TY - JOUR
T1 - Mapping the Porous and Chemical Structure-Function Relationships of Trace CH3I Capture by Metal-Organic Frameworks using Machine Learning
AU - Wu, Xiaoyu
AU - Che, Yu
AU - Chen, Linjiang
AU - Amigues, Eric
AU - Wang, Ruiyao
AU - He, Jinghui
AU - Dong, Huilong
AU - Ding, Lifeng
N1 - Funding Information:
The authors acknowledge financial support from the Xi’an Jiaotong-Liverpool University Research Development Fund (RDF-16-02-03, RDF-15-01-23, and PGRS2112001) and the key program special fund (KSF-E-03). The authors also acknowledge the use of computational resources at the Guangdong Tianhe and Shenzhen Cloud Computing Center.
Publisher Copyright:
© 2022 American Chemical Society.
PY - 2022/10/19
Y1 - 2022/10/19
N2 - Large-scale computational screening has become an indispensable tool for functional materials discovery. It, however, remains a challenge to adequately interrogate the large amount of data generated by a screening study. Here, we computationally screened 1087 metal−organic frameworks (MOFs), from the CoRE MOF 2014 database, for capturing trace amounts (300 ppmv) of methyl iodide (CH3I); as a primary representative of organic iodides, CH3129I is one of the most difficult radioactive contaminants to separate. Furthermore, we demonstrate a simple and general approach for mapping and interrogating the high-dimensional structure−function data obtained by high-throughput screening; this involves learning two-dimensional embeddings of the high-dimensional data by applying unsupervised learning to encoded structural and chemical features of MOFs. The resulting various porous and chemical structure−function maps are human-interpretable, revealing not only top-performing MOFs but also complex structure−function correlations that are hidden when inspecting individual MOF features. These maps also alleviate the need of laborious visual inspection of a large number of MOFs by clustering similar MOFs, per the encoding features, into defined regions on the map. We also show that these structure−function maps are amenable to supervised classification of the performances of MOFs for trace CH3I capture. We further show that the machine-learning models trained on the 1087 CoRE MOFs can be used to predict an unseen set of 250 MOFs randomly selected from a different MOF database, achieving high prediction accuracies.
AB - Large-scale computational screening has become an indispensable tool for functional materials discovery. It, however, remains a challenge to adequately interrogate the large amount of data generated by a screening study. Here, we computationally screened 1087 metal−organic frameworks (MOFs), from the CoRE MOF 2014 database, for capturing trace amounts (300 ppmv) of methyl iodide (CH3I); as a primary representative of organic iodides, CH3129I is one of the most difficult radioactive contaminants to separate. Furthermore, we demonstrate a simple and general approach for mapping and interrogating the high-dimensional structure−function data obtained by high-throughput screening; this involves learning two-dimensional embeddings of the high-dimensional data by applying unsupervised learning to encoded structural and chemical features of MOFs. The resulting various porous and chemical structure−function maps are human-interpretable, revealing not only top-performing MOFs but also complex structure−function correlations that are hidden when inspecting individual MOF features. These maps also alleviate the need of laborious visual inspection of a large number of MOFs by clustering similar MOFs, per the encoding features, into defined regions on the map. We also show that these structure−function maps are amenable to supervised classification of the performances of MOFs for trace CH3I capture. We further show that the machine-learning models trained on the 1087 CoRE MOFs can be used to predict an unseen set of 250 MOFs randomly selected from a different MOF database, achieving high prediction accuracies.
KW - GCMC simulation
KW - computational materials screening
KW - data visualization
KW - machine learning
KW - metal−organic frameworks
KW - methyl iodide capture
UR - http://www.scopus.com/inward/record.url?scp=85140416456&partnerID=8YFLogxK
U2 - 10.1021/acsami.2c10861
DO - 10.1021/acsami.2c10861
M3 - Article
C2 - 36197758
AN - SCOPUS:85140416456
SN - 1944-8244
VL - 14
SP - 47209
EP - 47221
JO - ACS applied materials & interfaces
JF - ACS applied materials & interfaces
IS - 41
ER -