Biology subjects

Baek, M.

Publications and source records attributed to Baek, M..

At least 37 records · Page 2Linked to original sources

bioRxiv2022

Protein-protein interactions in the Mla lipid transport system probed by computational structure prediction and deep mutational scanning

The outer membrane (OM) of Gram-negative bacteria is an asymmetric bilayer that protects the cell from various external stressors, such as antibiotics. The Mla transport system is implicated in the Maintenance of outer membrane Lipid Asymmetry and is thought to mediate retrograde phospholipid transport across the cell envelope. This system uses a shuttle-like mechanism to move lipids between the MlaFEDB inner membrane complex and the MlaA-OmpF/C OM complex, via a periplasmic lipid-binding protein, MlaC. MlaC binds to MlaD and MlaA, but the underlying protein-protein interactions that facilitate lipid transfer are not well understood. Here, we take an unbiased deep mutational scanning approach to map the fitness landscape of MlaC, which provides insights into important functional sites. Combining this analysis with AlphaFold2 structure predictions and binding experiments, we map the MlaC-MlaA and MlaC-MlaD protein-protein interfaces. Our results suggest that the MlaD and MlaA binding surfaces on MlaC overlap to a large extent, leading to a model in which MlaC can only bind one of these proteins at a time. Low-resolution cryo-electron microscopy (cryo-EM) maps of MlaC bound to MlaFEDB suggest that at least two MlaC molecules can bind to MlaD at once, in a conformation consistent with AlphaFold2 predictions. These data lead us to a model for MlaC interaction with its binding partners and insights into lipid transfer steps that underlie phospholipid transport between the inner and outer membranes.

biophysics↗

bioRxiv2022

Broadly applicable and accurate protein design by integrating structure prediction networks and diffusion generative models

There has been considerable recent progress in designing new proteins using deep learning methods1-9. Despite this progress, a general deep learning framework for protein design that enables solution of a wide range of design challenges, including de novo binder design and design of higher order symmetric architectures, has yet to be described. Diffusion models10,11 have had considerable success in image and language generative modeling but limited success when applied to protein modeling, likely due to the complexity of protein backbone geometry and sequence-structure relationships. Here we show that by fine tuning the RoseTTAFold structure prediction network on protein structure denoising tasks, we obtain a generative model of protein backbones that achieves outstanding performance on unconditional and topology-constrained protein monomer design, protein binder design, symmetric oligomer design, enzyme active site scaffolding, and symmetric motif scaffolding for therapeutic and metal-binding protein design. We demonstrate the power and generality of the method, called RoseTTAFold Diffusion (RFdiffusion), by experimentally characterizing the structures and functions of hundreds of new designs. In a manner analogous to networks which produce images from user-specified inputs, RFdiffusion enables the design of diverse, complex, functional proteins from simple molecular specifications.

biochemistry↗

bioRxiv2022

Accurate Mutation Effect Prediction using RoseTTAFold

Predicting the effects of mutations on protein function is an outstanding challenge. Here we assess the performance of the deep learning based RoseTTAFold structure prediction and design method for unsupervised mutation effect prediction. Using RoseTTAFold in inference mode, without any additional training, we obtain state of the art accuracy on predicting mutation effects for a set of diverse protein families. Thus, although the architecture of RoseTTAFold was developed to address the protein structure prediction problem, during model training RoseTTAFold acquired an understanding of the mutational landscapes of proteins comparable to that of large recently developed language models. The ability to reason over structure as well as sequence could enable even more precise mutation effect predictions following supervised training.

