Biology subjects

Gray, J. J.

Publications and source records attributed to Gray, J. J..

At least 37 records · Page 2Linked to original sources

bioRxiv2023

Flexible Protein-Protein Docking with a Multi-Track Iterative Transformer

Conventional protein-protein docking algorithms usually rely on heavy candidate sampling and re-ranking, but these steps are time-consuming and hinder applications that require high-throughput complex structure prediction, e.g., structure-based virtual screening. Existing deep learning methods for protein-protein docking, despite being much faster, suffer from low docking success rates. In addition, they simplify the problem to assume no conformational changes within any protein upon binding (rigid docking). This assumption precludes applications when binding-induced conformational changes play a role, such as allosteric inhibition or docking from uncertain unbound model structures. To address these limitations, we present GeoDock, a multi-track iterative transformer network to predict a docked structure from separate docking partners. Unlike deep learning models for protein structure prediction that input multiple sequence alignments (MSAs), GeoDock inputs just the sequences and structures of the docking partners, which suits the tasks when the individual structures are given. GeoDock is flexible at the protein residue level, allowing the prediction of conformational changes upon binding. For a benchmark set of rigid targets, GeoDock obtains a 41% success rate, outperforming all the other tested methods. For a more challenging benchmark set of flexible targets, GeoDock achieves a similar number of top-model successes as the traditional method ClusPro [1], but fewer than ReplicaDock2 [2]. GeoDock attains an average inference speed of under one second on a single GPU, enabling its application in large-scale structure screening. Although binding-induced conformational changes are still a challenge owing to limited training and evaluation data, our architecture sets up the foundation to capture this backbone flexibility. Code and a demonstration Jupyter notebook are available at https://github.com/Graylab/GeoDock.

bioinformatics↗

bioRxiv2023

Implicit model to capture electrostatic features of membrane environment.

Membrane protein structure prediction and design are challenging due to the complexity of capturing the interactions in the lipid layer, such as those arising from electrostatics. Accurately capturing electrostatic energies in the low-dielectric membrane often requires expensive Poisson-Boltzmann calculations that are not scalable for membrane protein structure prediction and design. In this work, we have developed a fast-to-compute implicit energy function that considers the realistic characteristics of different lipid bilayers, making design calculations tractable. This method captures the impact of the lipid head group using a mean-field-based approach and uses a depth-dependent dielectric constant to characterize the membrane environment. This energy function Franklin2023 (F23) is built upon Franklin2019 (F19), which is based on experimentally derived hydrophobicity scales in the membrane bilayer. We evaluated the performance of F23 on five different tests probing (1) protein orientation in the bilayer, (2) stability, and (3) sequence recovery. Relative to F19, F23 has improved the calculation of the tilt angle of membrane proteins for 90% of WALP peptides, 15% of TM-peptides, and 25% of the adsorbed peptides. The performances for stability and design tests were equivalent for F19 and F23. The speed and calibration of the implicit model will help F23 access biophysical phenomena at long time and length scales and accelerate the membrane protein design pipeline. Author summaryMembrane proteins participate in many life processes. They constitute 30% of the human proteome and are targets for over 60% pharmaceuticals. Accurate and accessible computational tools to design membrane proteins will transform the platform to engineer membrane proteins for therapeutic, sensor, and separation processes. While soluble protein design has advanced, membrane protein design remains challenging due to the difficulties in modeling the lipid bilayer. Electrostatics plays an intimate role in the physics of membrane protein structure and function. However, accurately capturing electrostatic energies in the low-dielectric membrane often requires expensive calculations that are not scalable. In this work, we contribute a fast-to-compute electrostatic model that considers different lipid bilayers and their features, making design calculations tractable. We demonstrate that the updated energy function improves the calculation of the tilt angle of membrane proteins, stability, and confidence in designing charged residues.

biophysics↗

bioRxiv2023

Structure-Based Neural Network Protein-Carbohydrate Interaction Predictions at the Residue Level

