Prediction of disordered regions in proteins with recurrent Neural Networks and protein dynamics

In silico identification of archaeal DNA-binding proteins

MOTIVATION

The rapid advancement of next-generation sequencing technologies has generated an immense volume of genetic data. However, these data are unevenly distributed, with well-studied organisms being disproportionately represented, while other organisms, such as from archaea, remain significantly underexplored. The study of archaea is particularly challenging due to the extreme environments they inhabit and the difficulties associated with culturing them in the laboratory. Despite these challenges, archaea likely represent a crucial evolutionary link between eukaryotic and prokaryotic organisms, and their investigation could shed light on the early stages of life on Earth. Yet, a significant portion of archaeal proteins are annotated with limited or inaccurate information. Among the various classes of archaeal proteins, DNA-binding proteins are of particular importance. While they represent a large portion of every known proteome, their identification in archaea is complicated by the substantial evolutionary divergence between archaeal and the other better studied organisms.

RESULTS

To address the challenges of identifying DNA-binding proteins in archaea, we developed Xenusia, a neural network-based tool capable of screening entire archaeal proteomes to identify DNA-binding proteins. Xenusia has proven effective across diverse datasets, including metagenomics data, successfully identifying novel DNA-binding proteins, with experimental validation of its predictions.

AVAILABILITY AND IMPLEMENTATION

Xenusia is available as a PyPI package, with source code accessible at https://github.com/grogdrinker/xenusia, and as a Google Colab web server application at xenusia.ipynb.

DisorderUnetLM: Validating ProteinUnet for efficient protein intrinsic disorder prediction

The prediction of intrinsic disorder regions has significant implications for understanding protein functions and dynamics. It can help to discover novel protein-protein interactions essential for designing new drugs and enzymes. Recently, a new generation of predictors based on protein language models (pLMs) is emerging. These algorithms reach state-of-the-art accuracy without calculating time-consuming multiple sequence alignments (MSAs). This article introduces the new DisorderUnetLM disorder predictor, which builds upon the idea of ProteinUnet. It uses the Attention U-Net convolutional network and incorporates features from the ProtTrans pLM. DisorderUnetLM achieves top results in the direct comparison with recent predictors exploiting MSAs and pLMs. Moreover, among 43 predictors on the latest CAID-2 benchmark, it ranks 1st for the NOX subset in terms of the ROC-AUC metric (0.844) and 2nd for the AP metric (0.596). For the CAID-2 PDB subset, it ranks in the top 10 (ROC-AUC of 0.924 and AP of 0.862). The code and model are publicly available and fully reproducible at doi.org/10.24433/CO.7350682.v1.

Versatile roles of disordered transcription factor effector domains in transcriptional regulation

Transcription, a crucial step in the regulation of gene expression, is tightly controlled and involves several essential processes, such as chromatin organization, recognition of the specific genomic sequences, DNA binding, and ultimately recruiting the transcriptional machinery to facilitate transcript synthesis. At the center of this regulation are transcription factors (TFs), which comprise at least one DNA-binding domain (DBD) and an effector domain (ED). Although the structure and function of DBDs have been well studied, our knowledge of the structure and function of effector domains is limited. EDs are of particular importance in generating distinct transcriptional responses between protein members of the same TF family that have similar DBDs and specificities. The study of transcriptional activity conferred by effector domains has traditionally been conducted through examining protein-protein interactions. However, recent research has uncovered alternative mechanisms by which EDs regulate gene expression, such as the formation of condensates that increase the local concentration of transcription factors, cofactors, and coregulated genes, as well as DNA binding. Here, we provide a comprehensive overview of the known roles of transcription factor EDs, with a specific focus on disordered regions. Additionally, we emphasize the significance of intrinsically disordered regions (IDRs) during transcriptional regulation. We examine the mechanisms underlying the establishment and maintenance of transcriptional specificity through the structural properties of predominantly disordered EDs. We then provide a comprehensive overview of the current understanding of these domains, including their physical and chemical characteristics, as well as their functional roles.

