Training data composition affects performance of protein structure analysis algorithms.
Ontology highlight
ABSTRACT:
SUBMITTER: Derry A
PROVIDER: S-EPMC8669736 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:The effects of High-Intensity Functional Training (HIFT) on body composition and the relationship of the latter with performance are not well defined. In this work we investigated, by means of Dual-energy X-ray Absorptiometry, the relative proportions of fat-, lean soft tissue-, and mineral mass in CrossFit® (CF, a popular mode of HIFT) participants (n = 24; age, 28.2 ± 3.39 y; BMI, 25.3 ± 2.04 kg/m2) with at least 1 year of CF training experience and weekly amount of training > 10 h/w (n = 13; Higher Training, HT) or < 10 h/w (n = 11; Lower Training, LT) as well as age- matched and BMI-matched physically active controls (CHT, CLT). Performance was assessed in the "Fran" workout. Data were analyzed by one-way or repeated measures ANOVA where needed. Association between variables was assessed with the Pearson's correlation coefficient r. Partial correlation was used where needed. Results showed that HT performed better than LT in the "Fran" (P < 0.001) and they had higher whole-body bone mineral density (P = 0.026) and higher lean soft mass (P = 0.002), and borderline lower percent fat mass (P = 0.050). The main difference between CF participants (HT, LT) and their respective controls (CHT, CLT) was a lower adiposity in the former. In CF participants, performance positively correlated with appendicular lean soft tissue mass (P = 0.030). It can be concluded that, in CF participants, a higher amount of weekly training improves most notably lean body mass and increases performance in association with increased skeletal muscle mass. CF participation is especially effective in reducing fat mass vs. age- and BMI-matched physically active controls.
| S-EPMC7440620 | biostudies-literature
Project description:Supervised machine learning algorithms are used by life scientists for a variety of objectives. Expert-curated public gene and protein databases are major resources for gathering data to train these algorithms. While these data resources are continuously updated, generally, these updates are not incorporated into published machine learning algorithms which thereby can become outdated soon after their introduction. In this paper, we propose a new model of operation for supervised machine learning algorithms that learn from genomic data. By defining these algorithms in a pipeline in which the training data gathering procedure and the learning process are automated, one can create a system that generates a classifier or predictor using information available from public resources. The proposed model is explained using three case studies on SignalP, MemLoci, and ApicoAP in which existing machine learning models are utilized in pipelines. Given that the vast majority of the procedures described for gathering training data can easily be automated, it is possible to transform valuable machine learning algorithms into self-evolving learners that benefit from the ever-changing data available for gene products and to develop new machine learning algorithms that are similarly capable.
| S-EPMC4324891 | biostudies-literature
Project description:BackgroundPerfusion quantification by using first-pass gadolinium-enhanced myocardial perfusion magnetic resonance imaging (MRI) has proved to be a reliable tool for the diagnosis of coronary artery disease that leads to reduced blood flow to the myocardium. The image series resulting from such acquisition usually exhibits a breathing motion that needs to be compensated for if a further automatic analysis of the perfusion is to be executed. Various algorithms have been presented to facilitate such a motion compensation, but the lack of publicly available data sets hinders a proper, reproducible comparison of these algorithms.MaterialFree breathing perfusion MRI series of ten patients considered clinically to have a stress perfusion defect were acquired; for each patient a rest and a stress study was executed. Manual segmentations of the left ventricle myocardium and the right-left ventricle insertion point are provided for all images in order to make a unified validation of the motion compensation algorithms and the perfusion analysis possible. In addition, all the scripts and the software required to run the experiments are provided alongside the data, and to enable interested parties to directly run the experiments themselves, the test bed is also provided as a virtual hard disk.FindingsTo illustrate the utility of the data set two motion compensation algorithms with publicly available implementations were applied to the data and earlier reported results about the performance of these algorithms could be confirmed.ConclusionThe data repository alongside the evaluation test bed provides the option to reliably compare motion compensation algorithms for myocardial perfusion MRI. In addition, we encourage that researchers add their own annotations to the data set, either to provide inter-observer comparisons of segmentations, or to make other applications possible, for example, the validation of segmentation algorithms.
