Dataset Information

High-throughput screening of chemicals as functional substitutes using structure-based classification models.

ABSTRACT: Identifying chemicals that provide a specific function within a product, yet have minimal impact on the human body or environment, is the goal of most formulation chemists and engineers practicing green chemistry. We present a methodology to identify potential chemical functional substitutes from large libraries of chemicals using machine learning based models. We collect and analyze publicly available information on the function of chemicals in consumer products or industrial processes to identify a suite of harmonized function categories suitable for modeling. We use structural and physicochemical descriptors for these chemicals to build 41 quantitative structure-use relationship (QSUR) models for harmonized function categories using random forest classification. We apply these models to screen a library of nearly 6400 chemicals with available structure information for potential functional substitutes. Using our Functional Use database (FUse), we could identify uses for 3121 chemicals; 4412 predicted functional uses had a probability of 80% or greater. We demonstrate the potential application of the models to high-throughput (HT) screening for "candidate alternatives" by merging the valid functional substitute classifications with hazard metrics developed from HT screening assays for bioactivity. A descriptor set could be obtained for 6356 Tox21 chemicals that have undergone a battery of HT in vitro bioactivity screening assays. By applying QSURs, we were able to identify over 1600 candidate chemical alternatives. These QSURs can be rapidly applied to thousands of additional chemicals to generate HT functional use information for combination with complementary HT toxicity information for screening for greener chemical alternatives.

SUBMITTER: Phillips KA

PROVIDER: S-EPMC6260937 | biostudies-literature | 2017

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

High-throughput screening of chemicals as functional substitutes using structure-based classification models.

Phillips Katherine A KA Wambaugh John F JF Grulke Christopher M CM Dionisio Kathie L KL Isaacs Kristin K KK

Green chemistry : an international journal and green chemistry resource : GC 20170101 4

Identifying chemicals that provide a specific function within a product, yet have minimal impact on the human body or environment, is the goal of most formulation chemists and engineers practicing green chemistry. We present a methodology to identify potential chemical functional substitutes from large libraries of chemicals using machine learning based models. We collect and analyze publicly available information on the function of chemicals in consumer products or industrial processes to ident ...[more]

PMID: 30505234

Similar Datasets

Project description:The ubiquitous presence of more than 80,000 chemicals in thousands of consumer products used on a daily basis stresses the need for screening a broader set of chemicals than the traditional well-studied suspect chemicals. This high-throughput screening combines stochastic chemical-product usage with mass balance-based exposure models and toxicity data to prioritize risks associated with household products. We first characterize product usage using the stochastic SHEDS-HT model and chemical content in common household products from the CPDat database, the chemical amounts applied daily varying over more than six orders of magnitude, from mg to kg. We then estimate multi-pathways near- and far-field exposures for 5,500 chemical-product combinations, applying an extended USEtox model to calculate product intake fractions ranging from 0.001 to ∼1, and exposure doses varying over more than nine orders of magnitude. Combining exposure doses with chemical-specific dose-responses and reference doses shows that risks can be substantial for multiple home maintenance products, such as paints or paint strippers, for some home-applied pesticides, leave-on personal care products, and cleaning products. Sixty percent of the chemical-product combinations have hazard quotients exceeding 1, and 9% of the combinations have lifetime cancer risks exceeding 10-4 . Population-level impacts of household products ingredients can be substantial, representing 5 to 100 minutes of healthy life lost per day, with users' exposures up to 103 minutes per day. To address this issue, present mass balance-based models are already able to provide exposure estimates for both users and populations. This screening study shows large variations of up to 10 orders of magnitude in impact across both chemicals and product combinations, demonstrating that prioritization based on hazard only is not acceptable, since it would neglect orders of magnitude variations in both product usage and exposure that need to be quantified. To address this, the USEtox suite of mass balance-based models is already able to provide exposure estimates for thousands of product-chemical combinations for both users and populations. The present study calls for more scrutiny of most impacting chemical-product combinations, fully ensuring from a regulatory perspective consumer product safety for high-end users and using protective measures for users.

Dataset Information

High-throughput screening of chemicals as functional substitutes using structure-based classification models.

Publications

High-throughput screening of chemicals as functional substitutes using structure-based classification models.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets