There is increasing adoption of artificial intelligence in drug discovery.
However, existing works use machine learning to mainly utilize the chemical
structures of molecules yet 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. We present a multi-modal molecule structure-text model,
MoleculeSTM, by jointly learning molecule's chemical structures and textual
descriptions via a contrastive learning strategy. To train MoleculeSTM, we
construct the largest multi-modal dataset to date, namely PubChemSTM, with over
280K chemical structure-text pairs. To demonstrate the effectiveness and
utility of MoleculeSTM, we design two challenging zero-shot tasks based on text
instructions, including structure-text retrieval and molecule editing.
MoleculeSTM possesses two main properties: open vocabulary and compositionality
via natural language. In experiments, MoleculeSTM obtains the state-of-the-art
generalization ability to novel biochemical concepts across various benchmarks.

该研究介绍了一种新的多模态分子结构 - 文本模型 MoleculeSTM，它结合学习化学结构和文本描述，以有效利用化学领域中丰富的文本知识，同时提高药物设计的效率和创新能力，并在多个基准测试中获得了最先进的泛化能力。