Predictions of EnzymeExplorer for UniRef90 clusters with no InterPro annotations

This dataset contains the results of predictions by the software EnzymeExplorer on UniRef90 clusters that are longer than 230 amino acid residues, have a predicted structure in AFDB, and do not have any annotation in InterPro, making them a protein dark matter. Enzyme explorer predicts whether a protein belongs to the family of terpene synthases (TPS). The dataset is a csv file with the following columns: id - The UniProt id of the predicted sequence sequence - The amino acid sequence of the protein TPS_score - Predicted TPS activity probability of the sequence GPP_score - Predicted geranyl diphosphate intake probability of the sequence FPP_score - Predicted farnesyl diphosphate (FPP) intake probability of the sequence GGPP_score - Predicted geranylgeranyl diphosphate (GGPP) intake probability of the sequence GFPP_score - Predicted geranylfarnesyl diphosphate intake probability of the sequence CPP_score - Predicted copalyl diphosphate intake probability of the sequence EDSQ_score - Predicted 2,3-epoxysqualene intake probability of the sequence 2xFPP_score - Predicted 2xFPP intake probability of the sequence 2xGGPP_score - Predicted 2xGGPP intake probability of the sequence IDS_score - Predicted isoprenyl diphosphate synthase (IDS) activity probability of the sequence