Proteus: a random forest classifier to predict disorder-to-order transitioning binding regions in intrinsically disordered proteins

Gain and loss of the centrosomal protein taxilin-beta influences cardiac proteostasis and stress

Centrosomes localize to perinuclear foci where they serve multifunctional roles, arranging the microtubule organizing center (MTOC) and anchoring ubiquitin proteasome system (UPS) machinery, as suggested by prior studies. In mature cardiomyocytes, centrosomal proteins redistribute into a specialized perinuclear cage-like structure, and a potential centrosomal-UPS interface has not been studied, despite established roles for UPS in cardiomyopathy. In addition, there have been no reports citing cardiomyocyte UPS dysfunction upon or after manipulation of centrosomal proteins. Taxilin-beta (Txlnb), a cardiomyocyte-enriched protein, belongs to a family of centrosome adapter proteins implicated in protein quality control. We hypothesize that Txlnb is part of the perinuclear centrosomal cage and regulates proteostasis in cardiomyocytes. Herein, we show that centrosome proteins, including Txlnb, have significantly broadly dysregulated RNA expressions in failing hearts; however, Txlnb protein levels appear to be unchanged. Reanalysis of Txlnb's interactome supports its involvement in cytoskeletal, microtubule, and UPS processes, particularly centrosome-related functions. Using gain and loss of function approaches, in cells and mice, we show that Txlnb is a novel regulator of cardiac proteostasis through its influence on UPS. Overexpressing Txlnb in cardiomyocytes reduces ubiquitinated protein accumulation and enhances proteasome activity during hypertrophy. Germline Txlnb knockout in mice increases ubiquitinated protein accumulation, decreases 26Sβ5 proteasome activity, and lowers cardiac mass with aging, indicating proteasomal insufficiency and altered cardiac growth. Loss of Txlnb worsens heart phenotypes in mouse models of cardiac proteotoxicity and pressure overload. Overall, our data implicate the centrosomal protein Txlnb as a novel regulator of cardiac proteostasis, highlighting the likely presence of an understudied and important centrosome-proteasome functional connection in cardiomyocytes.

Intrinsic Disorder and Other Malleable Arsenals of Evolved Protein Multifunctionality

Microscopic evolution at the functional biomolecular level is an ongoing process. Leveraging functional and high-throughput assays, along with computational data mining, has led to a remarkable expansion of our understanding of multifunctional protein (and gene) families over the past few decades. Various molecular and intermolecular mechanisms are now known that collectively meet the cumulative multifunctional demands in higher organisms along an evolutionary path. This multitasking ability is attributed to a certain degree of intrinsic or adapted flexibility at the structure-function level. Evolutionary diversification of structure-function relationships in proteins highlights the functional importance of intrinsically disordered proteins/regions (IDPs/IDRs) which are highly dynamic biological soft matter. Multifunctionality is favorably supported by the fluid-like shapes of IDPs/IDRs, enabling them to undergo disorder-to-order transitions upon binding to different molecular partners. Other new malleable members of the protein superfamily, such as those involved in fold-switching, also undergo structural transitions. This new insight diverges from all traditional notions of functional singularity in enzyme classes and emphasizes a far more complex, multi-layered diversification of protein functionality. However, a thorough review in this line, focusing on flexibility and function-driven structural transitions related to evolved multifunctionality in proteins, is currently missing. This review attempts to address this gap while broadening the scope of multifunctionality beyond single protein sequences. It argues that protein intrinsic disorder is likely the most striking mechanism for expressing multifunctionality in proteins. A phenomenological analogy has also been drawn to illustrate the increasingly complex nature of modern digital life, driven by the need for multitasking, particularly involving media.

Leveraging machine learning models for peptide-protein interaction prediction

Peptides play a pivotal role in a wide range of biological activities through participating in up to 40% protein-protein interactions in cellular processes. They also demonstrate remarkable specificity and efficacy, making them promising candidates for drug development. However, predicting peptide-protein complexes by traditional computational approaches, such as docking and molecular dynamics simulations, still remains a challenge due to high computational cost, flexible nature of peptides, and limited structural information of peptide-protein complexes. In recent years, the surge of available biological data has given rise to the development of an increasing number of machine learning models for predicting peptide-protein interactions. These models offer efficient solutions to address the challenges associated with traditional computational approaches. Furthermore, they offer enhanced accuracy, robustness, and interpretability in their predictive outcomes. This review presents a comprehensive overview of machine learning and deep learning models that have emerged in recent years for the prediction of peptide-protein interactions.

