Fig. 4: Inter-family secondary structure prediction.
From: RiNALMo: general-purpose RNA language models can generalize well on structure prediction tasks
a, Average F1 scores for secondary structure prediction on the ArchiveII evaluation datasets. The best result for each evaluation dataset in the tables is shown in bold. b, Distribution of F1 scores for different methods on the ArchiveII evaluation datasets (sample sizes n: 1, 283, 918, 557, 462, 454, 74, 67, 35, and 15, respectively). Box plots show the median (center line), 25th and 75th percentiles (bounds of box), whiskers extending to the smallest and largest values within 1.5× the interquartile range, and individual outliers beyond the whiskers. Minimum and maximum values are 0 and 1, respectively.
