Molecular design in drug discovery: a comprehensive review of deep generative models

Abstract

Deep generative models have been an upsurge in the deep learning community since they were proposed. These models are designed for generating new synthetic data including images, videos and texts by fitting the data approximate distributions. In the last few years, deep generative models have shown superior performance in drug discovery especially de novo molecular design. In this study, deep generative models are reviewed to witness the recent advances of de novo molecular design for drug discovery. In addition, we divide those models into two categories based on molecular representations in silico. Then these two classical types of models are reported in detail and discussed about both pros and cons. We also indicate the current challenges in deep generative models for de novo molecular design. De novo molecular design automatically is promising but a long road to be explored.

Semi-Synthetic Chasmanthinine Analogues with Antifeedant Effects against Spodoptera exigua

“…The spectral data of compounds a~s were given in the supplemental material. In the 13 and 73 ppm strongly indicated that the ester group was located at C-14 and the appearance of hydroxyl groups at C-8 and C-13. 12 This conclusion was also supported by the molecular masses difference between the title compounds and intermediate 1.…”

“…All the title compounds were identified by 1 H NMR, 13 C NMR, DEPT and HR-ESI-MS. The spectral data of compounds a~s were given in the supplemental material.…”

“…Esterification is a commonly used drug design method. 13 Our previous research also shows that esterification and/or etherification of HO-8 and/or HO-14 in a C19-diterpenoid alkaloid enhance the antifeedant activity. 9 However, the compounds synthesized in this study unfortunately does not exceed the activity of chasmanthinine.…”

“…The antifeedant mechanism of DAs also needs to be further explored. 13 C NMR (100 MHz, CDCl3) δ 86.0, 84.6, 82.4, 80.7, 79.6, 77.2, 72.6, 62.7, 59.3, 57.7, 57.3, 56.3, 53.7, 52.3, 50.6, 50.2 (2C), 49.4, 42.3, 39.6, 39.5, 35.9, 35.2, 25.9, 13.8. HRMS (ESI) m/z…”

“…The combined organic layer was dried over anhydrous Na2SO4, and evaporated to give compounds a~s after purification by column chromatography over silica gel (petroleum ether-acetone = 50:1-15:1).Compound a. pale yellow amorphous powder, yield 14% 1. H NMR (400 MHz, CDCl3) δ 8.03 (d, J = 6.0 Hz, 2H),7.56 (t, J = 7.4 Hz, 1H), 7.44 (t, J = 7.4 Hz, 2H), 5.17 (d, J = 5.0 Hz, 1H), 4.04 (d, J = 6.8 Hz, 1H),3.66 (d, J = 8.4 Hz, 1H), 3.38 (s, 3H), 3.29 (s, 3H), 3.27 (s, 3H), 3.26 (s, 3H), 1.11 (t, J = 7.0 Hz, 3H) 13. C NMR (100 MHz, CDCl3) δ 167.…”