Catalyst Energy Prediction with CatBERTa: Unveiling Feature Exploration Strategies through Large Language Models

Ock, Janghoon; Guntuboina, Chakradhar; Barati Farimani, Amir

doi:10.1021/acscatal.3c04956

Cited by 14 publications

(5 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Structures could also be physically modeled to predict their interactions with different substrates. In principle, an ML model could be trained to combine multimodal information such as spatial descriptors of protein structures with an LLM trained on information about chemical reactions. , This artificial intelligence (AI) model would act as protein structural biologist and organic chemist. By synthesizing these two forms of knowledge, the model could perform the laborious work of sifting through and identifying viable protein structures for desired reactivity (Figure C). , Finally, it is also possible to go beyond known protein sequences and expand the search for functional enzymes to microbial dark matter: metagenomic analysis has only scratched the surface of these genomes …”

Section: Discovery Of Functional Enzymes With Machine Learningmentioning

confidence: 99%

Opportunities and Challenges for Machine Learning-Assisted Enzyme Engineering

Yang,

Li,

Arnold

2024

ACS Cent. Sci.

View full text Add to dashboard Cite

Enzymes can be engineered at the level of their amino acid sequences to optimize key properties such as expression, stability, substrate range, and catalytic efficiencyor even to unlock new catalytic activities not found in nature. Because the search space of possible proteins is vast, enzyme engineering usually involves discovering an enzyme starting point that has some level of the desired activity followed by directed evolution to improve its “fitness” for a desired application. Recently, machine learning (ML) has emerged as a powerful tool to complement this empirical process. ML models can contribute to (1) starting point discovery by functional annotation of known protein sequences or generating novel protein sequences with desired functions and (2) navigating protein fitness landscapes for fitness optimization by learning mappings between protein sequences and their associated fitness values. In this Outlook, we explain how ML complements enzyme engineering and discuss its future potential to unlock improved engineering outcomes.

show abstract

Section: Discovery Of Functional Enzymes With Machine Learningmentioning

confidence: 99%

Opportunities and Challenges for Machine Learning-Assisted Enzyme Engineering

Yang,

Li,

Arnold

2024

ACS Cent. Sci.

View full text Add to dashboard Cite

show abstract

“…Moreover, a diverse range of machine learning techniques, such as graph neural networks, transformers, and multimodal models, are being increasingly utilized for modeling atomic systems. − For example, autoencoders have demonstrated success in translating the Brownian dynamics trajectories of a two-dimensional energy surface into a latent space representation . Additionally, supervised machine learning has been employed to pinpoint suitable collective variables for study .…”

Section: Introductionmentioning

confidence: 99%

GradNav: Accelerated Exploration of Potential Energy Surfaces with Gradient-Based Navigation

Ock,

Mollaei,

Barati Farimani

2024

J. Chem. Theory Comput.

Self Cite

View full text Add to dashboard Cite

Exploring the potential energy surface (PES) of molecular systems is important for comprehending their complex behaviors, particularly through the identification of various metastable states. However, the transition between these states is often hindered by substantial energy barriers, demanding prolonged molecular simulations that consume considerable computational resources. Our study introduces the gradient-based navigation (GradNav) algorithm, which accelerates the exploration of the energy surface and enables proper reconstruction of the PES. This algorithm employs a strategy of initiating short simulation runs from updated starting points derived from prior observations to effectively navigate across potential barriers and explore new regions. To evaluate GradNav’s performance, we introduce two metrics: the deepest well escape frame (DWEF) and the search success initialization ratio (SSIR). Through applications on Langevin dynamics within Müller-type PESs and molecular dynamics simulations of the Fs-peptide protein, these metrics demonstrate GradNav’s enhanced ability to escape deep energy wells and its reduced reliance on initial conditions, as denoted by the reduced DWEF values and increased SSIR values, respectively. Consequently, this improved exploration capability enables more precise energy estimations from simulation trajectories.

show abstract

“…The advancement of ML has driven revolutionary changes in many areas of scientific discovery. The most common scenarios of applying ML for science is to use discriminative ML models, which focus on distinguishing between different outcomes or classes, to predict the desired properties of a given input (e.g., the band gap of a crystal and the adsorption energy of a catalyst , ). ML models trained in a supervised manner can detect the nonlinear relationship between features of the input and the corresponding properties, leading to accurate and fast predictions.…”

mentioning

confidence: 99%

Machine Learning in Membrane Design: From Property Prediction to AI-Guided Optimization

Cao,

Barati Farimani,

Ock

et al. 2024

Nano Lett.

Self Cite

View full text Add to dashboard Cite

Porous membranes, either polymeric or two-dimensional materials, have been extensively studied because of their outstanding performance in many applications such as water filtration. Recently, inspired by the significant success of machine learning (ML) in many areas of scientific discovery, researchers have started to tackle the problem in the field of membrane design using data-driven ML tools. In this Mini Review, we summarize research efforts on three types of applications of machine learning in membrane design, including (1) membrane property prediction using ML, (2) gaining physical insight and drawing quantitative relationships between membrane properties and performance using explainable artificial intelligence, and (3) ML-guided design, optimization, or virtual screening of membranes. On top of the review of previous research, we discuss the challenges associated with applying ML for membrane design and potential future directions.

show abstract

Catalyst Energy Prediction with CatBERTa: Unveiling Feature Exploration Strategies through Large Language Models

Cited by 14 publications

References 47 publications

Opportunities and Challenges for Machine Learning-Assisted Enzyme Engineering

Opportunities and Challenges for Machine Learning-Assisted Enzyme Engineering

GradNav: Accelerated Exploration of Potential Energy Surfaces with Gradient-Based Navigation

Machine Learning in Membrane Design: From Property Prediction to AI-Guided Optimization

Contact Info

Product

Resources

About