際際滷shows by User: captaindare / http://www.slideshare.net/images/logo.gif 際際滷shows by User: captaindare / Fri, 27 Aug 2021 21:18:49 GMT 際際滷Share feed for 際際滷shows by User: captaindare OPERA, AN OPEN SOURCE AND OPEN DATA SUITE OF QSAR MODELS /slideshow/opera-an-open-source-and-open-data-suite-of-qsar-models/250066358 1004mansouri-210827211850
OPERA is a free and open source/open data suite of QSAR models providing predictions for toxicity endpoints and physicochemical, environmental fate, and ADME properties. In addition to predictions, OPERA provides accuracy estimates, applicability domain assessment and experimental data when available. Recent additions to OPERA include models for estrogenic activity, androgenic activity, and acute oral systemic toxicity developed through international collaborative modeling projects, and updates to models predicting plasma protein binding and intrinsic hepatic clearance.]]>
OPERA is a free and open source/open data suite of QSAR models providing predictions for toxicity endpoints and physicochemical, environmental fate, and ADME properties. In addition to predictions, OPERA provides accuracy estimates, applicability domain assessment and experimental data when available. Recent additions to OPERA include models for estrogenic activity, androgenic activity, and acute oral systemic toxicity developed through international collaborative modeling projects, and updates to models predicting plasma protein binding and intrinsic hepatic clearance.]]> Fri, 27 Aug 2021 21:18:49 GMT /slideshow/opera-an-open-source-and-open-data-suite-of-qsar-models/250066358 captaindare@slideshare.net(captaindare) OPERA, AN OPEN SOURCE AND OPEN DATA SUITE OF QSAR MODELS captaindare OPERA is a free and open source/open data suite of QSAR models providing predictions for toxicity endpoints and physicochemical, environmental fate, and ADME properties. In addition to predictions, OPERA provides accuracy estimates, applicability domain assessment and experimental data when available. Recent additions to OPERA include models for estrogenic activity, androgenic activity, and acute oral systemic toxicity developed through international collaborative modeling projects, and updates to models predicting plasma protein binding and intrinsic hepatic clearance. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/1004mansouri-210827211850-thumbnail.jpg?width=120&amp;height=120&amp;fit=bounds" /><br> OPERA is a free and open source/open data suite of QSAR models providing predictions for toxicity endpoints and physicochemical, environmental fate, and ADME properties. In addition to predictions, OPERA provides accuracy estimates, applicability domain assessment and experimental data when available. Recent additions to OPERA include models for estrogenic activity, androgenic activity, and acute oral systemic toxicity developed through international collaborative modeling projects, and updates to models predicting plasma protein binding and intrinsic hepatic clearance.
OPERA, AN OPEN SOURCE AND OPEN DATA SUITE OF QSAR MODELS from Kamel Mansouri
]]> 203 0 https://cdn.slidesharecdn.com/ss_thumbnails/1004mansouri-210827211850-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post http://activitystrea.ms/schema/1.0/posted 0 International Computational Collaborations to Solve Toxicology Problems /slideshow/international-computational-collaborations-to-solve-toxicology-problems/116919692 euroqsar18km-180927161240
EuroQSAR2018, September 19, 2018 Thessaloniki, Greece]]>
EuroQSAR2018, September 19, 2018 Thessaloniki, Greece]]> Thu, 27 Sep 2018 16:12:40 GMT /slideshow/international-computational-collaborations-to-solve-toxicology-problems/116919692 captaindare@slideshare.net(captaindare) International Computational Collaborations to Solve Toxicology Problems captaindare EuroQSAR2018, September 19, 2018 Thessaloniki, Greece <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/euroqsar18km-180927161240-thumbnail.jpg?width=120&amp;height=120&amp;fit=bounds" /><br> EuroQSAR2018, September 19, 2018 Thessaloniki, Greece
International Computational Collaborations to Solve Toxicology Problems from Kamel Mansouri
]]> 174 3 https://cdn.slidesharecdn.com/ss_thumbnails/euroqsar18km-180927161240-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post http://activitystrea.ms/schema/1.0/posted 0 Automated workflows for data curation and standardization of chemical structures for QSAR modeling. ACS 2018 (New Orleans, USA) /captaindare/automated-workflows-for-data-curation-and-standardization-of-chemical-structures-for-qsar-modeling-acs-2018-new-orleans-usa workflowsacs2018final-180325214829
Automated workflows for data curation and standardization of chemical structures for QSAR modeling.]]>
Automated workflows for data curation and standardization of chemical structures for QSAR modeling.]]> Sun, 25 Mar 2018 21:48:28 GMT /captaindare/automated-workflows-for-data-curation-and-standardization-of-chemical-structures-for-qsar-modeling-acs-2018-new-orleans-usa captaindare@slideshare.net(captaindare) Automated workflows for data curation and standardization of chemical structures for QSAR modeling. ACS 2018 (New Orleans, USA) captaindare Automated workflows for data curation and standardization of chemical structures for QSAR modeling. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/workflowsacs2018final-180325214829-thumbnail.jpg?width=120&amp;height=120&amp;fit=bounds" /><br> Automated workflows for data curation and standardization of chemical structures for QSAR modeling.
Automated workflows for data curation and standardization of chemical structures for QSAR modeling. ACS 2018 (New Orleans, USA) from Kamel Mansouri
]]> 252 3 https://cdn.slidesharecdn.com/ss_thumbnails/workflowsacs2018final-180325214829-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post http://activitystrea.ms/schema/1.0/posted 0 OPERA: A free and open source QSAR tool for predicting physicochemical properties and environmental fate endpoints. ACS 2018 (New Orleans, USA) /slideshow/opera-a-free-and-open-source-qsar-tool-for-predicting-physicochemical-properties-and-environmental-fate-endpoints-acs-2018-new-orleans-usa/91884994 operaacs2018final-180325214527
OPERA: A free and open source QSAR tool for predicting physicochemical properties and environmental fate endpoints]]>
OPERA: A free and open source QSAR tool for predicting physicochemical properties and environmental fate endpoints]]> Sun, 25 Mar 2018 21:45:27 GMT /slideshow/opera-a-free-and-open-source-qsar-tool-for-predicting-physicochemical-properties-and-environmental-fate-endpoints-acs-2018-new-orleans-usa/91884994 captaindare@slideshare.net(captaindare) OPERA: A free and open source QSAR tool for predicting physicochemical properties and environmental fate endpoints. ACS 2018 (New Orleans, USA) captaindare OPERA: A free and open source QSAR tool for predicting physicochemical properties and environmental fate endpoints <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/operaacs2018final-180325214527-thumbnail.jpg?width=120&amp;height=120&amp;fit=bounds" /><br> OPERA: A free and open source QSAR tool for predicting physicochemical properties and environmental fate endpoints
OPERA: A free and open source QSAR tool for predicting physicochemical properties and environmental fate endpoints. ACS 2018 (New Orleans, USA) from Kamel Mansouri
]]> 413 3 https://cdn.slidesharecdn.com/ss_thumbnails/operaacs2018final-180325214527-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post http://activitystrea.ms/schema/1.0/posted 0 Virtual screening of chemicals for endocrine disrupting activity: Case studies of the estrogen and androgen receptors. ACS 2018 (New Orleans, USA) /slideshow/virtual-screening-of-chemicals-for-endocrine-disrupting-activity-case-studies-of-the-estrogen-and-androgen-receptors-acs-2018-new-orleans-usa/91884920 eraracs2018-180325214332
Endocrine disrupting chemicals (EDCs) are xenobiotics that mimic the interaction of natural hormones at the receptor level and alter synthesis, transport and metabolism pathways. The prospect of EDCs causing adverse health effects in humans and wildlife has led to the development of scientific and regulatory approaches for evaluating bioactivity. This need is being partially addressed by the use of high-throughput screening (HTS) in vitro approaches and computational modeling. In the framework of the Endocrine Disruptor Screening Program (EDSP), the U.S. EPA led two worldwide consortiums to virtually (i.e., in silico) screen chemicals for their potential estrogenic and androgenic activities. The Collaborative Estrogen Receptor (ER) Activity Prediction Project (CERAPP) [1] predicted activities for 32,464 chemicals and the Collaborative Modeling Project for Androgen Receptor (AR) Activity (CoMPARA) generated predictions on the CERAPP list with additional simulated metabolites, totaling 55,450 unique structures. Modelers and computational toxicology scientists from 30 international groups contributed structure-based models and results for activity prediction to one or both projects, with methods ranging from QSARs to docking to predict binding, agonism and antagonism activities. Models were based on a common training set of 1746 chemicals having ToxCast/Tox21 HTS in vitro assay results (18 assays for ER and 11 for AR) integrated into computational networks. The models were then validated using curated literature data from different sources (~7,000 results for ER and ~5,000 results for AR). To overcome the limitations of single approaches, CERAPP and CoMPARA models were each combined into consensus models reaching high predictive accuracy. These consensus models were extended beyond the initially designed datasets by implementing them into the free and open-source application OPERA to avoid running every single model on new chemicals [2]. This implementation was used to screen the entire EPA DSSTox database of ~750,000 chemicals and predicted ER and AR activity is made freely available on the CompTox Chemistry dashboard (https://comptox.epa.gov/dashboard) [3].]]>
Endocrine disrupting chemicals (EDCs) are xenobiotics that mimic the interaction of natural hormones at the receptor level and alter synthesis, transport and metabolism pathways. The prospect of EDCs causing adverse health effects in humans and wildlife has led to the development of scientific and regulatory approaches for evaluating bioactivity. This need is being partially addressed by the use of high-throughput screening (HTS) in vitro approaches and computational modeling. In the framework of the Endocrine Disruptor Screening Program (EDSP), the U.S. EPA led two worldwide consortiums to virtually (i.e., in silico) screen chemicals for their potential estrogenic and androgenic activities. The Collaborative Estrogen Receptor (ER) Activity Prediction Project (CERAPP) [1] predicted activities for 32,464 chemicals and the Collaborative Modeling Project for Androgen Receptor (AR) Activity (CoMPARA) generated predictions on the CERAPP list with additional simulated metabolites, totaling 55,450 unique structures. Modelers and computational toxicology scientists from 30 international groups contributed structure-based models and results for activity prediction to one or both projects, with methods ranging from QSARs to docking to predict binding, agonism and antagonism activities. Models were based on a common training set of 1746 chemicals having ToxCast/Tox21 HTS in vitro assay results (18 assays for ER and 11 for AR) integrated into computational networks. The models were then validated using curated literature data from different sources (~7,000 results for ER and ~5,000 results for AR). To overcome the limitations of single approaches, CERAPP and CoMPARA models were each combined into consensus models reaching high predictive accuracy. These consensus models were extended beyond the initially designed datasets by implementing them into the free and open-source application OPERA to avoid running every single model on new chemicals [2]. This implementation was used to screen the entire EPA DSSTox database of ~750,000 chemicals and predicted ER and AR activity is made freely available on the CompTox Chemistry dashboard (https://comptox.epa.gov/dashboard) [3].]]