mCSM-lig: quantifying the effects of mutations on protein-small molecule affinity in genetic disease and emergence of drug resistance

A benchmark for evaluation of structure-based online tools for antibody-antigen binding affinity

The prediction of binding affinity changes caused by missense mutations can elucidate antigen-antibody interactions. A few accessible structure-based online computational tools have been proposed. However, selecting suitable software for particular research is challenging, especially research on the SARS-CoV-2 spike protein with antibodies. Therefore, benchmarking of the mutation-diverse SARS-CoV-2 datasets is critical. Here, we collected the datasets including 1216 variants about the changes in binding affinity of antigens from 22 complexes for SARS-CoV-2 S proteins and 22 monoclonal antibodies as well as applied them to evaluate the performance of seven binding affinity prediction tools. The tested tools' Pearson correlations between predicted and measured changes in binding affinity were between -0.158 and 0.657, while accuracy in classification tasks on predicting increasing or decreasing affinity ranged from 0.444 to 0.834. These tools performed relatively better on predicting single mutations, especially at epitope sites, whereas poor performance on extremely decreasing affinity. The tested tools were relatively insensitive to the experimental techniques used to obtain structures of complexes. In summary, we constructed a list of datasets and evaluated a range of structure-based online prediction tools that will explicate relevant processes of antigen-antibody interactions and enhance the computational design of therapeutic monoclonal antibodies.

piscesCSM: prediction of anticancer synergistic drug combinations

While drug combination therapies are of great importance, particularly in cancer treatment, identifying novel synergistic drug combinations has been a challenging venture. Computational methods have emerged in this context as a promising tool for prioritizing drug combinations for further evaluation, though they have presented limited performance, utility, and interpretability. Here, we propose a novel predictive tool, piscesCSM, that leverages graph-based representations to model small molecule chemical structures to accurately predict drug combinations with favourable anticancer synergistic effects against one or multiple cancer cell lines. Leveraging these insights, we developed a general supervised machine learning model to guide the prediction of anticancer synergistic drug combinations in over 30 cell lines. It achieved an area under the receiver operating characteristic curve (AUROC) of up to 0.89 on independent non-redundant blind tests, outperforming state-of-the-art approaches on both large-scale oncology screening data and an independent test set generated by AstraZeneca (with more than a 16% improvement in predictive accuracy). Moreover, by exploring the interpretability of our approach, we found that simple physicochemical properties and graph-based signatures are predictive of chemotherapy synergism. To provide a simple and integrated platform to rapidly screen potential candidate pairs with favourable synergistic anticancer effects, we made piscesCSM freely available online at https://biosig.lab.uq.edu.au/piscescsm/ as a web server and API. We believe that our predictive tool will provide a valuable resource for optimizing and augmenting combinatorial screening libraries to identify effective and safe synergistic anticancer drug combinations. SCIENTIFIC CONTRIBUTION: This work proposes piscesCSM, a machine-learning-based framework that relies on well-established graph-based representations of small molecules to identify and provide better predictive accuracy of syngenetic drug combinations. Our model, piscesCSM, shows that combining physiochemical properties with graph-based signatures can outperform current architectures on classification prediction tasks. Furthermore, implementing our tool as a web server offers a user-friendly platform for researchers to screen for potential synergistic drug combinations with favorable anticancer effects against one or multiple cancer cell lines.

Molecular Mechanism of Fusarium Fungus Inhibition by Phenazine-1-carboxamide

Fusarium head blight caused by Fusarium graminearum is a devastating disease in wheat that seriously endangers food security and human health. Previous studies have found that the secondary metabolite phenazine-1-carboxamide produced by biocontrol bacteria inhibited F. graminearum by binding to and inhibiting the activity of histone acetyltransferase Gcn5 (FgGcn5). However, the detailed mechanism of this inhibition remains unknown. Our structural and biochemical studies revealed that phenazine-1-carboxamide (PCN) binds to the histone acetyltransferase (HAT) domain of FgGcn5 at its cosubstrate acetyl-CoA binding site, thus competitively inhibiting the histone acetylation function of the enzyme. Alanine substitution of the residues in the binding site shared by PCN and acetyl-CoA not only decreased the histone acetylation level of the enzyme but also dramatically impacted the development, mycotoxin synthesis, and virulence of the strain. Taken together, our study elucidated a competitive inhibition mechanism of Fusarium fungus by PCN and provided a structural template for designing more potent phenazine-based fungicides.

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/.

Elucidating the binding mechanism of SARS-CoV-2 NSP6-TBK1 and structure-based designing of phytocompounds inhibitors for instigating the host immune response

SARS-CoV-2, also referred to as severe acute respiratory syndrome coronavirus 2, is the virus responsible for causing COVID-19, an infectious disease that emerged in Wuhan, China, in December 2019. Among its crucial functions, NSP6 plays a vital role in evading the human immune system by directly interacting with a receptor called TANK-binding kinase (TBK1), leading to the suppression of IFNβ production. Consequently, in the present study we used the structural and biophysical approaches to analyze the effect of newly emerged mutations on the binding of NSP6 and TBK1. Among the identified mutations, four (F35G, L37F, L125F, and I162T) were found to significantly destabilize the structure of NSP6. Furthermore, the molecular docking analysis highlighted that the mutant NSP6 displayed its highest binding affinity with TBK1, exhibiting docking scores of -1436.2 for the wildtype and -1723.2, -1788.6, -1510.2, and -1551.7 for the F35G, L37F, L125F, and I162T mutants, respectively. This suggests the potential for an enhanced immune system evasion capability of NSP6. Particularly, the F35G mutation exhibited the strongest binding affinity, supported by a calculated binding free energy of -172.19 kcal/mol. To disrupt the binding between NSP6 and TBK1, we conducted virtual drug screening to develop a novel inhibitor derived from natural products. From this screening, we identified the top 5 hit compounds as the most promising candidates with a docking score of -6.59 kcal/mol, -6.52 kcal/mol, -6.32 kcal/mol, -6.22 kcal/mol, and -6.21 kcal/mol. The molecular dynamic simulation of top 3 hits further verified the dynamic stability of drugs-NSP6 complexes. In conclusion, this study provides valuable insight into the higher infectivity of the SARS-CoV-2 new variants and a strong rationale for the development of novel drugs against NSP6.

