Artificial Intelligence/Machine Learning (AI/ML) SubSIG of SxP: A collaboration to advance Pharmacometrics using AI/ML methods.
Souvik Bhattacharya (1), Monica Simeoni (2), Camille Vong (3), Yuan Xiong(4), Hu Huang(1), Dan Lu(5) Akash Khandelwal (6)
Astellas Pharma, Cambridge, MA, USA(1), GSK, UK(2), GSK, Baar, Switzerland (3), Johnson & Johnson, Raritan, New Jersey, USA(4), Genentech, USA(5), UCB Bioscience GmbH, Monnheim am Rhein, Germany(6)
Artificial Intelligence (AI) is a widely known field originated from computer science, including theory and development of computer systems to mimic the capabilities of human intelligence, while Machine Learning (ML) is a subset of AI, focusing on techniques that train a machine to learn and analyze patterns within the data, in a way like humans. Recent advances in the field of AI/ML have brought a technological revolution across a wide range of relevant fields, and have started to gain popularity in the field of drug development. [1,2,3,4]
Pharmacometrics has evolved into an important discipline by developing novel mathematical modeling approaches and in-silico simulations to support drug development and accelerate market access of safe and efficacious therapies. Sponsored by the ISoP-ASA Statistics and Pharmacometrics Special Interest Group (SxP SIG), the Artificial Intelligence and Machine Learning Special Interest Sub-Group (AI/ML SubSIG) was recently created with the goal to promote a forum dedicated to fostering the advancement and application of AI/ML methods and to facilitate the integration of AI/ML approaches within pharmacometrics by supporting their development, use, and education.
The group started in December 2023. The current agenda includes the following items:
- Frequent brainstorming sessions among team members to foster new ideas and share experiences
- Planned future webinars and sessions at major conferences
- Planned local AI/ML focused meetups to provide networking opportunities for PMX and Statisticians
- Regular updates to internal AI/ML knowledge database with literature and training materials.
In conclusion, AI/MLSxP SubSIG is a collaborative effort to promote the use of AI/ML activities in drug development and is keen to learn from individual users of this methodology. Participation is open to all who are interested who can contribute with or without ISOP membership. For any queries, please contact either souvik.bhattacharya@astellas.com or akash.khandelwal@ucb.com.
References:
- Schneider G. Automating drug discovery. Nat Rev Drug Discov. 2018;17(2):97–113. doi: 10.1038/nrd.2017.232
- Chen H, Engkvist O, Wang Y, Olivecrona M, Blaschke T. The rise of deep learning in drug discovery. Drug Discov Today. 2018;23(6):1241–1250. doi: 10.1016/j.drudis.2018.01.039
- Mamoshina P, Vieira A, Putin E, Zhavoronkov A. Applications of Deep Learning in Biomedicine. Mol Pharm. 2016;13(5):1445–1454. doi: 10.1021/acs.molpharmaceut.5b00982
- Wallach I, Heifets A. Most Ligand-Based Classification Benchmarks Reward Memorization Rather than Generalization. J Chem Inf Model. 2018;58(5):916–932. doi: 10.1021/acs.jcim.7b00403