Interdatabase Variability in Cortical Thickness Measurements

2018 ◽  
Vol 29 (8) ◽  
pp. 3282-3293 ◽  
Author(s):  
M Ethan MacDonald ◽  
Rebecca J Williams ◽  
Nils D Forkert ◽  
Avery J L Berman ◽  
Cheryl R McCreary ◽  
...  
Keyword(s):  
Large Scale ◽  
Cross Validation ◽  
Prediction Performance ◽  
Rate Of Change ◽  
Prediction Modeling ◽  
Correlation Matrices ◽  
Cortical Thinning ◽  
Leave One Out ◽  
Thickness Measurements ◽  
Age Prediction

Abstract The phenomenon of cortical thinning with age has been well established; however, the measured rate of change varies between studies. The source of this variation could be image acquisition techniques including hardware and vendor specific differences. Databases are often consolidated to increase the number of subjects but underlying differences between these datasets could have undesired effects. We explore differences in cerebral cortex thinning between 4 databases, totaling 1382 subjects. We investigate several aspects of these databases, including: 1) differences between databases of cortical thinning rates versus age, 2) correlation of cortical thinning rates between regions for each database, and 3) regression bootstrapping to determine the effect of the number of subjects included. We also examined the effect of different databases on age prediction modeling. Cortical thinning rates were significantly different between databases in all 68 parcellated regions (ANCOVA, P < 0.001). Subtle differences were observed in correlation matrices and bootstrapping convergence. Age prediction modeling using a leave-one-out cross-validation approach showed varying prediction performance (0.64 < R2 < 0.82) between databases. When a database was used to calibrate the model and then applied to another database, prediction performance consistently decreased. We conclude that there are indeed differences in the measured cortical thinning rates between these large-scale databases.

Prediction of Microbe-drug Associations based on Chemical Structures and the KATZ Measure

2021 ◽  
Vol 16 ◽  
Author(s):  
Lingzhi Zhu ◽  
Guihua Duan ◽  
Cheng Yan ◽  
Jianxin Wang
Keyword(s):  
Computational Models ◽  
Cross Validation ◽  
Area Under The Curve ◽  
Prediction Performance ◽  
Complex Mechanism ◽  
Chemical Structures ◽  
Potential Association ◽  
Health And Disease ◽  
Leave One Out ◽  
Fold Cross Validation

Background: Microbial communities have important influences on our health and disease. Identifying potential human microbe-drug associations will be greatly advantageous to explore complex mechanisms of microbes in drug discovery, combinations and repositioning. Until now, the complex mechanism of microbe-drug associations remains unknown. Objective: Computational models play an important role in discovering hidden microbe-drug associations, because biological experiments are time-consuming and expensive. Based on chemical structures of drugs and the KATZ measure, a new computational model (HMDAKATZ) is proposed for identifying potential Human Microbe-Drug Associations. Methods: In HMDAKATZ, the similarity between microbes is computed using the Gaussian Interaction Profile (GIP) kernel based on known human microbe-drug associations. The similarity between drugs is computed based on known human microbe-drug associations and chemical structures. Then, a microbe-drug heterogeneous network is constructed by integrating the microbe-microbe network, the drug-drug network, and a known microbe-drug association network. Finally, we apply KATZ to identify potential association s between microbes and drugs. Results: The experimental results showed that HMDAKATZ achieved area under the curve (AUC) values of 0.9010±0.0020, 0.9066±0.0015, and 0.9116 in 5-fold cross validation (5-fold CV), 10-fold cross validation (10-fold CV), and leave one out cross validation (LOOCV), respectively, which outperformed four other computational models (SNMF, RLS, HGBI, and NBI). Conclusion: HMDAKATZ obtained the better prediction performance than four other methods in 5-fold CV, 10-fold CV, and LOOCV. Furthermore, three case studies also illustrated that HMDAKATZ is an effective way to discover hidden microbe-drug associations.

scholarly journals Predicting MiRNA-disease associations by multiple meta-paths fusion graph embedding model

