Proteome-scale analysis of phase-separated proteins in immunofluorescence images

Machine learning predictor PSPire screens for phase-separating proteins lacking intrinsically disordered regions

The burgeoning comprehension of protein phase separation (PS) has ushered in a wealth of bioinformatics tools for the prediction of phase-separating proteins (PSPs). These tools often skew towards PSPs with a high content of intrinsically disordered regions (IDRs), thus frequently undervaluing potential PSPs without IDRs. Nonetheless, PS is not only steered by IDRs but also by the structured modular domains and interactions that aren't necessarily reflected in amino acid sequences. In this work, we introduce PSPire, a machine learning predictor that incorporates both residue-level and structure-level features for the precise prediction of PSPs. Compared to current PSP predictors, PSPire shows a notable improvement in identifying PSPs without IDRs, which underscores the crucial role of non-IDR, structure-based characteristics in multivalent interactions throughout the PS process. Additionally, our biological validation experiments substantiate the predictive capacity of PSPire, with 9 out of 11 chosen candidate PSPs confirmed to form condensates within cells.

PredLLPS_PSSM: a novel predictor for liquid-liquid protein separation identification based on evolutionary information and a deep neural network

The formation of biomolecular condensates by liquid-liquid phase separation (LLPS) has become a universal mechanism for spatiotemporal coordination of biological activities in cells and has been widely observed to directly regulate the key cellular processes involved in cancer cell pathology. However, the complexity of protein sequences and the diversity of conformations are inherently disordered, which poses great challenges for LLPS protein calculations and experimental research. Herein, we proposed a novel predictor named PredLLPS_PSSM for LLPS protein identification based only on sequence evolution information. Because finding real and reliable samples is the cornerstone of building predictors, we collected anew and collated the LLPS proteins from the latest versions of three databases. By comparing the performance of the position-specific score matrix (PSSM) and word embedding, PredLLPS_PSSM combined PSSM-based information and two deep learning frameworks. Independent tests using three existing independent test datasets and two newly constructed independent test datasets demonstrated the superiority of PredLLPS_PSSM compared with state-of-the-art methods. Furthermore, we tested PredLLPS_PSSM on nine experimentally identified LLPS proteins from three insects that were not included in any of the databases. In addition, the powerful Shapley Additive exPlanation algorithm and heatmap were applied to find the most critical amino acids relevant to LLPS.

Sequence variations of phase-separating proteins and resources for studying biomolecular condensates

Phase separation (PS) is an important mechanism underlying the formation of biomolecular condensates. Physiological condensates are associated with numerous biological processes, such as transcription, immunity, signaling, and synaptic transmission. Changes in particular amino acids or segments can disturb the protein's phase behavior and interactions with other biomolecules in condensates. It is thus presumed that variations in the phase-separating-prone domains can significantly impact the properties and functions of condensates. The dysfunction of condensates contributes to a number of pathological processes. Pharmacological perturbation of these condensates is proposed as a promising way to restore physiological states. In this review, we characterize the variations observed in PS proteins that lead to aberrant biomolecular compartmentalization. We also showcase recent advancements in bioinformatics of membraneless organelles (MLOs), focusing on available databases useful for screening PS proteins and describing endogenous condensates, guiding researchers to seek the underlying pathogenic mechanisms of biomolecular condensates.

A model for identification of potential phase-separated proteins based on protein sequence, structure and cellular distribution

The cells are like a highly industrialized and urbanized city, filled with numerous biological macromolecules and metabolites, forming a crowded environment. While, the cells have compartmentalized organelles to complete different biological processes efficiently and orderly. However, membraneless organelles are more dynamic and adaptable for transient events including signal transduction and molecular interactions. Liquid-liquid phase separation (LLPS) is a mechanism that is widespread in which macromolecules form condensates without membranes to exert biological functions in crowded environments. Due to the lack of deep understanding of phase-separated proteins, platforms exploring phase-separated proteins by high-throughput methods is lacking. Bioinformatics has its unique properties and has proven to be a great impetus in multiple fields. Here, We integrated the amino acid sequence, protein structure, and cellular localization, then developed a workflow for screening phase-separated proteins and identified a novel cell cycle-related phase separation protein, serine/arginine-rich splicing factor 2 (SRSF2). In conclusion, we developed a workflow as a useful resource for predicting phase-separated proteins based on multi-prediction tool, which has an important contribution to the further identification of phase-separated proteins and the development strategies for treating disease.

