For DNA_T dataset, each protein chain is represented using 4 lines:
1: Protein ID
2: Amino acid sequence (from Uniprot sequence)
3: Amino acid sequence (from PDB chain) where . represents a residue that is not present in the PDB chain but is present in the UniProt sequence (inclusion of . is to align this PDB chain to the corresponding UniProt sequence)
4: The DNA-binding annotations where . indicates non-DNA-binding and letters stand for DNA-binding annotations

For RNA_T dataset, each protein chain is represented using 4 lines:
1: Protein ID
2: Amino acid sequence (from Uniprot sequence)
3: Amino acid sequence (from PDB chain) where . represents a residue that is not present in the PDB chain but is present in the UniProt sequence (inclusion of . is to align this PDB chain to the corresponding UniProt sequence)
4: The RNA-binding annotations where . indicates non-RNA-binding and letters stand for RNA-binding annotations

For Protein_T dataset, each protein chain is represented using 4 lines:
1: Protein ID
2: Amino acid sequence (from Uniprot sequence)
3: Amino acid sequence (from PDB chain) where . represents a residue that is not present in the PDB chain but is present in the UniProt sequence (inclusion of . is to align this PDB chain to the corresponding UniProt sequence)
4: The protein-binding annotations where . indicates non-protein-binding and letters stand for protein-binding annotations