0.25
0.5
0.75
1.25
1.5
1.75
2
Building Chemogenomics Models from a Large-Scale Public Dataset and Applying them to Industrial Datasets
Published on Jun 28, 201978 Views
ExCAPE was a European funded project aiming at harvesting the power of supercomputers to speed up drug discovery (http://excape-h2020.eu/). Thanks to the project team, we were given the amazing opport
Related categories
Chapter list
Building Chemogenomics Models From a Large Scale Public Dataset and Applying them to Industrial Datasets00:00
Chemogenomics modelling - 100:31
Chemogenomics modelling - 201:26
Chemogenomics modelling - 302:27
Chemogenomics modelling - 402:55
Aim of chemogenomics: Accelerate Drug Discovery03:29
Challenge: Application Domain - 106:37
Challenge: Application Domain - 207:09
Challenge: Application Domain - 308:40
Exa-Scale Compound Activity Prediction Engine09:47
Team10:39
Overall Workflow - 112:42
Dataset choice12:44
Chemogenomics data14:21
Machine learning dataset14:41
Target dataset sizes and active ratio16:23
ExCAPE-ML18:34
Compounds annotations in ExCAPE-ML19:32
Overall Workflow - 221:53
Chemical Series Bias - 122:00
Chemical Series Bias - 223:25
Cluster sizes24:11
Chemogenomics Matrix24:30
Overall Workflow - 325:05
Molecular Features - 125:07
Molecular Features - 226:12
Overall Workflow - 427:09
Virtual Screening27:13
Performance metrics - 128:49
Performance metrics - 230:01
Performance metrics - 330:31
Overall Workflow - 531:09
Matrix Factorization31:14
Deep Learning algorithm32:17
Overall Workflow - 633:03
Hyperparameters & algorithms33:10
Model evaluation workflow - 134:07
Model evaluation workflow - 234:21
Overall Workflow - 634:29
Hyperparameter Selection35:00
Overall Workflow - 736:58
Model evaluation workflow - 337:02
Test performances37:34
Winning algorithms38:30
Performance per protein family39:46
Imbalance Ratio of Target Datasets by Winning Algo40:38
Overall Workflow - 841:16
Prospective predictions41:32
Dataset preparation42:08
Industrial dataset profiles42:39
Application of Models to Industrial Datasets42:51
ExCAPE ML full scale model performance43:10
Investigating missed predictions - 143:49
Investigating missed predictions - 244:57
Investigating missed predictions - 345:39
Acknowlegments46:54