scholarly journals Design of proteins presenting discontinuous functional sites using deep learning

2020 ◽  
Author(s):  
Doug Tischer ◽  
Sidney Lisanza ◽  
Jue Wang ◽  
Runze Dong ◽  
Ivan Anishchenko ◽  
...  
Keyword(s):  
Loss Function ◽  
Protein Design ◽  
De Novo ◽  
Protein Structures ◽  
Functional Site ◽  
Structural Motif ◽  
Functional Sites ◽  
Binding Interface ◽  
Wide Range ◽  
Sampling Problem

AbstractAn outstanding challenge in protein design is the design of binders against therapeutically relevant target proteins via scaffolding the discontinuous binding interfaces present in their often large and complex binding partners. There is currently no method for sampling through the almost unlimited number of possible protein structures for those capable of scaffolding a specified discontinuous functional site; instead, current approaches make the sampling problem tractable by restricting search to structures composed of pre-defined secondary structural elements. Such restriction of search has the disadvantage that considerable trial and error can be required to identify architectures capable of scaffolding an arbitrary discontinuous functional site, and only a tiny fraction of possible architectures can be explored. Here we build on recent advances in de novo protein design by deep network hallucination to develop a solution to this problem which eliminates the need to pre-specify the structure of the scaffolding in any way. We use the trRosetta residual neural network, which maps input sequences to predicted inter-residue distances and orientations, to compute a loss function which simultaneously rewards recapitulation of a desired structural motif and the ideality of the surrounding scaffold, and generate diverse structures harboring the desired binding interface by optimizing this loss function by gradient descent. We illustrate the power and versatility of the method by scaffolding binding sites from proteins involved in key signaling pathways with a wide range of secondary structure compositions and geometries. The method should be broadly useful for designing small stable proteins containing complex functional sites.

scholarly journals Deep learning methods for designing proteins scaffolding functional sites

2021 ◽  
Author(s):  
Jue Wang ◽  
Sidney Lisanza ◽  
David Juergens ◽  
Doug Tischer ◽  
Ivan Anishchenko ◽  
...  
Keyword(s):  
Structure Prediction ◽  
Neutralizing Antibodies ◽  
De Novo ◽  
Specific Interaction ◽  
Protein Structures ◽  
Functional Site ◽  
Viral Inhibition ◽  
Structure Information ◽  
Functional Sites ◽  
Interaction Terms

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.

scholarly journals Extreme stability in de novo-designed repeat arrays is determined by unusually stable short-range interactions

2018 ◽  
Vol 115 (29) ◽  
pp. 7539-7544 ◽  
Author(s):  
Kathryn Geiger-Schuller ◽  
Kevin Sforza ◽  
Max Yuhas ◽  
Fabio Parmeggiani ◽  
David Baker ◽  
...  
Keyword(s):  
Protein Design ◽  
Nearest Neighbor ◽  
De Novo ◽  
Protein Structures ◽  
Free Energies ◽  
Intrinsic Stability ◽  
Repeat Proteins ◽  
Naturally Occurring ◽  
Wide Range ◽  
The Individual

Designed helical repeats (DHRs) are modular helix–loop–helix–loop protein structures that are tandemly repeated to form a superhelical array. Structures combining tandem DHRs demonstrate a wide range of molecular geometries, many of which are not observed in nature. Understanding cooperativity of DHR proteins provides insight into the molecular origins of Rosetta-based protein design hyperstability and facilitates comparison of energy distributions in artificial and naturally occurring protein folds. Here, we use a nearest-neighbor Ising model to quantify the intrinsic and interfacial free energies of four different DHRs. We measure the folding free energies of constructs with varying numbers of internal and terminal capping repeats for four different DHR folds, using guanidine-HCl and glycerol as destabilizing and solubilizing cosolvents. One-dimensional Ising analysis of these series reveals that, although interrepeat coupling energies are within the range seen for naturally occurring repeat proteins, the individual repeats of DHR proteins are intrinsically stable. This favorable intrinsic stability, which has not been observed for naturally occurring repeat proteins, adds to stabilizing interfaces, resulting in extraordinarily high stability. Stable repeats also impart a downhill shape to the energy landscape for DHR folding. These intrinsic stability differences suggest that part of the success of Rosetta-based design results from capturing favorable local interactions.

