Arturo Fiorellini Bernardis
About Arturo Fiorellini Bernardis
Arturo Fiorellini Bernardis is a Research Engineer specializing in Bio AI at InstaDeep Ltd, where he focuses on applying deep learning techniques to drug discovery. He holds a Ph.D. in Engineering Physics from Delft University of Technology and has extensive experience in protein binding affinity assessment.
Work at InstaDeep
Arturo Fiorellini Bernardis currently serves as a Research Engineer in Bio AI at InstaDeep Ltd, a position he has held since 2023. His role focuses on the application of advanced artificial intelligence techniques in the field of biotechnology. Based in Paris, Île-de-France, he contributes to projects that enhance drug discovery processes through innovative methodologies.
Education and Expertise
Arturo Fiorellini Bernardis has a strong academic background in engineering and applied physics. He completed his Doctor of Philosophy (PhD) in Engineering Physics/Applied Physics at Delft University of Technology from 2017 to 2022. Prior to this, he earned a Master of Science (MSc) in Microelectronics from the same institution from 2015 to 2017. His undergraduate studies culminated in a Bachelor's degree in Biomedical Engineering from Politecnico di Milano from 2011 to 2014. Additionally, he obtained a Master of Science (MS) in Electrical and Electronics Engineering from Politecnico di Milano from 2014 to 2015.
Background
Before joining InstaDeep, Arturo Fiorellini Bernardis worked as a Ph.D. Researcher at TU Delft in the Tera-Hertz Sensing Group from 2017 to 2022. His research during this period focused on advanced sensing technologies and their applications. This experience provided him with a solid foundation in both theoretical and practical aspects of engineering, particularly in the context of emerging technologies.
Achievements in Drug Discovery
Arturo Fiorellini Bernardis specializes in the integration of deep learning techniques within drug discovery processes. He has developed large language model (LLM) scorers that are specifically designed to assess protein binding affinity. Furthermore, he utilizes equivariant graph neural networks (GNNs) to predict both protein binding affinity and stability, contributing to advancements in the field of bioinformatics.