Carbohydrates dynamically and transiently interact with proteins for cell-cell recognition, cellular differentiation, immune response, and many other cellular processes. Despite the molecular importance of these interactions, there are currently few reliable computational tools to predict potential carbohydrate binding sites on any given protein. Here, we present two deep learning models named CArbohydrate-Protein interaction Site IdentiFier (CAPSIF) that predict carbohydrate binding sites on proteins: (1) a 3D-UNet voxel-based neural network model (CAPSIF:V) and (2) an equivariant graph neural network model (CAPSIF:G). While both models outperform previous surrogate methods used for carbohydrate binding site prediction, CAPSIF:V performs better than CAPSIF:G, achieving test Dice scores of 0.597 and 0.543 and test set Matthews correlation coefficients (MCCs) of 0.599 and 0.538, respectively. We further tested CAPSIF:V on AlphaFold2-predicted protein structures. CAPSIF:V performed equivalently on both experimentally determined structures and AlphaFold2 predicted structures. Finally, we demonstrate how CAPSIF models can be used in conjunction with local glycan-docking protocols, such as GlycanDock, to predict bound protein-carbohydrate structures.

biophysics↗

bioRxiv2022

Hallucinating structure-conditioned antibody libraries for target-specific binders

Antibodies are widely developed and used as therapeutics to treat cancer, infectious disease, and inflammation. During development, initial leads routinely undergo additional engineering to increase their target affinity. Experimental methods for affinity maturation are expensive, laborious, and time-consuming and rarely allow the efficient exploration of the relevant design space. Deep learning (DL) models are transforming the field of protein engineering and design. While several DL-based protein design methods have shown promise, the antibody design problem is distinct, and specialized models for antibody design are desirable. Inspired by hallucination frameworks that leverage accurate structure prediction DL models, we propose the FvHallucinator for designing antibody sequences, especially the CDR loops, conditioned on an antibody structure. Such a strategy generates targeted CDR libraries that retain the conformation of the binder and thereby the mode of binding to the epitope on the antigen. On a benchmark set of 60 antibodies, FvHallucinator generates sequences resembling natural CDRs and recapitulates perplexity of canonical CDR clusters. Furthermore, the FvHallucinator designs amino acid substitutions at the VH-VL interface that are enriched in human antibody repertoires and therapeutic antibodies. We propose a pipeline that screens FvHallucinator designs to obtain a library enriched in binders for an antigen of interest. We apply this pipeline to the CDR H3 of the Trastuzumab-HER2 complex to generate in silico designs improving upon the binding affinity and interfacial properties of the original antibody. Thus, the FvHallucinator pipeline enables generation of inexpensive, diverse, and targeted antibody libraries enriched in binders for antibody affinity maturation.

bioinformatics↗

bioRxiv2022

Towards generalizable prediction of antibody thermostability using machine learning on sequence and structure features

Over the last three decades, the appeal for monoclonal antibodies (mAbs) as therapeutics has been steadily increasing as evident with FDAs recent landmark approval of the 100th mAb. Unlike mAbs that bind to single targets, multispecific biologics (bsAbs) with their single-chain variable fragment (scFv) modules have garnered particular interest owing to the advantage of engaging distinct targets. Despite their exquisite specificity and affinity, the relatively poor thermostability of these scFv modules often hampers their development as a potential therapeutic drug. In recent years, engineering antibody sequences to enhance their stability by mutations has gained considerable momentum. As experimental methods for antibody engineering are time-intensive, laborious, and expensive, computational methods serve as a fast and inexpensive alternative to conventional routes. In this work, we show two machine learning methods - one with pre-trained language models (PTLM) capturing functional effects of sequence variation, and second, a supervised convolutional neural network (CNN) trained with Rosetta energetic features - to better classify thermostable scFv variants from sequence. Both these models are trained over temperature-specific data (TS50 measurements) derived from multiple libraries of scFv sequences. In this work, we show that a sufficiently simple CNN model trained with energetic features generalizes better than a pre-trained language model on out-of-distribution (blind) sequences (average Spearman correlation coefficient of 0.4 as opposed to 0.15). Further, we demonstrate that for an independent mAb with available thermal melting temperatures for 20 experimentally characterized thermostable mutations, these models trained on TS50 data could identify 18 residue positions and 5 identical amino-acid mutations showing remarkable generalizability. Our results suggest that such models can be broadly applicable for improving the biological characteristics of antibodies. Further, transferring such models for alternative physico-chemical properties of scFvs can have potential applications in optimizing large-scale production and delivery of mAbs or bsAbs.

