Gravesenratliff3582

An amendment to this paper has been published and can be accessed via a link at the top of the paper.An amendment to this paper has been published and can be accessed via a link at the top of the paper.Machine learning is a well-known approach for virtual screening. Recently, deep learning, a machine learning algorithm in artificial neural networks, has been applied to the advancement of precision medicine and drug discovery. In this study, we performed comparative studies between deep neural networks (DNN) and other ligand-based virtual screening (LBVS) methods to demonstrate that DNN and random forest (RF) were superior in hit prediction efficiency. By using DNN, several triple-negative breast cancer (TNBC) inhibitors were identified as potent hits from a screening of an in-house database of 165,000 compounds. In broadening the application of this method, we harnessed the predictive properties of trained model in the discovery of G protein-coupled receptor (GPCR) agonist, by which computational structure-based design of molecules could be greatly hindered by lack of structural information. Notably, a potent (~ 500 nM) mu-opioid receptor (MOR) agonist was identified as a hit from a small-size training set of 63 compounds. Our results show that DNN could be an efficient module in hit prediction and provide experimental evidence that machine learning could identify potent hits in silico from a limited training set.Endosymbionts and intracellular parasites are common in arthropod hosts. As a consequence, (co)amplification of untargeted bacterial sequences has been occasionally reported as a common problem in DNA barcoding. While identifying amphipod species with universal COI primers, we unexpectedly detected rickettsial endosymbionts belonging to the Torix group. To map the distribution and diversity of Rickettsia species among amphipod hosts, we conducted a nationwide molecular screening of seven families of New Zealand freshwater amphipods. In addition to uncovering a diversity of Torix Rickettsia species across multiple amphipod populations from three different families, our research indicates that (1) detecting Torix Rickettsia with universal primers is not uncommon, (2) obtaining 'Rickettsia COI sequences' from many host individuals is highly likely when a population is infected, and (3) obtaining 'host COI' may not be possible with a conventional PCR if an individual is infected. Because Rickettsia COI is highly conserved across diverse host taxa, we were able to design blocking primers that can be used in a wide range of host species infected with Torix Rickettsia. We propose the use of blocking primers to circumvent problems caused by unwanted amplification of Rickettsia and to obtain targeted host COI sequences for DNA barcoding, population genetics, and phylogeographic studies.Prognostic models play an important role in the clinical management of cervical radiculopathy (CR). No study has compared the performance of modern machine learning techniques, against more traditional stepwise regression techniques, when developing prognostic models in individuals with CR. We analysed a prospective cohort dataset of 201 individuals with CR. Four modelling techniques (stepwise regression, least absolute shrinkage and selection operator [LASSO], boosting, and multivariate adaptive regression splines [MuARS]) were each used to form a prognostic model for each of four outcomes obtained at a 12 month follow-up (disability-neck disability index [NDI]), quality of life (EQ5D), present neck pain intensity, and present arm pain intensity). For all four outcomes, the differences in mean performance between all four models were small (difference of NDI  less then  1 point; EQ5D  less then  0.1 point; neck and arm pain  less then  2 points). Given that the predictive accuracy of all four modelling methods were clinically similar, the optimal modelling method may be selected based on the parsimony of predictors. Some of the most parsimonious models were achieved using MuARS, a non-linear technique. Modern machine learning methods may be used to probe relationships along different regions of the predictor space.Radiographic osteoarthritis (OA) is most prevalent in the hand. The association of hand injury with pain or OA is unclear. The objective was to describe the relationship between hand injury and ipsilateral pain and OA in cricketers. Data from former and current cricketers aged ≥ 30 years was used. Data included history of cricket-related hand/finger injury leading to > 4 weeks of reduced exercise, hand/finger joint pain on most days of the last month, self-reported history of physician-diagnosed hand/finger OA. Logistic regression assessed the relationship between injury with hand pain (in former cricketers) and with OA (in all cricketers), adjusted for age, seasons played, playing standard. Of 1893 participants (844 former cricketers), 16.9% reported hand pain, 4.3% reported OA. A history of hand injury increased the odds of hand pain (OR (95% CI) 2.2, 1.4 to 3.6). A history of hand injury also had increased odds of hand OA (3.1, 2.1 to 4.7). Cricket-related hand injury was related to an increased odds of hand pain and OA. This highlights the importance of hand injury prevention strategies within cricket. The high prevalence of hand pain is concerning, and further research is needed to determine the impacts of hand pain.Cholangiocarcinoma (CCA) is a serious health challenge with low survival prognosis. The liver fluke, Opisthorchis viverrini, plays a role in the aetiology of CCA, through hepatobiliary abnormalities liver mass (LM), bile duct dilation, and periductal fibrosis (PDF). A population-based CCA screening program, the Cholangiocarcinoma Screening and Care Program, operates in Northeast Thailand. Hepatobiliary abnormalities were identified through ultrasonography. A multivariate zero-inflated, Poisson regression model measured associations between hepatobiliary abnormalities and covariates including age, sex, distance to water resource, and history of O. viverrini infection. Geographic distribution was described using Bayesian spatial analysis methods. Hepatobiliary abnormality prevalence was 38.7%; highest in males aged > 60 years (39.8%). read more PDF was most prevalent (20.1% of males). The Standardized Morbidity Ratio (SMR) for hepatobiliary abnormalities was highest in the lower and upper parts of the Northeast region. Hepatobiliary abnormalities specifically associated with CCA were also more common in males and those aged over 60 years and distributed along the Chi, Mun, and Songkram Rivers.