Kinact: a computational approach for predicting activating missense mutations in protein kinases

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.

Large-scale pathogenicity prediction analysis of cancer-associated kinase mutations reveals variability in sensitivity and specificity of computational methods

BACKGROUND

Mutations in kinases are the most frequent genetic alterations in cancer; however, experimental evidence establishing their cancerous nature is available only for a small fraction of these mutants.

AIMS

Predicition analysis of kinome mutations is the primary aim of this study. Further objective is to compare the performance of various softwares in pathogenicity prediction of kinase mutations.

MATERIALS AND METHODS

We employed a set of computational tools to predict the pathogenicity of over forty-two thousand mutations and deposited the kinase-wise data in Mendeley database (Estimated Pathogenicity of Kinase Mutants [EPKiMu]).

RESULTS

Mutations are more likely to be drivers when being present in the kinase domain (vs. non-kinase domain) and belonging to hotspot residues (vs. non-hotspot residues). We identified that, while predictive tools have low specificity in general, PolyPhen-2 had the best accuracy. Further efforts to combine all four tools by consensus, voting, or other simple methods did not significantly improve accuracy.

DISCUSSION

The study provides a large dataset of kinase mutations along with their predicted pathogenicity that can be used as a training set for future studies. Furthermore, a comparative sensitivity and selectivity of commonly used computational tools is presented.

CONCLUSION

Primary-structure-based in silico tools identified more cancerous/deleterious mutations in the kinase domains and at the hot spot residues while having higher sensitivity than specificity in detecting deleterious mutations.

Nadir paranazal sinüs kanserlerinde yeni tanımlanan reseptör tirozin kinaz mutasyonları ve potansiyel fonksiyonel etkileri

Amaç: Paranazal sinüs kanserleri oldukça nadir görülen heterojen bir hastalık grubudur. Maksiler sinüs skuamoz hücreli karsinomu, paranazal sinüs kanserlerinin anatomik ve histolojik olarak en yaygın alt tipidir. Bu kanserin genetik profiline dair bilginin sınırlı olması, hastaların hedefli tedavi seçeneklerinden yararlanamamasına neden olmaktadır. Çalışmamızda bu nadir kanserdeki reseptör tirozin kinaz mutasyonlarının tanımlanması ve mutasyonların olası fonksiyonel etkilerinin tahmin edilmesi amaçlanmıştır. Gereç ve Yöntem: Bu amaçla 30 olgunun tümörüne ait FFPE dokulardan DNA izolasyonu gerçekleştirildi, olguların mutasyon profili yeni nesil sekanslama yöntemi ve biyoinformatik değerlendirme ile belirlendi. Belirlenen patojenik/ olası patojenik varyantların fonksiyonel etkileri farklı in silico araçlar yardımıyla tahminlendi. Bulgular: Olgularının tamamında en az bir adet patojenik/olası patojenik KIT, PDFGRA ve RETmutasyonu belirlendi. KIT geninin katalitik bölgesindeki mutasyonların kinaz aktivitesini arttıracağı tahmin edildi. PDFGRA genindeki p.P567P ve p.D1074D mutasyonları, 30 olgunun tamamında ve SRA veritabanından elde edilen normal dokulara ait okumaların tümünde belirlendi. Sonuç: Reseptör tirozin kinaz mutasyonlarının paranazal sinüs kanserlerinde de önemli rol oynayabileceğinin belirlenmiş olması özellikle artmış kinaz aktivitesini hedefleyen tedavi yaklaşımlarını bu olguların erişimine sunma potansiyeli taşıması bakımından oldukça önemlidir.

Mass Spectrometry-Based Proteomics Workflows in Cancer Research: The Relevance of Choosing the Right Steps

The qualitative and quantitative evaluation of proteome changes that condition cancer development can be achieved with liquid chromatography-mass spectrometry (LC-MS). LC-MS-based proteomics strategies are carried out according to predesigned workflows that comprise several steps such as sample selection, sample processing including labeling, MS acquisition methods, statistical treatment, and bioinformatics to understand the biological meaning of the findings and set predictive classifiers. As the choice of best options might not be straightforward, we herein review and assess past and current proteomics approaches for the discovery of new cancer biomarkers. Moreover, we review major bioinformatics tools for interpreting and visualizing proteomics results and suggest the most popular machine learning techniques for the selection of predictive biomarkers. Finally, we consider the approximation of proteomics strategies for clinical diagnosis and prognosis by discussing current barriers and proposals to circumvent them.

