Technological innovation in the pharmaceutical sector is undergoing an unprecedented acceleration. At the heart of this transformation, Generative Artificial Intelligence (Generative AI) and supercomputing are progressively redefining research paradigms, enabling increasingly predictive, personalized and efficient approaches to drug development. 

Andrea Beccari, Head of Discovery Platform and Vice President at Exscalate, addressed this topic at the conference 

“Generative AI in Life Sciences: Navigating Wisely in a Changing World”

, organized by AboutPharma. In his remarks, Beccari highlighted the central role of AI in reshaping modern medicine, offering a clear and insightful overview of both the challenges and the opportunities now emerging for pharmaceutical research. 

“Generative AI represents the promise of a new evolutionary phase for medicine and pharmacology,” Beccari noted. “Thanks to supercomputing and new algorithms, we can finally tackle the complexity of biological systems in a more systematic and predictive manner.” 

Exscalate: A Pioneering Platform for Drug Discovery

Within this landscape, Dompé’s Exscalate platform stands out as one of Europe’s most advanced initiatives. Created to accelerate the drug-discovery phase, Exscalate leverages supercomputing and AI models to rapidly analyze the world’s largest structured molecular library, identifying promising candidates for preclinical and clinical development. 

By adopting Generative AI early in the preclinical arena, Exscalate has been able to evolve its algorithms at pace. Its technologies now cover strategic domains including: 

One of the most revolutionary aspects of this approach is the shift in how scientific data are conceived and managed. As Beccari explained, it is no longer merely a matter of collecting experimental data; the challenge now is to actively generate data—real or synthetic—that can effectively train AI models. 

The use of synthetic data—computer-generated information with characteristics like real datasets—helps overcome ethical constraints and dataset bias, enabling, for example, the creation of synthetic cohorts or digital twins to enhance the statistical robustness of clinical studies. 

At the same time, the move towards graph-based databases (knowledge graphs) has made it possible to analyze not only isolated data points but also the relationships between them, improving our understanding of pathological mechanisms and therapeutic responses. 

The European Context: Data and Infrastructure as Strategic Levers

Despite these promising developments, Beccari stressed that fully harnessing AI in medicine requires accessible data and advanced technological infrastructure. Although the European Union mandated data sharing as early as 2004, it is only since 2016 that a real framework for making such data usable has begun to take shape. 

Countries such as the United States and the United Kingdom are already frontrunners in this field. To ensure Europe does not fall behind, it is essential to foster an ecosystem that capitalizes on existing information assets and strengthens the global competitiveness of European scientific research. 

https://www.youtube.com/watch?v=orHpluIU0Sg&t=1s

Andrea Beccari, Head of Discovery Platform and Vice President at Exscalate, addressed this topic at the conference “Generative AI in Life Sciences: Navigating Wisely in a Changing World”, organized by AboutPharma. 

Generative Artificial Intelligence and Supercomputing: The New Frontier of Pharmaceutical Research 

Finding new medicines often begins with a simple but critical question: where can a drug attach to a protein? The answer lies in identifying “binding pockets”, tiny regions on proteins where molecules can interact and trigger therapeutic effects. Traditionally, this search has been slow and complex, especially when experimental data is missing. 

GENEOnet is changing the game. Developed by a team of scientists and engineers, led by Dompé, GENEOnet is an innovative artificial intelligence tool designed to scan proteins and pinpoint these strategic pockets quickly and reliably. By combining advanced machine learning with scientific expertise, GENEOnet offers a new way to support drug discovery-making the process faster, more accurate, and more accessible. 

Unlike traditional methods, GENEOnet analyzes the 3D structure of proteins using a streamlined, explainable approach. It highlights the most promising pockets for drug binding, even when only limited data is available. The system is user-friendly and requires fewer parameters, which means lower costs and faster results. Scientists can now prioritize where to focus their efforts, reducing false positives and accelerating the development of new treatments. 

Recent studies show that GENEOnet outperforms standard tools in identifying the correct binding pockets. It adapts well to different protein types and is already available online for the global scientific community. This technology has the potential to speed up virtual screening, improve the accuracy of drug design, and make advanced research tools available to more people worldwide. 

GENEOnet demonstrates that “less can be more”: with fewer parameters and more built-in knowledge, it delivers better results. Discover more and try the free web service at 

. For further details, read the full paper published from 

https://www.nature.com/articles/s41598-025-18132-5

Accelerating Drug Discovery with Smart, Accessible Technology 

Discover the story of Akash, from Assam to Naples.

GENEOnet: Artificial Intelligence Unveils the Key to Protein Binding Sites 

In partnership with Harvard Medical School spin-off, Aramis Biosciences, Exscalate was used to rapidly identify a lead compound for the previous unmet need of an effective treatment for Dry Eye Disease. The project progressed from zero to Phase II investigational new drug approval in just 14 months.

Dry Eye Disease, also referred to as dysfunctional tear syndrome, is a source of huge frustration for patients, often effecting their quality of live. Despite approximately 20 million people in the US being diagnosed with it (344 million people worldwide), according to the American 

, it remains misdiagnosed and under treated. Less than five per cent of patients are currently undergoing treatment for Dry Eye Disease with a Food and Drug Administration-approved product. This is likely due to the products’ questionable efficacy and tolerability limitations.

