Biology subjects

Ponnapati, M.

Publications and source records attributed to Ponnapati, M..

5 recordsLinked to original sources

bioRxiv2025

Designing proteins with reduced T-cell epitopes through policy optimization

AO_SCPLOWBSTRACTC_SCPLOWDeep generative models for protein structure and sequence are increasingly used to design proteins with therapeutic and industrial applications, but the clinical success of designed therapeutics ultimately depends on their compatibility with the human immune system. Immune response is triggered by a cascade of molecular events, including proteasomal cleavage, peptide elution, and binding to the highly polymorphic Major Histocompatibility Complex (MHC) Class I molecules, yet prior approaches have generally modeled these processes in isolation or restricted attention to a limited set of alleles. In this work, we develop predictors for cleavage, elution, and binding affinity in the MHC Class I pathway, incorporating evidential deep learning to provide unified uncertainty estimates. We first perform supervised fine-tuning of a protein language model on human proteins, and then align the model through group relative policy optimization (GRPO) to reduce MHC Class I epitopes under a curriculum learning framework, in which the curriculum progressively increases the number of masked predicted epitopes and the number of alleles considered during training. This strategy enables the generation of protein candidates that are optimized for immune compatibility across diverse MHC Class I alleles while accounting for predictive uncertainty in modeling the immune response.

bioengineering↗

bioRxiv2022

Design of Peptide-Based Protein Degraders via Contrastive Deep Learning

AO_SCPLOWBSTRACTC_SCPLOWTherapeutic modalities targeting pathogenic proteins are the gold standard of treatment for multiple disease indications. Unfortunately, a significant portion of these proteins are considered "undruggable" by standard small molecule-based approaches, largely due to their disordered nature and instability. Designing functional peptides to undruggable targets, either as standalone binders or fusions to effector domains, thus presents a unique opportunity for therapeutic intervention. In this work, we adapt recent models for contrastive language-image pre-training (CLIP) to devise a unified, sequence-based framework to design target-specific peptides. Furthermore, by leveraging known experimental binding proteins as scaffolds, we create a streamlined inference pipeline, termed Cut&CLIP, that efficiently selects peptides for downstream screening. Finally, we experimentally fuse candidate peptides to E3 ubiquitin ligase domains and demonstrate robust intracellular degradation of pathogenic protein targets in human cells, motivating further development of our technology for future clinical translation.

synthetic biology↗

bioRxiv2021

Sub-Picomolar Detection of SARS-CoV-2 RBD via Computationally-Optimized Peptide Beacons

The novel coronavirus SARS-CoV-2 continues to pose a significant global health threat. Along with vaccines and targeted therapeutics, there is a critical need for rapid diagnostic solutions. In this work, we employ deep learning-based protein design to engineer molecular beacons that function as conformational switches for high sensitivity detection of the SARS-CoV-2 spike protein receptor binding domain (S-RBD). The beacons contain two peptides, together forming a heterodimer, and a binding ligand between them to detect the presence of S-RBD. In the absence of S-RBD (OFF), the peptide beacons adopt a closed conformation that opens when bound to the S-RBD and produces a fluorescence signal (ON), utilizing a fluorophore-quencher pair at the two ends of the heterodimer stems. Two candidate beacons, C17LC21 and C21LC21, can detect the S-RBD with limits of detection (LoD) in the sub-picomolar range. We envision that these beacons can be easily integrated with on-chip optical sensors to construct a point-of-care diagnostic platform for SARS-CoV-2.

bioengineering↗

bioRxiv2021

Distillation of MSA Embeddings to Folded Protein Structures with Graph Transformers

AO_SCPLOWBSTRACTC_SCPLOWDetermining the structure of proteins has been a long-standing goal in biology. Language models have been recently deployed to capture the evolutionary semantics of protein sequences. Enriched with multiple sequence alignments (MSA), these models can encode protein tertiary structure. In this work, we introduce an attention-based graph architecture that exploits MSA Transformer embeddings to directly produce three-dimensional folded structures from protein sequences. We envision that this pipeline will provide a basis for efficient, end-to-end protein structure prediction.

synthetic biology↗

bioRxiv2020

Targeted Intracellular Degradation of SARS-CoV-2 RBD via Computationally-Optimized Peptide Fusions

The COVID-19 pandemic, caused by the novel coronavirus SARS-CoV-2, has elicited a global health crisis of catastrophic proportions. With no approved cure or vaccine currently available, there is a critical need for effective antiviral strategies. In this study, we report a novel antiviral platform, through computational design of ACE2-derived peptides which both target the viral spike protein receptor binding domain (RBD) and recruit E3 ubiquitin ligases for subsequent intracellular degradation of SARS-CoV-2 in the proteasome. Our engineered peptide fusions demonstrate robust RBD degradation capabilities in human cells, thus prompting their further experimental characterization and therapeutic development.

bioengineering↗