Description: We are sharing phenotypic data sets used in the pub “Harnessing genotype-phenotype nonlinearity to accelerate biological prediction”. Contained within are a set of publicly available empirical phenotype data sets, synthetic phenotypes we generated, and the output of an autoencoder model trained on them. Walkthroughs for all analyses using these data are available on GitHub. Files: “ail_cleaned_phenos.RDS”: .RDS file of mouse phenotypes from Bogue et al. 2015 “all_autoencoder_phenotype_predictions.csv“: .csv file containing accuracy statistics for all phenotype-phenotype autoencoder models analyzed in the pub “arapheno_cleaned_phenos.RDS“: .RDS file of Arabidopsis phenotypes from Exposito-Alonso et al. 2019 “autoencoder_phenos.zip“: directory of synthetic phenotype sets used to train the autoencoder models “dgrp_cleaned_phenos.RDS”: .RDS file of DGRP fruit fly phenotypes compiled from multiple sources, originally reported in Mackay et al. 2012 “jax_cleaned_phenos.RDS”: .RDS file of mouse phenotypes from Gonzales et al. 2018 “nematode_cleaned_phenos.RDS”: .RDS file of nematode phenotypes from Snoek et al. 2019 “phen_pleio_int_01_0_1.pk”: pickle of all synthetic phenotypes analyzed in the pub “yeast_cleaned_phenos.RDS”: .RDS file of yeast phenotypes from Bloom et al. 2019 A full description of how the synthetic phenotypes and autoencoder predictions were generated is available in the associated pub.