In one dataset based on oxBS-seq technology, 17% of CpG sites captured by reduced representation bisulfite sequencing (RRBS) and oxRRBS experiments exhibited overshoot (Booth et al., 2012).
However, our method outperforms a machine learning approach based on a SVM in one dataset and has comparable performance with the other, for larger training sets.
Informally, our approach may be considered as a 'correlated clustering' model, in which the allocation of genes to clusters in one dataset has an influence on the allocation of genes to clusters in another.
Considering the different types of samples that were mixed in one dataset, we also classified them into refined sub-groups based on the sample information that is abstracted above.
On the other hand, it is reasonable to assume that appearance in one dataset is negatively correlated with appearance in the other, as the NPFS was introduced to relieve pressure on GPs.
All this information is also easily accessible in one dataset which simplifies subsequent M&E.
This holds true also for other tested metrics such as S-CIELAB and PSNR-HVS-M, but not for SSIM and VSNR which show very high correlation in one dataset and very low in an another one.
The spatial point pattern test operates in such a way to create variability in one dataset by sampling at 85%% in order to generate nonparametric confidence intervals for statistical testing: comparing this test dataset to a baseline spatial distribution.
In one dataset the address there might be only the street name, while other datasets might include the street, umber and country, although they are both describing the actual address.
The compounds were put together in one dataset and duplicated structures reported as being active against more than one target were removed in order to have unique active compounds on each target class.
The chorda tympani could not be identified in one dataset.
