Machine Learning for the Prediction of Molecular Dipole Moments Obtained by Density Functional Theory

Overview

Journal J Cheminform

Publisher Biomed Central

Specialty Chemistry

Date 2018 Aug 24

PMID 30136001

Citations 5

Authors

Florbela Pereira

Joao Aires-de-Sousa

Affiliations

Soon will be listed here.

Abstract

Machine learning (ML) algorithms were explored for the fast estimation of molecular dipole moments calculated by density functional theory (DFT) by B3LYP/6-31G(d,p) on the basis of molecular descriptors generated from DFT-optimized geometries and partial atomic charges obtained by empirical or ML schemes. A database was used with 10,071 structures, new molecular descriptors were designed and the models were validated with external test sets. Several ML algorithms were screened. Random forest regression models predicted an external test set of 3368 compounds achieving mean absolute error up to 0.44 D. The results represent a significant improvement of the dipole moments calculated using empirical point charges located at the nucleus, even assuming the DFT-optimized geometry (root mean square error, RMSE, of 0.68 D vs. 1.53 D and R = 0.87 vs. 0.66).

Citing Articles

-Schistosomal activity and ADMET properties of 1,2,5-oxadiazinane-containing compound synthesized by visible-light photoredox catalysis.

Itoh K, Nakahara H, Takashino A, Hara A, Katsuno A, Abe Y RSC Med Chem. 2024; .

PMID: 39399310 PMC: 11467761. DOI: 10.1039/d4md00599f.

In-silico study unveils potential phytocompounds in Andrographis paniculata against E6 protein of the high-risk HPV-16 subtype for cervical cancer therapy.

Islam M, Hossain M, Hasnat S, Shuvo M, Akter S, Maria M Sci Rep. 2024; 14(1):17182.

PMID: 39060289 PMC: 11282209. DOI: 10.1038/s41598-024-65112-2.

approach: biological prediction of nordentatin derivatives as anticancer agent inhibitors in the cAMP pathway.

Abdjan M, Aminah N, Siswanto I, Thant T, Kristanti A, Takaya Y RSC Adv. 2022; 10(70):42733-42743.

PMID: 35514899 PMC: 9058016. DOI: 10.1039/d0ra07838g.

Machine learning prediction of UV-Vis spectra features of organic compounds related to photoreactive potential.

Mamede R, Pereira F, Aires-de-Sousa J Sci Rep. 2021; 11(1):23720.

PMID: 34887473 PMC: 8660842. DOI: 10.1038/s41598-021-03070-9.

Machine learning models for hydrogen bond donor and acceptor strengths using large and diverse training data generated by first-principles interaction free energies.

Bauer C, Schneider G, Goller A J Cheminform. 2021; 11(1):59.

PMID: 33430967 PMC: 6737620. DOI: 10.1186/s13321-019-0381-4.

References

Dalton L, Sullivan P, Bale D . Electric field poled organic electro-optic materials: state of the art and future prospects. Chem Rev. 2009; 110(1):25-55. DOI: 10.1021/cr9000429. View

Rai B, Bakken G . Fast and accurate generation of ab initio quality atomic charges using nonparametric statistical regression. J Comput Chem. 2013; 34(19):1661-71. DOI: 10.1002/jcc.23308. View

Pereira F, Xiao K, Latino D, Wu C, Zhang Q, Aires-de-Sousa J . Machine Learning Methods to Predict Density Functional Theory B3LYP Energies of HOMO and LUMO Orbitals. J Chem Inf Model. 2016; 57(1):11-21. DOI: 10.1021/acs.jcim.6b00340. View

Blum L, Reymond J . 970 million druglike small molecules for virtual screening in the chemical universe database GDB-13. J Am Chem Soc. 2009; 131(25):8732-3. DOI: 10.1021/ja902302h. View

Yap C . PaDEL-descriptor: an open source software to calculate molecular descriptors and fingerprints. J Comput Chem. 2011; 32(7):1466-74. DOI: 10.1002/jcc.21707. View

Matuszek A, Reynisson J . Defining Known Drug Space Using DFT. Mol Inform. 2016; 35(2):46-53. DOI: 10.1002/minf.201500105. View