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.

Predictive functional, statistical and structural analysis of CSNK2A1 and CSNK2B variants linked to neurodevelopmental diseases

Okur-Chung Neurodevelopmental Syndrome (OCNDS) and Poirier-Bienvenu Neurodevelopmental Syndrome (POBINDS) were recently identified as rare neurodevelopmental disorders. OCNDS and POBINDS are associated with heterozygous mutations in the CSNK2A1 and CSNK2B genes which encode CK2α, a serine/threonine protein kinase, and CK2β, a regulatory protein, respectively, which together can form a tetrameric enzyme called protein kinase CK2. A challenge in OCNDS and POBINDS is to understand the genetic basis of these diseases and the effect of the various CK2⍺ and CK2β mutations. In this study we have collected all variants available to date in CSNK2A1 and CSNK2B, and identified hotspots. We have investigated CK2⍺ and CK2β missense mutations through prediction programs which consider the evolutionary conservation, functionality and structure or these two proteins, compared these results with published experimental data on CK2α and CK2β mutants, and suggested prediction programs that could help predict changes in functionality of CK2α mutants. We also investigated the potential effect of CK2α and CK2β mutations on the 3D structure of the proteins and in their binding to each other. These results indicate that there are functional and structural consequences of mutation of CK2α and CK2β, and provide a rationale for further study of OCNDS and POBINDS-associated mutations. These data contribute to understanding the genetic and functional basis of these diseases, which is needed to identify their underlying mechanisms.

Allostery: Allosteric Cancer Drivers and Innovative Allosteric Drugs

Here, we discuss the principles of allosteric activating mutations, propagation downstream of the signals that they prompt, and allosteric drugs, with examples from the Ras signaling network. We focus on Abl kinase where mutations shift the landscape toward the active, imatinib binding-incompetent conformation, likely resulting in the high affinity ATP outcompeting drug binding. Recent pharmacological innovation extends to allosteric inhibitor (GNF-5)-linked PROTAC, targeting Bcr-Abl1 myristoylation site, and broadly, allosteric heterobifunctional degraders that destroy targets, rather than inhibiting them. Designed chemical linkers in bifunctional degraders can connect the allosteric ligand that binds the target protein and the E3 ubiquitin ligase warhead anchor. The physical properties and favored conformational state of the engineered linker can precisely coordinate the distance and orientation between the target and the recruited E3. Allosteric PROTACs, noncompetitive molecular glues, and bitopic ligands, with covalent links of allosteric ligands and orthosteric warheads, increase the effective local concentration of productively oriented and placed ligands. Through covalent chemical or peptide linkers, allosteric drugs can collaborate with competitive drugs, degrader anchors, or other molecules of choice, driving innovative drug discovery.

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.

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.

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.

Peptide-based electrochemical biosensors utilized for protein detection

Proteins are generally detected as biomarkers for tracing or determining various disorders in organisms. Biomarker proteins can be tracked in samples with various origins and in different concentrations, revealing whether an organism is in a healthy or unhealthy state. In regard to detection, electrochemical biosensors are a potential fusion of electronics, chemistry, and biology, allowing for fast and early point-of-care detection from a biological sample with the advantages of high sensitivity, simple construction, and easy operation. Peptides present a promising approach as a biorecognition element when connected with electrochemical biosensors. The benefits of short peptides lie mainly in their good stability and selective affinity to a target analyte. Therefore, peptide-based electrochemical biosensors (PBEBs) represent an alternative approach for the detection of different protein biomarkers. This review provides a summary of the past decade of recently proposed PBEBs designed for protein detection, dividing them according to different protein types: (i) enzyme detection, including proteases and kinases; (ii) antibody detection; and (iii) other protein detection. According to these protein types, different sensing mechanisms are discussed, such as the peptide cleavage by a proteases, phosphorylation by kinases, presence of antibodies, and exploiting of affinities; furthermore, measurements are obtained by different electrochemical methods. A discussion and comparison of various constructions, modifications, immobilization strategies and different sensing techniques in terms of high sensitivity, selectivity, repeatability, and potential for practical application are presented.

