Multi-domain and complex protein structure prediction using inter-domain interactions from deep learning

Expanding kinetoplastid genome annotation through protein structure comparison

Kinetoplastids belong to the Discoba supergroup, an early divergent eukaryotic clade. Although the amount of genomic information on these parasites has grown substantially, assigning gene functions through traditional sequence-based homology methods remains challenging. Recently, significant advancements have been made in in-silico protein structure prediction and algorithms for rapid and precise large-scale protein structure comparisons. In this work, we developed a protein structure-based homology search pipeline (ASC, Annotation by Structural Comparisons) and applied it to transfer biological information to all kinetoplastid proteins available in TriTrypDB, the reference database for this lineage. Our pipeline enabled the assignment of structural similarity to a substantial portion of kinetoplastid proteins, improving current knowledge through annotation transfer. Additionally, we identified structural homologs for representatives of 6,700 uncharacterized proteins across 33 kinetoplastid species, proteins that could not be annotated using existing sequence-based tools and databases. As a result, this approach allowed us to infer potential biological information for a considerable number of kinetoplastid proteins. Among these, we identified structural homologs to ubiquitous eukaryotic proteins that are challenging to detect in kinetoplastid genomes through standard genome annotation pipelines. The results (KASC, Kinetoplastid Annotation by Structural Comparison) are openly accessible to the community at kasc.fcien.edu.uy through a user-friendly, gene-by-gene interface that enables visual inspection of the data.

DeepAssembly2: A Web Server for Protein Complex Structure Assembly Based on Domain-Domain Interactions

Proteins often perform biological functions by forming complexes, thereby accurately predicting the structure of protein complexes is crucial to understanding and mastering their functions, as well as facilitating drug discovery. Protein monomeric structure prediction has made a breakthrough in recent years, but the accurate prediction of complex structure remains a challenge. In this work, we present DeepAssembly2, a web server for automatically assembling protein complex structure based on domain-domain interactions. First, the features are constructed according to the input complex sequence and monomeric structures, then these features are used to predict the inter-chain residue distance through a deep learning model, and finally, the complex structure is assembled under the guidance of inter-chain residue distances. Compared with the previously developed version, DeepAssembly2 is trained on a newly constructed inter-chain domain-domain interaction dataset. Meanwhile, several important features have been added, such as Interface Residue Propensity and Ultrafast Shape Recognition. In addition, we introduced the inter-chain residue distance from the AlphaFold-Multimer model to further improve the accuracy. Finally, we also integrate our recently developed model quality assessment method to select the output models. The performance of DeepAssembly2 is significantly improved compared with the previous version, and it is expected to provide new insights and an effective tool for drug development, vaccine design, etc. The web server of DeepAssembly2 is freely available at https://zhanglab-bioinf.com/DeepAssembly/.

Deep Learning-Assisted Discovery of Protein Entangling Motifs

Natural topological proteins exhibit unique properties including enhanced stability, controlled quaternary structures, and dynamic switching properties, highlighting topology as a unique dimension in protein engineering. Although artificial design and synthesis of topological proteins have achieved certain success, their diversity and complexity remain rather limited due to the scarcity of available entangling motifs essential for the construction of nontrivial protein topologies. In this work, we developed a deep-learning model to predict the entanglement features of a homodimer based solely on its amino acid sequence via the Gauss linking number matrices. The model achieved a search speed that was dozens of times faster than AlphaFold-Multimer, while maintaining comparable mean squared error. It was used to screen for entangling motifs from the genome of a hyperthermophilic archaeon. We demonstrated the effectiveness of our model by successful wet-lab synthesis of protein catenanes using two candidate entangling motifs. These findings show the great potential of our model for advancing the design and synthesis of novel topological proteins.

An outlook on structural biology after AlphaFold: tools, limits and perspectives

AlphaFold and similar groundbreaking, AI-based tools, have revolutionized the field of structural bioinformatics, with their remarkable accuracy in ab-initio protein structure prediction. This success has catalyzed the development of new software and pipelines aimed at incorporating AlphaFold's predictions, often focusing on addressing the algorithm's remaining challenges. Here, we present the current landscape of structural bioinformatics shaped by AlphaFold, and discuss how the field is dynamically responding to this revolution, with new software, methods, and pipelines. While the excitement around AI-based tools led to their widespread application, it is essential to acknowledge that their practical success hinges on their integration into established protocols within structural bioinformatics, often neglected in the context of AI-driven advancements. Indeed, user-driven intervention is still as pivotal in the structure prediction process as in complementing state-of-the-art algorithms with functional and biological knowledge.

