In order to test our predictions, we implement the 'induced beliefs method' and a within-subjects design, using the strategy method.
To demonstrate the predictive potential of our top prediction, we implemented computational models to distinguish MI from control samples using this gene's expression data.
For genome-wide prediction, we implemented ridge regression best linear unbiased prediction (RR-BLUP), modeling both additive and dominance effects as: Y={1}_nmu +{Z}_A a+{Z}_D d+ e. Y refers to BLUEs of the hybrids for grain yield.
For target sequence prediction, we implemented a combined target prediction using three common prediction algorithms, miRanda, RNAhybrid and SeedMatch.
To enhance the accuracy for miRNA target prediction, we implemented the 'context score' concept during the target prediction process.
To quantify the reliability of the predictions and assess which parameters are important to achieve a reliable prediction, we implemented a RF approach (Fig. 1c).
In order to evaluate the effect of sparsification on pseudoknotted RNA secondary structure prediction, we implemented original and sparsified variants of the Reeder and Giegerich (R&G) algorithm.
To facilitate the allergen prediction, we implemented our computational method in a web application, which can be available at http://gmobl.sjtu.edu.cn/PREAL/index.php.sjtu.edu.cn/PREAL/index.php
To calculate a tree from the TFBS predictions, we have implemented an interface to MrBayes [ 18, 19].
To fasten the predictions, we have implemented three separate queue systems, one each for vacuum, hydrophilic and hydrophobic environments.
