For the last few years, the world has been going through a difficult time, and the reason behind this is severe acute respiratory syndrome-coronavirus-2 (SARS-CoV-2), one of the significant members of the Coronaviridae family. The major research groups have shifted their focus towards finding a vaccine and drugs against SARS-CoV-2 to reduce the infection rate and save the life of human beings. Even the WHO has permitted using certain vaccines for an emergency attempt to cut the infection curve down. However, the virus has a great sense of mutation, and the vaccine’s effectiveness remains questionable. No natural medicine is available at the community level to cure the patients for now. In this study, we have screened the vast library of experimental drugs of Drug Bank with Schrodinger’s maestro by using three algorithms: high-throughput virtual screening (HTVS), standard precision, and extra precise docking followed by Molecular Mechanics/Generalized Born Surface Area (MMGBSA). We have identified 3-(7-diaminomethyl-naphthalen-2-YL)-propionic acid ethyl ester and Thymidine-5′-thiophosphate as potent inhibitors against the SARS-CoV-2, and both drugs performed impeccably and showed stability during the 100 ns molecular dynamics simulation. Both of the drugs are among the category of small molecules and have an acceptable range of ADME properties. They can be used after their validation in in-vitro and in-vivo conditions.

Lung Cancer is one of the deadliest cancers, responsible for more than 1.80 million deaths annually worldwide, and it is on the priority list of WHO. In the current scenario, when cancer cells become resistant to the drug, making it less effective leaves the patient in vulnerable conditions. To overcome this situation, researchers are constantly working on new drugs and medications that can help fight drug resistance and improve patients’ outcomes. In this study, we have taken five main proteins of lung cancer, namely RSK4 N-terminal kinase, guanylate kinase, cyclin-dependent kinase 2, kinase CK2 holoenzyme, tumour necrosis factor-alpha and screened the prepared Drug Bank library with 1,55,888 compounds against all using three Glide-based docking algorithms namely HTVS, standard precision and extra precise with a docking score ranging from −5.422 to −8.432 Kcal/mol. The poses were filtered with the MM\GBSA calculations, which helped to identify Imidazolidinyl urea C₁₁H₁₆N₈O₈ (DB14075) as a multitargeted inhibitor for lung cancer, validated with advanced computations like ADMET, interaction pattern fingerprints, and optimised the compound with Jaguar, producing satisfied relative energy. All five complexes were performed with MD Simulation for 100 ns with NPT ensemble class, producing cumulative deviation and fluctuations < 2 Å and a web of intermolecular interaction, making the complexes stable. Further, the in-vitro analysis for morphological imaging, Annexin V/PI FACS assay, ROS and MMP analysis caspase3//7 activity were performed on the A549 cell line producing promising results and can be an option to treat lung cancer at a significantly cheaper state. Communicated by Ramaswamy H. Sarma

Severe acute respiratory syndrome coronavirus-2 (SARS-CoV-2) is a member of the Coronaviridae family, causing major destructions to human life directly and indirectly to the economic crisis around the world. Although there is significant reporting on the whole genome sequences and updated data for the different receptors are widely analyzed and screened to find a proper medication. Only a few bioassay experiments were completed against SARS-CoV-2 spike protein. We collected the compounds dataset from the PubChem Bioassay database having 1786 compounds and split it into the ratio of 80–20% for model training and testing purposes, respectively. Initially, we have created 11 models and validated them using a fivefold validation strategy. The hybrid consensus model shows a predictive accuracy of 95.5% for training and 94% for the test dataset. The model was applied to screen a virtual chemical library of Natural products of 2598 compounds. Our consensus model has successfully identified 75 compounds with an accuracy range of 70–100% as active compounds against SARS-CoV-2 RBD protein. The output of ML data (75 compounds) was taken for the molecular docking and dynamics simulation studies. In the complete analysis, the Epirubicin and Daunorubicin have shown the docking score of −9.937 and −9.812, respectively, and performed well in the molecular dynamics simulation studies. Also, Pirarubicin, an analogue of anthracycline, has widely been used due to its lower cardiotoxicity. It shows the docking score of −9.658, which also performed well during the complete analysis. Hence, after the following comprehensive pipeline-based study, these drugs can be further tested in vivo for further human utilization. Communicated by Ramaswamy H. Sarma

