Homologous Pairs of Low and High Temperature Originating Proteins Spanning the Known Prokaryotic Universe.

Stability of proteins at high temperature has been a topic of interest for many years, as this attribute is favourable for applications ranging from therapeutics to industrial chemical manufacturing. Our current understanding and methods for designing high-temperature stability into target proteins are inadequate. To drive innovation in this space, we have curated a large dataset, learn2thermDB, of protein-temperature examples, totalling 24 million instances, and paired proteins across temperatures based on homology, yielding 69 million protein pairs - orders of magnitude larger than the current largest. This important step of pairing allows for study of high-temperature stability in a sequence-dependent manner in the big data era. The data pipeline is parameterized and open, allowing it to be tuned by downstream users. We further show that the data contains signal for deep learning. This data offers a new doorway towards thermal stability design models.

Low-cost prediction of molecular and transition state partition functions via machine learning.

We have generated an open-source dataset of over 30 000 organic chemistry gas phase partition functions. With this data, a machine learning deep neural network estimator was trained to predict partition functions of unknown organic chemistry gas phase transition states. This estimator only relies on reactant and product geometries and partition functions. A second machine learning deep neural network was trained to predict partition functions of chemical species from their geometry. Our models accurately predict the logarithm of test set partition functions with a maximum mean absolute error of 2.7%. Thus, this approach provides a means to reduce the cost of computing reaction rate constants ab initio. The models were also used to compute transition state theory reaction rate constant prefactors and the results were in quantitative agreement with the corresponding ab initio calculations with an accuracy of 98.3% on the log scale.

Progress towards machine learning reaction rate constants.

Quantum and classical reaction rate constant calculations come at the cost of exploring potential energy surfaces. Due to the "curse of dimensionality", their evaluation quickly becomes unfeasible as the system size grows. Machine learning algorithms can accelerate the calculation of reaction rate constants by predicting them using low cost input features. In this perspective, we briefly introduce supervised machine learning algorithms in the context of reaction rate constant prediction. We discuss existing and recently created kinetic datasets and input feature representations as well as the use and design of machine learning algorithms to predict reaction rate constants or quantities required for their computation. Amongst these, we first describe the use of machine learning to predict activation, reaction, solvation and dissociation energies. We then look at the use of machine learning to predict reactive force field parameters, reaction rate constants as well as to help accelerate the search for minimum energy paths. Lastly, we provide an outlook on areas which have yet to be explored so as to improve and evaluate the use of machine learning algorithms for chemical reaction rate constants.

Machine Learning Quantum Reaction Rate Constants.

The ab initio calculation of exact quantum reaction rate constants comes at a high cost due to the required dynamics of reactants on multidimensional potential energy surfaces. In turn, this impedes the rapid design of the kinetics for large sets of coupled reactions. In an effort to overcome this hurdle, a deep neural network (DNN) was trained to predict the logarithm of quantum reaction rate constants multiplied by their reactant partition function-rate products. The training dataset was generated in-house and contains ∼1.5 million quantum reaction rate constants for single, double, symmetric and asymmetric one-dimensional potentials computed over a broad range of reactant masses and temperatures. The DNN was able to predict the logarithm of the rate product with a relative error of 1.1%. Furthermore, when comparing the difference between the DNN prediction and classical transition state theory at temperatures below 300 K a relative percent error of 31% was found with respect to the exact difference. Systems beyond the test set were also studied, these included the H + H2 reaction, the diffusion of hydrogen on Ni(100), the Menshutkin reaction of pyridine with CH3Br in the gas phase, the reaction of formalcyanohydrin with HS- in water and the F + HCl reaction. For these reactions, the DNN predictions were accurate at high temperatures and in good agreement with the exact rates at lower temperatures. This work shows that one can take advantage of a DNN to gain insight on reactivity in the quantum regime.