> Sun, 25 Mar 2018 21:43:32 GMT /slideshow/virtual-screening-of-chemicals-for-endocrine-disrupting-activity-case-studies-of-the-estrogen-and-androgen-receptors-acs-2018-new-orleans-usa/91884920 captaindare@slideshare.net(captaindare) Virtual screening of chemicals for endocrine disrupting activity: Case studies of the estrogen and androgen receptors. ACS 2018 (New Orleans, USA) captaindare Endocrine disrupting chemicals (EDCs) are xenobiotics that mimic the interaction of natural hormones at the receptor level and alter synthesis, transport and metabolism pathways. The prospect of EDCs causing adverse health effects in humans and wildlife has led to the development of scientific and regulatory approaches for evaluating bioactivity. This need is being partially addressed by the use of high-throughput screening (HTS) in vitro approaches and computational modeling. In the framework of the Endocrine Disruptor Screening Program (EDSP), the U.S. EPA led two worldwide consortiums to virtually (i.e., in silico) screen chemicals for their potential estrogenic and androgenic activities. The Collaborative Estrogen Receptor (ER) Activity Prediction Project (CERAPP) [1] predicted activities for 32,464 chemicals and the Collaborative Modeling Project for Androgen Receptor (AR) Activity (CoMPARA) generated predictions on the CERAPP list with additional simulated metabolites, totaling 55,450 unique structures. Modelers and computational toxicology scientists from 30 international groups contributed structure-based models and results for activity prediction to one or both projects, with methods ranging from QSARs to docking to predict binding, agonism and antagonism activities. Models were based on a common training set of 1746 chemicals having ToxCast/Tox21 HTS in vitro assay results (18 assays for ER and 11 for AR) integrated into computational networks. The models were then validated using curated literature data from different sources (~7,000 results for ER and ~5,000 results for AR). To overcome the limitations of single approaches, CERAPP and CoMPARA models were each combined into consensus models reaching high predictive accuracy. These consensus models were extended beyond the initially designed datasets by implementing them into the free and open-source application OPERA to avoid running every single model on new chemicals [2]. This implementation was used to screen the entire EPA DSSTox database of ~750,000 chemicals and predicted ER and AR activity is made freely available on the CompTox Chemistry dashboard (https://comptox.epa.gov/dashboard) [3]. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/eraracs2018-180325214332-thumbnail.jpg?width=120&amp;height=120&amp;fit=bounds" /><br> Endocrine disrupting chemicals (EDCs) are xenobiotics that mimic the interaction of natural hormones at the receptor level and alter synthesis, transport and metabolism pathways. The prospect of EDCs causing adverse health effects in humans and wildlife has led to the development of scientific and regulatory approaches for evaluating bioactivity. This need is being partially addressed by the use of high-throughput screening (HTS) in vitro approaches and computational modeling. In the framework of the Endocrine Disruptor Screening Program (EDSP), the U.S. EPA led two worldwide consortiums to virtually (i.e., in silico) screen chemicals for their potential estrogenic and androgenic activities. The Collaborative Estrogen Receptor (ER) Activity Prediction Project (CERAPP) [1] predicted activities for 32,464 chemicals and the Collaborative Modeling Project for Androgen Receptor (AR) Activity (CoMPARA) generated predictions on the CERAPP list with additional simulated metabolites, totaling 55,450 unique structures. Modelers and computational toxicology scientists from 30 international groups contributed structure-based models and results for activity prediction to one or both projects, with methods ranging from QSARs to docking to predict binding, agonism and antagonism activities. Models were based on a common training set of 1746 chemicals having ToxCast/Tox21 HTS in vitro assay results (18 assays for ER and 11 for AR) integrated into computational networks. The models were then validated using curated literature data from different sources (~7,000 results for ER and ~5,000 results for AR). To overcome the limitations of single approaches, CERAPP and CoMPARA models were each combined into consensus models reaching high predictive accuracy. These consensus models were extended beyond the initially designed datasets by implementing them into the free and open-source application OPERA to avoid running every single model on new chemicals [2]. This implementation was used to screen the entire EPA DSSTox database of ~750,000 chemicals and predicted ER and AR activity is made freely available on the CompTox Chemistry dashboard (https://comptox.epa.gov/dashboard) [3].
Virtual screening of chemicals for endocrine disrupting activity: Case studies of the estrogen and androgen receptors. ACS 2018 (New Orleans, USA) from Kamel Mansouri
]]> 153 5 https://cdn.slidesharecdn.com/ss_thumbnails/eraracs2018-180325214332-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post http://activitystrea.ms/schema/1.0/posted 0 Chemical prioritization using in silico modeling. SOT 2018 (San Antonio, USA) /captaindare/chemical-prioritization-using-in-silico-modeling-sot-2018-san-antonio-usa prioritizationsot2018km-180325214132
The aim of this work was to design an in silico and in vitro approach to prioritize compounds and perform a quantitative safety assessment. To this end, we pursue a tiered approach taking into account bioactivity and bioavailability of chemicals and their metabolites using a human uterine epithelial cell (Ishikawa)-based assay. This biologically relevant fit-for-purpose assay was designed to quantitatively recapitulate in vivo human response and establish a margin of safety.]]>
The aim of this work was to design an in silico and in vitro approach to prioritize compounds and perform a quantitative safety assessment. To this end, we pursue a tiered approach taking into account bioactivity and bioavailability of chemicals and their metabolites using a human uterine epithelial cell (Ishikawa)-based assay. This biologically relevant fit-for-purpose assay was designed to quantitatively recapitulate in vivo human response and establish a margin of safety.]]> Sun, 25 Mar 2018 21:41:32 GMT /captaindare/chemical-prioritization-using-in-silico-modeling-sot-2018-san-antonio-usa captaindare@slideshare.net(captaindare) Chemical prioritization using in silico modeling. SOT 2018 (San Antonio, USA) captaindare The aim of this work was to design an in silico and in vitro approach to prioritize compounds and perform a quantitative safety assessment. To this end, we pursue a tiered approach taking into account bioactivity and bioavailability of chemicals and their metabolites using a human uterine epithelial cell (Ishikawa)-based assay. This biologically relevant fit-for-purpose assay was designed to quantitatively recapitulate in vivo human response and establish a margin of safety. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/prioritizationsot2018km-180325214132-thumbnail.jpg?width=120&amp;height=120&amp;fit=bounds" /><br> The aim of this work was to design an in silico and in vitro approach to prioritize compounds and perform a quantitative safety assessment. To this end, we pursue a tiered approach taking into account bioactivity and bioavailability of chemicals and their metabolites using a human uterine epithelial cell (Ishikawa)-based assay. This biologically relevant fit-for-purpose assay was designed to quantitatively recapitulate in vivo human response and establish a margin of safety.
Chemical prioritization using in silico modeling. SOT 2018 (San Antonio, USA) from Kamel Mansouri
]]> 54 2 https://cdn.slidesharecdn.com/ss_thumbnails/prioritizationsot2018km-180325214132-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post http://activitystrea.ms/schema/1.0/posted 0 Virtual screening of chemicals for endocrine disrupting activity through CERAPP and CoMPARA projects. SOT 2018 (San Antonio) /slideshow/virtual-screening-of-chemicals-for-endocrine-disrupting-activity-through-cerapp-and-compara-projects-sot-2018-san-antonio/91884644 er-arsot2018km-180325213636
Endocrine disrupting chemicals (EDCs) are xenobiotics that mimic the interaction of natural hormones at the receptor level and alter synthesis, transport and metabolism pathways. The prospect of EDCs causing adverse health effects in humans and wildlife has led to the development of scientific and regulatory approaches for evaluating bioactivity. This need is being partially addressed by the use of high-throughput screening (HTS) in vitro approaches and computational modeling. In the framework of the Endocrine Disruptor Screening Program (EDSP), the U.S. EPA led two worldwide consortiums to virtually (i.e., in silico) screen chemicals for their potential estrogenic and androgenic activities. The Collaborative Estrogen Receptor (ER) Activity Prediction Project (CERAPP) [1] predicted activities for 32,464 chemicals and the Collaborative Modeling Project for Androgen Receptor (AR) Activity (CoMPARA) generated predictions on the CERAPP list with additional simulated metabolites, totaling 55,450 unique structures. Modelers and computational toxicology scientists from 30 international groups contributed structure-based models and results for activity prediction to one or both projects, with methods ranging from QSARs to docking to predict binding, agonism and antagonism activities. Models were based on a common training set of 1746 chemicals having ToxCast/Tox21 HTS in vitro assay results (18 assays for ER and 11 for AR) integrated into computational networks. The models were then validated using curated literature data from different sources (~7,000 results for ER and ~5,000 results for AR). To overcome the limitations of single approaches, CERAPP and CoMPARA models were each combined into consensus models reaching high predictive accuracy. These consensus models were extended beyond the initially designed datasets by implementing them into the free and open-source application OPERA to avoid running every single model on new chemicals [2]. This implementation was used to screen the entire EPA DSSTox database of ~750,000 chemicals and predicted ER and AR activity is made freely available on the CompTox Chemistry dashboard (https://comptox.epa.gov/dashboard) [3]. ]]>
Endocrine disrupting chemicals (EDCs) are xenobiotics that mimic the interaction of natural hormones at the receptor level and alter synthesis, transport and metabolism pathways. The prospect of EDCs causing adverse health effects in humans and wildlife has led to the development of scientific and regulatory approaches for evaluating bioactivity. This need is being partially addressed by the use of high-throughput screening (HTS) in vitro approaches and computational modeling. In the framework of the Endocrine Disruptor Screening Program (EDSP), the U.S. EPA led two worldwide consortiums to virtually (i.e., in silico) screen chemicals for their potential estrogenic and androgenic activities. The Collaborative Estrogen Receptor (ER) Activity Prediction Project (CERAPP) [1] predicted activities for 32,464 chemicals and the Collaborative Modeling Project for Androgen Receptor (AR) Activity (CoMPARA) generated predictions on the CERAPP list with additional simulated metabolites, totaling 55,450 unique structures. Modelers and computational toxicology scientists from 30 international groups contributed structure-based models and results for activity prediction to one or both projects, with methods ranging from QSARs to docking to predict binding, agonism and antagonism activities. Models were based on a common training set of 1746 chemicals having ToxCast/Tox21 HTS in vitro assay results (18 assays for ER and 11 for AR) integrated into computational networks. The models were then validated using curated literature data from different sources (~7,000 results for ER and ~5,000 results for AR). To overcome the limitations of single approaches, CERAPP and CoMPARA models were each combined into consensus models reaching high predictive accuracy. These consensus models were extended beyond the initially designed datasets by implementing them into the free and open-source application OPERA to avoid running every single model on new chemicals [2]. This implementation was used to screen the entire EPA DSSTox database of ~750,000 chemicals and predicted ER and AR activity is made freely available on the CompTox Chemistry dashboard (https://comptox.epa.gov/dashboard) [3]. ]]> Sun, 25 Mar 2018 21:36:36 GMT /slideshow/virtual-screening-of-chemicals-for-endocrine-disrupting-activity-through-cerapp-and-compara-projects-sot-2018-san-antonio/91884644 captaindare@slideshare.net(captaindare) Virtual screening of chemicals for endocrine disrupting activity through CERAPP and CoMPARA projects. SOT 2018 (San Antonio) captaindare Endocrine disrupting