Recent Advances in Computational Prediction of Secondary and Supersecondary Structures from Protein Sequences

The secondary structures (SSs) and supersecondary structures (SSSs) underlie the three-dimensional structure of proteins. Prediction of the SSs and SSSs from protein sequences enjoys high levels of use and finds numerous applications in the development of a broad range of other bioinformatics tools. Numerous sequence-based predictors of SS and SSS were developed and published in recent years. We survey and analyze 45 SS predictors that were released since 2018, focusing on their inputs, predictive models, scope of their prediction, and availability. We also review 32 sequence-based SSS predictors, which primarily focus on predicting coiled coils and beta-hairpins and which include five methods that were published since 2018. Substantial majority of these predictive tools rely on machine learning models, including a variety of deep neural network architectures. They also frequently use evolutionary sequence profiles. We discuss details of several modern SS and SSS predictors that are currently available to the users and which were published in higher impact venues.

Taxonomy-specific assessment of intrinsic disorder predictions at residue and region levels in higher eukaryotes, protists, archaea, bacteria and viruses

Intrinsic disorder predictors were evaluated in several studies including the two large CAID experiments. However, these studies are biased towards eukaryotic proteins and focus primarily on the residue-level predictions. We provide first-of-its-kind assessment that comprehensively covers the taxonomy and evaluates predictions at the residue and disordered region levels. We curate a benchmark dataset that uniformly covers eukaryotic, archaeal, bacterial, and viral proteins. We find that predictive performance differs substantially across taxonomy, where viruses are predicted most accurately, followed by protists and higher eukaryotes, while bacterial and archaeal proteins suffer lower levels of accuracy. These trends are consistent across predictors. We also find that current tools, except for flDPnn, struggle with reproducing native distributions of the numbers and sizes of the disordered regions. Moreover, analysis of two variants of disorder predictions derived from the AlphaFold2 predicted structures reveals that they produce accurate residue-level propensities for archaea, bacteria and protists. However, they underperform for higher eukaryotes and generally struggle to accurately identify disordered regions. Our results motivate development of new predictors that target bacteria and archaea and which produce accurate results at both residue and region levels. We also stress the need to include the region-level assessments in future assessments.

Intrinsic disorder and salt-dependent conformational changes of the N-terminal region of TFIP11 splicing factor

Tuftelin Interacting Protein 11 (TFIP11) was identified as a critical human spliceosome assembly regulator, interacting with multiple proteins and localising in membrane-less organelles. However, a lack of structural information on TFIP11 limits the rationalisation of its biological role. TFIP11 is predicted as an intrinsically disordered protein (IDP), and more specifically concerning its N-terminal (N-TER) region. IDPs lack a defined tertiary structure, existing as a dynamic conformational ensemble, favouring protein-protein and protein-RNA interactions. IDPs are involved in liquid-liquid phase separation (LLPS), driving the formation of subnuclear compartments. Combining disorder prediction, molecular dynamics, and spectroscopy methods, this contribution shows the first evidence TFIP11 N-TER is a polyampholytic IDP, exhibiting a structural duality with the coexistence of ordered and disordered assemblies, depending on the ionic strength. Increasing the salt concentration enhances the protein conformational flexibility, presenting a more globule-like shape, and a fuzzier unstructured arrangement that could favour LLPS and protein-RNA interaction. The most charged and hydrophilic regions are the most impacted, including the G-Patch domain essential to TFIP11 function. This study gives a better understanding of the salt-dependent conformational behaviour of the N-TER TFIP11, supporting the hypothesis of the formation of different types of protein assembly, in line with its multiple biological roles.

