2020 Artificial Intelligence Awards

www.wealthandfinance-news.com 4 Wealth & Finance International - 2020 Artificial Intelligence Awards APR2w2 Science and Innovation lie at the core of PEACCEL. Everything they do, all the work they undertake, is under the premise of making something thoroughly different from the rest of the crowd. Under the leadership of the CEO Laurent Contaut and the 2 Co-founders, Prof Cadet and Prof Offmann, PEACCEL has quickly grown into a name that has international repute not only for the products it produces, but the quality of its scientific output. The team’s success is built around the 5 Ps, namely Platform, Paper, Patents, Products and People. The aforementioned Platform is Innov’SAR, which includes 3 impressive and technologically advanced modules. These are innov’SAR core, designed for the optimization of polypeptides (peptides, proteins, enzymes, antibodies, VHHs) and metabolic or signaling pathways, RAS module, for evaluating combination of Drugs (FDCs) in various diseases and automlSAR. automlSAR tests in parallel >130 algorithms, is agnostic with respect to the data set and can be combined with innov’SAR core & RAS module for maximum benefit. The platform is built on an extraordinary amount of research. Professors Cadet and Offmann are The importance of Life Sciences has been highlighted and accelerated by the COVID-19 pandemic, with companies forced to explore new and exciting ways of working that embrace the potential of the latest technology. Nowhere is this more obvious than with the team from PEACCEL. Their mission is to bridge AI and Life Sciences in order to open new horizons. We take a look at this astonishing firm to see how their work is taking us into a brave new world. Best Drug Development AI Partner 2020 &Most Innovative Clinical Data Science Platform: innov’SAR prodigious in their peer-reviewed output, with over 130 combined publications between them. Their work at PEACCEL has already brought about astonishing rewards, with 15 papers in peer reviewed journals in less than 2 years. This incredible success is matched by the team’s efforts to file patents. The approach is one which rewards patenting early and patenting across a broad range of activities. 3 have already been filed, with many more on the way. Of course, while Science and Innovation lead the way, it’s people who make sure that PEACCEL can progress towards new discoveries. The brightest and best from high tech fields are brought together to allow the fastest growth possible. The team’s specialism is in the optimization and engineering of peptides and proteins through the use of Artificial Intelligence. Their unique and innovative Sequence-Activity Relationship methodology, innov’SAR core, identifies high fitness mutants from smart mutant libraries and relies on physico-chemical properties of the amino acids, digital signal processing and regression techniques. This allows the team to tackle multi-parameters and predict multiple types of innovation in Life Sciences. With a revolutionary approach guiding many of the decisions made at PEACCEL, it’s little wonder that their unique technological platform is what allows the team and their partners to stand apart from the rest of the crowd. When considering the various modules that are available for use, it’s worth starting with the first one, innov’SAR core. It allows the prediction of parameters that are current bottlenecks in the industry such as aggregation, stereoselectivity and resistance to organic solvents to name but a few. This impressive display allows the team to predict up to 1 billion protein variants in one-shot and one round. To sum up the basic characteristic of the procedure, only an initial dataset containing the primary PEACCEL Dec20054 sequences of enzyme variants and the respective biological properties is required. It is different from other Machine Learning (ML) approaches due to the following characteristics. Firstly, thanks to the Fast Fourier Transform (FFT), the non-linear aspects inside the protein sequence are captured. Secondly, FFT allows to introduce new mutations at positions not previously explored or new positions of mutations. Thirdly, a single round, as in this case, allows the identification of high performing mutants, while avoiding the need for excessively large datasets customary in other ML or Deep Learning (DL) approaches. There is no need for alignment- based amino acid descriptors, no need for protein sequences of equal length. It also removes the need for large computational resources, with long computational times no longer a necessary factor in proceedings. Applying an FFT to a protein sequence digitally encoded is not the same as simply encoding it in another way, indeed this mathematical treatment makes it possible to take into account the order of the protein sequence and all the interactions between positions within it, and thus to better identify epistatic phenomena. The innov’SAR core approach is interpolative, extrapolative and predicts outside-the-box, not found in other state-of-the-art ML or DL approaches. Of course, the biggest challenge is to meet the needs of clients. The partners that the team works with operate in the biotechnology, pharmaceutical and chemical space. The firm is held in high enough regard to have taken on work for the FDA in the USA. Their specialized work allows them to play a major role in the development of new and exciting solutions for the marketplace. Time, costs, quality and associated risks are the main drivers in this industry to develop therapeutic drugs. In Research & Development, the main goals are to demonstrate the safety and efficacy Everything they do, all the work they undertake, is under the premise of making something thoroughly different from the rest of the crowd.