Cheng L, Assary R, Qu X, Jain A, Ong S, Rajput N . Accelerating Electrolyte Discovery for Energy Storage with High-Throughput Screening. J Phys Chem Lett. 2015; 6(2):283-91. DOI: 10.1021/jz502319n. View

Bianco A, Ferrari G, Castagna R, Rossi A, Carminati M, Pariani G . Light-induced dipole moment modulation in diarylethenes: a fundamental study. Phys Chem Chem Phys. 2016; 18(45):31154-31159. DOI: 10.1039/c6cp05609a. View

Delong W, Yongling W, Lanying W, Juntao F, Xing Z . Design, synthesis and evaluation of 3-arylidene azetidin-2-ones as potential antifungal agents against Alternaria solani Sorauer. Bioorg Med Chem. 2017; 25(24):6661-6673. DOI: 10.1016/j.bmc.2017.11.003. View

10.

Ramakrishnan R, Dral P, Rupp M, Anatole von Lilienfeld O . Quantum chemistry structures and properties of 134 kilo molecules. Sci Data. 2015; 1:140022. PMC: 4322582. DOI: 10.1038/sdata.2014.22. View

11.

Fong C . The effect of desolvation on the binding of inhibitors to HIV-1 protease and cyclin-dependent kinases: Causes of resistance. Bioorg Med Chem Lett. 2016; 26(15):3705-13. DOI: 10.1016/j.bmcl.2016.05.080. View

12.

Sliwoski G, Kothiwale S, Meiler J, Lowe Jr E . Computational methods in drug discovery. Pharmacol Rev. 2014; 66(1):334-95. PMC: 3880464. DOI: 10.1124/pr.112.007336. View

13.

Sulpizi M, Schelling P, Folkers G, Carloni P, Scapozza L . The rational of catalytic activity of herpes simplex virus thymidine kinase. a combined biochemical and quantum chemical study. J Biol Chem. 2001; 276(24):21692-7. DOI: 10.1074/jbc.M010223200. View

14.

Svetnik V, Liaw A, Tong C, Culberson J, Sheridan R, Feuston B . Random forest: a classification and regression tool for compound classification and QSAR modeling. J Chem Inf Comput Sci. 2003; 43(6):1947-58. DOI: 10.1021/ci034160g. View

15.

Wu J, Cheng Y, Lan J, Wu D, Qian S, Yan L . Molecular Engineering of Mechanochromic Materials by Programmed C-H Arylation: Making a Counterpoint in the Chromism Trend. J Am Chem Soc. 2016; 138(39):12803-12812. DOI: 10.1021/jacs.6b03890. View

16.

Faber F, Hutchison L, Huang B, Gilmer J, Schoenholz S, Dahl G . Prediction Errors of Molecular Machine Learning Models Lower than Hybrid DFT Error. J Chem Theory Comput. 2017; 13(11):5255-5264. DOI: 10.1021/acs.jctc.7b00577. View

17.

Mehata M, Singh A, Sinha R . Experimental and theoretical study of hydroxyquinolines: hydroxyl group position dependent dipole moment and charge-separation in the photoexcited state leading to fluorescence. Methods Appl Fluoresc. 2017; 4(4):045004. DOI: 10.1088/2050-6120/4/4/045004. View

18.

Irwin J, Sterling T, Mysinger M, Bolstad E, Coleman R . ZINC: a free tool to discover chemistry for biology. J Chem Inf Model. 2012; 52(7):1757-68. PMC: 3402020. DOI: 10.1021/ci3001277. View

19.

Adhikari N, Amin S, Saha A, Jha T . Combating breast cancer with non-steroidal aromatase inhibitors (NSAIs): Understanding the chemico-biological interactions through comparative SAR/QSAR study. Eur J Med Chem. 2017; 137:365-438. DOI: 10.1016/j.ejmech.2017.05.041. View

20.

Nakata M, Shimazaki T . PubChemQC Project: A Large-Scale First-Principles Electronic Structure Database for Data-Driven Chemistry. J Chem Inf Model. 2017; 57(6):1300-1308. DOI: 10.1021/acs.jcim.7b00083. View