PMID- 34732590
OWN - NLM
STAT- MEDLINE
DCOM- 20220404
LR  - 20220405
IS  - 1347-5215 (Electronic)
IS  - 0918-6158 (Linking)
VI  - 45
IP  - 1
DP  - 2022 Jan 1
TI  - Machine Learning Prediction of the Three Main Input Parameters of a Simplified 
      Physiologically Based Pharmacokinetic Model Subsequently Used to Generate 
      Time-Dependent Plasma Concentration Data in Humans after Oral Doses of 212 
      Disparate Chemicals.
PG  - 124-128
LID - 10.1248/bpb.b21-00769 [doi]
AB  - Physiologically based pharmacokinetic (PBPK) modeling has the potential to play 
      significant roles in estimating internal chemical exposures. The three major PBPK 
      model input parameters (i.e., absorption rate constants, volumes of the systemic 
      circulation, and hepatic intrinsic clearances) were generated in silico for 212 
      chemicals using machine learning algorithms. These input parameters were 
      calculated based on sets of between 17 and 65 chemical properties that were 
      generated by in silico prediction tools before being processed by machine 
      learning algorithms. The resulting simplified PBPK models were used to estimate 
      plasma concentrations after virtual oral administrations in humans. The estimated 
      absorption rate constants, volumes of the systemic circulation, and hepatic 
      intrinsic clearance values for the 212 test compounds determined traditionally 
      (i.e., based on fitting to measured concentration profiles) and newly estimated 
      had correlation coefficients of 0.65, 0.68, and 0.77 (p < 0.01, n = 212), 
      respectively. When human plasma concentrations were modeled using traditionally 
      determined input parameters and again using in silico estimated input parameters, 
      the two sets of maximum plasma concentrations (r = 0.85, p < 0.01, n = 212) and 
      areas under the curve (r = 0.80, p < 0.01, n = 212) were correlated. Virtual 
      chemical exposure levels in liver and kidney were also estimated using these 
      simplified PBPK models along with human plasma levels. These results indicate 
      that the PBPK model input parameters for humans of a diverse set of compounds can 
      be reliability estimated using chemical descriptors calculated using in silico 
      tools.
FAU - Kamiya, Yusuke
AU  - Kamiya Y
AD  - Showa Pharmaceutical University.
FAU - Handa, Kentaro
AU  - Handa K
AD  - Fujitsu Limited.
FAU - Miura, Tomonori
AU  - Miura T
AD  - Showa Pharmaceutical University.
FAU - Ohori, Junya
AU  - Ohori J
AD  - Fujitsu Limited.
FAU - Kato, Airi
AU  - Kato A
AD  - Showa Pharmaceutical University.
FAU - Shimizu, Makiko
AU  - Shimizu M
AD  - Showa Pharmaceutical University.
FAU - Kitajima, Masato
AU  - Kitajima M
AD  - Fujitsu Limited.
FAU - Yamazaki, Hiroshi
AU  - Yamazaki H
AD  - Showa Pharmaceutical University.
LA  - eng
PT  - Journal Article
DEP - 20211102
PL  - Japan
TA  - Biol Pharm Bull
JT  - Biological & pharmaceutical bulletin
JID - 9311984
RN  - 0 (Pharmaceutical Preparations)
SB  - IM
MH  - Administration, Oral
MH  - Humans
MH  - *Machine Learning
MH  - *Models, Biological
MH  - Pharmaceutical Preparations
MH  - Reproducibility of Results
OTO - NOTNLM
OT  - food component
OT  - general chemical
OT  - pharmacokinetics
OT  - physiologically based pharmacokinetic (PBPK) modeling
EDAT- 2021/11/05 06:00
MHDA- 2022/04/05 06:00
CRDT- 2021/11/04 05:39
PHST- 2021/11/05 06:00 [pubmed]
PHST- 2022/04/05 06:00 [medline]
PHST- 2021/11/04 05:39 [entrez]
AID - 10.1248/bpb.b21-00769 [doi]
PST - ppublish
SO  - Biol Pharm Bull. 2022 Jan 1;45(1):124-128. doi: 10.1248/bpb.b21-00769. Epub 2021 
      Nov 2.