Explore Research

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.

The introduction of AlphaFold 21 has spurred a revolution in modelling the structure of proteins and their interactions, enabling a huge range of applications in protein modelling and design2-6. Here we describe our AlphaFold 3 model with a substantially updated diffusion-based architecture that is capable of predicting the joint structure of complexes including proteins, nucleic acids, small molecules, ions and modified residues. The new AlphaFold model demonstrates substantially improved accuracy over many previous specialized tools: far greater accuracy for protein-ligand interactions compared with state-of-the-art docking tools, much higher accuracy for protein-nucleic acid interactions compared with nucleic-acid-specific predictors and substantially higher antibody-antigen prediction accuracy compared with AlphaFold-Multimer v.2.37,8. Together, these results show that high-accuracy modelling across biomolecular space is possible within a single unified deep-learning framework.

Protein structure prediction is important for understanding their function and behavior. This review study presents a comprehensive review of the computational models used in predicting protein structure. It covers the progression from established protein modeling to state-of-the-art artificial intelligence (AI) frameworks. The paper will start with a brief introduction to protein structures, protein modeling, and AI. The section on established protein modeling will discuss homology modeling, ab initio modeling, and threading. The next section is deep learning-based models. It introduces some state-of-the-art AI models, such as AlphaFold (AlphaFold, AlphaFold2, AlphaFold3), RoseTTAFold, ProteinBERT, etc. This section also discusses how AI techniques have been integrated into established frameworks like Swiss-Model, Rosetta, and I-TASSER. The model performance is compared using the rankings of CASP14 (Critical Assessment of Structure Prediction) and CASP15. CASP16 is ongoing, and its results are not included in this review. Continuous Automated Model EvaluatiOn (CAMEO) complements the biennial CASP experiment. Template modeling score (TM-score), global distance test total score (GDT_TS), and Local Distance Difference Test (lDDT) score are discussed too. This paper then acknowledges the ongoing difficulties in predicting protein structure and emphasizes the necessity of additional searches like dynamic protein behavior, conformational changes, and protein-protein interactions. In the application section, this paper introduces some applications in various fields like drug design, industry, education, and novel protein development. In summary, this paper provides a comprehensive overview of the latest advancements in established protein modeling and deep learning-based models for protein structure predictions. It emphasizes the significant advancements achieved by AI and identifies potential areas for further investigation.

The AlphaFold Protein Structure Database (AlphaFold DB, https://alphafold.ebi.ac.uk) is an openly accessible, extensive database of high-accuracy protein-structure predictions. Powered by AlphaFold v2.0 of DeepMind, it has enabled an unprecedented expansion of the structural coverage of the known protein-sequence space. AlphaFold DB provides programmatic access to and interactive visualization of predicted atomic coordinates, per-residue and pairwise model-confidence estimates and predicted aligned errors. The initial release of AlphaFold DB contains over 360,000 predicted structures across 21 model-organism proteomes, which will soon be expanded to cover most of the (over 100 million) representative sequences from the UniRef90 data set.

Protein structure prediction can be used to determine the three-dimensional shape of a protein from its amino acid sequence1. This problem is of fundamental importance as the structure of a protein largely determines its function2; however, protein structures can be difficult to determine experimentally. Considerable progress has recently been made by leveraging genetic information. It is possible to infer which amino acid residues are in contact by analysing covariation in homologous sequences, which aids in the prediction of protein structures3. Here we show that we can train a neural network to make accurate predictions of the distances between pairs of residues, which convey more information about the structure than contact predictions. Using this information, we construct a potential of mean force4 that can accurately describe the shape of a protein. We find that the resulting potential can be optimized by a simple gradient descent algorithm to generate structures without complex sampling procedures. The resulting system, named AlphaFold, achieves high accuracy, even for sequences with fewer homologous sequences. In the recent Critical Assessment of Protein Structure Prediction5 (CASP13)-a blind assessment of the state of the field-AlphaFold created high-accuracy structures (with template modelling (TM) scores6 of 0.7 or higher) for 24 out of 43 free modelling domains, whereas the next best method, which used sampling and contact information, achieved such accuracy for only 14 out of 43 domains. AlphaFold represents a considerable advance in protein-structure prediction. We expect this increased accuracy to enable insights into the function and malfunction of proteins, especially in cases for which no structures for homologous proteins have been experimentally determined7.