Investigating the ibrutinib resistance mechanism of L528W mutation on Bruton's tyrosine kinase via molecular dynamics simulations

Drug resistance to Bruton's Tyrosine Kinase (BTK) inhibitors presents a challenge in treating B-cell malignancies, and the mechanism behind drug resistance remains unclear. In this study, we focused on the BTK L528W mutation and investigated the underlying mechanisms of resistance to ibrutinib (including prototype and its active metabolite from, PCI-45227) using a combination of bioinformatics analysis, and molecular dynamics (MD) simulations. Protein stability of wild type (WT) BTK and L528W mutant was predicted using DUET, PoPMuSiC, and I-Mutant2.0. We performed MD simulations of six systems, apo-WT, metabolite-WT, prototype-WT and their mutants, to analyze the significant conformational and BTK-inhibitor binding affinity changes induced by the L528W mutation. Results show that the L528W mutation reduces the conformational stability of BTK compared to the WT. Principal component analysis (PCA) based free energy landscape (FEL) analysis shows that the L528W mutant ensemble tends to form more conformation clusters and exhibit higher levels of local minima than the WT counterpart. The interaction analysis reveal that the L528W mutation disrupts the strong hydrogen bond between Cys481 and inhibitors and reduces the number of hydrogen bonds between inhibitors and BTK in the L528W mutant complex structures compared to the WT. Porcupine plot analysis in association with cross-correlation analysis show the high-intensity flexible motion exhibited by the P-loop region. MM/GBSA calculations show that the L528W mutation in metabolite-BTK and prototype-BTK complexes increases binding free energy compared to the WT, with a reduction in binding affinity confirmed by per-residue energy decomposition. Specifically, the binding free energy increases from -57.86 kcal/mol to -48.26 kcal/mol for the metabolite-BTK complex and from -62.04 kcal/mol to -50.55 kcal/mol for the prototype-BTK complex. Overall, our study finds that the L528W mutation reduces BTK stability, decreases binding affinity, and leads to drug resistance and potential disease recurrence.

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.

Molecular docking and MD simulations reveal protease inhibitors block the catalytic residues in Prp8 intein of Aspergillus fumigatus: a potential target for antimycotics

Resistance to azoles and amphotericin B especially in Aspergillus fumigatus is a growing concern towards the treatment of invasive fungal infection. At this critical juncture, intein splicing would be a productive, and innovative target to establish therapies against resistant strains. Intein splicing is the central event for the activation of host protein, essential for the growth and survival of various microorganisms including A. fumigatus. The splicing process is a four-step protease-like nucleophilic cascade. Thus, we hypothesise that protease inhibitors would successfully halt intein splicing and potentially restrict the growth of the aforementioned pathogen. Using Rosetta Fold and molecular dynamics simulations, we modelled Prp8 intein structure; resembling classic intein fold with horse shoe shaped splicing domain. To fully comprehend the active site of Afu Prp8 intein, C1, T62, H65, H818, N819 from intein sequences and S820, the first C-extein residue are selected. Molecular docking shows that two FDA-approved drugs, i.e. Lufotrelvir and Remdesivir triphosphate efficiently interact with Prp8 intein from the assortment of 212 protease inhibitors. MD simulation portrayed that Prp8 undergoes conformational change upon ligand binding, and inferred the molecular recognition and stability of the docked complexes. Per-residue decomposition analysis confirms the importance of F: block R802, V803, and Q807 binding pocket in intein splicing domain towards recognition of inhibitors, along with active site residues through strong hydrogen bonds and hydrophobic contacts. However, in vitro and in vivo assays are required to confirm the inhibitory action on Prp8 intein splicing; which may pave the way for the development of new antifungals for A. fumigatus.Communicated by Ramaswamy H. Sarma.

Emden: A novel method integrating graph and transformer representations for predicting the effect of mutations on clinical drug response

Precision medicine based on personalized genomics provides promising strategies to enhance the efficacy of molecular-targeted therapies. However, the clinical effectiveness of drugs has been severely limited due to genetic variations that lead to drug resistance. Predicting the impact of missense mutations on clinical drug response is an essential way to reduce the cost of clinical trials and understand genetic diseases. Here, we present Emden, a novel method integrating graph and transformer representations that predicts the effect of missense mutations on drug response through binary classification with interpretability. Emden utilized protein sequences-based features and drug structures as inputs for rapid prediction, employing competitive representation learning and demonstrating strong generalization capabilities and robustness. Our study showed promising potential for clinical drug guidance and deep insight into computer-assisted precision medicine. Emden is freely available as a web server at https://www.psymukb.net/Emden.

In silico resources help combat cancer drug resistance mediated by target mutations

Drug resistance causes catastrophic cancer treatment failures. Mutations in target proteins with altered drug binding indicate a main mechanism of cancer drug resistance (CDR). Global research has generated considerable CDR-related data and well-established knowledge bases and predictive tools. Unfortunately, these resources are fragmented and underutilized. Here, we examine computational resources for exploring CDR caused by target mutations, analyzing these tools based on their functional characteristics, data capacity, data sources, methodologies and performance. We also discuss their disadvantages and provide examples of how potential inhibitors of CDR have been discovered using these resources. This toolkit is designed to help specialists explore resistance occurrence effectively and to explain resistance prediction to non-specialists easily.

Development of Antiepileptic Drugs throughout History: From Serendipity to Artificial Intelligence

This article provides a comprehensive narrative review of the history of antiepileptic drugs (AEDs) and their development over time. Firstly, it explores the significant role of serendipity in the discovery of essential AEDs that continue to be used today, such as phenobarbital and valproic acid. Subsequently, it delves into the historical progression of crucial preclinical models employed in the development of novel AEDs, including the maximal electroshock stimulation test, pentylenetetrazol-induced test, kindling models, and other animal models. Moving forward, a concise overview of the clinical advancement of major AEDs is provided, highlighting the initial milestones and the subsequent refinement of this process in recent decades, in line with the emergence of evidence-based medicine and the implementation of increasingly rigorous controlled clinical trials. Lastly, the article explores the contributions of artificial intelligence, while also offering recommendations and discussing future perspectives for the development of new AEDs.

Bedaquiline and clofazimine resistance in Mycobacterium tuberculosis: an in-vitro and in-silico data analysis

BACKGROUND

Bedaquiline is a core drug for the treatment of multidrug-resistant tuberculosis; however, the understanding of resistance mechanisms is poor, which is hampering rapid molecular diagnostics. Some bedaquiline-resistant mutants are also cross-resistant to clofazimine. To decipher bedaquiline and clofazimine resistance determinants, we combined experimental evolution, protein modelling, genome sequencing, and phenotypic data.

METHODS

For this in-vitro and in-silico data analysis, we used a novel in-vitro evolutionary model using subinhibitory drug concentrations to select bedaquiline-resistant and clofazimine-resistant mutants. We determined bedaquiline and clofazimine minimum inhibitory concentrations and did Illumina and PacBio sequencing to characterise selected mutants and establish a mutation catalogue. This catalogue also includes phenotypic and genotypic data of a global collection of more than 14 000 clinical Mycobacterium tuberculosis complex isolates, and publicly available data. We investigated variants implicated in bedaquiline resistance by protein modelling and dynamic simulations.

FINDINGS

We discerned 265 genomic variants implicated in bedaquiline resistance, with 250 (94%) variants affecting the transcriptional repressor (Rv0678) of the MmpS5-MmpL5 efflux system. We identified 40 new variants in vitro, and a new bedaquiline resistance mechanism caused by a large-scale genomic rearrangement. Additionally, we identified in vitro 15 (7%) of 208 mutations found in clinical bedaquiline-resistant isolates. From our in-vitro work, we detected 14 (16%) of 88 mutations so far identified as being associated with clofazimine resistance and also seen in clinically resistant strains, and catalogued 35 new mutations. Structural modelling of Rv0678 showed four major mechanisms of bedaquiline resistance: impaired DNA binding, reduction in protein stability, disruption of protein dimerisation, and alteration in affinity for its fatty acid ligand.

