Search NASA⌕ Search

SEARCH · Search NASA

Results for “Generative Protein Design”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 19 records
All sourcesNASA NTRSDOE OSTI
DOE OSTI2026

Flow matching meets biology and life science: a survey

Over the past decade, advances in generative modeling, such as generative adversarial networks, masked autoencoders, and diffusion models, have significantly transformed biological research and discovery, enabling breakthroughs in molecule design, protein generation, catalysis discovery, drug discovery, and beyond. At the same time, biological applications have served as valuable testbeds for evaluating the capabilities of generative models. Recently, flow matching has emerged as a powerful and efficient alternative to diffusion-based generative modeling, with growing interest in its application to problems in biology and life sciences. This paper presents the first comprehensive survey of recent developments in flow matching and its applications in biological domains. We begin by systematically reviewing the foundations and variants of flow matching, and then categorize its applications into three major areas: biological sequence modeling, molecule generation and design, and peptide and protein generation. For each, we provide an in-depth review of recent progress. We also summarize commonly used datasets and software tools, and conclude with a discussion of potential future directions.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2023

Generative design of de novo proteins based on secondary-structure constraints using an attention-based diffusion model

We report two generative deep-learning models that predict amino acid sequences and 3D protein structures on the basis of secondary-structure design objectives via either the overall content or the per-residue structure. Both models are robust regarding imperfect inputs and offer de novo design capacity because they can discover new protein sequences not yet discovered from natural mechanisms or systems. The residue-level secondary-structure design model generally yields higher accuracy and more diverse sequences. These findings suggest unexplored opportunities for protein designs and functional outcomes within the vast amino acid sequences beyond known proteins. Our models, based on an attention-based diffusion model and trained on a dataset extracted from experimentally known 3D protein structures, offer numerous downstream applications in the conditional generative design of various biological or engineering systems. Future work could include additional conditioning and an exploration of other functional properties of the generated proteins for various properties beyond structural objectives.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2023

De novo design of high-affinity binders of bioactive helical peptides

Many peptide hormones form an α-helix on binding their receptors, and sensitive methods for their detection could contribute to better clinical management of disease. De novo protein design can now generate binders with high affinity and specificity to structured proteins. However, the design of interactions between proteins and short peptides with helical propensity is an unmet challenge. Here we describe parametric generation and deep learning-based methods for designing proteins to address this challenge. We show that by extending RFdiffusion to enable binder design to flexible targets, and to refining input structure models by successive noising and denoising (partial diffusion), picomolar-affinity binders can be generated to helical peptide targets by either refining designs generated with other methods, or completely de novo starting from random noise distributions without any subsequent experimental optimization. The RFdiffusion designs enable the enrichment and subsequent detection of parathyroid hormone and glucagon by mass spectrometry, and the construction of bioluminescence-based protein biosensors. The ability to design binders to conformationally variable targets, and to optimize by partial diffusion both natural and designed proteins, should be broadly useful.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2024

Generative $β$-hairpin design using a residue-based physicochemical property landscape

De novo peptide design is a new frontier that has broad application potential in the biological and biomedical fields. Most existing models for de novo peptide design are largely based on sequence homology that can be restricted based on evolutionarily derived protein sequences and lack the physicochemical context essential in protein folding. Generative machine learning for de novo peptide design is a promising way to synthesize theoretical data that are based on, but unique from, the observable universe. In this study, we created and tested a custom peptide generative adversarial network intended to design peptide sequences that can fold into the -hairpin secondary structure. This deep neural network model is designed to establish a preliminary foundation of the generative approach based on physicochemical and conformational properties of 20 canonical amino acids, for example, hydrophobicity and residue volume, using extant structure-specific sequence data from the PDB. The beta generative adversarial network model robustly distinguishes secondary structures of hairpin from α helix and intrinsically disordered peptides with an accuracy of up to 96% and generates artificial -hairpin peptide sequences with minimum sequence identities around 31% and 50% when compared against the current NCBI PDB and nonredundant databases, respectively. These results highlight the potential of generative models specifically anchored by physicochemical and conformational property features of amino acids to expand the sequence-to-structure landscape of proteins beyond evolutionary limits.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2021