Machine learning model of the catalytic efficiency and substrate specificity of acyl-ACP thioesterase variants generated from natural and in vitro directed evolution

Modulating the catalytic activity of acyl-ACP thioesterase (TE) is an important biotechnological target for effectively increasing flux and diversifying products of the fatty acid biosynthesis pathway. In this study, a directed evolution approach was developed to improve the fatty acid titer and fatty acid diversity produced by E. coli strains expressing variant acyl-ACP TEs. A single round of in vitro directed evolution, coupled with a high-throughput colorimetric screen, identified 26 novel acyl-ACP TE variants that convey up to a 10-fold increase in fatty acid titer, and generate altered fatty acid profiles when expressed in a bacterial host strain. These in vitro-generated variant acyl-ACP TEs, in combination with 31 previously characterized natural variants isolated from diverse phylogenetic origins, were analyzed with a random forest classifier machine learning tool. The resulting quantitative model identified 22 amino acid residues, which define important structural features that determine the catalytic efficiency and substrate specificity of acyl-ACP TE.

A Specialized Centrosome-Proteasome Axis Mediates Proteostasis and Influences Cardiac Stress through Txlnb

Background

Centrosomes localize to perinuclear foci where they serve multifunctional roles, arranging the microtubule organizing center (MTOC) and anchoring ubiquitin-proteasome system (UPS) machinery. In mature cardiomyocytes, centrosomal proteins redistribute into a specialized perinuclear cage-like structure, and a potential centrosome-UPS interface has not been studied. Taxilin-beta (Txlnb), a cardiomyocyte-enriched protein, belongs to a family of centrosome adapter proteins implicated in protein quality control. We hypothesize that Txlnb plays a key role in centrosomal-proteasomal crosstalk in cardiomyocytes.

Methods

Integrative bioinformatics assessed centrosomal gene dysregulation in failing hearts. Txlnb gain/loss-of-function studies were conducted in cultured cardiomyocytes and mice. Txlnb's role in cardiac proteotoxicity and hypertrophy was examined using CryAB-R120G mice and transverse aortic constriction (TAC), respectively. Molecular modeling investigated Txlnb structure/function.

Results

Human failing hearts show consistent dysregulation of many centrosome-associated genes, alongside UPS-related genes. Txlnb emerged as a candidate regulator of cardiomyocyte proteostasis that localizes to the perinuclear centrosomal compartment. Txlnb's interactome strongly supports its involvement in cytoskeletal, microtubule, and UPS processes, particularly centrosome-related functions. Overexpressing Txlnb in cardiomyocytes reduced ubiquitinated protein accumulation and enhanced proteasome activity during hypertrophy. Txlnb-knockout (KO) mouse hearts exhibit proteasomal insufficiency and altered cardiac growth, evidenced by ubiquitinated protein accumulation, decreased 26Sβ5 proteasome activity, and lower mass with age. In Cryab-R120G mice, Txlnb loss worsened heart failure, causing lower ejection fractions. After TAC, Txlnb-KO mice also showed reduced ejection fraction, increased heart mass, and elevated ubiquitinated protein accumulation. Investigations into the molecular mechanisms revealed that Txlnb-KO did not affect proteasomal subunit expression but led to the upregulation of Txlna and several centrosomal proteins (Cep63, Ofd1, and Tubg) suggesting altered centrosomal dynamics. Structural predictions support Txlnb's role as a specialized centrosomal-adapter protein bridging centrosomes with proteasomes, confirmed by microtubule-dependent perinuclear localization.

Conclusions

Together, these data provide initial evidence connecting Txlnb to cardiac proteostasis, hinting at the potential importance of functional bridging between specialized centrosomes and UPS in cardiomyocytes.

Leveraging Machine Learning Models for Peptide-Protein Interaction Prediction

Peptides play a pivotal role in a wide range of biological activities through participating in up to 40% protein-protein interactions in cellular processes. They also demonstrate remarkable specificity and efficacy, making them promising candidates for drug development. However, predicting peptide-protein complexes by traditional computational approaches, such as Docking and Molecular Dynamics simulations, still remains a challenge due to high computational cost, flexible nature of peptides, and limited structural information of peptide-protein complexes. In recent years, the surge of available biological data has given rise to the development of an increasing number of machine learning models for predicting peptide-protein interactions. These models offer efficient solutions to address the challenges associated with traditional computational approaches. Furthermore, they offer enhanced accuracy, robustness, and interpretability in their predictive outcomes. This review presents a comprehensive overview of machine learning and deep learning models that have emerged in recent years for the prediction of peptide-protein interactions.

