epitope1D: accurate taxonomy-aware B-cell linear epitope prediction

The ability to identify B-cell epitopes is an essential step in vaccine design, immunodiagnostic tests and antibody production. Several computational approaches have been proposed to identify, from an antigen protein or peptide sequence, which residues are more likely to be part of an epitope, but have limited performance on relatively homogeneous data sets and lack interpretability, limiting biological insights that could otherwise be obtained. To address these limitations, we have developed epitope1D, an explainable machine learning method capable of accurately identifying linear B-cell epitopes, leveraging two new descriptors: a graph-based signature representation of protein sequences, based on our well-established Cutoff Scanning Matrix algorithm and Organism Ontology information. Our model achieved Areas Under the ROC curve of up to 0.935 on cross-validation and blind tests, demonstrating robust performance. A comprehensive comparison to alternative methods using distinct benchmark data sets was also employed, with our model outperforming state-of-the-art tools. epitope1D represents not only a significant advance in predictive performance, but also allows biologically meaningful features to be combined and used for model interpretation. epitope1D has been made available as a user-friendly web server interface and application programming interface at https://biosig.lab.uq.edu.au/epitope1d/.

Crystallization and preliminary X-ray diffraction analysis of human endoplasmic reticulum aminopeptidase 2

Endoplasmic reticulum aminopeptidase 2 (ERAP2) is a critical enzyme involved in the final processing of MHC class I antigens. Peptide trimming by ERAP2 and the other members of the oxytocinase subfamily is essential to customize longer precursor peptides in order to fit them to the correct length required for presentation on major histocompatibility complex class I molecules. While recent structures of ERAP1 have provided an understanding of the `molecular-ruler' mechanism of substrate selection, little is known about the complementary activities of its homologue ERAP2 despite their sharing 49% sequence identity. In order to gain insights into the structure-function relationship of the oxytocinase subfamily, and in particular ERAP2, the luminal region of human ERAP2 has been crystallized in the presence of the inhibitor bestatin. The crystals belonged to an orthorhombic space group and diffracted anisotropically to 3.3 Å resolution in the best direction on an in-house X-ray source. A molecular-replacement solution suggested that the enzyme has adopted the closed state as has been observed in other inhibitor-bound aminopeptidase structures.

VIVID: a web application for variant interpretation and visualisation in multidimensional analyses

Large-scale comparative genomics- and population genetic studies generate enormous amounts of polymorphism data in the form of DNA variants. Ultimately, the goal of many of these studies is to associate genetic variants to phenotypes or fitness. We introduce VIVID, an interactive, user-friendly web application that integrates a wide range of approaches for encoding genotypic to phenotypic information in any organism or disease, from an individual or population, in three-dimensional (3D) space. It allows mutation mapping and annotation, calculation of interactions and conservation scores, prediction of harmful effects, analysis of diversity and selection, and 3D visualization of genotypic information encoded in Variant Call Format on AlphaFold2 protein models. VIVID enables the rapid assessment of genes of interest in the study of adaptive evolution and the genetic load, and it helps prioritizing targets for experimental validation. We demonstrate the utility of VIVID by exploring the evolutionary genetics of the parasitic protist Plasmodium falciparum, revealing geographic variation in the signature of balancing selection in potential targets of functional antibodies.

Structural landscapes of PPI interfaces

Proteins are capable of highly specific interactions and are responsible for a wide range of functions, making them attractive in the pursuit of new therapeutic options. Previous studies focusing on overall geometry of protein-protein interfaces, however, concluded that PPI interfaces were generally flat. More recently, this idea has been challenged by their structural and thermodynamic characterisation, suggesting the existence of concave binding sites that are closer in character to traditional small-molecule binding sites, rather than exhibiting complete flatness. Here, we present a large-scale analysis of binding geometry and physicochemical properties of all protein-protein interfaces available in the Protein Data Bank. In this review, we provide a comprehensive overview of the protein-protein interface landscape, including evidence that even for overall larger, more flat interfaces that utilize discontinuous interacting regions, small and potentially druggable pockets are utilized at binding sites.

