Computer-aided drug discovery
Based on the pioneering work of Prof. Graham Richards FRS at Oxford University, Oxford Drug Design has spent many years developing a distinctive proprietary multi-toolkit of drug design technologies.
These incorporate powerful virtual screening for both ligand-based and structure-based design.
Rather than trying to solve every problem in the same way we apply our custom-developed AI/ML tools specifically to each drug discovery program. This leads to superior insights and the acceleration of our discovery outcomes.
Click here to see the impact of our computational methods to accelerate our own pipeline, and here to discover how we are differentiated when applying them to support your own discovery needs.
Innovative chemical representations
In order to be useful, any AI drug discovery method must be based on a meaningful representation of chemical structure.
A key differentiating strength of Oxford Drug Design is the special emphasis we place on generating such chemical representations.
Our proprietary tool EShape™ captures the complexities of molecular shape and charge in a compact and easily searchable form.
Once incorporated into our molecular databases, molecular similarity comparisons can be assessed at speeds of one million/sec. This enables data mining of very large scale drug-relevant chemical spaces.
The results critically include virtual compounds that are readily synthesizable from accessible chemical building blocks and sustain robust and reliable chemical reactions.
Generative AI
Generative AI methods are being applied to numerous fields. In drug discovery, these mostly result in large numbers of potential molecules which are not feasible or economical to make.
Our proprietary generative approach SynthAI™ uses ODD’s deep reinforcement learning integrated with our proprietary databases to generate only molecules with desired activity that can be made and made economically.
This in turn leads to a streamlined therapeutic discovery process impacting patient lives faster.
Topological data analysis (TDA)
TDA is the field of mathematics that provides a set of topological and geometrical tools to analyse complex, high-dimensional datasets. Oxford Drug Design has incorporated TDA into its molecular shape/fit AI methods.
We are applying and developing innovative analyses of molecules via TDA to extract persistent (homological) features from their three-dimensional shapes.
These novel representations then enrich and complement existing ones, thus generating important new opportunities for our machine learning applications.
AIScape for optimized predictions
AIScape™ integrates our machine learning models into a powerful predictive visualisation and data analysis tool.
An important aspect of these models is their interpretability, providing our scientists with an understanding of the reasoning behind the model prediction. This is preferable to “black box” AI methods that lack such essential understanding.
AIScape enables our domain scientists to gain superior insights into the relationships between chemical structures and their desired biological activity.
Click here to see the impact of our computational methods accelerating our own Pipeline, and here to discover how we can apply them to support your own discovery needs.