Biology subjects

Ovchinnikov, S.

Publications and source records attributed to Ovchinnikov, S..

At least 37 records · Page 2Linked to original sources

bioRxiv2024

BindCraft: one-shot design of functional protein binders

Protein-protein interactions (PPIs) are at the core of all key biological processes. However, the complexity of the structural features that determine PPIs makes their design challenging. We present BindCraft, an open-source and automated pipeline for de novo protein binder design with experimental success rates of 10-100%. BindCraft leverages the weights of AlphaFold21 to generate binders with nanomolar affinity without the need for high-throughput screening or experimental optimization, even in the absence of known binding sites. We successfully designed binders against a diverse set of challenging targets, including cell-surface receptors, common allergens, de novo designed proteins, and multi-domain nucleases, such as CRISPR-Cas9. We showcase the functional and therapeutic potential of designed binders by reducing IgE binding to birch allergen in patient-derived samples, modulating Cas9 gene editing activity, and reducing the cytotoxicity of a foodborne bacterial enterotoxin. Lastly, we utilize cell surface receptor-specific binders to redirect AAV capsids for targeted gene delivery. This work represents a significant advancement towards a "one design-one binder" approach in computational design, with immense potential in therapeutics, diagnostics, and biotechnology.

bioinformatics↗

bioRxiv2024

The OMG dataset: An Open MetaGenomic corpus for mixed-modality genomic language modeling

Biological language model performance depends heavily on pretraining data quality, diversity, and size. While metagenomic datasets feature enormous biological diversity, their utilization as pretraining data has been limited due to challenges in data accessibility, quality filtering and deduplication. Here, we present the Open MetaGenomic (OMG) corpus, a genomic pretraining dataset totalling 3.1T base pairs and 3.3B protein coding sequences, obtained by combining two largest metagenomic dataset repositories (JGIs IMG and EMBLs MGnify). We first document the composition of the dataset and describe the quality filtering steps taken to remove poor quality data. We make the OMG corpus available as a mixed-modality genomic sequence dataset that represents multi-gene encoding genomic sequences with translated amino acids for protein coding sequences, and nucleic acids for intergenic sequences. We train the first mixed-modality genomic language model (gLM2) that leverages genomic context information to learn robust functional representations, as well as coevolutionary signals in protein-protein interfaces and genomic regulatory syntax. Furthermore, we show that deduplication in embedding space can be used to balance the corpus, demonstrating improved performance on downstream tasks. The OMG dataset is publicly hosted on the Hugging Face Hub at https://huggingface.co/datasets/tattabio/OMG and gLM2 is available at https://huggingface.co/tattabio/gLM2_650M.

systems biology↗

bioRxiv2024

A resource for comparing AF-Cluster and other AlphaFold2 sampling methods

Predicting multiple conformational states of proteins represents a significant open challenge in structural biology. Increasingly many methods have been reported for perturbing and sampling AlphaFold2 (AF2) [1] to achieve multiple conformational states. However, if multiple methods achieve similar results, that does not in itself invalidate any method, nor does it answer why these methods work. Interpreting why deep learning models give the results they do is a critically important endeavor for future model development and appropriate usage. To help the field continue to try to answer these questions, this work addresses misunderstandings and inaccurate conclusions in refs. [2-6]. Deep learning methods development moves quickly, and by no means did we think that the implementation of AF-Cluster in [7] would be the final word on how to sample multiple conformations. However, Porter et al.s primary critique, that AF-Cluster does not use local evolutionary couplings in its MSA clusters, is incorrect. We report here further analysis that underscores our original finding that local evolutionary couplings do indeed play an important role in AF-Cluster predictions, and refute all false claims made against [7].

