Characterizing disease-associated human proteins without available protein structures or homologues
TL;DR: In this article, the authors used deep learning techniques such as RoseTTAFold and AlphaFold to predict the structure of human proteins even in the absence of structural homologues.
Abstract: Mutations in human proteins lead to diseases. The structure of these proteins can help understand the mechanism of such diseases and develop therapeutics against them. With improved deep learning techniques such as RoseTTAFold and AlphaFold, we can predict the structure of these proteins even in the absence of structural homologues. We modeled and extracted the domains from 553 disease-associated human proteins. We noticed that the model quality was higher and the RMSD lower between AlphaFold and RoseTTAFold models for domains that could be assigned to CATH families as compared to those which could be assigned to Pfam families of unknown structure or could not be assigned to either. We predicted ligand-binding sites, protein-protein interfaces, conserved residues and destabilising effects caused by residue mutations in these predicted structures. We then explored whether the disease-associated mutations were in the proximity of these predicted functional sites or if they destabilized the protein structure based on ddG calculations. We could explain 80% of these disease-associated mutations based on proximity to functional sites or structural destabilization. Usage of models from the two state-of-the-art techniques provide better confidence in our predictions, and we explain 93 additional mutations based on RoseTTAFold models which could not be explained based solely on AlphaFold models.
Citations
More filters
TL;DR: In this paper , a new classification protocol (CATH-Assign) was proposed for structural comparison and classification of AlphaFold2 (AF2) models for protein structure prediction.
Abstract: Deep-learning (DL) methods like DeepMind's AlphaFold2 (AF2) have led to substantial improvements in protein structure prediction. We analyse confident AF2 models from 21 model organisms using a new classification protocol (CATH-Assign) which exploits novel DL methods for structural comparison and classification. Of ~370,000 confident models, 92% can be assigned to 3253 superfamilies in our CATH domain superfamily classification. The remaining cluster into 2367 putative novel superfamilies. Detailed manual analysis on 618 of these, having at least one human relative, reveal extremely remote homologies and further unusual features. Only 25 novel superfamilies could be confirmed. Although most models map to existing superfamilies, AF2 domains expand CATH by 67% and increases the number of unique 'global' folds by 36% and will provide valuable insights on structure function relationships. CATH-Assign will harness the huge expansion in structural data provided by DeepMind to rationalise evolutionary changes driving functional divergence.
24 citations
Journal Article•
TL;DR: This work successfully applied AlphaFold in their end-to-end AI-powered drug discovery engines constituted of a biocomputational platform PandaOmics and a generative chemistry platform Chemistry42, to identify a first-in-class hit molecule of a novel target without an experimental structure starting from target selection towards hit identification in a costand time-efficient manner.
Abstract: The AlphaFold computer program predicted protein structures for the whole human genome, which has been considered as a remarkable breakthrough both in artificial intelligence (AI) application and structural biology. Despite the varying confidence level, these predicted structures still could significantly contribute to structure-based drug design of novel targets, especially the ones with no or limited structural information. In this work, we successfully applied AlphaFold in our end-to-end AI-powered drug discovery engines constituted of a biocomputational platform PandaOmics and a generative chemistry platform Chemistry42, to identify a first-in-class hit molecule of a novel target without an experimental structure starting from target selection towards hit identification in a cost- and time-efficient manner. PandaOmics provided the targets of interest and Chemistry42 generated the molecules based on the AlphaFold predicted structure, and the selected molecules were synthesized and tested in biological assays. Through this approach, we identified a small molecule hit compound for CDK20 with a Kd value of 8.9 +/- 1.6 uM (n = 4) within 30 days from target selection and after only synthesizing 7 compounds. Based on the available data, the second round of AI-powered compound generation was conducted and through which, a more potent hit molecule, ISM042-2 048, was discovered with a Kd value of 210.0 +/- 42.4 nM (n = 2), within 30 days and after synthesizing 6 compounds from the discovery of the first hit ISM042-2-001. To the best of our knowledge, this is the first reported small molecule targeting CDK20 and more importantly, this work is the first demonstration of AlphaFold application in the hit identification process in early drug discovery.
12 citations
TL;DR: Structured information can be used as an input for protein structure prediction as discussed by the authors , and a variety of structure-based machine learning approaches have been proposed to make use of the deluge of rich structural information as input.
