. De novo drug design is a computational approach that generates novel molecular structures from atomic building blocks with no a priori relationships. Conventional methods include structure-based and ligand-based design, which depend on the properties of the active site of a biological target or its known active binders, respectively. Artificial intelligence, including machine learning, is an emerging field that has positively impacted the drug discovery process. Deep reinforcement learning is a subdivision of machine learning that combines artificial neural networks with reinforcement-learning architectures. This method has successfully been employed to develop novel de novo drug design approaches using a variety of artificial networks including recurrent neural networks, convolutional neural networks, generative adversarial networks, and autoencoders. This review article summarizes advances in de novo drug design, from conventional growth algorithms to advanced machine-learning methodologies and highlights hot topics for further development.

Objective A prospective clinical imaging study has been conducted to investigate pain processing functional pathways during trigeminal heat stimulation (THS) in patients with migraine without aura experiencing ictal cutaneous allodynia (CA) (MwoA CA+). Methods Using whole-brain BOLD-fMRI, functional response to THS at three different intensities (41°, 51° and 53℃) was investigated interictally in 20 adult MwoA CA+ patients compared with 20 MwoA patients without ictal CA (MwoA CA-) and 20 healthy controls (HCs). Secondary analyses evaluated associations between BOLD signal change and clinical features of migraine. Results During moderate-noxious THS (51℃), we observed a significantly greater activation in (a) the anterior cingulate cortex in MwoA CA+ patients compared to HCs and (b) the middle frontal gyrus in MwoA CA+ patients compared to both MwoA CA- patients and HCs. Furthermore, during high-noxious THS (53℃) a significantly decreased activation in the secondary somatosensory cortices was observed in (a) MwoA CA- patients compared to both MwoA CA+ patients and HCs and (b) MwoA CA+ patients compared to HCs. CA severity was positively correlated with the secondary somatosensory cortices activation. Conclusions Our findings suggest that CA may be subtended by both a dysfunctional analgesic compensatory mechanism and an abnormal internal representation of pain in migraine patients.

No abstract