Deep Origin's Computational Platform Rationalizes Results of Molecular Glue Compound That Potently Kills Diffuse Large B Cell Lymphoma Cells

Deep Origin docking software and molecular dynamics simulations pinpointed the lead compound from a 17-compound library

Computational results aligned with laboratory experimentation results led by researchers at Stanford and MD Anderson Cancer Center and published in the journal Cell

SOUTH SAN FRANCISCO, Calif., July 20, 2026 (GLOBE NEWSWIRE) -- Deep Origin today announced that its computational platform contributed to a peer-reviewed study published in Cell in which the company's docking and molecular dynamics simulations successfully rationalized the researchers’ work identifying a potent compound to switch on cell-death programs in diffuse large B cell lymphoma (DLBCL).

The study, “A Bivalent Molecular Glue Linking Lysine Acetyltransferases to Oncogene-induced Cell Death,” was led by researchers at Stanford University and the University of Texas MD Anderson Cancer Center. It describes the development of KAT-TCIPs (lysine acetyltransferase transcriptional/epigenetic chemical inducers of proximity), which act as molecular glues that induce a ternary complex between the gene-activating enzymes p300/CBP and the cancer driver B cell lymphoma 6 (BCL6). The interaction is of interest to cancer researchers because it supports potent cell killing. Molecular glues, a type of CIP facilitating the assembly of unrelated proteins, is a fast-emerging drug class.

The researchers at Deep Origin used proprietary docking software, molecular dynamics (MD) simulations, and quantum mechanical calculations to assess a library of 17 compounds. First, the ternary complexes were generated by docking each compound at the protein-protein interface and selecting poses with the best docking scores. Then, Deep Origin’s molecular dynamics engine was used to run 300-nanosecond simulations for each ternary complex to refine the initial pose and generate an ensemble of structures. Finally, the quantum mechanical calculations were utilized to calculate linker strain energy for each compound based on the obtained structural ensembles. The team ranked the compounds by the energetic cost that they incur when forming the ternary complex.

The compound that incurred the least energetic cost killed lymphoma cells at sub-nanomolar concentrations (IC50 0.80 nM).

The computational results aligned with laboratory tests. In a mouse xenograft model of the disease, the selected compound led to complete or near-complete tumor clearance, and in immunized mice it depleted germinal center B cells, which express high levels of BCL6 and serve as a model for certain lymphomas, with no overt organ toxicity.

“Deep Origin’s computational simulations flagged the compound that would kill cancer cells most effectively – matching results achieved at the bench,” said Garegin Papoian, Ph.D., co-founder and chief scientific officer of Deep Origin. “This is a predictivity goal of in silico drug discovery – to determine the candidates most likely to achieve desired results prior to wet lab experimentation. At Deep Origin, we’ve made great strides in computational prediction by combining the rigor of physics-based simulation with the speed and scale of AI, outperforming industry benchmarks. This was a meaningful real-world test of our systems.”

TCIPs act through a gain-of-function mechanism that appears to activate cell death programs much more effectively than BCL6 degraders and inhibitors.

“We designed KAT-TCIPs to recruit the lysine acetyltransferases p300/CBP to BCL6 to activate repressed cell death genes in diffuse large B cell lymphoma,” said Meredith Nix, Ph.D. candidate at Stanford University and study co-author. “It was gratifying to see that Deep Origin’s computational analysis offered a rationale for why TCIP3 was the most effective KAT-TCIP at activating these repressed transcriptional programs.”

The computational plus in vivo data provide evidence of Deep Origin’s platforms’ biological predictivity in living systems. Learn more about the Deep Origin platform at https://www.deeporigin.com/platform.

To read the full research publication in Cell, visit: https://www.cell.com/cell/abstract/S0092-8674(26)00757-9.

About Deep Origin

Deep Origin is building computational discovery systems that model life, to close the gap between preclinical predictions and clinical outcomes. Co-founded by Michael Antonov, co-founder of Oculus, and Garegin Papoian, Ph.D., Monroe Martin Professor of biochemistry at the University of Maryland, Deep Origin runs drug discovery programs — its own and its partners' — through hybrid AI-mechanistic models that span biological scales from quantum to cellular to human body scale. The company engages through discovery partnerships and SaaS platform access. Deep Origin is backed by more than $50 million in capital and more than $32 million in contracts, including a $30 million ARPA-H CATALYST award to build in silico models that can replace animal testing in preclinical drug development. For more information, visit https://deeporigin.com/.

Media Contact:
Steve Cooper, Orangefiery
Scoop@Orangefiery.com

Legal Disclaimer:

EIN Presswire provides this news content "as is" without warranty of any kind. We do not accept any responsibility or liability for the accuracy, content, images, videos, licenses, completeness, legality, or reliability of the information contained in this article. If you have any complaints or copyright issues related to this article, kindly contact the author above.