2020 ◽  
Vol 21 (1) ◽  
Author(s):  
Lei Zhang ◽  
Bailong Liu ◽  
Zhengwei Li ◽  
Xiaoyan Zhu ◽  
Zhizhen Liang ◽  
...  
Keyword(s):  
Computational Models ◽  
Cross Validation ◽  
Complex Structure ◽  
Graph Embedding ◽  
Prostate Neoplasms ◽  
Prediction Performance ◽  
Linear Transformations ◽  
Disease Associations ◽  
Meta Path ◽  
Leave One Out

Abstract Background Many studies prove that miRNAs have significant roles in diagnosing and treating complex human diseases. However, conventional biological experiments are too costly and time-consuming to identify unconfirmed miRNA-disease associations. Thus, computational models predicting unidentified miRNA-disease pairs in an efficient way are becoming promising research topics. Although existing methods have performed well to reveal unidentified miRNA-disease associations, more work is still needed to improve prediction performance. Results In this work, we present a novel multiple meta-paths fusion graph embedding model to predict unidentified miRNA-disease associations (M2GMDA). Our method takes full advantage of the complex structure and rich semantic information of miRNA-disease interactions in a self-learning way. First, a miRNA-disease heterogeneous network was derived from verified miRNA-disease pairs, miRNA similarity and disease similarity. All meta-path instances connecting miRNAs with diseases were extracted to describe intrinsic information about miRNA-disease interactions. Then, we developed a graph embedding model to predict miRNA-disease associations. The model is composed of linear transformations of miRNAs and diseases, the means encoder of a single meta-path instance, the attention-aware encoder of meta-path type and attention-aware multiple meta-path fusion. We innovatively integrated meta-path instances, meta-path based neighbours, intermediate nodes in meta-paths and more information to strengthen the prediction in our model. In particular, distinct contributions of different meta-path instances and meta-path types were combined with attention mechanisms. The data sets and source code that support the findings of this study are available at https://github.com/dangdangzhang/M2GMDA. Conclusions M2GMDA achieved AUCs of 0.9323 and 0.9182 in global leave-one-out cross validation and fivefold cross validation with HDMM V2.0. The results showed that our method outperforms other prediction methods. Three kinds of case studies with lung neoplasms, breast neoplasms, prostate neoplasms, pancreatic neoplasms, lymphoma and colorectal neoplasms demonstrated that 47, 50, 49, 48, 50 and 50 out of the top 50 candidate miRNAs predicted by M2GMDA were validated by biological experiments. Therefore, it further confirms the prediction performance of our method.

scholarly journals Prioritizing Disease-Related Microbes Based on the Topological Properties of a Comprehensive Network

2021 ◽  
Vol 12 ◽  
Author(s):  
Haixiu Yang ◽  
Fan Tong ◽  
Changlu Qi ◽  
Ping Wang ◽  
Jiangyu Li ◽  
...  
Keyword(s):  
High Performance ◽  
Large Scale ◽  
Cross Validation ◽  
Area Under The Curve ◽  
Disease Pathogenesis ◽  
Physiological Processes ◽  
Disease Associations ◽  
Inflammatory Bowel ◽  
Leave One Out ◽  
Insight Into

Many microbes are parasitic within the human body, engaging in various physiological processes and playing an important role in human diseases. The discovery of new microbe–disease associations aids our understanding of disease pathogenesis. Computational methods can be applied in such investigations, thereby avoiding the time-consuming and laborious nature of experimental methods. In this study, we constructed a comprehensive microbe–disease network by integrating known microbe–disease associations from three large-scale databases (Peryton, Disbiome, and gutMDisorder), and extended the random walk with restart to the network for prioritizing unknown microbe–disease associations. The area under the curve values of the leave-one-out cross-validation and the fivefold cross-validation exceeded 0.9370 and 0.9366, respectively, indicating the high performance of this method. Despite being widely studied diseases, in case studies of inflammatory bowel disease, asthma, and obesity, some prioritized disease-related microbes were validated by recent literature. This suggested that our method is effective at prioritizing novel disease-related microbes and may offer further insight into disease pathogenesis.

scholarly journals Deep Neural Regression Prediction of Motor Imagery Skills Using EEG Functional Connectivity Indicators