Variation benchmark datasets: update, criteria, quality and applications

Development of new computational methods and testing their performance has to be carried out using experimental data. Only in comparison to existing knowledge can method performance be assessed. For that purpose, benchmark datasets with known and verified outcome are needed. High-quality benchmark datasets are valuable and may be difficult, laborious and time consuming to generate. VariBench and VariSNP are the two existing databases for sharing variation benchmark datasets used mainly for variation interpretation. They have been used for training and benchmarking predictors for various types of variations and their effects. VariBench was updated with 419 new datasets from 109 papers containing altogether 329 014 152 variants; however, there is plenty of redundancy between the datasets. VariBench is freely available at http://structure.bmc.lu.se/VariBench/. The contents of the datasets vary depending on information in the original source. The available datasets have been categorized into 20 groups and subgroups. There are datasets for insertions and deletions, substitutions in coding and non-coding region, structure mapped, synonymous and benign variants. Effect-specific datasets include DNA regulatory elements, RNA splicing, and protein property for aggregation, binding free energy, disorder and stability. Then there are several datasets for molecule-specific and disease-specific applications, as well as one dataset for variation phenotype effects. Variants are often described at three molecular levels (DNA, RNA and protein) and sometimes also at the protein structural level including relevant cross references and variant descriptions. The updated VariBench facilitates development and testing of new methods and comparison of obtained performances to previously published methods. We compared the performance of the pathogenicity/tolerance predictor PON-P2 to several benchmark studies, and show that such comparisons are feasible and useful, however, there may be limitations due to lack of provided details and shared data.

Database URL: http://structure.bmc.lu.se/VariBench

mCSM-membrane: predicting the effects of mutations on transmembrane proteins

Significant efforts have been invested into understanding and predicting the molecular consequences of mutations in protein coding regions, however nearly all approaches have been developed using globular, soluble proteins. These methods have been shown to poorly translate to studying the effects of mutations in membrane proteins. To fill this gap, here we report, mCSM-membrane, a user-friendly web server that can be used to analyse the impacts of mutations on membrane protein stability and the likelihood of them being disease associated. mCSM-membrane derives from our well-established mutation modelling approach that uses graph-based signatures to model protein geometry and physicochemical properties for supervised learning. Our stability predictor achieved correlations of up to 0.72 and 0.67 (on cross validation and blind tests, respectively), while our pathogenicity predictor achieved a Matthew's Correlation Coefficient (MCC) of up to 0.77 and 0.73, outperforming previously described methods in both predicting changes in stability and in identifying pathogenic variants. mCSM-membrane will be an invaluable and dedicated resource for investigating the effects of single-point mutations on membrane proteins through a freely available, user friendly web server at http://biosig.unimelb.edu.au/mcsm_membrane.

mCSM-AB2: guiding rational antibody design using graph-based signatures

MOTIVATION

A lack of accurate computational tools to guide rational mutagenesis has made affinity maturation a recurrent challenge in antibody (Ab) development. We previously showed that graph-based signatures can be used to predict the effects of mutations on Ab binding affinity.

RESULTS

Here we present an updated and refined version of this approach, mCSM-AB2, capable of accurately modelling the effects of mutations on Ab-antigen binding affinity, through the inclusion of evolutionary and energetic terms. Using a new and expanded database of over 1800 mutations with experimental binding measurements and structural information, mCSM-AB2 achieved a Pearson's correlation of 0.73 and 0.77 across training and blind tests, respectively, outperforming available methods currently used for rational Ab engineering.

