Improvement in goodness of fit with rank transformation on phenotype 1.

Applying the rank transform to phenotype 1 increases average cross-validated Spearman correlations for all regression approaches and regressor sets we tested. The performance improvement is especially large for subchallenges B2 and B3, where gene expression data is available.

将秩变换（rank transform）应用于表型1后，可提升本次测试中所有回归方法与回归器集的平均交叉验证斯皮尔曼相关性。在可获取基因表达数据的子挑战B2与B3中，该性能提升幅度尤为显著。