Sensors ◽  
2021 ◽  
Vol 21 (6) ◽  
pp. 1932
Author(s):  
Julian Caicedo-Acosta ◽  
German A. Castaño ◽  
Carlos Acosta-Medina ◽  
Andres Alvarez-Meza ◽  
German Castellanos-Dominguez
Keyword(s):  
Neural Network ◽  
Monte Carlo ◽  
Functional Connectivity ◽  
Cross Validation ◽  
Prediction Performance ◽  
Initial Training ◽  
High Prediction ◽  
Eeg Functional Connectivity ◽  
Leave One Out ◽  
The Relationship

Motor imaging (MI) induces recovery and neuroplasticity in neurophysical regulation. However, a non-negligible portion of users presents insufficient coordination skills of sensorimotor cortex control. Assessments of the relationship between wakefulness and tasks states are conducted to foster neurophysiological and mechanistic interpretation in MI-related applications. Thus, to understand the organization of information processing, measures of functional connectivity are used. Also, models of neural network regression prediction are becoming popular, These intend to reduce the need for extracting features manually. However, predicting MI practicing’s neurophysiological inefficiency raises several problems, like enhancing network regression performance because of the overfitting risk. Here, to increase the prediction performance, we develop a deep network regression model that includes three procedures: leave-one-out cross-validation combined with Monte Carlo dropout layers, subject clustering of MI inefficiency, and transfer learning between neighboring runs. Validation is performed using functional connectivity predictors extracted from two electroencephalographic databases acquired in conditions close to real MI applications (150 users), resulting in a high prediction of pretraining desynchronization and initial training synchronization with adequate physiological interpretability.

scholarly journals Measuring and inferring the ice thickness distribution of four glaciers in the Tien Shan, Kyrgyzstan

2020 ◽  
pp. 1-18
Author(s):  
Lander Van Tricht ◽  
Philippe Huybrechts ◽  
Jonas Van Breedam ◽  
Johannes J. Fürst ◽  
Oleg Rybak ◽  
...  
Keyword(s):  
Cross Validation ◽  
Thickness Distribution ◽  
Tien Shan ◽  
Ice Thickness ◽  
Ice Volume ◽  
In Situ Data ◽  
Radio Echo Sounding ◽  
Thickness Measurements ◽  
Tien Shan Mountains

Abstract Glaciers in the Tien Shan mountains contribute considerably to the fresh water used for irrigation, households and energy supply in the dry lowland areas of Kyrgyzstan and its neighbouring countries. To date, reconstructions of the current ice volume and ice thickness distribution remain scarce, and accurate data are largely lacking at the local scale. Here, we present a detailed ice thickness distribution of Ashu-Tor, Bordu, Golubin and Kara-Batkak glaciers derived from radio-echo sounding measurements and modelling. All the ice thickness measurements are used to calibrate three individual models to estimate the ice thickness in inaccessible areas. A cross-validation between modelled and measured ice thickness for a subset of the data is performed to attribute a weight to every model and to assemble a final composite ice thickness distribution for every glacier. Results reveal the thickest ice on Ashu-Tor glacier with values up to 201 ± 12 m. The ice thickness measurements and distributions are also compared with estimates composed without the use of in situ data. These estimates approach the total ice volume well, but local ice thicknesses vary substantially.

scholarly journals Effects of Climatic Drivers and Teleconnections on Late 20th Century Trends in Spring Freshet of Four Major Arctic-Draining Rivers

Water ◽  
2021 ◽  
Vol 13 (2) ◽  
pp. 179
Author(s):  
Roxanne Ahmed ◽  
Terry Prowse ◽  
Yonas Dibike ◽  
Barrie Bonsal
Keyword(s):  
Arctic Ocean ◽  
Large Scale ◽  
Southern Oscillation ◽  
Rate Of Change ◽  
The Arctic ◽  
Late 20Th Century ◽  
Basin Scale ◽  
The Arctic Ocean ◽  
Spring Freshet ◽  
Climatic Drivers

