No abstract

Deep learning (DL) is revolutionizing evidence-based decision-making techniques that can be applied across various sectors. Specifically, it possesses the ability to utilize two or more levels of non-linear feature transformation of the given data via representation learning in order to overcome limitations posed by large datasets. As a multidisciplinary field that is still in its nascent phase, articles that survey DL architectures encompassing the full scope of the field are rather limited. Thus, this paper comprehensively reviews the state-of-art DL modelling techniques and provides insights into their advantages and challenges. It was found that many of the models exhibit a highly domain-specific efficiency and could be trained by two or more methods. However, training DL models can be very time-consuming, expensive, and requires huge samples for better accuracy. Since DL is also susceptible to deception and misclassification and tends to get stuck on local minima, improved optimization of parameters is required to create more robust models. Regardless, DL has already been leading to groundbreaking results in the healthcare, education, security, commercial, industrial, as well as government sectors. Some models, like the convolutional neural network (CNN), generative adversarial networks (GAN), recurrent neural network (RNN), recursive neural networks, and autoencoders, are frequently used, while the potential of other models remains widely unexplored. Pertinently, hybrid conventional DL architectures have the capacity to overcome the challenges experienced by conventional models. Considering that capsule architectures may dominate future DL models, this work aimed to compile information for stakeholders involved in the development and use of DL models in the contemporary world.

The expeditious and world pandemic viral disease of new coronavirus (SARS-CoV-2) has formed a prompt urgency to discover auspicious target-based ligand for the treatment of COVID-19. Symptoms of novel coronavirus disease (COVID-19) typically include dry cough, fever, and shortness of breath. Recent studies on many COVID-19 patients in Italy and the United Kingdom found increasing anosmia and ageusia among the COVID-19-infected patients. SARS-CoV-2 possibly infects neurons in the nasal passage and disrupts the senses of smell and taste, like other coronaviruses, such as SARS-CoV and MERS-CoV that could target the central nervous system. Developing a drug based on the T2Rs might be of better understanding and worth finding better molecules to act against COVID-19. In this research, we have taken a taste receptor agonist molecule to find a better core molecule that may act as the best resource to design a drug or corresponding derivatives. Based on the computational docking studies, the antibiotic tobramycin showed the best interaction against 6LU7 COVID-19 main protease. Aromatic carbonyl functional groups of the molecule established intermolecular hydrogen bonding interaction with GLN189 amino acid and it showed the two strongest carbonyl interactions with receptor protein resulting in a glide score of −11.159. To conclude, depending on the molecular recognition of the GPCR proteins, the agonist molecule can be recognized to represent the cell secondary mechanism; thus, it provides enough confidence to design a suitable molecule based on the tobramycin drug.

No abstract

No abstract