| S-EPMC4226922 | biostudies-literature
Project description:The detection, identification, and localization of illicit nuclear materials in urban environments is of utmost importance for national security. Most often, the process of performing these operations consists of a team of trained individuals equipped with radiation detection devices that have built-in algorithms to alert the user to the presence nuclear material and, if possible, to identify the type of nuclear material present. To encourage the development of new detection, radioisotope identification, and source localization algorithms, a dataset consisting of realistic Monte Carlo-simulated radiation detection data from a 2 in. × 4 in. × 16 in. NaI(Tl) scintillation detector moving through a simulated urban environment based on Knoxville, Tennessee, was developed and made public in the form of a Topcoder competition. The methodology used to create this dataset has been verified using experimental data collected at the Fort Indiantown Gap National Guard facility. Realistic signals from special nuclear material and industrial and medical sources are included in the data for developing and testing algorithms in a dynamic real-world background.
| S-EPMC7536201 | biostudies-literature
Project description:ObjectiveTo identify non-EEG-based signals and algorithms for detection of motor and non-motor seizures in people lying in bed during video-EEG (VEEG) monitoring and to test whether these algorithms work in freely moving people during mobile EEG recordings.MethodsData of three groups of adult people with epilepsy (PwE) were analyzed. Group 1 underwent VEEG with additional devices (accelerometry, ECG, electrodermal activity); group 2 underwent VEEG; and group 3 underwent mobile EEG recordings both including one-lead ECG. All seizure types were analyzed. Feature extraction and machine-learning techniques were applied to develop seizure detection algorithms. Performance was expressed as sensitivity, precision, F1 score, and false positives per 24 hours.ResultsThe algorithms were developed in group 1 (35 PwE, 33 seizures) and achieved best results (F1 score 56%, sensitivity 67%, precision 45%, false positives 0.7/24 hours) when ECG features alone were used, with no improvement by including accelerometry and electrodermal activity. In group 2 (97 PwE, 255 seizures), this ECG-based algorithm largely achieved the same performance (F1 score 51%, sensitivity 39%, precision 73%, false positives 0.4/24 hours). In group 3 (30 PwE, 51 seizures), the same ECG-based algorithm failed to meet up with the performance in groups 1 and 2 (F1 score 27%, sensitivity 31%, precision 23%, false positives 1.2/24 hours). ECG-based algorithms were also separately trained on data of groups 2 and 3 and tested on the data of the other groups, yielding maximal F1 scores between 8% and 26%.SignificanceOur results suggest that algorithms based on ECG features alone can provide clinically meaningful performance for automatic detection of all seizure types. Our study also underscores that the circumstances under which such algorithms were developed, and the selection of the training and test data sets need to be considered and limit the application of such systems to unseen patient groups behaving in different conditions.
| S-EPMC8408591 | biostudies-literature
Project description:BACKGROUND:Recent advancements in high-throughput sequencing technologies have generated an unprecedented amount of genomic data that must be stored, processed, and transmitted over the network for sharing. Lossy genomic data compression, especially of the base quality values of sequencing data, is emerging as an efficient way to handle this challenge due to its superior compression performance compared to lossless compression methods. Many lossy compression algorithms have been developed for and evaluated using DNA sequencing data. However, whether these algorithms can be used on RNA sequencing (RNA-seq) data remains unclear. RESULTS:In this study, we evaluated the impacts of lossy quality value compression on common RNA-seq data analysis pipelines including expression quantification, transcriptome assembly, and short variants detection using RNA-seq data from different species and sequencing platforms. Our study shows that lossy quality value compression could effectively improve RNA-seq data compression. In some cases, lossy algorithms achieved up to 1.2-3 times further reduction on the overall RNA-seq data size compared to existing lossless algorithms. However, lossy quality value compression could affect the results of some RNA-seq data processing pipelines, and hence its impacts to RNA-seq studies cannot be ignored in some cases. Pipelines using HISAT2 for alignment were most significantly affected by lossy quality value compression, while the effects of lossy compression on pipelines that do not depend on quality values, e.g., STAR-based expression quantification and transcriptome assembly pipelines, were not observed. Moreover, regardless of using either STAR or HISAT2 as the aligner, variant detection results were affected by lossy quality value compression, albeit to a lesser extent when STAR-based pipeline was used. Our results also show that the impacts of lossy quality value compression depend on the compression algorithms being used and the compression levels if the algorithm supports setting of multiple compression levels. CONCLUSIONS:Lossy quality value compression can be incorporated into existing RNA-seq analysis pipelines to alleviate the data storage and transmission burdens. However, care should be taken on the selection of compression tools and levels based on the requirements of the downstream analysis pipelines to avoid introducing undesirable adverse effects on the analysis results.
