Precomputed Embeddings for Spectraverse

Read full text Summarise with VIRAT
Authors: Paul Krzakala
Cited by: 0

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Precomputed embeddings for the Spectraverse dataset. Data is split in train/test set such that no molecules in the test as the same formulae than a molecule in the train test. Spectra are encoded with DreAMS Molecules are encoded with ChemBERTa (Derify/ChemBERTa_augmented_pubchem_13m)

Fields of Study & Subjects

Computational Drug Discovery Methods Machine Learning in Materials Science Spectroscopy and Chemometric Analyses

Publication details

Journal / source
Zenodo (CERN European Organization for Nuclear Research)
Publication date
1 January 2026
Language
EN
Document type
Dataset