chemicals (EDCs) are xenobiotics that mimic the interaction of natural hormones at the receptor level and alter synthesis, transport and metabolism pathways. The prospect of EDCs causing adverse health effects in humans and wildlife has led to the development of scientific and regulatory approaches for evaluating bioactivity. This need is being partially addressed by the use of high-throughput screening (HTS) in vitro approaches and computational modeling. In the framework of the Endocrine Disruptor Screening Program (EDSP), the U.S. EPA led two worldwide consortiums to virtually (i.e., in silico) screen chemicals for their potential estrogenic and androgenic activities. The Collaborative Estrogen Receptor (ER) Activity Prediction Project (CERAPP) [1] predicted activities for 32,464 chemicals and the Collaborative Modeling Project for Androgen Receptor (AR) Activity (CoMPARA) generated predictions on the CERAPP list with additional simulated metabolites, totaling 55,450 unique structures. Modelers and computational toxicology scientists from 30 international groups contributed structure-based models and results for activity prediction to one or both projects, with methods ranging from QSARs to docking to predict binding, agonism and antagonism activities. Models were based on a common training set of 1746 chemicals having ToxCast/Tox21 HTS in vitro assay results (18 assays for ER and 11 for AR) integrated into computational networks. The models were then validated using curated literature data from different sources (~7,000 results for ER and ~5,000 results for AR). To overcome the limitations of single approaches, CERAPP and CoMPARA models were each combined into consensus models reaching high predictive accuracy. These consensus models were extended beyond the initially designed datasets by implementing them into the free and open-source application OPERA to avoid running every single model on new chemicals [2]. This implementation was used to screen the entire EPA DSSTox database of ~750,000 chemicals and predicted ER and AR activity is made freely available on the CompTox Chemistry dashboard (https://comptox.epa.gov/dashboard) [3]. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/er-arsot2018km-180325213636-thumbnail.jpg?width=120&amp;height=120&amp;fit=bounds" /><br> Endocrine disrupting chemicals (EDCs) are xenobiotics that mimic the interaction of natural hormones at the receptor level and alter synthesis, transport and metabolism pathways. The prospect of EDCs causing adverse health effects in humans and wildlife has led to the development of scientific and regulatory approaches for evaluating bioactivity. This need is being partially addressed by the use of high-throughput screening (HTS) in vitro approaches and computational modeling. In the framework of the Endocrine Disruptor Screening Program (EDSP), the U.S. EPA led two worldwide consortiums to virtually (i.e., in silico) screen chemicals for their potential estrogenic and androgenic activities. The Collaborative Estrogen Receptor (ER) Activity Prediction Project (CERAPP) [1] predicted activities for 32,464 chemicals and the Collaborative Modeling Project for Androgen Receptor (AR) Activity (CoMPARA) generated predictions on the CERAPP list with additional simulated metabolites, totaling 55,450 unique structures. Modelers and computational toxicology scientists from 30 international groups contributed structure-based models and results for activity prediction to one or both projects, with methods ranging from QSARs to docking to predict binding, agonism and antagonism activities. Models were based on a common training set of 1746 chemicals having ToxCast/Tox21 HTS in vitro assay results (18 assays for ER and 11 for AR) integrated into computational networks. The models were then validated using curated literature data from different sources (~7,000 results for ER and ~5,000 results for AR). To overcome the limitations of single approaches, CERAPP and CoMPARA models were each combined into consensus models reaching high predictive accuracy. These consensus models were extended beyond the initially designed datasets by implementing them into the free and open-source application OPERA to avoid running every single model on new chemicals [2]. This implementation was used to screen the entire EPA DSSTox database of ~750,000 chemicals and predicted ER and AR activity is made freely available on the CompTox Chemistry dashboard (https://comptox.epa.gov/dashboard) [3].
Virtual screening of chemicals for endocrine disrupting activity through CERAPP and CoMPARA projects. SOT 2018 (San Antonio) from Kamel Mansouri
]]> 114 6 https://cdn.slidesharecdn.com/ss_thumbnails/er-arsot2018km-180325213636-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post http://activitystrea.ms/schema/1.0/posted 0 Scoring and ranking of metabolic trees to computationally prioritize chemicals for testing using fit-for-purpose in vitro estrogen receptor assay. OpenTox USA 2017 /slideshow/scoring-and-ranking-of-metabolic-trees-to-computationally-prioritize-chemicals-for-testing-using-fitforpurpose-in-vitro-estrogen-receptor-assay-opentox-usa-2017/77804760 opentoxusa2017km-170712193350
The aim of this work was to design an in silico and in vitro approach to prioritize compounds and perform a quantitative safety assessment. To this end, we pursue a tiered approach taking into account bioactivity and bioavailability of chemicals and their metabolites using a human uterine epithelial cell (Ishikawa)-based assay. This biologically relevant fit-for-purpose assay was designed to quantitatively recapitulate in vivo human response and establish a margin of safety. ]]>
The aim of this work was to design an in silico and in vitro approach to prioritize compounds and perform a quantitative safety assessment. To this end, we pursue a tiered approach taking into account bioactivity and bioavailability of chemicals and their metabolites using a human uterine epithelial cell (Ishikawa)-based assay. This biologically relevant fit-for-purpose assay was designed to quantitatively recapitulate in vivo human response and establish a margin of safety. ]]> Wed, 12 Jul 2017 19:33:50 GMT /slideshow/scoring-and-ranking-of-metabolic-trees-to-computationally-prioritize-chemicals-for-testing-using-fitforpurpose-in-vitro-estrogen-receptor-assay-opentox-usa-2017/77804760 captaindare@slideshare.net(captaindare) Scoring and ranking of metabolic trees to computationally prioritize chemicals for testing using fit-for-purpose in vitro estrogen receptor assay. OpenTox USA 2017 captaindare The aim of this work was to design an in silico and in vitro approach to prioritize compounds and perform a quantitative safety assessment. To this end, we pursue a tiered approach taking into account bioactivity and bioavailability of chemicals and their metabolites using a human uterine epithelial cell (Ishikawa)-based assay. This biologically relevant fit-for-purpose assay was designed to quantitatively recapitulate in vivo human response and establish a margin of safety. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/opentoxusa2017km-170712193350-thumbnail.jpg?width=120&amp;height=120&amp;fit=bounds" /><br> The aim of this work was to design an in silico and in vitro approach to prioritize compounds and perform a quantitative safety assessment. To this end, we pursue a tiered approach taking into account bioactivity and bioavailability of chemicals and their metabolites using a human uterine epithelial cell (Ishikawa)-based assay. This biologically relevant fit-for-purpose assay was designed to quantitatively recapitulate in vivo human response and establish a margin of safety.
Scoring and ranking of metabolic trees to computationally prioritize chemicals for testing using fit-for-purpose in vitro estrogen receptor assay. OpenTox USA 2017 from Kamel Mansouri
]]> 259 5 https://cdn.slidesharecdn.com/ss_thumbnails/opentoxusa2017km-170712193350-thumbnail.jpg?width=120&height=120&fit=bounds presentation 000000 http://activitystrea.ms/schema/1.0/post http://activitystrea.ms/schema/1.0/posted 0 CoMPARA: Collaborative Modeling Project for Androgen Receptor Activity /slideshow/compara-collaborative-modeling-project-for-androgen-receptor-activity/75569925 comparasot-170501155604
In order to protect human health from chemicals that can mimic natural hormones, the U. S. Congress mandated the U.S. EPA to screen chemicals for their potential to be endocrine disruptors through the Endocrine Disruptor Screening Program (EDSP). However, the number of chemicals to which humans are exposed is too large (tens of thousands) to be accommodated by the EDSP Tier 1 battery, so combinations of in vitro high-throughput screening (HTS) assays and computational models are being developed to help prioritize chemicals for more detailed testing. Previously, CERAPP (Collaborative Estrogen Receptor Activity Prediction Project) demonstrated the effectiveness of combining many QSAR models trained on HTS data to prioritize a large chemical list for estrogen receptor activity. The limitations of single models were overcome by combining all models built by the consortium into consensus predictions. CoMPARA is a larger scale collaboration between 35 international groups, following the steps of CERAPP to model androgen receptor activity using a common training set of 1746 compounds provided by U.S. EPA. Eleven HTS ToxCast/Tox21 in vitro assays were integrated into a computational network model to detect true AR activity. Bootstrap uncertainty quantification was used to remove potential false positives/negatives. Reference chemicals (158) from the literature were used to validate the model, which showed 95.2% and 97.5% balanced accuracies for AR agonists and antagonists respectively. A library of ~80k chemical structure, including ~11k chemicals curated from PubChem literature data using ScrubChem tools was integrated with CoMPARAs consensus predictions that combined several structure-based and QSAR modeling approaches. The results of this project will be used to prioritize a large set of more than 50k chemicals for further testing over the next phases of ToxCast/Tox21, among other projects. This work does not reflect the official policy of any federal agency.]]>
In order to protect human health from chemicals that can mimic natural hormones, the U. S. Congress mandated the U.S. EPA to screen chemicals for their potential to be endocrine disruptors through the Endocrine Disruptor Screening Program (EDSP). However, the number of chemicals to which humans are exposed is too large (tens of thousands) to be accommodated by the EDSP Tier 1 battery, so combinations of in vitro high-throughput screening (HTS) assays and computational models are being developed to help prioritize chemicals for more detailed testing. Previously, CERAPP (Collaborative Estrogen Receptor Activity Prediction Project) demonstrated the effectiveness of combining many QSAR models trained on HTS data to prioritize a large chemical list for estrogen receptor activity. The limitations of single models were overcome by combining all models built by the consortium into consensus predictions. CoMPARA is a larger scale collaboration between 35 international groups, following the steps of CERAPP to model androgen receptor activity using a common training set of 1746 compounds provided by U.S. EPA. Eleven HTS ToxCast/Tox21 in vitro assays were integrated into a computational network model to detect true AR activity. Bootstrap uncertainty quantification was used to remove potential false positives/negatives. Reference chemicals (158) from the literature were used to validate the model, which showed 95.2% and 97.5% balanced accuracies for AR agonists and antagonists respectively. A library of ~80k chemical structure, including ~11k chemicals curated from PubChem literature data using ScrubChem tools was integrated with CoMPARAs consensus predictions that combined several structure-based and QSAR modeling approaches. The results of this project will be used to prioritize a large set of more than 50k chemicals for further testing over the next phases of ToxCast/Tox21, among other projects. This work does not reflect the official policy of any federal agency.]]