biochemistry↗

bioRxiv2022

Top-down design of protein nanomaterials with reinforcement learning

The multisubunit protein assemblies that play critical roles in biology are the result of evolutionary selection for function of the entire assembly, and hence the subunits in structures such as icosahedral viral capsids often fit together with remarkable shape complementarity1,2. In contrast, the large multisubunit assemblies that have been created by de novo protein design, notably the icosahedral nanocages used in a new generation of potent vaccines3-7, have been built by first designing symmetric oligomers with cyclic symmetry and then assembling these into nanocages while keeping the internal structure fixed8-14, which results in more porous structures with less extensive shape matching between the components. Such hierarchical "bottom-up" design approaches have the advantage that one interface can be designed and validated in the context of the cyclic oligomer building block15,16, but the disadvantage that the structural and functional features of the assemblies are limited by the properties of the predesigned building blocks. To overcome this limitation, we set out to develop a "top-down" reinforcement learning based approach to protein nanomaterial design in which both the structures of the subunits and the interactions between them are built up coordinately in the context of the entire assembly. We developed a Monte Carlo tree search (MCTS) method17,18 which assembles protein monomer structures in the context of an overall architecture guided by a loss function which enables specification of any desired overall structural properties such as shape and porosity. We demonstrate the power of the approach by designing hyperstable icosahedral assemblies more compact than any previously observed protein icosahedral structure (designed or naturally occurring), that have very low porosity and are robust to fusion and display of proteins as complex as influenza hemagglutinin. CryoEM structures of two designs are very close to the computational design models. Our top-down reinforcement learning approach should enable the design of a wide variety of complex protein nanomaterials by direct optimization of overall system properties.

synthetic biology↗

bioRxiv2022

Accurate prediction of nucleic acid and protein-nucleic acid complexes using RoseTTAFoldNA

Protein-nucleic acid complexes play critical roles in biology. Despite considerable recent advances in protein structure prediction, the prediction of the structures of protein-nucleic acid complexes without homology to known complexes is a largely unsolved problem. Here we extend the RoseTTAFold end-to-end deep learning approach to modeling of nucleic acid and protein-nucleic acid complexes. We develop a single trained network, RoseTTAFoldNA, that rapidly produces 3D structure models with confidence estimates for protein-DNA and protein-RNA complexes, and for RNA tertiary structures. In all three cases, confident predictions have considerably higher accuracy than current state of the art methods. RoseTTAFoldNA should be broadly useful for modeling the structure of naturally occurring protein-nucleic acid complexes, and for designing sequence specific RNA and DNA binding proteins.

bioinformatics↗

bioRxiv2022

Peptide binding specificity prediction using fine-tuned protein structure prediction networks

Peptide binding proteins play key roles in biology, and predicting their binding specificity is a long-standing challenge. While considerable protein structural information is available, the most successful current methods use sequence information alone, in part because it has been a challenge to model the subtle structural changes accompanying sequence substitutions. Protein structure prediction networks such as AlphaFold model sequence-structure relationships very accurately, and we reasoned that if it were possible to specifically train such networks on binding data, more generalizable models could be created. We show that placing a classifier on top of the AlphaFold network and fine-tuning the combined network parameters for both classification and structure prediction accuracy leads to a model with strong generalizable performance on a wide range of Class I and Class II peptide-MHC interactions that approaches the overall performance of the state-of-the-art NetMHCpan sequence-based method. The peptide-MHC optimized model shows excellent performance in distinguishing binding and non-binding peptides to SH3 and PDZ domains. This ability to generalize well beyond the training set far exceeds that of sequence only models, and should be particularly powerful for systems where less experimental data is available. Significance statementPeptide binding proteins carry out a variety of biological functions in cells and predicting their binding specificity could significantly improve our understanding of molecular pathways. Deep neural networks have achieved high structure prediction accuracy, but are not trained to predict binding specificity. Here we describe an approach to extending such networks to jointly predict protein structure and binding specificity. We incorporate AlphaFold into this approach, and fine-tune its parameters on peptide-MHC Class I and II structural and binding data. The fine-tuned model approaches state-of-the-art classification accuracy on peptide-MHC specificity prediction and generalizes to other peptide-binding systems such as the PDZ and SH3 domains.

bioinformatics↗

bioRxiv2022

Improving de novo Protein Binder Design with Deep Learning

We explore the improvement of energy-based protein binder design using deep learning. We find that using AlphaFold2 or RoseTTAFold to assess the probability that a designed sequence adopts the designed monomer structure, and the probability that this structure binds the target as designed, increases design success rates nearly 10-fold. We find further that sequence design using ProteinMPNN rather than Rosetta considerably increases computational efficiency.

