Biology subjects

Ovchinnikov, S.

Publications and source records attributed to Ovchinnikov, S..

54 records · Page 3Linked to original sources

bioRxiv2022

Prediction of multiple conformational states by combining sequence clustering with AlphaFold2

AlphaFold2 (AF2) has revolutionized structural biology by accurately predicting single structures of proteins and protein-protein complexes. However, biological function is rooted in a proteins ability to sample different conformational substates, and disease-causing point mutations are often due to population changes of these substates. This has sparked immense interest in expanding AF2s capability to predict conformational substates. We demonstrate that clustering an input multiple sequence alignment (MSA) by sequence similarity enables AF2 to sample alternate states of known metamorphic proteins, including the circadian rhythm protein KaiB, the transcription factor RfaH, and the spindle checkpoint protein Mad2, and score these states with high confidence. Moreover, we use AF2 to identify a minimal set of two point mutations predicted to switch KaiB between its two states. Finally, we used our clustering method, AF-cluster, to screen for alternate states in protein families without known fold-switching, and identified a putative alternate state for the oxidoreductase DsbE. Similarly to KaiB, DsbE is predicted to switch between a thioredoxin-like fold and a novel fold. This prediction is the subject of future experimental testing. Further development of such bioinformatic methods in tandem with experiments will likely have profound impact on predicting protein energy landscapes, essential for shedding light into biological function.

biochemistry↗

bioRxiv2022

Global statistical models of protein coevolution reveal higher-order sectors beyond those obtained from structure alone

1Recent methods have shown promise in using pairwise sequence coevolution predictions to illuminate physical interactions and functional relationships between pairs of protein residues. As a result, there has been an increased interest in identifying higher-order correlations between sequence positions in an effort to further understand how the multiple sequence alignment (MSA) encodes the conserved biological properties of a protein family. To this end, we propose a robust and generalizable spectral clustering model that can extract interconnected networks of coevolving residues - termed "protein sectors" - using pairwise sequence coevolution predicted by a global statistical model. We assess the statistical and evolutionary origins for protein sectors extracted from the MSA for 120 protein families. We show that protein sectors are extracted from a subset of densely connected components in the sequence coevolution matrix, many of which are not present in the pairwise residue contact graph that is constructed from the protein crystal structure, revealing the existence of networks of paired residues that are not necessarily in direct physical contact but are nonetheless evolutionarily coupled. We found that protein sectors form structurally connected entities in three-dimensional space, despite sector identification being independent of protein crystal structure. Interestingly, protein families with high structural similarity do not share similar protein sectors, suggesting that nuances in the sequence coevolution matrix can differentiate between the evolutionary histories of structurally-related protein families.

bioinformatics↗

bioRxiv2022

State-of-the-Art Estimation of Protein Model Accuracy using AlphaFold

The problem of predicting a proteins 3D structure from its primary amino acid sequence is a longstanding challenge in structural biology. Recently, approaches like AlphaFold have achieved remarkable performance on this task by combining deep learning techniques with coevolutionary data from multiple sequence alignments of related protein sequences. The use of coevolutionary information is critical to these models accuracy, and without it their predictive performance drops considerably. In living cells, however, the 3D structure of a protein is fully determined by its primary sequence and the biophysical laws that cause it to fold into a low-energy configuration. Thus, it should be possible to predict a proteins structure from only its primary sequence by learning a highly-accurate biophysical energy function. We provide evidence that AlphaFold has learned such an energy function, and uses coevolution data to solve the global search problem of finding a low-energy conformation. We demonstrate that AlphaFolds learned potential function can be used to rank the quality of candidate protein structures with state-of-the-art accuracy, without using any coevolution data. Finally, we explore several applications of this potential function, including the prediction of protein structures without MSAs.

