Application of an Artificial Neural Network to the Prediction of OH Radical Reaction Rate Constants for Evaluating Global Warming Potential

Challenges for Kinetics Predictions via Neural Network Potentials: A Wilkinson's Catalyst Case

Ab initio kinetic studies are important to understand and design novel chemical reactions. While the Artificial Force Induced Reaction (AFIR) method provides a convenient and efficient framework for kinetic studies, accurate explorations of reaction path networks incur high computational costs. In this article, we are investigating the applicability of Neural Network Potentials (NNP) to accelerate such studies. For this purpose, we are reporting a novel theoretical study of ethylene hydrogenation with a transition metal complex inspired by Wilkinson's catalyst, using the AFIR method. The resulting reaction path network was analyzed by the Generative Topographic Mapping method. The network's geometries were then used to train a state-of-the-art NNP model, to replace expensive ab initio calculations with fast NNP predictions during the search. This procedure was applied to run the first NNP-powered reaction path network exploration using the AFIR method. We discovered that such explorations are particularly challenging for general purpose NNP models, and we identified the underlying limitations. In addition, we are proposing to overcome these challenges by complementing NNP models with fast semiempirical predictions. The proposed solution offers a generally applicable framework, laying the foundations to further accelerate ab initio kinetic studies with Machine Learning Force Fields, and ultimately explore larger systems that are currently inaccessible.

Improved Machine Learning Models by Data Processing for Predicting Life-Cycle Environmental Impacts of Chemicals

Machine learning (ML) provides an efficient manner for rapid prediction of the life-cycle environmental impacts of chemicals, but challenges remain due to low prediction accuracy and poor interpretability of the models. To address these issues, we focused on data processing by using a mutual information-permutation importance (MI-PI) feature selection method to filter out irrelevant molecular descriptors from the input data, which improved the model interpretability by preserving the physicochemical meanings of original molecular descriptors without generation of new variables. We also applied a weighted Euclidean distance method to mine the data most relevant to the predicted targets by quantifying the contribution of each feature, thereby the prediction accuracy was improved. On the basis of above data processing, we developed artificial neural network (ANN) models for predicting the life-cycle environmental impacts of chemicals with R² values of 0.81, 0.81, 0.84, 0.75, 0.73, and 0.86 for global warming, human health, metal depletion, freshwater ecotoxicity, particulate matter formation, and terrestrial acidification, respectively. The ML models were interpreted using the Shapley additive explanation method by quantifying the contribution of each input molecular descriptor to environmental impact categories. This work suggests that the combination of feature selection by MI-PI and source data selection based on weighted Euclidean distance has a promising potential to improve the accuracy and interpretability of the models for predicting the life-cycle environmental impacts of chemicals.

Transfer Learning Approach to Multitarget Temperature-Dependent Reaction Rate Prediction

Accurate prediction of temperature-dependent reaction rate constants of organic compounds is of great importance to both atmospheric chemistry and combustion science. Extensive work has been done on developing automated mechanism generation systems but the lack of quality reaction rate data remains a huge bottleneck in the application of highly detailed mechanisms. Machine learning prediction models have been recently adopted to alleviate the data gap in thermochemistry and have great potential to do the same for kinetic data with the recent release of quality reaction rate data compilations. The ultimate goal is to formulate easily accessible, general-purpose, temperature-dependent, and multitarget models for the prediction of reaction rates. To that end, we propose a model that depends on the well-known Morgan fingerprints as well as learned representations transferred from the QM9 data set. We propose the use of an Arrhenius-based loss where predictions of the three modified-Arrhenius parameters (A, n, and B = E_a/R) are given instead of the direct prediction of reaction rate constants. Our model is >35% more accurate compared to a baseline model of feed forward network (FFN) on Morgan fingerprints.

Accelerating the pace of ecotoxicological assessment using artificial intelligence

Species Sensitivity Distribution (SSD) is a key metric for understanding the potential ecotoxicological impacts of chemicals. However, SSDs have been developed to estimate for only handful of chemicals due to the scarcity of experimental toxicity data. Here we present a novel approach to expand the chemical coverage of SSDs using Artificial Neural Network (ANN). We collected over 2000 experimental toxicity data in Lethal Concentration 50 (LC50) for 8 aquatic species and trained an ANN model for each of the 8 aquatic species based on molecular structure. The R2 values of resulting ANN models range from 0.54 to 0.75 (median R2 = 0.69). We applied the predicted LC50 values to fit SSD curves using bootstrapping method, generating SSDs for 8424 chemicals in the ToX21 database. The dataset is expected to serve as a screening-level reference SSD database for understanding potential ecotoxicological impacts of chemicals.

Deep Learning of Activation Energies

Quantitative predictions of reaction properties, such as activation energy, have been limited due to a lack of available training data. Such predictions would be useful for computer-assisted reaction mechanism generation and organic synthesis planning. We develop a template-free deep learning model to predict the activation energy given reactant and product graphs and train the model on a new, diverse data set of gas-phase quantum chemistry reactions. We demonstrate that our model achieves accurate predictions and agrees with an intuitive understanding of chemical reactivity. With the continued generation of quantitative chemical reaction data and the development of methods that leverage such data, we expect many more methods for reactivity prediction to become available in the near future.

Prediction of the Ultraviolet-Visible Absorption Spectra of Polycyclic Aromatic Hydrocarbons (Dibenzo and Naphtho) Derivatives of Fluoranthene

The annellation theory method has been used to predict the locations of maximum absorbance (LMA) of the ultraviolet-visible (UV-Vis) spectral bands in the group of polycyclic aromatic hydrocarbons (PAHs) C₂₄H₁₄ (dibenzo and naphtho) derivatives of fluoranthene (DBNFl). In this group of 21 PAHs, ten PAHs present a sextet migration pattern with four or more benzenoid rings that is potentially related to a high molecular reactivity and high mutagenic conduct. This is the first time that the locations of maximum absorbance in the UV-Vis spectra of naphth[1,2- a]aceanthrylene, dibenz[ a,l]aceanthrylene, indeno[1,2,3- de]naphthacene, naphtho[1,2- j]fluoranthene, naphth[2,1- e]acephenanthrylene, naphth[2,1- a]aceanthrylene, dibenz[ a,j]aceanthrylene, naphth[1,2- e]acephenanthrylene, and naphtho[2,1- j]fluoranthene have been predicted. Also, this represents the first report about the application of the annellation theory for the calculation of the locations of maximum absorbance in the UV-Vis spectra of PAHs with five-membered rings. Furthermore, this study constitutes the premier investigation beyond the pure benzenoid classical approach toward the establishment of a generalized annellation theory that will encompass not only homocyclic benzenoid and non-benzenoid PAHs, but also heterocyclic compounds.