bioengineering↗

bioRxiv2022

Hallucinating protein assemblies

Deep learning generative approaches provide an opportunity to broadly explore protein structure space beyond the sequences and structures of natural proteins. Here we use deep network hallucination to generate a wide range of symmetric protein homo-oligomers given only a specification of the number of protomers and the protomer length. Crystal structures of 7 designs are very close to the computational models (median RMSD: 0.6 [A]), as are 3 cryoEM structures of giant rings with up to 1550 residues, C33 symmetry, and 10 nanometer in diameter; all differ considerably from previously solved structures. Our results highlight the rich diversity of new protein structures that can be created using deep learning, and pave the way for the design of increasingly complex nanomachines and biomaterials. One-sentence summaryDeep network-based protein design enables the generation of cyclic homo-oligomers across the nanoscopic scale.

biophysics↗

bioRxiv2022

The {varphi}PA3 Phage Nucleus is Enclosed by a Self-Assembling, 2D Crystalline Lattice

A growing number of jumbo bacteriophages, with genomes exceeding 200 kb, have been found to establish a Phage Nucleus--a micron-scale, proteinaceous structure encompassing the replicating phage DNA. Bacteriophage and host proteins associated with replication and transcription are concentrated inside the Phage Nucleus while nucleotide synthesis, translation, and numerous other host and exogenous proteins are effectively excluded, including CRISPR-Cas and restriction endonuclease host defense systems. Here, we show that fragments of the Phage Nucleus isolated from {phi}PA3 infected Pseudomonas aeruginosa cells form a square lattice and demonstrate that the recombinantly purified primary Phage Nuclear Enclosure (PhuN) protein spontaneously assembles into sheets also constructed from a square lattice which we resolve to 3.8 [A] by cryo-EM. Our structure reveals that the flexible termini and large loops mediate adaptable inter-tetramer contacts that drive shell assembly into a C2-symmetric lattice. While the interfaces between subunits are mostly well packed, two of the interfaces are open, forming clear channels that likely have important functional implications for the transport of proteins, mRNA, and small molecules.

biochemistry↗

bioRxiv2022

Little skate genome exposes the gene regulatory mechanisms underlying the evolution of vertebrate locomotion

The little skate Leucoraja erinacea, a cartilaginous fish, displays pelvic fin driven walking-like behaviors using genetic programs and neuronal subtypes similar to those of land vertebrates. However, mechanistic studies on little skate motor circuit development have been limited, due to a lack of high-quality reference genome. Here, we generated an assembly of the little skate genome, containing precise gene annotation and structures, which allowed post-genome analysis of spinal motor neurons (MNs) essential for locomotion. Through interspecies comparison of mouse, skate and chicken MN transcriptomes, shared and divergent MN expression profiles were identified. Conserved MN genes were enriched for early-stage nervous system development. Comparison of accessible chromatin regions between mouse and skate MNs revealed conservation of the potential regulators with divergent transcription factor (TF) networks through which expression of MN genes is differentially regulated. TF networks in little skate MNs are much simpler than those in mouse MNs, suggesting a more fine-grained control of gene expression operates in mouse MNs. These findings suggest conserved and divergent mechanisms controlling MN development system of vertebrates during evolution and the contribution of intricate gene regulatory networks in the emergence of sophisticated motor system in tetrapods.

evolutionary biology↗

bioRxiv2021

Deep learning methods for designing proteins scaffolding functional sites

Current approaches to de novo design of proteins harboring a desired binding or catalytic motif require pre-specification of an overall fold or secondary structure composition, and hence considerable trial and error can be required to identify protein structures capable of scaffolding an arbitrary functional site. Here we describe two complementary approaches to the general functional site design problem that employ the RosettaFold and AlphaFold neural networks which map input sequences to predicted structures. In the first "constrained hallucination" approach, we carry out gradient descent in sequence space to optimize a loss function which simultaneously rewards recapitulation of the desired functional site and the ideality of the surrounding scaffold, supplemented with problem-specific interaction terms, to design candidate immunogens presenting epitopes recognized by neutralizing antibodies, receptor traps for escape-resistant viral inhibition, metalloproteins and enzymes, and target binding proteins with designed interfaces expanding around known binding motifs. In the second "missing information recovery" approach, we start from the desired functional site and jointly fill in the missing sequence and structure information needed to complete the protein in a single forward pass through an updated RoseTTAFold trained to recover sequence from structure in addition to structure from sequence. We show that the two approaches have considerable synergy, and AlphaFold2 structure prediction calculations suggest that the approaches can accurately generate proteins containing a very wide array of functional sites.

