Drug candidate identification based on gene expression of treated cells using tensor decomposition-based unsupervised feature extraction for large-scale data

Table 1 The number of the inferred compounds and inferred genes associated with significant dose-dependent activity

Cell lines	BT20	HS578T	MCF10A	MCF7	MDAMB231	SKBR3
Tumour	Breast
Inferred genes	41	57	42	55	41	46
Inferred compounds	4	3	2	6	5	6
All compounds	110	106	106	108	108	106
Predicted targets	418	576	476	480	560	423
Cell lines	A549	HCC515	HA1E	HEPG2	HT29	PC3
Tumour		Lung	Kidney	Liver	Colon	Prostate
Inferred genes	45	46	48	54	50	63
Inferred compounds	8	5	7	2	2	9
All compounds	265	270	262	269	270	270
Predicted targets	428	352	423	396	358	439
Cell lines	A375
Tumour	Melanoma
Inferred genes	43
Inferred compounds	6
All compounds	269
Predicted targets	421

The target genes predicted by means of the comparison with the data showing upregulation of the expression of individual genes (‘predicted targets’) are also shown. The full list of inferred genes and predicted targets is available in Additional file 7. Inferred compounds are presented in Table 2. ‘All compounds’ rows represent the total number of compounds used for the treatment of each cell line

ISSN: 1471-2105