Engineering topics

Li, Xingyu

Publications and source records attributed to Li, Xingyu.

2 records

DOE OSTI2023

Linker Vacancy Engineering of a Robust ftw–type Zr–MOF for Hexane Isomers Separation

Discrimination of physically similar molecules by porous solids represents an important yet challenging task in industrially relevant chemical separations. Precisely controlled pore dimension and/or tailored pore surface functionality are crucial to achieve high-efficiency separation. Metal-organic frameworks (MOFs) are promising candidates for these challenging separations in light of their structural diversity as well as highly adjustable pore dimension/functionality. We report here a microporous, ftw-type Zr-based MOF structure, HIAM-410 (HIAM=Hoffmann Institute of Advanced Materials), built on hexanuclear Zr 6 cluster and pyrene-1,3,6,8-tetracarboxylate (ptc 4– ). Its crystallographic structure has been determined using continuous rotation electron diffraction (cRED) technique combined with Rietveld refinement against powder X-ray diffraction data, aided by low-dose high-resolution transmission electron microscopy (HRTEM) imaging. The compound features exceptional framework stability that is comparable to the prototype MOF UiO-66. Interestingly, the linker vacancies in the pristine MOF structure could be partially restored by post-synthetic linker insertion. Its separation capability of hexane isomers is enhanced substantially upon the linker vacancy engineering. As a result, the restored structure exhibits efficient splitting of monobranched and dibranched hexane isomers at both room temperature and industrially relevant temperature.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

DOE OSTI2023

Multimodal representation learning for predicting molecule–disease relations

Motivation: Predicting molecule–disease indications and side effects is important for drug development and pharmacovigilance. Comprehensively mining molecule–molecule, molecule–disease and disease–disease semantic dependencies can potentially improve prediction performance. Methods: We introduce a Multi-Modal REpresentation Mapping Approach to Predicting molecular-disease relations (M2REMAP) by incorporating clinical semantics learned from electronic health records (EHR) of 12.6 million patients. Specifically, M2REMAP first learns a multimodal molecule representation that synthesizes chemical property and clinical semantic information by mapping molecule chemicals via a deep neural network onto the clinical semantic embedding space shared by drugs, diseases and other common clinical concepts. To infer molecule–disease relations, M2REMAP combines multimodal molecule representation and disease semantic embedding to jointly infer indications and side effects. Results: We extensively evaluate M2REMAP on molecule indications, side effects and interactions. Results show that incorporating EHR embeddings improves performance significantly, for example, attaining an improvement over the baseline models by 23.6% in PRC-AUC on indications and 23.9% on side effects. Further, M2REMAP overcomes the limitation of existing methods and effectively predicts drugs for novel diseases and emerging pathogens. Availability and implementation: The code is available at https://github.com/celehs/M2REMAP, and prediction results are provided at https://shiny.parse-health.org/drugs-diseases-dev/.

59 BASIC BIOLOGICAL SCIENCES↗