bioinformatics↗

bioRxiv2022

Fast, accurate antibody structure prediction from deep learning on massive set of natural antibodies

Antibodies have the capacity to bind a diverse set of antigens, and they have become critical therapeutics and diagnostic molecules. The binding of antibodies is facilitated by a set of six hypervariable loops that are diversified through genetic recombination and mutation. Even with recent advances, accurate structural prediction of these loops remains a challenge. Here, we present IgFold, a fast deep learning method for antibody structure prediction. IgFold consists of a pre-trained language model trained on 558M natural antibody sequences followed by graph networks that directly predict backbone atom coordinates. IgFold predicts structures of similar or better quality than alternative methods (including AlphaFold) in significantly less time (under one minute). Accurate structure prediction on this timescale makes possible avenues of investigation that were previously infeasible. As a demonstration of IgFolds capabilities, we predicted structures for 105K paired antibody sequences, expanding the observed antibody structural space by over 40 fold.

bioinformatics↗

bioRxiv2022

Virtually the same? Evaluating the effectiveness of remote undergraduate research experiences

In-person undergraduate research experiences (UREs) promote students integration into careers in life science research. In 2020, the COVID-19 pandemic prompted institutions hosting summer URE programs to offer them remotely, raising questions about whether undergraduates who participate in remote research can experience scientific integration. To address this, we investigated indicators of scientific integration for students who participated in remote life science URE programs in summer 2020. We found that these students experienced gains in their scientific self-efficacy and scientific identity similar to results reported for in-person UREs. We also found that these students perceived high benefits and low costs of doing research at the outset of their programs, and their perceptions did not change despite the remote circumstances. Yet, their perceptions differed by program, indicating that programs differentially affected students perceptions of the costs of doing research. Finally, we observed that students with prior research experience made greater gains in self-efficacy and identity, as well as in their perceptions of the alignment of their values with those of the scientific community, in comparison to students with no prior research experience. This finding suggests that additional programming may be needed for undergraduates with no prior experience to benefit from remote research.

scientific communication and education↗

bioRxiv2021

Generative Language Modeling for Antibody Design

Discovery and optimization of monoclonal antibodies for therapeutic applications relies on large sequence libraries, but is hindered by developability issues such as low solubility, low thermal stability, high aggregation, and high immunogenicity. Generative language models, trained on millions of protein sequences, are a powerful tool for on-demand generation of realistic, diverse sequences. We present Immunoglobulin Language Model (IgLM), a deep generative language model for creating synthetic libraries by re-designing variable-length spans of antibody sequences. IgLM formulates antibody design as an autoregressive sequence generation task based on text-infilling in natural language. We trained IgLM on 558M antibody heavy- and light-chain variable sequences, conditioning on each sequences chain type and species-of-origin. We demonstrate that IgLM can generate full-length heavy and light chain sequences from a variety of species, as well as infilled CDR loop libraries with improved developability profiles. IgLM is a powerful tool for antibody design and should be useful in a variety of applications.

bioengineering↗

bioRxiv2021

Induced fit with replica exchange improves protein complex structure prediction

Despite the progress in prediction of protein complexes over the last decade, recent blind protein complex structure prediction challenges revealed limited success rates (less than 20% models with DockQ score > 0.4) on targets that exhibit significant conformational change upon binding. To overcome limitations in capturing backbone motions, we developed a new, aggressive sampling method that incorporates temperature replica exchange Monte Carlo (T-REMC) and conformational sampling techniques within docking protocols in Rosetta. Our method, ReplicaDock 2.0, mimics induced-fit mechanism of protein binding to sample backbone motions across putative interface residues on-the-fly, thereby recapitulating binding-partner induced conformational changes. Furthermore, ReplicaDock 2.0 clocks in at 150-500 CPU hours per target (protein-size dependent); a runtime that is significantly faster than Molecular Dynamics based approaches. For a benchmark set of 88 proteins with moderate to high flexibility (unbound-to-bound iRMSD over 1.2 [A]), ReplicaDock 2.0 successfully docks 61% of moderately flexible complexes and 35% of highly flexible complexes. Additionally, we demonstrate that by biasing backbone sampling particularly towards residues comprising flexible loops or hinge domains, highly flexible targets can be predicted to under 2 [A] accuracy. This indicates that additional gains are possible when mobile protein segments are known. Significance StatementProteins bind each other in a highly specific and regulated manner, and these associated dynamics of binding are intimately linked to their function. Conventional techniques of structure determination such as cryo-EM, X-ray crystallography and NMR are time-consuming and arduous. Using a temperature-replica exchange Monte Carlo approach that mimics the kinetic mechanism of "induced fit" binding, we improved prediction of protein complex structures, particularly for targets that exhibit considerable conformational changes upon binding (Interface root mean square deviation (unbound-bound) > 1.2 [A]. Capturing these binding-induced conformational changes in proteins can aid us in better understanding biological mechanisms and suggest intervention strategies for disease mechanisms.

