Supporting datasets for DeepGreenGO

This record archives the datasets used in the study of DeepGreenGO. It contains protein structures, amino acid sequences, and GO terms from Viridiplantae (green plants) retrieved from publicly available biological databases. The following files are included: GO Hierarchy File (go-basic.obo)The Gene Ontology (GO) hierarchy file in OBO format, obtained from the Gene Ontology database (https://geneontology.org/). This file was used to obtain hierarchical relationships between GO terms. PDB2GO Annotation File (pdb_chain_go.rar)Chain-to-GO term annotation file obtained from the SIFTS database (Structure Integration with Function, Taxonomy and Sequences; https://www.ebi.ac.uk/pdbe/docs/sifts/). This file was used to retrieve GO annotations for individual PDB chains. PDB ID List (rcsb_pdb_ids.txt)A list of PDB accession numbers retrieved from the RCSB Protein Data Bank (https://www.rcsb.org/) for experimentally determined structures within the taxonomic lineage Viridiplantae. PDB2Sequence file (pdb2sequences.fasta)Chain-to-amino acid sequence mapping file obtained from RCSB Protein Data Bank (https://www.rcsb.org/).