Poanna Tran
Research Scientist
Gubra ApS
Talk Information
Incretins and Polypharmacology
19 June 2025, 09:15am - 09:30am, in the Pacific Jewel Ballroom
L56 – Machine Learning Guided Peptide Drug Discovery Speeds up Lead Identification as Demonstrated with Novel GLP-1R Agonists
Dr. Poanna Tran is a Research Scientist at Gubra ApS, a Danish biotech company specializing in preclinical contract research and peptide-based drug discovery. Her work focuses on integrating machine learning approaches into peptide drug discovery, aiming to accelerate the identification of lead compounds for therapeutic development.
Academic Background
While specific details about Dr. Tran's academic background are not publicly available, her current role at Gubra ApS and her contributions to scientific conferences suggest a strong foundation in chemical biology and computational methods applied to drug discovery.
Research Focus
At Gubra, Dr. Tran's research centers on the application of machine learning techniques to peptide drug discovery. She is involved in developing computational models that can predict peptide-receptor interactions, which streamlines the process of lead identification and optimization. Her work contributes to the advancement of peptide therapeutics, particularly in targeting metabolic diseases.
Notable Contributions
Dr. Tran is scheduled to present at the 2025 American Peptide Symposium, where she will discuss her work on "Machine Learning Guided Peptide Drug Discovery Speeds up Lead Identification as Demonstrated with Novel GLP-1R Agonists." This presentation highlights the practical applications of her research in accelerating the discovery of peptide-based therapeutics for conditions such as obesity and diabetes.
Professional Engagements
Beyond her research activities, Dr. Tran actively participates in scientific conferences and collaborative projects within the biotech community. Her contributions to the field of peptide drug discovery underscore her commitment to advancing innovative therapeutic strategies through interdisciplinary approaches.
Through her integration of computational methods and peptide chemistry, Dr. Poanna Tran continues to make significant strides in the development of novel therapeutics, exemplifying the impact of emerging technologies in modern drug discovery.
Machine Learning Guided Peptide Drug Discovery Speeds up Lead
Identification as Demonstrated with Novel GLP-1R Agonists
We have developed streaMLine, an innovative platform for peptide drug discovery that greatly shortens the time from initial hit to clinical drug candidate. The platform allows for high throughput synthesis and screening. Thousands of peptides are systematically screened in in vitro assays and on chemical- and physical parameters, whereby the streaMLine platform enables complete sequence exploration and simultaneous optimization of key parameters.
We employ a fully digitalized laboratory system where detailed information on all aspects of a sample lifetime is tracked. This enables accurate distinction of key chemical peptide modification from artefact background effects, using a machine learning approach. This unique strategy for peptide screening integrates with state-of-the-art in vivo pharmacology facilities, including advanced animal models and rapid determination of PK/PD relationships.
Using the streaMLine platform, we developed novel GLP-1R agonists, to demonstrate how high throughput screening peptide libraries and machine learning guided drug design can be applied to accelerate drug discovery. We systematically synthesized and screened a total of 2,688 peptides in a parallelized optimization workflow. Using this approach, we identified a vast chemical solution space for generating novel GLP-1R agonists based on an alternative peptide starting point, that is, the secretin backbone. To validate the developed QSAR pipeline, we conducted an in-depth profiling of a
developed GLP-1R agonist that showed high receptor selectivity, attractive physicochemical properties and pharmacokinetic profiling, and a potent weight-lowering in vivo efficacy.