Loïc Kwate Dassi
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Loïc Kwate Dassi has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Daniel Probst
Bioinformatics Group University & Research Wageningen The Netherlands
2 shared publications - Yves Gaetan Nana Teukam
IBM Research - Zurich
2 shared publications Matteo Manica
1 shared publication- Matteo Manica
IBM Research Europe, Rüschlikon, Switzerland
1 shared publication Philippe Schwaller
1 shared publication- Philippe Schwaller
École Polytechnique Fédérale de Lausanne
1 shared publication
Latest Publications
- Open Access
- 1 February 2023
- Published by American Chemical Society (ACS) in ChemRxiv
Language models can identify enzymatic active sites in protein sequences
Recent advances in language modeling have tremendously impacted how we handle sequential data in science. Language architectures have emerged as a hotbed of innovation and creativity in natural language processing over the last decade, and have since gained prominence in modeling proteins and chemical processes, elucidating structural relationships from textual/sequential data. Surprisingly, some of these relationships refer to three-dimensional structural features, raising important questions on the dimensionality of the information contained in sequential data. We demonstrate that the unsupervised use of a language model architecture to a language representation of bio-catalyzed chemical reactions can capture the signal at the base of the substrate-active site atomic interactions, identifying the three- dimensional active site position in unknown protein sequences. The language representation comprises a reaction-simplified molecular-input line-entry system (SMILES) for substrate and products, and amino acid sequence information for the enzyme. This approach can recover, with no supervision, 52.12% of the active site when considering co-crystallized substrate-enzyme structures as ground truth, vastly outperforming other attention-based models.
- 1 February 2023
- Published by American Chemical Society (ACS) in ChemRxiv
Open AccessLanguage models can identify enzymatic active sites in protein sequences
Recent advances in language modeling have tremendously impacted how we handle sequential data in science. Language architectures have emerged as a hotbed of innovation and creativity in natural language processing over the last decade, and have since gained prominence in modeling proteins and chemical processes, elucidating structural relationships from textual/sequential data. Surprisingly, some of these relationships refer to three-dimensional structural features, raising important questions on the dimensionality of the information contained in sequential data. We demonstrate that the unsupervised use of a language model architecture to a language representation of bio-catalyzed chemical reactions can capture the signal at the base of the substrate-active site atomic interactions, identifying the three- dimensional active site position in unknown protein sequences. The language representation comprises a reaction-simplified molecular-input line-entry system (SMILES) for substrate and products, and amino acid sequence information for the enzyme. This approach can recover, with no supervision, 52.12% of the active site when considering co-crystallized substrate-enzyme structures as ground truth, vastly outperforming other attention-based models.