Following more than a decade of research at The Schepens Eye Research Institute of Mass Eye and Ear and Department of Ophthalmology at Harvard Medical School where the role of a certain subset of pro-inflammatory T helper cells were found to be central to the immunopathogenesis of dry eye disease, Aramis Biosciences was founded in 2018 to address this treatment gap in dry eye disease. As a spin-off from Harvard Medical School, Aramis set up as a clinical-stage immuno-ophthalmology biopharmaceutical company. It brought together a team of accomplished pharmaceutical executives and leading experts in the fields of corneal disorders, ocular inflammation and immunology, who are all committed to the development of disease-modifying therapy for ocular surface disease, which encompasses dry eye disease.

Following its research, Aramis patented an in-vivo model for IL-17R target in the dry eye indication. The task now was to identify potential lead candidates. Following a partnership agreement with Exscalate, the Exscalate platform was leveraged to accelerate Aramis’ drug discovery process. 

In the first six months, with the use of its Virtual Library and the power of super computing, Exscalate was able to design and define an in-silico library of peptides. This peptide chemical space was fine-tuned in preparation for primary screening.

From here the workflow consisted of peptides synthesis and definition of a physical library. This resulted in a definition of a pool of peptides for secondary screening.

Following secondary screening and optimization, the most promising lead candidate was identified. In-vivo testing of this lead candidate, A197, was performed by Aramis, which proved to have a high potency compared with anti-IL-17. This drug discovery process took just 14 months. 

From here, the financial and operational resource partnership with Exscalate, enabled Aramis to complete all IND-enabling preclinical studies, Chemistry, Manufacturing, and Controls (CMC) development as well as providing Phase II clinical supply of A197. In a licensing agreement with Exscalate, Aramis secures the global ophthalmic rights to this novel, first-in-class, propriety molecule

Following the successful completion of Series A financing, Aramis is continuing to work with its partners, including Exscalate, to advance the company’s pipeline, especially its lead product candidate, A197. The hope is that this promising investigational therapy will improve the lives of dry eye patients worldwide.

Finding a cure for dry eye disease

Aramis success story

, an acronym for EXaSCale smArt pLatform Against paThogEns. It is one of the most powerful intelligent

globally, capable of analyzing over 3 million molecules per second and exploiting a

of over 500 billion compounds of pharmacological interest.

was born in 2004 during a meeting on supercomputing applications to unexplored areas at the

. And it's not a coincidence that Cineca is the home of

, Europe's most powerful supercomputer for research and the ninth of the Top500 worldwide.

That meeting was the beginning of a new era: Dompé decided to invest in a platform for identifying new pharmacological molecules to be exploited before starting clinical trials on patients. "The aim was not to exploit an existing technology, but to develop a new one, from scratch," says

, Head of Discovery Platforms Dompé: "Our innovation was the use of a supercomputer with unprecedented computing power."

The company started collaborative research through simulations in a virtually infinite chemical space, including many types of evaluation such as toxicity analyses and possible side effects, working with Italian and European supercomputing centers. In this way, the entire drug discovery chain has been shortened, focusing on safer molecules with a better risk profile.

Over more than 15 years, the power of the hardware and software of supercomputers has increased to the so-called exascale (indicating a force capable of performing more than 18 million billion operations per second) through the optimization of networks and information flows, eliminating anything that slows down work times.

In December 2019, the Covid-19 pandemic hit Europe, and the

was born. Coordinated by Dompé, it aims to harness the supercomputing resources of all EU countries and some of the continent's best life sciences research laboratories to fight pandemics more quickly and efficiently than before.

"A system like EXSCALATE had the benefit not to be a commercial product nor a line of academic research. It is not calibrated to obtain scientific publications but to give concrete and valuable answers - explains Beccari - With Covid-19, the platform has shown that it can quickly identify molecules that have the potential to reach the clinical phase, which has already been tested".

The speed and chemical space increase thanks to the use of quantum computers with capabilities beyond even exascale level and the introduction of cutting-edge technologies such as neuron chips. Now more complex simulations with even hundreds of molecular targets in parallel are being prepared, increasing the possibilities to find effective molecules and minimizing the risks of side effects.

"We brought molecule to clinical phase in 10 months from scratch thanks to the EXSCALATE platform, and that repays all the effort of these years. It is the dream of those who work in pharmacology and have the ambition to bring health solutions", Beccari underlines. "The reason why we work every day is precisely to provide new treatments for patients more quickly."

Now the drug discovery can count on a new digital ally, EXSCALATE, an acronym for EXaSCale smArt pLatform Against paThogEns. It is one of the most powerful intelligent supercomputing platforms globally, capable of analyzing over 3 million molecules per second and exploiting a chemical library of over 500 billion compounds of pharmacological interest.

