AI Target Identification: A novel approach to drive drug R&D in IPF?


Within the realm of lung diseases, developing new drugs to treat Idiopathic Pulmonary Fibrosis (IPF) remains a formidable challenge. Characterized by progressive scarring of lung tissue, IPF significantly impairs breathing and has a median survival rate of just 2 to 3 years post-diagnosis. Current therapeutic options are limited, often providing only marginal relief while failing to halt disease progression. The development of more effective treatments is critical to improve outcomes for patients and alleviate the substantial burden on healthcare systems worldwide.


Innovative Target Identification Through AI: A Case Study

The use of artificial intelligence (AI) to identify novel therapeutic targets is much discussed in both the scientific and popular literature. In a recent example, Ren and colleagues described using AI to pinpoint TRAF2- and NCK-interacting kinase (TNIK) as a promising anti-fibrotic target. This AI-driven methodology leverages advanced algorithms to analyze vast multiomics datasets, integrating biological network analyses and scientific literature. This data-driven approach is hypothesized to ensure a robust identification process yielding the most promising targets.


From Target Identification to Clinical Trials

The identified target, TNIK, underwent a rigorous validation process, leading to the development of INS018_055, a small-molecule TNIK inhibitor. This compound demonstrated significant anti-fibrotic and anti-inflammatory properties in various preclinical models. Within 18 months, the AI-driven pipeline progressed from target discovery to the nomination of a preclinical candidate. This accelerated timeline underscores the potential of AI in streamlining drug development. Phase I clinical trials have shown that INS018_055 is safe and well-tolerated, paving the way for further clinical evaluations.



Does the use of AI in target identification, as demonstrated in this case study, marks a paradigm shift in drug discovery? The answer likely depends on the specific implementation, and how AI-based approaches will be combined in parallel with traditional discovery methods. By prioritising target identification over molecule design, researchers can ensure a more strategic and, potentially, effective development process. However, experimental characterisation of compounds remains crucial to fully understand their in vivo profiles


As an expert in translational medicine, TherapeutAix is poised to assist you in designing research strategies that leverage data-driven approaches to clinical development – in IPF, but in other disease areas as well. Contact us to discuss how we can support your R&D efforts, ensuring your projects are grounded in cutting-edge science and optimised for success.


We’d like to send you our company updates, invites to events and any other relevant news. By providing your details and subscribing to this list, you are giving us your consent to send you these updates.

We’ll always be mindful of how often we send our updates and you can amend your preferences at any time.

We’ll never sell or swap your data with any organisation and we’ll store your details securely, respecting your trust and privacy. Please view our privacy policy for further details.

Marketing Permissions
Please select all the ways you would like to hear from TherapeutAix:
You can unsubscribe at any time by clicking the link in the footer of our emails. For information about our privacy practices, please visit our website.