VUS next in rare diseases? Deciphering genetic determinants of biomolecular condensation

The diagnostic odysseys for rare disease patients are getting shorter as next-generation sequencing becomes more widespread. However, the complex genetic diversity and factors influencing expressivity continue to challenge accurate diagnosis, leaving more than 50% of genetic variants categorized as variants of uncertain significance.Genomic expression intricately hinges on localized interactions among its products. Conventional variant prioritization, biased towards known disease genes and the structure-function paradigm, overlooks the potential impact of variants shaping the composition, location, size, and properties of biomolecular condensates, genuine membraneless organelles swiftly sensing and responding to environmental changes, and modulating expressivity.To address this complexity, we propose to focus on the nexus of genetic variants within biomolecular condensates determinants. Scrutinizing variant effects in these membraneless organelles could refine prioritization, enhance diagnostics, and unveil the molecular underpinnings of rare diseases. Integrating comprehensive genome sequencing, transcriptomics, and computational models can unravel variant pathogenicity and disease mechanisms, enabling precision medicine. This paper presents the rationale driving our proposal and describes a protocol to implement this approach. By fusing state-of-the-art knowledge and methodologies into the clinical practice, we aim to redefine rare diseases diagnosis, leveraging the power of scientific advancement for more informed medical decisions.

flDPnn2: Accurate and Fast Predictor of Intrinsic Disorder in Proteins

Prediction of the intrinsic disorder in protein sequences is an active research area, with well over 100 predictors that were released to date. These efforts are motivated by the functional importance and high levels of abundance of intrinsic disorder, combined with relatively low amounts of experimental annotations. The disorder predictors are periodically evaluated by independent assessors in the Critical Assessment of protein Intrinsic Disorder prediction (CAID) experiments. The recently completed CAID2 experiment assessed close to 40 state-of-the-art methods demonstrating that some of them produce accurate results. In particular, flDPnn2 method, which is the successor of flDPnn that performed well in the CAID1 experiment, secured the overall most accurate results on the Disorder-NOX dataset in CAID2. flDPnn2 implements a number of improvements when compared to its predecessor including changes to the inputs, increased size of the deep network model that we retrained on a larger training set, and addition of an alignment module. Using results from CAID2, we show that flDPnn2 produces accurate predictions very quickly, modestly improving over the accuracy of flDPnn and reducing the runtime by half, to about 27 s per protein. flDPnn2 is freely available as a convenient web server at http://biomine.cs.vcu.edu/servers/flDPnn2/.

Data-driven probabilistic definition of the low energy conformational states of protein residues

Protein dynamics and related conformational changes are essential for their function but difficult to characterise and interpret. Amino acids in a protein behave according to their local energy landscape, which is determined by their local structural context and environmental conditions. The lowest energy state for a given residue can correspond to sharply defined conformations, e.g. in a stable helix, or can cover a wide range of conformations, e.g. in intrinsically disordered regions. A good definition of such low energy states is therefore important to describe the behaviour of a residue and how it changes with its environment. We propose a data-driven probabilistic definition of six low energy conformational states typically accessible for amino acid residues in proteins. This definition is based on solution NMR information of 1322 proteins through a combined analysis of structure ensembles with interpreted chemical shifts. We further introduce a conformational state variability parameter that captures, based on an ensemble of protein structures from molecular dynamics or other methods, how often a residue moves between these conformational states. The approach enables a different perspective on the local conformational behaviour of proteins that is complementary to their static interpretation from single structure models.

DR-BERT: A protein language model to annotate disordered regions

Despite their lack of a rigid structure, intrinsically disordered regions (IDRs) in proteins play important roles in cellular functions, including mediating protein-protein interactions. Therefore, it is important to computationally annotate IDRs with high accuracy. In this study, we present Disordered Region prediction using Bidirectional Encoder Representations from Transformers (DR-BERT), a compact protein language model. Unlike most popular tools, DR-BERT is pretrained on unannotated proteins and trained to predict IDRs without relying on explicit evolutionary or biophysical data. Despite this, DR-BERT demonstrates significant improvement over existing methods on the Critical Assessment of protein Intrinsic Disorder (CAID) evaluation dataset and outperforms competitors on two out of four test cases in the CAID 2 dataset, while maintaining competitiveness in the others. This performance is due to the information learned during pretraining and DR-BERT's ability to use contextual information.

