Global ETD Search

Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.

Results

Showing 1 to 18 of 18 for “"ProteinMPNN"”.

  1. Computational Design of Proteins that Bind to TLR7 and FCyRIIa

    … design tools including RF Diffusion, ProteinMPNN, and Alphafold 2, designing protein adjuvants for these targets has become possible. The results of the TLR7 adjuvant design campaign show through yeast display and BLI that there are 2 potential binding candidates. The IL6 activation …

    washington Repository record for Computational Design of Proteins that Bind to TLR7 and FCyRIIa (opens in a new tab)

  2. Computational Stabilization of a Non-heme Iron Enzyme Enables Efficient Evolution of New Function

    … we evaluate the use of the deep-learning tool ProteinMPNN for redesigning a non-heme amino acid iron hydroxylase with promiscuous C-H hydroxylation activity towards a carboxylic acid substrate. We describe the process by which critical residues in our candidate enzyme were fixed prior to design …

    washington Repository record for Computational Stabilization of a Non-heme Iron Enzyme Enables Efficient Evolution of New Function (opens in a new tab)

  3. Computational and Rational Stabilization of Toll-Like Receptors for the Development of Novel Tools

    … tools. Using AI-guided design with ProteinMPNN, AlphaFold2 and RosettaFold Diffusion in addition to physics and rational approaches, we generated stabilized and expressible variants of TLR2 and TLR5, facilitating downstream applications including de novo minibinder generation and …

    washington Repository record for Computational and Rational Stabilization of Toll-Like Receptors for the Development of Novel Tools (opens in a new tab)

  4. Deep Learning Tools for Protein Binder Design

    … bind. I will then demonstrate how we can use the ProteinMPNN model, in combination with classical Rosetta protocols, to perform efficient sequence design on binder backbones. Finally, I will show how we trained a denoising diffusion model to generate protein backbones and how this can be used to …

    washington Repository record for Deep Learning Tools for Protein Binder Design (opens in a new tab)

  5. De Novo Design of Protein Inhibitors Against Bacterial Pathogen Type III Secretion System (T3SS) Assembly

    … Deep learning-based software, RFDiffusion and ProteinMPNN, were used to generate α-helical bundle proteins that bind and target polymerization hotspots of the Salmonella Typhimurium T3SS needle protein, PrgI. Initial inhibitor candidates were identified through in silico screening of …

    gatech Repository record for De Novo Design of Protein Inhibitors Against Bacterial Pathogen Type III Secretion System (T3SS) Assembly (opens in a new tab)

  6. Bacterial Production of Soluble Snake Venom Metalloproteinase (SVMP) for High-Throughput Binder Discovery

    … learning programs, which includes AlphaFold2, ProteinMPNN, and PyRosetta. This approach aims to engineer or redesign complex venom proteins to improve their expression and solubility while maintaining their native structural conformation. Laboratory validations show the success of this protein …

    bristol Repository record for Bacterial Production of Soluble Snake Venom Metalloproteinase (SVMP) for High-Throughput Binder Discovery (opens in a new tab) Embargoed until 2027-03-17

  7. Design and Characterization of De Novo Photoactivated Charge Separating Proteins

    … and machine learning techniques (Alphafold and proteinMPNN) to design and screen charge separation scaffolds. Our first generation of designs contained only the porphyrin sites. We expressed and purified the twelve sequences that performed best in silico. Six express with heme bound, and of the …

    cuny-grad Repository record for Design and Characterization of De Novo Photoactivated Charge Separating Proteins (opens in a new tab)

  8. Developing Novel in Silico Tools for Heterochiral Macrocycle Design

    … Second, CyclicMPNN, a fine-tuned adaptation of ProteinMPNN, is presented, showing that in silico-derived datasets can significantly improve cyclic peptide sequence design across multiple sizes and conditional generation tasks. Third, CyclicCAE, a convolutional autoencoder, is developed to encode …

    oregon Repository record for Developing Novel in Silico Tools for Heterochiral Macrocycle Design (opens in a new tab) Embargoed until 2028-07-31

  9. De novo computational design of bone morphogenetic protein-2 knuckle binders

    … the rate of success with RFDiffusion[4] and ProteinMPNN[5] computational techniques. This thesis overviews the successful de novo design of a protein binder with an equilibrium dissociation constant of 771 nM as measured by biolayer interferometry.

    oregon Repository record for De novo computational design of bone morphogenetic protein-2 knuckle binders (opens in a new tab)

  10. Exploring the rational design of bZip-based Dominant-Negative peptides: An integrative strategy for oncogenic activity suppression