INTERPRETATION

Our findings advance the understanding of drug resistance mechanisms in M tuberculosis complex strains. We have established an extended mutation catalogue, comprising variants implicated in resistance and susceptibility to bedaquiline and clofazimine. Our data emphasise that genotypic testing can delineate clinical isolates with borderline phenotypes, which is essential for the design of effective treatments.

FUNDING

Leibniz ScienceCampus Evolutionary Medicine of the Lung, Deutsche Forschungsgemeinschaft, Research Training Group 2501 TransEvo, Rhodes Trust, Stanford University Medical Scientist Training Program, National Institute for Health and Care Research Oxford Biomedical Research Centre, Oxford University Hospitals NHS Foundation Trust, Bill & Melinda Gates Foundation, Wellcome Trust, and Marie Skłodowska-Curie Actions.

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.

PSnpBind-ML: predicting the effect of binding site mutations on protein-ligand binding affinity

Protein mutations, especially those which occur in the binding site, play an important role in inter-individual drug response and may alter binding affinity and thus impact the drug's efficacy and side effects. Unfortunately, large-scale experimental screening of ligand-binding against protein variants is still time-consuming and expensive. Alternatively, in silico approaches can play a role in guiding those experiments. Methods ranging from computationally cheaper machine learning (ML) to the more expensive molecular dynamics have been applied to accurately predict the mutation effects. However, these effects have been mostly studied on limited and small datasets, while ideally a large dataset of binding affinity changes due to binding site mutations is needed. In this work, we used the PSnpBind database with six hundred thousand docking experiments to train a machine learning model predicting protein-ligand binding affinity for both wild-type proteins and their variants with a single-point mutation in the binding site. A numerical representation of the protein, binding site, mutation, and ligand information was encoded using 256 features, half of them were manually selected based on domain knowledge. A machine learning approach composed of two regression models is proposed, the first predicting wild-type protein-ligand binding affinity while the second predicting the mutated protein-ligand binding affinity. The best performing models reported an RMSE value within 0.5 [Formula: see text] 0.6 kcal/mol^-1 on an independent test set with an R² value of 0.87 [Formula: see text] 0.90. We report an improvement in the prediction performance compared to several reported models developed for protein-ligand binding affinity prediction. The obtained models can be used as a complementary method in early-stage drug discovery. They can be applied to rapidly obtain a better overview of the ligand binding affinity changes across protein variants carried by people in the population and narrow down the search space where more time-demanding methods can be used to identify potential leads that achieve a better affinity for all protein variants.

In silico analyses of isoniazid and streptomycin resistance-associated mutations in Mycobacterium tuberculosis

Multi-drug resistant tuberculosis is categorised by the World Health Organisation (WHO) as a public health crisis. In silico techniques were used to probe the structural basis of Mycobacterium tuberculosis resistance to isoniazid and streptomycin. Isoniazid resistance-associated mutations in InhA were predicted to reduce the binding affinity of NADH to InhA, without affecting INH-NAD (competitive-inhibitor) binding. Perturbation of the mutated residues was predicted (with the AlloSigMA server) to modulate the free energy of allosteric modulation of key binding site residues F41, F149, Y158 and W222. These results suggest that allosteric modulation of the protein structure may be key to the mechanism by which isoniazid resistance-associated mutations act. Mutations in the methyltransferase glucose-inhibited division gene B (GidB) are associated with streptomycin resistance. Molecular docking was carried out to predict the structure of the GidB bound to its substrate (s-adenosyl methionine). The effects of streptomycin resistance-associated mutations in GidB on protein stability and substrate binding were predicted (using SDM and mCSM-lig). All GidB mutants were predicted to disfavour SAM binding.

embryoTox: Using Graph-Based Signatures to Predict the Teratogenicity of Small Molecules

Teratogenic drugs can lead to extreme fetal malformation and consequently critically influence the fetus's health, yet the teratogenic risks associated with most approved drugs are unknown. Here, we propose a novel predictive tool, embryoTox, which utilizes a graph-based signature representation of the chemical structure of a small molecule to predict and classify molecules likely to be safe during pregnancy. embryoTox was trained and validated using in vitro bioactivity data of over 700 small molecules with characterized teratogenicity effects. Our final model achieved an area under the receiver operating characteristic curve (AUC) of up to 0.96 on 10-fold cross-validation and 0.82 on nonredundant blind tests, outperforming alternative approaches. We believe that our predictive tool will provide a practical resource for optimizing screening libraries to determine effective and safe molecules to use during pregnancy. To provide a simple and integrated platform to rapidly screen for potential safe molecules and their risk factors, we made embryoTox freely available online at https://biosig.lab.uq.edu.au/embryotox/.

High-Throughput Prediction of the Impact of Genetic Variability on Drug Sensitivity and Resistance Patterns for Clinically Relevant Epidermal Growth Factor Receptor Mutations from Atomistic Simulations

Mutations in the kinase domain of the epidermal growth factor receptor (EGFR) can be drivers of cancer and also trigger drug resistance in patients receiving chemotherapy treatment based on kinase inhibitors. A priori knowledge of the impact of EGFR variants on drug sensitivity would help to optimize chemotherapy and design new drugs that are effective against resistant variants before they emerge in clinical trials. To this end, we explored a variety of in silico methods, from sequence-based to "state-of-the-art" atomistic simulations. We did not find any sequence signal that can provide clues on when a drug-related mutation appears or the impact of such mutations on drug activity. Low-level simulation methods provide limited qualitative information on regions where mutations are likely to cause alterations in drug activity, and they can predict around 70% of the impact of mutations on drug efficiency. High-level simulations based on nonequilibrium alchemical free energy calculations show predictive power. The integration of these "state-of-the-art" methods into a workflow implementing an interface for parallel distribution of the calculations allows its automatic and high-throughput use, even for researchers with moderate experience in molecular simulations.

Exploring novel fluorine-rich fuberidazole derivatives as hypoxic cancer inhibitors: Design, synthesis, pharmacokinetics, molecular docking, and DFT evaluations

Sixteen fuberidazole derivatives as potential new anticancer bioreductive prodrugs were prepared and characterized. The in vitro anticancer potential was examined to explore their cytotoxic properties by employing apoptosis, DNA damage, and proliferation tests on chosen hypoxic cancer cells. Eight substances (Compound 5a, 5c, 5d, 5e, 5g, 5h, 5i, and 5m) showed promising cytotoxicity values compared to the standard control. The potential of compounds was also examined through in silico studies (against human serum albumin), including chem-informatics, to understand the structure-activity relationship (SAR), pharmacochemical strength, and the mode of interactions responsible for their action. The DFT calculations revealed that only the 5b compound showed the lowest ΔET (2.29 eV) while 5i showed relatively highest βtot (69.89 x 10-31 esu), highest αave (3.18 x 10-23 esu), and dipole moment (6.49 Debye). This study presents a novel class of fuberidazole derivatives with selectivity toward hypoxic cancer cells.