Overview of AlphaFold2 and breakthroughs in overcoming its limitations

Predicting three-dimensional (3D) protein structures has been challenging for decades. The emergence of AlphaFold2 (AF2), a deep learning-based machine learning method developed by DeepMind, became a game changer in the protein folding community. AF2 can predict a protein's three-dimensional structure with high confidence based on its amino acid sequence. Accurate prediction of protein structures can dramatically accelerate our understanding of biological mechanisms and provide a solid foundation for reliable drug design. Although AF2 breaks through the barriers in predicting protein structures, many rooms remain to be further studied. This review provides a brief historical overview of the development of protein structure prediction, covering template-based, template-free, and machine learning-based methods. In addition to reviewing the potential benefits (Pros) and considerations (Cons) of using AF2, this review summarizes the diverse applications, including protein structure predictions, dynamic changes, point mutation, integration of language model and experimental data, protein complex, and protein-peptide interaction. It underscores recent advancements in efficiency, reliability, and broad application of AF2. This comprehensive review offers valuable insights into the applications of AF2 and AF2-inspired AI methods in structural biology and its potential for clinically significant drug target discovery.

A bipartite NLS motif mediates the nuclear import of Drosophila moesin

The ERM protein family, which consists of three closely related proteins in vertebrates, ezrin, radixin, and moesin (ERM), is an ancient and important group of cytoplasmic actin-binding and organizing proteins. With their FERM domain, ERMs bind various transmembrane proteins and anchor them to the actin cortex through their C-terminal F-actin binding domain, thus they are major regulators of actin dynamics in the cell. ERMs participate in many fundamental cellular processes, such as phagocytosis, microvilli formation, T-cell activation and tumor metastasis. We have previously shown that, besides its cytoplasmic activities, the single ERM protein of Drosophila melanogaster, moesin, is also present in the cell nucleus, where it participates in gene expression and mRNA export. Here we study the mechanism by which moesin enters the nucleus. We show that the nuclear import of moesin is an NLS-mediated, active process. The nuclear localization sequence of the moesin protein is an evolutionarily highly conserved, conventional bipartite motif located on the surface of the FERM domain. Our experiments also reveal that the nuclear import of moesin does not require PIP2 binding or protein activation, and occurs in monomeric form. We propose, that the balance between the phosphorylated and non-phosphorylated protein pools determines the degree of nuclear import of moesin.

Biophysical characterization of the Plasmodium falciparum circumsporozoite protein's N-terminal domain

The circumsporozoite protein (CSP) is the main surface antigen of the Plasmodium sporozoite (SPZ) and forms the basis of the currently only licensed anti-malarial vaccine (RTS,S/AS01). CSP uniformly coats the SPZ and plays a pivotal role in its immunobiology, in both the insect and the vertebrate hosts. Although CSP's N-terminal domain (CSPN ) has been reported to play an important role in multiple CSP functions, a thorough biophysical and structural characterization of CSPN is currently lacking. Here, we present an alternative method for the recombinant production and purification of CSPN from Plasmodium falciparum (PfCSPN ), which provides pure, high-quality protein preparations with high yields. Through an interdisciplinary approach combining in-solution experimental methods and in silico analyses, we provide strong evidence that PfCSPN is an intrinsically disordered region displaying some degree of compaction.

DeepDRP: Prediction of intrinsically disordered regions based on integrated view deep learning architecture from transformer-enhanced and protein information

Intrinsic disorder in proteins, a widely distributed phenomenon in nature, is related to many crucial biological processes and various diseases. Traditional determination methods tend to be costly and labor-intensive, therefore it is desirable to seek an accurate identification method of intrinsically disordered proteins (IDPs). In this paper, we proposed a novel Deep learning model for Intrinsically Disordered Regions in Proteins named DeepDRP. DeepDRP employed an innovative TimeDistributed strategy and Bi-LSTM architecture to predict IDPs and is driven by integrated view features of PSSM, Energy-based encoding, AAindex, and transformer-enhanced embeddings including DR-BERT, OntoProtein, Prot-T5, and ESM-2. The comparison of different feature combinations indicates that the transformer-enhanced features contribute far more than traditional features to predict IDPs and ESM-2 accounts for a larger contribution in the pre-trained fusion vectors. The ablation test verified that the TimeDistributed strategy surely increased the model performance and is an efficient approach to the IDP prediction. Compared with eight state-of-the-art methods on the DISORDER723, S1, and DisProt832 datasets, the Matthews correlation coefficient of DeepDRP significantly outperformed competing methods by 4.90 % to 36.20 %, 11.80 % to 26.33 %, and 4.82 % to 13.55 %. In brief, DeepDRP is a reliable model for IDP prediction and is freely available at https://github.com/ZX-COLA/DeepDRP.

