A matrix, similar to this was used in Gianola et al. (2011) for predicting milk, fat and protein production in Jersey cows. In this software version we do not center the incidence matrix for the additive effects.

\(G=\frac{X_a X_a'}{2\sum_{j=1}^p p_j (1-p_j)},\)

where

\(X_a\) is the design matrix for allele substitution effects for additivity.

\(p_j\) is the frecuency of the second allele at locus \(j\) and \(q_j=1-p_j\).

Gianola, D. Okut, H., Weigel, K. and Rosa, G. 2011. "Predicting complex quantitative traits with Bayesian neural networks: a case study with Jersey cows and wheat". *BMC Genetics*,
**12**,87.