Identifying congenital generalized lipodystrophy using deep learning-DEEPLIPO.

Congenital Generalized Lipodystrophy (CGL) is a rare autosomal recessive disease characterized by near complete absence of functional adipose tissue from birth. CGL diagnosis can be based on clinical data including acromegaloid features, acanthosis nigricans, reduction of total body fat, muscular hypertrophy, and protrusion of the umbilical scar. The identification and knowledge of CGL by the health care professionals is crucial once it is associated with severe and precocious cardiometabolic complications and poor outcome. Image processing by deep learning algorithms have been implemented in medicine and the application into routine clinical practice is feasible. Therefore, the aim of this study was to identify congenital generalized lipodystrophy phenotype using deep learning. A deep learning approach model using convolutional neural network was presented as a detailed experiment with evaluation steps undertaken to test the effectiveness. These experiments were based on CGL patient's photography database. The dataset consists of two main categories (training and testing) and three subcategories containing photos of patients with CGL, individuals with malnutrition and eutrophic individuals with athletic build. A total of 337 images of individuals of different ages, children and adults were carefully chosen from internet open access database and photographic records of stored images of medical records of a reference center for inherited lipodystrophies. For validation, the dataset was partitioned into four parts, keeping the same proportion of the three subcategories in each part. The fourfold cross-validation technique was applied, using 75% (3 parts) of the data as training and 25% (1 part) as a test. Following the technique, four tests were performed, changing the parts that were used as training and testing until each part was used exactly once as validation data. As a result, a mean accuracy, sensitivity, and specificity were obtained with values of [90.85 ± 2.20%], [90.63 ± 3.53%] and [91.41 ± 1.10%], respectively. In conclusion, this study presented for the first time a deep learning model able to identify congenital generalized lipodystrophy phenotype with excellent accuracy, sensitivity and specificity, possibly being a strategic tool for detecting this disease.

Evaluation of the anti-diabetic drug sitagliptin as a novel attenuate to SARS-CoV-2 evidence-based in silico: molecular docking and molecular dynamics.

The current outbreak of COVID-19 cases worldwide has been responsible for a significant number of deaths, especially in hospitalized patients suffering from comorbidities, such as obesity, diabetes, hypertension. The disease not only has prompted an interest in the pathophysiology, but also it has propelled a massive race to find new anti-SARS-CoV-2 drugs. In this scenario, known drugs commonly used to treat other diseases have been suggested as alternative or complementary therapeutics. Herein we propose the use of sitagliptin, an inhibitor of dipeptidyl peptidase-4 (DPP4) used to treat type-II diabetes, as an agent to block and inhibit the activity of two proteases, 3CLpro and PLpro, related to the processing of SARS-CoV-2 structural proteins. Inhibition of these proteases may possibly reduce the viral load and infection on the host by hampering the synthesis of new viruses, thus promoting a better outcome. In silico assays consisting in the modeling of the ligand sitagliptin and evaluation of its capacity to interact with 3CLpro and PLpro through the prediction of the ligand bioactivity, molecular docking, overlapping of crystal structures, and molecular dynamic simulations were conducted. The experiments indicate that sitagliptin can interact and bind to both targets. However, this interaction seems to be stronger and more stable to 3CLpro (ΔG = -7.8 kcal mol-1), when compared to PLpro (ΔG = -7.5 kcal mol-1). This study suggests that sitagliptin may be suitable to treat COVID-19 patients, beyond its common use as an anti-diabetic medication. In vivo studies may further support this hypothesis. Supplementary Information: The online version contains supplementary material available at 10.1007/s13205-022-03406-w.