scholarly journals A bottom-up approach for the de novo design of functional proteins

2020 ◽  
Author(s):  
Che Yang ◽  
Fabian Sesterhenn ◽  
Jaume Bonet ◽  
Eva van Aalen ◽  
Leo Scheller ◽  
...  
Keyword(s):  
Protein Design ◽  
Mammalian Cells ◽  
De Novo ◽  
Protein Structures ◽  
Functional Protein ◽  
Regular Secondary Structure ◽  
Bottom Up ◽  
Binding Motifs ◽  
Wide Range ◽  
Novel Protein

AbstractDe novo protein design has enabled the creation of novel protein structures. To design novel functional proteins, state-of-the-art approaches use natural proteins or first design protein scaffolds that subsequently serve as templates for the transplantation of functional motifs. In these approaches, the templates are function-agnostic and motifs have been limited to those with regular secondary structure. Here, we present a bottom-up approach to build de novo proteins tailored to structurally complex functional motifs. We applied a bottom-up strategy to design scaffolds for four different binding motifs, including one bi-functionalized protein with two motifs. The de novo proteins were functional as biosensors to quantify epitope-specific antibody responses and as orthogonal ligands to activate a signaling pathway in engineered mammalian cells. Altogether, we present a versatile strategy for the bottom-up design of functional proteins, applicable to a wide range of functional protein design challenges.

scholarly journals De novo protein design by deep network hallucination

2020 ◽  
Author(s):  
Ivan Anishchenko ◽  
Tamuka M. Chidyausiku ◽  
Sergey Ovchinnikov ◽  
Samuel J. Pellock ◽  
David Baker
Keyword(s):  
Amino Acid ◽  
Protein Design ◽  
Structure Prediction ◽  
De Novo ◽  
Protein Structures ◽  
Monte Carlo Sampling ◽  
Amino Acid Sequences ◽  
Wide Range ◽  
Physically Based ◽  
Folded Proteins

AbstractThere has been considerable recent progress in protein structure prediction using deep neural networks to infer distance constraints from amino acid residue co-evolution1–3. We investigated whether the information captured by such networks is sufficiently rich to generate new folded proteins with sequences unrelated to those of the naturally occuring proteins used in training the models. We generated random amino acid sequences, and input them into the trRosetta structure prediction network to predict starting distance maps, which as expected are quite featureless. We then carried out Monte Carlo sampling in amino acid sequence space, optimizing the contrast (KL-divergence) between the distance distributions predicted by the network and the background distribution. Optimization from different random starting points resulted in a wide range of proteins with diverse sequences and all alpha, all beta sheet, and mixed alpha-beta structures. We obtained synthetic genes encoding 129 of these network hallucinated sequences, expressed and purified the proteins in E coli, and found that 27 folded to monomeric stable structures with circular dichroism spectra consistent with the hallucinated structures. Thus deep networks trained to predict native protein structures from their sequences can be inverted to design new proteins, and such networks and methods should contribute, alongside traditional physically based models, to the de novo design of proteins with new functions.

scholarly journals The register shift rules for βαβ-motifs for de novo protein design

PLoS ONE ◽  
2021 ◽  
Vol 16 (8) ◽  
pp. e0256895
Author(s):  
Hiroto Murata ◽  
Hayao Imakawa ◽  
Nobuyasu Koga ◽  
George Chikenji
Keyword(s):  
Protein Design ◽  
De Novo ◽  
Protein Structures ◽  
Sampling Bias ◽  
Conformational Sampling ◽  
Design Rules ◽  
Loop Region ◽  
Wide Range ◽  
Physical Interactions ◽  
Register Shift