biophysics↗

bioRxiv2022

Disentanglement of Entropy and Coevolution using Spectral Regularization

The rise in the number of protein sequences in the post-genomic era has led to a major breakthrough in fitting generative sequence models for contact prediction, protein design, alignment, and homology search. Despite this success, the interpretability of the modeled pairwise parameters continues to be limited due to the entanglement of coevolution, phylogeny, and entropy. For contact prediction, post-correction methods have been developed to remove the contribution of entropy from the predicted contact maps. However, all remaining applications that rely on the raw parameters, lack a direct method to correct for entropy. In this paper, we investigate the origins of the entropy signal and propose a new spectral regularizer to down weight it during model fitting. We find the added regularizer to GREMLIN, a Markov Random Field or Potts model, allows for the inference of a sparse contact map without loss in precision, meanwhile improving interpretability, and resolving overfitting issues important for sequence evaluation and design.

bioinformatics↗

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

End-to-end learning of multiple sequence alignments with differentiable Smith-Waterman

Multiple Sequence Alignments (MSAs) of homologous sequences contain information on structural and functional constraints and their evolutionary histories. Despite their importance for many downstream tasks, such as structure prediction, MSA generation is often treated as a separate pre-processing step, without any guidance from the application it will be used for. Here, we implement a smooth and differentiable version of the Smith-Waterman pairwise alignment algorithm that enables jointly learning an MSA and a downstream machine learning system in an end-to-end fashion. To demonstrate its utility, we introduce SMURF (Smooth Markov Unaligned Random Field), a new method that jointly learns an alignment and the parameters of a Markov Random Field for unsupervised contact prediction. We find that SMURF learns MSAs that mildly improve contact prediction on a diverse set of protein and RNA families. As a proof of concept, we demonstrate that by connecting our differentiable alignment module to AlphaFold and maximizing predicted confidence, we can learn MSAs that improve structure predictions over the initial MSAs. Interestingly, the alignments that improve AlphaFold predictions are self-inconsistent and can be viewed as adversarial. This work highlights the potential of differentiable dynamic programming to improve neural network pipelines that rely on an alignment and the potential dangers of relying on black-box methods for optimizing predictions of protein sequences.

bioinformatics↗

bioRxiv2021

A structural biology community assessment of AlphaFold 2 applications

Most proteins fold into 3D structures that determine how they function and orchestrate the biological processes of the cell. Recent developments in computational methods have led to protein structure predictions that have reached the accuracy of experimentally determined models. While this has been independently verified, the implementation of these methods across structural biology applications remains to be tested. Here, we evaluate the use of AlphaFold 2 (AF2) predictions in the study of characteristic structural elements; the impact of missense variants; function and ligand binding site predictions; modelling of interactions; and modelling of experimental structural data. For 11 proteomes, an average of 25% additional residues can be confidently modelled when compared to homology modelling, identifying structural features rarely seen in the PDB. AF2-based predictions of protein disorder and protein complexes surpass state-of-the-art tools and AF2 models can be used across diverse applications equally well compared to experimentally determined structures, when the confidence metrics are critically considered. In summary, we find that these advances are likely to have a transformative impact in structural biology and broader life science research.

biophysics↗

bioRxiv2021

ColabFold - Making protein folding accessible to all

ColabFold offers accelerated protein structure and complex predictions by combining the fast homology search of MMseqs2 with AlphaFold2 or RoseTTAFold. ColabFolds 40 - 60x faster search and optimized model use allows predicting close to a thousand structures per day on a server with one GPU. Coupled with Google Colaboratory, ColabFold becomes a free and accessible platform for protein folding. ColabFold is open-source software available at github.com/sokrypton/ColabFold. Its novel environmental databases are available at colabfold.mmseqs.com Contactmilot.mirdita@mpibpc.mpg.de, so@fas.harvard.edu, martin.steinegger@snu.ac.kr

bioinformatics↗

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

BacPROTACs mediate targeted protein degradation in bacteria

Hijacking the cellular protein degradation system offers unique opportunities for drug discovery, as exemplified by proteolysis targeting chimeras (PROTACs). Despite their superior properties over classical inhibitors, it has so far not been possible to reprogram the bacterial degradation machinery to interfere with microbial infections. Here, we develop small-molecule degraders, so-called BacPROTACs, that bind to the substrate receptor of the ClpC:ClpP protease, priming neo-substrates for degradation. In addition to their targeting function, BacPROTACs activate ClpC, transforming the resting unfoldase into its functional state. The induced higher-order oligomer was visualized by cryo-EM analysis, providing a structural snapshot of activated ClpC unfolding a protein substrate. Finally, degradation assays performed in mycobacteria demonstrate in vivo activity of BacPROTACs, highlighting the potential of the technology to provide next generation antibiotics.