biophysics↗

bioRxiv2024

Patterns and drivers of diatom diversity and abundance in the global ocean

Diatoms constitute one of the most diverse and ecologically important phytoplankton groups, yet their large-scale diversity patterns and drivers of abundance are unclear due to limited observations. Here, we utilize Tara Oceans molecular and morphological data, spanning pole to pole, to describe marine diatom diversity, abundance, and environmental adaptation and acclimation strategies. The dominance of diatoms among phytoplankton in terms of relative abundance and diversity was confirmed, and the most prevalent genera were Chaetoceros, Thalassiosira, Actinocyclus and Pseudo-nitzschia. We defined 25 distinct diatom communities with varying environmental preferences illustrative of different life strategies. The Arctic Ocean stands out as a diatom hotspot with 6 of the diatom communities being exclusive to it. Light harvesting and photoprotection were among the cellular functions in which natural diatom populations invested the bulk of their transcriptional efforts. This comprehensive study sheds light on marine diatom distributions, offering insights to assess impacts of global change and oceanic anthropogenic impacts.

ecology↗

bioRxiv2024

SaprotHub: Making Protein Modeling Accessible to All Biologists

Training and deploying large-scale protein language models typically requires deep machine learning expertise -- a barrier for researchers outside this field. SaprotHub overcomes this challenge by offering an intuitive platform that facilitates training and prediction as well as storage and sharing of models. We provide the ColabSaprot framework built on Google Colab which potentially powers hundreds of protein training and prediction applications, enabling researchers to collaboratively build and share customized models.

bioinformatics↗

bioRxiv2024

Predicting absolute protein folding stability using generative models

While there has been substantial progress in our ability to predict changes in protein stability due to amino acid substitutions, progress has been slower in methods to predict the absolute stability of a protein. Here we show how a generative model for protein sequence can be leveraged to predict absolute protein stability. We benchmark our predictions across a broad set of proteins and find a mean error of 1.5 kcal/mol and a correlation coefficient of 0.7 for the absolute stability across a range of natural, small-medium sized proteins up to ca. 150 amino acid residues. We analyse current limitations and future directions including how such model may be useful for predicting conformational free energies. Our approach is simple to use and freely available via an online implementation.

biophysics↗

bioRxiv2024

Protein language models learn evolutionary statistics of interacting sequence motifs

Protein language models (pLMs) have emerged as potent tools for predicting and designing protein structure and function, and the degree to which these models fundamentally understand the inherent biophysics of protein structure stands as an open question. Motivated by a discovery that pLM-based structure predictors erroneously predict nonphysical structures for protein isoforms, we investigated the nature of sequence context needed for contact predictions in the pLM ESM-2. We demonstrate by use of a "categorical Jacobian" calculation that ESM-2 stores statistics of coevolving residues, analogously to simpler modelling approaches like Markov Random Fields and Multivariate Gaussian models. We further investigated how ESM-2 "stores" information needed to predict contacts by comparing sequence masking strategies, and found that providing local windows of sequence information allowed ESM-2 to best recover predicted contacts. This suggests that pLMs predict contacts by storing motifs of pairwise contacts. Our investigation highlights the limitations of current pLMs and underscores the importance of understanding the underlying mechanisms of these models. Significance StatementProtein language models (pLMs) have exhibited remarkable capabilities in protein structure prediction and design. However, the extent to which they comprehend the intrinsic biophysics of protein structures remains uncertain. We present a suite of analyses that dissect how the flagship pLM ESM-2 predicts structure. Motivated by a consistent error of protein isoforms predicted as structured fragments, we developed a completely unsupervised method to uniformly evaluate any protein language model that allows for us to compare coevolutionary statistics to older linear models. We further identified t hat E SM-2 a ppears to have a precise context size that is needed to predict inter-residue contacts. Our study highlights the current limitations of pLMs and contributes to a deeper understanding of their underlying mechanisms, paving the way for more reliable protein structure predictions.

bioinformatics↗

bioRxiv2023

AF2BIND: Predicting ligand-binding sites using the pair representation of AlphaFold2