A wide range of de novo design of αβ-proteins has been achieved based on the design rules, which describe secondary structure lengths and loop torsion patterns favorable for design target topologies. This paper proposes design rules for register shifts in βαβ-motifs, which have not been reported previously, but are necessary for determining a target structure of de novo design of αβ-proteins. By analyzing naturally occurring protein structures in a database, we found preferences for register shifts in βαβ-motifs, and derived the following empirical rules: (1) register shifts must not be negative regardless of torsion types for a constituent loop in βαβ-motifs; (2) preferred register shifts strongly depend on the loop torsion types. To explain these empirical rules by physical interactions, we conducted physics-based simulations for systems mimicking a βαβ-motif that contains the most frequently observed loop type in the database. We performed an exhaustive conformational sampling of the loop region, imposing the exclusion volume and hydrogen bond satisfaction condition. The distributions of register shifts obtained from the simulations agreed well with those of the database analysis, indicating that the empirical rules are a consequence of physical interactions, rather than an evolutionary sampling bias. Our proposed design rules will serve as a guide to making appropriate target structures for the de novo design of αβ-proteins.

scholarly journals Protein designer David Baker: I like doing things that seem like magic

2020 ◽  
Vol 7 (8) ◽  
pp. 1410-1412
Author(s):  
Weijie Zhao ◽  
Chu Wang
Keyword(s):  
Protein Design ◽  
De Novo ◽  
Protein Structures ◽  
Computational Prediction ◽  
Biological Functions ◽  
Personal Experiences ◽  
De Novo Protein Design ◽  
And Function ◽  
The University ◽  
Opening Up

Abstract Search ‘de novo protein design’ on Google and you will find the name David Baker in all results of the first page. Professor David Baker at the University of Washington and other scientists are opening up a new world of fantastic proteins. Protein is the direct executor of most biological functions and its structure and function are fully determined by its primary sequence. Baker's group developed the Rosetta software suite that enabled the computational prediction and design of protein structures. Being able to design proteins from scratch means being able to design executors for diverse purposes and benefit society in multiple ways. Recently, NSR interviewed Prof. Baker on this fast-developing field and his personal experiences.

scholarly journals De novo protein design: how do we expand into the universe of possible protein structures?

2015 ◽  
Vol 33 ◽  
pp. 16-26 ◽  
Author(s):  
Derek N Woolfson ◽  
Gail J Bartlett ◽  
Antony J Burton ◽  
Jack W Heal ◽  
Ai Niitsu ◽  
...  
Keyword(s):  
Protein Design ◽  
De Novo ◽  
Protein Structures ◽  
De Novo Protein Design ◽  
The Universe

scholarly journals Computational protein design with backbone plasticity

2016 ◽  
Vol 44 (5) ◽  
pp. 1523-1529 ◽  
Author(s):  
James T. MacDonald ◽  
Paul S. Freemont
Keyword(s):  
Protein Design ◽  
De Novo ◽  
Protein Structures ◽  
Search Space ◽  
Computational Protein Design ◽  
Artificial Enzymes ◽  
Backbone Flexibility ◽  
Artificial Proteins ◽  
Naturally Occurring ◽  
Backbone Structure

The computational algorithms used in the design of artificial proteins have become increasingly sophisticated in recent years, producing a series of remarkable successes. The most dramatic of these is the de novo design of artificial enzymes. The majority of these designs have reused naturally occurring protein structures as ‘scaffolds’ onto which novel functionality can be grafted without having to redesign the backbone structure. The incorporation of backbone flexibility into protein design is a much more computationally challenging problem due to the greatly increased search space, but promises to remove the limitations of reusing natural protein scaffolds. In this review, we outline the principles of computational protein design methods and discuss recent efforts to consider backbone plasticity in the design process.

scholarly journals Multi-Scale Structural Analysis of Proteins by Deep Semantic Segmentation

2018 ◽  
Author(s):  
Raphael R. Eguchi ◽  
Po-Ssu Huang
Keyword(s):  
Image Classification ◽  
Protein Design ◽  
Large Scale ◽  
De Novo ◽  
Protein Structures ◽  
Semantic Segmentation ◽  
Amino Acid Sequences ◽  
Structural Quality ◽  
Small Subset ◽  
Structural Prediction