biochemistry↗

bioRxiv2020

Single Layers of Attention Suffice to Predict Protein Contacts

AO_SCPLOWBSTRACTC_SCPLOWThe established approach to unsupervised protein contact prediction estimates co-evolving positions using undirected graphical models. This approach trains a Potts model on a Multiple Sequence Alignment, then predicts that the edges with highest weight correspond to contacts in the 3D structure. On the other hand, increasingly large Transformers are being pretrained on protein sequence databases but have demonstrated mixed results for downstream tasks, including contact prediction. This has sparked discussion about the role of scale and attention-based models in unsupervised protein representation learning. We argue that attention is a principled model of protein interactions, grounded in real properties of protein family data. We introduce a simplified attention layer, factored attention, and show that it achieves comparable performance to Potts models, while sharing parameters both within and across families. Further, we extract contacts from the attention maps of a pretrained Transformer and show they perform competitively with the other two approaches. This provides evidence that large-scale pretraining can learn meaningful protein features when presented with unlabeled and unaligned data. We contrast factored attention with the Transformer to indicate that the Transformer leverages hierarchical signal in protein family databases not captured by our single-layer models. This raises the exciting possibility for the development of powerful structured models of protein family databases.1

bioinformatics↗

bioRxiv2020

Transformer protein language models are unsupervised structure learners

AO_SCPLOWBSTRACTC_SCPLOWUnsupervised contact prediction is central to uncovering physical, structural, and functional constraints for protein structure determination and design. For decades, the predominant approach has been to infer evolutionary constraints from a set of related sequences. In the past year, protein language models have emerged as a potential alternative, but performance has fallen short of state-of-the-art approaches in bioinformatics. In this paper we demonstrate that Transformer attention maps learn contacts from the unsupervised language modeling objective. We find the highest capacity models that have been trained to date already outperform a state-of-the-art unsupervised contact prediction pipeline, suggesting these pipelines can be replaced with a single forward pass of an end-to-end model.1

synthetic biology↗

bioRxiv2020

The structure-fitness landscape of pairwise relations in generative sequence models

If disentangled properly, patterns distilled from evolutionarily related sequences of a given protein family can inform their traits - such as their structure and function. Recent years have seen an increase in the complexity of generative models towards capturing these patterns; from sitewise to pairwise to deep and variational. In this study we evaluate the degree of structure and fitness patterns learned by a suite of progressively complex models. We introduce pairwise saliency, a novel method for evaluating the degree of captured structural information. We also quantify the fitness information learned by these models by using them to predict the fitness of mutant sequences and then correlate these predictions against their measured fitness values. We observe that models that inform structure do not necessarily inform fitness and vice versa, contrasting recent claims in this field. Our work highlights a dearth of consistency across fitness assays as well as divergently provides a general approach for understanding the pairwise decomposable relations learned by a given generative sequence model.

bioinformatics↗

bioRxiv2020

Design of proteins presenting discontinuous functional sites using deep learning

An 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.

