Novel Approach of Deep Learning in Toxicity Prediction
Adhithiyan M1, Karmel A2
1Adhithiyan M, M.Tech SCSE, VIT University, Chennai Campus, (Tamil Nadu), India.
2Dr. Karmel A, SCSE, VIT University, Chennai Campus, (Tamil Nadu), India.
Manuscript received on 17 February 2019 | Revised Manuscript received on 08 March 2019 | Manuscript Published on 08 June 2019 | PP: 698-704 | Volume-7 Issue-5S4, February 2019 | Retrieval Number: E11440275S419/19©BEIESP
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Humans are always exposed to various harmful, harmless chemicals everyday. toxicity prediction is the method to find the toxicity of the chemicals , ie it is Toxic or Non toxic. among all the applications the toxicity prediction isvery much important as it involves large amount of expenses, chemicals, labour, etc. in the world of big data and artificial intelligence, toxicity prediction can be done effectively using machine learning and deep learning instead of drug evaluations in lab such as cellular, animal and clinical methods. in this paper we review machine learning methods to predict toxicity and extention of toxicity testing using deep learning such as DNN. we discuss about the molecular descriptors and certain endpoints and its relationship.
Keywords: Toxicity Prediction, Machine Learning, Deep Learning, Molecular Descriptors, Endpoints.
Scope of the Article: Deep Learning