Bridging Text and Crystal Structures: Literature-driven Contrastive Learning for Materials Science

TL;DR

This paper introduces CLaSP, a contrastive learning framework that creates crossmodal embeddings between crystal structures and texts, enabling intuitive materials retrieval and analysis based on property-related descriptions.

Contribution

CLaSP is the first to align crystal structure embeddings with textual descriptions, facilitating property-based material exploration using large-scale literature data.

Findings

Effective text-based crystal structure screening demonstrated

Embedding space visualization reveals meaningful structure-property relationships

Leverages over 400,000 structures and publication records for training

Abstract

Understanding structure-property relationships is an essential yet challenging aspect of materials discovery and development. To facilitate this process, recent studies in materials informatics have sought latent embedding spaces of crystal structures to capture their similarities based on properties and functionalities. However, abstract feature-based embedding spaces are human-unfriendly and prevent intuitive and efficient exploration of the vast materials space. Here we introduce Contrastive Language--Structure Pre-training (CLaSP), a learning paradigm for constructing crossmodal embedding spaces between crystal structures and texts. CLaSP aims to achieve material embeddings that 1) capture property- and functionality-related similarities between crystal structures and 2) allow intuitive retrieval of materials via user-provided description texts as queries. To compensate for the lack of sufficient datasets linking crystal structures with textual descriptions, CLaSP leverages a dataset of over 400,000 published crystal structures and corresponding publication records, including paper titles and abstracts, for training. We demonstrate the effectiveness of CLaSP through text-based crystal structure screening and embedding space visualization.