search

zjunlp / OntoProtein

[ICLR 2022] OntoProtein: Protein Pretraining With Gene Ontology Embedding
MIT License
138 stars 22 forks source link

Important relation for the protein sequence #32

Closed anonimoustt closed 4 months ago

anonimoustt commented 4 months ago

Hi,

I see the following relations in the knowledge graph: ['enables_nucleotide_binding', 'enables_metal_ion_binding', 'enables_transferase_activity', 'enables', 'involved_in_signal_transduction', 'involved_in_regulation_of_transcription,_DNA-templated', 'involved_in_phosphorylation', 'involved_in', 'part_of_nucleus', 'part_of_cytoplasm', 'part_of', 'part_of_cytosol', 'part_of_membrane', 'colocalizes_with', 'involved_in_proteolysis', 'NOT|involved_in', 'part_of_integral_component_of_membrane', 'involved_in_cation_transport', 'involved_in_cellular_response_to_DNA_damage_stimulus', 'part_of_mitochondrion', 'involved_in_metabolic_process', 'involved_in_cell_cycle', 'involved_in_cell_division', 'involved_in_lipid_metabolic_process', 'enables_RNA_binding', 'acts_upstream_of_or_within', 'enables_catalytic_activity', 'enables_hydrolase_activity', 'enables_DNA_binding', 'contributes_to', 'involved_in_carbohydrate_metabolic_process', 'involved_in_translation', 'part_of_extracellular_region', 'acts_upstream_of_or_within_positive_effect', 'involved_in_protein_transport', 'NOT|enables', 'acts_upstream_of', 'part_of_ribosome', 'involved_in_transmembrane_transport', 'NOT|part_of', 'NOT|involved_in_tRNA_processing', 'is_active_in', 'located_in', 'NOT|located_in', 'acts_upstream_of_positive_effect']

which relation is the most important for protein sequence?

Alexzhuan commented 4 months ago

Hi,

I believe there isn't a single most crucial relationship for protein sequences within the knowledge graph. Each relationship holds its unique significance. However, certain relationships, such as 'part_of_cytosol' or 'enables_hydrolase_activity', stem from broader relationships like 'part_of' and 'enables', which are respectively derived from the Cellular Component Ontology and Molecular Function Ontology. These relationships are introduced to address imbalances within knowledge graph and foster better comprehension of protein representations.

anonimoustt commented 4 months ago

Thanks. Is there any tool to visualize the Protein KG knowledge graph data: https://www.zjukg.org/project/ProteinKG25/

Alexzhuan commented 4 months ago

We manually drew this figure of subgraph of ProteinKG25 demonstrated in the above site using PowerPoint. Of course, you can also visualize the knowledge graph with Neo4j tool.