Mostrar el registro sencillo del ítem
dc.contributor.author | Jimenez-Carretero, Daniel | |
dc.contributor.author | Abrishami, Vahid | |
dc.contributor.author | Fernandez-de-Manuel, Laura | |
dc.contributor.author | Palacios, Irene | |
dc.contributor.author | Quilez-Alvarez, Antonio | |
dc.contributor.author | Diez-Sanchez, Alberto | |
dc.contributor.author | del Pozo, Miguel Angel | |
dc.contributor.author | Montoya, Maria | |
dc.date.accessioned | 2019-02-07T13:51:09Z | |
dc.date.available | 2019-02-07T13:51:09Z | |
dc.date.issued | 2018 | |
dc.identifier.citation | PLoS Comput Biol. 2018; 14(11):e1006238 | es_ES |
dc.identifier.issn | 1553-7358 | es_ES |
dc.identifier.uri | http://hdl.handle.net/20.500.12105/7142 | |
dc.description.abstract | Toxicity is an important factor in failed drug development, and its efficient identification and prediction is a major challenge in drug discovery. We have explored the potential of microscopy images of fluorescently labeled nuclei for the prediction of toxicity based on nucleus pattern recognition. Deep learning algorithms obtain abstract representations of images through an automated process, allowing them to efficiently classify complex patterns, and have become the state-of-the art in machine learning for computer vision. Here, deep convolutional neural networks (CNN) were trained to predict toxicity from images of DAPI-stained cells pre-treated with a set of drugs with differing toxicity mechanisms. Different cropping strategies were used for training CNN models, the nuclei-cropping-based Tox_CNN model outperformed other models classifying cells according to health status. Tox_CNN allowed automated extraction of feature maps that clustered compounds according to mechanism of action. Moreover, fully automated region-based CNNs (RCNN) were implemented to detect and classify nuclei, providing per-cell toxicity prediction from raw screening images. We validated both Tox_(R)CNN models for detection of pre-lethal toxicity from nuclei images, which proved to be more sensitive and have broader specificity than established toxicity readouts. These models predicted toxicity of drugs with mechanisms of action other than those they had been trained for and were successfully transferred to other cell assays. The Tox_(R)CNN models thus provide robust, sensitive, and cost-effective tools for in vitro screening of drug-induced toxicity. These models can be adopted for compound prioritization in drug screening campaigns, and could thereby increase the efficiency of drug discovery. | es_ES |
dc.description.sponsorship | This study was supported by grants BIO2014-62200-EXP and PI16/02132 from the Spanish Ministry of Science, Innovation and Universities (http://www.ciencia.gob.es/portal/site/ MICINN/), and from the European Union’s Horizon 2020 research and innovation programme under the Marie Sklodowska-Curie grant agreement No 641639 (https://ec.europa.eu/programmes/ horizon2020/) to MCM. ADS received a fellowship from La Caixa Foundation (https:// obrasociallacaixa.org/es/). AQA was supported by a Marie Curie Initial Training Network (ITN) “BIOPOL” No 641639 (https://ec.europa.eu/ programmes/horizon2020/). Work in the MAdP laboratory was supported by grants SAF201451876-R and SAF2017-83130-R from the Spanish Ministry of Science, Innovation and Universities (http://www.ciencia.gob.es/portal/site/MICINN/) and grant 15-0404 from Worldwide Cancer Research (https://www.worldwidecancerresearch. org/) and the European Union’s Horizon 2020 research and innovation programme under the Marie Sklodowska-Curie grant agreement No 641639 (https://ec.europa.eu/programmes/ horizon2020/). The CNIC is supported by the Spanish Ministry of Science, Innovation and Universities (http://www.ciencia.gob.es/portal/site/ MICINN/) and the Pro CNIC Foundation (https:// www.fundacionprocnic.es/fundacion.php), and is a Severo Ochoa Center of Excellence (SEV-20150505) | es_ES |
dc.language.iso | eng | es_ES |
dc.type.hasVersion | VoR | es_ES |
dc.rights.uri | http://creativecommons.org/licenses/by/4.0/ | * |
dc.title | Tox_(R)CNN: Deep learning-based nuclei profiling tool for drug toxicity screening | es_ES |
dc.type | journal article | es_ES |
dc.rights.license | Atribución 4.0 Internacional | * |
dc.identifier.pubmedID | 30500821 | es_ES |
dc.format.volume | 14 | es_ES |
dc.format.number | 11 | es_ES |
dc.format.page | e1006238 | es_ES |
dc.identifier.doi | 10.1371/journal.pcbi.1006238 | es_ES |
dc.contributor.funder | Ministerio de Ciencia, Innovación y Universidades (España) | |
dc.contributor.funder | Unión Europea. Comisión Europea | |
dc.contributor.funder | Fundación ProCNIC | |
dc.contributor.funder | Worldwide Cancer Research | |
dc.contributor.funder | Fundación La Caixa | |
dc.description.peerreviewed | Sí | es_ES |
dc.identifier.e-issn | 1553-7358 | es_ES |
dc.relation.publisherversion | https://doi.org/10.1371/journal.pcbi.1006238 | es_ES |
dc.identifier.journal | PLoS computational biology | es_ES |
dc.repisalud.orgCNIC | CNIC::Grupos de investigación::Señalización por Integrinas | es_ES |
dc.repisalud.orgCNIC | CNIC::Unidades técnicas::Celómica | es_ES |
dc.repisalud.institucion | CNIC | es_ES |
dc.relation.projectID | info:eu-repo/grantAgreement/EC/H2020/641639 | es_ES |
dc.relation.projectID | info:eu-repo/grantAgreement/ES/SEV-2015-0505 | es_ES |
dc.relation.projectID | info:eu-repo/grantAgreement/ES/BIO2014-62200-EXP | es_ES |
dc.relation.projectID | info:eu-repo/grantAgreement/ES/SAF201-451876-R | es_ES |
dc.relation.projectID | info:eu-repo/grantAgreement/ES/SAF2017-83130-R | es_ES |
dc.rights.accessRights | open access | es_ES |