CoMemMoRFPred: Sequence-based Prediction of MemMoRFs by Combining Predictors of Intrinsic Disorder, MoRFs and Disordered Lipid-binding Regions

Molecular recognition features (MoRFs) are a commonly occurring type of intrinsically disordered regions (IDRs) that undergo disorder-to-order transition upon binding to partner molecules. We focus on recently characterized and functionally important membrane-binding MoRFs (MemMoRFs). Motivated by the lack of computational tools that predict MemMoRFs, we use a dataset of experimentally annotated MemMoRFs to conceptualize, design, evaluate and release an accurate sequence-based predictor. We rely on state-of-the-art tools that predict residues that possess key characteristics of MemMoRFs, such as intrinsic disorder, disorder-to-order transition and lipid-binding. We identify and combine results from three tools that include flDPnn for the disorder prediction, DisoLipPred for the prediction of disordered lipid-binding regions, and MoRFCHiBiLight for the prediction of disorder-to-order transitioning protein binding regions. Our empirical analysis demonstrates that combining results produced by these three methods generates accurate predictions of MemMoRFs. We also show that use of a smoothing operator produces predictions that closely mimic the number and sizes of the native MemMoRF regions. The resulting CoMemMoRFPred method is available as an easy-to-use webserver at http://biomine.cs.vcu.edu/servers/CoMemMoRFPred. This tool will aid future studies of MemMoRFs in the context of exploring their abundance, cellular functions, and roles in pathologic phenomena.

Tutorial: a guide for the selection of fast and accurate computational tools for the prediction of intrinsic disorder in proteins

Intrinsic disorder is instrumental for a wide range of protein functions, and its analysis, using computational predictions from primary structures, complements secondary and tertiary structure-based approaches. In this Tutorial, we provide an overview and comparison of 23 publicly available computational tools with complementary parameters useful for intrinsic disorder prediction, partly relying on results from the Critical Assessment of protein Intrinsic Disorder prediction experiment. We consider factors such as accuracy, runtime, availability and the need for functional insights. The selected tools are available as web servers and downloadable programs, offer state-of-the-art predictions and can be used in a high-throughput manner. We provide examples and instructions for the selected tools to illustrate practical aspects related to the submission, collection and interpretation of predictions, as well as the timing and their limitations. We highlight two predictors for intrinsically disordered proteins, flDPnn as accurate and fast and IUPred as very fast and moderately accurate, while suggesting ANCHOR2 and MoRFchibi as two of the best-performing predictors for intrinsically disordered region binding. We link these tools to additional resources, including databases of predictions and web servers that integrate multiple predictive methods. Altogether, this Tutorial provides a hands-on guide to comparatively evaluating multiple predictors, submitting and collecting their own predictions, and reading and interpreting results. It is suitable for experimentalists and computational biologists interested in accurately and conveniently identifying intrinsic disorder, facilitating the functional characterization of the rapidly growing collections of protein sequences.

Protein intrinsically disordered region prediction by combining neural architecture search and multi-objective genetic algorithm

BACKGROUND

Intrinsically disordered regions (IDRs) are widely distributed in proteins and related to many important biological functions. Accurately identifying IDRs is of great significance for protein structure and function analysis. Because the long disordered regions (LDRs) and short disordered regions (SDRs) share different characteristics, the existing predictors fail to achieve better and more stable performance on datasets with different ratios between LDRs and SDRs. There are two main reasons. First, the existing predictors construct network structures based on their own experiences such as convolutional neural network (CNN) which is used to extract the feature of neighboring residues in protein, and long short-term memory (LSTM) is used to extract the long-distance dependencies feature of protein residues. But these networks cannot capture the hidden feature associated with the length-dependent between residues. Second, many algorithms based on deep learning have been proposed but the complementarity of the existing predictors is not fully explored and used.

