CSM-Potential is 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
COVID-3D is an online resource that provides a bridge between the wealth of genomic information being collected on SARS-CoV-2 and their structural and functional consequences, to provide biological insights and help guide therapeutic development efforts.
DockNet, an efficient siamese graph-based deep neural network method which predicts contact residues between two interacting proteins. Unlike other methods that only utilise 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.
Calculation and visualisation of all molecular interactions between atoms of molecules of interest, including proteins, nucleic acids, carbohydrates as well as small molecules.
Reliable and open source virtual screening and clustering.
A tool for mapping and visualising genetic sequencing data on protein 3D structure.
Quantification of the extent of localized purifying selection in protein-coding sequences. The missense tolerance ratio (MTR) summarizes available human standing variation data within genes to encapsulate population level genetic variation.
An optimised knowledge based method for predicting effects of mutations on protein stability.
A novel graph-based signature approach for the quantitative prediction of the effects of missense mutations on protein stability.
An integrated computational approach for quantitative prediction of the effects of missense mutations on protein stability.
Analysis and visualisation of protein dynamics using normal mode analysis. Quantitative prediction of the effects of missense mutations on protein dynamics and stability.
Fast and accurate evaluation of the effects of single and multiple point mutations on protein folding, stability, flexibility and conformation by combining protein dynamics and machine learning.
Predicting the effects of mutations in membrane proteins on stability, and whether they are likely to be benign or pathogenic.
A novel graph-based signature approach for the quantitative prediction of the effects of missense mutations on protein-protein binding affinity.
An optimised novel graph-based signature approach for the quantitative prediction of the effects of missense mutations on protein-protein binding affinity.
A scalable and effective machine learning model for accurately assessing changes in protein-protein binding affinity caused by single and multiple missense mutations
Quantitative prediction of the effects of missense mutations on antibody-antigen binding affinity to guide rational antibody engineering.
Optimised predictions of the effects of mutations on antibody-antigen binding affinity.
Predicting the effects of introducing multiple point mutations on antibody-antigen binding affinity.
A novel graph-based signature approach for the quantitative prediction of the effects of missense mutations on protein-DNA binding affinity.
Quantitative prediction of the effects of missense mutations on protein-nucleic acid binding affinities using graph-based signatures.
Predicting the effects of multiple point mutations on protein-nucleic acid interactions.
Quantitative prediction of the effects of missense mutations on affinities of small molecules for proteins using graph-based signatures.
Predicting the effect of mutations in AtpE on Bedaquiline sensitivity.
Predicting the effect of mutations in pncA on Pyrazinamide sensitivity.
Predicting the effect of mutations in rpoB on Rifampicin sensitivity.
kinCSM is an integrative computational tool capable of accurately identifying potent cyclin-dependent kinase 2 (CDK2) inhibitors, quantitatively predicting CDK2 ligand-kinase inhibition constants (pKi) and classify inhibition modes without kinase informatio
Identification of protein kinase activating missense mutations.
Target and Symptom-based computational Model for miRNA-Disease Association prediction (TSMDA) is a novel machine learning method that leverages target and symptom information and negative sample selection to predict miRNA-disease association.
Predicting antibody-antigen binding affinity.
Predicting the protein binding affinity of small molecules using graph-based signatures.
Predicting metal binding sites in protein 3D structures.
epitope3D is a web resource tool for conformational epitope prediction.
toxCSM leverages our well established graph-based signatures concept to develop scalable and accurate predictive models using supervised learning, outperforming alternative methods. Using these signatures we have developed 36 models for predicting a wide range of toxicity properties, from nuclear and stress responses to environmental toxicity, which can assist in the development of safer and less toxic drugs as well as herbicides and pesticides
Prediction of small molecule pharmacokinetic and toxicity properties using graph-based signatures.
A graph-based signature approach to rapidly identify compounds likely to be active against Mycobacterium
A graph-based signature approach to rapidly identify compounds likely to be active against over 70 different cancer cell lines.
A graph-based signature approach to rapidly identify ligands against 36 major GPCR targets, across 4 classes.
A machine learning approach that uses a graph-based representation of small molecules to help guide identification of modulating protein-protein interactions via inhibition.
Prediction and optimisation of dendrimer intravenous pharmacokinetic profiles.
To facilitate the further development and evaluation of methods to predict these changes, we have developed ThermoMutDB, a manually curated database containing >14,669 experimental data of thermodynamic parameters for wild type and mutant proteins.
This manually curated, literature-derived database of the effects of over 1,000 mutations protein-ligand binding affinity together with the three-dimensional structures of the complex.
Accurate prediction of the risk of ccRCC associated with all possible VHL missense mutations.
A relational database to facilitate rational protein engineering of Botulinum for therapeutic use.
A novel machine learning method for the identification of 8 different types of therapeutic peptides