Predictive modelling of compound properties using MD and machine learning
Utilizing molecular dynamics (MD) simulations combined with machine learning (ML) to predict emergent properties of chemical compounds. This approach leverages descriptors from MD simulations to train ML models, enabling the prediction of properties without extensive simulations.
Overview
DAMSL Ltd presents an innovative approach to predictive modelling by integrating molecular dynamics (MD) simulations with machine learning (ML). This combined methodology enables the prediction of emergent properties of chemical compounds that are not directly observable through MD alone, due to constraints in time and size scales. By leveraging multiscale MD simulations and extracting interaction descriptors, this method allows for the training of ML models to predict complex system properties efficiently.
Technical specifications
Key features:
- Utilizes coarse-grained (Martini) models in MD simulations to obtain molecular interaction descriptors.
- Trains ML models using descriptors to predict emergent properties, thus bypassing the need for extensive MD simulations.
- Applicable for predicting properties like drug loading and anti-aggregation characteristics based on chemical structure.
- Involves constructing a training dataset exemplifying chemical components and processing parameters for model training.
- Suitable for simulating excipient/protein mixtures and polymer/drug mixtures.
Technology readiness level
This technology is at TRL 3, indicating experimental proof of concept. DAMSL Ltd seeks partnerships to provide validated experimental data for model training, as well as funding for personnel and computational resources to advance the development process.
About DAMSL Ltd
DAMSL Ltd is a research-led data science company founded in 2017 that provides bespoke solutions in data analytics, statistical modelling, and machine learning. Operated by a team of internationally renowned academic researchers and professors, the firm specializes in cutting-edge mathematics, computer science, and statistics. Their service offerings are categorized into three main areas: providing bespoke algorithms, code, and software products; delivering expert consultancy on data modelling and decision-making; and conducting tailored training courses for businesses. Their technical expertise includes Bayesian learning, uncertainty quantification, image analysis, and the development of digital twins, with capabilities that span R and Python-based data science environments.
By offering commercial access to advanced research methods, DAMSL helps partners across diverse sectors, such as retail, healthcare, energy, and pharmaceuticals, solve complex analytical problems and extract actionable value from their data. The company leverages deep academic knowledge to address challenges ranging from process parameter optimisation to clinical drug discovery and human behavioural data analysis. Their engagement model focuses on providing rigorous scientific insights, ensuring that clients benefit from evidence-based, robust statistical techniques and high-performance computing capabilities to drive business performance and innovation.
delivered to your inbox.