Computation-guided optimization of split protein systems

Splitting bioactive proteins into conditionally reconstituting fragments is a powerful strategy for building tools to study and control biological systems. However, split proteins often exhibit a high propensity to reconstitute, even without the conditional trigger, limiting their utility. Current approaches for tuning reconstitution propensity are laborious, context-specific or often ineffective. Here, we report a computational design strategy grounded in fundamental protein biophysics to guide experimental evaluation of a sparse set of mutants to identify an optimal functional window. We hypothesized that testing a limited set of mutants would direct subsequent mutagenesis efforts by predicting desirable mutant combinations from a vast mutational landscape. This strategy varies the degree of interfacial destabilization while preserving stability and catalytic activity. We validate our method by solving two distinct split protein design challenges, generating both design and mechanistic insights. Furthermore, this new technology will streamline the generation and use of split protein systems for diverse applications.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2022

Generation of bright monomeric red fluorescent proteins via computational design of enhanced chromophore packing

Red fluorescent proteins (RFPs) have found widespread application in chemical and biological research due to their longer emission wavelengths. Here, we use computational protein design to increase the quantum yield and thereby brightness of a dim monomeric RFP (mRojoA, quantum yield = 0.02) by optimizing chromophore packing with aliphatic residues, which we hypothesized would reduce torsional motions causing non-radiative decay. Experimental characterization of the top 10 designed sequences yielded mSandy1 (λ em = 609 nm, quantum yield = 0.26), a variant with equivalent brightness to mCherry, a widely used RFP. We next used directed evolution to further increase brightness, resulting in mSandy2 (λ em = 606 nm, quantum yield = 0.35), the brightest Discosoma sp. derived monomeric RFP with an emission maximum above 600 nm reported to date. Crystallographic analysis of mSandy2 showed that the chromophore p-hydroxybenzylidene moiety is sandwiched between the side chains of Leu63 and Ile197, a structural motif that has not previously been observed in RFPs, and confirms that aliphatic packing leads to chromophore rigidification. Our results demonstrate that computational protein design can be used to generate bright monomeric RFPs, which can serve as templates for the evolution of novel far-red fluorescent proteins.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2025

Bond-centric modular design of protein assemblies

Directional interactions that generate regular coordination geometries are a powerful means of guiding molecular and colloidal self-assembly, but implementing such high-level interactions with proteins remains challenging due to their complex shapes and intricate interface properties. Here we describe a modular approach to protein nanomaterial design inspired by the rich chemical diversity that can be generated from the small number of atomic valencies. We design protein building blocks using deep learning-based generative tools, incorporating regular coordination geometries and tailorable bonding interactions that enable the assembly of diverse closed and open architectures guided by simple geometric principles. Experimental characterization confirms the successful formation of more than 20 multicomponent polyhedral protein cages, two-dimensional arrays and three-dimensional protein lattices, with a high (10%–50%) success rate and electron microscopy data closely matching the corresponding design models. Due to modularity, individual building blocks can assemble with different partners to generate distinct regular assemblies, resulting in an economy of parts and enabling the construction of reconfigurable networks for designer nanomaterials.

Biomaterials – proteins↗
DOE OSTI2025

Computational design of potent and selective binders of BAK and BAX

Potent and selective binders of the key proapoptotic proteins BAK and BAX have not been described. We use computational protein design to generate high affinity binders of BAK and BAX with greater than 100-fold specificity for their target. Both binders activate their targets when at low concentration, driving pore formation, but inhibit membrane permeabilization when in excess. Crystallography shows that the BAK binder induces BAK unfolding, exposing the α6 helix and BH3 domain. Together, these data suggest that upon binding, BAK or BAX unfold; at high binder concentrations, self-association of the partially folded BAK or BAX proteins is blocked and the membrane remains intact, whereas at low concentrations, dimers form, and the membrane ruptures. Our designed binders modulate apoptosis via direct, specific interactions with BAK and BAX and reveal that for therapeutic strategies targeting BAK and BAX, inhibition requires saturating binder concentrations at the site of action.

