Zebrafish references
Zebrafish are smarter than we thought. MIT News
Zebrafish have been used as models for studying human diseases. Nature.com
Zebrafish possess an adaptive immune system with memory cells, similar to humans. Laboratory Animal Research
Zebrafish brains are more sophisticated than previously thought and AI tools can help researchers better understand the complex neural networks in the zebrafish brain. Medical & Biological Engineering & Computing
Recent advances in AI in drug development
Accelerating Clinical Trials: AI is being used to streamline the design and execution of clinical trials. (Nature).
Drug Discovery and Protein Design: AI is boosting drug discovery by generating new therapeutic proteins and assessing their properties. (GeekWire).
Quantum Computing and AI: AI combined with quantum computing is set to revolutionize drug development by providing better medical insights and predictive healthcare analytics. (World Economic Forum).
Identifying Drug Targets: AI algorithms analyze large datasets from various omics studies to uncover new potential drug targets by identifying connections between genes, proteins, and diseases (Nature) (PharmExec).
Designing Novel Molecules: AI systems generate and optimize new drug molecules by iteratively proposing and refining chemical structures for desired therapeutic properties (World Economic Forum) (FDA).
Recent advances in AI in regulatory sciences
FDA: The FDA has issued guidelines exploring the use of AI/ML in drug development, focusing on digital health technologies and real-world data analytics to create a flexible regulatory framework that promotes innovation while ensuring patient safety (FDA).
EMA: The EMA’s guidance on AI in medicinal products emphasizes transparency, robustness, reproducibility, and the need for thorough validation of AI models, with encouragement for early dialogue with regulatory authorities (Nature)
MHRA: The MHRA’s guidelines for integrating AI in clinical trials stress the importance of data quality and integrity, requiring clear documentation and validation procedures to meet regulatory standards (MHRA).
Some favorite books
“Superintelligence: Paths, Dangers, Strategies” by Nick Bostrom – This book delves into the potential future scenarios of AI development and the risks associated with superintelligent machines.
“Artificial Intelligence: A Modern Approach” by Stuart Russell and Peter Norvig – Often considered the definitive textbook on AI, this book covers a wide range of topics and provides a thorough introduction to the field.
“Life 3.0: Being Human in the Age of Artificial Intelligence” by Max Tegmark – Tegmark explores the implications of AI on our future society, including ethical considerations and the potential for AI to surpass human intelligence
“Human Compatible: Artificial Intelligence and the Problem of Control” by Stuart Russell – This book addresses the challenge of ensuring that AI systems remain aligned with human values and do not pose unintended risks.
“The Master Algorithm: How the Quest for the Ultimate Learning Machine Will Remake Our World” by Pedro Domingos – Domingos discusses the different types of machine learning algorithms and the quest to develop a universal algorithm that can learn anything.
“Architects of Intelligence: The Truth About AI from the People Building It” by Martin Ford – This book features interviews with prominent AI researchers and practitioners, offering a wide range of perspectives on the future of AI.
“Deep Learning” by Ian Goodfellow, Yoshua Bengio, and Aaron Courville – A comprehensive textbook on deep learning, covering the theory and practical applications of this subfield of AI.