Field Of Structure Prediction Research Articles

Challenge for Deep Learning: Protein Structure Prediction of Ligand-Induced Conformational Changes at Allosteric and Orthosteric Sites.

In the realm of biomedical research, understanding the intricate structure of proteins is crucial, as these structures determine how proteins function within our bodies and interact with potential drugs. Traditionally, methods like X-ray crystallography and cryo-electron microscopy have been used to unravel these structures, but they are often challenging, time-consuming and costly. Recently, a breakthrough in computational biology has emerged with the development of deep learning algorithms capable of predicting protein structures based on their amino acid sequences (Jumper, J., et al. Nature 2021, 596, 583. Lane, T. J. Nature Methods 2023, 20, 170. Kryshtafovych, A., et al. Proteins: Structure, Function and Bioinformatics 2021, 89, 1607). This study focuses on predicting the dynamic changes that proteins undergo upon ligand binding, specifically when they bind to allosteric sites, i.e. a pocket different from the active site. Allosteric modulators are particularly important for drug discovery, as they open new avenues for designing drugs that can target proteins more effectively and with fewer side effects (Nussinov, R.; Tsai, C. J. Cell 2013, 153, 293). To study this, we curated a data set of 578 X-ray structures comprised of proteins displaying orthosteric and allosteric binding as well as a general framework to evaluate deep learning-based structure prediction methods. Our findings demonstrate the potential and current limitations of deep learning methods, such as AlphaFold2 (Jumper, J., et al. Nature 2021, 596, 583), NeuralPLexer (Qiao, Z., et al. Nat Mach Intell 2024, 6, 195), and RoseTTAFold All-Atom (Krishna, R., et al. Science 2024, 384, eadl2528) to predict not just static protein structures but also the dynamic conformational changes. Herein we show that predicting the allosteric induce-fit conformation still poses a challenge to deep learning methods as they more accurately predict the orthosteric bound conformation compared to the allosteric induce fit conformation. For AlphaFold2, we observed that conformational diversity, and sampling between the apo and holo state could be increased by modifying the MSA depth, but this did not enhance the ability to generate conformations close to the allosteric induced-fit conformation. To further support advancements in protein structure prediction field, the curated data set and evaluation framework are made publicly available.

Critical Assessment of Methods for Predicting the 3D Structure of Proteins and Protein Complexes.

Advances in a scientific discipline are often measured by small, incremental steps. In this review, we report on two intertwined disciplines in the protein structure prediction field, modeling of single chains and modeling of complexes, that have over decades emulated this pattern, as monitored by the community-wide blind prediction experiments CASP and CAPRI. However, over the past few years, dramatic advances were observed for the accurate prediction of single protein chains, driven by a surge of deep learning methodologies entering the prediction field. We review the mainscientific developments that enabled these recent breakthroughs and feature the important role of blind prediction experiments in building up and nurturing the structure prediction field. We discuss how the new wave of artificial intelligence-based methods is impacting the fields of computational and experimental structural biology and highlight areas in which deep learning methods are likely to lead to future developments, provided that major challenges are overcome.

Evaluating GPCR modeling and docking strategies in the era of deep learning-based protein structure prediction

While deep learning (DL) has brought a revolution in the protein structure prediction field, still an important question remains how the revolution can be transferred to advances in structure-based drug discovery. Because the lessons from the recent GPCR dock challenge were inconclusive primarily due to the size of the dataset, in this work we further elaborated on 70 diverse GPCR complexes bound to either small molecules or peptides to investigate the best-practice modeling and docking strategies for GPCR drug discovery. From our quantitative analysis, it is shown that substantial improvements in docking and virtual screening have been possible by the advance in DL-based protein structure predictions with respect to the expected results from the combination of best pre-DL tools. The success rate of docking on DL-based model structures approaches that of cross-docking on experimental structures, showing over 30% improvement from the best pre-DL protocols. This amount of performance could be achieved only when two modeling points were considered properly: 1) correct functional-state modeling of receptors and 2) receptor-flexible docking. Best-practice modeling strategies and the model confidence estimation metric suggested in this work may serve as a guideline for future computer-aided GPCR drug discovery scenarios.

