Quantum Lens
Physics-Based Intelligence for Drug Discovery
Quantum Lens, our quantum and AI platform, provides the depth needed to guide high-stakes discovery decisions and support the discovery and design of differentiated drug candidates.
We bring therapeutic design into focus through the lens of fundamental physics.
The Expertise
We identify the physical hurdles stalling your program - deciding which factors need to be modelled and at what level of accuracy.
The Technology
Our platform provides the depth needed to illuminate molecular behaviours that standard high-throughput tools cannot resolve.
The Insight
Customers receive actionable discovery decisions, not raw data. We navigate the complexity of the science, so your team can focus on decisions that move programmes forward.
Selected Areas of Expertise
1. Covalent Reactivity
Predict reactivity and understand covalency in ways other methods miss, enabling accurate tuning and design
Suitable for multiple target classes: kinases, GPCRs, ion channels, enzymes.
Kinetic-Driven Potency: Modelling binding as a dynamic reaction to identify compounds with superior residence time and potency.
Structural Bias Elimination: Automatically identifying link-orbitals via DMET to only include the orbitals that contribute to the bonding process - more efficient calculations.
Site-Specific Selectivity: Tuning warhead reactivity via Fukui Indices to prevent off-target bonding and reduce systemic toxicity.
Validated Covalent Engagement: Distinguishing true chemical bonds from non-specific proximity using Mayer Bond Orders to gain a quantitative measure of covalency.
Predictive Inactivation Rates: Leveraging Two-Body Correlators for understanding how the covalent bond forms.
Electronic Affinity Mapping: Capturing sub-atomic "entanglement" to find potency drivers that standard docking and FEP consistently overlook.
2. Hard-to-Drug Enzyme Targets
Design potent, selective inhibitors for hard-to-drug enzymes by exploiting non-obvious binding interactions and Transition State modelling.
Enzyme Inhibitors inspired by enzyme function for exquisite selectivity and potency
Transition State Informed Lead Selectivity: Creating unique "quantum fingerprints" of the transition state to achieve world-class selectivity across highly homologous isoforms and mutants.
Generative Drug-Like Innovation: Translating complex transition-state insights into practical, low-molecular-weight leads that medicinal chemists actually want to synthesise.
Electronic Context Mapping: Factoring in sub-atomic entanglement and local environments to predict binding affinity where standard forcefields fail.
High-Velocity TS-Design: Streamlining transition-state workflows to deliver high-resolution, physics-first results in months, significantly accelerating drug-like transition-state inhibitor design.
3. Allosteric / Shallow Pockets
Discover insights, resolve confounding non-intuitive variables, and make confident design decisions.
Suitable for multiple target classes and modalities: kinases, GPCRs, ion channels, enzymes, glues, peptides and PPI’s
FMO-Driven Affinity Mapping: Deconstructing binding scores into residue-specific electronic contributions to identify precise, actionable potency drivers.
Entanglement-Based Target Mapping: Measuring complex electronic environments to identify non-obvious binding interactions for high-affinity optimisation.
Intelligence-Driven Molecular Generation: Translating deep quantum insights into novel, synthesisable chemical structures optimised for superior pharmacological performance in novel IP space.
Expanding Multi-Scale Physics Architecture: Deploying and expanding a specialised suite of advanced technologies to resolve confounding variables in the most challenging targets.