SSnet: A Deep Learning Approach for Protein-Ligand Interaction Prediction.

Computational prediction of Protein-Ligand Interaction (PLI) is an important step in the modern drug discovery pipeline as it mitigates the cost, time, and resources required to screen novel therapeutics. Deep Neural Networks (DNN) have recently shown excellent performance in PLI prediction. However, the performance is highly dependent on protein and ligand features utilized for the DNN model. Moreover, in current models, the deciphering of how protein features determine the underlying principles that govern PLI is not trivial. In this work, we developed a DNN framework named SSnet that utilizes secondary structure information of proteins extracted as the curvature and torsion of the protein backbone to predict PLI. We demonstrate the performance of SSnet by comparing against a variety of currently popular machine and non-Machine Learning (ML) models using various metrics. We visualize the intermediate layers of SSnet to show a potential latent space for proteins, in particular to extract structural elements in a protein that the model finds influential for ligand binding, which is one of the key features of SSnet. We observed in our study that SSnet learns information about locations in a protein where a ligand can bind, including binding sites, allosteric sites and cryptic sites, regardless of the conformation used. We further observed that SSnet is not biased to any specific molecular interaction and extracts the protein fold information critical for PLI prediction. Our work forms an important gateway to the general exploration of secondary structure-based Deep Learning (DL), which is not just confined to protein-ligand interactions, and as such will have a large impact on protein research, while being readily accessible for de novo drug designers as a standalone package.

The Impact of Hospitality Work Environment on Employees' Turnover Intentions During COVID-19 Pandemic: The Mediating Role of Work-Family Conflict.

Employees' turnover intentions and work-family conflict as a result of the hospitality work environment are considered the major global challenges confronted by hospitality organizations, especially in the era of COVID-19. This study aims at identifying the impact of the hospitality work environment on work-family conflict (WFC), as well as turnover intentions and examining the potential mediating role of WFC in the relationship between work environment and turnover intentions, during the COVID-19 pandemic in a sample of three- and four-star resorts in Egypt. A total of 413 resorts employees from Egyptian destinations (Sharm El-Sheikh and Hurghada) participated in the study. The findings of the Structural Equation Modeling (SEM) revealed that the hospitality work environment significantly and positively affects employees' turnover intentions and WFC. In the context of the mediating role of WFC, results illustrated that WFC significantly partially mediates the relationship between the hospitality work environment and turnover intentions. Upon these findings, the study suggests that to prevent WFC and eliminate turnover intentions among resorts' employees, an urgent need to create a better work environment is vitally important. limitations and future research directions have been discussed.

Evaluating robotic-assisted surgery training videos with multi-task convolutional neural networks.

We seek to understand if an automated algorithm can replace human scoring of surgical trainees performing the urethrovesical anastomosis in radical prostatectomy with synthetic tissue. Specifically, we investigate neural networks for predicting the surgical proficiency score (GEARS score) from video clips. We evaluate videos of surgeons performing the urethral anastomosis using synthetic tissue. The algorithm tracks surgical instrument locations from video, saving the positions of key points on the instruments over time. These positional features are used to train a multi-task convolutional network to infer each sub-category of the GEARS score to determine the proficiency level of trainees. Experimental results demonstrate that the proposed method achieves good performance with scores matching manual inspection in 86.1% of all GEARS sub-categories. Furthermore, the model can detect the difference between proficiency (novice to expert) in 83.3% of videos. Evaluation of GEARS sub-categories with artificial neural networks is possible for novice and intermediate surgeons, but additional research is needed to understand if expert surgeons can be evaluated with a similar automated system.

Efficacy of Sofosbuvir plus Ledipasvir in Egyptian patients with COVID-19 compared to standard treatment: a randomized controlled trial.

COVID-19 is a pandemic disease caused by SARS-CoV-2, which is an RNA virus similar to the hepatitis C virus (HCV) in the replication process. Sofosbuvir/ledipasvir is an approved drug to treat HCV infection. This study investigates the efficacy of Sofosbuvir/ledipasvir as a treatment for patients with moderate COVID-19 infection. This is a single-blinded parallel-randomized controlled trial. The participants were randomized equally into the intervention group that received Sofosbuvir/ledipasvir (S.L. group), and the control group received Oseltamivir, Hydroxychloroquine, and Azithromycin (OCH group). The primary outcomes were the cure rate over time and the incidence of serious adverse events. The secondary outcomes included the laboratory findings. 250 patients were divided equally into each group. Both groups were similar regarding gender, but age was higher in the S.L. group (p=0.001). In the S.L. group, 89 (71.2%) patients were cured, while only 51 (40.8%) patients were cured in the OCH group. The cure rate was significantly higher in the S.L. group (RR=1.75, p<0.001). Kaplan-Meir plot showed a considerably higher cure over time in the S.L. group (Log-rank test, p=0.032). There were no deaths in the S.L. group, but there were six deaths (4.8%) in the OCH group (RR=0.08, p=0.013). Seven patients (5.6%) in the S.L. group and six patients (4.8%) in the OCH group were admitted to the intensive care unit (ICU) (RR=1.17, P=0.776). There were no significant differences between treatment groups regarding total leukocyte and neutrophils count, lymph, and urea. Sofosbuvir/ledipasvir is suggestive of being effective in treating patients with moderate COVID-19 infection. Further studies are needed to compare Sofosbuvir/ledipasvir with new treatment protocols.

