OpenLB
Open Library of Bioscience
Advanced Search
Frontiers in neuroscience
2022;16 858126.

DeePred-BBB: A Blood Brain Barrier Permeability Prediction Model With Improved Accuracy.

Rajnish Kumar, Anju Sharma, Athanasios Alexiou, Anwar L Bilgrami, Mohammad Amjad Kamal, Ghulam Md Ashraf
Author Information
  1. Rajnish Kumar: Amity Institute of Biotechnology, Amity University Uttar Pradesh, Lucknow, India.
  2. Anju Sharma: Department of Applied Science, Indian Institute of Information Technology Allahabad, Prayagraj, India.
  3. Athanasios Alexiou: Department of Science and Engineering, Novel Global Community Educational Foundation, Hebersham, NSW, Australia.
  4. Anwar L Bilgrami: Department of Entomology, Rutgers, The State University of New Jersey, New Brunswick, NJ, United States.
  5. Mohammad Amjad Kamal: Institutes for Systems Genetics, Frontiers Science Center for Disease-Related Molecular Network, West China Hospital, Sichuan University, Chengdu, China.
  6. Ghulam Md Ashraf: Pre-Clinical Research Unit, King Fahd Medical Research Center, King Abdulaziz University, Jeddah, Saudi Arabia.
PMID: 35592264 DOI: 10.3389/fnins.2022.858126

Abstract

The blood-brain barrier (BBB) is a selective and semipermeable boundary that maintains homeostasis inside the central nervous system (CNS). The BBB permeability of compounds is an important consideration during CNS-acting drug development and is difficult to formulate in a succinct manner. Clinical experiments are the most accurate method of measuring BBB permeability. However, they are time taking and labor-intensive. Therefore, numerous efforts have been made to predict the BBB permeability of compounds using computational methods. However, the accuracy of BBB permeability prediction models has always been an issue. To improve the accuracy of the BBB permeability prediction, we applied deep learning and machine learning algorithms to a dataset of 3,605 diverse compounds. Each compound was encoded with 1,917 features containing 1,444 physicochemical (1D and 2D) properties, 166 molecular access system fingerprints (MACCS), and 307 substructure fingerprints. The prediction performance metrics of the developed models were compared and analyzed. The prediction accuracy of the deep neural network (DNN), one-dimensional convolutional neural network, and convolutional neural network by transfer learning was found to be 98.07, 97.44, and 97.61%, respectively. The best performing DNN-based model was selected for the development of the "DeePred-BBB" model, which can predict the BBB permeability of compounds using their simplified molecular input line entry system (SMILES) notations. It could be useful in the screening of compounds based on their BBB permeability at the preliminary stages of drug development. The DeePred-BBB is made available at https://github.com/12rajnish/DeePred-BBB.

Keywords

CNS-permeability blood-brain barrier convolutional neural network deep learning machine learning prediction