Spring freshet is the dominant annual discharge event in all major Arctic draining rivers with large contributions to freshwater inflow to the Arctic Ocean. Research has shown that the total freshwater influx to the Arctic Ocean has been increasing, while at the same time, the rate of change in the Arctic climate is significantly higher than in other parts of the globe. This study assesses the large-scale atmospheric and surface climatic conditions affecting the magnitude, timing and regional variability of the spring freshets by analyzing historic daily discharges from sub-basins within the four largest Arctic-draining watersheds (Mackenzie, Ob, Lena and Yenisei). Results reveal that climatic variations closely match the observed regional trends of increasing cold-season flows and earlier freshets. Flow regulation appears to suppress the effects of climatic drivers on freshet volume but does not have a significant impact on peak freshet magnitude or timing measures. Spring freshet characteristics are also influenced by El Niño-Southern Oscillation, the Pacific Decadal Oscillation, the Arctic Oscillation and the North Atlantic Oscillation, particularly in their positive phases. The majority of significant relationships are found in unregulated stations. This study provides a key insight into the climatic drivers of observed trends in freshet characteristics, whilst clarifying the effects of regulation versus climate at the sub-basin scale.

Mapping Arctic clam abundance using multiple datasets, models, and a spatially explicit accuracy assessment

2019 ◽  
Vol 76 (7) ◽  
pp. 2349-2361
Author(s):  
Benjamin Misiuk ◽  
Trevor Bell ◽  
Alec Aitken ◽  
Craig J Brown ◽  
Evan N Edinger
Keyword(s):  
Spatial Autocorrelation ◽  
Cross Validation ◽  
Predictive Accuracy ◽  
Accuracy Assessment ◽  
Small Scale ◽  
Suitable Habitat ◽  
Distribution Models ◽  
Management Tools ◽  
Seabed Topography ◽  
Leave One Out

Abstract Species distribution models are commonly used in the marine environment as management tools. The high cost of collecting marine data for modelling makes them finite, especially in remote locations. Underwater image datasets from multiple surveys were leveraged to model the presence–absence and abundance of Arctic soft-shell clam (Mya spp.) to support the management of a local small-scale fishery in Qikiqtarjuaq, Nunavut, Canada. These models were combined to predict Mya abundance, conditional on presence throughout the study area. Results suggested that water depth was the primary environmental factor limiting Mya habitat suitability, yet seabed topography and substrate characteristics influence their abundance within suitable habitat. Ten-fold cross-validation and spatial leave-one-out cross-validation (LOO CV) were used to assess the accuracy of combined predictions and to test whether this was inflated by the spatial autocorrelation of transect sample data. Results demonstrated that four different measures of predictive accuracy were substantially inflated due to spatial autocorrelation, and the spatial LOO CV results were therefore adopted as the best estimates of performance.

scholarly journals Equatorial ionospheric disturbance observed through a transequatorial HF propagation experiment

2006 ◽  
Vol 24 (5) ◽  
pp. 1401-1409 ◽  
Author(s):  
T. Maruyama ◽  
M. Kawamura
Keyword(s):  
Large Scale ◽  
Ionospheric Disturbance ◽  
Great Circle ◽  
Rate Of Change ◽  
Spatial Distance ◽  
Propagation Path ◽  
Multiple Signal Classification ◽  
Radio Broadcasting ◽  
Equatorial Plasma Bubbles ◽  
Propagation Experiment

Abstract. A transequatorial radio-wave propagation experiment at shortwave frequencies (HF-TEP) was done between Shepparton, Australia, and Oarai, Japan, using the radio broadcasting signals of Radio Australia. The receiving facility at Oarai was capable of direction finding based on the MUSIC (Multiple Signal Classification) algorithm. The results were plotted in azimuth-time diagrams (AT plots). During the daytime, the propagation path was close to the great circle connecting Shepparton and Oarai, thus forming a single line in the AT plots. After sunset, off-great-circle paths, or satellite traces in the AT plot, often appeared abruptly to the west and gradually returned to the great circle direction. However, there were very few signals across the great circle to the east. The off-great-circle propagation was very similar to that previously reported and was attributed to reflection by an ionospheric structure near the equator. From the rate of change in the direction, we estimated the drift velocity of the structure to range mostly from 100 to 300 m/s eastward. Multiple instances of off-great-circle propagation with a quasi-periodicity were often observed and their spatial distance in the east-west direction was within the range of large-scale traveling ionospheric disturbances (LS-TIDs). Off-great-circle propagation events were frequently observed in the equinox seasons. Because there were many morphological similarities, the events were attributed to the onset of equatorial plasma bubbles.

Sign in / Sign up

Export Citation Format

Share Document