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.

A recurrent de novo splice site variant involving DNM1 exon 10a causes developmental and epileptic encephalopathy through a dominant-negative mechanism

Heterozygous pathogenic variants in DNM1 cause developmental and epileptic encephalopathy (DEE) as a result of a dominant-negative mechanism impeding vesicular fission. Thus far, pathogenic variants in DNM1 have been studied with a canonical transcript that includes the alternatively spliced exon 10b. However, after performing RNA sequencing in 39 pediatric brain samples, we find the primary transcript expressed in the brain includes the downstream exon 10a instead. Using this information, we evaluated genotype-phenotype correlations of variants affecting exon 10a and identified a cohort of eleven previously unreported individuals. Eight individuals harbor a recurrent de novo splice site variant, c.1197-8G>A (GenBank: NM_001288739.1), which affects exon 10a and leads to DEE consistent with the classical DNM1 phenotype. We find this splice site variant leads to disease through an unexpected dominant-negative mechanism. Functional testing reveals an in-frame upstream splice acceptor causing insertion of two amino acids predicted to impair oligomerization-dependent activity. This is supported by neuropathological samples showing accumulation of enlarged synaptic vesicles adherent to the plasma membrane consistent with impaired vesicular fission. Two additional individuals with missense variants affecting exon 10a, p.Arg399Trp and p.Gly401Asp, had a similar DEE phenotype. In contrast, one individual with a missense variant affecting exon 10b, p.Pro405Leu, which is less expressed in the brain, had a correspondingly less severe presentation. Thus, we implicate variants affecting exon 10a as causing the severe DEE typically associated with DNM1-related disorders. We highlight the importance of considering relevant isoforms for disease-causing variants as well as the possibility of splice site variants acting through a dominant-negative mechanism.

kinCSM: Using graph-based signatures to predict small molecule CDK2 inhibitors

Protein phosphorylation acts as an essential on/off switch in many cellular signaling pathways. This has led to ongoing interest in targeting kinases for therapeutic intervention. Computer-aided drug discovery has been proven a useful and cost-effective approach for facilitating prioritization and enrichment of screening libraries, but limited effort has been devoted providing insights on what makes a potent kinase inhibitor. To fill this gap, here we developed kinCSM, an integrative computational tool capable of accurately identifying potent cyclin-dependent kinase 2 (CDK2) inhibitors, quantitatively predicting CDK2 ligand-kinase inhibition constants (pKi ) and classifying different types of inhibitors based on their favorable binding modes. kinCSM predictive models were built using supervised learning and leveraged the concept of graph-based signatures to capture both physicochemical properties and geometry properties of small molecules. CDK2 inhibitors were accurately identified with Matthew's Correlation Coefficients (MCC) of up to 0.74, and inhibition constants predicted with Pearson's correlation of up to 0.76, both with consistent performances of 0.66 and 0.68 on a nonredundant blind test, respectively. kinCSM was also able to identify the potential type of inhibition for a given molecule, achieving MCC of up to 0.80 on cross-validation and 0.73 on the blind test. Analyzing the molecular composition of revealed enriched chemical fragments in CDK2 inhibitors and different types of inhibitors, which provides insights into the molecular mechanisms behind ligand-kinase interactions. kinCSM will be an invaluable tool to guide future kinase drug discovery. To aid the fast and accurate screening of CDK2 inhibitors, kinCSM is freely available at https://biosig.lab.uq.edu.au/kin_csm/.

cardioToxCSM: A Web Server for Predicting Cardiotoxicity of Small Molecules

The design of novel, safe, and effective drugs to treat human diseases is a challenging venture, with toxicity being one of the main sources of attrition at later stages of development. Failure due to toxicity incurs a significant increase in costs and time to market, with multiple drugs being withdrawn from the market due to their adverse effects. Cardiotoxicity, for instance, was responsible for the failure of drugs such as fenspiride, propoxyphene, and valdecoxib. While significant effort has been dedicated to mitigate this issue by developing computational approaches that aim to identify molecules likely to be toxic, including quantitative structure-activity relationship models and machine learning methods, current approaches present limited performance and interpretability. To overcome these, we propose a new web-based computational method, cardioToxCSM, which can predict six types of cardiac toxicity outcomes, including arrhythmia, cardiac failure, heart block, hERG toxicity, hypertension, and myocardial infarction, efficiently and accurately. cardioToxCSM was developed using the concept of graph-based signatures, molecular descriptors, toxicophore matchings, and molecular fingerprints, leveraging explainable machine learning, and was validated internally via different cross validation schemes and externally via low-redundancy blind sets. The models presented robust performances with areas under ROC curves of up to 0.898 on 5-fold cross-validation, consistent with metrics on blind tests. Additionally, our models provide interpretation of the predictions by identifying whether substructures that are commonly enriched in toxic compounds were present. We believe cardioToxCSM will provide valuable insight into the potential cardiotoxicity of small molecules early on drug screening efforts. The method is made freely available as a web server at https://biosig.lab.uq.edu.au/cardiotoxcsm.

Molecular basis of Toxoplasma gondii oryzalin resistance from a novel α-tubulin binding site model

Oryzalin (ORY) is a dinitroaniline derivative that inhibits the microtubule polymerization in plants and parasitic protozoa by selectively binding to the α-tubulin subunit. This herbicidal agent exhibits good antiprotozoal activity against major human parasites, such as Toxoplasma gondii (toxoplasmosis), Leishmania mexicana (leishmaniasis), and Plasmodium falciparum (malaria). Previous chemical mutagenesis assays on T. gondii α-tubulin (TgAT) have identified key mutations that lead to ORY resistance. Herein, we employed alchemical free energy methods and molecular dynamics simulations to determine if the ORY resistance mutations either decrease the TgAT's affinity of the compound or increase the protein stability. Our results here suggest that L136F and V202F mutations significantly decrease the affinity of ORY to TgAT, while T239I and V252L mutations diminish TgAT's flexibility. On the other hand, protein stability predictors determined that R243S mutation reduces TgAT stability due to the loss of its salt bridge interaction with E27. Interestingly, molecular dynamics simulations confirm that the loss of this key interaction leads to ORY binding site closure. Our study provides a better insight into the TgAT-ORY interaction, further supporting our recently proposed ORY-binding site.

Evaluating hierarchical machine learning approaches to classify biological databases

The rate of biological data generation has increased dramatically in recent years, which has driven the importance of databases as a resource to guide innovation and the generation of biological insights. Given the complexity and scale of these databases, automatic data classification is often required. Biological data sets are often hierarchical in nature, with varying degrees of complexity, imposing different challenges to train, test and validate accurate and generalizable classification models. While some approaches to classify hierarchical data have been proposed, no guidelines regarding their utility, applicability and limitations have been explored or implemented. These include ‘Local’ approaches considering the hierarchy, building models per level or node, and ‘Global’ hierarchical classification, using a flat classification approach. To fill this gap, here we have systematically contrasted the performance of ‘Local per Level’ and ‘Local per Node’ approaches with a ‘Global’ approach applied to two different hierarchical datasets: BioLip and CATH. The results show how different components of hierarchical data sets, such as variation coefficient and prediction by depth, can guide the choice of appropriate classification schemes. Finally, we provide guidelines to support this process when embarking on a hierarchical classification task, which will help optimize computational resources and predictive performance.

