PMID- 21501711
OWN - NLM
STAT- MEDLINE
DCOM- 20110901
LR  - 20110419
IS  - 1873-4324 (Electronic)
IS  - 0003-2670 (Linking)
VI  - 692
IP  - 1-2
DP  - 2011 Apr 29
TI  - In silico classification of human maximum recommended daily dose based on 
      modified random forest and substructure fingerprint.
PG  - 50-6
LID - 10.1016/j.aca.2011.02.010 [doi]
AB  - A modified random forest (RF) algorithm, as a novel machine learning technique, 
      was developed to estimate the maximum recommended daily dose (MRDD) of a large 
      and diverse pharmaceutical dataset for phase I human trials using substructure 
      fingerprint descriptors calculated from simple molecular structure alone. This 
      type of novel molecular descriptors encodes molecular structure in a series of 
      binary bits that represent the presence or absence of particular substructures in 
      the molecule and thereby can accurately and directly depict a series of local 
      information hidden in this molecule. Two model validation approaches, 5-fold 
      cross-validation and an independent validation set, were used for assessing the 
      prediction capability of our models. The results obtained in this study indicate 
      that the modified RF gave prediction accuracy of 80.45%, sensitivity of 75.08%, 
      specificity of 84.85% for 5-fold cross-validation, and prediction accuracy of 
      80.5%, sensitivity of 76.47%, specificity of 83.48% for independent validation 
      set, respectively, which are as a whole better than those by the original RF. At 
      the same time, the important substructure fingerprints, recognized by the RF 
      technique, gave some insights into the structure features related to toxicity of 
      pharmaceuticals. This could help provide intuitive understanding for medicinal 
      chemists.
CI  - Copyright (c) 2011. Published by Elsevier B.V.
FAU - Cao, Dong-Sheng
AU  - Cao DS
AD  - Research Center of Modernization of Traditional Chinese Medicines, Central South 
      University, Changsha, PR China.
FAU - Hu, Qian-Nan
AU  - Hu QN
FAU - Xu, Qing-Song
AU  - Xu QS
FAU - Yang, Yan-Ning
AU  - Yang YN
FAU - Zhao, Jian-Chao
AU  - Zhao JC
FAU - Lu, Hong-Mei
AU  - Lu HM
FAU - Zhang, Liang-Xiao
AU  - Zhang LX
FAU - Liang, Yi-Zeng
AU  - Liang YZ
LA  - eng
PT  - Journal Article
PT  - Research Support, Non-U.S. Gov't
DEP - 20110315
PL  - Netherlands
TA  - Anal Chim Acta
JT  - Analytica chimica acta
JID - 0370534
RN  - 0 (Pharmaceutical Preparations)
SB  - IM
MH  - *Algorithms
MH  - *Artificial Intelligence
MH  - Clinical Trials, Phase I as Topic
MH  - Computational Biology/*methods
MH  - *Drug Dosage Calculations
MH  - Humans
MH  - Pharmaceutical Preparations/chemistry
MH  - Structure-Activity Relationship
EDAT- 2011/04/20 06:00
MHDA- 2011/09/02 06:00
CRDT- 2011/04/20 06:00
PHST- 2010/08/12 00:00 [received]
PHST- 2010/12/07 00:00 [revised]
PHST- 2011/02/03 00:00 [accepted]
PHST- 2011/04/20 06:00 [entrez]
PHST- 2011/04/20 06:00 [pubmed]
PHST- 2011/09/02 06:00 [medline]
AID - S0003-2670(11)00182-6 [pii]
AID - 10.1016/j.aca.2011.02.010 [doi]
PST - ppublish
SO  - Anal Chim Acta. 2011 Apr 29;692(1-2):50-6. doi: 10.1016/j.aca.2011.02.010. Epub 
      2011 Mar 15.