DC Field | Value | Language |
---|---|---|
dc.contributor.author | Shin, Moonshik | ko |
dc.contributor.author | Jang, Dongjin | ko |
dc.contributor.author | Nam, Hojung | ko |
dc.contributor.author | Lee, Kwang-Hyung | ko |
dc.contributor.author | Lee, Doheon | ko |
dc.date.accessioned | 2018-05-23T06:31:08Z | - |
dc.date.available | 2018-05-23T06:31:08Z | - |
dc.date.created | 2016-12-27 | - |
dc.date.created | 2016-12-27 | - |
dc.date.issued | 2018-03 | - |
dc.identifier.citation | IEEE-ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS, v.15, no.2, pp.432 - 440 | - |
dc.identifier.issn | 1545-5963 | - |
dc.identifier.uri | http://hdl.handle.net/10203/241539 | - |
dc.description.abstract | The human colorectal carcinoma cell line (Caco-2) is a commonly used in-vitro test that predicts the absorption potential of orally administered drugs. In-silico prediction methods, based on the Caco-2 assay data, may increase the effectiveness of the high-throughput screening of new drug candidates. However, previously developed in-silico models that predict the Caco-2 cellular permeability of chemical compounds use handcrafted features that may be dataset-specific and induce over-fitting problems. Deep Neural Network (DNN) generates high-level features based on non-linear transformations for raw features, which provides high discriminant power and, therefore, creates a good generalized model. We present a DNNbased binary Caco-2 permeability classifier. Our model was constructed based on 663 chemical compounds with in-vitro Caco-2 apparent permeability data. 209 molecular descriptors are used for generating the high-level features during DNN model generation. Dropout regularization is applied to solve the over-fitting problem and the non-linear activation. The Rectified Linear Unit (ReLU) is adopted to reduce the vanishing gradient problem. The results demonstrate that the high-level features generated by the DNN are more robust than handcrafted features for predicting the cellular permeability of structurally diverse chemical compounds in Caco-2 cell lines. | - |
dc.language | English | - |
dc.publisher | IEEE COMPUTER SOC | - |
dc.subject | DRUG DISCOVERY | - |
dc.subject | GASTROINTESTINAL ABSORPTION | - |
dc.subject | ORAL BIOAVAILABILITY | - |
dc.subject | CACO-2 MONOLAYERS | - |
dc.subject | NEURAL-NETWORKS | - |
dc.subject | ADME EVALUATION | - |
dc.subject | IN-SILICO | - |
dc.subject | PERMEABILITY | - |
dc.subject | MOLECULES | - |
dc.subject | TRANSPORT | - |
dc.title | Predicting the Absorption Potential of Chemical Compounds through a Deep Learning Approach | - |
dc.type | Article | - |
dc.identifier.wosid | 000428936900010 | - |
dc.identifier.scopusid | 2-s2.0-85044928925 | - |
dc.type.rims | ART | - |
dc.citation.volume | 15 | - |
dc.citation.issue | 2 | - |
dc.citation.beginningpage | 432 | - |
dc.citation.endingpage | 440 | - |
dc.citation.publicationname | IEEE-ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS | - |
dc.identifier.doi | 10.1109/TCBB.2016.2535233 | - |
dc.contributor.localauthor | Lee, Kwang-Hyung | - |
dc.contributor.localauthor | Lee, Doheon | - |
dc.contributor.nonIdAuthor | Nam, Hojung | - |
dc.description.isOpenAccess | N | - |
dc.type.journalArticle | Article; Proceedings Paper | - |
dc.subject.keywordAuthor | Machine learning | - |
dc.subject.keywordAuthor | deep learning | - |
dc.subject.keywordAuthor | neural nets | - |
dc.subject.keywordAuthor | Caco-2 permeability | - |
dc.subject.keywordAuthor | absorption prediction | - |
dc.subject.keywordPlus | DRUG DISCOVERY | - |
dc.subject.keywordPlus | GASTROINTESTINAL ABSORPTION | - |
dc.subject.keywordPlus | ORAL BIOAVAILABILITY | - |
dc.subject.keywordPlus | CACO-2 MONOLAYERS | - |
dc.subject.keywordPlus | NEURAL-NETWORKS | - |
dc.subject.keywordPlus | ADME EVALUATION | - |
dc.subject.keywordPlus | IN-SILICO | - |
dc.subject.keywordPlus | PERMEABILITY | - |
dc.subject.keywordPlus | MOLECULES | - |
dc.subject.keywordPlus | TRANSPORT | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.