Many previous studies on link prediction have focused on using common neighbors to predict the existence of links between pairs of nodes.
Surprisingly, most literature on human mobility prediction has focused on next location prediction, but has overlooked the exploration prediction problem.
Early work on miRNA target prediction has focused on using static sequence information.
Most work on homology prediction has focused on the problem of detecting remote homology without inclusion of chance sequence similarity.
Rather, current research on acute suicide prediction has focused largely on warning signs that are patient-dependent, such as precipitating events [ 5- 9], behavior changes [ 10, 11], or intense affective states [ 12- 19].
Yet, published work on B-cell epitope prediction has focused mainly on immunogenicity that leads to production of antibodies cross-reactive with (i.e., also capable of preferentially binding) a target other than the immunogen (i.e., antigen used for immunization).
Most of the prior work in PPI prediction has focussed on building models separately for individual organisms (Chen and Liu, 2005; Qi et al., 2006; Singh et al., 2006; Wu et al., 2006) or on building a model specific to a disease in the case of host pathogen PPI prediction (Dyer et al., 2007; Kshirsagar et al., 2012; Qi et al., 2009; Tastan et al., 2009).
Other clinical prediction rules have focused to predict eligibility for ICU admission.
In summary, while past studies with model substrates have demonstrated differences between murine and human TAP specificity, subsequent large-scale studies that allow for the development of general quantitative prediction models have focused on human TAP alone.