Protein structures can provide invaluable information, both for reasoning about biological processes and for enabling interventions such as structure-based drug development or targeted mutagenesis. After decades of effort, 17% of the total residues in human protein sequences are covered by an experimentally determined structure1. Here we markedly expand the structural coverage of the proteome by applying the state-of-the-art machine learning method, AlphaFold2, at a scale that covers almost the entire human proteome (98.5% of human proteins). The resulting dataset covers 58% of residues with a confident prediction, of which a subset (36% of all residues) have very high confidence. We introduce several metrics developed by building on the AlphaFold model and use them to interpret the dataset, identifying strong multi-domain predictions as well as regions that are likely to be disordered. Finally, we provide some case studies to illustrate how high-quality predictions could be used to generate biological hypotheses. We are making our predictions freely available to the community and anticipate that routine large-scale and high-accuracy structure prediction will become an important tool that will allow new questions to be addressed from a structural perspective.

Models of protein structures enable molecular understanding of biological processes. Current protein structure prediction tools lie at the interface of biology, chemistry and computer science. Millions of protein structure models have been generated in a very short space of time through a revolution in protein structure prediction driven by deep learning, led by AlphaFold. This has provided a wealth of new structural information. Interpreting these predictions is critical to determining where and when this information is useful. But proteins are not static nor do they act alone, and structures of proteins interacting with other proteins and other biomolecules are critical to a complete understanding of their biological function at the molecular level. This review focuses on the application of state-of-the-art protein structure prediction to these advanced applications. We also suggest a set of guidelines for reporting AlphaFold predictions.

The AlphaFold Database Protein Structure Database (AlphaFold DB, https://alphafold.ebi.ac.uk) has significantly impacted structural biology by amassing over 214 million predicted protein structures, expanding from the initial 300k structures released in 2021. Enabled by the groundbreaking AlphaFold2 artificial intelligence (AI) system, the predictions archived in AlphaFold DB have been integrated into primary data resources such as PDB, UniProt, Ensembl, InterPro and MobiDB. Our manuscript details subsequent enhancements in data archiving, covering successive releases encompassing model organisms, global health proteomes, Swiss-Prot integration, and a host of curated protein datasets. We detail the data access mechanisms of AlphaFold DB, from direct file access via FTP to advanced queries using Google Cloud Public Datasets and the programmatic access endpoints of the database. We also discuss the improvements and services added since its initial release, including enhancements to the Predicted Aligned Error viewer, customisation options for the 3D viewer, and improvements in the search engine of AlphaFold DB.

Proteins are essential to life, and understanding their structure can facilitate a mechanistic understanding of their function. Through an enormous experimental effort<SUP>1-4</SUP>, the structures of around 100,000 unique proteins have been determined<SUP>5</SUP>, but this represents a small fraction of the billions of known protein sequences<SUP>6,7</SUP>. 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'<SUP>8</SUP>—has been an important open research problem for more than 50 years<SUP>9</SUP>. Despite recent progress<SUP>10-14</SUP>, 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)<SUP>15</SUP>, 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.