Improvement of Fusel Alcohol Production by Engineering of the Yeast Branched-Chain Amino Acid Aminotransaminase

Branched-chain higher alcohols (BCHAs), or fusel alcohols, including isobutanol, isoamyl alcohol, and active amyl alcohol, are useful compounds in several industries. The yeast Saccharomyces cerevisiae can synthesize these compounds via the metabolic pathways of branched-chain amino acids (BCAAs). Branched-chain amino acid aminotransaminases (BCATs) are the key enzymes for BCHA production via the Ehrlich pathway of BCAAs. BCATs catalyze a bidirectional transamination reaction between branched-chain α-keto acids (BCKAs) and BCAAs. In S. cerevisiae, there are two BCAT isoforms, Bat1 and Bat2, which are encoded by the genes BAT1 and BAT2. Although many studies have shown the effects of deletion or overexpression of BAT1 and BAT2 on BCHA production, there have been no reports on the enhancement of BCHA production by functional variants of BCATs. Here, to improve BCHA productivity, we designed variants of Bat1 and Bat2 with altered enzyme activity by using in silico computational analysis: the Gly333Ser and Gly333Trp Bat1 and corresponding Gly316Ser and Gly316Trp Bat2 variants, respectively. When expressed in S. cerevisiae cells, most of these variants caused a growth defect in minimal medium. Interestingly, the Gly333Trp Bat1 and Gly316Ser Bat2 variants achieved 18.7-fold and 17.4-fold increases in isobutanol above that for the wild-type enzyme, respectively. The enzyme assay revealed that the catalytic activities of all four BCAT variants were lower than that of the wild-type enzyme. Our results indicate that the decreased BCAT activity enhanced BCHA production by reducing BCAA biosynthesis, which occurs via a pathway that directly competes with BCHA production.

IMPORTANCE Recently, several studies have attempted to increase the production of branched-chain higher alcohols (BCHAs) in the yeast Saccharomyces cerevisiae. The key enzymes for BCHA biosynthesis in S. cerevisiae are the branched-chain amino acid aminotransaminases (BCATs) Bat1 and Bat2. Deletion or overexpression of the genes encoding BCATs has an impact on the production of BCHAs; however, amino acid substitution variants of Bat1 and Bat2 that could affect enzymatic properties—and ultimately BCHA productivity—have not been fully studied. By using in silico analysis, we designed variants of Bat1 and Bat2 and expressed them in yeast cells. We found that the engineered BCATs decreased catalytic activities and increased BCHA production. Our approach provides new insight into the functions of BCATs and will be useful in the future construction of enzymes optimized for high-level production of BCHAs.

Diverse Molecular Mechanisms Underlying Pathogenic Protein Mutations: Beyond the Loss-of-Function Paradigm

Most known disease-causing mutations occur in protein-coding regions of DNA. While some of these involve a loss of protein function (e.g., through premature stop codons or missense changes that destabilize protein folding), many act via alternative molecular mechanisms and have dominant-negative or gain-of-function effects. In nearly all cases, these non-loss-of-function mutations can be understood by considering interactions of the wild-type and mutant protein with other molecules, such as proteins, nucleic acids, or small ligands and substrates. Here, we review the diverse molecular mechanisms by which pathogenic mutations can have non-loss-of-function effects, including by disrupting interactions, increasing binding affinity, changing binding specificity, causing assembly-mediated dominant-negative and dominant-positive effects, creating novel interactions, and promoting aggregation and phase separation. We believe that increased awareness of these diverse molecular disease mechanisms will lead to improved diagnosis (and ultimately treatment) of human genetic disorders. Expected final online publication date for the Annual Review of Genomics and Human Genetics, Volume 23 is October 2022. Please see http://www.annualreviews.org/page/journal/pubdates for revised estimates.

Crystal structure of Acetyl-CoA carboxylase (AccB) from Streptomyces antibioticus and insights into the substrate-binding through in silico mutagenesis and biophysical investigations

Acetyl-CoA carboxylase (ACC) is crucial for polyketides biosynthesis and acts as an essential metabolic checkpoint. It is also an attractive drug target against obesity, cancer, microbial infections, and diabetes. However, the lack of knowledge, particularly sequence-structure function relationship to narrate ligand-enzyme binding, has hindered the progress of ACC-specific therapeutics and unnatural "natural" polyketides. Structural characterization of such enzymes will boost the opportunity to understand the substrate binding, designing new inhibitors and information regarding the molecular rules which control the substrate specificity of ACCs. To understand the substrate specificity, we determined the crystal structure of AccB (Carboxyl-transferase, CT) from Streptomyces antibioticus with a resolution of 2.3 Å and molecular modeling approaches were employed to unveil the molecular mechanism of acetyl-CoA recognition and processing. The CT domain of S. antibioticus shares a similar structural organization with the previous structures and the two steps reaction was confirmed by enzymatic assay. Furthermore, to reveal the key hotspots required for the substrate recognition and processing, in silico mutagenesis validated only three key residues (V223, Q346, and Q514) that help in the fixation of the substrate. Moreover, we also presented atomic level knowledge on the mechanism of the substrate binding, which unveiled the terminal loop (500-514) function as an opening and closing switch and pushes the substrate inside the cavity for stable binding. A significant decline in the hydrogen bonding half-life was observed upon the alanine substitution. Consequently, the presented structural data highlighted the potential key interacting residues for substrate recognition and will also help to re-design ACCs active site for proficient substrate specificity to produce diverse polyketides.

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.

HGDiscovery: An online tool providing functional and phenotypic information on novel variants of homogentisate 1,2- dioxigenase

Alkaptonuria (AKU), a rare genetic disorder, is characterized by the accumulation of homogentisic acid (HGA) in the body. Affected individuals lack functional levels of an enzyme required to breakdown HGA. Mutations in the homogentisate 1,2-dioxygenase (HGD) gene cause AKU and they are responsible for deficient levels of functional HGD, which, in turn, leads to excess levels of HGA. Although HGA is rapidly cleared from the body by the kidneys, in the long term it starts accumulating in various tissues, especially cartilage. Over time (rarely before adulthood), it eventually changes the color of affected tissue to slate blue or black. Here we report a comprehensive mutation analysis of 111 pathogenic and 190 non-pathogenic HGD missense mutations using protein structural information. Using our comprehensive suite of graph-based signature methods, mCSM complemented with sequence-based tools, we studied the functional and molecular consequences of each mutation on protein stability, interaction and evolutionary conservation. The scores generated from the structure and sequence-based tools were used to train a supervised machine learning algorithm with 89% accuracy. The empirical classifier was used to generate the variant phenotype for novel HGD missense mutations. All this information is deployed as a user friendly freely available web server called HGDiscovery (https://biosig.lab.uq.edu.au/hgdiscovery/).

•

Functional and phenotypic consequences of HGD non-synonymous variations.