Predicting ligand-binding sites, particularly in the absence of previously resolved homologous structures, presents a significant challenge in structural biology. Here, we leverage the internal pairwise representation of AlphaFold2 (AF2) to train a model, AF2BIND, to accurately predict small-molecule-binding residues given only a target protein. AF2BIND uses 20 "bait" amino acids to optimally extract the binding signal in the absence of a small-molecule ligand. We find that the AF2 pair representation outperforms other neural-network representations for binding-site prediction. Moreover, unique combinations of the 20 bait amino acids are correlated with chemical properties of the ligand.

bioinformatics↗

bioRxiv2023

Differentiable Search of Evolutionary Trees from Leaves

Inferring the most probable evolutionary tree given leaf nodes is an important problem in computational biology that reveals the evolutionary relationships between species. Due to the exponential growth of possible tree topologies, finding the best tree in polynomial time becomes computationally infeasible. In this work, we propose a novel differentiable approach as an alternative to traditional heuristic-based combinatorial tree search methods in phylogeny. The optimization objective of interest in this work is to find the most parsimonious tree (i.e., to minimize the total number of evolutionary changes in the tree). We empirically evaluate our method using randomly generated trees of up to 128 leaves, with each node represented by a 256-length protein sequence. Our method exhibits promising convergence (< 1% error for trees up to 32 leaves, < 8% error up to 128 leaves, given only leaf node information), illustrating its potential in much broader phylogenetic inference problems and possible integration with end-to-end differentiable models. The code to reproduce the experiments in this paper can be found at https://github.ramith.io/diff-evol-tree-search.

bioinformatics↗

bioRxiv2023

ColabDock: inverting AlphaFold structure prediction model for protein-protein docking with experimental restraints

Prediction of protein complex structures and interfaces potentially has wide applications and can benefit the study of biological mechanisms involving protein-protein interactions. However, the surface prediction accuracy of traditional docking methods and AlphaFold-Multimer is limited. Here we present ColabDock, a framework that makes use of ColabDesign, but reimplements it for the purpose of restrained complex conformation prediction. With a generation-prediction architecture and trained ranking model, ColabDock outperforms HADDOCK and ClusPro not only in complex structure predictions with simulated residue and surface restraints, but also in those assisted by NMR chemical shift perturbation as well as covalent labeling. It further assists antibody-antigen interface prediction with emulated interface scan restraints, which could be obtained by experiments such as Deep Mutation Scan. ColabDock provides a general approach to integrate sparse interface restraints of different experimental forms and sources into one optimization framework.

bioinformatics↗

bioRxiv2023

An atlas of protein homo-oligomerization across domains of life

Protein structures are essential to understand cellular processes in molecular detail. While advances in AI revealed the tertiary structure of proteins at scale, their quaternary structure remains mostly unknown. Here, we describe a scalable strategy based on AlphaFold2 to predict homo-oligomeric assemblies across four proteomes spanning the tree of life. We find that 50% of archaeal, 45% of bacterial, and 20% of eukaryotic proteomes form homomers. Our predictions accurately capture protein homo-oligomerization, recapitulate megadalton complexes, and unveil hundreds of novel homo-oligomer types. Analyzing these datasets reveals coiled-coil regions as major enablers of quaternary structure evolution in Eukaryotes. Integrating these structures with omics data shows that a majority of known protein complexes are symmetric. Finally, these datasets provide a structural context for interpreting disease mutations, which we find enriched at interfaces. Our strategy is applicable to any organism and provides a comprehensive view of homo-oligomerization in proteomes, protein networks, and disease. O_FIG O_LINKSMALLFIG WIDTH=200 HEIGHT=193 SRC="FIGDIR/small/544317v1_ufig1.gif" ALT="Figure 1"> View larger version (79K): org.highwire.dtl.DTLVardef@1507a12org.highwire.dtl.DTLVardef@7e522aorg.highwire.dtl.DTLVardef@1445410org.highwire.dtl.DTLVardef@eb09f7_HPS_FORMAT_FIGEXP M_FIG C_FIG

bioinformatics↗

bioRxiv2023

Validation of de novo designed water-soluble and transmembrane proteins by in silico folding and melting