Exploring Protein Supersecondary Structure Through Changes in Protein Folding, Stability, and Flexibility

The ability to predict how mutations affect protein structure, folding, and flexibility can elucidate the molecular mechanisms leading to disruption of supersecondary structures, the emergence of phenotypes, as well guiding rational protein engineering. The advent of fast and accurate computational tools has enabled us to comprehensively explore the landscape of mutation effects on protein structures, prioritizing mutations for rational experimental validation.Here we describe the use of two complementary web-based in silico methods, DUET and DynaMut, developed to infer the effects of mutations on folding, stability, and flexibility and how they can be used to explore and interpret these effects on protein supersecondary structures.

Unveiling six potent and highly selective antileishmanial agents via the open source compound collection 'Pathogen Box' against antimony-sensitive and -resistant Leishmania braziliensis

Despite all efforts to provide new chemical entities to tackle leishmaniases, we are still dependent on a the limited drug arsenal, together with drawbacks like toxicity and drug-resistant parasites. Collaborative drug discovery emerged as an option to speed up the way to find alternative antileishmanial agents. This is the case of Medicines for Malaria Ventures - MMV, that promotes an open source drug discovery initiative to fight diseases worldwide. Here, we screened 400 compounds from 'Pathogen Box' (PBox) collection against Leishmania braziliensis, the main etiological agent of cutaneous leishmaniasis in Brazil. Twenty-three compounds were able to inhibit ≥ 80 % L. braziliensis growth at 5 μM. Six out of the PBox selected 23 compounds were found to be highly selective against L. braziliensis intracellular amastigotes with selectivity index varying from > 104 to > 746 and IC₅₀s ranging from 47 to 480 nM. The compounds were also active against antimony-resistant L. braziliensis isolated from the field or laboratory selected mutants, revealing the potential on treating patients infected with drug resistant parasites. Most of the selected compounds were known to be active against kinetoplastids, however, two compounds (MMV688703 and MMV676477) were part of toxoplasmosis and tuberculosis 'PBox' disease set, reinforcing the potential of phenotyping screening to unveil drug repurposing. Here we applied a computational prediction of pharmacokinetic properties using the ADMET predictor pkCSM (http://biosig.unimelb.edu.au/pkcsm/). The tool offered clues on potential drug development needs and can support further in vivo studies. Molecular docking analysis identified CRK3 (LbrM.35.0660), CYP450 (LbrM.30.3580) and PKA (LbrM.18.1180) as L. braziliensis targets for MMV676604, MMV688372 and MMV688703, respectively. Compounds from 'Pathogen Box' thus represents a new hope for novel (or repurposed) small molecules source to tackle leishmaniases.

A 30 kDa polyethylene glycol-enfuvirtide complex enhances the exposure of enfuvirtide in lymphatic viral reservoirs in rats

HIV therapy with anti-retroviral drugs is limited by the poor exposure of viral reservoirs, such as lymphoid tissue, to these small molecule drugs. We therefore investigated the effect of PEGylation on the anti-retroviral activity and subcutaneous lymphatic pharmacokinetics of the peptide-based fusion inhibitor enfuvirtide in thoracic lymph duct cannulated rats. Both the peptide and the PEG were quantified in plasma and lymph via ELISA. Conjugation to a single 5 kDa linear PEG decreased anti-HIV activity three-fold compared to enfuvirtide. Whilst plasma and lymphatic exposure to peptide mass was moderately increased, the loss of anti-viral activity led to an overall decrease in exposure to enfuvirtide activity. A 20 kDa 4-arm branched PEG conjugated with an average of two enfuvirtide peptides decreased peptide activity by six-fold. Plasma and lymph exposure to enfuvirtide, however, increased significantly such that anti-viral activity was increased two- and six-fold respectively. The results suggest that a multi-enfuvirtide-PEG complex may optimally enhance the anti-retroviral activity of the peptide in plasma and lymph.

