1. | EXECUTIVE SUMMARY |
1.1. | Report Scope |
1.2. | Report Scope: Drug Discovery |
1.3. | Challenges in the Drug Discovery Process |
1.4. | AI in Drug Discovery: Why Now? |
1.5. | Drivers & Constraints of AI in Drug Discovery |
1.6. | AI in Virtual Screening |
1.7. | AI in Virtual Screening: Key Players |
1.8. | AI in Virtual Screening: Conclusions |
1.9. | AI in De Novo Drug Design |
1.10. | AI in De Novo Drug Design: Key players |
1.11. | AI in De Novo Drug Design: Conclusions |
1.12. | AI in Lead Optimization |
1.13. | AI in Chemical Synthesis Planning |
1.14. | Funding in AI in Drug Discovery |
1.15. | AI in Drug Discovery: Business Models |
1.16. | AI in Drug Discovery Market Landscape: By Geography |
1.17. | AI in Drug Discovery Market Landscape: By Application |
1.18. | AI in Drug Discovery: Market Outlook |
1.19. | Conclusions |
2. | INTRODUCTION |
2.1. | Report Scope |
2.2. | The Drug Development Process |
2.3. | Report Scope: Drug Discovery |
2.4. | Key Terminology: Targets and Ligands |
2.5. | Targets and Ligands: Lock and Key Analogy |
2.6. | Challenges in the Drug Discovery Process |
2.7. | Drug Discovery is Expensive |
2.8. | History of AI in Drug Discovery |
2.9. | AI in Drug Discovery: Why Now? |
2.10. | Benefits of AI in Drug Discovery |
2.11. | Drivers & Constraints of AI in Drug Discovery |
3. | AI IN DRUG DISCOVERY |
3.1.1. | What is Artificial Intelligence? |
3.1.2. | AI, ML & DL in Drug Discovery |
3.1.3. | AI Methods in Drug Discovery |
3.1.4. | Applicability and Predictive Capabilities of Key AI Algorithms |
3.1.5. | Constructing an AI Model: Which Algorithms to Use? |
3.1.6. | How are Compound Structures Encoded into an AI Model? |
3.1.7. | Molecular Fingerprints |
3.1.8. | Simplified Molecular Input Line Entry Specification (SMILES) |
3.2. | AI in Virtual Screening |
3.2.1. | AI in Virtual Screening |
3.2.2. | AI in Virtual Screening: Key Players |
3.2.3. | AI in Virtual Screening: Funding |
3.2.4. | AI in Virtual Screening: By Application and Drug Type |
3.2.5. | Structure-Based Virtual Screening |
3.2.6. | Recursion Pharmaceuticals |
3.2.7. | Atomwise |
3.2.8. | Micar Innovation |
3.2.9. | TwoXAR |
3.2.10. | Ligand-Based Virtual Screening |
3.2.11. | Tencent |
3.2.12. | Phenotypic Virtual Screening |
3.2.13. | e-Therapeutics |
3.2.14. | AI in Virtual Screening: Progress from Lab to Bedside |
3.2.15. | AI for Virtual Screening: Clinical Trials |
3.2.16. | AI for Virtual Screening: Partnerships |
3.2.17. | AI in Virtual Screening: Software Capabilities |
3.2.18. | AI in Virtual Screening: Technology Readiness |
3.2.19. | AI in Virtual Screening: Conclusions |
3.3. | Phenotypic Screening: AI for Cell Sorting and Classification |
3.3.1. | Image Recognition AI |
3.3.2. | Classification of Phenotypic HTS Results |
3.4. | AI in De Novo Drug Design |
3.4.1. | AI in De Novo Drug Design |
3.4.2. | AI in De Novo Drug Design: Key players |
3.4.3. | AI in De Novo Drug Design: Funding |
3.4.4. | AI in De Novo Drug Design: By Drug Type |
