Improved protein structure prediction with trRosettaX2, AlphaFold2, and optimized MSAs in CASP15

An easy-to-use three-dimensional protein-structure-prediction online platform "DPL3D" based on deep learning algorithms

The change in the three-dimensional (3D) structure of a protein can affect its own function or interaction with other protein(s), which may lead to disease(s). Gene mutations, especially missense mutations, are the main cause of changes in protein structure. Due to the lack of protein crystal structure data, about three-quarters of human mutant proteins cannot be predicted or accurately predicted, and the pathogenicity of missense mutations can only be indirectly evaluated by evolutionary conservation. Recently, many computational methods have been developed to predict protein 3D structures with accuracy comparable to experiments. This progress enables the information of structural biology to be further utilized by clinicians. Thus, we developed a user-friendly platform named DPL3D (http://nsbio.tech:3000) which can predict and visualize the 3D structure of mutant proteins. The crystal structure and other information of proteins were downloaded together with the software including AlphaFold 2, RoseTTAFold, RoseTTAFold All-Atom, and trRosettaX-Single. We implemented a query module for 210,180 molecular structures, including 52,248 human proteins. Visualization of protein two-dimensional (2D) and 3D structure prediction can be generated via LiteMol automatically or manually and interactively. This platform will allow users to easily and quickly retrieve large-scale structural information for biological discovery.

The proteomic code: Novel amino acid residue pairing models "encode" protein folding and protein-protein interactions

Recent advances in protein 3D structure prediction using deep learning have focused on the importance of amino acid residue-residue connections (i.e., pairwise atomic contacts) for accuracy at the expense of mechanistic interpretability. Therefore, we decided to perform a series of analyses based on an alternative framework of residue-residue connections making primary use of the TOP2018 dataset. This framework of residue-residue connections is derived from amino acid residue pairing models both historic and new, all based on genetic principles complemented by relevant biophysical principles. Of these pairing models, three new models (named the GU, Transmuted and Shift pairing models) exhibit the highest observed-over-expected ratios and highest correlations in statistical analyses with various intra- and inter-chain datasets, in comparison to the remaining models. In addition, these new pairing models are universally frequent across different connection ranges, secondary structure connections, and protein sizes. Accordingly, following further statistical and other analyses described herein, we have come to a major conclusion that all three pairing models together could represent the basis of a universal proteomic code (second genetic code) sufficient, in and of itself, to "encode" for both protein folding mechanisms and protein-protein interactions.

AF3Complex Yields Improved Structural Predictions of Protein Complexes

Motivation

Accurate structures of protein complexes are essential for understanding biological pathway function. A previous study showed how downstream modifications to AlphaFold 2 could yield AF2Complex, a model better suited for protein complexes. Here, we introduce AF3Complex, a model equipped with the same improvements as AF2Complex, along with a novel method for excluding ligands, built on AlphaFold 3.

Results

Benchmarking AF3Complex and AlphaFold 3 on a large dataset of protein complexes, it was shown that AF3Complex outperforms AlphaFold 3 to a significant degree. Moreover, by evaluating the structures generated by AF3Complex on a dataset of protein-peptide complexes and antibody-antigen complexes, it was established that AF3Complex could create high-fidelity structures for these challenging complex types. Additionally, when deployed to generate structural predictions for the two antibody-antigen and seven protein-protein complexes used in the recent CASP16 competition, AF3Complex yielded structures that would have placed it among the top models in the competition.

Availability

The AF3Complex code is freely available at https://github.com/Jfeldman34/AF3Complex.git.

Contact

Please contact skolnick@gatech.edu.

Easy and accurate protein structure prediction using ColabFold

Since its public release in 2021, AlphaFold2 (AF2) has made investigating biological questions, by using predicted protein structures of single monomers or full complexes, a common practice. ColabFold-AF2 is an open-source Jupyter Notebook inside Google Colaboratory and a command-line tool that makes it easy to use AF2 while exposing its advanced options. ColabFold-AF2 shortens turnaround times of experiments because of its optimized usage of AF2's models. In this protocol, we guide the reader through ColabFold best practices by using three scenarios: (i) monomer prediction, (ii) complex prediction and (iii) conformation sampling. The first two scenarios cover classic static structure prediction and are demonstrated on the human glycosylphosphatidylinositol transamidase protein. The third scenario demonstrates an alternative use case of the AF2 models by predicting two conformations of the human alanine serine transporter 2. Users can run the protocol without computational expertise via Google Colaboratory or in a command-line environment for advanced users. Using Google Colaboratory, it takes <2 h to run each procedure. The data and code for this protocol are available at https://protocol.colabfold.com .

