https://www.selleckchem.com/products/Temsirolimus.html The SqueezeNet that comes forward with its light network design is tuned for the COVID-19 diagnosis with Bayesian optimization additive. Fine-tuned hyperparameters and augmented dataset make the proposed network perform much better than existing network designs and to obtain a higher COVID-19 diagnosis accuracy. COVID-19, the disease caused by the novel SARS-CoV-2, a betacoronavirus structurally similar to SARS-CoV. Based on both structural and syndromic similarities with SARS-CoV, a hypothesis is formed on SARS-CoV-2 potential to affect the host's metabolism as part of its lifecycle. This hypothesis is evaluated by (a) exploratory analysis of SARS-CoV/human transcriptomic interaction data and gene set enrichment analysis (b) a confirmatory, focused review of the literature based on the findings by (a). A STRING Viruses (available search for human - SARS-CoV (NCBI taxonomy Id 9606 vs. NCBI taxonomy Id 694009) genomic interactions reveals ten human proteins, interacting with SARS-CoV SGTA, FGL2, SPECC1, STAT3, PHB, BCL2L1, PPP1CA, CAV1, JUN, XPO1. Gene set enrichment analyses (GSEA) with STRING on this network revealed their role as a putative protein - protein interaction network (PPI; Enrichment p-value = 0.0296) mediating, viral parasitism, interleukin as well as insulin signaling, diabetes and triglyceride catabolism. In the literature, SARS-CoV has been known to cause de novo diabetes by ACE2-dependent uptake on pancreatic isle cells, and furthermore dysregulate lipid autophagy in favor of the viral lifecycle. Conversely, currently there are only non-causative, observational evidence of worse outcomes for COVID-19 patients with comorbid diabetes or hyperglycemia. No study has reported on the lipid profiles of COVID-19 patients; however, lipid-targeting molecules have been proposed as agents against SARS-CoV-2. Future studies, reporting on lipid and glucose metabolism of COVID-19 patients could help elucidate