Sign In

Tristan Cazenave

Professeur chez Université Paris Dauphine

Tristan Cazenave is a Professor at Université Paris Dauphine in Paris, France.1 He has a strong academic background, having received his education from Université Pierre et Marie Curie (Paris VI).1

As a professor, Tristan Cazenave is actively involved in research and academic activities:

Research Interests

Tristan Cazenave's research interests appear to be diverse, focusing on areas such as:

  • Artificial Intelligence: He has given keynote speeches on topics like "Bootstrapping Artificial Intelligence" at conferences such as the Advances in Computer Games conference.36
  • Drug Discovery: He has been involved in research on atom-based generation of drug-like compounds using AI models.2
  • Neural Architecture Search: He has worked on applying Monte Carlo Tree Search to Neural Architecture Search.5

Academic Contributions

Tristan Cazenave regularly participates in academic conferences and publishes research papers:

  • He presented a paper on Neural Architecture Search with Monte Carlo Tree Search at the Radar 2024 conference.5
  • He gave a keynote speech titled "Bootstrapping Artificial Intelligence" at the 2023 Advances in Computer Games conference.36

Collaborative Work

Tristan Cazenave appears to collaborate with other researchers on various projects:

  • He was involved in the development of BrAIcht, a theatrical agent that speaks like Bertolt Brecht's characters, working alongside Roland Baz, Kristina Malyseva, and Anna Pappa.4

Through his work and research, Tristan Cazenave contributes to advancing knowledge in artificial intelligence, particularly in areas related to game theory, drug discovery, and neural architecture search.

Highlights

Sep 9 · linkedin

DrugSynthMC: An Atom-Based Generation of Drug-like Molecules with Monte Carlo Search Milo Roucairol, Alexios Georgiou, Tristan Cazenave, Filippo Prischi, Olivier Pardo https://lnkd.in/e-nnFY5U Our paper on the generation of drug-like molecules has been published in the Journal of Chemical Information and Modeling. Abstract A growing number of deep learning (DL) methodologies have recently been developed to design novel compounds and expand the chemical space within virtual libraries. Most of these neural network approaches design molecules to specifically bind a target based on its structural information and/or knowledge of previously identified binders. Fewer attempts have been made to develop approaches for de novo design of virtual libraries, as synthesizability of generated molecules remains a challenge. In this work, we developed a new Monte Carlo Search (MCS) algorithm, DrugSynthMC (Drug Synthesis using Monte Carlo), in conjunction with DL and statistical-based priors to generate thousands of interpretable chemical structures and novel drug-like molecules per second. DrugSynthMC produces drug-like compounds using an atom-based search model that builds molecules as SMILES, character by character. Designed molecules follow Lipinski’s “rule of 5″, show a high proportion of highly water-soluble nontoxic predicted-to-be synthesizable compounds, and efficiently expand the chemical space within the libraries, without reliance on training data sets, synthesizability metrics, or enforcing during SMILES generation. Our approach can function with or without an underlying neural network and is thus easily explainable and versatile. This ease in drug-like molecule generation allows for future integration of score functions aimed at different target- or job-oriented goals. Thus, DrugSynthMC is expected to enable the functional assessment of large compound libraries covering an extensive novel chemical space, overcoming the limitations of existing drug collections. The software is available at https://lnkd.in/eFWX2KVc.

Aug 24 · linkedin

11 gold medals at the 2024 Computer Olympiad!

Quentin Cohen-Solal and I entered 15 games at the 2024 Computer Olympiad, and we won 11 gold medals. This makes a total of 48 gold medals since our first Computer Olympiad with Athénan in 2020. A record difficult to beat :).

Related Questions

What are Tristan Cazenave's main research interests?
What courses does Tristan Cazenave teach at Université Paris Dauphine?
Has Tristan Cazenave published any notable papers recently?
What is Tristan Cazenave's background in cybersecurity?
How did Tristan Cazenave transition from MITRE to Université Paris Dauphine?
Tristan Cazenave
Tristan Cazenave, photo 1
Tristan Cazenave, photo 2
Add to my network

Location

Greater Paris Metropolitan Region