References

Nature. 2017 Feb 2;542(7639):115-118 [PMID: 28117445]
J Chem Inf Model. 2021 Feb 22;61(2):676-688 [PMID: 33449694]
Molecules. 2012 Aug 31;17(9):10429-45 [PMID: 22941223]
Drug Resist Updat. 2015 Mar;19:1-12 [PMID: 25791797]
J Mol Graph Model. 2020 May;96:107516 [PMID: 31940508]
BMC Neurol. 2009 Jun 12;9 Suppl 1:S3 [PMID: 19534732]
J Cheminform. 2020 Sep 1;12(1):51 [PMID: 33431044]
Front Bioeng Biotechnol. 2020 Sep 28;8:573775 [PMID: 33117784]
Mini Rev Med Chem. 2018;18(3):196-207 [PMID: 28302041]
Pharm Res. 2008 Aug;25(8):1902-14 [PMID: 18553217]
Neurosurg Focus. 2015 Mar;38(3):E10 [PMID: 25727219]
Fitoterapia. 2020 Jan;140:104447 [PMID: 31805306]
Front Neurosci. 2019 Jun 04;13:521 [PMID: 31213970]
Adv Drug Deliv Rev. 2016 Jun 1;101:89-98 [PMID: 27182629]
J Cell Biol. 2015 May 25;209(4):493-506 [PMID: 26008742]
J Med Chem. 2002 Jun 6;45(12):2615-23 [PMID: 12036371]
Chem Res Toxicol. 2021 Feb 15;34(2):217-239 [PMID: 33356168]
NMR Biomed. 2020 Oct;33(10):e4374 [PMID: 32715563]
Trends Pharmacol Sci. 2022 Jan;43(1):30-42 [PMID: 34863533]
AAPS J. 2018 Mar 21;20(3):54 [PMID: 29564576]
Neural Netw. 2021 Mar;135:201-211 [PMID: 33401226]
Bioinformatics. 2021 May 23;37(8):1135-1139 [PMID: 33112379]
Nature. 2015 May 28;521(7553):436-44 [PMID: 26017442]
J Chem Inf Model. 2010 Jun 28;50(6):1034-41 [PMID: 20578727]
Med Chem. 2017;13(7):664-669 [PMID: 28185535]
Phys Med. 2020 Jan;69:233-240 [PMID: 31918375]
Arch Neurol. 2000 Mar;57(3):418-20 [PMID: 10714674]
ChemMedChem. 2018 Oct 22;13(20):2189-2201 [PMID: 30110511]
Sci Rep. 2020 Jan 21;10(1):834 [PMID: 31965034]
Nat Rev Neurosci. 2006 Jan;7(1):41-53 [PMID: 16371949]
PLoS Comput Biol. 2008 Oct;4(10):e1000173 [PMID: 18974822]
Microvasc Res. 1999 Nov;58(3):312-28 [PMID: 10527772]
Comput Biol Chem. 2020 Dec;89:107377 [PMID: 33010784]
Cold Spring Harb Perspect Biol. 2015 Jan 05;7(1):a020412 [PMID: 25561720]
Sci Rep. 2020 Mar 23;10(1):5245 [PMID: 32251324]
Nat Methods. 2021 Feb;18(2):203-211 [PMID: 33288961]
Front Neurosci. 2014 Dec 16;8:404 [PMID: 25565938]
Drug Discov Today. 2017 Jul;22(7):1069-1076 [PMID: 28111329]
Curr Drug Metab. 2019;20(3):209-216 [PMID: 30251599]
Bioengineering (Basel). 2021 Feb 23;8(2): [PMID: 33672148]
Mol Inform. 2019 Jun;38(6):e1800082 [PMID: 30844132]
BMC Bioinformatics. 2019 Jun 13;20(1):330 [PMID: 31196129]
NeuroRx. 2005 Jan;2(1):3-14 [PMID: 15717053]
J Comput Biol. 2002;9(6):849-64 [PMID: 12614551]
Artif Intell. 2014 May;210:78-122 [PMID: 24771879]
Biochim Biophys Acta Gen Subj. 2018 Dec;1862(12):2779-2787 [PMID: 30251666]
Sci Rep. 2019 Jun 19;9(1):8802 [PMID: 31217424]
IEEE Trans Neural Netw Learn Syst. 2021 Feb;32(2):748-762 [PMID: 32275612]
Mol Neurodegener. 2018 Apr 4;13(1):17 [PMID: 29618365]
J Med Chem. 2019 Nov 14;62(21):9824-9836 [PMID: 31603678]
NeuroRx. 2005 Jan;2(1):15-26 [PMID: 15717054]
ACS Omega. 2019 Sep 30;4(16):16774-16780 [PMID: 31646222]
Int J Mol Sci. 2021 Apr 28;22(9): [PMID: 33925236]
Lancet Neurol. 2020 Mar;19(3):255-265 [PMID: 31813850]
J Bioinform Comput Biol. 2016 Feb;14(1):1650005 [PMID: 26632324]
J Comput Chem. 2011 May;32(7):1466-74 [PMID: 21425294]
J Cell Biol. 1967 Jul;34(1):207-17 [PMID: 6033532]
Drug Discov Today. 2002 Jan 1;7(1):5-7 [PMID: 11790589]
J Chem Inf Model. 2007 Jan-Feb;47(1):170-5 [PMID: 17238262]
PLoS Comput Biol. 2014 Jul 17;10(7):e1003711 [PMID: 25033408]
Anesth Analg. 2003 Apr;96(4):1150-1154 [PMID: 12651675]
Curr Pharm Biotechnol. 2019;20(14):1163-1171 [PMID: 31433750]
Front Physiol. 2020 Aug 21;11:830 [PMID: 32973540]
Fluids Barriers CNS. 2018 Aug 31;15(1):23 [PMID: 30165870]
PLoS One. 2019 Dec 4;14(12):e0225574 [PMID: 31800601]
Curr Med Chem. 2021;28(10):2033-2047 [PMID: 32452320]
BMC Bioinformatics. 2020 Mar 27;21(1):126 [PMID: 32216744]
Biomed Res Int. 2015;2015:292683 [PMID: 26504797]
Journal Article

Word Cloud

Similar Articles

Cited By