    … aimed to address these challenges by employing ProteinMPNN for the in-silico design of a dominant-negative peptide, such as a modified C/EBPβ, to potentially disrupt the heterodimerization of ATF4 with its natural binding partners. Subsequent in-vitro fluorescent polarization assays assessed the …

    iastate Repository record for Exploring the rational design of bZip-based Dominant-Negative peptides: An integrative strategy for oncogenic activity suppression (opens in a new tab)

  11. Large Scale Kmer-Based Proteomic Analysis: An Application Towards Evolutionary Constraint Discovery

    … interpreted cautiously. Finally, comparison with ProteinMPNN-generated sequences shows how exact natural k-mer counts can be used to evaluate biases in protein sequence design models. Together, these results provide evidence for structured constraints in protein sequence space and show how …

    calpoly Repository record for Large Scale Kmer-Based Proteomic Analysis: An Application Towards Evolutionary Constraint Discovery (opens in a new tab)

  12. De Novo Design Approaches Toward the Development of Artificial Cu Proteins (ArCuPs) for Activation of Small Molecules with Functional Relevance to Cu Monooxygenases

    … using deep-learning tools such as Alphafold2, ProteinMPNN, and Rosetta, followed by high-throughput methods to evaluate their folding and catalytic properties. This work leverages the capabilities of de novo metalloprotein design toward developing an artificial class of enzymes that advances …

    mississippi Repository record for De Novo Design Approaches Toward the Development of Artificial Cu Proteins (ArCuPs) for Activation of Small Molecules with Functional Relevance to Cu Monooxygenases (opens in a new tab)

  13. Computational Design of Peptides and Proteins for Cyclic Peptide Applications

    … to make CIDs. I used Rosetta, Alphafold2, and ProteinMPNN to design and filter peptide binding proteins. The binding was validated using isothermal calorimetry, and equilibrium dialysis leading to the identification of multiple nanomolar and micromolar peptide binders. Finally, we can use the …

    washington Repository record for Computational Design of Peptides and Proteins for Cyclic Peptide Applications (opens in a new tab)

  14. Tool development for single-mRNA translation dynamics imaging and quantification

    … into functional intrabodies. Using AlphaFold2, ProteinMPNN, and live-cell screening, we generate a panel of intrabodies targeting synthetic and viral epitopes, and diverse histone modifications. This work establishes a generalizable and scalable framework for intrabody development, enabling the …

    colostate Repository record for Tool development for single-mRNA translation dynamics imaging and quantification (opens in a new tab) Embargoed until 2028-06-05

  15. Structure-guided ligand discovery and computational redesign of plasmodium falciparum protein targets

    … Zielproteine besser nutzbar zu machen, wurde ein ProteinMPNN-Redesign-Ansatz entwickelt, bei dem evolutionär konservierte sowie struktur- und bindungsrelevante Positionen beibehalten wurden. Das übrige Proteingerüst wurde auf höhere Stabilität hin optimiert. Der Ansatz wurde auf PfBDP1 BRD, …

    freiburg-diss Repository record for Structure-guided ligand discovery and computational redesign of plasmodium falciparum protein targets (opens in a new tab)

  16. From Site-Directed DNA Conjugation to Binder Design: Engineering Affinity Proteins for Diagnostics

    … combining RFDiffusion backbone diffusion, ProteinMPNN sequence design, and AlphaFold2 structural filtering was established. De novo affinity proteins targeting the head domain of Influenza A H1 hemagglutinin were designed. All top-ranked designs selected for experimental characterization …

    ethz Repository record for From Site-Directed DNA Conjugation to Binder Design: Engineering Affinity Proteins for Diagnostics (opens in a new tab)

  17. Functionalization of de novo TIM barrels

    … combined AI-based methods like RFdiffusion and ProteinMPNN, for generating structural extensions, and the physics-based software Triad for enzyme design. A key aspect of the extension design was the positioning of one catalytic residue above the barrel. This placement enabled the extensions to …

    bayreuth Repository record for Functionalization of de novo TIM barrels (opens in a new tab)

  18. Reverse Transcriptase Characterization and Engineering for Genome Editing

    Abstract Templated editing, consisting of a Cas9 enzyme coupled to a reverse transcriptase (RT) directed by a programmable guide RNA to install edits in the genome, offers unprecedented potential for treating genetic diseases. Yet, translation to clinical applications is hindered by unpredictable …

    chalmers Repository record for Reverse Transcriptase Characterization and Engineering for Genome Editing (opens in a new tab)