Characterization of the host specificity of the SH3 cell wall binding domain of the staphylococcal phage 88 endolysin

Bacteriophages produce endolysins at the end of the lytic cycle, which are crucial for lysing the host cells and releasing virion progeny. This lytic feature allows endolysins to act as effective antimicrobial alternatives when applied exogenously. Staphylococcal endolysins typically possess a modular structure with one or two enzymatically active N-terminal domains (EADs) and a C-terminal cell wall binding domain (CBD). The EADs degrade the peptidoglycan layer, leading to bacterial lysis, while the CBD binds to the specific host cell wall, and therefore, influences specificity of the endolysin. This study aimed to alter and characterize the host specificity of the CBD by exploring the impact of amino acid modifications within the CBD of a staphylococcal endolysin, Endo88. Endo88 was able to lyse Staphylococcus spp. and Enterococcus faecalis. However, despite attempts to mutate amino acids hypothesized for binding with cell wall components, the host-range was not affected but the lytic activity was severely reduced instead, although no alterations were performed on the EADs (Cysteine, histidine-dependent aminohydrolases/peptidases domain and Amidase domain). Further investigations of the CBD alone (Src homology3 domain, SH3) without the EADs suggested that binding and lytic activity may not be correlated in some cases since Endo88 and its mutants could lyse Staphylococcus epidermidis well but no binding activity was observed in the flow cytometry analysis. Molecular docking was used to gain insights on the observations for the binding and lytic activity which may help future strategies in designing enhanced engineered endolysins.

Mass spectrometry-complemented molecular modeling predicts the interaction interface for a camelid single-domain antibody targeting the Plasmodium falciparum circumsporozoite protein's C-terminal domain

Background

Bioanalytical methods that enable rapid and high-detail characterization of binding specificities and strengths of protein complexes with low sample consumption are highly desired. The interaction between a camelid single domain antibody (sdAbCSP1) and its target antigen (PfCSP-Cext) was selected as a model system to provide proof-of-principle for the here described methodology.

Research design and methods

The structure of the sdAbCSP1 - PfCSP-Cext complex was modeled using AlphaFold2. The recombinantly expressed proteins, sdAbCSP1, PfCSP-Cext, and the sdAbCSP1 - PfCSP-Cext complex, were subjected to limited proteolysis and mass spectrometric peptide analysis. ITEM MS (Intact Transition Epitope Mapping Mass Spectrometry) and ITC (Isothermal Titration Calorimetry) were applied to determine stoichiometry and binding strength.

Results

The paratope of sdAbCSP1 mainly consists of its CDR3 (aa100-118). PfCSP-Cext's epitope is assembled from its α-helix (aa40-52) and opposing loop (aa83-90). PfCSP-Cext's GluC cleavage sites E46 and E58 were shielded by complex formation, confirming the predicted epitope. Likewise, sdAbCSP1's tryptic cleavage sites R105 and R108 were shielded by complex formation, confirming the predicted paratope. ITEM MS determined the 1:1 stoichiometry and the high complex binding strength, exemplified by the gas phase dissociation reaction enthalpy of 50.2 kJ/mol. The in-solution complex dissociation constant is 5 × 10-10 M.

Conclusions

Combining AlphaFold2 modeling with mass spectrometry/limited proteolysis generated a trustworthy model for the sdAbCSP1 - PfCSP-Cext complex interaction interface.

Computational tools to predict context-specific protein complexes

Interactions between thousands of proteins define cells' protein-protein interaction (PPI) network. Some of these interactions lead to the formation of protein complexes. It is challenging to identify a protein complex in a haystack of protein-protein interactions, and it is even more difficult to predict all protein complexes of the complexome. Simulations and machine learning approaches try to crack these problems by looking at the PPI network or predicted protein structures. Clustering of PPI networks led to the first protein complex predictions, while most recently, atomistic models of protein complexes and deep-learning-based structure prediction methods have also emerged. The simulation of PPI level interactions even enables the quantitative prediction of protein complexes. These methods, the required data sources, and their potential future developments are discussed in this review.