AbstractRecent advancements in computational methods have facilitated large-scale sampling of protein structures, leading to breakthroughs in protein structural prediction and enabling de novo protein design. Establishing methods to identify candidate structures that can lead to native folds or designable structures remains a challenge, since few existing metrics capture high-level structural features such as architectures, folds, and conformity to conserved structural motifs. Convolutional Neural Networks (CNNs) have been successfully used in semantic segmentation — a subfield of image classification in which a class label is predicted for every pixel. Here, we apply semantic segmentation to protein structures as a novel strategy for fold identification and structural quality assessment. We represent protein structures as 2D α-carbon distance matrices (“contact maps”), and train a CNN that assigns each residue in a multi-domain protein to one of 38 architecture classes designated by the CATH database. Our model performs exceptionally well, achieving a per-residue accuracy of 90.8% on the test set (95.0% average accuracy over all classes; 87.8% average within-structure accuracy). The unique aspect of our classifier is that it encodes sequence agnostic residue environments from the PDB and can assess structural quality as quantitative probabilities. We demonstrate that individual class probabilities can be used as a metric that indicates the degree to which a randomly generated structure assumes a specific fold, as well as a metric that highlights non-conformative regions of a protein belonging to a known class. These capabilities yield a powerful tool for guiding structural sampling for both structural prediction and design.SignificanceRecent computational advances have allowed researchers to predict the structure of many proteins from their amino acid sequences, as well as designing new sequences that fold into predefined structures. However, these tasks are often challenging because they require selection of a small subset of promising structural models from a large pool of stochastically generated ones. Here, we describe a novel approach to protein model selection that uses 2D image classification techniques to evaluate 3D protein models. Our method can be used to select structures based on the fold that they adopt, and can also be used to identify regions of low structural quality. These capabilities yield a powerful tool for both protein design and structure prediction.

scholarly journals A community proposal to integrate structural bioinformatics activities in ELIXIR (3D-Bioinfo Community)

F1000Research ◽  
2020 ◽  
Vol 9 ◽  
pp. 278
Author(s):  
Christine Orengo ◽  
Sameer Velankar ◽  
Shoshana Wodak ◽  
Vincent Zoete ◽  
Alexandre M.J.J. Bonvin ◽  
...  
Keyword(s):  
Structural Biology ◽  
Protein Design ◽  
Sequence Data ◽  
Protein Structures ◽  
Structural Bioinformatics ◽  
Data Sets ◽  
Educational Training ◽  
Scientific Methods ◽  
Functional Sites ◽  
Common Interests

Structural bioinformatics provides the scientific methods and tools to analyse, archive, validate, and present the biomolecular structure data generated by the structural biology community. It also provides an important link with the genomics community, as structural bioinformaticians also use the extensive sequence data to predict protein structures and their functional sites. A very broad and active community of structural bioinformaticians exists across Europe, and 3D-Bioinfo will establish formal platforms to address their needs and better integrate their activities and initiatives. Our mission will be to strengthen the ties with the structural biology research communities in Europe covering life sciences, as well as chemistry and physics and to bridge the gap between these researchers in order to fully realize the potential of structural bioinformatics. Our Community will also undertake dedicated educational, training and outreach efforts to facilitate this, bringing new insights and thus facilitating the development of much needed innovative applications e.g. for human health, drug and protein design. Our combined efforts will be of critical importance to keep the European research efforts competitive in this respect. Here we highlight the major European contributions to the field of structural bioinformatics, the most pressing challenges remaining and how Europe-wide interactions, enabled by ELIXIR and its platforms, will help in addressing these challenges and in coordinating structural bioinformatics resources across Europe. In particular, we present recent activities and future plans to consolidate an ELIXIR 3D-Bioinfo Community in structural bioinformatics and propose means to develop better links across the community. These include building new consortia, organising workshops to establish data standards and seeking community agreement on benchmark data sets and strategies. We also highlight existing and planned collaborations with other ELIXIR Communities and other European infrastructures, such as the structural biology community supported by Instruct-ERIC, with whom we have synergies and overlapping common interests.

Sign in / Sign up

Export Citation Format

Share Document