AVAILABILITY AND IMPLEMENTATION

mCSM-AB2 is available as a user-friendly and freely accessible web server providing rapid analysis of both individual mutations or the entire binding interface to guide rational antibody affinity maturation at http://biosig.unimelb.edu.au/mcsm_ab2.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

DynaMut2: Assessing changes in stability and flexibility upon single and multiple point missense mutations

Predicting the effect of missense variations on protein stability and dynamics is important for understanding their role in diseases, and the link between protein structure and function. Approaches to estimate these changes have been proposed, but most only consider single‐point missense variants and a static state of the protein, with those that incorporate dynamics are computationally expensive. Here we present DynaMut2, a web server that combines Normal Mode Analysis (NMA) methods to capture protein motion and our graph‐based signatures to represent the wildtype environment to investigate the effects of single and multiple point mutations on protein stability and dynamics. DynaMut2 was able to accurately predict the effects of missense mutations on protein stability, achieving Pearson's correlation of up to 0.72 (RMSE: 1.02 kcal/mol) on a single point and 0.64 (RMSE: 1.80 kcal/mol) on multiple‐point missense mutations across 10‐fold cross‐validation and independent blind tests. For single‐point mutations, DynaMut2 achieved comparable performance with other methods when predicting variations in Gibbs Free Energy (ΔΔG) and in melting temperature (ΔT_m). We anticipate our tool to be a valuable suite for the study of protein flexibility analysis and the study of the role of variants in disease. DynaMut2 is freely available as a web server and API at http://biosig.unimelb.edu.au/dynamut2.

Identifying Genotype-Phenotype Correlations via Integrative Mutation Analysis

Mutations in protein-coding regions can lead to large biological changes and are associated with genetic conditions, including cancers and Mendelian diseases, as well as drug resistance. Although whole genome and exome sequencing help to elucidate potential genotype-phenotype correlations, there is a large gap between the identification of new variants and deciphering their molecular consequences. A comprehensive understanding of these mechanistic consequences is crucial to better understand and treat diseases in a more personalized and effective way. This is particularly relevant considering estimates that over 80% of mutations associated with a disease are incorrectly assumed to be causative. A thorough analysis of potential effects of mutations is required to correctly identify the molecular mechanisms of disease and enable the distinction between disease-causing and non-disease-causing variation within a gene. Here we present an overview of our integrative mutation analysis platform, which focuses on refining the current genotype-phenotype correlation methods by using the wealth of protein structural information.

Challenges and Opportunities in Cancer Drug Resistance

There has been huge progress in the discovery of targeted cancer therapies in recent years. However, even for the most successful and impactful cancer drugs which have been approved, both innate and acquired mechanisms of resistance are commonplace. These emerging mechanisms of resistance have been studied intensively, which has enabled drug discovery scientists to learn how it may be possible to overcome such resistance in subsequent generations of treatments. In some cases, novel drug candidates have been able to supersede previously approved agents; in other cases they have been used sequentially or in combinations with existing treatments. This review summarizes the current field in terms of the challenges and opportunities that cancer resistance presents to drug discovery scientists, with a focus on small molecule therapeutics. As part of this review, common themes and approaches have been identified which have been utilized to successfully target emerging mechanisms of resistance. This includes the increase in target potency and selectivity, alternative chemical scaffolds, change of mechanism of action (covalents, PROTACs), increases in blood-brain barrier permeability (BBBP), and the targeting of allosteric pockets. Finally, wider approaches are covered such as monoclonal antibodies (mAbs), bispecific antibodies, antibody drug conjugates (ADCs), and combination therapies.

mycoCSM: Using Graph-Based Signatures to Identify Safe Potent Hits against Mycobacteria

Development of new potent, safe drugs to treat Mycobacteria has proven to be challenging, with limited hit rates of initial screens restricting subsequent development efforts. Despite significant efforts and the evolution of quantitative structure-activity relationship as well as machine learning-based models for computationally predicting molecule bioactivity, there is an unmet need for efficient and reliable methods for identifying biologically active compounds against Mycobacterium that are also safe for humans. Here we developed mycoCSM, a graph-based signature approach to rapidly identify compounds likely to be active against bacteria from the genus Mycobacterium, or against specific Mycobacteria species. mycoCSM was trained and validated on eight organism-specific and for the first time a general Mycobacteria data set, achieving correlation coefficients of up to 0.89 on cross-validation and 0.88 on independent blind tests, when predicting bioactivity in terms of minimum inhibitory concentration. In addition, we also developed a predictor to identify those compounds likely to penetrate in necrotic tuberculosis foci, which achieved a correlation coefficient of 0.75. Together with a built-in estimator of the maximum tolerated dose in humans, we believe this method will provide a valuable resource to enrich screening libraries with potent, safe molecules. To provide simple guidance in the selection of libraries with favorable anti-Mycobacteria properties, we made mycoCSM freely available online at http://biosig.unimelb.edu.au/myco_csm.

