Skip to main content

Table 1 Summary and comparison of data sets used by different hybrid shift prediction approaches

From: NightShift: NMR shift inference by general hybrid model training - a framework for NMR chemical shift prediction

Approach Year Size of training set Size of test set X-ray/NMR resolved Homolog
   Files (shifts) Files (shifts)   Exclusion
Meiler [15] 2003 292 (n. a.) 30 (n. a.) mixed N
Sparta [17] 2007 200 (n. a.) 25 (n. a.) X-ray N
CamShift [18] 2009 n. a. (224,036) 35 (n. a.) X-ray N
ShiftX2 [21] 2010 197 (206,903) 61 (n. a.) X-ray Y
NightShift 2012 515 (326,652) 344 (217,768) NMR, X-ray, or mixed Y
  1. The third and fourth columns show the size of the data set, measured as the number of proteins contained within. The CamShift publication reported only the overall number of shifts, which we denote in parentheses. Note that for the NightShift set, we already excluded homologous proteins. The table only includes methods for which these numbers could be reliably determined.