Abstract: Recent breakthroughs in protein structure prediction demarcate the start of a new era in structural bioinformatics. Combined with various advances in experimental structure determination and the uninterrupted pace at which new structures are published, this promises an age in which protein structure information is as prevalent and ubiquitous as sequence. Machine learning in protein bioinformatics has been dominated by sequence-based methods, but this is now changing to make use of the deluge of rich structural information as input. Machine learning methods making use of structures are scattered across literature and cover a number of different applications and scopes; while some try to address questions and tasks within a single protein family, others aim to capture characteristics across all available proteins. In this review, we look at the variety of structure-based machine learning approaches, how structures can be used as input, and typical applications of these approaches in protein biology. We also discuss current challenges and opportunities in this all-important and increasingly popular field.
References
More filters
TL;DR: This version of MAFFT has several new features, including options for adding unaligned sequences into an existing alignment, adjustment of direction in nucleotide alignment, constrained alignment and parallel processing, which were implemented after the previous major update.
Abstract: We report a major update of the MAFFT multiple sequence alignment program. This version has several new features, including options for adding unaligned sequences into an existing alignment, adjustment of direction in nucleotide alignment, constrained alignment and parallel processing, which were implemented after the previous major update. This report shows actual examples to explain how these features work, alone and in combination. Some examples incorrectly aligned by MAFFT are also shown to clarify its limitations. We discuss how to avoid misalignments, and our ongoing efforts to overcome such limitations.
27,771 citations
TL;DR: A comparative protein modelling method designed to find the most probable structure for a sequence given its alignment with related structures, which is automated and illustrated by the modelling of trypsin from two other serine proteinases.
12,386 citations
TL;DR: For example, AlphaFold as mentioned in this paper predicts protein structures with an accuracy competitive with experimental structures in the majority of cases using a novel deep learning architecture. But the accuracy is limited by the fact that no homologous structure is available.
Abstract: Proteins are essential to life, and understanding their structure can facilitate a mechanistic understanding of their function. Through an enormous experimental effort1–4, the structures of around 100,000 unique proteins have been determined5, but this represents a small fraction of the billions of known protein sequences6,7. Structural coverage is bottlenecked by the months to years of painstaking effort required to determine a single protein structure. Accurate computational approaches are needed to address this gap and to enable large-scale structural bioinformatics. Predicting the three-dimensional structure that a protein will adopt based solely on its amino acid sequence—the structure prediction component of the ‘protein folding problem’8—has been an important open research problem for more than 50 years9. Despite recent progress10–14, existing methods fall far short of atomic accuracy, especially when no homologous structure is available. Here we provide the first computational method that can regularly predict protein structures with atomic accuracy even in cases in which no similar structure is known. We validated an entirely redesigned version of our neural network-based model, AlphaFold, in the challenging 14th Critical Assessment of protein Structure Prediction (CASP14)15, demonstrating accuracy competitive with experimental structures in a majority of cases and greatly outperforming other methods. Underpinning the latest version of AlphaFold is a novel machine learning approach that incorporates physical and biological knowledge about protein structure, leveraging multi-sequence alignments, into the design of the deep learning algorithm. AlphaFold predicts protein structures with an accuracy competitive with experimental structures in the majority of cases using a novel deep learning architecture.
10,601 citations
TL;DR: An update to the SWISS-MODEL server is presented, which includes the implementation of a new modelling engine, ProMod3, and the introduction a new local model quality estimation method, QMEANDisCo.
Abstract: Homology modelling has matured into an important technique in structural biology, significantly contributing to narrowing the gap between known protein sequences and experimentally determined structures. Fully automated workflows and servers simplify and streamline the homology modelling process, also allowing users without a specific computational expertise to generate reliable protein models and have easy access to modelling results, their visualization and interpretation. Here, we present an update to the SWISS-MODEL server, which pioneered the field of automated modelling 25 years ago and been continuously further developed. Recently, its functionality has been extended to the modelling of homo- and heteromeric complexes. Starting from the amino acid sequences of the interacting proteins, both the stoichiometry and the overall structure of the complex are inferred by homology modelling. Other major improvements include the implementation of a new modelling engine, ProMod3 and the introduction a new local model quality estimation method, QMEANDisCo. SWISS-MODEL is freely available at https://swissmodel.expasy.org.
7,022 citations
TL;DR: Anfinsen as discussed by the authors provided a sketch of the rich history of research that provided the foundation for his work on protein folding and the Thermodynamic Hypothesis, and outlined potential avenues of current and future scientific exploration.
Abstract: Stanford Moore, William Stein, and Anfinsen were awarded the Nobel Prize in Chemistry in 1972 for \"their contribution
to the understanding of the connection between chemical structure and catalytic activity of the active center of the ribonuclease
molecule.\" In his Nobel Lecture, Anfinsen provided a sketch of the rich history of research that provided the foundation
for his work on protein folding and the \"Thermodynamic Hypothesis,\" and outlined potential avenues of current and
future scientific exploration.
6,520 citations