Table 4 A detailed comparison of the contents of the RnaBench dataset (Inverse RNA Folding Dataset) with our dataset. If the number of different samples for a given ID is greater than one, the number is provided in parentheses next to the ID.
From: Comprehensive datasets for RNA design, machine learning, and beyond
Compared datasets | RFAM/PDB id | Avg. structure length (std. dev.) | No. of shared samples |
|---|---|---|---|
RnaBench vs Our Dataset (samples extracted from the Rfam database) | RF00001, RF00005 (2), RF00007, RF00014, RF00019, RF00020, RF00021, RF00026, RF00029, RF00037, RF00043, RF00047, RF00053, RF00056, RF00090, RF00103, RF00167, RF00231, RF00237, RF00322, RF00400, RF00404, RF00406, RF00413, RF00422, RF00424, RF00446, RF00451, RF00545, RF00553, RF00565, RF00568, RF00582, RF00617, RF00641, RF00657, RF00667, RF00679, RF00906, RF00951, RF01225, RF01234, RF01241, RF01418, RF01751, RF01782, RF01797, RF01844, RF02030, RF02097, RF02635, RF02689, RF02723, RF02736, RF02737, RF02741, RF02742, RF02749, RF02755 | 87.4 (72.3) | 60 |
RnaBench vs Our Dataset (samples extracted from the RNAsolo database) | 1JOX_1_A, 1R2P_9_A, 1U3K_7_A, 7UW1_1_B | 51.75 (36.47) | 4 |
