Explore Research

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.