In silico validation of de novo designed proteins with deep learning (DL)-based structure prediction algorithms has become mainstream. However, formal evidence of the relationship between a high-quality predicted model and the chance of experimental success is lacking. We used experimentally characterized de novo designs to show that AlphaFold2 and ESMFold excel at different tasks. ESMFold can efficiently identify designs generated based on high-quality (designable) backbones. However, only AlphaFold2 can predict which sequences have the best chance of experimentally folding among similar designs. We show that ESMFold can generate high-quality structures from just a few predicted contacts and introduce a new approach based on incremental perturbation of the prediction ("in silico melting"), which can reveal differences in the presence of favorable contacts between designs. This study provides a new insight on DL-based structure prediction models explainability and on how they could be leveraged for the design of increasingly complex proteins; in particular membrane proteins which have historically lacked basic in silico validation tools.

bioinformatics↗

bioRxiv2023

Computational design of soluble analogues of integral membrane protein structures

De novo design of complex protein folds using solely computational means remains a significant challenge. Here, we use a robust deep learning pipeline to design complex folds and soluble analogues of integral membrane proteins. Unique membrane topologies, such as those from GPCRs, are not found in the soluble proteome and we demonstrate that their structural features can be recapitulated in solution. Biophysical analyses reveal high thermal stability of the designs and experimental structures show remarkable design accuracy. The soluble analogues were functionalized with native structural motifs, standing as a proof-of-concept for bringing membrane protein functions to the soluble proteome, potentially enabling new approaches in drug discovery. In summary, we designed complex protein topologies and enriched them with functionalities from membrane proteins, with high experimental success rates, leading to a de facto expansion of the functional soluble fold space.

bioinformatics↗

bioRxiv2023

Deep learning of genomic contexts predicts protein co-regulation and function

Deciphering the relationship between a gene and its genomic context is fundamental to understanding and engineering biological systems. Machine learning has shown promise in learning latent relationships underlying the sequence-structure-function paradigm from massive protein sequence datasets. However, to date, limited attempts have been made in extending this continuum to include higher order genomic context information. Evolutionary processes dictate the specificity of genomic contexts in which a gene is found across phylogenetic distances, and these emergent genomic patterns can be leveraged to uncover functional relationships between gene products. Here, we trained a genomic language model (gLM) on millions of metagenomic scaffolds to learn the latent functional and regulatory relationships between genes. gLM learns contextualized protein embeddings that capture the genomic context as well as the protein sequence itself, and encode biologically meaningful and functionally relevant information (e.g. enzymatic function, taxonomy). Our analysis of the attention patterns demonstrates that gLM is learning co-regulated functional modules (i.e. operons). Our findings illustrate that gLMs unsupervised deep learning of the metagenomic corpus is an effective and promising approach to encode functional semantics and regulatory syntax of genes in their genomic contexts and uncover complex relationships between genes in a genomic region.

bioinformatics↗

bioRxiv2023

Cyclic peptide structure prediction and design using AlphaFold

Deep learning networks offer considerable opportunities for accurate structure prediction and design of biomolecules. While cyclic peptides have gained significant traction as a therapeutic modality, developing deep learning methods for designing such peptides has been slow, mostly due to the small number of available structures for molecules in this size range. Here, we report approaches to modify the AlphaFold network for accurate structure prediction and design of cyclic peptides. Our results show this approach can accurately predict the structures of native cyclic peptides from a single sequence, with 36 out of 49 cases predicted with high confidence (pLDDT > 0.85) matching the native structure with root mean squared deviation (RMSD) less than 1.5 [A]. Further extending our approach, we describe computational methods for designing sequences of peptide backbones generated by other backbone sampling methods and for de novo design of new macrocyclic peptides. We extensively sampled the structural diversity of cyclic peptides between 7-13 amino acids, and identified around 10,000 unique design candidates predicted to fold into the designed structures with high confidence. X-ray crystal structures for seven sequences with diverse sizes and structures designed by our approach match very closely with the design models (root mean squared deviation < 1.0 [A]), highlighting the atomic level accuracy in our approach. The computational methods and scaffolds developed here provide the basis for custom-designing peptides for targeted therapeutic applications.

