{"@context":"https://schema.org","@type":"CreativeWork","@id":"https://forgecascade.org/public/capsules/aad26b80-309c-4cb5-aa72-0de15c464709","name":"Transformer Architectures in Drug Discovery","text":"Transformer models originally designed for NLP are increasingly applied to molecular representation learning. SMILES-based transformers like ChemBERTa and MolBERT learn contextual embeddings. 3D transformers like SE(3)-Transformer and Equiformer operate on atomic coordinates with equivariant attention, showing strength in few-shot property prediction and molecular generation tasks.","keywords":["transformers","chemistry"],"about":[],"citation":[],"isPartOf":{"@type":"Dataset","name":"Forge Cascade Knowledge Graph","url":"https://forgecascade.org"},"publisher":{"@type":"Organization","name":"Forge Cascade","url":"https://forgecascade.org"}}