Deep Learning Algorithms for Diagnosis of Lung Cancer: A Systematic Review and Meta-Analysis.

We conducted a systematic review and meta-analysis of the diagnostic performance of current deep learning algorithms for the diagnosis of lung cancer. We searched major databases up to June 2022 to include studies that used artificial intelligence to diagnose lung cancer, using the histopathological analysis of true positive cases as a reference. The quality of the included studies was assessed independently by two authors based on the revised Quality Assessment of Diagnostic Accuracy Studies. Six studies were included in the analysis. The pooled sensitivity and specificity were 0.93 (95% CI 0.85−0.98) and 0.68 (95% CI 0.49−0.84), respectively. Despite the significantly high heterogeneity for sensitivity (I2 = 94%, p < 0.01) and specificity (I2 = 99%, p < 0.01), most of it was attributed to the threshold effect. The pooled SROC curve with a bivariate approach yielded an area under the curve (AUC) of 0.90 (95% CI 0.86 to 0.92). The DOR for the studies was 26.7 (95% CI 19.7−36.2) and heterogeneity was 3% (p = 0.40). In this systematic review and meta-analysis, we found that when using the summary point from the SROC, the pooled sensitivity and specificity of DL algorithms for the diagnosis of lung cancer were 93% and 68%, respectively.

Specificity of peptidases secreted by filamentous fungi.

Peptidases are enzymes that cleave peptide bonds, yielding proteins and peptides. Enzymes in this class also perform several other functions, regulating the activation or inactivation of target substrates via proteolysis. Owing to these functions, peptidases have been extensively used in industrial and biotechnological applications. Given their potential functions, it is important to optimize the use of these enzymes, which requires determination of the specificity of each peptidase. The peptidase specificity must be taken into account in choosing a peptidase to catalyze the available protein source within the desired application. The specificity of a peptidase defines the profile of enzyme-substrate interactions, and for this the catalytic site and the arrangement of the amino acid residues involved in peptide bond cleavage need to be known. The catalytic sites of peptidases may be composed of several subsites that interact with amino acid residues for proteolysis. Filamentous fungi produce peptidases with varying specificity, and here we provide a review of those reported to date and their potential applications.

Box-Behnken analysis and storage of spray-dried collagenolytic proteases from Myceliophthora thermophila submerged bioprocess.

Enzymes do not have long-term storage stability in soluble forms, thus drying methods could minimize the loss of enzymatic activity, the spray dryer removes water under high temperatures and little time. The aims of this study were to improve the stability of enzymatic extract from Myceliophthora thermophila for potential applications in industry and to evaluate the best conditions to remove the water by spray drying technique. The parameters were tested according to Box-Behnken and evaluated by analysis of variance (ANOVA), all the parameters measured were found to influence the final enzyme activity and spray drying process yield ranged from 38.65 to 63.75%. Enzyme powders showed increased storage stability than extract and maintained about 100% of collagenolytic activity after 180 days of storage at 30°C. The results showed that the microbial enzymes maintained activity during the spray drying process and were stable during long-term storage; these are promising characteristics for industrial applications.