Abstract:Background
Several QSAR methodology developments have shown promise in recent years. These include the consensus approach to generate the final prediction of a model, utilizing new, advanced machine learning algorithms and streamlining, standardization and automation of various QSAR steps. One approach that seems under-explored is at-the-runtime generation of local models specific to individual compounds. This approach was quite likely limited by the computational requirements, but with current in… Show more
“…Algorithm aiQSAR methodology described by Vukovic et al [34] was applied for development of regression and classification models. This method is based on the-runtime derivation of local models specific to each compound (in this section referred to as the target compound).…”
Section: Methodsmentioning
confidence: 99%
“…Figure 1 summarizes the entire aiQSAR workflow.Fig. 1Workflow for aiQSAR-based model development(Adapted from [34])…”
The median lethal dose for rodent oral acute toxicity (LD50) is a standard piece of information required to categorize chemicals in terms of the potential hazard posed to human health after acute exposure. The exclusive use of in vivo testing is limited by the time and costs required for performing experiments and by the need to sacrifice a number of animals. (Quantitative) structure–activity relationships [(Q)SAR] proved a valid alternative to reduce and assist in vivo assays for assessing acute toxicological hazard. In the framework of a new international collaborative project, the NTP Interagency Center for the Evaluation of Alternative Toxicological Methods and the U.S. Environmental Protection Agency’s National Center for Computational Toxicology compiled a large database of rat acute oral LD50 data, with the aim of supporting the development of new computational models for predicting five regulatory relevant acute toxicity endpoints. In this article, a series of regression and classification computational models were developed by employing different statistical and knowledge-based methodologies. External validation was performed to demonstrate the real-life predictability of models. Integrated modeling was then applied to improve performance of single models. Statistical results confirmed the relevance of developed models in regulatory frameworks, and confirmed the effectiveness of integrated modeling. The best integrated strategies reached RMSEs lower than 0.50 and the best classification models reached balanced accuracies over 0.70 for multi-class and over 0.80 for binary endpoints. Computed predictions will be hosted on the EPA’s Chemistry Dashboard and made freely available to the scientific community.
“…Algorithm aiQSAR methodology described by Vukovic et al [34] was applied for development of regression and classification models. This method is based on the-runtime derivation of local models specific to each compound (in this section referred to as the target compound).…”
Section: Methodsmentioning
confidence: 99%
“…Figure 1 summarizes the entire aiQSAR workflow.Fig. 1Workflow for aiQSAR-based model development(Adapted from [34])…”
The median lethal dose for rodent oral acute toxicity (LD50) is a standard piece of information required to categorize chemicals in terms of the potential hazard posed to human health after acute exposure. The exclusive use of in vivo testing is limited by the time and costs required for performing experiments and by the need to sacrifice a number of animals. (Quantitative) structure–activity relationships [(Q)SAR] proved a valid alternative to reduce and assist in vivo assays for assessing acute toxicological hazard. In the framework of a new international collaborative project, the NTP Interagency Center for the Evaluation of Alternative Toxicological Methods and the U.S. Environmental Protection Agency’s National Center for Computational Toxicology compiled a large database of rat acute oral LD50 data, with the aim of supporting the development of new computational models for predicting five regulatory relevant acute toxicity endpoints. In this article, a series of regression and classification computational models were developed by employing different statistical and knowledge-based methodologies. External validation was performed to demonstrate the real-life predictability of models. Integrated modeling was then applied to improve performance of single models. Statistical results confirmed the relevance of developed models in regulatory frameworks, and confirmed the effectiveness of integrated modeling. The best integrated strategies reached RMSEs lower than 0.50 and the best classification models reached balanced accuracies over 0.70 for multi-class and over 0.80 for binary endpoints. Computed predictions will be hosted on the EPA’s Chemistry Dashboard and made freely available to the scientific community.
“…aiQSAR is a general system used to generate in silico models, both classification and regression models, 32 which was developed by Kristijan Vukovic (Istituto Mario Negri, Milano, Italy). A total of 38 models have already been developed and implemented.…”
Section: Tools For Research In Vegahubmentioning
confidence: 99%
“…SARpy works better on a data set of at least a few hundred substances, but it has also been used on smaller data sets. 31 aiQSAR aiQSAR is a general system used to generate in silico models, both classification and regression models, 32 which was developed by Kristijan Vukovic (Istituto Mario Negri, Milano, Italy). A total of 38 models have already been developed and implemented.…”
VEGAHUB ( www.vegahub.eu ) is a repository of freely available, downloadable tools based on computational toxicology methodologies. The main software tool available in VEGAHUB is VEGA QSAR software encoding more than 90 quantitative structure–activity relationship (QSAR) models for tens of endpoints for human toxicology, ecotoxicology, environmental, physico-chemical and toxicokinetic properties. However, beyond VEGA QSAR, VEGAHUB offers several other tools. Here, we present these resources, the possibilities to fully exploit them and the ways in which to integrate results provided by different VEGAHUB tools. Read-across and weight-of-evidence represent a major advantage of VEGAHUB. Integration between hazard and exposure is provided within innovative tools, which are specific for well-defined scenarios, such as those for cosmetic products. Prioritisation can be achieved by integrating results from 48 models. Finally, we highlight how some tools may not only fit predefined endpoints but also could be applied to general problems and research applications in the QSAR field. A couple of examples are provided, in which a critical assessment of the predictions and the documentation associated with the prediction are considered, in order to properly assess the quality of the results. These results may be associated with different levels of uncertainty or even be conflicting.
“…SN-Mordred only predicted seven compounds to be in EPA class I, demonstrating considerable caution with respect to the most toxic EPA class. To underpin the results and decisions returned using AI, future efforts could include the development of deep learning or QSAR models using molecular descriptors strongly correlated with acute toxicity 49 or by building local QSAR models from closely similar structures 54 . Such efforts would provide a physical and mechanical basis grounded in molecular structure for interpreting toxicity estimates from AI.…”
In
this article, we present our recent study on computational methodology for
predicting the toxicity of PFAS known as “forever chemicals” based on chemical
structures through evaluation of multiple machine learning methods. To address
the scarcity of PFAS toxicity data, a deep “transfer learning” method has been
investigated by leveraging toxicity information over the entire organic
chemical domain and an uncertainty-informed workflow by incorporating SelectiveNet
architecture, which can support future guidance of high throughput screening
with knowledge of chemical structures, has been developed.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