Revolutionizing Molecular Design for Innovative Therapeutic Applications through Artificial Intelligence

The field of computational protein engineering has been transformed by recent advancements in machine learning, artificial intelligence, and molecular modeling, enabling the design of proteins with unprecedented precision and functionality. Computational methods now play a crucial role in enhancing the stability, activity, and specificity of proteins for diverse applications in biotechnology and medicine. Techniques such as deep learning, reinforcement learning, and transfer learning have dramatically improved protein structure prediction, optimization of binding affinities, and enzyme design. These innovations have streamlined the process of protein engineering by allowing the rapid generation of targeted libraries, reducing experimental sampling, and enabling the rational design of proteins with tailored properties. Furthermore, the integration of computational approaches with high-throughput experimental techniques has facilitated the development of multifunctional proteins and novel therapeutics. However, challenges remain in bridging the gap between computational predictions and experimental validation and in addressing ethical concerns related to AI-driven protein design. This review provides a comprehensive overview of the current state and future directions of computational methods in protein engineering, emphasizing their transformative potential in creating next-generation biologics and advancing synthetic biology.

Unveiling the evolution of policies for enhancing protein structure predictions: A comprehensive analysis

Predicting protein structure is both fascinating and formidable, playing a crucial role in structure-based drug discovery and unraveling diseases with elusive origins. The Critical Assessment of Protein Structure Prediction (CASP) serves as a biannual battleground where global scientists converge to untangle the intricate relationships within amino acid chains. Two primary methods, Template-Based Modeling (TBM) and Template-Free (TF) strategies, dominate protein structure prediction. The trend has shifted towards Template-Free predictions due to their broader sequence coverage with fewer templates. The predictive process can be broadly classified into contact map, binned-distance, and real-valued distance predictions, each with distinctive strengths and limitations manifested through tailored loss functions. We have also introduced revolutionary end-to-end, and all-atom diffusion-based techniques that have transformed protein structure predictions. Recent advancements in deep learning techniques have significantly improved prediction accuracy, although the effectiveness is contingent upon the quality of input features derived from natural bio-physiochemical attributes and Multiple Sequence Alignments (MSA). Hence, the generation of high-quality MSA data holds paramount importance in harnessing informative input features for enhanced prediction outcomes. Remarkable successes have been achieved in protein structure prediction accuracy, however not enough for what structural knowledge was intended to, which implies need for development in some other aspects of the predictions. In this regard, scientists have opened other frontiers for protein structural prediction. The utilization of subsampling in multiple sequence alignment (MSA) and protein language modeling appears to be particularly promising in enhancing the accuracy and efficiency of predictions, ultimately aiding in drug discovery efforts. The exploration of predicting protein complex structure also opens up exciting opportunities to deepen our knowledge of molecular interactions and design therapeutics that are more effective. In this article, we have discussed the vicissitudes that the scientists have gone through to improve prediction accuracy, and examined the effective policies in predicting from different aspects, including the construction of high quality MSA, providing informative input features, and progresses in deep learning approaches. We have also briefly touched upon transitioning from predicting single-chain protein structures to predicting protein complex structures. Our findings point towards promoting open research environments to support the objectives of protein structure prediction.

Multi-faceted regulation of CREB family transcription factors

cAMP response element-binding protein (CREB) is a ubiquitously expressed nuclear transcription factor, which can be constitutively activated regardless of external stimuli or be inducibly activated by external factors such as stressors, hormones, neurotransmitters, and growth factors. However, CREB controls diverse biological processes including cell growth, differentiation, proliferation, survival, apoptosis in a cell-type-specific manner. The diverse functions of CREB appear to be due to CREB-mediated differential gene expression that depends on cAMP response elements and multi-faceted regulation of CREB activity. Indeed, the transcriptional activity of CREB is controlled at several levels including alternative splicing, post-translational modification, dimerization, specific transcriptional co-activators, non-coding small RNAs, and epigenetic regulation. In this review, we present versatile regulatory modes of CREB family transcription factors and discuss their functional consequences.

