New webinars on open-source AI and publications about foundation models in medicine (like ChatGPT)
View in browser

Dear Colleague,

We are delighted to offer many new AI-themed events this month: 

  • Register to attend a webinar by the Cambridge Crystallographic Data Centre “Deriving a General Force Field by Machine Learning on Experimental Crystal Structures”, to be held on May 3rd 2023 at 7 am PST (10 am EST, 3 pm London). In this work, our CCDC colleagues used experimentally determined crystal structures from the Cambridge Structural Database to train a machine learning model and create a general force field. The method shows good accuracy, and presents a means to predict chemical and physical properties of crystals (including co-former screening, polymorph stability, and solubility), in a computationally affordable manner.
  • Register to attend a webinar by the Pistoia Alliance AI CoE “Mobilizing Machine Learning Community for Biology”, on May 10th, 8-9 am PST (11 am EST, 4 pm London). This is the first webinar in a series of two events that describe community-based, no-code approaches to AI. Superbio.ai provides datasets, pre-trained AI models, benchmarks, visualization and inference tools, all in a cloud environment, empowering scientists to advance their research with community-driven machine learning. In this webinar, company founder and CEO Berke Buyukkucak will describe his work to democratize the Artificial Intelligence.
  • Register to attend a webinar by the Pistoia Alliance AI CoE “Ersilia, a Hub of Open-Source AI/ML Models for Drug Discovery and Global Health”, on May 25th, 8-9 am PST (11 am EST, 4 pm London). This is our second webinar in a series of two events that describe community-based, no-code approaches to AI. The Ersilia open-source initiative is a non-profit organization with the mission to equip laboratories and universities in low resource areas with AI tools for infectious disease research. Ersilia has developed a set of AI-based tools to support medicinal chemistry, parasitology and ADME experimental pipelines, offering them via a unified, open-source platform the Ersilia Model Hub. Ersilia’s ideas in open-source AI will be presented by Gemma Turon, PhD, CEO.
  • Register to attend ConTech Pharma-2023 (June 8th, hybrid event: in-person meeting in London and on-line). As we look at patient first approaches of developing medicines using AI and Data Driven techniques, it is in the areas of intersection between real-world data, pre-clinical and clinical data that challenges and opportunities arise and challenges are overcome. Come and hear how the world’s best minds in data science, digital healthcare and precision drug development are thinking about these challenges and taking effective action. ConTech Pharma 2023 will showcase the very latest thinking and help organisations to understand how these changes will affect them.
  • We are planning a training event on ontologies. Would you be interested? Please vote for the choice of topics using this form.
  • View the webinar by our Good Machine Learning Practices (GMLP) team held on April 5th. Our panel of distinguished industry leaders: Prashant Natarajan, General Manager, H2O.ai; Bikalpa Neupane, PhD, Director, Advanced Technologies & Experimentation, Takeda; Christophe Chabbert, PhD, Senior Scientist, Discovery Informatics, Roche; and Natalja Kurbatova, PhD, Lead Scientist, Zifo R&D; discussed the common use cases, challenges, and best practices for application of AI, specific to the pharmaceutical enterprise.
  • Have a look at these recent publications on AI:
    • ChemCrow: Augmenting large-language models with chemistry tools. Pre-print
    • Rethink reporting of evaluation results in AI. Science
    • FAIR: Making Data AI-Ready Book Chapter in Artificial Intelligence for Science
    • An implementation framework to improve the transparency and reproducibility of computational models of infectious diseases
    • Evolutionary-scale prediction of atomic-level protein structure with a language model. Science
    • In Minnesota, researchers explore how to audit health AI models on a patient level
    • How Well Do Large Language Models Support Clinician Information Needs?
    • How Foundation Models Can Advance AI in Healthcare
    • The Shaky Foundations of Foundation Models in Healthcare
    • Benefits, Limits, and Risks of GPT-4 as an AI Chatbot for Medicine
    • The Shaky Foundations of Clinical Foundation Models: A Survey of Large Language Models and Foundation Models for EMRs. Pre-print

As always, please get in touch.

 

Best wishes,

 

Vladimir Makarov, PhD, MBA
Project Manager, Pistoia Alliance
Email: vladimir.makarov@pistoiaalliance.org
Mobile: +1-626-222-5642
Skype: vladimir_makarov

Subscribe to updates

The Artificial Intelligence and Machine Learning Community is a great example of the value the Pistoia Alliance delivers to its members. There has never been a more important time to collaborate as an industry, and we hope you find our CoE inspiring and informative.  If you would like to find out more about the benefits of Pistoia Alliance membership and how you can get involved with all the different initiatives we run, please send an email to Membership@PistoiaAlliance.org.

Pistoia Alliance, 401 Edgewater Place, Wakefield, MA 01880, United States

Unsubscribe Manage preferences