A transfer learning approach via procrustes analysis and mean shift for cancer drug sensitivity prediction

Keyphrases

• Training Set 100%
• Mean Shift 100%
• Auxiliary Data 100%
• Drug Sensitivity Prediction 100%
• Chemotherapy Sensitivity 100%
• Target Training 100%
• Procrustes Analysis 100%
• Transfer Learning Models 100%
• Performance Prediction 50%
• Breast Cancer Patients 50%
• Triple-negative Breast Cancer 50%
• Clinical Trials 25%
• Machine Learning Algorithms 25%
• Breast Cancer 25%
• Real-world Application 25%
• Supervised Learning 25%
• Knowledge Transfer 25%
• Statistical Significance 25%
• Feature Space 25%
• Transfer Learning Algorithm 25%
• Non-small Cell Lung Cancer (NSCLC) 25%
• Multiple Myeloma 25%
• Cisplatin Sensitivity 25%
• Docetaxel Sensitivity 25%
• Predicting the Future 25%
• Area under the Receiver Operating Characteristic (AUROC) 25%
• Large-scale Training Set 25%
• Limited Training Set 25%

Computer Science

• Learning Approach 100%
• Transfer Learning 100%
• mean shift 100%
• Procrustes Analysis 100%
• Cancer Patient 66%
• Baseline Approach 66%
• Prediction Performance 66%
• Learning Algorithm 33%
• Experimental Result 33%
• World Application 33%
• Supervised Learning 33%
• Machine Learning Algorithm 33%
• Feature Space 33%
• Characteristic Curve 33%

Medicine and Dentistry

• Malignant Neoplasm 100%
• Drug Sensitivity 100%
• Transfer of Learning 100%
• Breast Cancer 66%
• Triple Negative Breast Cancer 66%
• Clinical Trial 33%
• Non Small Cell Lung Cancer 33%
• Multiple Myeloma 33%
• Machine Learning Algorithm 33%
• Area under the Curve 33%
• Docetaxel 33%
• Cisplatin 33%