Berger, Stephanie↗
DOE OSTI2020

Modular repeat protein sculpting using rigid helical junctions

The ability to precisely design large proteins with diverse shapes would enable applications ranging from the design of protein binders that wrap around their target to the positioning of multiple functional sites in specified orientations. We describe a protein backbone design method for generating a wide range of rigid fusions between helix-containing proteins and use it to design 75,000 structurally unique junctions between monomeric and homo-oligomeric de novo designed and ankyrin repeat proteins (RPs). Of the junction designs that were experimentally characterized, 82% have circular dichroism and solution small-angle X-ray scattering profiles consistent with the design models and are stable at 95 °C. Crystal structures of four designed junctions were in close agreement with the design models with rmsds ranging from 0.9 to 1.6 Å. Electron microscopic images of extended tetrameric structures and ~10-nm-diameter “L” and “V” shapes generated using the junctions are close to the design models, demonstrating the control the rigid junctions provide for protein shape sculpting over multiple nanometer length scales.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2022

Robust deep learning–based protein sequence design using ProteinMPNN

Although deep learning has revolutionized protein structure prediction, almost all experimentally characterized de novo protein designs have been generated using physically based approaches such as Rosetta. Here, we describe a deep learning–based protein sequence design method, ProteinMPNN, that has outstanding performance in both in silico and experimental tests. On native protein backbones, ProteinMPNN has a sequence recovery of 52.4% compared with 32.9% for Rosetta. The amino acid sequence at different positions can be coupled between single or multiple chains, enabling application to a wide range of current protein design challenges. We demonstrate the broad utility and high accuracy of ProteinMPNN using x-ray crystallography, cryo–electron microscopy, and functional studies by rescuing previously failed designs, which were made using Rosetta or AlphaFold, of protein monomers, cyclic homo-oligomers, tetrahedral nanoparticles, and target-binding proteins.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2024

Control over Conformational Landscapes of Polypeptoids by Monomer Sequence Patterning

The ability to program chain conformation and structure through control over the monomer sequence of synthetic polymers has broad implications for next-generation material design. While related problems of protein-folding and de novo design have generated accurate predictions of 3D folded chain structures, generalization to synthetic polymers remains intractable due to the requirement of large structural databases and the intrinsically disordered nature of polymer building blocks. In this work, polypeptoids, a class of peptidomimetic synthetic polymers, are utilized to build a general workflow for the study of relationships between monomer sequence and dynamic 3D chain structure in solution. Furthermore, this work demonstrates how control over the monomer sequence can alter the conformational landscape of synthetic polymers to deviate dramatically from classical chain statistics. Specifically, the distribution of end-to-end distances, as measured by double electron-electron resonance spectroscopy in dilute solvent, is systematically skewed towards shorter distances with an increasing number of hydrophobes and further refined by hydrophobe arrangement in amphiphilic polypeptoid chains.

36 MATERIALS SCIENCE↗
DOE OSTI2024

Simultaneous enhancement of multiple functional properties using evolution-informed protein design

Abstract A major challenge in protein design is to augment existing functional proteins with multiple property enhancements. Altering several properties likely necessitates numerous primary sequence changes, and novel methods are needed to accurately predict combinations of mutations that maintain or enhance function. Models of sequence co-variation (e.g., EVcouplings), which leverage extensive information about various protein properties and activities from homologous protein sequences, have proven effective for many applications including structure determination and mutation effect prediction. We apply EVcouplings to computationally design variants of the model protein TEM-1 β -lactamase. Nearly all the 14 experimentally characterized designs were functional, including one with 84 mutations from the nearest natural homolog. The designs also had large increases in thermostability, increased activity on multiple substrates, and nearly identical structure to the wild type enzyme. This study highlights the efficacy of evolutionary models in guiding large sequence alterations to generate functional diversity for protein design applications.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2025

Design of facilitated dissociation enables timing of cytokine signalling

Protein design has focused on the design of ground states, ensuring that they are sufficiently low energy to be highly populated. Designing the kinetics and dynamics of a system requires, in addition, the design of excited states that are traversed in transitions from one low-lying state to another. This is a challenging task because such states must be sufficiently strained to be poorly populated, but not so strained that they are not populated at all, and because protein design methods have focused on generating near-ideal structures. Here we describe a general approach for designing systems that use an induced-fit power stroke to generate a structurally frustrated and strained excited state, allosterically driving protein complex dissociation. X-ray crystallography, double electron–electron resonance spectroscopy and kinetic binding measurements show that incorporating excited states enables the design of effector-induced increases in dissociation rates as high as 5,700-fold. We highlight the power of this approach by designing rapid biosensors, kinetically controlled circuits and cytokine mimics that can be dissociated from their receptors within seconds, enabling dissection of the temporal dynamics of interleukin-2 signalling.

