10.1002/cmdc.202000786
ChemMedChem
COMMUNICATION
Table 1. DDR1 inhibitory activity of the synthesized compounds
that compound 3 is registed in PubChem with CID 58614959
and is annotated as Raf kinase and p38 MAP kinase inhibitor.
Pharmacophore
score[a]
Binding affinity
score [kJ/mol][b]
Compound
IC50 [nM][c]
In conclusion, we were able to designed DDR1 inhibitors with a
desired pharmacophore using DGMs. Compound 3 showed
potent inhibitory activity with an IC50 value of 92.5 nM against
DDR1. In general, in order to predict inhibitory activities of
generated compounds from DGMs, many experimental inhibitory
data are needed to construct accurate prediction models.
However, our strategy needs only pharmacophore information to
design inhibitors against a target protein.Therefore, our strategy
can be used in the early stage of drug discovery process.
Ponatinib is a drug used to treat chronic myeloid leukemia and
inhibits DDR1 with a Kd value of 1.3 nM.[16] In this study, our
pharmacophore is derived from the crystal structure of DDR1
kinase domain in complex with ponatinib. The scaffolds of the
synthesized compounds (Figure 4) were found to be different
from that of ponatinib (Figure 2). Thus, our strategy can also be
used for scaffold hopping.
1
2
0.96
0.95
0.83
0.96
0.86
0.84
0.85
0.85
0.85
0.85
0.85
0.85
-50.51
-52.67
-47.13
-51.97
-37.29
-40.83
-54.38
-51.78
-49.46
-53.06
-51.15
-54.83
1005.9
2239.4
92.5
3
4
186.7
> 30,000
> 30,000
NT[d]
5
6
7
8
NT
9
NT
7a
8a
9a
171.3
1244.3
1111.0
[a] Calculated using Relative Pharmacophore-Fit score in LigandScout 4.4.
[b] Calculated using iaffnity module in LigandScout 4.4.
[c] The compound concentration required for 50% inhibition (IC50) was
determined from semi-logarithmic dose–response plots, and the results
represent the mean of duplicated samples.
In order to determine which compounds to synthesize, it is
important to filter generated structures from the agent network
efficiently. We are now trying to construct more practical filtering
methods that include criteria such as drug-likeness score,[19]
ADMET properties[20] and synthesis accessibility[21]. We believe
that this pharmacophore-based DGM strategy can be applied to
various drug discovery campaigns in the future.
[d] NT = not tested
The synthesized compounds were evaluated for their inhibitory
activity against DDR1. The kinase assays were performed using
Off-chip Mobility Shift Assay which were carried out via a kinase
profiling service (Carna Biosciences, Inc., Kobe, Japan) (see
Supporting Information). The results are summarized in Table 1.
Among the tested compounds, compound 3 exhibited interesting
Acknowledgements
We would like to thank Dr. Hirofumi Nakano for insightful
comments and suggestions.
double-digit nanomolar inhibitory activity against DDR1 (IC50
=
92.5 nM). The binding interaction of compound 3 derived from
pharmacophore matching is shown in Figure 5A. Compound 3
fulfills all of the pharmacophore features of a DDR1 inhibitor,
although there are slightly misaligned features.
Keywords: Deep Generative Model • Pharmacophore Model •
De novo Design • DDR1
[1] H. Huang, P.S. Yu, C. Wang, arXiv:1803.04469v2 2018.
[2] M. Johnson, M. Schuster, Q. V. Le, M. Krikun, Y. Wu, Z. Chen, N. Thorat,
F. Viégas, M. Wattenberg, G. Corrado, M. Hughes, J. Dean, Trans.
Assoc. Comput. Linguist. 2017, 5, 339–351.
Compounds 4 and 7a were also found to have potent inhibitory
activities (IC50 values: 186.7 and 171.3 nM, respectively).
Compound 7a was designed by removing a Cl atom from 1,2,4-
trichlorobenzene in compound 7 as illustrated in Figure 5B.
Compounds 1, 2, 8a, 9a were found to moderately inhibit DDR1
activity (IC50 values: 1005.9, 2239.4, 1244.3 and 1111.0 nM,
respectively). Compounds 5 and 6 did not exhibit any inhibitory
activity at all. Binding affinity scores of the two compounds are
high values (-37.29, and -40.83 kJ/mol), indicating low binding
affinities. These results indicate that our strategy of using DGMs
has worked efficiently to design DDR1 inhibitors.
[3] R. de Bem, A. Ghosh, T Ajanthan, O. Miksik, A Boukhayma, N. Siddharth,
P. Torr, Int. J. Comput. Vis. 2020, 128, 1537–1563.
[4] D.C. Elton, Z. Boukouvalas, M. D. Fugea, P.W. Chung, Mol. Syst. Des. Eng.
2019, 4, 828–849.
[5] D. Merk, L. Friedrich, F. Grisoni, G. Schneider, Mol. Inform. 2018, 37,
1700153.
[6] A. Zhavoronkov, Y. A. Ivanenkov, A. Aliper, M. S. Veselov, V. A. Aladinskiy,
A. V. Aladinskaya, V. A. Terentiev, D. A. Polykovskiy, M. D. Kuznetsov,
A. Asadulaev, Y. Volkov, A. Zholus, R. R. Shayakhmetov, A. Zhebrak,
L. I. Minaeva, B. A. Zagribelnyy, L. H. Lee, R. Soll, D. Madge, L. Xing,
T. Guo, A. Aspuru-Guzik, Nat. Biotechnol. 2019, 37, 1038–1040.
[7] Q. Gao, L. Yang, Y. Zhu, Curr. Comput. Aided. Drug. Des. 2010, 6(1), 37–
49.
A
B
[8] A. Yoshimori, E. Kawasaki, C. Kanai, T. Tasaka, Chem. Pharm. Bull. 2020,
68 (3), 227–233.
[9] D. J. Weininger, J. Chem. Inf. Comput. Sci. 1988, 28 (1), 31–36.
[10] A. P. Bento, A. Gaulton, A. Hersey, L. J. Bellis, J. Chambers, M. Davies,
F. A. Krüger, Y. Light, L. Mak, S. McGlinchey, M. Nowotka, G.
Papadatos, R. Santos, J. P. Overington, Nucleic Acids Res. 2014, 42,
D1083–D1090.
Figure 5. Binding interactions of A) compound 3 and B) compound 7
[11] a) REINVENT: Molecular de novo design using recurrent neural networks
and
reinforcement
learning
To check if the generated structures (compound 1-6, 7a-9a) have
already been registered in certain databases, structure search
was performed in ChEMBL[10] and PubChem.[18] We have found
Blaschke, O. Engkvist, H. Chen, J. Cheminform. 2017, 9, 1
3
This article is protected by copyright. All rights reserved.