bioinformatics↗

bioRxiv2021

Growing Glycans in Rosetta: Accurate de novo glycan modeling, density fitting, and rational sequon design

Carbohydrates and glycoproteins modulate key biological functions. Computational approaches inform function to aid in carbohydrate structure prediction, structure determination, and design. However, experimental structure determination of sugar polymers is notoriously difficult as glycans can sample a wide range of low energy conformations, thus limiting the study of glycan-mediated molecular interactions. In this work, we expanded the RosettaCarbohydrate framework, developed and benchmarked effective tools for glycan modeling and design, and extended the Rosetta software suite to better aid in structural analysis and benchmarking tasks through the SimpleMetrics framework. We developed a glycan-modeling algorithm, GlycanTreeModeler, that computationally builds glycans layer-by-layer, using adaptive kernel density estimates (KDE) of common glycan conformations derived from data in the Protein Data Bank (PDB) and from quantum mechanics (QM) calculations. After a rigorous optimization of kinematic and energetic considerations to improve near-native sampling enrichment and decoy discrimination, GlycanTreeModeler was benchmarked on a test set of diverse glycan structures, or "trees". Structures predicted by GlycanTreeModeler agreed with native structures at high accuracy for both de novo modeling and experimental density-guided building. GlycanTreeModeler algorithms and associated tools were employed to design de novo glycan trees into a protein nanoparticle vaccine that are able to direct the immune response by shielding regions of the scaffold from antibody recognition. This work will inform glycoprotein model prediction, aid in both X-ray and electron microscopy density solutions and refinement, and help lead the way towards a new era of computational glycobiology.

molecular biology↗

bioRxiv2021

Improved antibody structure prediction by deep learning of side chain conformations

Antibody engineering is becoming increasingly popular in medicine for the development of diagnostics and immunotherapies. Antibody function relies largely on the recognition and binding of antigenic epitopes via the loops in the complementarity determining regions. Hence, accurate high-resolution modeling of these loops is essential for effective antibody engineering and design. Deep learning methods have previously been shown to effectively predict antibody backbone structures described as a set of inter-residue distances and orientations. However, antigen binding is also dependent on the specific conformations of surface side chains. To address this shortcoming, we created DeepSCAb: a deep learning method that predicts inter-residue geometries as well as side chain dihedrals of the antibody variable fragment. The network requires only sequence as input, rendering it particularly useful for antibodies without any known backbone conformations. Rotamer predictions use an interpretable self-attention layer, which learns to identify structurally conserved anchor positions across several species. We evaluate the performance of our model for discriminating near-native structures from sets of decoys and find that DeepSCAb outperforms similar methods lacking side chain context. When compared to alternative rotamer repacking methods, which require an input backbone structure, DeepSCAb predicts side chain conformations competitively. Our findings suggest that DeepSCAb improves antibody structure prediction with accurate side chain modeling and is adaptable to applications in docking of antibody-antigen complexes and design of new therapeutic antibody sequences.

biophysics↗

bioRxiv2021

Accurately positioning functional residues with robotics-inspired computational protein design

Accurate positioning of functional residues is critical for the design of new protein functions, but has remained difficult because of the prevalence of irregular local geometries in active sites. Here we introduce two computational methods that build local protein geometries from sequence with atomic accuracy: fragment kinematic closure (FKIC) and loophash kinematic closure (LHKIC). FKIC and LHKIC integrate two approaches: robotics-inspired kinematics of protein backbones and insertion of peptide fragments, and show up to 140-fold improvements in native-like predictions over either approach alone. We then integrate these methods into a new design protocol, pull-into-place (PIP), to position functionally important sidechains via design of new structured loop conformations. We validate PIP by remodeling a sizeable active site region in an enzyme and confirming the engineered new conformations of two designs with crystal structures. The described methods can be applied broadly to the design of many new protein geometries and functions.