RESULTS

In this study, the neural architecture search (NAS) algorithm was employed to automatically construct the network structures so as to capture the hidden features in protein sequences. In order to stably predict both the LDRs and SDRs, the model constructed by NAS was combined with length-dependent models for capturing the unique features of SDRs or LDRs and general models for capturing the common features between LDRs and SDRs. A new predictor called IDP-Fusion was proposed.

CONCLUSIONS

Experimental results showed that IDP-Fusion can achieve more stable performance than the other existing predictors on independent test sets with different ratios between SDRs and LDRs.

An overview of descriptors to capture protein properties - Tools and perspectives in the context of QSAR modeling

Proteins are important ingredients in food and feed, they are the active components of many pharmaceutical products, and they are necessary, in the form of enzymes, for the success of many technical processes. However, production can be challenging, especially when using heterologous host cells such as bacteria to express and assemble recombinant mammalian proteins. The manufacturability of proteins can be hindered by low solubility, a tendency to aggregate, or inefficient purification. Tools such as in silico protein engineering and models that predict separation criteria can overcome these issues but usually require the complex shape and surface properties of proteins to be represented by a small number of quantitative numeric values known as descriptors, as similarly used to capture the features of small molecules. Here, we review the current status of protein descriptors, especially for application in quantitative structure activity relationship (QSAR) models. First, we describe the complexity of proteins and the properties that descriptors must accommodate. Then we introduce descriptors of shape and surface properties that quantify the global and local features of proteins. Finally, we highlight the current limitations of protein descriptors and propose strategies for the derivation of novel protein descriptors that are more informative.

A sequence-based foldability score combined with AlphaFold2 predictions to disentangle the protein order/disorder continuum

Order and disorder govern protein functions, but there is a great diversity in disorder, from regions that are-and stay-fully disordered to conditional order. This diversity is still difficult to decipher even though it is encoded in the amino acid sequences. Here, we developed an analytic Python package, named pyHCA, to estimate the foldability of a protein segment from the only information of its amino acid sequence and based on a measure of its density in regular secondary structures associated with hydrophobic clusters, as defined by the hydrophobic cluster analysis (HCA) approach. The tool was designed by optimizing the separation between foldable segments from databases of disorder (DisProt) and order (SCOPe [soluble domains] and OPM [transmembrane domains]). It allows to specify the ratio between order, embodied by regular secondary structures (either participating in the hydrophobic core of well-folded 3D structures or conditionally formed in intrinsically disordered regions) and disorder. We illustrated the relevance of pyHCA with several examples and applied it to the sequences of the proteomes of 21 species ranging from prokaryotes and archaea to unicellular and multicellular eukaryotes, for which structure models are provided in the AlphaFold protein structure database. Cases of low-confidence scores related to disorder were distinguished from those of sequences that we identified as foldable but are still excluded from accurate modeling by AlphaFold2 due to a lack of sequence homologs or to compositional biases. Overall, our approach is complementary to AlphaFold2, providing guides to map structural innovations through evolutionary processes, at proteome and gene scales.

Computational Prediction of Protein Intrinsically Disordered Region Related Interactions and Functions

Intrinsically Disordered Proteins (IDPs) and Regions (IDRs) exist widely. Although without well-defined structures, they participate in many important biological processes. In addition, they are also widely related to human diseases and have become potential targets in drug discovery. However, there is a big gap between the experimental annotations related to IDPs/IDRs and their actual number. In recent decades, the computational methods related to IDPs/IDRs have been developed vigorously, including predicting IDPs/IDRs, the binding modes of IDPs/IDRs, the binding sites of IDPs/IDRs, and the molecular functions of IDPs/IDRs according to different tasks. In view of the correlation between these predictors, we have reviewed these prediction methods uniformly for the first time, summarized their computational methods and predictive performance, and discussed some problems and perspectives.

