In Silico Prediction of Physicochemical Properties of Environmental Chemicals Using Molecular Fingerprints and Machine Learning

Abstract

There are little available toxicity data on the vast majority of chemicals in commerce. High-throughput screening (HTS) studies, such as being carried out by the U.S. Environmental Protection Agency (EPA) ToxCast program in partnership with the federal Tox21 research program, can generate biological data to inform models for predicting potential toxicity. However, physicochemical properties are also needed to model environmental fate and transport, as well as exposure potential. The purpose of the present study was to generate an open-source Quantitative Structure-Property Relationship (QSPR) workflow to predict a variety of physicochemical properties that would have cross-platform compatibility to integrate into existing cheminformatics workflows. In this effort, decades-old experimental property data sets available within EPA EPI Suite™ were reanalyzed using modern cheminformatics workflows to build updated QSPR models capable of supplying computationally efficient, open, and transparent HTS property predictions in support of environmental modeling efforts. Models were built using updated EPI Suite data sets for the prediction of six physicochemical properties: octanol-water partition coefficient (log P), water solubility (log S), boiling point (BP), melting point (MP), vapor pressure (log VP) and bioconcentration factor (log BCF). The coefficient of determination (R2) between the estimated values and experimental data for the six predicted properties ranged from 0.826 (MP) to 0.965 (BP), with model performance for five of the six properties exceeding those from the original EPI Suite™ models. The newly derived models can be employed for rapid estimation of physicochemical properties within an open-source HTS workflow to inform fate and toxicity prediction models of environmental chemicals.

Modeling Physico-Chemical ADMET Endpoints with Multitask Graph Convolutional Networks

“…Machine learning approaches are typically used to map the structure of compounds to their properties, a method called quantitative structure-activity relationship (QSAR). Common algorithms include multiple linear regression, random forest or support vector machine in combination with circular fingerprints or molecular properties to describe the molecules [3][4][5][6][7]. Water solubility and melting point are two endpoints for which a lot of previous modeling was published [3][4][5][8][9][10][11][12][13].…”

Utilizing Machine Learning for Efficient Parameterization of Coarse Grained Molecular Force Fields

“…This level of error is consistent with other current state-of-the-art log P prediction methods, which generally come from Quantitative Structure Activity Relationships (QSAR). 61,62 On the left hand side of Figure 1, the initialization process is expounded, which provides initial training data for the optimizer upon which to initialize its Gaussian process. In this phase, force field parameters are selected at random from a sampling grid constructed by the optimizer based upon user input.…”

Predicting mammalian metabolism and toxicity of pesticides in silico

“…Their predictive accuracy varies with the chemistry involved, so the best way to assess their usefulness for a particular area of chemistry is to compare their predictions to the observed values for compounds one has recently encountered whose properties have been measured. Applicability domain information alone may not be adequate for herbicides, which are not well represented in many ADMET data sets . Moreover, training sets are likely to be biased towards either very well‐behaved commercial compounds or notorious ones like methyl viologen and dioxins, for example, instead of the kind of lead compounds likely to be encountered in agrochemical discovery and development.…”

“…Applicability domain information alone may not be adequate for herbicides, which are not well represented in many ADMET data sets. 49 Moreover, training sets are likely to be biased towards either very well-behaved commercial compounds or notorious ones like methyl viologen and dioxins, for example, instead of the kind of lead compounds likely to be encountered in agrochemical discovery and development.…”