Deepening insights into cholinergic agents for intraocular pressure reduction: systems genetics, molecular modeling, and in vivo perspectives

Parasympathetic activation in the anterior eye segment regulates various physiological functions. This process, mediated by muscarinic acetylcholine receptors, also impacts intraocular pressure (IOP) through the trabecular meshwork. While FDA-approved M3 muscarinic receptor (M3R) agonists exist for IOP reduction, their systemic cholinergic adverse effects pose limitations in clinical use. Therefore, advancing our understanding of the cholinergic system in the anterior segment of the eye is crucial for developing additional IOP-reducing agents with improved safety profiles. Systems genetics analyses were utilized to explore correlations between IOP and the five major muscarinic receptor subtypes. Molecular docking and dynamics simulations were applied to human M3R homology model using a comprehensive set of human M3R ligands and 1,667 FDA-approved or investigational drugs. Lead compounds from the modeling studies were then tested for their IOP-lowering abilities in mice. Systems genetics analyses unveiled positive correlations in mRNA expressions among the five major muscarinic receptor subtypes, with a negative correlation observed only in M3R with IOP. Through modeling studies, rivastigmine and edrophonium emerged as the most optimally suited cholinergic drugs for reducing IOP via a potentially distinct mechanism from pilocarpine or physostigmine. Subsequent animal studies confirmed comparable IOP reductions among rivastigmine, edrophonium, and pilocarpine, with longer durations of action for rivastigmine and edrophonium. Mild cholinergic adverse effects were observed with pilocarpine and rivastigmine but absent with edrophonium. These findings advance ocular therapeutics, suggesting a more nuanced role of the parasympathetic system in the anterior eye segment for reducing IOP than previously thought.

Apprehensions and emerging solutions in ML-based protein structure prediction

The three-dimensional structure of proteins determines their function in vital biological processes. Thus, when the structure is known, the molecular mechanism of protein function can be understood in more detail and obtained information utilized in biotechnological, diagnostics, and therapeutic applications. Over the past five years, machine learning (ML)-based modeling has pushed protein structure prediction to the next level with AlphaFold in the front line, predicting the structure for hundreds of millions of proteins. Further advances recently report promising ML-based approaches for solving remaining challenges by incorporating functionally important metals, co-factors, post-translational modifications, structural dynamics, and interdomain and multimer interactions in the structure prediction process.

Biallelic variants in CSMD1 are implicated in a neurodevelopmental disorder with intellectual disability and variable cortical malformations

CSMD1 (Cub and Sushi Multiple Domains 1) is a well-recognized regulator of the complement cascade, an important component of the innate immune response. CSMD1 is highly expressed in the central nervous system (CNS) where emergent functions of the complement pathway modulate neural development and synaptic activity. While a genetic risk factor for neuropsychiatric disorders, the role of CSMD1 in neurodevelopmental disorders is unclear. Through international variant sharing, we identified inherited biallelic CSMD1 variants in eight individuals from six families of diverse ancestry who present with global developmental delay, intellectual disability, microcephaly, and polymicrogyria. We modeled CSMD1 loss-of-function (LOF) pathogenesis in early-stage forebrain organoids differentiated from CSMD1 knockout human embryonic stem cells (hESCs). We show that CSMD1 is necessary for neuroepithelial cytoarchitecture and synchronous differentiation. In summary, we identified a critical role for CSMD1 in brain development and biallelic CSMD1 variants as the molecular basis of a previously undefined neurodevelopmental disorder.

Recent Progress of Protein Tertiary Structure Prediction

The prediction of three-dimensional (3D) protein structure from amino acid sequences has stood as a significant challenge in computational and structural bioinformatics for decades. Recently, the widespread integration of artificial intelligence (AI) algorithms has substantially expedited advancements in protein structure prediction, yielding numerous significant milestones. In particular, the end-to-end deep learning method AlphaFold2 has facilitated the rise of structure prediction performance to new heights, regularly competitive with experimental structures in the 14th Critical Assessment of Protein Structure Prediction (CASP14). To provide a comprehensive understanding and guide future research in the field of protein structure prediction for researchers, this review describes various methodologies, assessments, and databases in protein structure prediction, including traditionally used protein structure prediction methods, such as template-based modeling (TBM) and template-free modeling (FM) approaches; recently developed deep learning-based methods, such as contact/distance-guided methods, end-to-end folding methods, and protein language model (PLM)-based methods; multi-domain protein structure prediction methods; the CASP experiments and related assessments; and the recently released AlphaFold Protein Structure Database (AlphaFold DB). We discuss their advantages, disadvantages, and application scopes, aiming to provide researchers with insights through which to understand the limitations, contexts, and effective selections of protein structure prediction methods in protein-related fields.

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.