Skip to main content
Premium Trial:

Request an Annual Quote

UK s Amedis Pharmaceuticals Attracts Argenta With AI-driven ADMET Prediction Platform


Amedis Pharmaceuticals, a Cambridge, UK-based drug discovery firm, recently used its artificial intelligence to attract Argenta Discovery as a partner: Amedis is using AI technology to predict the absorption, distribution, metabolism, excretion, and toxicity, or ADMET, properties of drug molecules, and in a deal signed last week with Argenta, of Harlow, UK, agreed to apply this technology to compound bioavailability and toxicity. The agreement expands upon a collaboration between the two firms that began in June 2002.

Effective ADMET prediction is a key goal for drug discovery research; if the ADMET properties of molecules can be determined before they are synthesized, the industry could shave several years and millions of dollars off the drug development process. Amedis uses several algorithms based on genetic programming that it claims are quite effective in predicting ADMET properties. According to CEO John Montana, the company begins with a database of drugs, and breaks those compounds down into their atomic components. “We calculate properties on that set of atomic components, and then we equate those calculated properties to the original biological data.”

Amedis uses genetic programming to identify associations of the calculated properties of the compounds with the biological data, “and that generates a predictive model for the way in which those compounds interact with the proteins in question,” according to Montana. The company then applies the predictive model to a database of compounds to predict their activity against a target.

The collaboration with Argenta will concentrate on “specific metabolizing enzymes and other aspects of toxicology,” Montana said. The partnership not only provides validation of the company’s technology, but it will also give Amedis researchers access to Argenta’s datasets, which will help it refine its computational models even further, according to Montana. In addition, he said, “there are a number of other features in the collaboration that haven’t been announced that are beneficial to the company.”

Of Amedis’ 24 employees, six are dedicated to developing the AI platform, which the company is extending into new areas. For example, while ADMET prediction focuses on the enzymes and proteins that are involved in the degradation of molecules, “the same principles can also be applied to efficacy,” Montana noted. “So if the target protein was an enzyme or receptor that was involved in a particular disease, then you could generate predictive models for the interactions of small molecules with that particular protein.”

Amedis is applying this approach to generate what it calls “therapeutic switches” — essentially new uses for existing drugs. By generating predictive models for clinically proven mechanisms of action, the company hopes to identify known drugs that would be active against particular targets. Montana estimated that the company would have initial therapeutic switches ready for clinical trials in the first half of this year.

Amedis was founded in 1999 and has raised £6 million (US$9.7 million) in financing so far. The company is in the process of raising Series B financing. In addition to the AI technology, Amedis has developed a silicon-based medicinal chemistry platform.

— BT

Filed under

The Scan

Genome Sequences Reveal Range Mutations in Induced Pluripotent Stem Cells

Researchers in Nature Genetics detect somatic mutation variation across iPSCs generated from blood or skin fibroblast cell sources, along with selection for BCOR gene mutations.

Researchers Reprogram Plant Roots With Synthetic Genetic Circuit Strategy

Root gene expression was altered with the help of genetic circuits built around a series of synthetic transcriptional regulators in the Nicotiana benthamiana plant in a Science paper.

Infectious Disease Tracking Study Compares Genome Sequencing Approaches

Researchers in BMC Genomics see advantages for capture-based Illumina sequencing and amplicon-based sequencing on the Nanopore instrument, depending on the situation or samples available.

LINE-1 Linked to Premature Aging Conditions

Researchers report in Science Translational Medicine that the accumulation of LINE-1 RNA contributes to premature aging conditions and that symptoms can be improved by targeting them.