Idiap and InflamAlps, together to accelerate antibiotic research
Accelerating the selection of potential sources of antibiotics using artificial intelligence is one of the objectives of the ABRoad project. It is led by a cross-sectoral partnership from Valais: the Monthey-based company InflamAlps, a specialist in pharmaceutical research and development, and the Martigny-based research institute Idiap, a world expert in artificial intelligence. Supported by the Ark Foundation, this innovative project aims to develop a digital platform enabling the selection of potential sources of antibiotics.
Supporting drug discovery, determination of bioequivalent substances and identification of new antibiotics are the objectives of the ABRoad project, which is the result of collaboration between the company InflamAlps, based at the BioArk Monthey technology site, and the renowned artificial intelligence research institute, Idiap, in Martigny.
The design of a natural language processing (NLP) software infrastructure to support biomedical data discovery on large scientific textual databases (articles and patents), as well as the development of a model allowing the comparison of chemical formulas in addition to the texts about them, is expected to start this fall.
The potential to reduce the costs of pharmaceutical research
The identification of potential sources of antibiotic substances, which can then be validated experimentally, requires the interpretation of scientific literature (articles and patents) on a large scale. A titanic task!
"How can we know that what we are looking for does not already exist?" says Vincent Mutel, CEO of InflamAlps. Thanks to recent advances in natural language processing (NLP), it is now possible to automate important parts of this selection process. "The stakes are very high. It's about avoiding unnecessary research and therefore accelerating the discovery of new antibiotics," explains Vincent Mutel.
A technology that can be used in other fields!
By using cutting-edge methods developed by Idiap in Natural Language Inference (NLI) the project aims to develop a textual interpretation platform to support biomedical discovery. “In the past few years, these methods have dramatically evolved to support the interpretation of textual evidence at scale. At ABRoad, we will demonstrate their value in augmenting the antibiotic discovery process.”continues André Freitas, Head of the Reasoning & Explainable AI Lab (ExplAIn Lab) at the Idiap Research Institute.
The software infrastructure developed for the ABRoad project is a real proof of concept of the application of contemporary NLP methods and will give a real strategic boost to biomedical companies in Valais, and beyond.
The project also reinforces the position of the canton of Valais as a national focal point in the area of Natural Language Processing.