- This event has passed.
BE Seminar: “Designing Programmable Protein Therapeutics with Generative Language Models” (Pranam Chatterjee, Duke University)
September 5 at 3:30 PM - 4:30 PM
CRISPR has revolutionized biotechnology by enabling the simple design of guide RNAs to target and edit almost any DNA sequence. By developing new generative protein design algorithms, my hybrid lab focuses on extending this CRISPR-like programmability to proteins and other key molecules. In this talk, we will first delve into our algorithms that design binders to undruggable proteins, such as those driving pediatric cancers (alveolar rhabdomyosarcoma and Ewing’s sarcoma) and neurodegenerative diseases (Huntington’s and Alexander Disease). Our generative language models, including SaLT&PepPr, PepPrCLIP, and PepMLM, design short binding peptides from target sequence alone, with no dependence on stable 3D structures, and by fusing these “guide” peptides to E3 ubiquitin ligases, deubiquitinases, and other modifying enzymes, we have created a CRISPR-analogous system to edit these proteins. To be even more specific, we train isoform-specific targeting models such as PTM-Mamba for PTM-specific binding, FusOn-pLM for fusion oncoprotein-specific degradation, and moPPIt for motif-specific targeting of protein-protein interactions. Inspired by the power of language models, we further show how we can extend this programmability to DNA with our PAM-free CRISPR enzymes and our recent DPAC model, which allows us to design proteins that can bind and modulate any DNA sequence. Moreover, we are creating binders for heavy metals through our MetaLATTE algorithm, aiming to sequester and detoxify metals from contaminated environments, and addressing chemical pollutants, such as PFAS, by leveraging our generative models to develop proteins that can bind and degrade these persistent environmental toxins. Finally, we will explore our long-term goal of generating new cell states with model-designed proteins, highlighting our recent work on transcription factor-directed stem cell differentiation to ovarian cell types, such as granulosa cells and oogonia. By combining generative design with experimental engineering, our hybrid lab aims to translate these advances into practical applications for treating intractable diseases and addressing environmental challenges.
Pranam Chatterjee, PhD
Assistant Professor, Biomedical Engineering and Computer Science, Duke University
Pranam Chatterjee is an Assistant Professor of Biomedical Engineering and Computer Science at Duke University. Research in his Programmable Biology Group exists at the interface of computational and experimental design, specifically training generative language models to de novo design proteins that bind and edit target molecules. Having completed his SB, SM, and PhD from MIT, he developed sequence-based algorithms to engineer broad-targeting CRISPR enzymes, which can programmably bind and edit any DNA sequence. His lab further establishes deep learning-based methods that discover transcription factor proteins which direct differentiation of stem cells, with a key focus on ovarian cell types. More recently, his research has extended to the emergent field of “proteome” editing, where his team has pioneered the development of generative language models for the design of “guide” peptides, which bind and post-translationally modify undruggable proteins, including those implicated in neurodegenerative diseases, viral diseases, and pediatric cancers. To translate this work, he has co-founded two companies, UbiquiTx, Inc. and Gameto, Inc., which builds upon his foundational research to commercialize novel protein-based cancer therapeutics and fertility solutions, respectively. He is the recipient of the Hartwell Individual Biomedical Research Award, as well as numerous foundation and NIH awards for his work. Overall, the long-term goals of his lab are to de novo design protein-based binders to any molecule, whether mutant DNA, undruggable proteins, heavy metals, or pollutant chemicals, by integrating the newest advances in artificial intelligence with robust experimental engineering platforms.
Programmable Biology Group: https://www.
Gameto, Inc: https://www.gametogen.