biochemistry↗

bioRxiv2020

Protein sequence design by explicit energy landscape optimization

The protein design problem is to identify an amino acid sequence which folds to a desired structure. Given Anfinsens thermodynamic hypothesis of folding, this can be recast as finding an amino acid sequence for which the lowest energy conformation is that structure. As this calculation involves not only all possible amino acid sequences but also all possible structures, most current approaches focus instead on the more tractable problem of finding the lowest energy amino acid sequence for the desired structure, often checking by protein structure prediction in a second step that the desired structure is indeed the lowest energy conformation for the designed sequence, and discarding the in many cases large fraction of designed sequences for which this is not the case. Here we show that by backpropagating gradients through the trRosetta structure prediction network from the desired structure to the input amino acid sequence, we can directly optimize over all possible amino acid sequences and all possible structures, and in one calculation explicitly design amino acid sequences predicted to fold into the desired structure and not any other. We find that trRosetta calculations, which consider the full conformational landscape, can be more effective than Rosetta single point energy estimations in predicting folding and stability of de novo designed proteins. We compare sequence design by landscape optimization to the standard fixed backbone sequence design methodology in Rosetta, and show that the results of the former, but not the latter, are sensitive to the presence of competing low-lying states. We show further that more funneled energy landscapes can be designed by combining the strengths of the two approaches: the low resolution trRosetta model serves to disfavor alternative states, and the high resolution Rosetta model, to create a deep energy minimum at the design target structure. SignificanceComputational protein design has primarily focused on finding sequences which have very low energy in the target designed structure. However, what is most relevant during folding is not the absolute energy of the folded state, but the energy difference between the folded state and the lowest lying alternative states. We describe a deep learning approach which captures the entire folding landscape, and show that it can enhance current protein design methods.

biophysics↗

bioRxiv2020

De novo protein design by deep network hallucination

There 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.

bioengineering↗

bioRxiv2019

Improved protein structure prediction using predicted inter-residue orientations

The prediction of inter-residue contacts and distances from co-evolutionary data using deep learning has considerably advanced protein structure prediction. Here we build on these advances by developing a deep residual network for predicting inter-residue orientations in addition to distances, and a Rosetta constrained energy minimization protocol for rapidly and accurately generating structure models guided by these restraints. In benchmark tests on CASP13 and CAMEO derived sets, the method outperforms all previously described structure prediction methods. Although trained entirely on native proteins, the network consistently assigns higher probability to de novo designed proteins, identifying the key fold determining residues and providing an independent quantitative measure of the "ideality" of a protein structure. The method promises to be useful for a broad range of protein structure prediction and design problems.

bioinformatics↗

bioRxiv2018

An Empirical Demonstration of Unsupervised Machine Learning in Species Delimitation

One major challenge to delimiting species with genetic data is successfully differentiating species divergences from population structure, with some current methods biased towards overestimating species numbers. Many fields of science are now utilizing machine learning (ML) approaches, and in systematics and evolutionary biology, supervised ML algorithms have recently been incorporated to infer species boundaries. However, these methods require the creation of training data with associated labels. Unsupervised ML, on the other hand, uses the inherent structure in data and hence does not require any user-specified training labels, thus providing a more objective approach to species delimitation. In the context of integrative taxonomy, we demonstrate the utility of three unsupervised ML approaches, specifically random forests, variational autoencoders, and t-distributed stochastic neighbor embedding, for species delimitation utilizing a short-range endemic harvestman taxon (Laniatores, Metanonychus). First, we combine mitochondrial data with examination of male genitalic morphology to identify a priori species hypotheses. Then we use single nucleotide polymorphism data derived from sequence capture of ultraconserved elements (UCEs) to test the efficacy of unsupervised ML algorithms in successfully identifying a priori species, comparing results to commonly used genetic approaches. Finally, we use two validation methods to assess a priori species hypotheses using UCE data. We find that unsupervised ML approaches successfully cluster samples according to species level divergences and not to high levels of population structure, while standard model-based validation methods over-split species, in some instances suggesting that all sampled individuals are distinct species. Moreover, unsupervised ML approaches offer the benefits of better data visualization in two-dimensional space and the ability to accommodate various data types. We argue that ML methods may be better suited for species delimitation relative to currently used model-based validation methods, and that species delimitation in a truly integrative framework provides more robust final species hypotheses relative to separating delimitation into distinct \"discovery\" and \"validation\" phases. Unsupervised ML is a powerful analytical approach that can be incorporated into many aspects of systematic biology, including species delimitation. Based on results of our empirical dataset, we make several taxonomic changes including description of a new species.

evolutionary biology↗