bioengineering↗

bioRxiv2021

Antibody structure prediction using interpretable deep learning

Therapeutic antibodies make up a rapidly growing segment of the biologics market. However, rational design of antibodies is hindered by reliance on experimental methods for determining antibody structures. In recent years, deep learning methods have driven significant advances in general protein structure prediction. Here, we present DeepAb, a deep learning method for predicting accurate antibody FV structures from sequence. We evaluate DeepAb on two benchmark sets - one balanced for structural diversity and the other composed of clinical-stage therapeutic antibodies - and find that our method consistently outperforms the leading alternatives. Previous deep learning methods have operated as "black boxes" and offered few insights into their predictions. By introducing a directly interpretable attention mechanism, we show that our network attends to physically important residue pairs. For example, in prediction of one CDR H3 residue conformation, the network attends to proximal aromatics and a key hydrogen bonding interaction that constrain the loop conformation. Finally, we present a novel mutant scoring metric derived from network confidence and show that for a particular antibody, all eight of the top-ranked mutations improve binding affinity. These results suggest that this model will be useful for a broad range of antibody prediction and design tasks. SignificanceAccurate structure models are critical for understanding the properties of potential therapeutic antibodies. Conventional methods for protein structure determination require significant investments of time and resources and may fail. Although greatly improved, methods for general protein structure prediction still cannot consistently provide the accuracy necessary to understand or design antibodies. We present a deep learning method for antibody structure prediction and demonstrate improvement over alternatives on diverse, therapeutically relevant benchmarks. In addition to its improved accuracy, our method reveals interpretable outputs about specific amino acids and residue interactions that should facilitate design of novel therapeutic antibodies.

biophysics↗

bioRxiv2021

"How do we do this at a distance?!" A descriptive study of remote undergraduate research programs during COVID-19

The COVID-19 pandemic shut down undergraduate research programs across the U.S. Twenty-three sites offered remote undergraduate research programs in the life sciences during summer 2020. Given the unprecedented offering of remote research experiences, we carried out a study to describe and evaluate these programs. Using structured templates, we documented how programs were designed and implemented, including who participated. Through focus groups and surveys, we identified programmatic strengths and shortcomings as well as recommendations for improvements from the perspectives of participating students. Strengths included the quality of mentorship, opportunities for learning and professional development, and development of a sense of community. Weaknesses included limited cohort building, challenges with insufficient structure, and issues with technology. Although all programs had one or more activities related to diversity, equity, inclusion, and justice, these topics were largely absent from student reports even though programs coincided with a peak in national consciousness about racial inequities and structural racism. Our results provide evidence for designing remote REUs that are experienced favorably by students. Our results also indicate that remote REUs are sufficiently positive to further investigate their affordances and constraints, including the potential to scale up offerings, with minimal concern about disenfranchising students.

scientific communication and education↗

bioRxiv2021

Colicin-mediated transport of DNA through the iron transporter FepA

Colicins are protein antibiotics used by bacteria to eliminate competing Escherichia coli. Colicins frequently exploit outer membrane (OM) nutrient transporters to penetrate through the strictly impermeable bacterial cellular envelope. Here, applying live-cell fluorescence imaging we were able to follow colicin B (ColB) into E. coli and localize it within the periplasm. We further demonstrate that single-stranded DNA coupled to ColB is also transported into the periplasm, emphasizing that the import routes of colicins can be exploited to carry large cargo molecules into bacteria. Moreover, we characterize the molecular mechanism of ColB association with its OM receptor FepA, applying a combination of photo-activated crosslinking, mass spectrometry, and structural modeling. We demonstrate that complex formation is coincident with a large-scale conformational change in the colicin. Finally In vivo crosslinking experiments and supplementary simulations of the translocation process indicate that part of the colicin engages active transport by disguising itself to part of the cellular receptor.

microbiology↗

bioRxiv2020

High-resolution mapping of glycoprotein structure-activity relationships by shotgun scanning glycomutagenesis