This python script allows one to find contacts between residues in multimeric structure files produced as output from Alphafold2 via the Colabfold pipeline https://github.com/sokrypton/ColabFold/tree/main/colabfold. It integrates both physical proximity and Alphafold confidence metrics such as the predicted Alignment Error(pAE) and the predicted Local Distance Difference Test (pLDDT) to determine whether a pair of residues is a valid contact. It's external dependencies are numpy and pandas. Running this script will produce one or more folders each containing 3 comma seperated value (CSV) files that you can then open with a standard text editor or any spreadhseet program. The 3 files are: summary.csv, interfaces.csv, and contacts.csv. usage: colabfold_analysis.py [-h] [--distance DISTANCE] [--pae PAE] [--pae-mode {min,avg}] [--plddt PLDDT] [--combine-all] [input [input ...]] positional arguments: input One or more folders with PDB files and pAE JSON files output by Colabfold. Note that '.done.txt' marker files produced by Colabfold are used to find the names of complexes to analyze. optional arguments: -h, --help show this help message and exit --distance DISTANCE Maximum distance in Angstroms that any two atoms in two residues in different chains can have for them be considered in contact for the analysis. Default is 8 Angstroms. --pae PAE Maximum predicted Angstrom Error (pAE) value in Angstroms allowed for a contact(pair of residues) to be considered in the analysis. Valid values range from 0 (best) to 30 (worst). Default is 15. --pae-mode {min,avg} How to combine the dual PAE values (x, y) and (y, x) into a single PAE value for a residue pair (x, y). Default is 'min'. --plddt PLDDT Minimum pLDDT values required by both residues in a contact in order for that contact to be included in the analysis. Values range from 0 (worst) to 100 (best). Default is 50. --aas AAS A string representing what amino acids contacts to look/filter for. Allows you to limit what contacts to include in the analysis. By default is blank meaning all amino acids. A value of K would be for any lysine lysine pairs. KR would be RR, KR, RK, or RR pairs, etc --name-filter NAME_FILTER An optional string that allows one to only analyze complexes that contain that string in their name --combine-all Combine the analysis from multiple folders specified by the input argument --ignore-pae Ignore PAE values and just analyze the PDB files. Overides any other PAE settings. EXAMPLES: python3 colabfold_analysis.py my_exciting_colabfold_output_folder python3 colabfold_analysis.py my_exciting_colabfold_output_folder --pae 12 --plddt 50 --pae-mode avg python3 colabfold_analysis.py folder1 folder2 folder3 --pae 12 --plddt 50 --pae-mode avg --combine-all python3 colabfold_analysis.py folder1 --aas DEHKR python3 colabfold_analysis.py folder1 --ignore-pae --name-filter MCM python3 colabfold_analysis.py folder_? --distance 10 --plddt 60 --pae-mode min --combine-all summary.csv Summarizes all the findings per complex across all models that were run for it. Each row is a summary for one complex. complex_name avg_n_models max_n_models num_contacts_with_max_n_models num_unique_contacts best_model_num best_pdockq best_plddt_avg best_pae_avg name of the complex avg number of models per contact max number of models any contact was seen in number of unique contacts that were seen max model number of times number of unique contacts across all models anlayzed model number of prediction producing strongest interaction score (pdockq) highest pdockq score recorded across all predictions for this complex the average pLDDT values across the interface for the model with the highest pDOCKQ the average pAE values across the interface for the model with the highest pDOCKQ interfaces.csv Shows the statistics for each prediction made for each complex. Each row is 1 prediction (structure/JSON score file) complex_name model_num pdockq ncontacts plddt_min plddt_avg plddt_max pae_min pae_avg pae_max distance_avg name of the complex AF model number predicted DOCKQ interface accuracy score ranges from 0 worst to best 1 number of contacts seen in prediction Min residue pair pLDDT observed in the interface Average pair pLDDT observed in the interface Max residue pair pLDDT observed in the interface Min residue pair PAE observed in the interface Average residue pair PAE observed in the interface Max residue pair PAE observed in the interface Average distance between closest atoms in residue pairs in the interface contacts.csv A comprehensive table of all residue contact pairs between all chains that met the contact criteria specified during the run. Each row is 1 pair of interacting residues in different chains. complex_name model_num aa1_chain aa1_index aa2_chain aa1_plddt aa2_index aa2_type aa2_plddt aa1_type pae min_distance Name of the complex AlphaFold model number chain residue 1 is in Index of residue 1 within its chain chain residue 2 is in pLDDT for aa1 Index of residue 2 within its chain 1 letter code for residue 2 pLDDT for aa2 1 letter code for residue 1 Combined pAE value for residue pair calculated using specified "pae_mode" Minimum distance in angstroms between the 2 residues.

