Uploaded December 2025 | Updated September 2026, 4 days ago
#AI
This is part six of a ten part podcast series focused on the ten most impactful developments in artificial intelligence expected to transition from limited use to infrastructure-level technology over the next five years.
Specifically, this podcast introduces AI Driven Drug Discovery Platforms with Closed Loop Lab Automation.
Detailing how this technology uses AI to design experiments and robotics to execute them, creating a continuous, self-optimizing cycle. The overview explains that this AI-driven approach, often termed a "self-driving lab," can significantly cut early-stage research and development time and cost by rapidly generating and testing candidate molecules.
Furthermore, the discussion outlines the technical components, expected timelines for adoption (beginning around 2025-2026), and crucial challenges facing widespread implementation, such as regulatory validation, high initial costs, issues with data quality and fragmentation, and the need for specialized talent.
AI was used to assist in the creation of this video.
Source files and an Index to all our YouTube videos are accessible from here
gsfsoftware.co.uk/PBTutorials/Projects.htm
I don't work for, nor am I paid by, or sponsored by, the owners of PowerBASIC or any other company mentioned in this podcast, I'm just a fan of their products.
For more information on PowerBASIC visit
pbusers.org
OR
pump.richheimer.de/index.php
Music by ghosthack.de
#AI
This is part six of a ten part podcast series focused on the ten most impactful developments in artificial intelligence expected to transition from limited use to infrastructure-level technology over the next five years.
Specifically, this podcast introduces AI Driven Drug Discovery Platforms with Closed Loop Lab Automation.
Detailing how this technology uses AI to design experiments and robotics to execute them, creating a continuous, self-optimizing cycle. The overview explains that this AI-driven approach, often termed a "self-driving lab," can significantly cut early-stage research and development time and cost by rapidly generating and testing candidate molecules.
Furthermore, the discussion outlines the technical components, expected timelines for adoption (beginning around 2025-2026), and crucial challenges facing widespread implementation, such as regulatory validation, high initial costs, issues with data quality and fragmentation, and the need for specialized talent.
AI was used to assist in the creation of this video.
Source files and an Index to all our YouTube videos are accessible from here
gsfsoftware.co.uk/PBTutorials/Projects.htm
I don't work for, nor am I paid by, or sponsored by, the owners of PowerBASIC or any other company mentioned in this podcast, I'm just a fan of their products.
For more information on PowerBASIC visit
pbusers.org
OR
pump.richheimer.de/index.php
Music by ghosthack.de
