TY - CHAP
T1 - Impact and Challenges of Chemoinformatics in Drug Discovery
AU - Subbarayan, Pochi R.
N1 - Funding Information:
I thank Dr Olga Kel-Margoulis for introducing me to the exciting world of Chemoinformatics and giving me access to the standalone version of PASS. She is the Director of Applied Life Science Informatics, geneXplain GmbH. I also thank Dr Vladimir Poroikov for sharing his publications on the PASS algorithm and for his critical reading of this manuscript. He is the head of the Department for Bioinformatics and Laboratory for Structure-Function Based Drug Design, Institute of Biomedical Chemistry, Moscow, Russia. Lisa Tarka of Thomson Reuters gave me access to the MetaDrug module. I also thank Dr Malancha Sarkar and Ms Nitya Ramalingam, Department of Biology, University of Miami for their input and valuable discussion. This work was supported by the American Cancer Society Institutional Research Grant (IRG #98-277-07), Interdisciplinary Research Development Initiative (IRDI #102504) award, and the University of Miami Clinical and Translational Science Institute (CTSI) Pilot Research Grant (CTSI-2013-P03) to PRS. The Pilot and Collaborative Translational and Clinical Studies component is supported by Grant #1UL1TR000460, the University of Miami CTSI, from the National Center for Advancing Translational Sciences and the National Institute on Minority Health and Health Disparities.
Publisher Copyright:
© 2016 Elsevier Inc. All rights reserved.
PY - 2016
Y1 - 2016
N2 - The last decade has witnessed the integration of systems biology and Chemoinformatics datasets. Many open source and commercial programs have streamlined drug discovery research efforts. In this chapter, we report the predictive accuracy of PASS and MetaDrug, two commercial Chemoinformatics programs, in deciphering biological activity of the test compound PE3. Both programs identified PE3 as an antineoplastic and antiviral agent. PASS recognized PE3 as a photosensitizer with a high degree of confidence, while MetaDrug failed to determine this important property. Overall, PASS predicted the biological properties of PE3 better than MetaDrug. At present, no single Chemoinformatics program can conclusively predict the biological activity spectrum of new chemical entities (NCEs). Therefore, we recommend using several Chemoinformatics programs and experimental data to predict drug-like properties of NCEs. Such an approach may accelerate drug discovery.
AB - The last decade has witnessed the integration of systems biology and Chemoinformatics datasets. Many open source and commercial programs have streamlined drug discovery research efforts. In this chapter, we report the predictive accuracy of PASS and MetaDrug, two commercial Chemoinformatics programs, in deciphering biological activity of the test compound PE3. Both programs identified PE3 as an antineoplastic and antiviral agent. PASS recognized PE3 as a photosensitizer with a high degree of confidence, while MetaDrug failed to determine this important property. Overall, PASS predicted the biological properties of PE3 better than MetaDrug. At present, no single Chemoinformatics program can conclusively predict the biological activity spectrum of new chemical entities (NCEs). Therefore, we recommend using several Chemoinformatics programs and experimental data to predict drug-like properties of NCEs. Such an approach may accelerate drug discovery.
KW - Natural products
KW - Shotgun approach to drug discovery
KW - Systematic drug discovery efforts
KW - Systems biology
KW - Target deconvolution
KW - Virtual screening
UR - http://www.scopus.com/inward/record.url?scp=84967648080&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84967648080&partnerID=8YFLogxK
U2 - 10.1016/B978-0-12-801559-9.00007-7
DO - 10.1016/B978-0-12-801559-9.00007-7
M3 - Chapter
AN - SCOPUS:84967648080
SN - 9780128015599
SP - 141
EP - 152
BT - Artificial Neural Network for Drug Design, Delivery and Disposition
PB - Elsevier Inc.
ER -