| 'id': The ID number in our dataset. Homodimers are prefixed with "EID_", while heterodimers are prefixed with "ID_". | |
| 'sequence': The protein pair sequence, formatted as: Sequence A: Sequence B. | |
| 'len1': The length of Sequence A. | |
| 'len2': The length of Sequence B. | |
| 'plddt': The pLDDT score for the predicted complex. | |
| 'ptm': The pTM score for the predicted complex. | |
| 'iptm': The ipTM score for the predicted complex. | |
| 'gene_id1': The gene ID for Sequence A. | |
| 'gene_id2': The gene ID for Sequence B. | |
| 'protein_names1': The protein name for Sequence A. | |
| 'protein_names2': The protein name for Sequence B. | |
| 'organism1': The name of the species to which Sequence A belongs. | |
| 'organism2': The name of the species to which Sequence B belongs. |