biochemistry↗

bioRxiv2023

Efficient and scalable de novo protein design using a relaxed sequence space

Deep learning techniques are being used to design new proteins by creating target backbone geometries and finding sequences that can fold into those shapes. While methods like ProteinMPNN provide an efficient algorithm for generating sequences for a given protein backbone, there is still room for improving the scope and computational efficiency of backbone generation. Here, we report a backbone hallucination protocol that uses a relaxed sequence representation. Our method enables protein backbone generation using a gradient descent driven hallucination approach and offers orders-of-magnitude efficiency enhancements over previous hallucination approaches. We designed and experimentally produced over 50 proteins, most of which expressed well in E. Coli, were soluble and adopted the desired oligomeric state along with the correct composition of secondary structure as measured by CD. Exemplarily, we determined 3D electron density maps using single-particle cryo EM analysis for three single-chain de-novo proteins comprising 600 AA which closely matched with the designed shape. These have no structural analogues in the protein data bank (PDB), representing potentially novel folds or arrangement of domains. Our approach broadens the scope of de novo protein design and contributes to accessibility to a wider community.

synthetic biology↗

bioRxiv2022

Language models generalize beyond natural proteins

Learning the design patterns of proteins from sequences across evolution may have promise toward generative protein design. However it is unknown whether language models, trained on sequences of natural proteins, will be capable of more than memorization of existing protein families. Here we show that language models generalize beyond natural proteins to generate de novo proteins. We focus on two protein design tasks: fixed backbone design where the structure is specified, and unconstrained generation where the structure is sampled from the model. Remarkably although the models are trained only on sequences, we find that they are capable of designing structure. A total of 228 generated proteins are evaluated experimentally with high overall success rates (152/228 or 67%) in producing a soluble and monomeric species by size exclusion chromatography. Out of 152 experimentally successful designs, 35 have no significant sequence match to known natural proteins. Of the remaining 117, sequence identity to the nearest sequence match is at median 27%, below 20% for 6 designs, and as low as 18% for 3 designs. For fixed backbone design, the language model generates successful designs for each of eight experimentally evaluated artificially created fixed backbone targets. For unconstrained generation, sampled proteins cover diverse topologies and secondary structure compositions, and have high experimental success rate (71/129 or 55%). The designs reflect deep patterns linking sequence and structure, including motifs that occur in related natural structures, and motifs that are not observed in similar structural contexts in known protein families. The results show that language models, though only trained on sequences, learn a deep grammar that enables the design of protein structure, extending beyond natural proteins.

synthetic biology↗

bioRxiv2022

Mega-scale experimental analysis of protein folding stability in biology and protein design

Advances in DNA sequencing and machine learning are illuminating protein sequences and structures on an enormous scale. However, the energetics driving folding are invisible in these structures and remain largely unknown. The hidden thermodynamics of folding can drive disease, shape protein evolution, and guide protein engineering, and new approaches are needed to reveal these thermodynamics for every sequence and structure. We present cDNA display proteolysis, a new method for measuring thermodynamic folding stability for up to 900,000 protein domains in a one-week experiment. From 1.8 million measurements in total, we curated a set of ~850,000 high-quality folding stabilities covering all single amino acid variants and selected double mutants of 354 natural and 188 de novo designed protein domains 40-72 amino acids in length. Using this immense dataset, we quantified (1) environmental factors influencing amino acid fitness, (2) thermodynamic couplings (including unexpected interactions) between protein sites, and (3) the global divergence between evolutionary amino acid usage and protein folding stability. We also examined how our approach could identify stability determinants in designed proteins and evaluate design methods. The cDNA display proteolysis method is fast, accurate, and uniquely scalable, and promises to reveal the quantitative rules for how amino acid sequences encode folding stability. One-Sentence SummaryMassively parallel measurement of protein folding stability by cDNA display proteolysis

biophysics↗