AI-Based Protein Structure Prediction in Drug Discovery: Impacts and Challenges.

Proteins are the molecular machinery of the human body, and their malfunctioning is often responsible for diseases, making them crucial targets for drug discovery. The three-dimensional structure of a protein determines its biological function, its conformational state determines substrates, cofactors, and protein binding. Rational drug discovery employs engineered small molecules to selectively interact with proteins to modulate their function. To selectively target a protein and to design small molecules, knowing the protein structure with all its specific conformation is critical. Unfortunately, for a large number of proteins relevant for drug discovery, the three-dimensional structure has not yet been experimentally solved. Therefore, accurately predicting their structure based on their amino acid sequence is one of the grant challenges in biology. Recently, AlphaFold2, a machine learning application based on a deep neural network, was able to predict unknown structures of proteins with an unprecedented accuracy. Despite the impressive progress made by AlphaFold2, nature still challenges the field of structure prediction. In this Perspective, we explore how AlphaFold2 and related methods help make drug design more efficient. Furthermore, we discuss the roles of predicting domain-domain orientations, all relevant conformational states, the influence of posttranslational modifications, and conformational changes due to protein binding partners. We highlight where further improvements are needed for advanced machine learning methods to be successfully and frequently used in the pharmaceutical industry.

ContactPFP: Protein Function Prediction Using Predicted Contact Information

Computational function prediction is one of the most important problems in bioinformatics as elucidating the function of genes is a central task in molecular biology and genomics. Most of the existing function prediction methods use protein sequences as the primary source of input information because the sequence is the most available information for query proteins. There are attempts to consider other attributes of query proteins. Among these attributes, the three-dimensional (3D) structure of proteins is known to be very useful in identifying the evolutionary relationship of proteins, from which functional similarity can be inferred. Here, we report a novel protein function prediction method, ContactPFP, which uses predicted residue-residue contact maps as input structural features of query proteins. Although 3D structure information is known to be useful, it has not been routinely used in function prediction because the 3D structure is not experimentally determined for many proteins. In ContactPFP, we overcome this limitation by using residue-residue contact prediction, which has become increasingly accurate due to rapid development in the protein structure prediction field. ContactPFP takes a query protein sequence as input and uses predicted residue-residue contact as a proxy for the 3D protein structure. To characterize how predicted contacts contribute to function prediction accuracy, we compared the performance of ContactPFP with several well-established sequence-based function prediction methods. The comparative study revealed the advantages and weaknesses of ContactPFP compared to contemporary sequence-based methods. There were many cases where it showed higher prediction accuracy. We examined factors that affected the accuracy of ContactPFP using several illustrative cases that highlight the strength of our method.

Assessment of the CASP14 assembly predictions.

In CASP14, 39 research groups submitted more than 2500 3D models on 22 protein complexes. In general, the community performed well in predicting the fold of the assemblies (for 80% of the targets), although it faced significant challenges in reproducing the native contacts. This is especially the case for the complexes without whole-assembly templates. The leading predictor, BAKER-experimental, used a methodology combining classical techniques (template-based modeling, protein docking) with deep learning-based contact predictions and a fold-and-dock approach. The Venclovas team achieved the runner-up position with template-based modeling and docking. By analyzing the target interfaces, we showed that the complexes with depleted charged contacts or dominating hydrophobic interactions were the most challenging ones to predict. We also demonstrated that if AlphaFold2 predictions were at hand, the interface prediction challenge could be alleviated for most of the targets. All in all, it is evident that new approaches are needed for the accurate prediction of assemblies, which undoubtedly will expand on the significant improvements in the tertiary structure prediction field.

High-accuracy protein structure prediction in CASP14.

