Show simple item record

dc.contributor.authorKarim, Abdul
dc.contributor.authorMishra, Avinash
dc.contributor.authorNewton, MA Hakim
dc.contributor.authorSattar, Abdul
dc.date.accessioned2019-09-10T02:40:32Z
dc.date.available2019-09-10T02:40:32Z
dc.date.issued2019
dc.identifier.issn2470-1343
dc.identifier.doi10.1021/acsomega.8b03173
dc.identifier.urihttp://hdl.handle.net/10072/387156
dc.description.abstractToxicity prediction of chemical compounds is a grand challenge. Lately, it achieved significant progress in accuracy but using a huge set of features, implementing a complex blackbox technique such as a deep neural network, and exploiting enormous computational resources. In this paper, we strongly argue for the models and methods that are simple in machine learning characteristics, efficient in computing resource usage, and powerful to achieve very high accuracy levels. To demonstrate this, we develop a single task-based chemical toxicity prediction framework using only 2D features that are less compute intensive. We effectively use a decision tree to obtain an optimum number of features from a collection of thousands of them. We use a shallow neural network and jointly optimize it with decision tree taking both network parameters and input features into account. Our model needs only a minute on a single CPU for its training while existing methods using deep neural networks need about 10 min on NVidia Tesla K40 GPU. However, we obtain similar or better performance on several toxicity benchmark tasks. We also develop a cumulative feature ranking method which enables us to identify features that can help chemists perform prescreening of toxic compounds effectively.
dc.description.peerreviewedYes
dc.languageEnglish
dc.language.isoeng
dc.publisherAmerican Chemical Society
dc.relation.ispartofpagefrom1874
dc.relation.ispartofpageto1888
dc.relation.ispartofissue1
dc.relation.ispartofjournalACS Omega
dc.relation.ispartofvolume4
dc.subject.fieldofresearchNanotechnology
dc.subject.fieldofresearchChemical Engineering
dc.subject.fieldofresearchMaterials Engineering
dc.subject.fieldofresearchcode1007
dc.subject.fieldofresearchcode0904
dc.subject.fieldofresearchcode0912
dc.subject.keywordsScience & Technology
dc.subject.keywordsPhysical Sciences
dc.subject.keywordsChemistry, Multidisciplinary
dc.subject.keywordsChemistry
dc.subject.keywordsDEEP ARCHITECTURES
dc.titleEfficient Toxicity Prediction via Simple Features Using Shallow Neural Networks and Decision Trees
dc.typeJournal article
dc.type.descriptionC1 - Articles
dcterms.bibliographicCitationKarim, A; Mishra, A; Newton, MAH; Sattar, A, Efficient Toxicity Prediction via Simple Features Using Shallow Neural Networks and Decision Trees, ACS Omega, 2019, 4 (1), pp. 1874-1888
dcterms.licensehttp://pubs.acs.org/page/policy/authorchoice_termsofuse.html
dc.date.updated2019-09-10T02:32:10Z
dc.description.versionVersion of Record (VoR)
gro.rights.copyright© 2019 American Chemical Society. This is an open access article published under an ACS AuthorChoice License, which permits copying and redistribution of the article or any adaptations for non-commercial purposes.
gro.hasfulltextFull Text
gro.griffith.authorSattar, Abdul
gro.griffith.authorNewton, MAHakim A.
gro.griffith.authorMishra, Avinash
gro.griffith.authorKarim, Abdul


Files in this item

This item appears in the following Collection(s)

  • Journal articles
    Contains articles published by Griffith authors in scholarly journals.

Show simple item record