•

Biophysical, structural and evolutionary analysis of novel and known clinical variants.

•

Pathogenic mutations affected protein stability and conformational flexibility.

•

Pathogenic mutations associated with deleterious scores for sequence-based features.

•

HGDiscovery (http://biosig.unimelb.edu.au/hgdiscovery/) – webserver.

CSM-carbohydrate: protein-carbohydrate binding affinity prediction and docking scoring function

Protein-carbohydrate interactions are crucial for many cellular processes but can be challenging to biologically characterise. To improve our understanding and ability to model these molecular interactions, we used a carefully curated set of 370 protein-carbohydrate complexes with experimental structural and biophysical data in order to train and validate a new tool, cutoff scanning matrix (CSM)-carbohydrate, using machine learning algorithms to accurately predict their binding affinity and rank docking poses as a scoring function. Information on both protein and carbohydrate complementarity, in terms of shape and chemistry, was captured using graph-based structural signatures. Across both training and independent test sets, we achieved comparable Pearson's correlations of 0.72 under cross-validation [root mean square error (RMSE) of 1.58 Kcal/mol] and 0.67 on the independent test (RMSE of 1.72 Kcal/mol), providing confidence in the generalisability and robustness of the final model. Similar performance was obtained across mono-, di- and oligosaccharides, further highlighting the applicability of this approach to the study of larger complexes. We show CSM-carbohydrate significantly outperformed previous approaches and have implemented our method and make all data freely available through both a user-friendly web interface and application programming interface, to facilitate programmatic access at http://biosig.unimelb.edu.au/csm_carbohydrate/. We believe CSM-carbohydrate will be an invaluable tool for helping assess docking poses and the effects of mutations on protein-carbohydrate affinity, unravelling important aspects that drive binding recognition.

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.

PremPLI: a machine learning model for predicting the effects of missense mutations on protein-ligand interactions

Resistance to small-molecule drugs is the main cause of the failure of therapeutic drugs in clinical practice. Missense mutations altering the binding of ligands to proteins are one of the critical mechanisms that result in genetic disease and drug resistance. Computational methods have made a lot of progress for predicting binding affinity changes and identifying resistance mutations, but their prediction accuracy and speed are still not satisfied and need to be further improved. To address these issues, we introduce a structure-based machine learning method for quantitatively estimating the effects of single mutations on ligand binding affinity changes (named as PremPLI). A comprehensive comparison of the predictive performance of PremPLI with other available methods on two benchmark datasets confirms that our approach performs robustly and presents similar or even higher predictive accuracy than the approaches relying on first-principle statistical mechanics and mixed physics- and knowledge-based potentials while requires much less computational resources. PremPLI can be used for guiding the design of ligand-binding proteins, identifying and understanding disease driver mutations, and finding potential resistance mutations for different drugs. PremPLI is freely available at https://lilab.jysw.suda.edu.cn/research/PremPLI/ and allows to do large-scale mutational scanning.

Sun et al. present PremPLI, a machine learning approach and web tool to predict how missense mutations in a drug’s target protein will affect the drug’s binding affinity. PremPLI can be applied to identify drug resistance mechanisms in cancer cells and microorganisms and develop drugs to combat drug resistance.

COSMIC Cancer Gene Census 3D database: understanding the impacts of mutations on cancer targets

Mutations in hallmark genes are believed to be the main drivers of cancer progression. These mutations are reported in the Catalogue of Somatic Mutations in Cancer (COSMIC). Structural appreciation of where these mutations appear, in protein-protein interfaces, active sites or deoxyribonucleic acid (DNA) interfaces, and predicting the impacts of these mutations using a variety of computational tools are crucial for successful drug discovery and development. Currently, there are 723 genes presented in the COSMIC Cancer Gene Census. Due to the complexity of the gene products, structures of only 87 genes have been solved experimentally with structural coverage between 90% and 100%. Here, we present a comprehensive, user-friendly, web interface (https://cancer-3d.com/) of 714 modelled cancer-related genes, including homo-oligomers, hetero-oligomers, transmembrane proteins and complexes with DNA, ribonucleic acid, ligands and co-factors. Using SDM and mCSM software, we have predicted the impacts of reported mutations on protein stability, protein-protein interfaces affinity and protein-nucleic acid complexes affinity. Furthermore, we also predicted intrinsically disordered regions using DISOPRED3.

epitope3D: a machine learning method for conformational B-cell epitope prediction

The ability to identify antigenic determinants of pathogens, or epitopes, is fundamental to guide rational vaccine development and immunotherapies, which are particularly relevant for rapid pandemic response. A range of computational tools has been developed over the past two decades to assist in epitope prediction; however, they have presented limited performance and generalization, particularly for the identification of conformational B-cell epitopes. Here, we present epitope3D, a novel scalable machine learning method capable of accurately identifying conformational epitopes trained and evaluated on the largest curated epitope data set to date. Our method uses the concept of graph-based signatures to model epitope and non-epitope regions as graphs and extract distance patterns that are used as evidence to train and test predictive models. We show epitope3D outperforms available alternative approaches, achieving Mathew's Correlation Coefficient and F1-scores of 0.55 and 0.57 on cross-validation and 0.45 and 0.36 during independent blind tests, respectively.

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/.

In Silico Characterization of Masitinib Interaction with SARS-CoV-2 Main Protease

Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection continues to be a global health problem. Despite the current implementation of COVID-19 vaccination schedules, identifying effective antiviral drug treatments for this disease continues to be a priority. A recent study showed that masitinib (MST), a tyrosine kinase inhibitor, blocks the proteolytic activity of SARS-CoV-2 main protease (Mpro ). Although MST is a potential candidate for COVID-19 treatment, a comprehensive analysis of its interaction with Mpro has not been done. In this work, we performed molecular dynamics simulations of the MST-Mpro complex crystal structure. The effect of the protonation states of Mpro H163 residue and MST titratable groups were studied. Furthermore, we identified the MST substituents and Mpro mutations that affect the stability of the complex. Our results provide valuable insights into the design of new MST analogs as potential treatments for COVID-19.

Decoding disease: from genomes to networks to phenotypes

Interpreting the effects of genetic variants is key to understanding individual susceptibility to disease and designing personalized therapeutic approaches. Modern experimental technologies are enabling the generation of massive compendia of human genome sequence data and associated molecular and phenotypic traits, together with genome-scale expression, epigenomics and other functional genomic data. Integrative computational models can leverage these data to understand variant impact, elucidate the effect of dysregulated genes on biological pathways in specific disease and tissue contexts, and interpret disease risk beyond what is feasible with experiments alone. In this Review, we discuss recent developments in machine learning algorithms for genome interpretation and for integrative molecular-level modelling of cells, tissues and organs relevant to disease. More specifically, we highlight existing methods and key challenges and opportunities in identifying specific disease-causing genetic variants and linking them to molecular pathways and, ultimately, to disease phenotypes.

