We've updated our Privacy Policy to make it clearer how we use your personal data. We use cookies to provide you with a better experience. You can read our Cookie Policy here.


No One Size Fits All: The Challenges of Vendor Agnostic Software

No One Size Fits All: The Challenges of Vendor Agnostic Software content piece image
Credit: Pixabay
Listen with
Register for free to listen to this article
Thank you. Listen to this article using the player above.

Want to listen to this article for FREE?

Complete the form below to unlock access to ALL audio articles.

Read time: 2 minutes

Biosero, Inc. develops automation software that uses artificial intelligence to speed up critical lab work. Their Green Button GoTM scheduling software is vendor agnostic, which is important in lab environments that may incorporate equipment from several different Original Equipment Manufacturers (OEMs). We caught up with David Dambman, Biosero’s Director of Engineering, to talk about the challenges of developing agnostic software, and how labs can implement artificial intelligence into their processes.

Ruairi Mackenzie (RM): Your Green Button Go software is vendor agnostic – whilst the advantages of this approach are obvious, what are the challenges in designing software to be agnostic?

David Dambman (DB): The challenge of designing a vendor-agnostic software platform is ensuring that it can adapt to workflows and capabilities that have not yet been defined. Biosero accomplished this through the careful componentization of the application and a powerful plugin system. These tools extend the capabilities of Green Button Go when and where needed, without making changes to the core. Biosero adds new capabilities as customers need them by writing new plugins for schedulers, workflow elements, instrument drivers and data visualization. This capability speeds up the development and deployment of the software. Using plugins, the software supports the capabilities and functionality that are critical to a customer’s success, yet may only be relevant to their deployment.

RM: How can you ensure the software remains future-proof as vendors update their instruments?

DD: The scientific community moves quickly. It’s critical for Biosero to maintain great relationships with all the equipment manufacturers and our shared customers who are early adopters and innovators. We work with vendors to support their evolving instruments and to provide guidance on best practices for instrument interfaces - both hardware and software. Biosero partners with customers to develop novel workflows for those instruments. 

RM: How is AI incorporated into Green Button Go?

DD: The proper management of data is critical. No matter how much you invest in AI and machine learning, the quality and quantity of data make the difference between success and failure.

Green Button Go has a powerful data management platform that integrates with existing informatics systems and extends them. The platform captures and manages raw data about the instrument, process, utilization, environment, as well as the metadata that provides context and meaning to the primary data. This transforms the data into actionable information and knowledge make informed decisions. This is where Artificial or Human Intelligence gets incorporated. These decisions can then be automatically fed back through Green Button Go’s extensive control interface to solve problems or makes real-time changes to orders and workflows.  

RM: Adding AI to lab processes can be useful, but what is the timescale for implementing AI in labs?

DD: The use of AI in the Life Science industry is still in its infancy. Biosero is working with progressive innovators who are already actively using AI, and we can bring those capabilities to the lab now. The timescale for it to take hold everywhere is hard to predict, but it is coming, and faster than you might expect. One thing is clear. The foundation of successful AI is the quantity and quality of data. Even if the algorithms are still under development, it is vital that there is enough good data to train those algorithms to make them useful. It is critical that the industry improve its data practices now to pave the way for successful AI in the future. 

David Dambman was speaking with Ruairi J Mackenzie, Science Writer for Technology Networks.