A hybrid positive unlabeled learning framework for uncovering scaffolds across human proteome by measuring the propensity to drive phase separation

Scaffold proteins drive liquid-liquid phase separation (LLPS) to form biomolecular condensates and organize various biochemical reactions in cells. Dysregulation of scaffolds can lead to aberrant condensate assembly and various complex diseases. However, bioinformatics predictors dedicated to scaffolds are still lacking and their development suffers from an extreme imbalance between limited experimentally identified scaffolds and unlabeled candidates. Here, using the joint distribution of hybrid multimodal features, we implemented a positive unlabeled (PU) learning-based framework named PULPS that combined ProbTagging and penalty logistic regression (PLR) to profile the propensity of scaffolds. PULPS achieved the best AUC of 0.8353 and showed an area under the lift curve (AUL) of 0.8339 as an estimation of true performance. Upon reviewing recent experimentally verified scaffolds, we performed a partial recovery with 2.85% increase in AUL from 0.8339 to 0.8577. In comparison, PULPS showed a 45.7% improvement in AUL compared with PLR, whereas 8.2% superiority over other existing tools. Our study first proved that PU learning is more suitable for scaffold prediction and demonstrated the widespread existence of phase separation states. This profile also uncovered potential scaffolds that co-drive LLPS in the human proteome and generated candidates for further experiments. PULPS is free for academic research at http://pulps.zbiolab.cn.

Genetic variation associated with condensate dysregulation in disease

A multitude of cellular processes involve biomolecular condensates, which has led to the suggestion that diverse pathogenic mutations may dysregulate condensates. Although proof-of-concept studies have identified specific mutations that cause condensate dysregulation, the full scope of the pathological genetic variation that affects condensates is not yet known. Here, we comprehensively map pathogenic mutations to condensate-promoting protein features in putative condensate-forming proteins and find over 36,000 pathogenic mutations that plausibly contribute to condensate dysregulation in over 1,200 Mendelian diseases and 550 cancers. This resource captures mutations presently known to dysregulate condensates, and experimental tests confirm that additional pathological mutations do indeed affect condensate properties in cells. These findings suggest that condensate dysregulation may be a pervasive pathogenic mechanism underlying a broad spectrum of human diseases, provide a strategy to identify proteins and mutations involved in pathologically altered condensates, and serve as a foundation for mechanistic insights into disease and therapeutic hypotheses.

Screening membraneless organelle participants with machine-learning models that integrate multimodal features

Protein self-assembly is one of the formation mechanisms of biomolecular condensates. However, most phase-separating systems (PS) demand multiple partners in biological conditions. In this study, we divided PS proteins into two groups according to the mechanism by which they undergo PS: PS-Self proteins can self-assemble spontaneously to form droplets, while PS-Part proteins interact with partners to undergo PS. Analysis of the amino acid composition revealed differences in the sequence pattern between the two protein groups. Existing PS predictors, when evaluated on two test protein sets, preferentially predicted self-assembling proteins. Thus, a comprehensive predictor is required. Herein, we propose that properties other than sequence composition can provide crucial information in screening PS proteins. By incorporating phosphorylation frequencies and immunofluorescence image-based droplet-forming propensity with other PS-related features, we built two independent machine-learning models to separately predict the two protein categories. Results of independent testing suggested the superiority of integrating multimodal features. We performed experimental verification on the top-scored proteins DHX9, K_i-67, and NIFK. Their PS behavior in vitro revealed the effectiveness of our models in PS prediction. Further validation on the proteome of membraneless organelles confirmed the ability of our models to identify PS-Part proteins. We implemented a web server named PhaSePred (http://predict.phasep.pro/) that incorporates our two models together with representative PS predictors. PhaSePred displays proteome-level quantiles of different features, thus profiling PS propensity and providing crucial information for identification of candidate proteins.