Artificial intelligence to deep learning: machine intelligence approach for drug discovery

Drug designing and development is an important area of research for pharmaceutical companies and chemical scientists. However, low efficacy, off-target delivery, time consumption, and high cost impose a hurdle and challenges that impact drug design and discovery. Further, complex and big data from genomics, proteomics, microarray data, and clinical trials also impose an obstacle in the drug discovery pipeline. Artificial intelligence and machine learning technology play a crucial role in drug discovery and development. In other words, artificial neural networks and deep learning algorithms have modernized the area. Machine learning and deep learning algorithms have been implemented in several drug discovery processes such as peptide synthesis, structure-based virtual screening, ligand-based virtual screening, toxicity prediction, drug monitoring and release, pharmacophore modeling, quantitative structure-activity relationship, drug repositioning, polypharmacology, and physiochemical activity. Evidence from the past strengthens the implementation of artificial intelligence and deep learning in this field. Moreover, novel data mining, curation, and management techniques provided critical support to recently developed modeling algorithms. In summary, artificial intelligence and deep learning advancements provide an excellent opportunity for rational drug design and discovery process, which will eventually impact mankind. The primary concern associated with drug design and development is time consumption and production cost. Further, inefficiency, inaccurate target delivery, and inappropriate dosage are other hurdles that inhibit the process of drug delivery and development. With advancements in technology, computer-aided drug design integrating artificial intelligence algorithms can eliminate the challenges and hurdles of traditional drug design and development. Artificial intelligence is referred to as superset comprising machine learning, whereas machine learning comprises supervised learning, unsupervised learning, and reinforcement learning. Further, deep learning, a subset of machine learning, has been extensively implemented in drug design and development. The artificial neural network, deep neural network, support vector machines, classification and regression, generative adversarial networks, symbolic learning, and meta-learning are examples of the algorithms applied to the drug design and discovery process. Artificial intelligence has been applied to different areas of drug design and development process, such as from peptide synthesis to molecule design, virtual screening to molecular docking, quantitative structure-activity relationship to drug repositioning, protein misfolding to protein-protein interactions, and molecular pathway identification to polypharmacology. Artificial intelligence principles have been applied to the classification of active and inactive, monitoring drug release, pre-clinical and clinical development, primary and secondary drug screening, biomarker development, pharmaceutical manufacturing, bioactivity identification and physiochemical properties, prediction of toxicity, and identification of mode of action.

Structural and Genomic Insights Into Pyrazinamide Resistance in Mycobacterium tuberculosis Underlie Differences Between Ancient and Modern Lineages

Resistance to drugs used to treat tuberculosis disease (TB) continues to remain a public health burden, with missense point mutations in the underlying Mycobacterium tuberculosis bacteria described for nearly all anti-TB drugs. The post-genomics era along with advances in computational and structural biology provide opportunities to understand the interrelationships between the genetic basis and the structural consequences of M. tuberculosis mutations linked to drug resistance. Pyrazinamide (PZA) is a crucial first line antibiotic currently used in TB treatment regimens. The mutational promiscuity exhibited by the pncA gene (target for PZA) necessitates computational approaches to investigate the genetic and structural basis for PZA resistance development. We analysed 424 missense point mutations linked to PZA resistance derived from ∼35K M. tuberculosis clinical isolates sourced globally, which comprised the four main M. tuberculosis lineages (Lineage 1-4). Mutations were annotated to reflect their association with PZA resistance. Genomic measures (minor allele frequency and odds ratio), structural features (surface area, residue depth and hydrophobicity) and biophysical effects (change in stability and ligand affinity) of point mutations on pncA protein stability and ligand affinity were assessed. Missense point mutations within pncA were distributed throughout the gene, with the majority (>80%) of mutations with a destabilising effect on protomer stability and on ligand affinity. Active site residues involved in PZA binding were associated with multiple point mutations highlighting mutational diversity due to selection pressures at these functionally important sites. There were weak associations between genomic measures and biophysical effect of mutations. However, mutations associated with PZA resistance showed statistically significant differences between structural features (surface area and residue depth), but not hydrophobicity score for mutational sites. Most interestingly M. tuberculosis lineage 1 (ancient lineage) exhibited a distinct protein stability profile for mutations associated with PZA resistance, compared to modern lineages.

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.

pdCSM-cancer: Using Graph-Based Signatures to Identify Small Molecules with Anticancer Properties

The development of new, effective, and safe drugs to treat cancer remains a challenging and time-consuming task due to limited hit rates, restraining subsequent development efforts. Despite the impressive progress of quantitative structure–activity relationship and machine learning-based models that have been developed to predict molecule pharmacodynamics and bioactivity, they have had mixed success at identifying compounds with anticancer properties against multiple cell lines. Here, we have developed a novel predictive tool, pdCSM-cancer, which uses a graph-based signature representation of the chemical structure of a small molecule in order to accurately predict molecules likely to be active against one or multiple cancer cell lines. pdCSM-cancer represents the most comprehensive anticancer bioactivity prediction platform developed till date, comprising trained and validated models on experimental data of the growth inhibition concentration (GI50%) effects, including over 18,000 compounds, on 9 tumor types and 74 distinct cancer cell lines. Across 10-fold cross-validation, it achieved Pearson’s correlation coefficients of up to 0.74 and comparable performance of up to 0.67 across independent, non-redundant blind tests. Leveraging the insights from these cell line-specific models, we developed a generic predictive model to identify molecules active in at least 60 cell lines. Our final model achieved an area under the receiver operating characteristic curve (AUC) of up to 0.94 on 10-fold cross-validation and up to 0.94 on independent non-redundant blind tests, outperforming alternative approaches. We believe that our predictive tool will provide a valuable resource to optimizing and enriching screening libraries for the identification of effective and safe anticancer molecules. To provide a simple and integrated platform to rapidly screen for potential biologically active molecules with favorable anticancer properties, we made pdCSM-cancer freely available online at http://biosig.unimelb.edu.au/pdcsm_cancer.

Computational Enzyme Engineering Pipelines for Optimized Production of Renewable Chemicals

To enable a sustainable supply of chemicals, novel biotechnological solutions are required that replace the reliance on fossil resources. One potential solution is to utilize tailored biosynthetic modules for the metabolic conversion of CO₂ or organic waste to chemicals and fuel by microorganisms. Currently, it is challenging to commercialize biotechnological processes for renewable chemical biomanufacturing because of a lack of highly active and specific biocatalysts. As experimental methods to engineer biocatalysts are time- and cost-intensive, it is important to establish efficient and reliable computational tools that can speed up the identification or optimization of selective, highly active, and stable enzyme variants for utilization in the biotechnological industry. Here, we review and suggest combinations of effective state-of-the-art software and online tools available for computational enzyme engineering pipelines to optimize metabolic pathways for the biosynthesis of renewable chemicals. Using examples relevant for biotechnology, we explain the underlying principles of enzyme engineering and design and illuminate future directions for automated optimization of biocatalysts for the assembly of synthetic metabolic pathways.

