MARVEL researchers feature heavily in CHIMIA issue on artificial intelligence

This was published on January 14, 2020

Papers from NCCR MARVEL members Clemence Corminboeuf, Michele Ceriotti, Anatole von Lilienfeld and Teodoro Laino made up nearly half of the scientific articles included in CHIMIA's recent publication focused on Artificial Intelligence in Swiss Chemical Research.

Carey Sargent, EPFL, NCCR MARVEL

Accounting for four of the ten scientific articles it featured, CHIMIA, the journal of the Swiss Chemical Society, relied heavily on material from NCCR MARVEL researchers for its recent special edition on Artificial Intelligence in Swiss Chemical Research. 

Professor Clemence Corminboeuf, along with colleagues including doctoral student Alberto Fabrizio and post-doc Benjamin Meyer, also MARVEL members, contributed an article entitled Quantum Chemistry Meets Machine Learning. In it, they show how statistical learning approaches can be leveraged across a range of different quantum chemical areas to transform the scaling, nature, and complexity of the problems they face. 


Clémence Corminboeuf
Clémence Corminboeuf
Group leader
EPFL, Lausanne

Professor Michele Ceriotti and doctoral student Félix Musil contributed the article Machine Learning at the Atomic Scale, a review in which they discuss recent progress in the field, focusing in particular on the problem of representing an atomic configuration in a mathematically robust and computationally efficient way.  


Michele Ceriotti
Michele Ceriotti
Project leader
EPFL, Lausanne

Professor Anatole von Lilienfeld and a colleague contributed with Operator Quantum Machine Learning: Navigating the Chemical Space of Response Properties, a paper that explains, reviews and discusses the recently introduced operator formalism, which substantially improves the data efficiency for quantum machine learning models of common response properties.


Anatole von Lilienfeld
Anatole von Lilienfeld
Project leader
UniBas, Basel

Finally, Teodoro Laino contributed with colleagues a paper entitled Data-driven Chemical Reaction Prediction and Retrosynthesis. In it, they review different approaches to predicting forward reactions and retrosynthesis, with a strong focus on data-driven ones.


Teodoro Laino
Teodoro Laino
Project leader
IBM, Rüschlikon


CHIMIA is published 10 times a year and is listed in the most important databases: Current Contents/Physical, Chemical and Earth Sciences, Chemical Abstracts, Science Citation Index, Research Alert, Scisearch, Index Chemicus, Chemistry Citation Index, Current Chemical Reactions, Reaction Citation Index, and Biological Abstracts.

Stay in touch with the MARVEL project

Low-volume newsletters, targeted to the scientific and industrial communities.

Subscribe to our newsletter