22717-56-2Relevant articles and documents
De Novo Design of Bioactive Small Molecules by Artificial Intelligence
Merk, Daniel,Friedrich, Lukas,Grisoni, Francesca,Schneider, Gisbert
, (2018)
Generative artificial intelligence offers a fresh view on molecular design. We present the first-time prospective application of a deep learning model for designing new druglike compounds with desired activities. For this purpose, we trained a recurrent neural network to capture the constitution of a large set of known bioactive compounds represented as SMILES strings. By transfer learning, this general model was fine-tuned on recognizing retinoid X and peroxisome proliferator-activated receptor agonists. We synthesized five top-ranking compounds designed by the generative model. Four of the compounds revealed nanomolar to low-micromolar receptor modulatory activity in cell-based assays. Apparently, the computational model intrinsically captured relevant chemical and biological knowledge without the need for explicit rules. The results of this study advocate generative artificial intelligence for prospective de novo molecular design, and demonstrate the potential of these methods for future medicinal chemistry.
Development of DHQ-based chemical biology probe to profile cellular targets for HBV
Zhang, Qing,Huang, Jianzhou,Chow, Hoi Yee,Wang, Jinzheng,Zhang, Yingjun,Fung, Yi Man Eva,Ren, Qingyun,Li, Xuechen
supporting information, (2020/10/29)
Chronic hepatitis B virus (HBV) infection has been a serious public health burden worldwide. Current anti-HBV therapies could not eliminate HBV ultimately. Considering the characteristics of HBV, it is impossible to be entirely cured based on current therapies. Therefore, it is urgently needed to develop novel therapeutic agents with new mechanism of action. The dihydroquinolizinone (DHQ) derivatives exhibited potent anti-HBV activity by decreasing HBV DNA and HBsAg level in an obscure mechanism of action. In this study, we have optimized the DHQ scaffold, developed the photoaffinity probe, with which to identify potential binding proteins.
Synthesis and biological evaluation of novel 5,6,7-trimethoxy flavonoid salicylate derivatives as potential anti-tumor agents
Deng, Xiangping,Feng, Wanshi,Lei, Xiaoyong,Liu, Renbo,Peng, Yijiao,Tang, Guotao,Xie, Zhizhong,Xiong, Runde,Zheng, Xing,Zou, Yang
, (2020/02/13)
5,6,7-Trimethoxy flavonoid salicylate derivatives were designed by the joining of three important pharmacophores (TMP, flavonoid, and SA) according to the combination principle. A series of novel trimethoxy flavonoid salicylate derivatives were synthesized and their in vitro anti-tumor activities were evaluated. Among these derivatives, compound 7f exhibited excellent antiproliferative activity against HGC-27 cells and MGC-803 cells with IC50 values of 10.26 ± 6.94 μM and 17.17 ± 3.03 μM, respectively. Subsequently, the effects on cell colony formation (clonogenic survival assay), cell migration (wound healing assay), cell cycle distribution (PI staining assay), cell apoptosis (Hoechst 33258 staining assay and annexin V-FITC/PI dual staining assay), lactate level (lactate measurement), microtubules disarrangement (immunofluorescence staining analysis) and docking posture (molecular docking simulation) were determined. Further western blot analysis confirmed that compound 7f could effectively down-regulate the expression of glycolysis-related proteins HIF-1α, PFKM and PKM2 and tumor angiogenesis-related proteins VEGF. Overall, these studies suggested that compound 7f, as the representative compound of those, might be a promising candidate for the treatment of gastric cancer and deserved the further studies.