Traditional design of small molecule therapies has focused on specific, disease-associated protein targets which have led to the development of many breakthrough medicines. However, once a drug enters the body, it interacts with dozens, if not hundreds, of proteins before it is eliminated from the body. These off-target interactions can impact the safety of a drug or may lead to drug repurposing opportunities. Cyclica's drug-centric, proteome-wide approach focuses on a drug's polypharmacology — all the proteins it interacts with — to provide insights into repurposing efforts, target identification, lead prioritization, and adverse effect elucidation.
Cyclica has designed, patented, and optimized our Ligand Design technology, which can uniquely de novo design chemical entities across a panel of desirable targets while avoiding undesirable anti-targets. Driven by a metaheuristic genetic algorithm coupled with a novel AI technology that we have built internally at Cyclica called POEM (patents filed Sept 2018), Ligand Design begins by fragmenting seed molecules and derivatizing them with preferred fragment libraries to explore synthetically accessible chemical space. Ligand Design then selects amongst these hypothetical molecules for those with desirable physicochemical and pharmacokinetic properties to proceed to the next step - this is based on our internally developed ADMET-Prediction technology. Ligand Design then computes polypharmacological profiles, selects those with preferred profiles, and then initiates another cycle of DDD. This process continues until a set of molecules with desirable properties are fashioned.
Cyclica has developed, validated, patented and commercialized Ligand Express®, a cloud-based platform that screens small-molecule drugs against repositories of structurally-characterized proteins or ‘proteomes’ to determine polypharmacological profiles. Accordingly, Ligand Express® identifies significant protein targets using an innovative structure-based and drug-centric technology, leverages artificial intelligence to determine the drug’s effect on these targets, and visualizes the predicted drug-protein interactome using bioinformatics and systems biology. The platform provides a unique panoramic view of a small-molecule, by identifying on- and off-target interactions that may be expected, as well as those that are unanticipated.
Click on the image above to see more details about the Ligand Express approach.
Why is Ligand Express Valuable?
By understanding how a small-molecule drug will interact with all proteins in the body, Ligand Express® augments scientific investigation by elucidating mechanism of action, prioritizing lead candidates, understanding side effects, as well as determining new uses for existing drugs. You can access our platform at ligandexpress.com.
New to Ligand Express: ADMET Prediction
A drug needs to do more than binding to a drug target; it also needs to have desirable pharmacological properties. Ligand Express® is gaining a collection of predictive ADMET models built using a proprietary AI methodology to help translate small molecules into drugs. The technology has demonstrated enhanced predictive accuracy for generating QSAR models compared to traditional classifiers as seen in the validation note here. Understanding polypharmacology through Ligand Express® and coupling that with ADMET Prediction will allow scientists to make efficient and informed decisions like never before.
New to Ligand Express: Single Nucleotide Variants
Genetic data holds remarkable insights into human health; however, scientists are still developing methods to best utilize this plethora of data. With the support of the Ontario Centres of Excellence and IBM, Cyclica drives actionable insights out of genetic data by integrating them within Ligand Express® through a technology called Structural Pharmacogenomics (SPG). Using super computing, Cyclica has prepared a robust genetic database of single nucleotide polymorphisms (SNPs) and maps them to the protein structure. This mapping exercise allows researchers to quickly identify potential genetic variants that would impact small molecule binding (see image below) or are implicated in disease. Planned integration: Early 2019.