| S-EPMC7372835 | biostudies-literature
Project description:BackgroundGenome-sequencing projects are currently producing an enormous amount of new sequences and cause the rapid increasing of protein sequence databases. The unsupervised classification of these data into functional groups or families, clustering, has become one of the principal research objectives in structural and functional genomics. Computer programs to automatically and accurately classify sequences into families become a necessity. A significant number of methods have addressed the clustering of protein sequences and most of them can be categorized in three major groups: hierarchical, graph-based and partitioning methods. Among the various sequence clustering methods in literature, hierarchical and graph-based approaches have been widely used. Although partitioning clustering techniques are extremely used in other fields, few applications have been found in the field of protein sequence clustering. It is not fully demonstrated if partitioning methods can be applied to protein sequence data and if these methods can be efficient compared to the published clustering methods.MethodsWe developed four partitioning clustering approaches using Smith-Waterman local-alignment algorithm to determine pair-wise similarities of sequences. Four different sets of protein sequences were used as evaluation data sets for the proposed methods.ResultsWe show that these methods outperform several other published clustering methods in terms of correctly predicting a classifier and especially in terms of the correctness of the provided prediction. The software is available to academic users from the authors upon request.
| S-EPMC2678123 | biostudies-literature
Project description:Esports as the competitive play of digital games has gained considerable popularity. However, a comprehensive framework for esport training is still missing. In this paper, a performance model integrating insights from game research and sport science is developed. Based on this model, an online questionnaire was designed and applied to investigate training in different esports regarding relevant competencies and training areas. Overall, 1,835 esports players voluntarily participated in the study. Age ranged from 13 to 47 years (M = 20,9; SD = 4,5), and males clearly dominated (95%). Furthermore, the mean weakly playing time was 20.03 hours (SD = 15.8). Training occupied 38.85% (7.75 h) of the playing time on average. On the one hand, the results reveal game-specific competence and training structures in the five esports selected for the study (Starcraft II, League of Legends, Rocket League, FIFA, and Counter Strike). On the other hand, the factor structure of competencies closely resembles the esports performance model. As a conclusion, esports training methods should always consider the specific competence profile of the respective esports game.
| S-EPMC7447068 | biostudies-literature
Project description:BACKGROUND:Mapping tropical forest structure is a critical requirement for accurate estimation of emissions and removals from land use activities. With the availability of a wide range of remote sensing imagery of vegetation characteristics from space, development of finer resolution and more accurate maps has advanced in recent years. However, the mapping accuracy relies heavily on the quality of input layers, the algorithm chosen, and the size and quality of inventory samples for calibration and validation. RESULTS:By using airborne lidar data as the "truth" and focusing on the mean canopy height (MCH) as a key structural parameter, we test two commonly-used non-parametric techniques of maximum entropy (ME) and random forest (RF) for developing maps over a study site in Central Gabon. Results of mapping show that both approaches have improved accuracy with more input layers in mapping canopy height at 100 m (1-ha) pixels. The bias-corrected spatial models further improve estimates for small and large trees across the tails of height distributions with a trade-off in increasing overall mean squared error that can be readily compensated by increasing the sample size. CONCLUSIONS:A significant improvement in tropical forest mapping can be achieved by weighting the number of inventory samples against the choice of image layers and the non-parametric algorithms. Without future satellite observations with better sensitivity to forest biomass, the maps based on existing data will remain slightly biased towards the mean of the distribution and under and over estimating the upper and lower tails of the distribution.
| S-EPMC4996895 | biostudies-literature
Project description:BackgroundThe development of algorithms to infer the structure of gene regulatory networks based on expression data is an important subject in bioinformatics research. Validation of these algorithms requires benchmark data sets for which the underlying network is known. Since experimental data sets of the appropriate size and design are usually not available, there is a clear need to generate well-characterized synthetic data sets that allow thorough testing of learning algorithms in a fast and reproducible manner.ResultsIn this paper we describe a network generator that creates synthetic transcriptional regulatory networks and produces simulated gene expression data that approximates experimental data. Network topologies are generated by selecting subnetworks from previously described regulatory networks. Interaction kinetics are modeled by equations based on Michaelis-Menten and Hill kinetics. Our results show that the statistical properties of these topologies more closely approximate those of genuine biological networks than do those of different types of random graph models. Several user-definable parameters adjust the complexity of the resulting data set with respect to the structure learning algorithms.ConclusionThis network generation technique offers a valid alternative to existing methods. The topological characteristics of the generated networks more closely resemble the characteristics of real transcriptional networks. Simulation of the network scales well to large networks. The generator models different types of biological interactions and produces biologically plausible synthetic gene expression data.
| S-EPMC1373604 | biostudies-literature