Advancing protein structure prediction beyond AlphaFold2

Accurate prediction of protein structures is essential for understanding their biological functions. The release of AlphaFold2 in 2021 marked a significant breakthrough, delivering unprecedented accuracy. However, challenges remain, particularly for proteins with limited evolutionary data or complex molecular interactions. This review explores efforts to enhance AlphaFold2's performance through advanced sequence search techniques and alternative approaches, including protein language models and frameworks that integrate diverse biomolecular interactions. We propose that future progress will depend on developing models grounded in fundamental physicochemical principles, offering more accurate and comprehensive predictions across a wider spectrum of biological systems.

Physical-aware model accuracy estimation for protein complex using deep learning method

With the breakthrough of AlphaFold2 on monomers, the research focus of structure prediction has shifted to protein complexes, driving the continued development of new methods for multimer structure prediction. Therefore, it is crucial to accurately estimate quality scores for the multimer model independent of the used prediction methods. In this work, we propose a physical-aware deep learning method, DeepUMQA-PA, to evaluate the residue-wise quality of protein complex models. Given the input protein complex model, the residue-based contact area and orientation features were first constructed using Voronoi tessellation, representing the potential physical interactions and hydrophobic properties. Then, the relationship between local residues and the overall complex topology as well as the inter-residue evolutionary information are characterized by geometry-based features, protein language model embedding representation, and knowledge-based statistical potential features. Finally, these features are fed into a fused network architecture employing equivalent graph neural network and ResNet network to estimate residue-wise model accuracy. Experimental results on the CASP15 test set demonstrate that our method outperforms the state-of-the-art method DeepUMQA3 by 3.69 % and 3.49 % on Pearson and Spearman, respectively. Notably, our method achieved 16.8 % and 15.5 % improvement in Pearson and Spearman, respectively, for the evaluation of nanobody-antigens. In addition, DeepUMQA-PA achieved better MAE scores than AlphaFold-Multimer and AlphaFold3 self-assessment methods on 43 % and 50 % of the targets, respectively. All these results suggest that physical-aware information based on the area and orientation of atom-atom and atom-solvent contacts has the potential to capture sequence-structure-quality relationships of proteins, especially in the case of flexible proteins. The DeepUMQA-PA server is freely available at http://zhanglab-bioinf.com/DeepUMQA-PA/.

The Historical Evolution and Significance of Multiple Sequence Alignment in Molecular Structure and Function Prediction

Multiple sequence alignment (MSA) has evolved into a fundamental tool in the biological sciences, playing a pivotal role in predicting molecular structures and functions. With broad applications in protein and nucleic acid modeling, MSAs continue to underpin advancements across a range of disciplines. MSAs are not only foundational for traditional sequence comparison techniques but also increasingly important in the context of artificial intelligence (AI)-driven advancements. Recent breakthroughs in AI, particularly in protein and nucleic acid structure prediction, rely heavily on the accuracy and efficiency of MSAs to enhance remote homology detection and guide spatial restraints. This review traces the historical evolution of MSA, highlighting its significance in molecular structure and function prediction. We cover the methodologies used for protein monomers, protein complexes, and RNA, while also exploring emerging AI-based alternatives, such as protein language models, as complementary or replacement approaches to traditional MSAs in application tasks. By discussing the strengths, limitations, and applications of these methods, this review aims to provide researchers with valuable insights into MSA's evolving role, equipping them to make informed decisions in structural prediction research.

The TolC and Lipopolysaccharide-Specific Escherichia coli Bacteriophage TLS-the Tlsvirus Archetype Virus

Introduction

TLS is a virulent bacteriophage of Escherichia coli that utilizes TolC and lipopolysaccharide as its cell surface receptors.

Methods

The genome was reannotated using the latest online resources and compared to other T1-like phages.

Results

The TLS genome consists of 49,902 base pairs, encoding 86 coding sequences that display considerable sequence similarity with the T1 phage genome. It also contains 18 intergenic 21-base long repeats, each of them upstream of a predicted start codon and in the direction of transcription. Data revealed that DNA packaging occurs through the pac site-mediated headful mechanism.

Conclusions

Based on sequence analysis of its genome, TLS belongs to the Drexlerviridae family and represents the type member of the Tlsvirus genus.

