jzhoulab / orca

sequence-based prediction of multiscale genome structure from kilobase to whole-chromosome scale
Other
70 stars 21 forks source link

process_seqstr: add model_labels #7

Closed gr-grey closed 9 months ago

gr-grey commented 9 months ago

In process_seqstr: add parameter "model_labels" when pass in Orca leukemia models leuA, leuB, labels are needed for plotting pdfs.

Tested case

seqstr_input = '[hg38]chr9:94904000-100904000 +;'     
custom_models = [leuA, leuB]
model_labels = ['T-ALL (GSE134761)','THP1', 'GM12878', 'NALM6', 'Non-ETP (GSE146901)','ETP (GSE146901)', 'K562', 'KBM7']
outputs_ref = process_seqstr(seqstr_input, file = '/orca_pred',  custom_models=custom_models, model_labels=model_labels, use_cuda=True)

Got the same result as current server https://orca.zhoulab.io/results/ed322ec6-bf29-447f-9355-a7fb5097d723