deformation dynamics↗
DOE OSTI2022

Ig-VAE: Generative modeling of protein structure by direct 3D coordinate generation

While deep learning models have seen increasing applications in protein science, few have been implemented for protein backbone generation—an important task in structure-based problems such as active site and interface design. We present a new approach to building class-specific backbones, using a variational auto-encoder to directly generate the 3D coordinates of immunoglobulins. Our model is torsion- and distance-aware, learns a high-resolution embedding of the dataset, and generates novel, high-quality structures compatible with existing design tools. We show that the Ig-VAE can be used with Rosetta to create a computational model of a SARS-CoV2-RBD binder via latent space sampling. We further demonstrate that the model’s generative prior is a powerful tool for guiding computational protein design, motivating a new paradigm under which backbone design is solved as constrained optimization problem in the latent space of a generative model.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2021

Design of multi-scale protein complexes by hierarchical building block fusion

A systematic and robust approach to generating complex protein nanomaterials would have broad utility. We develop a hierarchical approach to designing multi-component protein assemblies from two classes of modular building blocks: designed helical repeat proteins (DHRs) and helical bundle oligomers (HBs). We first rigidly fuse DHRs to HBs to generate a large library of oligomeric building blocks. We then generate assemblies with cyclic, dihedral, and point group symmetries from these building blocks using architecture guided rigid helical fusion with new software named WORMS. X-ray crystallography and cryo-electron microscopy characterization show that the hierarchical design approach can accurately generate a wide range of assemblies, including a 43 nm diameter icosahedral nanocage. The computational methods and building block sets described here provide a very general route to de novo designed protein nanomaterials.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2023

Directing polymorph specific calcium carbonate formation with de novo protein templates

Biomolecules modulate inorganic crystallization to generate hierarchically structured biominerals, but the atomic structure of the organic-inorganic interfaces that regulate mineralization remain largely unknown. We hypothesized that heterogeneous nucleation of calcium carbonate could be achieved by a structured flat molecular template that pre-organizes calcium ions on its surface. To test this hypothesis, we design helical repeat proteins (DHRs) displaying regularly spaced carboxylate arrays on their surfaces and find that both protein monomers and protein-C a2+ supramolecular assemblies directly nucleate nano-calcite with non-natural {110} or {202} faces while vaterite, which forms first in the absence of the proteins, is bypassed. These protein-stabilized nanocrystals then assemble by oriented attachment into calcite mesocrystals. We find further that nanocrystal size and polymorph can be tuned by varying the length and surface chemistry of the designed protein templates. Thus, bio-mineralization can be programmed using de novo protein design, providing a route to next-generation hybrid materials.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2023

Large language models generate functional protein sequences across diverse families

Deep-learning language models have shown promise in various biotechnological applications, including protein design and engineering. Here, in this paper, we describe ProGen, a language model that can generate protein sequences with a predictable function across large protein families, akin to generating grammatically and semantically correct natural language sentences on diverse topics. The model was trained on 280 million protein sequences from >19,000 families and is augmented with control tags specifying protein properties. ProGen can be further fine-tuned to curated sequences and tags to improve controllable generation performance of proteins from families with sufficient homologous samples. Artificial proteins fine-tuned to five distinct lysozyme families showed similar catalytic efficiencies as natural lysozymes, with sequence identity to natural proteins as low as 31.4%. ProGen is readily adapted to diverse protein families, as we demonstrate with chorismate mutase and malate dehydrogenase.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2025

ProteinTuneRL

ProteinTuneRL is a framework designed to harness the power of reinforcement learning for advanced protein design. The project enables fine-tuning of generative models to explore and optimize protein sequences with tailored structural and functional properties.

Landajuela Larma, Mikel [Lawrence Livermore Nation↗