mmCSM-AB: guiding rational antibody engineering through multiple point mutations

While antibodies are becoming an increasingly important therapeutic class, especially in personalized medicine, their development and optimization has been largely through experimental exploration. While there have been many efforts to develop computational tools to guide rational antibody engineering, most approaches are of limited accuracy when applied to antibody design, and have largely been limited to analysing a single point mutation at a time. To overcome this gap, we have curated a dataset of 242 experimentally determined changes in binding affinity upon multiple point mutations in antibody-target complexes (89 increasing and 153 decreasing binding affinity). Here, we have shown that by using our graph-based signatures and atomic interaction information, we can accurately analyse the consequence of multi-point mutations on antigen binding affinity. Our approach outperformed other available tools across cross-validation and two independent blind tests, achieving Pearson's correlations of up to 0.95. We have implemented our new approach, mmCSM-AB, as a web-server that can help guide the process of affinity maturation in antibody design. mmCSM-AB is freely available at http://biosig.unimelb.edu.au/mmcsm_ab/.

A Comprehensive Computational Platform to Guide Drug Development Using Graph-Based Signature Methods

High-throughput computational techniques have become invaluable tools to help increase the overall success, process efficiency, and associated costs of drug development. By designing ligands tailored to specific protein structures in a disease of interest, an understanding of molecular interactions and ways to optimize them can be achieved prior to chemical synthesis. This understanding can help direct crucial chemical and biological experiments by maximizing available resources on higher quality leads. Moreover, predicting molecular binding affinity within specific biological contexts, as well as ligand pharmacokinetics and toxicities, can aid in filtering out redundant leads early on within the process. We describe a set of computational tools which can aid in drug discovery at different stages, from hit identification (EasyVS) to lead optimization and candidate selection (CSM-lig, mCSM-lig, Arpeggio, pkCSM). Incorporating these tools along the drug development process can help ensure that candidate leads are chemically and biologically feasible to become successful and tractable drugs.

dendPoint: a web resource for dendrimer pharmacokinetics investigation and prediction

Nanomedicine development currently suffers from a lack of efficient tools to predict pharmacokinetic behavior without relying upon testing in large numbers of animals, impacting success rates and development costs. This work presents dendPoint, the first in silico model to predict the intravenous pharmacokinetics of dendrimers, a commonly explored drug vector, based on physicochemical properties. We have manually curated the largest relational database of dendrimer pharmacokinetic parameters and their structural/physicochemical properties. This was used to develop a machine learning-based model capable of accurately predicting pharmacokinetic parameters, including half-life, clearance, volume of distribution and dose recovered in the liver and urine. dendPoint successfully predicts dendrimer pharmacokinetic properties, achieving correlations of up to r = 0.83 and Q² up to 0.68. dendPoint is freely available as a user-friendly web-service and database at http://biosig.unimelb.edu.au/dendpoint. This platform is ultimately expected to be used to guide dendrimer construct design and refinement prior to embarking on more time consuming and expensive in vivo testing.

mCSM-PPI2: predicting the effects of mutations on protein-protein interactions

Protein-protein Interactions are involved in most fundamental biological processes, with disease causing mutations enriched at their interfaces. Here we present mCSM-PPI2, a novel machine learning computational tool designed to more accurately predict the effects of missense mutations on protein-protein interaction binding affinity. mCSM-PPI2 uses graph-based structural signatures to model effects of variations on the inter-residue interaction network, evolutionary information, complex network metrics and energetic terms to generate an optimised predictor. We demonstrate that our method outperforms previous methods, ranking first among 26 others on CAPRI blind tests. mCSM-PPI2 is freely available as a user friendly webserver at http://biosig.unimelb.edu.au/mcsm_ppi2/.