3.4.5. | How does AI-driven De Novo Drug Design Work? |
3.4.6. | DMTA Cycles Must be Reduced |
3.4.7. | How does AI-driven De Novo Drug Design Work? |
3.4.8. | IBM Research Zurich |
3.4.9. | Insilico Medicine |
3.4.10. | Exscientia |
3.4.11. | CaroCure |
3.4.12. | Aqemia |
3.4.13. | GlamorousAI |
3.4.14. | AstraZeneca |
3.4.15. | Arzeda |
3.4.16. | BenevolentAI |
3.4.17. | AI in De Novo Drug Design: Partnerships |
3.4.18. | AI in De Novo Drug Design: Progress from Lab to Bedside |
3.4.19. | AI in De Novo Drug Design: Software Capabilities |
3.4.20. | AI in De Novo Drug Design: Software Capabilities |
3.4.21. | AI in De Novo Drug Design: Technology Readiness |
3.4.22. | AI in De Novo Drug Design: Conclusions |
3.5. | AI in Lead Optimization |
3.5.1. | AI in Lead Optimization |
3.5.2. | History of Lead Optimization |
3.5.3. | Key Properties and AI Algorithms |
3.5.4. | Predictive Capabilities of Key AI Algorithms |
3.5.5. | AI in Lead Optimisation: Process |
3.5.6. | Quantitative Structure-Activity Relationship Models |
3.5.7. | Intellegens |
3.5.8. | PEACCEL |
3.5.9. | ProteinQure |
3.5.10. | Iktos |
3.5.11. | Molomics |
3.5.12. | Denovicon Therapeutics |
3.5.13. | XtalPi |
3.5.14. | Peptone |
3.5.15. | GlaxoSmithKline |
3.5.16. | AI in Lead Optimization: Software Capabilities |
3.5.17. | AI in Lead Optimization: Technology Readiness |
3.5.18. | AI in Lead Optimization: Conclusions |
3.5.19. | AI in Lead Optimization: Challenges |
3.6. | AI in Chemical Synthesis Planning |
3.6.1. | Chemical Synthesis Planning |
3.6.2. | Retrosynthesis Pathway Prediction |
3.6.3. | Computer-Aided Retrosynthesis |
3.6.4. | AI in Chemical Synthesis Planning |
3.6.5. | AI in Chemical Synthesis Planning: Software Architecture |
3.6.6. | AI in Chemical Synthesis Planning: Key Players |
3.6.7. | Merck KGaA |
3.6.8. | Iktos |
3.6.9. | PostEra |
3.6.10. | Molecule.one |
3.6.11. | DeepMatter |
3.6.12. | University of Glasgow |
3.6.13. | AI in Chemical Synthesis Planning: Partnerships |
3.6.14. | AI in Chemical Synthesis Planning: Software Capabilities |
3.6.15. | AI in Chemical Synthesis Planning: Technology Readiness |
3.6.16. | AI in Chemical Synthesis Planning: Conclusions & Outlook |
4. | MARKET LANDSCAPE |
4.1. | Overview |
4.2. | Funding in AI in Drug Discovery |
4.3. | AI in Drug Discovery: Business Models |
4.4. | Collaborations Between Big Pharma and AI Companies |
4.5. | AI in Drug Discovery Market Landscape: By Geography |
4.6. | AI in Drug Discovery Market Landscape: By Application |
4.7. | AI in Drug Discovery Market Landscape: By Drug Type |
4.8. | AI in Drug Discovery Market Landscape: 2010-2020 |
4.9. | AI in Drug Discovery: Market Outlook |
5. | OUTLOOK |
5.1. | AI-Driven Automation |
5.2. | Is Deep Learning Suitable for Drug Discovery? |
5.3. | Polypharmacology and Multi-Target Drugs |
5.4. | Data Availability and Data Quality |
5.5. | Other challenges facing drug discovery AI companies |
5.6. | Final Thoughts |
5.7. | Company profiles |