## HGNC download is from gene families site at HGNC, where gene is in the 2nd column & family name is in the 11th column
## Protein kinase lists can be obtained from numerous sources. The format expected for use below is gene\tfamily
## Drug class info can be obtained via DrugBank/DrugPort, NIH, and others. The format used below expects two columns drug\tclass
## Ensembl .gtf was necessary for longest transcript calculation. Run determine_transcript_lengths.pl to get gene, transcript, length (gtl) data.
# annotated .clusters with a variety of details. These simply append columns, and so they can accumulate.
annotate_clusters_MAF.pl #expects gtl data and the .maf used for clustering
annotate_clusters_PDB.pl #needs HotSpot3D data
annotate_clusters_domains.pl #needs HotSpot3D data
annotate_clusters_drug_class.pl #expects a drug class list
annotate_clusters_HGNC_Kinase.pl #expects HGNC download & protein kinase list
annotate_clusters_families.pl #expects HGNC download

# determine cluster presence/representation for PDB structures associated with the gene
clusterPDBPresence.drug.pl #for drug-mutation pairs/clusters
clusterPDBPresence.pl #for mutation-mutation pairs/clusters

genePDBPresence.pl #for genes instead of clusters

#determine number of structures for each gene
nStructures.pl