biochemistry↗

bioRxiv2021

Structures of core eukaryotic protein complexes

Protein-protein interactions play critical roles in biology, but despite decades of effort, the structures of many eukaryotic protein complexes are unknown, and there are likely many interactions that have not yet been identified. Here, we take advantage of recent advances in proteome-wide amino acid coevolution analysis and deep-learning-based structure modeling to systematically identify and build accurate models of core eukaryotic protein complexes, as represented within the Saccharomyces cerevisiae proteome. We use a combination of RoseTTAFold and AlphaFold to screen through paired multiple sequence alignments for 8.3 million pairs of S. cerevisiae proteins and build models for strongly predicted protein assemblies with two to five components. Comparison to existing interaction and structural data suggests that these predictions are likely to be quite accurate. We provide structure models spanning almost all key processes in Eukaryotic cells for 104 protein assemblies which have not been previously identified, and 608 which have not been structurally characterized. One-sentence summaryWe take advantage of recent advances in proteome-wide amino acid coevolution analysis and deep-learning-based structure modeling to systematically identify and build accurate models of core eukaryotic protein complexes.

biochemistry↗

bioRxiv2021

Toward More General Embeddings for Protein Design: Harnessing Joint Representations of Sequence and Structure

AO_SCPLOWBSTRACTC_SCPLOWProtein embeddings learned from aligned sequences have been leveraged in a wide array of tasks in protein understanding and engineering. The sequence embeddings are generated through semi-supervised training on millions of sequences with deep neural models defined with hundreds of millions of parameters, and they continue to increase in performance on target tasks with increasing complexity. We report a more data-efficient approach to encode protein information through joint training on protein sequence and structure in a semi-supervised manner. We show that the method is able to encode both types of information to form a rich embedding space which can be used for downstream prediction tasks. We show that the incorporation of rich structural information into the context under consideration boosts the performance of the model by predicting the effects of single-mutations. We attribute increases in accuracy to the value of leveraging proximity within the enriched representation to identify sequentially and spatially close residues that would be affected by the mutation, using experimentally validated or predicted structures.

biochemistry↗

bioRxiv2021

Accurate prediction of protein structures and interactions using a 3-track network

DeepMind presented remarkably accurate protein structure predictions at the CASP14 conference. We explored network architectures incorporating related ideas and obtained the best performance with a 3-track network in which information at the 1D sequence level, the 2D distance map level, and the 3D coordinate level is successively transformed and integrated. The 3-track network produces structure predictions with accuracies approaching those of DeepMind in CASP14, enables rapid solution of challenging X-ray crystallography and cryo-EM structure modeling problems, and provides insights into the functions of proteins of currently unknown structure. The network also enables rapid generation of accurate models of protein-protein complexes from sequence information alone, short circuiting traditional approaches which require modeling of individual subunits followed by docking. We make the method available to the scientific community to speed biological research. One-Sentence SummaryAccurate protein structure modeling enables rapid solution of structure determination problems and provides insights into biological function.

bioinformatics↗

bioRxiv2021

Structure of the phosphoinositide 3-kinase p110γ-p101 complex reveals molecular mechanism of GPCR activation

The class IB phosphoinositide 3-kinase (PI3K), PI3K{gamma}, is a master regulator of immune cell function, and a promising drug target for both cancer and inflammatory diseases. Critical to PI3K{gamma} function is the association of the p110{gamma} catalytic subunit to either a p101 or p84 regulatory subunit, which mediates activation by G-protein coupled receptors (GPCRs). Here, we report the cryo-EM structure of a heterodimeric PI3K{gamma} complex, p110{gamma}-p101. This structure reveals a unique assembly of catalytic and regulatory subunits that is distinct from other class I PI3K complexes. p101 mediates activation through its G{beta}{gamma} binding domain, recruiting the heterodimer to the membrane and allowing for engagement of a secondary G{beta}{gamma} binding site in p110{gamma}. Multiple oncogenic mutations mapped to these novel interfaces and enhanced G{beta}{gamma} activation. A nanobody that specifically binds to the p101-G{beta}{gamma} interface blocks activation providing a novel tool to study and target p110{gamma}-p101-specific signaling events in vivo.