The application of state-of-the-art deep-learning approaches to the protein modeling problem has expanded the "high-accuracy" category in CASP14 to encompass all targets. Building on the metrics used for high-accuracy assessment in previous CASPs, we evaluated the performance of all groups that submitted models for at least 10 targets across all difficulty classes, and judged the usefulness of those produced by AlphaFold2 (AF2) as molecular replacement search models with AMPLE. Driven by the qualitative diversity of the targets submitted to CASP, we also introduce DipDiff as a new measure for the improvement in backbone geometry provided by a model versus available templates. Although a large leap in high-accuracy is seen due to AF2, the second-best method in CASP14 out-performed the best in CASP13, illustrating the role of community-based benchmarking in the development and evolution of the protein structure prediction field.

Modeling of protein complexes in CASP14 with emphasis on the interaction interface prediction.

The goal of CASP experiments is to monitor the progress in the protein structure prediction field. During the 14th CASP edition we aimed to test our capabilities of predicting structures of protein complexes. Our protocol for modeling protein assemblies included both template‐based modeling and free docking. Structural templates were identified using sensitive sequence‐based searches. If sequence‐based searches failed, we performed structure‐based template searches using selected CASP server models. In the absence of reliable templates we applied free docking starting from monomers generated by CASP servers. We evaluated and ranked models of protein complexes using an improved version of our protein structure quality assessment method, VoroMQA, taking into account both interaction interface and global structure scores. If reliable templates could be identified, generally accurate models of protein assemblies were generated with the exception of an antibody‐antigen interaction. The success of free docking mainly depended on the accuracy of initial subunit models and on the scoring of docking solutions. To put our overall results in perspective, we analyzed our performance in the context of other CASP groups. Although the subunits in our assembly models often were not of the top quality, these models had, overall, the best‐predicted intersubunit interfaces according to several accuracy measures. We attribute our relative success primarily to the emphasis on the interaction interface when modeling and scoring.

Deep Learning-Based Advances in Protein Structure Prediction.

Obtaining an accurate description of protein structure is a fundamental step toward understanding the underpinning of biology. Although recent advances in experimental approaches have greatly enhanced our capabilities to experimentally determine protein structures, the gap between the number of protein sequences and known protein structures is ever increasing. Computational protein structure prediction is one of the ways to fill this gap. Recently, the protein structure prediction field has witnessed a lot of advances due to Deep Learning (DL)-based approaches as evidenced by the success of AlphaFold2 in the most recent Critical Assessment of protein Structure Prediction (CASP14). In this article, we highlight important milestones and progresses in the field of protein structure prediction due to DL-based methods as observed in CASP experiments. We describe advances in various steps of protein structure prediction pipeline viz. protein contact map prediction, protein distogram prediction, protein real-valued distance prediction, and Quality Assessment/refinement. We also highlight some end-to-end DL-based approaches for protein structure prediction approaches. Additionally, as there have been some recent DL-based advances in protein structure determination using Cryo-Electron (Cryo-EM) microscopy based, we also highlight some of the important progress in the field. Finally, we provide an outlook and possible future research directions for DL-based approaches in the protein structure prediction arena.

The Future of Protein Secondary Structure Prediction Was Invented by Oleg Ptitsyn.

When Oleg Ptitsyn and his group published the first secondary structure prediction for a protein sequence, they started a research field that is still active today. Oleg Ptitsyn combined fundamental rules of physics with human understanding of protein structures. Most followers in this field, however, use machine learning methods and aim at the highest (average) percentage correctly predicted residues in a set of proteins that were not used to train the prediction method. We show that one single method is unlikely to predict the secondary structure of all protein sequences, with the exception, perhaps, of future deep learning methods based on very large neural networks, and we suggest that some concepts pioneered by Oleg Ptitsyn and his group in the 70s of the previous century likely are today’s best way forward in the protein secondary structure prediction field.

Assessment of protein assembly prediction in CASP13

AbstractWe present the assembly category assessment in the 13th edition of the CASP community‐wide experiment. For the second time, protein assemblies constitute an independent assessment category. Compared to the last edition we see a clear uptake in participation, more oligomeric targets released, and consistent, albeit modest, improvement of the predictions quality. Looking at the tertiary structure predictions, we observe that ignoring the oligomeric state of the targets hinders modeling success. We also note that some contact prediction groups successfully predicted homomeric interfacial contacts, though it appears that these predictions were not used for assembly modeling. Homology modeling with sizeable human intervention appears to form the basis of the assembly prediction techniques in this round of CASP. Future developments should see more integrated approaches where subunits are modeled in the context of the assemblies they form.

