Skip to main content

Table 4 Single task learning with direct combination and label scaling for siRNA efficacy prediction.

From: Multi-task learning for cross-platform siRNA efficacy prediction: an in-silico study

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
  1. "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.