Lung cancer starts when lung cells grow uncontrollably, forming tumours that make breathing difficult. There are more than 100 types of human cancer, and in most cases, it is untreatable due to the unavailability of medico-infrastructure and facilities, even though the USFDA approved 57 anticancer drugs in 2020 alone. WHO reported more than 10 million cancer-related deaths yearly, and lung cancer alone accounts for more than 1.80 million deaths and a few studies suggest lung cancer incidence and deaths may surpass 3.8 million and 3.2 million by 2050, which demands rapid drug designing and repurposing and the role of artificial intelligence (AI) found to be the best solutions. AI in lung cancer therapeutics has emerged as a significant area of research in recent years. This state-of-the-art review aims to explore the various applications of AI in lung cancer treatment and its potential to revolutionise patient care, and predictive models can analyse large datasets, including clinical data, genetic information, and treatment outcomes, for novel drug design and to generate personalised treatment recommendations, having the potential to optimise therapeutic strategies, enhance treatment efficacy, and minimise adverse effects.Methods: A thorough and extensive literature review was conducted after reading relevant research papers and book chapters of the last decade, indexed in PubMed and Scopus to get high-quality articles to compile this article. Several engineering conference proceedings have also been included, as they meet our quality review standards.Results: Advanced algorithms accelerate the process and improve efficiency, with accuracy beyond 95% in many cases, validated with traditional computational drug designing and repurposing approaches such as Molecular Docking and Dynamic Simulations. We have also compiled the use of convolutional neural networks, recurrent neural networks, generative adversarial networks, variational autoencoders, reinforcement learning, and many more.Conclusion: The role of AI in lung cancer therapeutics holds excellent promise through accurate detection, personalised treatment planning, novel drug design, drug repurposing, and decision support. AI can potentially transform lung cancer therapeutics by providing a robust solution that is most accurate in the least time, which can save the time and effort of experimental biological scientists. Advanced AI algorithms such as Convolutional Neural Networks, Recurrent Neural Networks, Generative Adversarial Networks, Variational Autoencoders, and Reinforcement Learning have been used in various drug repurposing articles, and even the drugs and vaccines are in clinical trial stages in just years which earlier were taking decades to get a drug or vaccine in market, and the SARS CoV-2 vaccine is the result for the same. However, further research and collaboration are required to address the existing challenges and fully realise the potential of AI in this field.

Background: Epidermal growth factor receptor (EGFR/HER-1) and its role in tumor development and progression through the mechanism of tumor angiogenesis is prevalent in non-small lung cancer, head and neck cancer, cholangiocarcinoma & glioblastoma. Previous treatments targeting the oncogenic activity of EGFR's kinase domain have been hindered by acquired mutational resistance and side effects from existing drugs like erlotinib, highlighting the need for new EGFR inhibitors through structure- based drug designing. Objective: The research aims to develop novel quinazoline derivatives through structure-based virtual screening, molecular docking, and molecular dynamics simulation to potentially interact with EGFR's kinase domain and impede tumor angiogenic phenomenon. Methods: Quinazoline derivatives were retrieved and filtered from the PubChem database using structure- based virtual screening and the Lipinski rule of five drug-likeness studies. Molecular docking-based virtual screening methods and molecular dynamics simulation were then carried out to identify top leads. Results: A total of 1000 quinazoline derivatives were retrieved, with 671 compounds possessing druglike properties after applying Lipinski filters. Further filtration using ADME and toxicity filters yielded 28 compounds with good pharmacokinetic profiles. Docking-based virtual screening identified seven compounds with better binding scores than the control drug, dacomitinib. After cross-checking binding scores, three top compounds QU524, QU571, and QU297 were selected for molecular dynamics simulation study of 100 ns interval using Desmond module of Schrodinger maestro to understand their conformational stability. Conclusion: The research results showed that the selected quinazoline leads exhibited better binding affinity and conformational stability than the control drug, erlotinib. These compounds also had good pharmacokinetic and pharmacodynamic profiles and did not violate Lipinski’s rule of five limits. The findings suggest that these leads have the potential to target EGFR's kinase domain and inhibit the EGFR-associated phenomenon of tumor angiogenesis.