DNA-PKcs, Allostery, and DNA Double-Strand Break Repair: Defining the Structure and Setting the Stage

DNA-dependent protein kinase catalytic subunit (DNA-PKcs) is central to the regulation of the DNA damage response and repair through nonhomologous end joining. The structure has proved challenging due to its large size and multiple HEAT repeats. We have recently reported crystals of selenomethionine-labeled DNA-PKcs complexed with native KU80ct₁₉₄ (KU80 residues 539-732) diffracting to 4.3Å resolution. The novel use of crystals of selenomethionine-labeled protein expressed in HeLa cells has facilitated the use of single anomalous X-ray scattering of this 4128 amino acid, multiple HEAT-repeat structure. The monitoring of the selenomethionines in the anomalous-difference density map has allowed the checking of the amino acid residue registration in the electron density, and the labeling of the Ku-C-terminal moiety with selenomethionine has further allowed its identification in the structure of the complex with DNA-PKcs. The crystal structure defines a stage on which many of the components assemble and regulate the kinase activity through modulating the conformation and allosteric regulation of kinase activity.

Understanding and predicting the functional consequences of missense mutations in BRCA1 and BRCA2

BRCA1 and BRCA2 are tumour suppressor genes that play a critical role in maintaining genomic stability via the DNA repair mechanism. DNA repair defects caused by BRCA1 and BRCA2 missense variants increase the risk of developing breast and ovarian cancers. Accurate identification of these variants becomes clinically relevant, as means to guide personalized patient management and early detection. Next-generation sequencing efforts have significantly increased data availability but also the discovery of variants of uncertain significance that need interpretation. Experimental approaches used to measure the molecular consequences of these variants, however, are usually costly and time-consuming. Therefore, computational tools have emerged as faster alternatives for assisting in the interpretation of the clinical significance of newly discovered variants. To better understand and predict variant pathogenicity in BRCA1 and BRCA2, various machine learning algorithms have been proposed, however presented limited performance. Here we present BRCA1 and BRCA2 gene-specific models and a generic model for quantifying the functional impacts of single-point missense variants in these genes. Across tenfold cross-validation, our final models achieved a Matthew's Correlation Coefficient (MCC) of up to 0.98 and comparable performance of up to 0.89 across independent, non-redundant blind tests, outperforming alternative approaches. We believe our predictive tool will be a valuable resource for providing insights into understanding and interpreting the functional consequences of missense variants in these genes and as a tool for guiding the interpretation of newly discovered variants and prioritizing mutations for experimental validation.

DockNet: high-throughput protein-protein interface contact prediction

MOTIVATION

Over 300 000 protein-protein interaction (PPI) pairs have been identified in the human proteome and targeting these is fast becoming the next frontier in drug design. Predicting PPI sites, however, is a challenging task that traditionally requires computationally expensive and time-consuming docking simulations. A major weakness of modern protein docking algorithms is the inability to account for protein flexibility, which ultimately leads to relatively poor results.

RESULTS

Here, we propose DockNet, an efficient Siamese graph-based neural network method which predicts contact residues between two interacting proteins. Unlike other methods that only utilize a protein's surface or treat the protein structure as a rigid body, DockNet incorporates the entire protein structure and places no limits on protein flexibility during an interaction. Predictions are modeled at the residue level, based on a diverse set of input node features including residue type, surface accessibility, residue depth, secondary structure, pharmacophore and torsional angles. DockNet is comparable to current state-of-the-art methods, achieving an area under the curve (AUC) value of up to 0.84 on an independent test set (DB5), can be applied to a variety of different protein structures and can be utilized in situations where accurate unbound protein structures cannot be obtained.

AVAILABILITY AND IMPLEMENTATION

DockNet is available at https://github.com/npwilliams09/docknet and an easy-to-use webserver at https://biosig.lab.uq.edu.au/docknet. All other data underlying this article are available in the article and in its online supplementary material.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

PEGylated interferon displays differences in plasma clearance and bioavailability between male and female mice and between female immunocompetent C57Bl/6J and athymic nude mice