Supercomputers at the service of drug discovery: this is how Exscalate was born

Computational chemists have long desired to correlate protein-ligand complex structures with their binding affinity, especially for designing drugs to combat devastating diseases. Accurately predicting on a computer the behavior of molecules has proven challenging but huge progress is being made especially with new computing power and the development of stronger AI capabilities.. Springer's recently published 

Exscalate4CoV: High-Performance Computing for COVID Drug Discovery 

 opens a window on what can be, and has been done with these new tools right in the middle of the worst pandemic living humans have seen. The book would have not been possible without the support, encouragement, and feedback of so many team members, authors, and collaborators of the 

(coordinated by Dompé farmaceutici) and 

projects who worked to complete their tasks.

Edited by Silvano Colletti and Gabriella Bernardi, the book aims, for the first time, to gather available evidence on researches and use cases of artificial intelligence techniques and HPC resources aiming to accelerate the drug discovery and development process.  It aims to indicate avenues for future research and policy actions that could impact precision medicine. Eminent international experts have been invited to contribute to this work, thus representing the state of the art in this field.

As the recognition and consideration of AI in drug development is increasing in significance and applications at all levels, the need has arisen for a reference text that can be used across disciplines to guide research and practice based on a precision medicine paradigm. This book is meant for drug hunters, AI and HPC experts, students, policymakers, academic researchers, and other stakeholders to encourage and promote a precision medicine approach in basic research and clinical practice, as well as novel policy actions. 

A big thank you goes out to the contributing authors for their enthusiasm in joining the project and their dedication to the chapters. 

Last but not least, a special thanks to the Nobel Laureate Dr. Arieh Warshel from University of Southern California and Dr. Thomas Skordas, deputy director-general  of Directorate-General for Communications Networks, Content and Technology from the European Commission, for their input which uniquely values and frames the importance of the work done by the science and technology teams.

Springer's recently published Exscalate4CoV: High-Performance Computing for COVID Drug Discovery  opens a window on what can be, and has been done with these new tools right in the middle of the worst pandemic living humans have seen.

Exscalate4Cov is now a book on High-Performance Computing for COVID Drug Discovery

As part of a strategic R&D collaboration with pioneering biopharma start-up Engitix, the Exscalate platform is being leveraged to identify new treatments for diseases that represent a huge unmet clinical need, including fibrosis and liver-associated solid tumors

Both cancer and fibrosis are leading causes of death around the world. As cancer progresses it causes solid tumors, which are largely untreatable. Fibrosis similarly has no approved drugs to treat it. A pathological feature of many diseases occurring as a result of inflammation or damage, fibrosis eventually leads to organ failure. In the case of Primary Sclerosing Cholangitis (PSC), a persistent and progressive fibrotic disease of the liver, the only effective therapy to date is a liver transplant.

Engitix, a spin out of University College London, was founded in 2016 to address this unmet clinical need. This biopharmaceutical start-up aims to pioneer new, advanced therapeutics to help significantly improve the lives of fibrosis and solid tumor patients and their families. 

Through its cutting-edge research at the Institute for Liver and Digestive Health, Division of Medicine, University College London (UCL), Engitix’ founders discovered that a key limitation in developing effective treatments in fibrosis and various solid cancers has been the failure to include human extracellular matrix (ECM) in experimental models. It’s a reason why the majority of compounds fail in late stage clinical trials. 

Essentially, the ECM is the bioactive scaffold that provides structural and biochemical support to cells within human tissues and organs. It also regulates crucial biochemical and biomechanical processes. However, being a dynamic structure the ECM is constantly being remodeled. Genetic mutations can result from this remodeling, which affects the phenotype of the associated cells and as such leads to fibrosis and cancer. Engitix discovered that the proteins that make up and regulate the remodeling of the ECM represent promising therapeutic targets.

As a result of this discovery, Engitix developed a human ECM-based platform for drug target identification and validation. The hope is that through the use of this platform, in which healthy and diseased cells can be tested with potential therapeutic agents within their natural physiological and pathological microenvironment, will help reduce late-stage clinical failures and accelerate drug discovery.

In early 2022, Engitix announced a multi-year, multi-programme strategic collaboration with Exscalate, which includes equity investment. Engitix will not only have direct access to Exscalate’s facilities, resources and expertise but it will also be able to leverage the capabilities of the Exscalate ultra-high performance virtual screening platform. Combining the power of Exscalate with Engitix’s deep understanding of the biology of the fibrosis and solid tumors microenvironment and the unique strength of its ECM platform, will enable Engitix to further accelerate the clinical translation of its targets and drug discovery process.

Exscalate’s partnership with pioneering biopharma start-up Engitix has already resulted in a co-developed pipeline in fibrosis and cancer. Together the companies are accelerating the drug discovery process to help improve lives through pioneering new precision medicines for previously unmet needs. 

In 2022 Dompé farmaceutici announced a strategic collaboration with and investment in Engitix as part of Engitix s $54m series A financing.

Identifying new innovative treatments for fibrosis and cancer

Contact Us

header

Exscalate insights

With traditional drug discovery processes being slow, inefficient and costly, our AI-driven virtual screening platform brings speed and precision. 

Exscalate insights

New cures, faster

Our Success Stories