The rise of artificial intelligence in drug discovery: Challenges and opportunities
Over the past few years, artificial intelligence (AI) has seen increasing adoption across the whole drug discovery process. From early-stage discovery to the approval stage, AI tools and approaches promise to accelerate and improve drug discovery. At the same time, challenges such as access to high-quality training data are becoming more apparent, leading to a stronger focus on questions of data, metadata, and data stewardship.
This Patterns special collection aims to bring together thought leaders from academia and industry, showcasing original research, review articles, and other available article types in Patterns pertaining to the application of AI in drug discovery. When submitting your paper, please mention in your cover letter that the paper is submitted to the special collection: AI in drug discovery.
Patterns promotes all types of cross-disciplinary data science research and outputs. The topics of the special collection include, but are not limited to: |
• |
AI applications in the discovery stage and in preclinical research (synthesis of biomedical information, novel target identification, generative chemistry, etc.) |
|
|
• |
AI applications for clinical development of novel drug candidates, including analysis of real-world evidence |
|
|
• |
Generation, capture, and integration of relevant data and metadata suitable for AI applications in drug discovery |
|
|
• |
Data standards, data stewardship, governance, and FAIR compliance |
|
|
• |
Benchmarking of AI tools and software against conventional industry approaches |
|
|
• |
Novel AI techniques (reinforcement learning, DRL, federated learning, etc.) and their role in drug discovery |
|
|
|
We welcome manuscripts presenting original research studies and reviews. Deadline for submissions to this special collection is December 31, 2021. Manuscripts should be prepared according to the guide for authors and should be submitted online.
|