A Large-Scale Nanocrystal Database with Aligned Synthesis and Properties, Enabling Generative Inverse Design

TY - JOUR

T1 - A Large-Scale Nanocrystal Database with Aligned Synthesis and Properties, Enabling Generative Inverse Design

AU - Gu, Kai

AU - Liang, Yingping

AU - Peng, Senliang

AU - Guo, Aotian

AU - Fu, Ying

AU - Zhong, Haizheng

N1 - Publisher Copyright: © 2026 American Chemical Society

PY - 2026/6/23

Y1 - 2026/6/23

N2 - Nanocrystal synthesis has been highly dependent on trial and error due to the complex correlation between synthesis parameters and physicochemical properties. Although deep learning offers a potential methodology to achieve generative inverse design, it is still hindered by the scarcity of high-quality data sets that align nanocrystal synthesis routes with their properties. In this work, we developed NanoExtractor, a large language model (LLM) with well-designed data augmentation strategies to extract structured synthesis routes and corresponding properties from unstructured literature. NanoExtractor achieves a weighted average score of 92% on the test set, significantly outperforming other chemistry-specialized (9%) and general-purpose LLMs (57%). With this model, we constructed a large-scale nanocrystal synthesis-property (NSP) database containing nearly 160 000 aligned entries. On the basis of this database, we further developed NanoDesigner, an LLM for generative inverse synthesis design, achieving an F1 score of 0.85. The applicability of NanoDesigner was experimentally validated across multiple nanocrystal systems, including MgF2, CsPbBr3, and PbS. Notably, NanoDesigner recommends a critical nonstoichiometric precursor concentration for synthesizing MgF2 nanocrystals, which was experimentally proven to be essential for suppressing byproduct formation. In all, our work bridges the gap between unstructured literature and data-driven synthesis, providing a human-AI collaborative paradigm for accelerating material discovery.

AB - Nanocrystal synthesis has been highly dependent on trial and error due to the complex correlation between synthesis parameters and physicochemical properties. Although deep learning offers a potential methodology to achieve generative inverse design, it is still hindered by the scarcity of high-quality data sets that align nanocrystal synthesis routes with their properties. In this work, we developed NanoExtractor, a large language model (LLM) with well-designed data augmentation strategies to extract structured synthesis routes and corresponding properties from unstructured literature. NanoExtractor achieves a weighted average score of 92% on the test set, significantly outperforming other chemistry-specialized (9%) and general-purpose LLMs (57%). With this model, we constructed a large-scale nanocrystal synthesis-property (NSP) database containing nearly 160 000 aligned entries. On the basis of this database, we further developed NanoDesigner, an LLM for generative inverse synthesis design, achieving an F1 score of 0.85. The applicability of NanoDesigner was experimentally validated across multiple nanocrystal systems, including MgF2, CsPbBr3, and PbS. Notably, NanoDesigner recommends a critical nonstoichiometric precursor concentration for synthesizing MgF2 nanocrystals, which was experimentally proven to be essential for suppressing byproduct formation. In all, our work bridges the gap between unstructured literature and data-driven synthesis, providing a human-AI collaborative paradigm for accelerating material discovery.

KW - inverse design

KW - large language model

KW - literature extraction

KW - nanocrystal synthesis

KW - quantum dots

UR - https://www.scopus.com/pages/publications/105042523019

U2 - 10.1021/acsnano.6c03070

DO - 10.1021/acsnano.6c03070

M3 - Article

AN - SCOPUS:105042523019

SN - 1936-0851

VL - 20

SP - 17413

EP - 17422

JO - ACS Nano

JF - ACS Nano

IS - 24

ER -