has made the development of computational approaches to characterise these interactions a challenge. Consequently, most approaches to understand the effects of missense mutations on protein-nucleic acid affinity have focused on single-point mutations and have presented a limited performance on independent data sets. To overcome this, we have curated the largest dataset of experimentally measured effects of mutations on nucleic acid binding affinity to date, encompassing 856 single-point mutations and 141 multiple-point mutations across 155 experimentally solved complexes. This was used in combination with an optimized version of our graph-based signatures to develop mmCSM-NA (http://biosig.unimelb.edu.au/mmcsm_na), the first scalable method capable of quantitatively and accurately predicting the effects of multiple-point mutations on nucleic acid binding affinities. mmCSM-NA obtained a Pearson's correlation of up to 0.67 (RMSE of 1.06 Kcal/mol) on single-point mutations under cross-validation, and up to 0.65 on independent non-redundant datasets of multiple-point mutations (RMSE of 1.12 kcal/mol), outperforming similar tools. mmCSM-NA is freely available as an easy-to-use web-server and API. We believe it will be an invaluable tool to shed light on the role of mutations affecting protein-nucleic acid interactions in diseases.

Artificial intelligence and machine learning assisted drug delivery for effective treatment of infectious diseases

In the era of antimicrobial resistance, the prevalence of multidrug-resistant microorganisms that resist conventional antibiotic treatment has steadily increased. Thus, it is now unquestionable that infectious diseases are significant global burdens that urgently require innovative treatment strategies. Emerging studies have demonstrated that artificial intelligence (AI) can transform drug delivery to promote effective treatment of infectious diseases. In this review, we propose to evaluate the significance, essential principles, and popular tools of AI in drug delivery for infectious disease treatment. Specifically, we will focus on the achievements and key findings of current research, as well as the applications of AI on drug delivery throughout the whole antimicrobial treatment process, with an emphasis on drug development, treatment regimen optimization, drug delivery system and administration route design, and drug delivery outcome prediction. To that end, the challenges of AI in drug delivery for infectious disease treatments and their current solutions and future perspective will be presented and discussed.

Structure-guided machine learning prediction of drug resistance mutations in Abelson 1 kinase

Kinases play crucial roles in cellular signalling and biological processes with their dysregulation associated with diseases, including cancers. Kinase inhibitors, most notably those targeting ABeLson 1 (ABL1) kinase in chronic myeloid leukemia, have had a significant impact on cancer survival, yet emergence of resistance mutations can reduce their effectiveness, leading to therapeutic failure. Limited effort, however, has been devoted to developing tools to accurately identify ABL1 resistance mutations, as well as providing insights into their molecular mechanisms. Here we investigated the structural basis of ABL1 mutations modulating binding affinity of eight FDA-approved drugs. We found mutations impair affinity of type I and type II inhibitors differently and used this insight to developed a novel web-based diagnostic tool, SUSPECT-ABL, to pre-emptively predict resistance profiles and binding free-energy changes (ΔΔG) of all possible ABL1 mutations against inhibitors with different binding modes. Resistance mutations in ABL1 were successfully identified, achieving a Matthew's Correlation Coefficient of up to 0.73 and the resulting change in ligand binding affinity with a Pearson's correlation of up to 0.77, with performances consistent across non-redundant blind tests. Through an in silico saturation mutagenesis, our tool has identified possibly emerging resistance mutations, which offers opportunities for in vivo experimental validation. We believe SUSPECT-ABL will be an important tool not just for improving precision medicine efforts, but for facilitating the development of next-generation inhibitors that are less prone to resistance. We have made our tool freely available at http://biosig.unimelb.edu.au/suspect_abl/.

mmCSM-PPI: predicting the effects of multiple point mutations on protein-protein interactions

Protein-protein interactions play a crucial role in all cellular functions and biological processes and mutations leading to their disruption are enriched in many diseases. While a number of computational methods to assess the effects of variants on protein-protein binding affinity have been proposed, they are in general limited to the analysis of single point mutations and have been shown to perform poorly on independent test sets. Here, we present mmCSM-PPI, a scalable and effective machine learning model for accurately assessing changes in protein-protein binding affinity caused by single and multiple missense mutations. We expanded our well-established graph-based signatures in order to capture physicochemical and geometrical properties of multiple wild-type residue environments and integrated them with substitution scores and dynamics terms from normal mode analysis. mmCSM-PPI was able to achieve a Pearson's correlation of up to 0.75 (RMSE = 1.64 kcal/mol) under 10-fold cross-validation and 0.70 (RMSE = 2.06 kcal/mol) on a non-redundant blind test, outperforming existing methods. Our method is freely available as a user-friendly and easy-to-use web server and API at http://biosig.unimelb.edu.au/mmcsm_ppi.

Distinguishing between PTEN clinical phenotypes through mutation analysis

Phosphate and tensin homolog on chromosome ten (PTEN) germline mutations are associated with an overarching condition known as PTEN hamartoma tumor syndrome. Clinical phenotypes associated with this syndrome range from macrocephaly and autism spectrum disorder to Cowden syndrome, which manifests as multiple noncancerous tumor-like growths (hamartomas), and an increased predisposition to certain cancers. It is unclear, however, the basis by which mutations might lead to these very diverse phenotypic outcomes. Here we show that, by considering the molecular consequences of mutations in PTEN on protein structure and function, we can accurately distinguish PTEN mutations exhibiting different phenotypes. Changes in phosphatase activity, protein stability, and intramolecular interactions appeared to be major drivers of clinical phenotype, with cancer-associated variants leading to the most drastic changes, while ASD and non-pathogenic variants associated with more mild and neutral changes, respectively. Importantly, we show via saturation mutagenesis that more than half of variants of unknown significance could be associated with disease phenotypes, while over half of Cowden syndrome mutations likely lead to cancer. These insights can assist in exploring potentially important clinical outcomes delineated by PTEN variation.

Mechanisms and detection methods of Mycobacterium tuberculosis rifampicin resistance: The phenomenon of drug resistance is complex

Tuberculosis (TB) is an infectious disease that poses a serious threat to human health. Rifampin (RIF) is an important first-line anti-TB drug, and rifampin resistance (RIF-R) is a key factor in formulating treatment regimen and evaluating the prognosis of TB. Compared with other drugs resistance, the RIF-R mechanism of Mycobacterium tuberculosis (M. tuberculosis) is one of the clearest, which is mainly caused by RIF resistance-related mutations in the rpoB gene. This provides a convenient condition for developing rapid detection methods, and also an ideal object for studying the general drug resistance mechanisms of M. tuberculosis. This review focuses on the mechanisms that influence the RIF resistance of M. tuberculosis and related detection methods. Besides the mutations in rpoB, M. tuberculosis can decrease the amount of drugs entering the cells, enhance the drugs efflux, and be heterogeneous RIF susceptibility to resist drug pressure. Based on the results of current researches, many genes participate in influencing the susceptibility to RIF, which indicates the phenomenon of M. tuberculosis drug resistance is very complex.