The introduction of AlphaFold 2<SUP>1</SUP> has spurred a revolution in modelling the structure of proteins and their interactions, enabling a huge range of applications in protein modelling and design<SUP>2, 3, 4, 5─6</SUP>. Here we describe our AlphaFold 3 model with a substantially updated diffusion-based architecture that is capable of predicting the joint structure of complexes including proteins, nucleic acids, small molecules, ions and modified residues. The new AlphaFold model demonstrates substantially improved accuracy over many previous specialized tools: far greater accuracy for protein─ligand interactions compared with state-of-the-art docking tools, much higher accuracy for protein─nucleic acid interactions compared with nucleic-acid-specific predictors and substantially higher antibody─antigen prediction accuracy compared with AlphaFold-Multimer v.2.3<SUP>7,8</SUP>. Together, these results show that high-accuracy modelling across biomolecular space is possible within a single unified deep-learning framework.

The AlphaFold Protein Structure Database (AlphaFold DB, https://alphafold.ebi.ac.uk) is an openly accessible, extensive database of high-accuracy protein-structure predictions. Powered by AlphaFold v2.0 of DeepMind, it has enabled an unprecedented expansion of the structural coverage of the known protein-sequence space. AlphaFold DB provides programmatic access to and interactive visualization of predicted atomic coordinates, per-residue and pairwise model-confidence estimates and predicted aligned errors. The initial release of AlphaFold DB contains over 360,000 predicted structures across 21 model-organism proteomes, which will soon be expanded to cover most of the (over 100 million) representative sequences from the UniRef90 data set.

The computer artificial intelligence system AlphaFold has recently predicted previously unknown three-dimensional structures of thousands of proteins. Focusing on the subset with high-confidence scores, we algorithmically analyze these predictions for cases where the protein backbone exhibits rare topological complexity, i.e. knotting. Amongst others, we discovered a $7_1$-knot, the most topologically complex knot ever found in a protein, as well several 6-crossing composite knots comprised of two methyltransferase or carbonic anhydrase domains, each containing a simple trefoil knot. These deeply embedded composite knots occur evidently by gene duplication and interconnection of knotted dimers. Finally, we report two new five-crossing knots including the first $5_1$-knot. Our list of analyzed structures forms the basis for future experimental studies to confirm these novel knotted topologies and to explore their complex folding mechanisms.

AlphaFold 3 represents a transformative advancement in computational biology, enhancing protein structure prediction through novel multi-scale transformer architectures, biologically informed cross-attention mechanisms, and geometry-aware optimization strategies. These innovations dramatically improve predictive accuracy and generalization across diverse protein families, surpassing previous methods. Crucially, AlphaFold 3 embodies a paradigm shift toward differentiable simulation, bridging traditional static structural modeling with dynamic molecular simulations. By reframing protein folding predictions as a differentiable process, AlphaFold 3 serves as a foundational framework for integrating deep learning with physics-based molecular

The idea of this project is to study the protein structure and sequence relationship using the hidden markov model and artificial neural network. In this context we have assumed two hidden markov models. In first model we have taken protein secondary structures as hidden and protein sequences as observed. In second model we have taken protein sequences as hidden and protein structures as observed. The efficiencies for both the hidden markov models have been calculated. The results show that the efficiencies of first model is greater that the second one .These efficiencies are cross validated using artificial neural network. This signifies the importance of protein secondary structures as the main hidden controlling factors due to which we observe a particular amino acid sequence. This also signifies that protein secondary structure is more conserved in comparison to amino acid sequence.