biochemistry↗

bioRxiv2021

Class I Histone Deacetylases (HDAC1-3) are Histone Lysine Delactylases

Lysine O_SCPLOWLC_SCPLOW-lactylation [K(O_SCPLOWLC_SCPLOW-la)] is a newly discovered histone mark that can be stimulated under conditions of high glycolysis, such as the Warburg effect. K(O_SCPLOWLC_SCPLOW-la) is associated with functions that are different from the widely studied histone acetylation. While K(O_SCPLOWLC_SCPLOW-la) can be introduced by the acetyltransferase p300, histone delactylase enzymes remain unknown. Here, we report the systematic evaluation of zinc- and NAD+-dependent HDACs for their ability to cleave {varepsilon}-N-O_SCPLOWLC_SCPLOW-lactyllysine marks. Our screens identified HDACs 1-3 and SIRT1-3 as delactylases in vitro. HDACs 1-3 show robust activity toward not only K(O_SCPLOWLC_SCPLOW-la) but also K(O_SCPLOWDC_SCPLOW-la) and diverse short-chain acyl modifications. We further confirmed the de-O_SCPLOWLC_SCPLOW-lactylase activity of HDACs 1 and 3 in cells. Identification of p300 and HDAC3 as regulatory enzymes suggests that histone lactylation is installed and removed by enzymes as opposed to spontaneous chemical reactivity. Our results therefore represent an important step toward full characterization of this pathways regulatory elements.

biochemistry↗

bioRxiv2020

Learning a force field from small-molecule crystal lattice predictions enables consistent sub-Angstrom protein-ligand docking

Accurate and rapid calculation of protein-small molecule interaction energies is critical for computational drug discovery. Because of the large chemical space spanned by drug-like molecules, classical force fields contain thousands of parameters describing atom-pair distance and torsional preferences; each parameter is typically optimized independently on simple representative molecules. Here we describe a new approach in which small-molecule force field parameters are jointly optimized guided by the rich source of information contained within thousands of available small molecule crystal structures. We optimize parameters by requiring that the experimentally determined molecular lattice arrangements have lower energy than all alternative lattice arrangements. Thousands of independent crystal lattice-prediction simulations were run on each of 1,386 small molecule crystal structures, and energy function parameters of an implicit solvent energy model were optimized so native crystal lattice arrangements had lowest energy. The resulting energy model was implemented in Rosetta, together with a rapid genetic algorithm docking method employing grid based scoring and receptor flexibility. The success rate of bound structure recapitulation in cross-docking on 1,112 complexes was improved by more than 10% over previously published methods, with solutions within <1 [A] in over half of the cases. Our results demonstrate that small molecule crystal structures are a rich source of information for systematically improving computational drug discovery.

biophysics↗

bioRxiv2020

Improved protein structure refinement guided by deep learning based accuracy estimation

We develop a deep learning framework (DeepAccNet) that estimates per-residue accuracy and residue-residue distance signed error in protein models and uses these predictions to guide Rosetta protein structure refinement. The network uses 3D convolutions to evaluate local atomic environments followed by 2D convolutions to provide their global contexts and outperforms other methods that similarly predict the accuracy of protein structure models. Overall accuracy predictions for X-ray and cryoEM structures in the PDB correlate with their resolution, and the network should be broadly useful for assessing the accuracy of both predicted structure models and experimentally determined structures and identifying specific regions likely to be in error. Incorporation of the accuracy predictions at multiple stages in the Rosetta refinement protocol considerably increased the accuracy of the resulting protein structure models, illustrating how deep learning can improve search for global energy minima of biomolecules.

bioinformatics↗