Multi-modal Molecule Structure-text Model for Text-based Retrieval and Editing. (arXiv:2212.10789v3 [cs.LG] UPDATED)

There is increasing adoption of artificial intelligence in drug discovery.
However, existing studies use machine learning to mainly utilize the chemical
structures of molecules but ignore the vast textual knowledge available in
chemistry. Incorporating textual knowledge enables us to realize new drug
design objectives, adapt to text-based instructions and predict complex
biological activities. Here we present a multi-modal molecule structure-text
model, MoleculeSTM, by jointly learning molecules' chemical structures and
textual descriptions via a contrastive learning strategy. To train MoleculeSTM,
we …

adapt adoption artificial artificial intelligence arxiv chemistry cs.lg design discovery drug design drug discovery editing intelligence knowledge machine machine learning modal molecules multi-modal retrieval studies text textual vast