Protein Function Analysis through Machine Learning

Machine learning (ML) has been an important arsenal in computational biology used to elucidate protein function for decades. With the recent burgeoning of novel ML methods and applications, new ML approaches have been incorporated into many areas of computational biology dealing with protein function. We examine how ML has been integrated into a wide range of computational models to improve prediction accuracy and gain a better understanding of protein function. The applications discussed are protein structure prediction, protein engineering using sequence modifications to achieve stability and druggability characteristics, molecular docking in terms of protein-ligand binding, including allosteric effects, protein-protein interactions and protein-centric drug discovery. To quantify the mechanisms underlying protein function, a holistic approach that takes structure, flexibility, stability, and dynamics into account is required, as these aspects become inseparable through their interdependence. Another key component of protein function is conformational dynamics, which often manifest as protein kinetics. Computational methods that use ML to generate representative conformational ensembles and quantify differences in conformational ensembles important for function are included in this review. Future opportunities are highlighted for each of these topics.

Challenges in describing the conformation and dynamics of proteins with ambiguous behavior

Traditionally, our understanding of how proteins operate and how evolution shapes them is based on two main data sources: the overall protein fold and the protein amino acid sequence. However, a significant part of the proteome shows highly dynamic and/or structurally ambiguous behavior, which cannot be correctly represented by the traditional fixed set of static coordinates. Representing such protein behaviors remains challenging and necessarily involves a complex interpretation of conformational states, including probabilistic descriptions. Relating protein dynamics and multiple conformations to their function as well as their physiological context (e.g., post-translational modifications and subcellular localization), therefore, remains elusive for much of the proteome, with studies to investigate the effect of protein dynamics relying heavily on computational models. We here investigate the possibility of delineating three classes of protein conformational behavior: order, disorder, and ambiguity. These definitions are explored based on three different datasets, using interpretable machine learning from a set of features, from AlphaFold2 to sequence-based predictions, to understand the overlap and differences between these datasets. This forms the basis for a discussion on the current limitations in describing the behavior of dynamic and ambiguous proteins.

Panoramic Perspective on Human Phosphosites

Protein phosphorylation is the most common reversible post-translational modification of proteins and is key in the regulation of many cellular processes. Due to this importance, phosphorylation is extensively studied, resulting in the availability of a large amount of mass spectrometry-based phospho-proteomics data. Here, we leverage the information in these large-scale phospho-proteomics data sets, as contained in Scop3P, to analyze and characterize proteome-wide protein phosphorylation sites (P-sites). First, we set out to differentiate correctly observed P-sites from false-positive sites using five complementary site properties. We then describe the context of these P-sites in terms of the protein structure, solvent accessibility, structural transitions and disorder, and biophysical properties. We also investigate the relative prevalence of disease-linked mutations on and around P-sites. Moreover, we assess the structural dynamics of P-sites in their phosphorylated and unphosphorylated states. As a result, we show how large-scale reprocessing of available proteomics experiments can enable a more reliable view on proteome-wide P-sites. Furthermore, adding the structural context of proteins around P-sites helps uncover possible conformational switches upon phosphorylation. Moreover, by placing sites in different biophysical contexts, we show the differential preference in protein dynamics at phosphorylated sites when compared to the nonphosphorylated counterparts.

Compositional Bias of Intrinsically Disordered Proteins and Regions and Their Predictions

Intrinsically disordered regions (IDRs) carry out many cellular functions and vary in length and placement in protein sequences. This diversity leads to variations in the underlying compositional biases, which were demonstrated for the short vs. long IDRs. We analyze compositional biases across four classes of disorder: fully disordered proteins; short IDRs; long IDRs; and binding IDRs. We identify three distinct biases: for the fully disordered proteins, the short IDRs and the long and binding IDRs combined. We also investigate compositional bias for putative disorder produced by leading disorder predictors and find that it is similar to the bias of the native disorder. Interestingly, the accuracy of disorder predictions across different methods is correlated with the correctness of the compositional bias of their predictions highlighting the importance of the compositional bias. The predictive quality is relatively low for the disorder classes with compositional bias that is the most different from the “generic” disorder bias, while being much higher for the classes with the most similar bias. We discover that different predictors perform best across different classes of disorder. This suggests that no single predictor is universally best and motivates the development of new architectures that combine models that target specific disorder classes.