Databases and SMILES format

For more info about our services contact : help@bestpfe.com

Table of contents

1 Introduction 
2 Context and environment 
2.1 LORIA
2.2 About the Orpailleur team
2.3 Internship and research contract
2.4 The covid-19 section
2.5 Organization
2.6 Equipment
3 State of the art 
3.1 Machine learning models
3.1.1 Logistic regression
3.1.2 Random forests and AdaBoost
3.1.3 Neural networks
3.2 Antibiotics classication
3.2.1 Databases and SMILES format
3.2.2 Chemprop
3.2.3 DeepChem
3.3 Explainers
3.3.1 LIME
3.3.2 SHAP
3.3.3 PathExplain
3.4 Models metrics
3.5 Software
3.5.1 Scikit-learn
3.5.2 Tensorow
3.5.3 PyTorch
3.5.4 RDKit
3.5.5 Flask
4 Contributions to FixOut 
4.1 Problem description
4.1.1 Fairness issues in machine learning
4.1.2 The purpose of FixOut
4.1.3 The interest in textual applications
4.2 General adaptation of FixOut to text
4.2.1 Problem analysis
4.2.2 Proposed solution
4.2.3 Implementation
4.2.4 Results
4.3 Adaptation to neural networks
4.3.1 Avoiding re-training of many sub-models
4.3.2 Using gradient based explainers
4.3.3 Implementation
4.3.4 Results
4.4 Discussion
4.5 Interactive web demo
5 Explanation of antibiotic molecules 
5.1 Problem analysis
5.1.1 Models to explain
5.2 Proposed solution
5.2.1 Explanation of DeepChem
5.2.2 Explanation of Chemprop
5.3 Implementation
5.3.1 LIME and SHAP for Chemprop
5.3.2 Molecule visualizations
5.3.3 Mol graph organization
5.4 Results
5.4.1 Interpretation of DeepChem results is not trivial
5.4.2 Chemprop, by considering the average contribution
5.4.3 By considering each feature separately
5.4.4 Color scale normalization
5.5 Comparison to PathExplain and interaction explanation
5.5.1 PathExplain for interaction explanations
5.5.2 The problem of explaining interactions with LIME
5.5.3 Implementation of PathExplain
5.5.4 Results
5.6 Discussion
5.7 Web interface
6 Conclusion