(4pd) Accelerating Discovery of Framework Materials By Integrating Synthetic and Data-Driven Methods

The societal challenges of climate change, clean energy, and health necessitate innovative solutions such as framework materials tailored to specific applications. However, currently, there is a gap between the framework materials we require and our ability to realize them, as the vast number of molecular building blocks makes trial-and-error activities—with limited design and predictive analysis—laborious and time-consuming. Therefore, smart solutions that bypass extensive synthesis screening and the limits of chemical intuition are crucial for linking molecular building units to achieve on-demand framework materials.

My research group will couple new synthetic methods with data-driven tools to discover and engineer framework materials for sustainability and human health. This includes metal-organic frameworks (MOFs), covalent organic frameworks (COFs), zeolitic imidazolate frameworks (ZIFs), and others. In particular, my research group seeks to address the challenges of discovering framework materials through:

(1) Developing new design principles and crystallization methods for programmable multivariate framework materials (e.g., COFs and MOFs containing multiple different ligands and/or metals) that are unattainable through traditional synthesis approaches for on-demand chemical separations.

(2) Discovering porous framework materials with bio-inspired motifs for catalysis and drug delivery using active learning approaches with automated platforms to reduce experimental burdens.

(3) Leveraging deep learning models to accurately predict both framework crystal structures based on synthesis conditions and host-guest interactions, such as preferential adsorption and catalytic activities, under various experimental conditions.

Research Experience:

My research spans synthetic chemistry, materials science, chemical engineering, and data science, combining both experimental and computational methods. Initially trained as an inorganic chemist during my doctoral research with Prof. Omar Yaghi, I designed and synthesized new metal-organic frameworks to address climate change, specifically, atmospheric water harvesting and CO₂ capture. I successfully developed a robust kilogram-scale green synthesis method for aluminum MOFs [1-3] and tested their water-harvesting devices in the field (Death Valley National Park, CA) to extract water from extremely arid air [4].

Later in my doctoral study, I became interested in leveraging digital tools for experimental discovery. From an experimentalist’s perspective, I integrated large language model (LLM) agents with machine learning (ML) tools to automate literature data extraction [5], molecular structure editing [6], image recognition [7], synthesis planning [8, 9], and reaction optimization [9]. This work was foundational for this rapidly growing field and proved efficient in accelerating the discovery of molecules and frameworks.

To broaden my training in integrating experimental and computational approaches, as a postdoctoral scholar with Prof. Klavs Jensen, I focused on discovering new electrochemical organic reactions through high-throughput experimentation and data-driven approaches. By combining the data mined from literature and my experiments, I trained machine learning models to predict reaction outcome and site selectivity for C-H oxidation under electrochemical conditions, as well as developed an ML-driven workflow for synthesis optimization. In addition, I explored the role of LLMs in interfacing with ML and chemical experiments to deepen our understanding of electrochemical synthesis and accelerate the discovery of new reactions.

Teaching Interests:

Chemical Engineering Core Courses: Separation Processes, Kinetics and Reactor Design, Thermodynamics

Chemical Engineering Electives: Crystallization Science, Data-Driven Chemical Engineering, Material Discovery and Manufacturing, Deep Learning and Generative Models

Besides research pursuits, I have a strong interest in teaching and mentoring students. I believe my interdisciplinary background brings unique perspectives invaluable to students' education and training. Throughout my journey, I have taught 5 undergraduate-level courses and mentored 4 students (3 graduate students and 1 undergraduate researcher) from diverse backgrounds, including chemistry, chemical engineering, and materials science. In addition, I contributed to the design and development of a new chemistry laboratory course focused on synthesizing water-harvesting MOFs to address water shortages. This course led to co-authoring a publication in the Journal of Chemical Education in 2023, discussing how the cutting-edge nature of these materials and related research fuels student motivation and spurs broader conversations about ongoing scientific advancements [10]. Consequently, I have realized that an efficient way to teach is to integrate examples relevant to the challenges in chemical science that scientists and engineers are currently addressing. Incorporating recent examples—such as water harvesting, large language models, robotic platforms, and automation—maximizes student learning. This experience has solidified my desire to educate students through teaching and leading a group of scientific colleagues.

References

[1] Z. Zheng, H. L. Nguyen, N. Hanikel, K.-K. Li, Z. Zhou, T. Ma, O. M. Yaghi. “High-yield, green and scalable methods for producing MOF-303 for water harvesting from desert air.” Nat. Protoc., 18, 136–156 (2023).

[2] Z. Zheng, N. Hanikel, H. Lyu, O. M. Yaghi. “Broadly tunable atmospheric water harvesting in multivariate metal–organic frameworks.” J. Am. Chem. Soc., 144, 22669-22675 (2022).

[3] Z. Zheng, A. H. Alawadhi, O. M. Yaghi. “Green synthesis and scale-up of MOFs for water harvesting from air.” Mol. Front. J., 7, 1-20 (2023).

[4] W. Song, Z. Zheng, A. H. Alawadhi, O. M. Yaghi. “MOF water harvester produces water from Death Valley desert air in ambient sunlight”. Nat. Water, 1, 626–634 (2023).

[5] Z. Zheng, O. Zhang, C. Borgs, J. T. Chayes, O. M. Yaghi. “ChatGPT Chemistry Assistant for text mining and prediction of MOF synthesis.” J. Am. Chem. Soc., 145, 18048–18062 (2023).

[6] Z. Zheng, A. H. Alawadhi, S. Chheda, S. E. Neumann, N. Rampal, S. Liu, H. L. Nguyen, Y.-H. Lin, Z. Rong, J. I. Siepmann, L. Gagliardi, A. Anandkumar, C. Borgs, J. T. Chayes, O. M. Yaghi. “Shaping the water harvesting behavior of metal-organic frameworks aided by fine-tuned GPT models.” J. Am. Chem. Soc., 145, 28284-28295 (2023).

[7] Z. Zheng, Z. He, S. Chheda, O. Khattab, N. Rampal, M. A. Zaharia, C. Borgs, J. T. Chayes, O. M. Yaghi. “Image and data mining in reticular chemistry powered by GPT-4V.” Digital Discovery, 3, 491-501 (2024).

[8] Z. Zheng, Z. Rong, N. Rampal, C. Borgs, J. T. Chayes, O. M. Yaghi. “A GPT-4 reticular chemist for MOF discovery.” Angew. Chem. Int. Ed., 62, e202311983 (2023).

[9] Z. Zheng, O. Zhang, H. L. Nguyen, N. Rampal, A. H. Alawadhi, Z. Rong, T. Head-Gordon, C. Borgs, J. T. Chayes, O. M. Yaghi. “ChatGPT Research Group for optimizing the crystallinity of MOFs and COFs.” ACS Cent. Sci., 9, 2161–2170 (2023).

[10] S. Neumann, K. Neumann, Z. Zheng, N. Hanikel, J. Tsao, O. M. Yaghi. “Harvesting water in the classroom.” J. Chem. Educ., 100, 4482–4487 (2023).