> Mon, 01 May 2017 15:56:04 GMT /slideshow/compara-collaborative-modeling-project-for-androgen-receptor-activity/75569925 captaindare@slideshare.net(captaindare) CoMPARA: Collaborative Modeling Project for Androgen Receptor Activity captaindare In order to protect human health from chemicals that can mimic natural hormones, the U. S. Congress mandated the U.S. EPA to screen chemicals for their potential to be endocrine disruptors through the Endocrine Disruptor Screening Program (EDSP). However, the number of chemicals to which humans are exposed is too large (tens of thousands) to be accommodated by the EDSP Tier 1 battery, so combinations of in vitro high-throughput screening (HTS) assays and computational models are being developed to help prioritize chemicals for more detailed testing. Previously, CERAPP (Collaborative Estrogen Receptor Activity Prediction Project) demonstrated the effectiveness of combining many QSAR models trained on HTS data to prioritize a large chemical list for estrogen receptor activity. The limitations of single models were overcome by combining all models built by the consortium into consensus predictions. CoMPARA is a larger scale collaboration between 35 international groups, following the steps of CERAPP to model androgen receptor activity using a common training set of 1746 compounds provided by U.S. EPA. Eleven HTS ToxCast/Tox21 in vitro assays were integrated into a computational network model to detect true AR activity. Bootstrap uncertainty quantification was used to remove potential false positives/negatives. Reference chemicals (158) from the literature were used to validate the model, which showed 95.2% and 97.5% balanced accuracies for AR agonists and antagonists respectively. A library of ~80k chemical structure, including ~11k chemicals curated from PubChem literature data using ScrubChem tools was integrated with CoMPARAs consensus predictions that combined several structure-based and QSAR modeling approaches. The results of this project will be used to prioritize a large set of more than 50k chemicals for further testing over the next phases of ToxCast/Tox21, among other projects. This work does not reflect the official policy of any federal agency. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/comparasot-170501155604-thumbnail.jpg?width=120&amp;height=120&amp;fit=bounds" /><br> In order to protect human health from chemicals that can mimic natural hormones, the U. S. Congress mandated the U.S. EPA to screen chemicals for their potential to be endocrine disruptors through the Endocrine Disruptor Screening Program (EDSP). However, the number of chemicals to which humans are exposed is too large (tens of thousands) to be accommodated by the EDSP Tier 1 battery, so combinations of in vitro high-throughput screening (HTS) assays and computational models are being developed to help prioritize chemicals for more detailed testing. Previously, CERAPP (Collaborative Estrogen Receptor Activity Prediction Project) demonstrated the effectiveness of combining many QSAR models trained on HTS data to prioritize a large chemical list for estrogen receptor activity. The limitations of single models were overcome by combining all models built by the consortium into consensus predictions. CoMPARA is a larger scale collaboration between 35 international groups, following the steps of CERAPP to model androgen receptor activity using a common training set of 1746 compounds provided by U.S. EPA. Eleven HTS ToxCast/Tox21 in vitro assays were integrated into a computational network model to detect true AR activity. Bootstrap uncertainty quantification was used to remove potential false positives/negatives. Reference chemicals (158) from the literature were used to validate the model, which showed 95.2% and 97.5% balanced accuracies for AR agonists and antagonists respectively. A library of ~80k chemical structure, including ~11k chemicals curated from PubChem literature data using ScrubChem tools was integrated with CoMPARAs consensus predictions that combined several structure-based and QSAR modeling approaches. The results of this project will be used to prioritize a large set of more than 50k chemicals for further testing over the next phases of ToxCast/Tox21, among other projects. This work does not reflect the official policy of any federal agency.
CoMPARA: Collaborative Modeling Project for Androgen Receptor Activity from Kamel Mansouri
]]> 151 6 https://cdn.slidesharecdn.com/ss_thumbnails/comparasot-170501155604-thumbnail.jpg?width=120&height=120&fit=bounds presentation 000000 http://activitystrea.ms/schema/1.0/post http://activitystrea.ms/schema/1.0/posted 0 Consensus Models to Predict Endocrine Disruption for All Human-Exposure Chemicals. /slideshow/consensus-models-to-predict-endocrine-disruption-for-all-humanexposure-chemicals/75569820 kamelmansouriaaaskmcrsj-170501155248
AAAS annual meeting (Boston, Feb 2017) Humans are potentially exposed to tens of thousands of man-made chemicals in the environment. It is well known that some environmental chemicals mimic natural hormones and thus have the potential to be endocrine disruptors. Most of these environmental chemicals have never been tested for their ability to disrupt the endocrine system, in particular, their ability to interact with the estrogen receptor. EPA needs tools to prioritize thousands of chemicals, for instance in the Endocrine Disruptor Screening Program (EDSP). Collaborative Estrogen Receptor Activity Prediction Project (CERAPP) was intended to be a demonstration of the use of predictive computational models on HTS data including ToxCast and Tox21 assays to prioritize a large chemical universe of 32464 unique structures for one specific molecular target the estrogen receptor. CERAPP combined multiple computational models for prediction of estrogen receptor activity, and used the predicted results to build a unique consensus model. Models were developed in collaboration between 17 groups in the U.S. and Europe and applied to predict the common set of chemicals. Structure-based techniques such as docking and several QSAR modeling approaches were employed, mostly using a common training set of 1677 compounds provided by U.S. EPA, to build a total of 42 classification models and 8 regression models for binding, agonist and antagonist activity. All predictions were evaluated on ToxCast data and on an external validation set collected from the literature. In order to overcome the limitations of single models, a consensus was built weighting models based on their prediction accuracy scores (including sensitivity and specificity against training and external sets). Individual model scores ranged from 0.69 to 0.85, showing high prediction reliabilities. The final consensus predicted 4001 chemicals as actives to be considered as high priority for further testing and 6742 as suspicious chemicals. The same approach is now being applied on a larger scale project to predict the potential androgen receptor (AR) activity of chemicals. This project called CoMPARA (Collaborative Modeling Project for Androgen Receptor Activity) is a collaboration between 35 international groups working on a common set of ~55k chemicals. This abstract does not necessarily reflect U.S. EPA policy ]]>
AAAS annual meeting (Boston, Feb 2017) Humans are potentially exposed to tens of thousands of man-made chemicals in the environment. It is well known that some environmental chemicals mimic natural hormones and thus have the potential to be endocrine disruptors. Most of these environmental chemicals have never been tested for their ability to disrupt the endocrine system, in particular, their ability to interact with the estrogen receptor. EPA needs tools to prioritize thousands of chemicals, for instance in the Endocrine Disruptor Screening Program (EDSP). Collaborative Estrogen Receptor Activity Prediction Project (CERAPP) was intended to be a demonstration of the use of predictive computational models on HTS data including ToxCast and Tox21 assays to prioritize a large chemical universe of 32464 unique structures for one specific molecular target the estrogen receptor. CERAPP combined multiple computational models for prediction of estrogen receptor activity, and used the predicted results to build a unique consensus model. Models were developed in collaboration between 17 groups in the U.S. and Europe and applied to predict the common set of chemicals. Structure-based techniques such as docking and several QSAR modeling approaches were employed, mostly using a common training set of 1677 compounds provided by U.S. EPA, to build a total of 42 classification models and 8 regression models for binding, agonist and antagonist activity. All predictions were evaluated on ToxCast data and on an external validation set collected from the literature. In order to overcome the limitations of single models, a consensus was built weighting models based on their prediction accuracy scores (including sensitivity and specificity against training and external sets). Individual model scores ranged from 0.69 to 0.85, showing high prediction reliabilities. The final consensus predicted 4001 chemicals as actives to be considered as high priority for further testing and 6742 as suspicious chemicals. The same approach is now being applied on a larger scale project to predict the potential androgen receptor (AR) activity of chemicals. This project called CoMPARA (Collaborative Modeling Project for Androgen Receptor Activity) is a collaboration between 35 international groups working on a common set of ~55k chemicals. This abstract does not necessarily reflect U.S. EPA policy ]]> Mon, 01 May 2017 15:52:47 GMT /slideshow/consensus-models-to-predict-endocrine-disruption-for-all-humanexposure-chemicals/75569820 captaindare@slideshare.net(captaindare) Consensus Models to Predict Endocrine Disruption for All Human-Exposure Chemicals. captaindare AAAS annual meeting (Boston, Feb 2017) Humans are potentially exposed to tens of thousands of man-made chemicals in the environment. It is well known that some environmental chemicals mimic natural hormones and thus have the potential to be endocrine disruptors. Most of these environmental chemicals have never been tested for their ability to disrupt the endocrine system, in particular, their ability to interact with the estrogen receptor. EPA needs tools to prioritize thousands of chemicals, for instance in the Endocrine Disruptor Screening Program (EDSP). Collaborative Estrogen Receptor Activity Prediction Project (CERAPP) was intended to be a demonstration of the use of predictive computational models on HTS data including ToxCast and Tox21 assays to prioritize a large chemical universe of 32464 unique structures for one specific molecular target the estrogen receptor. CERAPP combined multiple computational models for prediction of estrogen receptor activity, and used the predicted results to build a unique consensus model. Models were developed in collaboration between 17 groups in the U.S. and Europe and applied to predict the common set of chemicals. Structure-based techniques such as docking and several QSAR modeling approaches were employed, mostly using a common training set of 1677 compounds provided by U.S. EPA, to build a total of 42 classification models and 8 regression models for binding, agonist and antagonist activity. All predictions were evaluated on ToxCast data and on an external validation set collected from the literature. In order to overcome the limitations of single models, a consensus was built weighting models based on their prediction accuracy scores (including sensitivity and specificity against training and external sets). Individual model scores ranged from 0.69 to 0.85, showing high prediction reliabilities. The final consensus predicted 4001 chemicals as actives to be considered as high priority for further testing and 6742 as suspicious chemicals. The same approach is now being applied on a larger scale project to predict the potential androgen receptor (AR) activity of chemicals. This project called CoMPARA (Collaborative Modeling Project for Androgen Receptor Activity) is a collaboration between 35 international groups working on a common set of ~55k chemicals. This abstract does not necessarily reflect U.S. EPA policy <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/kamelmansouriaaaskmcrsj-170501155248-thumbnail.jpg?width=120&amp;height=120&amp;fit=bounds" /><br> AAAS annual meeting (Boston, Feb 2017) Humans are potentially exposed to tens of thousands of man-made chemicals in the environment. It is well known that some environmental chemicals mimic natural hormones and thus have the potential to be endocrine disruptors. Most of these environmental chemicals have never been tested for their ability to disrupt the endocrine system, in particular, their ability to interact with the estrogen receptor. EPA needs tools to prioritize thousands of chemicals, for instance in the Endocrine Disruptor Screening Program (EDSP). Collaborative Estrogen Receptor Activity Prediction Project (CERAPP) was intended to be a demonstration of the use of predictive computational models on HTS data including ToxCast and Tox21 assays to prioritize a large chemical universe of 32464 unique structures for one specific molecular target the estrogen receptor. CERAPP combined multiple computational models for prediction of estrogen receptor activity, and used the predicted results to build a unique consensus model. Models were developed in collaboration between 17 groups in the U.S. and Europe and applied to predict the common set of chemicals. Structure-based techniques such as docking and several QSAR modeling approaches were employed, mostly using a common training set of 1677 compounds provided by U.S. EPA, to build a total of 42 classification models and 8 regression models for binding, agonist and antagonist activity. All predictions were evaluated on ToxCast data and on an external validation set collected from the literature. In order to overcome the limitations of single models, a consensus was built weighting models based on their prediction accuracy scores (including sensitivity and specificity against training and external sets). Individual model scores ranged from 0.69 to 0.85, showing high prediction reliabilities. The final consensus predicted 4001 chemicals as actives to be considered as high priority for further testing and 6742 as suspicious chemicals. The same approach is now being applied on a larger scale project to predict the potential androgen receptor (AR) activity of chemicals. This project called CoMPARA (Collaborative Modeling Project for Androgen Receptor Activity) is a collaboration between 35 international groups working on a common set of ~55k chemicals. This abstract does not necessarily reflect U.S. EPA policy
Consensus Models to Predict Endocrine Disruption for All Human-Exposure Chemicals. from Kamel Mansouri
]]> 185 8 https://cdn.slidesharecdn.com/ss_thumbnails/kamelmansouriaaaskmcrsj-170501155248-thumbnail.jpg?width=120&height=120&fit=bounds presentation 000000 http://activitystrea.ms/schema/1.0/post http://activitystrea.ms/schema/1.0/posted 0 Free online access to experimental and predicted chemical properties through the EPAs CompTox /slideshow/free-online-access-to-experimental-and-predicted-chemical-properties-through-the-epas-comptox/75535167 acsposter-170430013402
The increasing number and size of public databases is facilitating the collection of chemical structures and associated experimental data for QSAR modeling. However, the performance of QSAR models is highly dependent not only on the modeling methodology, but also on the quality of the data used. In this study we developed robust QSAR models for endpoints of environmental interest with the aim of helping the regulatory process. We used the publicly available PHYSPROP database that includes a set of thirteen common physicochemical and environmental fate properties, including logP, melting point, Henrys coefficient, and biodegradability among others. Curation and standardization workflows have been applied to use the highest quality data and generate QSAR-ready structures. The developed models are in agreement with the five OECD principles that requires QSARs to be simple and reliable. These models were applied to a set of ~700k chemicals to produce predictions for display on the EPA CompTox Chemistry Dashboard. In addition to the predictions, this free web and mobile application provides access to the experimental data used for training as well as detailed reports including general model performances, specific applicability domain and prediction accuracy, and the nearest neighboring structures used for prediction. The dashboard also provides access to model QMRFs (QSAR modeling report format) which is a downloadable pdf containing additional details about the modeling approaches, the data, and molecular descriptor interpretation. ]]>
The increasing number and size of public databases is facilitating the collection of chemical structures and associated experimental data for QSAR modeling. However, the performance of QSAR models is highly dependent not only on the modeling methodology, but also on the quality of the data used. In this study we developed robust QSAR models for endpoints of environmental interest with the aim of helping the regulatory process. We used the publicly available PHYSPROP database that includes a set of thirteen common physicochemical and environmental fate properties, including logP, melting point, Henrys coefficient, and biodegradability among others. Curation and standardization workflows have been applied to use the highest quality data and generate QSAR-ready structures. The developed models are in agreement with the five OECD principles that requires QSARs to be simple and reliable. These models were applied to a set of ~700k chemicals to produce predictions for display on the EPA CompTox Chemistry Dashboard. In addition to the predictions, this free web and mobile application provides access to the experimental data used for training as well as detailed reports including general model performances, specific applicability domain and prediction accuracy, and the nearest neighboring structures used for prediction. The dashboard also provides access to model QMRFs (QSAR modeling report format) which is a downloadable pdf containing additional details about the modeling approaches, the data, and molecular descriptor interpretation. ]]> Sun, 30 Apr 2017 01:34:02 GMT /slideshow/free-online-access-to-experimental-and-predicted-chemical-properties-through-the-epas-comptox/75535167 captaindare@slideshare.net(captaindare) Free online access to experimental and predicted chemical properties through the EPAs CompTox captaindare The increasing number and size of public databases is facilitating the collection of chemical structures and associated experimental data for QSAR modeling. However, the performance of QSAR models is highly dependent not only on the modeling methodology, but also on the quality of the data used. In this study we developed robust QSAR models for endpoints of environmental interest with the aim of helping the regulatory process. We used the publicly available PHYSPROP database that includes a set of thirteen common physicochemical and environmental fate properties, including logP, melting point, Henrys coefficient, and biodegradability among others. Curation and standardization workflows have been applied to use the highest quality data and generate QSAR-ready structures. The developed models are in agreement with the five OECD principles that requires QSARs to be simple and reliable. These models were applied to a set of ~700k chemicals to produce predictions for display on the EPA CompTox Chemistry Dashboard. In addition to the predictions, this free web and mobile application provides access to the experimental data used for training as well as detailed reports including general model performances, specific applicability domain and prediction accuracy, and the nearest neighboring structures used for prediction. The dashboard also provides access to model QMRFs (QSAR modeling report format) which is a downloadable pdf containing additional details about the modeling approaches, the data, and molecular descriptor interpretation. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/acsposter-170430013402-thumbnail.jpg?width=120&amp;height=120&amp;fit=bounds" /><br> The increasing number and size of public databases is facilitating the collection of chemical structures and associated experimental data for QSAR modeling. However, the performance of QSAR models is highly dependent not only on the modeling methodology, but also on the quality of the data used. In this study we developed robust QSAR models for endpoints of environmental interest with the aim of helping the regulatory process. We used the publicly available PHYSPROP database that includes a set of thirteen common physicochemical and environmental fate properties, including logP, melting point, Henrys coefficient, and biodegradability among others. Curation and standardization workflows have been applied to use the highest quality data and generate QSAR-ready structures. The developed models are in agreement with the five OECD principles that requires QSARs to be simple and reliable. These models were applied to a set of ~700k chemicals to produce predictions for display on the EPA CompTox Chemistry Dashboard. In addition to the predictions, this free web and mobile application provides access to the experimental data used for training as well as detailed reports including general model performances, specific applicability domain and prediction accuracy, and the nearest neighboring structures used for prediction. The dashboard also provides access to model QMRFs (QSAR modeling report format) which is a downloadable pdf containing additional details about the modeling approaches, the data, and molecular descriptor interpretation.
Free online access to experimental and predicted chemical properties through the EPAs CompTox from Kamel Mansouri
]]> 105 6 https://cdn.slidesharecdn.com/ss_thumbnails/acsposter-170430013402-thumbnail.jpg?width=120&height=120&fit=bounds presentation 000000 http://activitystrea.ms/schema/1.0/post http://activitystrea.ms/schema/1.0/posted 0 QSAR STUDY ON READY BIODEGRADABILITY OF CHEMICALS. Presented at the 3rd Chemoinformatics Summer School. Strasbourg, France 25 29 June 2012. And ESOF EuroScience Open Forum, Dublin, Ireland 11-15 July 2012 /slideshow/qsar-study-on-ready-biodegradability-of-chemicals-presented-at-the-3rd-chemoinformatics-summer-school-strasbourg-france-25-29-june-2012/63552822 posterstrasbgf-160629051000
The goal of this study was to predict ready biodegradation of chemicals by QSAR modeling. The dataset used for this purpose was produced by the Japanese Ministry of International Trade and Industry (MITI) with experimental results according to the OECD test guideline 301C. Molecular descriptors from Dragon 6 were calculated. Variable selection coupled with classification methods were applied to find the most predictive models with low cross-validation error rate. The best models were after that validated using the preselected test set to check its prediction reliability and for further analysis.]]>
The goal of this study was to predict ready biodegradation of chemicals by QSAR modeling. The dataset used for this purpose was produced by the Japanese Ministry of International Trade and Industry (MITI) with experimental results according to the OECD test guideline 301C. Molecular descriptors from Dragon 6 were calculated. Variable selection coupled with classification methods were applied to find the most predictive models with low cross-validation error rate. The best models were after that validated using the preselected test set to check its prediction reliability and for further analysis.]]> Wed, 29 Jun 2016 05:09:59 GMT /slideshow/qsar-study-on-ready-biodegradability-of-chemicals-presented-at-the-3rd-chemoinformatics-summer-school-strasbourg-france-25-29-june-2012/63552822 captaindare@slideshare.net(captaindare) QSAR STUDY ON READY BIODEGRADABILITY OF CHEMICALS. Presented at the 3rd Chemoinformatics Summer School. Strasbourg, France 25 29 June 2012. And ESOF EuroScience Open Forum, Dublin, Ireland 11-15 July 2012 captaindare The goal of this study was to predict ready biodegradation of chemicals by QSAR modeling. The dataset used for this purpose was produced by the Japanese Ministry of International Trade and Industry (MITI) with experimental results according to the OECD test guideline 301C. Molecular descriptors from Dragon 6 were calculated. Variable selection coupled with classification methods were applied to find the most predictive models with low cross-validation error rate. The best models were after that validated using the preselected test set to check its prediction reliability and for further analysis. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/posterstrasbgf-160629051000-thumbnail.jpg?width=120&amp;height=120&amp;fit=bounds" /><br> The goal of this study was to predict ready biodegradation of chemicals by QSAR modeling. The dataset used for this purpose was produced by the Japanese Ministry of International Trade and Industry (MITI) with experimental results according to the OECD test guideline 301C. Molecular descriptors from Dragon 6 were calculated. Variable selection coupled with classification methods were applied to find the most predictive models with low cross-validation error rate. The best models were after that validated using the preselected test set to check its prediction reliability and for further analysis.
QSAR STUDY ON READY BIODEGRADABILITY OF CHEMICALS. Presented at the 3rd Chemoinformatics Summer School. Strasbourg, France 25 29 June 2012. And ESOF EuroScience Open Forum, Dublin, Ireland 11-15 July 2012 from Kamel Mansouri
]]> 224 7 https://cdn.slidesharecdn.com/ss_thumbnails/posterstrasbgf-160629051000-thumbnail.jpg?width=120&height=120&fit=bounds document Black http://activitystrea.ms/schema/1.0/post http://activitystrea.ms/schema/1.0/posted 0 In-silico study of ToxCast GPCR assays by quantitative structure-activity relationships (QSARs) modeling. Presented at ACS 2014 11 August 2014, San Francisco, USA 2014 /slideshow/insilico-study-of-toxcast-gpcr-assays-by-quantitative-structureactivity-relationships-qsars-modeling-presented-at-acs-2014-11-august-2014-san-francisco-usa-2014/63420687 acs2014kamel-160624162740
The EPA tested several thousand chemicals in 700 toxicity-related in-vitro HTS bioassays through the ToxCast and Tox21 projects. However, the chemical space of interest for environmental exposure is much wider than this set of chemicals. Thus, there is a need to fill data gaps with in-silico methods, and quantitative structure-activity relationships (QSARs) are a cost effective approach to predict biological activity. The overall goal of this project was to use QSAR predictions to fill the data gaps in a larger environmental database of ~30K structures. The specific aim of the current work was to build QSAR models for multiple ToxCast assays using a subset of 1800 chemicals tested in 18 G-Protein Coupled Receptor (GPCR) assays. These assays are part of the aminergic category which was among the most active within the biochemical assays. Using PLSDA for the human histamine H1 GPCR assay, the classification accuracy reached 94% with a non-error rate of 89% in fitting and 80% in 5-fold CV, with only 2 latent variables. These results demonstrate the ability of QSAR models to predict bioactivity. ]]>
The EPA tested several thousand chemicals in 700 toxicity-related in-vitro HTS bioassays through the ToxCast and Tox21 projects. However, the chemical space of interest for environmental exposure is much wider than this set of chemicals. Thus, there is a need to fill data gaps with in-silico methods, and quantitative structure-activity relationships (QSARs) are a cost effective approach to predict biological activity. The overall goal of this project was to use QSAR predictions to fill the data gaps in a larger environmental database of ~30K structures. The specific aim of the current work was to build QSAR models for multiple ToxCast assays using a subset of 1800 chemicals tested in 18 G-Protein Coupled Receptor (GPCR) assays. These assays are part of the aminergic category which was among the most active within the biochemical assays. Using PLSDA for the human histamine H1 GPCR assay, the classification accuracy reached 94% with a non-error rate of 89% in fitting and 80% in 5-fold CV, with only 2 latent variables. These results demonstrate the ability of QSAR models to predict bioactivity. ]]> Fri, 24 Jun 2016 16:27:40 GMT /slideshow/insilico-study-of-toxcast-gpcr-assays-by-quantitative-structureactivity-relationships-qsars-modeling-presented-at-acs-2014-11-august-2014-san-francisco-usa-2014/63420687 captaindare@slideshare.net(captaindare) In-silico study of ToxCast GPCR assays by quantitative structure-activity relationships (QSARs) modeling. Presented at ACS 2014 11 August 2014, San Francisco, USA 2014 captaindare The EPA tested several thousand chemicals in 700 toxicity-related in-vitro HTS bioassays through the ToxCast and Tox21 projects. However, the chemical space of interest for environmental exposure is much wider than this set of chemicals. Thus, there is a need to fill data gaps with in-silico methods, and quantitative structure-activity relationships (QSARs) are a cost effective approach to predict biological activity. The overall goal of this project was to use QSAR predictions to fill the data gaps in a larger environmental database of ~30K structures. The specific aim of the current work was to build QSAR models for multiple ToxCast assays using a subset of 1800 chemicals tested in 18 G-Protein Coupled Receptor (GPCR) assays. These assays are part of the aminergic category which was among the most active within the biochemical assays. Using PLSDA for the human histamine H1 GPCR assay, the classification accuracy reached 94% with a non-error rate of 89% in fitting and 80% in 5-fold CV, with only 2 latent variables. These results demonstrate the ability of QSAR models to predict bioactivity. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/acs2014kamel-160624162740-thumbnail.jpg?width=120&amp;height=120&amp;fit=bounds" /><br> The EPA tested several thousand chemicals in 700 toxicity-related in-vitro HTS bioassays through the ToxCast and Tox21 projects. However, the chemical space of interest for environmental exposure is much wider than this set of chemicals. Thus, there is a need to fill data gaps with in-silico methods, and quantitative structure-activity relationships (QSARs) are a cost effective approach to predict biological activity. The overall goal of this project was to use QSAR predictions to fill the data gaps in a larger environmental database of ~30K structures. The specific aim of the current work was to build QSAR models for multiple ToxCast assays using a subset of 1800 chemicals tested in 18 G-Protein Coupled Receptor (GPCR) assays. These assays are part of the aminergic category which was among the most active within the biochemical assays. Using PLSDA for the human histamine H1 GPCR assay, the classification accuracy reached 94% with a non-error rate of 89% in fitting and 80% in 5-fold CV, with only 2 latent variables. These results demonstrate the ability of QSAR models to predict bioactivity.
In-silico study of ToxCast GPCR assays by quantitative structure-activity relationships (QSARs) modeling. Presented at ACS 2014 11 August 2014, San Francisco, USA 2014 from Kamel Mansouri
]]> 385 5 https://cdn.slidesharecdn.com/ss_thumbnails/acs2014kamel-160624162740-thumbnail.jpg?width=120&height=120&fit=bounds presentation 000000 http://activitystrea.ms/schema/1.0/post http://activitystrea.ms/schema/1.0/posted 0 The importance of data curation on QSAR Modeling: PHYSPROP open data as a case study. Presented at QSAR2016 Miami, FL 13-17, 2016 /slideshow/the-importance-of-data-curation-on-qsar-modeling-physprop-open-data-as-a-case-study-presented-at-qsar2016-miami-fl-1317-2016/63307610 qsar2016june1st2016ajwrsjrstar-160621192606
This presentation highlighted how data curation impacts the reliability of QSAR models. We examined key datasets related to environmental endpoints to validate across chemical structure representations (e.g., mol file and SMILES) and identifiers (chemical names and registry numbers), and approaches to standardize data into QSAR-ready formats prior to modeling procedures. This allowed us to quantify and segregate data into quality categories. This improved our ability to evaluate the resulting models that can be developed from these data slices, and to quantify to what extent efforts developing high-quality datasets have the expected pay-off in terms of predicting performance. The most accurate models that we build will be accessible via our public-facing platform and will be used for screening and prioritizing chemicals for further testing.]]>
This presentation highlighted how data curation impacts the reliability of QSAR models. We examined key datasets related to environmental endpoints to validate across chemical structure representations (e.g., mol file and SMILES) and identifiers (chemical names and registry numbers), and approaches to standardize data into QSAR-ready formats prior to modeling procedures. This allowed us to quantify and segregate data into quality categories. This improved our ability to evaluate the resulting models that can be developed from these data slices, and to quantify to what extent efforts developing high-quality datasets have the expected pay-off in terms of predicting performance. The most accurate models that we build will be accessible via our public-facing platform and will be used for screening and prioritizing chemicals for further testing.]]> Tue, 21 Jun 2016 19:26:06 GMT /slideshow/the-importance-of-data-curation-on-qsar-modeling-physprop-open-data-as-a-case-study-presented-at-qsar2016-miami-fl-1317-2016/63307610 captaindare@slideshare.net(captaindare) The importance of data curation on QSAR Modeling: PHYSPROP open data as a case study. Presented at QSAR2016 Miami, FL 13-17, 2016 captaindare This presentation highlighted how data curation impacts the reliability of QSAR models. We examined key datasets related to environmental endpoints to validate across chemical structure representations (e.g., mol file and SMILES) and identifiers (chemical names and registry numbers), and approaches to standardize data into QSAR-ready formats prior to modeling procedures. This allowed us to quantify and segregate data into quality categories. This improved our ability to evaluate the resulting models that can be developed from these data slices, and to quantify to what extent efforts developing high-quality datasets have the expected pay-off in terms of predicting performance. The most accurate models that we build will be accessible via our public-facing platform and will be used for screening and prioritizing chemicals for further testing. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/qsar2016june1st2016ajwrsjrstar-160621192606-thumbnail.jpg?width=120&amp;height=120&amp;fit=bounds" /><br> This presentation highlighted how data curation impacts the reliability of QSAR models. We examined key datasets related to environmental endpoints to validate across chemical structure representations (e.g., mol file and SMILES) and identifiers (chemical names and registry numbers), and approaches to standardize data into QSAR-ready formats prior to modeling procedures. This allowed us to quantify and segregate data into quality categories. This improved our ability to evaluate the resulting models that can be developed from these data slices, and to quantify to what extent efforts developing high-quality datasets have the expected pay-off in terms of predicting performance. The most accurate models that we build will be accessible via our public-facing platform and will be used for screening and prioritizing chemicals for further testing.