In recent years, advances in artificial intelligence (AI) have transformed structural biology, particularly protein structure prediction. Though AI-based methods, such as AlphaFold (AF), often predict single conformations of proteins with high accuracy and confidence, predictions of alternative folds are often inaccurate, low-confidence, or simply not predicted at all. Here, we review three blind spots that alternative conformations reveal about AF-based protein structure prediction. First, proteins that assume conformations distinct from their training-set homologs can be mispredicted. Second, AF overrelies on its training set to predict alternative conformations. Third, degeneracies in pairwise representations can lead to high-confidence predictions inconsistent with experiment. These weaknesses suggest approaches to predict alternative folds more reliably.

Abstract Proteins are essential to life, and understanding their structure can facilitate a mechanistic understanding of their function. Through an enormous experimental effort 1–4 , the structures of around 100,000 unique proteins have been determined 5 , but this represents a small fraction of the billions of known protein sequences 6,7 . 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 years 9 . Despite recent progress 10–14 , 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.

Abstract The introduction of AlphaFold 2 1 has spurred a revolution in modelling the structure of proteins and their interactions, enabling a huge range of applications in protein modelling and design 2–6 . Here we describe our AlphaFold 3 model with a substantially updated diffusion-based architecture that is capable of predicting the joint structure of complexes including proteins, nucleic acids, small molecules, ions and modified residues. The new AlphaFold model demonstrates substantially improved accuracy over many previous specialized tools: far greater accuracy for protein–ligand interactions compared with state-of-the-art docking tools, much higher accuracy for protein–nucleic acid interactions compared with nucleic-acid-specific predictors and substantially higher antibody–antigen prediction accuracy compared with AlphaFold-Multimer v.2.3 7,8 . Together, these results show that high-accuracy modelling across biomolecular space is possible within a single unified deep-learning framework.

The AlphaFold Protein Structure Database (AlphaFold DB, https://alphafold.ebi.ac.uk) is an openly accessible, extensive database of high-accuracy protein-structure predictions. Powered by AlphaFold v2.0 of DeepMind, it has enabled an unprecedented expansion of the structural coverage of the known protein-sequence space. AlphaFold DB provides programmatic access to and interactive visualization of predicted atomic coordinates, per-residue and pairwise model-confidence estimates and predicted aligned errors. The initial release of AlphaFold DB contains over 360,000 predicted structures across 21 model-organism proteomes, which will soon be expanded to cover most of the (over 100 million) representative sequences from the UniRef90 data set.

While the vast majority of well-structured single protein chains can now be predicted to high accuracy due to the recent AlphaFold [1] model, the prediction of multi-chain protein complexes remains a challenge in many cases. In this work, we demonstrate that an AlphaFold model trained specifically for multimeric inputs of known stoichiometry, which we call AlphaFold-Multimer, significantly increases accuracy of predicted multimeric interfaces over input-adapted single-chain AlphaFold while maintaining high intra-chain accuracy. On a benchmark dataset of 17 heterodimer proteins without templates (introduced in [2]) we achieve at least medium accuracy (DockQ [3] ≥ 0.49) on 13 targets and high accuracy (DockQ ≥ 0.8) on 7 targets, compared to 9 targets of at least medium accuracy and 4 of high accuracy for the previous state of the art system (an AlphaFold-based system from [2]). We also predict structures for a large dataset of 4,446 recent protein complexes, from which we score all non-redundant interfaces with low template identity. For heteromeric interfaces we successfully predict the interface (DockQ ≥ 0.23) in 70% of cases, and produce high accuracy predictions (DockQ ≥ 0.8) in 26% of cases, an improvement of +27 and +14 percentage points over the flexible linker modification of AlphaFold [4] respectively. For homomeric inter-faces we successfully predict the interface in 72% of cases, and produce high accuracy predictions in 36% of cases, an improvement of +8 and +7 percentage points respectively.