Ontotext talks to a team at a global collaboration center in Massachusetts aiming to bring new, safe, and efficient drugs to patients faster.
Introduction
In this interview, we dive into the decision-making process, benefits, and transformative impact of Ontotext Target Discovery on a research team’s workflow. Faced with the need to rank complex data and streamline drug target identification, the team shares why Ontotext’s ranking capabilities and customized approach stood out. We learn how Ontotext’s flexible support and data integration have empowered them to efficiently prioritize targets, enhance research flows, and incorporate AI tools, ultimately enabling more focused, impactful research paths.
Why did you choose Ontotext Target Discovery?
We couldn’t find options for ranking and configuration, which was important to what we needed for our research. Other options we looked at were more about pulling data as aggregators but they lacked the ability to take information from other databases and add rankings. A big and key piece of the value of Target Discovery was the ranking by targets – that caught our attention. And the willingness of Ontotext to work with us to understand our needs was a good part of the choice. They showed how we could use our data, and customized the tool and process to fit our needs.
How do you leverage Ontotext Target Discovery?
There are always a lot of potential drug targets after a screening is done, but it’s hard to sort through all the options. Now, we can rank based on druggability, we get greater control and context, and we can emphasize different aspects to focus on for prioritization. We generate very large data sets and some could be interesting to pursue. Still, they are very complicated with many relationships, so it helps to prioritize based on what criteria to focus on. Ontotext integrates all this internal data and helps us to go from thousands of choices to 10. So this helps us make sense of large data sets and gives a shorter path to identifying leads. With large datasets, it’s hard to find and rank so examples help.
How does Ontotext Target Discovery help in research flows?
Efficacy and prioritization targets. All being available in one interface helps us to see the genes and proteins that are part of the research flow. And, most simply, it does what they said it would do. It does what we need it to do. What was big for us was the willingness of the Ontotext team to adjust the tool based on our needs. This relationship has been very big and positive for us.
How are you incorporating AI into the overall flow?
If we didn’t have this, we would have to dedicate other resources to do a lot of what we are doing. If we could wave a magic wand to make Target Discovery do more – it would be to incorporate a large language model into the flow, so we could ask natural language questions of the tool. The hard part of them selling this to us – and other companies, is that although people need an AI solution, they just may not know what they need. By the work Ontotext did – making it experiential and simplified in their presentation – they focused less on the how, and more on the outcome of what Target Discovery could do for us. That really made a difference.