Computational methods for predicting hotspots at protein-RNA interfaces

Protein-RNA interactions play essential roles in many critical biological events. A comprehensive understanding of the mechanisms underlying these interactions is helpful when studying cellular activities and therapeutic applications. Hotspots are a small portion of residues contributing much toward protein-RNA binding affinity. In pharmaceutical research, the hotspot residues are seen as the best option for designing small molecules to target proteins of therapeutic interest. With the accumulation of experimental data about protein-RNA interactions, computational methods have been produced for hotspot prediction on a large scale. In this review, we first present an overview of the existing databases for protein-RNA binding data. Furthermore, we outline the most adopted computational methods for hotspots prediction in protein-RNA interactions. Finally, we discuss the applications of hotspot prediction. This article is categorized under: RNA Interactions with Proteins and Other Molecules > Protein-RNA Recognition RNA Interactions with Proteins and Other Molecules > Protein-RNA Interactions: Functional Implications RNA Methods > RNA Analyses In Vitro and In Silico.

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.

Recent advances in user-friendly computational tools to engineer protein function

Progress in technology and algorithms throughout the past decade has transformed the field of protein design and engineering. Computational approaches have become well-engrained in the processes of tailoring proteins for various biotechnological applications. Many tools and methods are developed and upgraded each year to satisfy the increasing demands and challenges of protein engineering. To help protein engineers and bioinformaticians navigate this emerging wave of dedicated software, we have critically evaluated recent additions to the toolbox regarding their application for semi-rational and rational protein engineering. These newly developed tools identify and prioritize hotspots and analyze the effects of mutations for a variety of properties, comprising ligand binding, protein-protein and protein-nucleic acid interactions, and electrostatic potential. We also discuss notable progress to target elusive protein dynamics and associated properties like ligand-transport processes and allosteric communication. Finally, we discuss several challenges these tools face and provide our perspectives on the further development of readily applicable methods to guide protein engineering efforts.

Structure-Guided Computational Approaches to Unravel Druggable Proteomic Landscape of Mycobacterium leprae

Leprosy, caused by Mycobacterium leprae (M. leprae), is treated with a multidrug regimen comprising Dapsone, Rifampicin, and Clofazimine. These drugs exhibit bacteriostatic, bactericidal and anti-inflammatory properties, respectively, and control the dissemination of infection in the host. However, the current treatment is not cost-effective, does not favor patient compliance due to its long duration (12 months) and does not protect against the incumbent nerve damage, which is a severe leprosy complication. The chronic infectious peripheral neuropathy associated with the disease is primarily due to the bacterial components infiltrating the Schwann cells that protect neuronal axons, thereby inducing a demyelinating phenotype. There is a need to discover novel/repurposed drugs that can act as short duration and effective alternatives to the existing treatment regimens, preventing nerve damage and consequent disability associated with the disease. Mycobacterium leprae is an obligate pathogen resulting in experimental intractability to cultivate the bacillus in vitro and limiting drug discovery efforts to repositioning screens in mouse footpad models. The dearth of knowledge related to structural proteomics of M. leprae, coupled with emerging antimicrobial resistance to all the three drugs in the multidrug therapy, poses a need for concerted novel drug discovery efforts. A comprehensive understanding of the proteomic landscape of M. leprae is indispensable to unravel druggable targets that are essential for bacterial survival and predilection of human neuronal Schwann cells. Of the 1,614 protein-coding genes in the genome of M. leprae, only 17 protein structures are available in the Protein Data Bank. In this review, we discussed efforts made to model the proteome of M. leprae using a suite of software for protein modeling that has been developed in the Blundell laboratory. Precise template selection by employing sequence-structure homology recognition software, multi-template modeling of the monomeric models and accurate quality assessment are the hallmarks of the modeling process. Tools that map interfaces and enable building of homo-oligomers are discussed in the context of interface stability. Other software is described to determine the druggable proteome by using information related to the chokepoint analysis of the metabolic pathways, gene essentiality, homology to human proteins, functional sites, druggable pockets and fragment hotspot maps.

Cryo-EM structure of a thermostable bacterial nanocompartment

Protein nanocompartments are widespread in bacteria and archaea, but their functions are not yet well understood. Here, the cryo-EM structure of a nanocompartment from the thermophilic bacterium Thermotoga maritima is reported at 2.0 Å resolution. The high resolution of this structure shows that interactions in the E-loop domain may be important for the thermostability of the nanocompartment assembly. Also, the channels at the fivefold axis, threefold axis and dimer interface are assessed for their ability to transport iron. Finally, an unexpected flavin ligand was identified on the exterior of the shell, indicating that this nanocompartment may also play a direct role in iron metabolism.

Computational modeling and bioinformatic analyses of functional mutations in drug target genes in Mycobacterium tuberculosis

•

MycoTRAP-DB, a database of mutations and their impact on normal functionality of protein in M.tb genes.

•

Several secondary mutations were identified with significant impact on protein structure and function.

•

Comprehensive information gives insight for screening of suspected hotspots in advance to combat drug resistant TB.

Tuberculosis (TB) continues to be the leading cause of deaths due to its persistent drug resistance and the consequent ineffectiveness of anti-TB treatment. Recent years witnessed huge amount of sequencing data, revealing mutations responsible for drug resistance. However, the lack of an up-to-date repository remains a barrier towards utilization of these data and identifying major mutations-associated with resistance. Amongst all mutations, non-synonymous mutations alter the amino acid sequence of a protein and have a much greater effect on pathogenicity. Hence, this type of gene mutation is of prime interest of the present study. The purpose of this study is to develop an updated database comprising almost all reported substitutions within the Mycobacterium tuberculosis (M.tb) drug target genes rpoB, inhA, katG, pncA, gyrA and gyrB. Various bioinformatics prediction tools were used to assess the structural and biophysical impacts of the resistance causing non-synonymous single nucleotide polymorphisms (nsSNPs) at the molecular level. This was followed by evaluating the impact of these mutations on binding affinity of the drugs to target proteins. We have developed a comprehensive online resource named MycoTRAP-DB (Mycobacterium tuberculosis Resistance Associated Polymorphisms Database) that connects mutations in genes with their structural, functional and pathogenic implications on protein. This database is accessible at http://139.59.12.92. This integrated platform would enable comprehensive analysis and prioritization of SNPs for the development of improved diagnostics and antimycobacterial medications. Moreover, our study puts forward secondary mutations that can be important for prognostic assessments of drug-resistance mechanism and actionable anti-TB drugs.

Biological impact of mutually exclusive exon switching

Alternative splicing can expand the diversity of proteomes. Homologous mutually exclusive exons (MXEs) originate from the same ancestral exon and result in polypeptides with similar structural properties but altered sequence. Why would some genes switch homologous exons and what are their biological impact? Here, we analyse the extent of sequence, structural and functional variability in MXEs and report the first large scale, structure-based analysis of the biological impact of MXE events from different genomes. MXE-specific residues tend to map to single domains, are highly enriched in surface exposed residues and cluster at or near protein functional sites. Thus, MXE events are likely to maintain the protein fold, but alter specificity and selectivity of protein function. This comprehensive resource of MXE events and their annotations is available at: http://gene3d.biochem.ucl.ac.uk/mxemod/. These findings highlight how small, but significant changes at critical positions on a protein surface are exploited in evolution to alter function.