Valorization of single-carbon chemicals by using carboligases as key enzymes

Single-carbon (C1) biorefinery plays a key role in the consumption of global greenhouse gases and a circular carbon economy. Thereby, we have focused on the valorization of C1 compounds (e.g. methanol, formaldehyde, and formate) into multicarbon products, including bioplastic monomers, glycolate, and ethylene glycol. For instance, methanol, derived from the oxidation of CH4, can be converted into glycolate, ethylene glycol, or erythrulose via formaldehyde and glycolaldehyde, employing C1 and/or C2 carboligases as essential enzymes. Escherichia coli was engineered to convert formate, produced from CO via CO2 or from CO2 directly, into glycolate. Recent progress in the design of biotransformation pathways, enzyme discovery, and engineering, as well as whole-cell biocatalyst engineering for C1 biorefinery, was addressed in this review.

Recent Advances and Challenges in Protein Structure Prediction

Artificial intelligence has made significant advances in the field of protein structure prediction in recent years. In particular, DeepMind's end-to-end model, AlphaFold2, has demonstrated the capability to predict three-dimensional structures of numerous unknown proteins with accuracy levels comparable to those of experimental methods. This breakthrough has opened up new possibilities for understanding protein structure and function as well as accelerating drug discovery and other applications in the field of biology and medicine. Despite the remarkable achievements of artificial intelligence in the field, there are still some challenges and limitations. In this Review, we discuss the recent progress and some of the challenges in protein structure prediction. These challenges include predicting multidomain protein structures, protein complex structures, multiple conformational states of proteins, and protein folding pathways. Furthermore, we highlight directions in which further improvements can be conducted.

DeepFold: enhancing protein structure prediction through optimized loss functions, improved template features, and re-optimized energy function

MOTIVATION

Predicting protein structures with high accuracy is a critical challenge for the broad community of life sciences and industry. Despite progress made by deep neural networks like AlphaFold2, there is a need for further improvements in the quality of detailed structures, such as side-chains, along with protein backbone structures.

RESULTS

Building upon the successes of AlphaFold2, the modifications we made include changing the losses of side-chain torsion angles and frame aligned point error, adding loss functions for side chain confidence and secondary structure prediction, and replacing template feature generation with a new alignment method based on conditional random fields. We also performed re-optimization by conformational space annealing using a molecular mechanics energy function which integrates the potential energies obtained from distogram and side-chain prediction. In the CASP15 blind test for single protein and domain modeling (109 domains), DeepFold ranked fourth among 132 groups with improvements in the details of the structure in terms of backbone, side-chain, and Molprobity. In terms of protein backbone accuracy, DeepFold achieved a median GDT-TS score of 88.64 compared with 85.88 of AlphaFold2. For TBM-easy/hard targets, DeepFold ranked at the top based on Z-scores for GDT-TS. This shows its practical value to the structural biology community, which demands highly accurate structures. In addition, a thorough analysis of 55 domains from 39 targets with publicly available structures indicates that DeepFold shows superior side-chain accuracy and Molprobity scores among the top-performing groups.

AVAILABILITY AND IMPLEMENTATION

DeepFold tools are open-source software available at https://github.com/newtonjoo/deepfold.

Critical assessment of methods of protein structure prediction (CASP)-Round XV

Computing protein structure from amino acid sequence information has been a long-standing grand challenge. Critical assessment of structure prediction (CASP) conducts community experiments aimed at advancing solutions to this and related problems. Experiments are conducted every 2 years. The 2020 experiment (CASP14) saw major progress, with the second generation of deep learning methods delivering accuracy comparable with experiment for many single proteins. There is an expectation that these methods will have much wider application in computational structural biology. Here we summarize results from the most recent experiment, CASP15, in 2022, with an emphasis on new deep learning-driven progress. Other papers in this special issue of proteins provide more detailed analysis. For single protein structures, the AlphaFold2 deep learning method is still superior to other approaches, but there are two points of note. First, although AlphaFold2 was the core of all the most successful methods, there was a wide variety of implementation and combination with other methods. Second, using the standard AlphaFold2 protocol and default parameters only produces the highest quality result for about two thirds of the targets, and more extensive sampling is required for the others. The major advance in this CASP is the enormous increase in the accuracy of computed protein complexes, achieved by the use of deep learning methods, although overall these do not fully match the performance for single proteins. Here too, AlphaFold2 based method perform best, and again more extensive sampling than the defaults is often required. Also of note are the encouraging early results on the use of deep learning to compute ensembles of macromolecular structures. Critically for the usability of computed structures, for both single proteins and protein complexes, deep learning derived estimates of both local and global accuracy are of high quality, however the estimates in interface regions are slightly less reliable. CASP15 also included computation of RNA structures for the first time. Here, the classical approaches produced better agreement with experiment than the new deep learning ones, and accuracy is limited. Also, for the first time, CASP included the computation of protein-ligand complexes, an area of special interest for drug design. Here too, classical methods were still superior to deep learning ones. Many new approaches were discussed at the CASP conference, and it is clear methods will continue to advance.