Leveraging infrared spectroscopy for automated structure elucidation
Marvin Alberts, Teodoro Laino, Alain C. Vaucher · 2024
Read Leveraging infrared spectroscopy for automated structure elucidation by Marvin Alberts, Teodoro Laino, Alain C. Vaucher (2024) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-11569215.txt.
Description
Marvin Alberts, Teodoro Laino, and Alain Vaucher presented in 2024 a model that reads an infrared spectrum and predicts the structure of a molecule. Infrared tools are cheap and simple, but people can read only a few peaks in a spectrum. Most of the signal goes unused in daily work.
Their transformer model was first trained on more than six hundred thousand simulated spectra, then tuned on a few thousand real ones. For mid-size compounds, its top guess was right in over four cases in ten, and the right answer sat in the top ten far more often. For the core frame of a molecule, results were much higher.
Catalog record
| CREATOR | Marvin Alberts, Teodoro Laino, Alain C. Vaucher |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 50 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |