CoMPARA: Collaborative Modeling Project for Androgen Receptor Activity

Mansouri, Kamel; Kleinstreuer, Nicole; Abdelaziz, Ahmed; Alberga, Domenico; Alves, Vinícius M.; Andersson, Patrik L.; Andrade, Carolina Horta; Bai, Fang; Balabin, Ilya A.; Ballabio, Davide; Benfenati, Emilio; Bhhatarai, Barun; Boyer, Scott; Chen, Jingwen; Consonni, Viviana; Farag, Sherif; Fourches, Denis; García-Sosa, Alfonso T.; Gramatica, Paola; Grisoni, Francesca; Grulke, Christopher M.; Hong, Huixiao; Horvath, Dragos; Hu, Xin; Huang, Ruili; Jeliazkova, Nina; Li, Jiazhong; Li, Xuehua; Liu, Huanxiang; Manganelli, Serena; Mangiatordi, Giuseppe Felice; Maran, Uko; Marcou, Gilles; Martin, Todd M.; Muratov, Eugene; Nguyễn, Ðắc-Trung; Nicolotti, Orazio; Nikolov, Nikolai Georgiev; Norinder, Ulf; Papa, Ester; Petitjean, Michel; Piir, Geven; Pogodin, Pavel V.; Poroikov, Vladimir; Qiao, Xianliang; Richard, Ann M.; Roncaglioni, Alessandra; Ruíz, Patricia; Rupakheti, Chetan; Sakkiah, Sugunadevi; Sangion, Alessandro; Schramm, Karl‐Werner; Selvaraj, Chandrabose; Shah, Imran; Sild, Sulev; Sun, Lixia; Taboureau, Olivier; Tang, Yun; Tetko, Igor V.; Todeschini, Roberto; Tong, Weida; Trisciuzzi, Daniela; Tropsha, Alexander; Driessche, George Van Den; Varnek, Alexandre; Wang, Zhongyu; Wedebye, Eva Bay; Williams, Antony J.; Xie, Hong-Bin; Zakharov, Alexey; Zheng, Ziye; Judson, Richard S.

doi:10.1289/ehp5580

Cited by 151 publications

(149 citation statements)

References 85 publications

Supporting

Mentioning

145

Contrasting

Order By: Relevance

“…Since set-up and reported performance measures differ from this CP study, they can not directly be compared. Very recently, CoMPARA, an extensive study on androgen receptor modelling, was published by Mansouri et al [55]. Scientists from 25 research groups have contributed to consensus models for androgen receptor binding, agonism, and antagonism with a predictive accuracy of 78% for the AA evaluation set (which is in the same range as the CP accuracy (SCP) obtained for the original Know-Tox-AA model, see Table 3).…”

Section: Conformal Predictors-validation Of Aa Modelmentioning

confidence: 99%

KnowTox: pipeline and case study for confident prediction of potential toxic effects of compounds in early phases of development

Morger¹,

Mathea²,

Achenbach³

et al. 2020

J Cheminform

View full text Add to dashboard Cite

Risk assessment of newly synthesised chemicals is a prerequisite for regulatory approval. In this context, in silico methods have great potential to reduce time, cost, and ultimately animal testing as they make use of the ever-growing amount of available toxicity data. Here, KnowTox is presented, a novel pipeline that combines three different in silico toxicology approaches to allow for confident prediction of potentially toxic effects of query compounds, i.e. machine learning models for 88 endpoints, alerts for 919 toxic substructures, and computational support for read-across. It is mainly based on the ToxCast dataset, containing after preprocessing a sparse matrix of 7912 compounds tested against 985 endpoints. When applying machine learning models, applicability and reliability of predictions for new chemicals are of utmost importance. Therefore, first, the conformal prediction technique was deployed, comprising an additional calibration step and per definition creating internally valid predictors at a given significance level. Second, to further improve validity and information efficiency, two adaptations are suggested, exemplified at the androgen receptor antagonism endpoint. An absolute increase in validity of 23% on the in-house dataset of 534 compounds could be achieved by introducing KNNRegressor normalisation. This increase in validity comes at the cost of efficiency, which could again be improved by 20% for the initial ToxCast model by balancing the dataset during model training. Finally, the value of the developed pipeline for risk assessment is discussed using two in-house triazole molecules. Compared to a single toxicity prediction method, complementing the outputs of different approaches can have a higher impact on guiding toxicity testing and de-selecting most likely harmful development-candidate compounds early in the development process.

show abstract

Section: Conformal Predictors-validation Of Aa Modelmentioning

confidence: 99%

KnowTox: pipeline and case study for confident prediction of potential toxic effects of compounds in early phases of development

Morger¹,

Mathea²,

Achenbach³

et al. 2020

J Cheminform

View full text Add to dashboard Cite

show abstract

“…EDCs modulate hormone receptors and affect the production, storage and uptake of hormones, or the action of a hormone within a specific target tissue or organ (Lee et al, 2018). There are numerous known or suspected EDCs present in aquatic environments, with sewage treatment plant (STP) effluent being a major environmental source (Xu et al, 2015;Mansouri et al, 2020). Domestic STP effluents may contain mixtures of EDCs, such as natural (17β-estradiol, estrone and estriol) and synthetic estrogens (17α-ethinylestradiol, alkylphenol ethoxylates and bisphenol A) (Gorelick et al, 2014).…”

