POCSTagger: Identifying part-of-chemical-speech with transformers
- Alessandra Toniato
- Philippe Schwaller
- et al.
- 2021
- ACS Fall 2021
Bio
Teo received the Master degree in theoretical chemistry in 2001 (University of Pisa and Scuola Normale Superiore di Pisa, Italy) and the doctorate in computational chemistry in 2006 (Scuola Normale Superiore di Pisa, Italy) defending a thesis on 'Multi-Grid QM/ MM Approaches in ab initio Molecular Dynamics' supervised by Prof. Dr. Michele Parrinello. From 2006 to 2008, Teo worked as a post-doctoral researcher in the research group of Prof. Dr. Jürg Hutter at the University of Zurich, contributing to the development of the CP2K simulation package. In 2008, Teo joined the IBM Research - Zurich Laboratory (ZRL) as Research Scientist. He is currently Distinguished Research Scientist and manager.
His research interests focus on developing machine learning/artificial intelligence technologies to digitalize chemistry and materials science, with IBM RXN for chemistry being an example of a recent community success. In 2022, the team received the Sandmeyer Award of the Swiss Chemical Society for the important contributions to the field of digital chemistry.
Publications
Inferring experimental procedures from text-based representations of chemical reactions
- Alain C. Vaucher
- Philippe Schwaller
- et al.
- 2021
- Nature Communications
Extraction of organic chemistry grammar from unsupervised learning of chemical reactions
- Philippe Schwaller
- Benjamin Hoover
- et al.
- 2021
- Science Advances
Transformer-based neural networks capture organic chemistry grammar from unsupervised learning of chemical reactions
- Philippe Schwaller
- Benjamin Hoover
- et al.
- 2021
- ACS Spring 2021
Learning from literature-extracted synthesis actions for organic synthesis
- Alain Vaucher
- Philippe Schwaller
- et al.
- 2021
- ACS Spring 2021
Prediction of chemical reaction yields using deep learning
- Philippe Schwaller
- Alain C. Vaucher
- et al.
- 2021
- Machine Learning: Science and Tech.
Unassisted noise reduction of chemical reaction datasets
- Alessandra Toniato
- Philippe Schwaller
- et al.
- 2021
- Nature Machine Intelligence
Data-driven molecular design for discovery and synthesis of novel ligands: A case study on SARS-CoV-2
- Jannis Born
- Matteo Manica
- et al.
- 2021
- Machine Learning: Science and Tech.
Mapping the space of chemical reactions using attention-based neural networks
- Philippe Schwaller
- Daniel Probst
- et al.
- 2021
- Nature Machine Intelligence
Neural machine translation for conditional generation of novel procedures
- Joppe Geluykens
- Sandra Mitrovic
- et al.
- 2021
- HICSS 2021
Patents
- US
- 11854670
- US
- 11133528
- US
- 11121409
- US
- 11016965
- US
- 10559847
- US
- 10170790
- US
- 9971736
Projects
AI for Scientific Discovery
Creating the AI-enabled lab for a new era of reproducible and collaborative experimentation
Lab that Learns
Leveraging AI foundation models and multi-cloud computing to usher in a new era of reproducible and collaborative experimentation for scientific discovery.
Blog posts
Thieme trains IBM RXN for Chemistry with high-quality data
NewsAlain Vaucher, Fiona Shortt de Hernandez, Sascha Hausberg, and Teodoro Laino6 minute readIBM RXN for Chemistry: Unveiling the grammar of the organic chemistry language
ResearchPhilippe Schwaller, Hendrik Strobelt, Teodoro Laino, and Benjamin Hoover7 minute readIBM RXN for Chemistry: Automatically cleaning chemical reaction datasets
ResearchAlessandra Toniato and Teodoro Laino7 minute readIBM RXN: New AI model boosts mapping of chemical reactions
ResearchPhilippe Schwaller and Teodoro Laino5 minute read- See more blog posts
Top collaborators
MM
Matteo Manica
Senior Research Scientist
FZ
Federico Zipoli
Research Scientist
MA
MG
Mara Graziani
Research Scientist