As a common protein modification, asparagine-linked (N-linked) glycosylation has the capacity to greatly influence the biological and biophysical properties of proteins. However, the routine use of glycosylation at naive sites as a strategy for engineering proteins with advantageous properties is currently limited by our inability to construct large collections of glycoproteins for interrogating the structural and functional consequences of glycan installation. To address this challenge, we describe a combinatorial strategy termed shotgun scanning glycomutagenesis (SSGM) in which DNA libraries encoding all possible glycosylation site variants of a given protein are constructed and subsequently expressed in glycosylation-competent bacteria, thereby enabling rapid determination of glycosylatable sites in the protein. Moreover, the resulting neoglycoproteins can be readily subjected to available medium- to high-throughput assays, making it possible to systematically investigate the structural and functional consequences of glycan conjugation along a protein backbone. The utility of this approach was demonstrated with three different acceptor proteins, namely bacterial immunity protein Im7, bovine pancreatic ribonuclease A, and a human anti-HER2 single-chain Fv antibody, all of which were found to tolerate N-glycan attachment at a large number of positions and with relatively high efficiency. The stability and activity of many glycovariants was measurably altered by the N-linked glycan in a manner that critically depended on the precise location of the modification. Importantly, we anticipate that our workflow for creating and characterizing large ensembles of neoglycoproteins should provide access to unexplored regions of glycoprotein structural space and to custom-made glycoproteins with desirable properties.

synthetic biology↗

bioRxiv2020

Structural basis for peptide substrate specificities of glycosyltransferase GalNAc-T2

The polypeptide N-acetylgalactosaminyl transferase (GalNAc-T) enzyme family initiates O-linked mucin-type glycosylation. The family constitutes 20 isozymes in humans--an unusually large number--unique to O-glycosylation. GalNAc-Ts exhibit both redundancy and finely tuned specificity for a wide range of peptide substrates. In this work, we deciphered the sequence and structural motifs that determine the peptide substrate preferences for the GalNAc-T2 isoform. Our approach involved sampling and characterization of peptide-enzyme conformations obtained from Rosetta Monte Carlo-minimization-based flexible docking. We computationally scanned 19 amino acid residues at positions -1 and +1 of an eight-residue peptide substrate, which comprised a dataset of 361 (19x19) peptides with previously characterized experimental GalNAc-T2 glycosylation efficiencies. The calculations recapitulated experimental specificity data, successfully discriminating between glycosylatable and non-glycosylatable peptides with a probability of 96.5% (ROC-AUC score), a balanced accuracy of 85.5% and a false positive rate of 7.3%. The glycosylatable peptide substrates viz. peptides with proline, serine, threonine, and alanine at the -1 position of the peptide preferentially exhibited cognate sequon-like conformations. The preference for specific residues at the -1 position of the peptide was regulated by enzyme residues R362, K363, Q364, H365 and W331, which modulate the pocket size and specific enzyme-peptide interactions. For the +1 position of the peptide, enzyme residues K281 and K363 formed gating interactions with aromatics and glutamines at the +1 position of the peptide, leading to modes of peptide-binding sub-optimal for catalysis. Overall, our work revealed enzyme features that lead to the finely tuned specificity observed for a broad range of peptide substrates for the GalNAc-T2 enzyme. We anticipate that the key sequence and structural motifs can be extended to analyze specificities of other isoforms of the GalNAc-T family and can be used to guide design of variants with tailored specificity.

biophysics↗

bioRxiv2020

Diverse scientific benchmarks for implicit membrane energy functions

Energy functions are fundamental to biomolecular modeling. Their success depends on robust physical formalisms, efficient optimization, and high-resolution data for training and validation. Over the past 20 years, progress in each area has advanced soluble protein energy functions. Yet, energy functions for membrane proteins lag behind due to sparse and low-quality data, leading to overfit tools. To overcome this challenge, we assembled a suite of 12 tests on independent datasets varying in size, diversity, and resolution. The tests probe an energy functions ability to capture membrane protein orientation, stability, sequence, and structure. Here, we present the tests and use the franklin2019 energy function to demonstrate them. We then present a vision for transforming these "small" datasets into "big data" that can be used for more sophisticated energy function optimization. The tests are available through the Rosetta Benchmark Server (https://benchmark.graylab.jhu.edu/) and GitHub (https://github.com/rfalford12/Implicit-Membrane-Energy-Function-Benchmark).

biophysics↗