Emerging fluorescence tools for the study of proteostasis in cells

Understanding how cells maintain the functional proteome and respond to stress conditions is critical for deciphering molecular pathogenesis and developing treatments for conditions such as neurodegenerative diseases. Efforts towards finer quantification of cellular proteostasis machinery efficiency, phase transitions and local environment changes remain a priority. Herein, we describe recent developments in fluorescence-based strategy and methodology, building on the experimental toolkit, for the study of proteostasis (protein homeostasis) in cells. We hope this review can assist in bridging gaps between a multitude of research disciplines and promote interdisciplinary collaboration to address the crucial topic of proteostasis.

On the potential of machine learning to examine the relationship between sequence, structure, dynamics and function of intrinsically disordered proteins

Intrinsically disordered proteins (IDPs) constitute a broad set of proteins with few uniting and many diverging properties. IDPs-and intrinsically disordered regions (IDRs) interspersed between folded domains-are generally characterized as having no persistent tertiary structure; instead they interconvert between a large number of different and often expanded structures. IDPs and IDRs are involved in an enormously wide range of biological functions and reveal novel mechanisms of interactions, and while they defy the common structure-function paradigm of folded proteins, their structural preferences and dynamics are important for their function. We here discuss open questions in the field of IDPs and IDRs, focusing on areas where machine learning and other computational methods play a role. We discuss computational methods aimed to predict transiently formed local and long-range structure, including methods for integrative structural biology. We discuss the many different ways in which IDPs and IDRs can bind to other molecules, both via short linear motifs, as well as in the formation of larger dynamic complexes such as biomolecular condensates. We discuss how experiments are providing insight into such complexes and may enable more accurate predictions. Finally, we discuss the role of IDPs in disease and how new methods are needed to interpret the mechanistic effects of genomic variants in IDPs.

Computational Screening of Phase-separating Proteins

Phase separation is an important mechanism that mediates the compartmentalization of proteins in cells. Proteins that can undergo phase separation in cells share certain typical sequence features, like intrinsically disordered regions (IDRs) and multiple modular domains. Sequence-based analysis tools are commonly used in the screening of these proteins. However, current phase separation predictors are mostly designed for IDR-containing proteins, thus inevitably overlook the phase-separating proteins with relatively low IDR content. Features other than amino acid sequence could provide crucial information for identifying possible phase-separating proteins: protein–protein interaction (PPI) networks show multivalent interactions that underlie phase separation process; post-translational modifications (PTMs) are crucial in the regulation of phase separation behavior; spherical structures revealed in immunofluorescence (IF)images indicate condensed droplets formed by phase-separating proteins, distinguishing these proteins from non-phase-separating proteins. Here, we summarize the sequence-based tools for predicting phase-separating proteins and highlight the importance of incorporating PPIs, PTMs, and IF images into phase separation prediction in future studies.

Computational resources for identifying and describing proteins driving liquid-liquid phase separation

One of the most intriguing fields emerging in current molecular biology is the study of membraneless organelles formed via liquid–liquid phase separation (LLPS). These organelles perform crucial functions in cell regulation and signalling, and recent years have also brought about the understanding of the molecular mechanism of their formation. The LLPS field is continuously developing and optimizing dedicated in vitro and in vivo methods to identify and characterize these non-stoichiometric molecular condensates and the proteins able to drive or contribute to LLPS. Building on these observations, several computational tools and resources have emerged in parallel to serve as platforms for the collection, annotation and prediction of membraneless organelle-linked proteins. In this survey, we showcase recent advancements in LLPS bioinformatics, focusing on (i) available databases and ontologies that are necessary to describe the studied phenomena and the experimental results in an unambiguous way and (ii) prediction methods to assess the potential LLPS involvement of proteins. Through hands-on application of these resources on example proteins and representative datasets, we give a practical guide to show how they can be used in conjunction to provide in silico information on LLPS.