Materials

The snoRNA-disease association dataset is divided into different sub-datasets according to two application scenarios:

(1) : All known snoRNA-disease association (KSD.pdf)

(2) : Corresponding snoRNA names (all_snoRNA_name.pdf)

(3) : Corresponding disease names (all_disease_name.pdf)

(4) : SnoRNA features (snoRNA_features.pdf)

(5) : Disease semantic similarity (Disease_semantic_similarity.pdf)

For the first application scenario 'identifying potential snoRNA-disease associations':

(1) : SnoRNA-disease associations (NA_train.pdf) in Training dataset.

(2) : SnoRNA-disease associations (NA_val.pdf) in Validation dataset

(3) : SnoRNA-disease associations (NA_test.pdf) in Independent dataset

For the second application scenario 'identifying novel snoRNA-associated diseases':

(1) : Known snoRNAs (Train_snoRNAs.pdf) in Training dataset.

(2) : Query snoRNAs (Val_snoRNAs.pdf) in Validation dataset.

(3) : Query snoRNAs (Test_snoRNAs.pdf) in Independent dataset.

Transfer dataset:

(1) : Gene names: (gene_names.pdf).

(2) : Gene features: (gene_feature.pdf).

(3) : Gene-disease associations and corresponding labels: (Transfer_GDA.pdf).