Table 4.

Single task learning with direct combination and label scaling for siRNA efficacy prediction.

Test	RMSE
	T1	T2	T3	T4	T5	T6	T7
Test 1	23.5500	23.0800	12.8500	30.2500	27.8400	32.8000	32.9700
Test 2	24.9500	29.8900	31.2700	26.8300	32.1900	29.5200	29.2500
	T8	T9	T10	T11	T12	T13	T14
Test 1	26.5700	13.6100	13.4400	36.9900	33.6700	17.3300	28.7000
Test 2	27.2600	15.8700	12.3700	26.2400	30.3800	21.4700	25.9700

"E" denotes "Experiment". Test 1: Selected 50% of the data from each experiment to train a regression model, and tested the model on the remain 50% of the data of each experiment, respectively. Test 2: Scaled all the experimental labels into [0,1] and pooling together 50% of the data from each experiment to train a general model, and tested the model on the remain 50% of the data of each experiment, respectively. p-value calculated by pair t-test on Test 1 and Test 2 is 0.7043.