Motivation Machine-learning-based prediction of compound–protein interactions (CPIs) is important for drug design, screening and repurposing. Despite numerous recent publication with increasing methodological sophistication claiming consistent improvements in predictive accuracy, we have observed a number of fundamental issues in experiment design that produce overoptimistic estimates of model performance. Results We systematically analyze the impact of several factors affecting generalization performance of CPI predictors that are overlooked in existing work: (i) similarity between training and test examples in cross-validation; (ii) synthesizing negative examples in absence of experimentally verified negative examples and (iii) alignment of evaluation protocol and performance metrics with real-world use of CPI predictors in screening large compound libraries. Using both state-of-the-art approaches by other researchers as well as a simple kernel-based baseline, we have found that effective assessment of generalization performance of CPI predictors requires careful control over similarity between training and test examples. We show that, under stringent performance assessment protocols, a simple kernel-based approach can exceed the predictive performance of existing state-of-the-art methods. We also show that random pairing for generating synthetic negative examples for training and performance evaluation results in models with better generalization in comparison to more sophisticated strategies used in existing studies. Our analyses indicate that using proposed experiment design strategies can offer significant improvements for CPI prediction leading to effective target compound screening for drug repurposing and discovery of putative chemical ligands of SARS-CoV-2-Spike and Human-ACE2 proteins. Availability and implementation Code and supplementary material available at https://github.com/adibayaseen/HKRCPI. Supplementary information Supplementary data are available at Bioinformatics online.
Most of the Thermal (Infrared) cameras nowadays are equipped with a motorized lens for focusing a scene manually. The subjective nature of manual focusing makes it an inefficient and cumbersome process. In contrast, Autofocusing (AF) obtains the best focused image based on a quantitative measure with the benefits of convenience and intelligence. Various AF systems for visual cameras have been developed, but relatively less amount of work has been done for thermal imaging systems. This paper presents a Vision and Control based Autofocusing System (VCAFS) comprising: (1) an uncooled thermal camera with motorized lens, (2) a passive contrast-based focus measure, (3) a smoothing operator to avoid local extrema, and (4) two different lens motion controllers. Experimental results show the efficacy of the proposed system on live videos even when the scene and its depth are continuously changing. INDEX TERMS Contrast detection, Focus measures, Passive Autofocusing, Thermal imaging system.
High ambient temperature is one of the most alarming climatic factors in challenging the productivity and sustainability of crops worldwide. An effective way to cope this problem is the development of climate smart, heat resilient maize hybrids through evaluating the cultivated germplasm. The main objective of current study was to evaluate local and multinational maize hybrids for their performance under optimal and heat stress conditions and to devise a selection criterion for the identification of heat tolerant maize hybrids. Nine maize hybrids, including local and multinational, were evaluated under optimal and heat stress conditions across three consecutive spring seasons (2017-18, 2018-19 and 2019-20) at Maize and Millets Research Institute, Yusafwala, Sahiwal. Results revealed the presence of highly significant differences among maize hybrids under both conditions and for all three seasons. Kernel yield was found to be highly correlated with net photosynthetic rate (0.735 ** ), shelling percentage (0.910 ** ) and relative cell injury percentage (-0.775 ** ) under stress conditions. Cluster and biplot analysis unveiled that two local maize hybrids YH-5507 and YH-5427 were highly heat tolerant while multinational hybrids i.e. NK-8711, P-1543 and DK-6724 were highly productive under control/optimal conditions only. These hybrids can be invaluable sources of genes/alleles for the development of climate smart maize genotypes.
Objective: To evaluate the prevalence of extensively drug-resistant Salmonella typhi (XDR) in RMU Allied Hospitals. Study Design: A descriptive cross-sectional study. Material and Methods: It is a cross-sectional, prospective study conducted at RMU Allied Hospitals from January 2019–December 2019. Blood culture samples were received in the pathology lab, they were collected by simple random sampling and processed by conventional incubation. Antibiotic susceptibility of the isolates was done on Muller Hinton agar using modified Kirby Bauer disk diffusion method and antibiotic zone diameters were measured according to CLSI guidelines. Results: Out of the total 8045 cultures, 911 (11%) showed growth, among which 179 (20%) were Salmonella typhi and 135 (15%) XDR Salmonella. Meropenem revealed the highest sensitivity, Chloramphenicol, and Augmentin revealed the highest resistance. Conclusion: Blood culture results revealed Salmonella typhi 20% with a significant number of XDR Salmonella 15%. Antibiotics susceptibility pattern exhibits Meropenem and Azithromycin as the only antibiotics for XDR Salmonella. Salmonella typhi infection has a significantly high prevalence among children as compared to adults. (p=0.0017) Injudicious use of antibiotics is one of the important aspects of the occurrence of antibiotic-resistant Salmonella.
Avian polyomavirus (APV) infection, also called as budgerigar fledgling disease (BFD) causes various health problems in many psittacine species which may cause untimely death. The aims of this study were to investigate, for the first time, the detection, molecular characterization and phylogenetic analysis of avian polyomavirus (APV) in Pakistani psittacine birds. In an aviary a disease similar to APV was found and 90% of the nestlings died within a few weeks. Seven to ten-day-old parrot nestlings (n = 3) from the aviary were presented with feather abnormalities, plumage defect and were clinically depressed. Birds died at 11th, 14th and 16th day of age. Samples of hearts, livers, spleen, feathers and kidneys were collected from the dead birds. Samples were analyzed for the presence of APV DNA by using PCR. APV VP1 gene was partially sequenced, and phylogenetic analysis was performed. The APV strain was similar to those previously reported in other areas of the world. The results of this investigation indicate presence of a high frequency of APV infections in psittacine birds in Pakistan.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.