The importance of data curation on QSAR Modeling: PHYSPROP open data as a case study. Presented at QSAR2016 Miami, FL 13-17, 2016 from Kamel Mansouri
]]> 534 9 https://cdn.slidesharecdn.com/ss_thumbnails/qsar2016june1st2016ajwrsjrstar-160621192606-thumbnail.jpg?width=120&height=120&fit=bounds presentation 000000 http://activitystrea.ms/schema/1.0/post http://activitystrea.ms/schema/1.0/posted 0 EDSP Prioritization: Collaborative Estrogen Receptor Activity Prediction Project (CERAPP). Presented at SOT 2015, San Diego, CA, March 22 - 26, 2015. /slideshow/edsp-prioritization-collaborative-estrogen-receptor-activity-prediction-project-cerapp-presented-at-sot-2015-san-diego-ca-march-22-26-2015/62701011 kamelsot15cerapp-160603162745
Humans are potentially exposed to tens of thousands of man-made chemicals in the environment. It is well known that some environmental chemicals mimic natural hormones and thus have the potential to be endocrine disruptors. Most of these environmental chemicals have never been tested for their ability to disrupt the endocrine system, in particular, their ability to interact with the estrogen receptor. EPA needs tools to prioritize thousands of chemicals, for instance in the Endocrine Disruptor Screening Program (EDSP). This project was intended to be a demonstration of the use of predictive computational models on HTS data including ToxCast and Tox21 assays to prioritize a large chemical universe of 32464 unique structures for one specific molecular target the estrogen receptor. CERAPP combined multiple computational models for prediction of estrogen receptor activity, and used the predicted results to build a unique consensus model. Models were developed in collaboration between 17 groups in the U.S. and Europe and applied to predict the common set of chemicals. Structure-based techniques such as docking and several QSAR modeling approaches were employed, mostly using a common training set of 1677 compounds provided by U.S. EPA, to build a total of 42 classification models and 8 regression models for binding, agonist and antagonist activity. All predictions were evaluated on ToxCast data and on an external validation set collected from the literature. In order to overcome the limitations of single models, a consensus was built weighting models based on their prediction accuracy scores (including sensitivity and specificity against training and external sets). Individual model scores ranged from 0.69 to 0.85, showing high prediction reliabilities. The final consensus predicted 4001 chemicals as actives to be considered as high priority for further testing and 6742 as suspicious chemicals. This abstract does not necessarily reflect U.S. EPA policy]]>
Humans are potentially exposed to tens of thousands of man-made chemicals in the environment. It is well known that some environmental chemicals mimic natural hormones and thus have the potential to be endocrine disruptors. Most of these environmental chemicals have never been tested for their ability to disrupt the endocrine system, in particular, their ability to interact with the estrogen receptor. EPA needs tools to prioritize thousands of chemicals, for instance in the Endocrine Disruptor Screening Program (EDSP). This project was intended to be a demonstration of the use of predictive computational models on HTS data including ToxCast and Tox21 assays to prioritize a large chemical universe of 32464 unique structures for one specific molecular target the estrogen receptor. CERAPP combined multiple computational models for prediction of estrogen receptor activity, and used the predicted results to build a unique consensus model. Models were developed in collaboration between 17 groups in the U.S. and Europe and applied to predict the common set of chemicals. Structure-based techniques such as docking and several QSAR modeling approaches were employed, mostly using a common training set of 1677 compounds provided by U.S. EPA, to build a total of 42 classification models and 8 regression models for binding, agonist and antagonist activity. All predictions were evaluated on ToxCast data and on an external validation set collected from the literature. In order to overcome the limitations of single models, a consensus was built weighting models based on their prediction accuracy scores (including sensitivity and specificity against training and external sets). Individual model scores ranged from 0.69 to 0.85, showing high prediction reliabilities. The final consensus predicted 4001 chemicals as actives to be considered as high priority for further testing and 6742 as suspicious chemicals. This abstract does not necessarily reflect U.S. EPA policy]]> Fri, 03 Jun 2016 16:27:45 GMT /slideshow/edsp-prioritization-collaborative-estrogen-receptor-activity-prediction-project-cerapp-presented-at-sot-2015-san-diego-ca-march-22-26-2015/62701011 captaindare@slideshare.net(captaindare) EDSP Prioritization: Collaborative Estrogen Receptor Activity Prediction Project (CERAPP). Presented at SOT 2015, San Diego, CA, March 22 - 26, 2015. captaindare Humans are potentially exposed to tens of thousands of man-made chemicals in the environment. It is well known that some environmental chemicals mimic natural hormones and thus have the potential to be endocrine disruptors. Most of these environmental chemicals have never been tested for their ability to disrupt the endocrine system, in particular, their ability to interact with the estrogen receptor. EPA needs tools to prioritize thousands of chemicals, for instance in the Endocrine Disruptor Screening Program (EDSP). This project was intended to be a demonstration of the use of predictive computational models on HTS data including ToxCast and Tox21 assays to prioritize a large chemical universe of 32464 unique structures for one specific molecular target the estrogen receptor. CERAPP combined multiple computational models for prediction of estrogen receptor activity, and used the predicted results to build a unique consensus model. Models were developed in collaboration between 17 groups in the U.S. and Europe and applied to predict the common set of chemicals. Structure-based techniques such as docking and several QSAR modeling approaches were employed, mostly using a common training set of 1677 compounds provided by U.S. EPA, to build a total of 42 classification models and 8 regression models for binding, agonist and antagonist activity. All predictions were evaluated on ToxCast data and on an external validation set collected from the literature. In order to overcome the limitations of single models, a consensus was built weighting models based on their prediction accuracy scores (including sensitivity and specificity against training and external sets). Individual model scores ranged from 0.69 to 0.85, showing high prediction reliabilities. The final consensus predicted 4001 chemicals as actives to be considered as high priority for further testing and 6742 as suspicious chemicals. This abstract does not necessarily reflect U.S. EPA policy <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/kamelsot15cerapp-160603162745-thumbnail.jpg?width=120&amp;height=120&amp;fit=bounds" /><br> Humans are potentially exposed to tens of thousands of man-made chemicals in the environment. It is well known that some environmental chemicals mimic natural hormones and thus have the potential to be endocrine disruptors. Most of these environmental chemicals have never been tested for their ability to disrupt the endocrine system, in particular, their ability to interact with the estrogen receptor. EPA needs tools to prioritize thousands of chemicals, for instance in the Endocrine Disruptor Screening Program (EDSP). This project was intended to be a demonstration of the use of predictive computational models on HTS data including ToxCast and Tox21 assays to prioritize a large chemical universe of 32464 unique structures for one specific molecular target the estrogen receptor. CERAPP combined multiple computational models for prediction of estrogen receptor activity, and used the predicted results to build a unique consensus model. Models were developed in collaboration between 17 groups in the U.S. and Europe and applied to predict the common set of chemicals. Structure-based techniques such as docking and several QSAR modeling approaches were employed, mostly using a common training set of 1677 compounds provided by U.S. EPA, to build a total of 42 classification models and 8 regression models for binding, agonist and antagonist activity. All predictions were evaluated on ToxCast data and on an external validation set collected from the literature. In order to overcome the limitations of single models, a consensus was built weighting models based on their prediction accuracy scores (including sensitivity and specificity against training and external sets). Individual model scores ranged from 0.69 to 0.85, showing high prediction reliabilities. The final consensus predicted 4001 chemicals as actives to be considered as high priority for further testing and 6742 as suspicious chemicals. This abstract does not necessarily reflect U.S. EPA policy
EDSP Prioritization: Collaborative Estrogen Receptor Activity Prediction Project (CERAPP). Presented at SOT 2015, San Diego, CA, March 22 - 26, 2015. from Kamel Mansouri
]]> 128 6 https://cdn.slidesharecdn.com/ss_thumbnails/kamelsot15cerapp-160603162745-thumbnail.jpg?width=120&height=120&fit=bounds presentation 000000 http://activitystrea.ms/schema/1.0/post http://activitystrea.ms/schema/1.0/posted 0 CERAPP - Collaborative Estrogen Receptor Activity Prediction Project. Computational Toxicology Communities of Practice /slideshow/cerapp-collaborative-estrogen-receptor-activity-prediction-project-computational-toxicology-communities-of-practice/62700813 cerappconsensus-160603162114
U.S. Congress mandated that the EPA screen chemicals for their potential to be endocrine disruptors Led to development of the Endocrine Disruptor Screening Program (EDSP) Initial focus was on environmental estrogens, but program expanded to include androgens and thyroid pathway disruptors]]>
U.S. Congress mandated that the EPA screen chemicals for their potential to be endocrine disruptors Led to development of the Endocrine Disruptor Screening Program (EDSP) Initial focus was on environmental estrogens, but program expanded to include androgens and thyroid pathway disruptors]]> Fri, 03 Jun 2016 16:21:14 GMT /slideshow/cerapp-collaborative-estrogen-receptor-activity-prediction-project-computational-toxicology-communities-of-practice/62700813 captaindare@slideshare.net(captaindare) CERAPP - Collaborative Estrogen Receptor Activity Prediction Project. Computational Toxicology Communities of Practice captaindare U.S. Congress mandated that the EPA screen chemicals for their potential to be endocrine disruptors Led to development of the Endocrine Disruptor Screening Program (EDSP) Initial focus was on environmental estrogens, but program expanded to include androgens and thyroid pathway disruptors <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/cerappconsensus-160603162114-thumbnail.jpg?width=120&amp;height=120&amp;fit=bounds" /><br> U.S. Congress mandated that the EPA screen chemicals for their potential to be endocrine disruptors Led to development of the Endocrine Disruptor Screening Program (EDSP) Initial focus was on environmental estrogens, but program expanded to include androgens and thyroid pathway disruptors
CERAPP - Collaborative Estrogen Receptor Activity Prediction Project. Computational Toxicology Communities of Practice from Kamel Mansouri
]]> 198 7 https://cdn.slidesharecdn.com/ss_thumbnails/cerappconsensus-160603162114-thumbnail.jpg?width=120&height=120&fit=bounds presentation 000000 http://activitystrea.ms/schema/1.0/post http://activitystrea.ms/schema/1.0/posted 0 An examination of data quality on QSAR Modeling in regards to the environmental sciences. Presented at UNC-CH Talk, Chapel Hill, NC, April 12, 2016. /slideshow/an-examination-of-data-quality-on-qsar-modeling-in-regards-to-the-environmental-sciences-presented-at-uncch-talk-chapel-hill-nc-april-12-2016/62697606 dashboardandepisuitekmfinal-160603144159
The development of QSAR models is critically dependent on the quality of available data. As part of our efforts to develop public platforms to provide access to predictive models, we have attempted to discriminate the influence of the quality versus quantity of data available to develop and validate QSAR models. We have focused our efforts on the widely used EPISuite software that was initially developed over two decades ago and, specifically, on the PHYSPROP dataset used to train the EPISuite prediction models. This presentation will review our approaches to examining key datasets, the delivery of curated data and the development of machine-learning models for thirteen separate property endpoints of interest to environmental science. We will also review how these data will be made freely accessible to the community via a new chemistry dashboard. This abstract does not reflect U.S. EPA policy.]]>
The development of QSAR models is critically dependent on the quality of available data. As part of our efforts to develop public platforms to provide access to predictive models, we have attempted to discriminate the influence of the quality versus quantity of data available to develop and validate QSAR models. We have focused our efforts on the widely used EPISuite software that was initially developed over two decades ago and, specifically, on the PHYSPROP dataset used to train the EPISuite prediction models. This presentation will review our approaches to examining key datasets, the delivery of curated data and the development of machine-learning models for thirteen separate property endpoints of interest to environmental science. We will also review how these data will be made freely accessible to the community via a new chemistry dashboard. This abstract does not reflect U.S. EPA policy.]]> Fri, 03 Jun 2016 14:41:59 GMT /slideshow/an-examination-of-data-quality-on-qsar-modeling-in-regards-to-the-environmental-sciences-presented-at-uncch-talk-chapel-hill-nc-april-12-2016/62697606 captaindare@slideshare.net(captaindare) An examination of data quality on QSAR Modeling in regards to the environmental sciences. Presented at UNC-CH Talk, Chapel Hill, NC, April 12, 2016. captaindare The development of QSAR models is critically dependent on the quality of available data. As part of our efforts to develop public platforms to provide access to predictive models, we have attempted to discriminate the influence of the quality versus quantity of data available to develop and validate QSAR models. We have focused our efforts on the widely used EPISuite software that was initially developed over two decades ago and, specifically, on the PHYSPROP dataset used to train the EPISuite prediction models. This presentation will review our approaches to examining key datasets, the delivery of curated data and the development of machine-learning models for thirteen separate property endpoints of interest to environmental science. We will also review how these data will be made freely accessible to the community via a new chemistry dashboard. This abstract does not reflect U.S. EPA policy. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/dashboardandepisuitekmfinal-160603144159-thumbnail.jpg?width=120&amp;height=120&amp;fit=bounds" /><br> The development of QSAR models is critically dependent on the quality of available data. As part of our efforts to develop public platforms to provide access to predictive models, we have attempted to discriminate the influence of the quality versus quantity of data available to develop and validate QSAR models. We have focused our efforts on the widely used EPISuite software that was initially developed over two decades ago and, specifically, on the PHYSPROP dataset used to train the EPISuite prediction models. This presentation will review our approaches to examining key datasets, the delivery of curated data and the development of machine-learning models for thirteen separate property endpoints of interest to environmental science. We will also review how these data will be made freely accessible to the community via a new chemistry dashboard. This abstract does not reflect U.S. EPA policy.