Skeletal Muscle Function, Structure, and Metabolism in Patients With Heart Failure With Reduced Ejection Fraction and Heart Failure With Preserved Ejection Fraction.

BACKGROUND: Reduced exercise capacity in patients with heart failure (HF) could be partially explained by skeletal muscle dysfunction. We compared skeletal muscle function, structure, and metabolism among clinically stable outpatients with HF with preserved ejection fraction, HF with reduced ejection fraction, and healthy controls (HC). Furthermore, the molecular, metabolic, and clinical profile of patients with reduced muscle endurance was described. METHODS: Fifty-five participants were recruited prospectively at the University Hospital Jena (17 HF with preserved ejection fraction, 18 HF with reduced ejection fraction, and 20 HC). All participants underwent echocardiography, cardiopulmonary exercise testing, 6-minute walking test, isokinetic muscle function, and skeletal muscle biopsies. Expression levels of fatty acid oxidation, glucose metabolism, atrophy genes, and proteins as well as inflammatory biomarkers were assessed. Mitochondria were evaluated using electron microscopy. RESULTS: Patients with HF with preserved ejection fraction showed compared with HF with reduced ejection fraction and HC reduced muscle strength (eccentric extension: 13.3±5.0 versus 18.0±5.9 versus 17.9±5.1 Nm/kg, P=0.04), elevated levels of MSTN-2 (myostatin-2), FBXO-32 (F-box only protein 32 [Atrogin1]) gene and protein, and smaller mitochondrial size (P<0.05). Mitochondrial function and fatty acid and glucose metabolism were impaired in HF-patients compared with HC (P<0.05). In a multiple regression analysis, GDF-15 (growth and differentiation factor 15), CPT1B (carnitine palmitoyltransferase IB)-protein and oral anticoagulation were independent factors for predicting reduced muscle endurance after adjusting for age (log10 GDF-15 [pg/mL] [B, -54.3 (95% CI, -106 to -2.00), P=0.043], log10 CPT1B per fold increase [B, 49.3 (95% CI, 1.90-96.77), P=0.042]; oral anticoagulation present [B, 44.8 (95% CI, 27.90-61.78), P<0.001]). CONCLUSIONS: Patients with HF with preserved ejection fraction have worse muscle function and predominant muscle atrophy compared with those with HF with reduced ejection fraction and HC. Inflammatory biomarkers, fatty acid oxidation, and oral anticoagulation were independent factors for predicting reduced muscle endurance.

Management of calcaneal fractures using the Ilizarov external fixator.

Twenty five intra-articular fractures of the calcaneus in 25 patients were reduced through a minimal incision and fixed with an Ilizarov external fixator. The average age of patients was 38.6 years (range: 17 to 62 years). According to the Sanders CT classification, 10 (40%) were type II, 9 (36%) type III, and 6 (24%) type IV. The average follow-up was 30 months (range: 24-40 months). According to the AOFAS scale for ankle and hind foot there were 6 (24%) excellent, 11 (44%) good, 6 (24%) fair, and two (8%) poor results. The average score was 68 with a range of 48 to 92. The average length of the treatment period with the fixator was 9.7 weeks (range, 8 to 12 weeks). Radiological assessment revealed reduction malalignment < 5 degrees in 22 cases and > 10 degrees in 3 cases. The calcaneal width averaged 112% of the contralateral side. The calcaneal height was restored to 92% of the normal side, the mean (+/- SD) Böhler angle was changed from 11 degrees +/- 9 degrees preoperatively to 24 degrees +/- 5 degrees postoperatively. The most common complication was superficial skin infection at wire insertion sites. The results with this technique in a small number of non randomised cases with an average follow-up of 2.5 years seem to indicate that it could be a good alternative to traditional methods for management of intraarticular calcaneus fractures, with fewer secondary problems.