M3-20M is a new multi-modal molecular dataset with over 20 million molecules, and the paper reports improved molecule generation and property prediction with it.
Extracting structured data from organic synthesis procedures using a fine-tuned large language model
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
q-bio.QM 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
M$^{3}$-20M: A Large-Scale Multi-Modal Molecule Dataset for AI-driven Drug Design and Discovery
M3-20M is a new multi-modal molecular dataset with over 20 million molecules, and the paper reports improved molecule generation and property prediction with it.