Two New Heuristic Methods for Protein Model Quality Assessment.

Protein tertiary structure prediction is an important open challenge in bioinformatics and requires effective methods to accurately evaluate the quality of protein 3-D models generated computationally. Many quality assessment (QA) methods have been proposed over the past three decades. However, the accuracy or robustness is unsatisfactory for practical applications. In this paper, two new heuristic QA methods are proposed: MUfoldQA_S and MUfoldQA_C. The MUfoldQA_S is a quasi-single-model QA method that assesses the model quality based on the known protein structures with similar sequences. This algorithm can be directly applied to protein fragments without the necessity of building a full structural model. A BLOSUM-based heuristic is also introduced to help differentiate accurate templates from poor ones. In MUfoldQA_C, the ideas from MUfoldQA_S were combined with the consensus approach to create a multi-model QA method that could also utilize information from existing reference models and have demonstrated improved performance. Extensive experimental results of these two methods have shown significant improvement over existing methods. In addition, both methods have been blindly tested in the CASP12 world-wide competition in the protein structure prediction field and ranked as top performers in their respective categories.

Protein Sequence Coevolution, Energy Landscapes and their Connections to Protein Structure, Folding and Function

Energy landscape theory has been a powerful approach to study protein folding dynamics and function. The discovery that an accurate estimate of the joint probability distribution of amino acid occupancies in protein families provides insights about residue-residue coevolution and concrete details about protein folding landscapes and therefore has also advanced structural biophysics. Our realization that the collection of couplings and local fields as parameters of such distribution is inherently connected with the thermodynamics of sequence selection towards folding and function demonstrates the importance of coevolutionary methods to understand stability and function of biomolecules. The synergy between structure based models and coevolutionary information has spearheaded the field of structure prediction, including protein and RNA, as well as accelerating the discovery of functional structural states and the prediction of protein complexes. Coevolution signals can also be used to create protein recognition metrics, which led to successful experimental efforts, and the uncovering of novel molecular interactions. This idea has opened the door to encode recognition in protein pairs. Coevolved interfaces can also be combined with small molecule hot spot estimation methods to improve the discovery of druggable interfaces. Finally, we show that biophysical modeling via statistical inference approaches can shed light on structural properties of chromosomes. We demonstrate that it is possible to reconstruct with fidelity experimental maps of interacting genomic regions for particular chromosomal types by learning only generic properties of single chromosomes. We provide evidence of the depth and coverage of energy landscape theory approaches linked with coevolutionary methods and their impact in our goal to understand biological function at the molecular level.

Comparative Study of Classification Techniques For Large Scale Data - Case Study

The existence of Massive datasets that are generated in many applications provides various opportunities and challenges. Especially, scalable mining of such large-scale datasets is a challenging issue that attracted some recent research. In the present study, the main focus is to analyse the classification techniques using WEKA machine learning workbench. Moreover, a large-scale dataset was used. This dataset comes from the protein structure prediction field. It has already been partitioned into training and test sets using the ten-fold cross-validation methodology. In this experiment, nine different methods have been tested. As a result, it became obvious that it is not applicable to test more than one classifier from the (tree) family in the same experiment. On the other hand, using (NaiveBayes) Classifier with the default properties of the attribute selection filter has a great time consuming. Finally, varying the parameters of the attribute selections should be prioritized for more accurate results.

