TABLE 2.
Sequence length for each dataset. For the median and mean, the data record was counted on each data record basis. The distribution of the length is provided in Supplementary Material.
| Dataset | Sequence | Max | Min | Median | Mean |
|---|---|---|---|---|---|
| McPAS | CDR3α | 26 | 6 | 13 | 13.27 |
| CDR3β | 21 | 7 | 14 | 13.79 | |
| Peptide | 25 | 8 | 9 | 9.761 | |
| VDJdb-without10x | CDR3α | 22 | 5 | 13 | 13.37 |
| CDR3β | 21 | 8 | 13 | 13.76 | |
| Peptide | 20 | 8 | 9 | 9.462 | |
| Combined data dataset | CDR3α | 26 | 5 | 14 | 13.61 |
| CDR3β | 26 | 7 | 14 | 14.37 | |
| Peptide | 25 | 7 | 9 | 9.520 | |
| COVID-19 dataset | CDR3α | 20 | 6 | 14 | 13.69 |
| CDR3β | 21 | 10 | 15 | 14.60 | |
| Peptide | 9 | 9 | 9 | 9.00 |