Gender and immune status can considerably impact on the pharmacokinetics (PK) of macromolecular and small molecule drugs. However, these effects are often not considered in drug development. We aimed to quantitatively evaluate effects of gender and immune status on the PK of PEGylated interferon in frequently used murine models. Chronically cannulated female athymic nude and female and male immunocompetent C57Bl/6J mice (n = 24 in total) received a single intravenous or subcutaneous (s.c.) dose of PEGylated interferon. Serial blood samples were taken for 48 h. Noncompartmental analysis and population PK modeling with covariate analysis were performed to evaluate the data. The PK of PEGylated interferon followed a three compartment disposition model with two sequential compartments for s.c. absorption. Female nude mice had significantly higher plasma clearance than C57Bl/6J mice (0.503 vs. 0.397 mL/h). Male mice had a slower absorption rate constant (0.138 h(-1)) and extent (46.2%) of s.c. absorption than female mice (0.274 in C57Bl/6J and 0.374 h(-1) in nude, 60.8% in both). Thus, gender and immune status significantly impacted on important PK parameters of PEGylated interferon in murine models commonly utilized in drug development. It is critical to take into account these differences when choosing animal models and conducting translational pharmacology research.

CSM-Potential: mapping protein interactions and biological ligands in 3D space using geometric deep learning

Recent advances in protein structural modelling have enabled the accurate prediction of the holo 3D structures of almost any protein, however protein function is intrinsically linked to the interactions it makes. While a number of computational approaches have been proposed to explore potential biological interactions, they have been limited to specific interactions, and have not been readily accessible for non-experts or use in bioinformatics pipelines. Here we present CSM-Potential, a geometric deep learning approach to identify regions of a protein surface that are likely to mediate protein-protein and protein-ligand interactions in order to provide a link between 3D structure and biological function. Our method has shown robust performance, outperforming existing methods for both predictive tasks. By assessing the performance of CSM-Potential on independent blind tests, we show that our method was able to achieve ROC AUC values of up to 0.81 for the identification of potential protein-protein binding sites, and up to 0.96 accuracy on biological ligand classification. Our method is freely available as a user-friendly and easy-to-use web server and API at http://biosig.unimelb.edu.au/csm_potential.

Mercury methylation by metabolically versatile and cosmopolitan marine bacteria

Microbes transform aqueous mercury (Hg) into methylmercury (MeHg), a potent neurotoxin that accumulates in terrestrial and marine food webs, with potential impacts on human health. This process requires the gene pair hgcAB, which encodes for proteins that actuate Hg methylation, and has been well described for anoxic environments. However, recent studies report potential MeHg formation in suboxic seawater, although the microorganisms involved remain poorly understood. In this study, we conducted large-scale multi-omic analyses to search for putative microbial Hg methylators along defined redox gradients in Saanich Inlet, British Columbia, a model natural ecosystem with previously measured Hg and MeHg concentration profiles. Analysis of gene expression profiles along the redoxcline identified several putative Hg methylating microbial groups, including Calditrichaeota, SAR324 and Marinimicrobia, with the last the most active based on hgc transcription levels. Marinimicrobia hgc genes were identified from multiple publicly available marine metagenomes, consistent with a potential key role in marine Hg methylation. Computational homology modelling predicts that Marinimicrobia HgcAB proteins contain the highly conserved amino acid sites and folding structures required for functional Hg methylation. Furthermore, a number of terminal oxidases from aerobic respiratory chains were associated with several putative novel Hg methylators. Our findings thus reveal potential novel marine Hg-methylating microorganisms with a greater oxygen tolerance and broader habitat range than previously recognized.

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.

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/.

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.

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/.

Covalent inactivation of Mycobacterium thermoresistibile inosine-5'-monophosphate dehydrogenase (IMPDH)

Inosine-5'-monophosphate dehydrogenase (IMPDH) is a rate-limiting enzyme involved in nucleotide biosynthesis. Because of its critical role in purine biosynthesis, IMPDH is a drug design target for immunosuppressive, anticancer, antiviral and antimicrobial chemotherapy. In this study, we use mass spectrometry and X-ray crystallography to show that the inhibitor 6-Cl-purine ribotide forms a covalent adduct with the Cys-341 residue of Mycobacterium thermoresistibile IMPDH.

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.

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.