Section: Introductionmentioning

confidence: 99%

“…This study investigated the toxicity effects of eight EDCs on embryonic-larval zebrafish development: estrone (E1), 17ß-estradiol (E2), 17α-ethynylestradiol (EE2), estriol (E3), triclosan (TCS), p-(tertoctyl) phenol (POP), bisphenol A (BPA) and 9,9-bis(4-hydroxyphenyl) fluorene (BHPF). EDCs may trigger a range of pathological characteristics and phenotypic malformations due to their different target molecules and effector organs, though they all have similarly estrogenic effects (Mansouri et al, 2020;Moreman et al, 2017). Therefore, it is possible to reveal toxicity mechanisms according to their different targets or action receptors.…”

Section: Introductionmentioning

confidence: 99%

Identification of receptors for eight endocrine disrupting chemicals and their underlying mechanisms using zebrafish as a model organism

Huang

Lin

et al. 2020

Ecotoxicology and Environmental Safety

View full text Add to dashboard Cite

Herein, eight common endocrine disrupting chemicals (EDCs) were exposed to zebrafish (Danio rerio) to investigate the relationship between different EDCs and their activated estrogen receptors. Under acute exposure, we identified five major malformation types whose incidence and deformity modes differed among EDCs. Luciferase analysis divided the EDC receptors into four categories: (i) triclosan (TCS), 17ß-estradiol (E2) and estriol (E3) mainly activated GPER expression; (ii) bisphenol A (BPA), p-(tert-octyl) phenol (POP), 17α-ethynylestradiol (EE2), E2 and E3 activated ERβ expression; (iii) E2 and E3 acted on both GPER and ERβ; and (iv) estrone (E1) and 9,9-bis(4-hydroxyphenyl)fluorene (BHPF) had little effect on the two receptors. In vivo immunofluorescence experiments on 96-hpf larvae provided evidence that TCS and POP acted on GPER and ERβ, respectively, while E2 acted on the two receptors simultaneously. Luciferase activities in the promoter regions of gper (À 986 to À 488) and erβ (À 1998 to À 1496) were higher than those in other regions, identifying these key regions as targets for transcription activity. TCS promoted GPER expression by acting on the JUND transcription factor, while POP promoted ERβ expression by activating the Foxl1 transcription factor. In contrast, E2 mainly regulated transcription of GPER and ERβ by Arid3a. These findings provide compelling evidence that different EDCs possess varying estrogen receptors, leading to differential regulatory pathways and abnormality symptoms. These results offer an experimental strategy and fundamental information to assess the molecular mechanisms of EDC-induced estrogen effects.

show abstract

“…A comparative study of the first version of the GUSAR program and CoMFA, CoMSIA, Golpe/GRID, HQSAR, and other widely used methods to construct QSAR models demonstrated the advantages of our approach [25]. Recently, in the Collaborative Modeling Project for Androgen Receptor Activity (CoMPARA), GUSAR estimations were shown to be very good [41].…”

Section: Gusarmentioning

confidence: 88%

Computational Approaches to Identify a Hidden Pharmacological Potential in Large Chemical Libraries

Druzhilovskiy

Stolbov

Savosina

et al. 2020

JSFI

View full text Add to dashboard Cite

To improve the discovery of more effective and less toxic pharmaceutical agents, large virtual repositories of synthesizable molecules have been generated to increase the explored chemicalpharmacological space diversity. Such libraries include billions of structural formulae of druglike molecules associated with data on synthetic schemes, required building blocks, estimated physical-chemical parameters, etc. Clearly, such repositories are "Big Data". Thus, to identify the most promising compounds with the required pharmacological properties (hits) among billions of available opportunities, special computational methods are necessary. We have proposed using a combined computational approach, which combines structural similarity assessment, machine learning, and molecular modeling. Our approach has been validated in a project aimed at finding new pharmaceutical agents against HIV/AIDS and associated comorbidities from the Synthetically Accessible Virtual Inventory (SAVI), a 1.75 billion compound database. Potential inhibitors of HIV-1 protease and reverse transcriptase and agonists of toll-like receptors and STING, affecting innate immunity, were computationally identified. The activity of the three synthesized compounds has been confirmed in a cell-based assay. These compounds belong to the chemical classes, in which the agonistic effect on TLR 7/8 had not been previously shown. Synthesis and biological testing of several dozens of compounds with predicted antiretroviral activity are currently taking place at the NCI/NIH. We also carried out virtual screening among one billion substances to find compounds potentially possessing anti-SARS-CoV-2 activity. The selected hits' information has been accepted by the European Initiative "JEDI Grand Challenge against COVID-19" for synthesis and further biological evaluation. The possibilities and limitations of the approach are discussed.

show abstract

CoMPARA: Collaborative Modeling Project for Androgen Receptor Activity

Cited by 151 publications

References 85 publications

KnowTox: pipeline and case study for confident prediction of potential toxic effects of compounds in early phases of development

KnowTox: pipeline and case study for confident prediction of potential toxic effects of compounds in early phases of development

Identification of receptors for eight endocrine disrupting chemicals and their underlying mechanisms using zebrafish as a model organism

Computational Approaches to Identify a Hidden Pharmacological Potential in Large Chemical Libraries

Contact Info

Product

Resources

About