Segment assembly, structure alignment and iterative simulation in protein structure prediction

Segment assembly, structure alignment and iterative simulation in protein structure prediction

Quantification of protein group coherence and pathway assignment using functional association

BackgroundGenomics and proteomics experiments produce a large amount of data that are awaiting functional elucidation. An important step in analyzing such data is to identify functional units, which consist of proteins that play coherent roles to carry out the function. Importantly, functional coherence is not identical with functional similarity. For example, proteins in the same pathway may not share the same Gene Ontology (GO) terms, but they work in a coordinated fashion so that the aimed function can be performed. Thus, simply applying existing functional similarity measures might not be the best solution to identify functional units in omics data.ResultsWe have designed two scores for quantifying the functional coherence by considering association of GO terms observed in two biological contexts, co-occurrences in protein annotations and co-mentions in literature in the PubMed database. The counted co-occurrences of GO terms were normalized in a similar fashion as the statistical amino acid contact potential is computed in the protein structure prediction field. We demonstrate that the developed scores can identify functionally coherent protein sets, i.e. proteins in the same pathways, co-localized proteins, and protein complexes, with statistically significant score values showing a better accuracy than existing functional similarity scores. The scores are also capable of detecting protein pairs that interact with each other. It is further shown that the functional coherence scores can accurately assign proteins to their respective pathways.ConclusionWe have developed two scores which quantify the functional coherence of sets of proteins. The scores reflect the actual associations of GO terms observed either in protein annotations or in literature. It has been shown that they have the ability to accurately distinguish biologically relevant groups of proteins from random ones as well as a good discriminative power for detecting interacting pairs of proteins. The scores were further successfully applied for assigning proteins to pathways.

Predicting solid compounds via global exploration of the energy landscape of solids on theab initiolevel without recourse to experimental information

Predicting which crystalline modifications can exist in a chemical system requires the global exploration of its energy landscape. Due to the large computational effort involved, in the past this search for sufficiently stable minima has been performed employing a variety of empirical potentials and cost functions followed by a local optimization on the ab initio level. However, this might introduce some bias favoring certain types of chemical bonding and entails the risk of overlooking important modifications that are not modeled accurately using empirical potentials. In order to overcome this critical limitation, it is necessary to employ ab initio energy functions during the global optimization phase of the structure prediction. In this paper, we review the current state of the field of structure prediction on the ab initio level.

The grail problem.

The grail problem.

Fast evaluation of internal loops in RNA secondary structure prediction.

Though not as abundant in known biological processes as proteins, RNA molecules serve as more than mere intermediaries between DNA and proteins. Research in the last 15 years demonstrates that RNA molecules serve in many roles, including catalysis. Furthermore, RNA secondary structure prediction based on free energy rules for stacking and loop formation remains one of the few major breakthroughs in the field of structure prediction, as minimum free energy structures and related quantities can be computed with full mathematical rigor. However, with the current energy parameters, the algorithms used hitherto suffer the disadvantage of either employing heuristics that risk (though highly unlikely) missing the optimal structure or becoming prohibitively time consuming for moderate to large sequences. We present a new method to evaluate internal loops utilizing currently used energy rules. This method reduces the time complexity of this part of the structure prediction from O(n4) to O(n3), thus reducing the overall complexity to O(n3). Even when the size of evaluated internal loops is bounded by k (a commonly used heuristic), the method presented has a competitive edge by reducing the time complexity of internal loop evaluation from O(k2n2) to O(kn2). The method also applies to the calculation of the equilibrium partition function. Source code for an RNA secondary structure prediction program implementing this method is available at ftp://www.ibc.wustl.edu/pub/zuker/zuker .tar.Z

An Improved Algorithm for RNA Secondary Structure Prediction

Though not as abundant in known biological processes as proteins,<br />RNA molecules serve as more than mere intermediaries between<br />DNA and proteins, e.g. as catalytic molecules. Furthermore,<br />RNA secondary structure prediction based on free energy<br />rules for stacking and loop formation remains one of the few major<br />breakthroughs in the field of structure prediction. We present a<br />new method to evaluate all possible internal loops of size at most<br />k in an RNA sequence, s, in time O(k|s|^2); this is an improvement<br />from the previously used method that uses time O(k^2|s|^2).<br />For unlimited loop size this improves the overall complexity of<br />evaluating RNA secondary structures from O(|s|^4) to O(|s|^3) and<br />the method applies equally well to finding the optimal structure<br />and calculating the equilibrium partition function. We use our<br />method to examine the soundness of setting k = 30, a commonly<br />used heuristic.