An examination of data quality on QSAR Modeling in regards to the environmental sciences. Presented at UNC-CH Talk, Chapel Hill, NC, April 12, 2016. from Kamel Mansouri
]]> 256 7 https://cdn.slidesharecdn.com/ss_thumbnails/dashboardandepisuitekmfinal-160603144159-thumbnail.jpg?width=120&height=120&fit=bounds presentation 000000 http://activitystrea.ms/schema/1.0/post http://activitystrea.ms/schema/1.0/posted 0 In-silico structure activity relationship study of toxicity endpoints by QSAR modeling. Presented at SOT 2014, Phoenix, AZ, March 23 - 27, 2014. /slideshow/insilico-structure-activity-relationship-study-of-toxicity-endpoints-by-qsar-modeling/62697183 kmansourisotposterv3-160603143038
Several thousand chemicals were tested in hundreds of toxicity-related in-vitro high-throughput screening (HTS) bioassays through the EPAs ToxCast and Tox21 projects. However, this chemical set only covers a portion of the chemical space of interest for environmental risk assessment, leading to a need to fill data gaps with other methods. A cost effective and reliable approach to fullfill this task is to build quantitative structure-activity relationships (QSARs). In this work, a subset of 1877 chemicals from ToxCast were used to build QSAR models. These models will be applied to predict values for multiple ToxCast assays in a larger environmental database of ~30K chemical structures. Based on a clustering study by Sipes et al. (2013), the initial molecular targets of this effort consisted of a set of 18 NovaScreen G-protein coupled receptor (GPCR) assays. These assays are part of the aminergic category that showed the highest number of actives within the ToxCast portfolio. Classification methods including SOM, SVM, PLSDA and kNN, were tested. These methods were coupled to variable selection techniques such as genetic algorithms that were applied in order to select the best representative molecular descriptors based on statistical fitness functions. The obtained models were validated and their prediction ability measured. The models that showed good results will be applied within the limits of their established chemical space defined by the applicability domain.]]>
Several thousand chemicals were tested in hundreds of toxicity-related in-vitro high-throughput screening (HTS) bioassays through the EPAs ToxCast and Tox21 projects. However, this chemical set only covers a portion of the chemical space of interest for environmental risk assessment, leading to a need to fill data gaps with other methods. A cost effective and reliable approach to fullfill this task is to build quantitative structure-activity relationships (QSARs). In this work, a subset of 1877 chemicals from ToxCast were used to build QSAR models. These models will be applied to predict values for multiple ToxCast assays in a larger environmental database of ~30K chemical structures. Based on a clustering study by Sipes et al. (2013), the initial molecular targets of this effort consisted of a set of 18 NovaScreen G-protein coupled receptor (GPCR) assays. These assays are part of the aminergic category that showed the highest number of actives within the ToxCast portfolio. Classification methods including SOM, SVM, PLSDA and kNN, were tested. These methods were coupled to variable selection techniques such as genetic algorithms that were applied in order to select the best representative molecular descriptors based on statistical fitness functions. The obtained models were validated and their prediction ability measured. The models that showed good results will be applied within the limits of their established chemical space defined by the applicability domain.]]> Fri, 03 Jun 2016 14:30:38 GMT /slideshow/insilico-structure-activity-relationship-study-of-toxicity-endpoints-by-qsar-modeling/62697183 captaindare@slideshare.net(captaindare) In-silico structure activity relationship study of toxicity endpoints by QSAR modeling. Presented at SOT 2014, Phoenix, AZ, March 23 - 27, 2014. captaindare Several thousand chemicals were tested in hundreds of toxicity-related in-vitro high-throughput screening (HTS) bioassays through the EPAs ToxCast and Tox21 projects. However, this chemical set only covers a portion of the chemical space of interest for environmental risk assessment, leading to a need to fill data gaps with other methods. A cost effective and reliable approach to fullfill this task is to build quantitative structure-activity relationships (QSARs). In this work, a subset of 1877 chemicals from ToxCast were used to build QSAR models. These models will be applied to predict values for multiple ToxCast assays in a larger environmental database of ~30K chemical structures. Based on a clustering study by Sipes et al. (2013), the initial molecular targets of this effort consisted of a set of 18 NovaScreen G-protein coupled receptor (GPCR) assays. These assays are part of the aminergic category that showed the highest number of actives within the ToxCast portfolio. Classification methods including SOM, SVM, PLSDA and kNN, were tested. These methods were coupled to variable selection techniques such as genetic algorithms that were applied in order to select the best representative molecular descriptors based on statistical fitness functions. The obtained models were validated and their prediction ability measured. The models that showed good results will be applied within the limits of their established chemical space defined by the applicability domain. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/kmansourisotposterv3-160603143038-thumbnail.jpg?width=120&amp;height=120&amp;fit=bounds" /><br> Several thousand chemicals were tested in hundreds of toxicity-related in-vitro high-throughput screening (HTS) bioassays through the EPAs ToxCast and Tox21 projects. However, this chemical set only covers a portion of the chemical space of interest for environmental risk assessment, leading to a need to fill data gaps with other methods. A cost effective and reliable approach to fullfill this task is to build quantitative structure-activity relationships (QSARs). In this work, a subset of 1877 chemicals from ToxCast were used to build QSAR models. These models will be applied to predict values for multiple ToxCast assays in a larger environmental database of ~30K chemical structures. Based on a clustering study by Sipes et al. (2013), the initial molecular targets of this effort consisted of a set of 18 NovaScreen G-protein coupled receptor (GPCR) assays. These assays are part of the aminergic category that showed the highest number of actives within the ToxCast portfolio. Classification methods including SOM, SVM, PLSDA and kNN, were tested. These methods were coupled to variable selection techniques such as genetic algorithms that were applied in order to select the best representative molecular descriptors based on statistical fitness functions. The obtained models were validated and their prediction ability measured. The models that showed good results will be applied within the limits of their established chemical space defined by the applicability domain.
In-silico structure activity relationship study of toxicity endpoints by QSAR modeling. Presented at SOT 2014, Phoenix, AZ, March 23 - 27, 2014. from Kamel Mansouri
]]> 233 9 https://cdn.slidesharecdn.com/ss_thumbnails/kmansourisotposterv3-160603143038-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post http://activitystrea.ms/schema/1.0/posted 0 The influence of data curation on QSAR Modeling Presented at American Chemical Society, San Diego, CA, March 13 - 17, 2016. /slideshow/the-influence-of-data-curation-on-qsar-modeling-examining-issues-of-quality-versus-quantity-of-data-62442493/62442493 acsmppg124arichard1-160526200922
This presentation examined the impact of data quality on the construction of QSAR models being developed within the EPAs National Center for Computational Toxicology. We have developed a public-facing platform to provide access to predictive models. As part of the work we have attempted to disentangle the influence of the quality versus quantity of data available to develop and validate QSAR models. This abstract does not reflect U.S. EPA policy.]]>
This presentation examined the impact of data quality on the construction of QSAR models being developed within the EPAs National Center for Computational Toxicology. We have developed a public-facing platform to provide access to predictive models. As part of the work we have attempted to disentangle the influence of the quality versus quantity of data available to develop and validate QSAR models. This abstract does not reflect U.S. EPA policy.]]> Thu, 26 May 2016 20:09:22 GMT /slideshow/the-influence-of-data-curation-on-qsar-modeling-examining-issues-of-quality-versus-quantity-of-data-62442493/62442493 captaindare@slideshare.net(captaindare) The influence of data curation on QSAR Modeling Presented at American Chemical Society, San Diego, CA, March 13 - 17, 2016. captaindare This presentation examined the impact of data quality on the construction of QSAR models being developed within the EPAs National Center for Computational Toxicology. We have developed a public-facing platform to provide access to predictive models. As part of the work we have attempted to disentangle the influence of the quality versus quantity of data available to develop and validate QSAR models. This abstract does not reflect U.S. EPA policy. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/acsmppg124arichard1-160526200922-thumbnail.jpg?width=120&amp;height=120&amp;fit=bounds" /><br> This presentation examined the impact of data quality on the construction of QSAR models being developed within the EPAs National Center for Computational Toxicology. We have developed a public-facing platform to provide access to predictive models. As part of the work we have attempted to disentangle the influence of the quality versus quantity of data available to develop and validate QSAR models. This abstract does not reflect U.S. EPA policy.
The influence of data curation on QSAR Modeling Presented at American Chemical Society, San Diego, CA, March 13 - 17, 2016. from Kamel Mansouri
]]> 512 10 https://cdn.slidesharecdn.com/ss_thumbnails/acsmppg124arichard1-160526200922-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post http://activitystrea.ms/schema/1.0/posted 0 https://cdn.slidesharecdn.com/profile-photo-captaindare-48x48.jpg?cb=1655238795 - Computational Chemist/Toxicologist - Expert in chemoinformatics tools and data mining - Expert in QSAR/QSPR and ADME-Tox properties modeling - Deep knowledge of chemicals risk assessment - Excellent programming skills - Creative in developing and applying novel machine learning algorithms - Deep knowledge of molecular modeling and computer aided drug design - Excellent communication skills - Personal attributes: creativity, leadership, problem solving, integrity, work ethics and diplomacy. http://orcid.org/0000-0002-6426-8036 https://cdn.slidesharecdn.com/ss_thumbnails/1004mansouri-210827211850-thumbnail.jpg?width=320&height=320&fit=bounds slideshow/opera-an-open-source-and-open-data-suite-of-qsar-models/250066358 OPERA, AN OPEN SOURCE ... https://cdn.slidesharecdn.com/ss_thumbnails/euroqsar18km-180927161240-thumbnail.jpg?width=320&height=320&fit=bounds slideshow/international-computational-collaborations-to-solve-toxicology-problems/116919692 International Computat... https://cdn.slidesharecdn.com/ss_thumbnails/workflowsacs2018final-180325214829-thumbnail.jpg?width=320&height=320&fit=bounds captaindare/automated-workflows-for-data-curation-and-standardization-of-chemical-structures-for-qsar-modeling-acs-2018-new-orleans-usa Automated workflows fo...