Prediction of protein-protein interaction sites in intrinsically disordered proteins

Intrinsically disordered proteins (IDPs) participate in many biological processes by interacting with other proteins, including the regulation of transcription, translation, and the cell cycle. With the increasing amount of disorder sequence data available, it is thus crucial to identify the IDP binding sites for functional annotation of these proteins. Over the decades, many computational approaches have been developed to predict protein-protein binding sites of IDP (IDP-PPIS) based on protein sequence information. Moreover, there are new IDP-PPIS predictors developed every year with the rapid development of artificial intelligence. It is thus necessary to provide an up-to-date overview of these methods in this field. In this paper, we collected 30 representative predictors published recently and summarized the databases, features and algorithms. We described the procedure how the features were generated based on public data and used for the prediction of IDP-PPIS, along with the methods to generate the feature representations. All the predictors were divided into three categories: scoring functions, machine learning-based prediction, and consensus approaches. For each category, we described the details of algorithms and their performances. Hopefully, our manuscript will not only provide a full picture of the status quo of IDP binding prediction, but also a guide for selecting different methods. More importantly, it will shed light on the inspirations for future development trends and principles.

Improving peptide-protein docking with AlphaFold-Multimer using forced sampling

Protein interactions are key in vital biological processes. In many cases, particularly in regulation, this interaction is between a protein and a shorter peptide fragment. Such peptides are often part of larger disordered regions in other proteins. The flexible nature of peptides enables the rapid yet specific regulation of important functions in cells, such as their life cycle. Consequently, knowledge of the molecular details of peptide-protein interactions is crucial for understanding and altering their function, and many specialized computational methods have been developed to study them. The recent release of AlphaFold and AlphaFold-Multimer has led to a leap in accuracy for the computational modeling of proteins. In this study, the ability of AlphaFold to predict which peptides and proteins interact, as well as its accuracy in modeling the resulting interaction complexes, are benchmarked against established methods. We find that AlphaFold-Multimer predicts the structure of peptide-protein complexes with acceptable or better quality (DockQ ≥0.23) for 66 of the 112 complexes investigated-25 of which were high quality (DockQ ≥0.8). This is a massive improvement on previous methods with 23 or 47 acceptable models and only four or eight high quality models, when using energy-based docking or interaction templates, respectively. In addition, AlphaFold-Multimer can be used to predict whether a peptide and a protein will interact. At 1% false positives, AlphaFold-Multimer found 26% of the possible interactions with a precision of 85%, the best among the methods benchmarked. However, the most interesting result is the possibility of improving AlphaFold by randomly perturbing the neural network weights to force the network to sample more of the conformational space. This increases the number of acceptable models from 66 to 75 and improves the median DockQ from 0.47 to 0.55 (17%) for first ranked models. The best possible DockQ improves from 0.58 to 0.72 (24%), indicating that selecting the best possible model is still a challenge. This scheme of generating more structures with AlphaFold should be generally useful for many applications involving multiple states, flexible regions, and disorder.

Capturing a Crucial ‘Disorder-to-Order Transition’ at the Heart of the Coronavirus Molecular Pathology—Triggered by Highly Persistent, Interchangeable Salt-Bridges

The COVID-19 origin debate has greatly been influenced by genome comparison studies of late, revealing the emergence of the Furin-like cleavage site at the S1/S2 junction of the SARS-CoV-2 Spike (FLCSSpike) containing its 681PRRAR685 motif, absent in other related respiratory viruses. Being the rate-limiting (i.e., the slowest) step, the host Furin cleavage is instrumental in the abrupt increase in transmissibility in COVID-19, compared to earlier onsets of respiratory viral diseases. In such a context, the current paper entraps a ‘disorder-to-order transition’ of the FLCSSpike (concomitant to an entropy arrest) upon binding to Furin. The interaction clearly seems to be optimized for a more efficient proteolytic cleavage in SARS-CoV-2. The study further shows the formation of dynamically interchangeable and persistent networks of salt-bridges at the Spike–Furin interface in SARS-CoV-2 involving the three arginines (R682, R683, R685) of the FLCSSpike with several anionic residues (E230, E236, D259, D264, D306) coming from Furin, strategically distributed around its catalytic triad. Multiplicity and structural degeneracy of plausible salt-bridge network archetypes seem to be the other key characteristic features of the Spike–Furin binding in SARS-CoV-2, allowing the system to breathe—a trademark of protein disorder transitions. Interestingly, with respect to the homologous interaction in SARS-CoV (2002/2003) taken as a baseline, the Spike–Furin binding events, generally, in the coronavirus lineage, seems to have preference for ionic bond formation, even with a lesser number of cationic residues at their potentially polybasic FLCSSpike patches. The interaction energies are suggestive of characteristic metastabilities attributed to Spike–Furin interactions, generally to the coronavirus lineage, which appears to be favorable for proteolytic cleavages targeted at flexible protein loops. The current findings not only offer novel mechanistic insights into the coronavirus molecular pathology and evolution, but also add substantially to the existing theories of proteolytic cleavages.

Intrinsically disordered proteins identified in the aggregate proteome serve as biomarkers of neurodegeneration

A protein's structure is determined by its amino acid sequence and post-translational modifications, and provides the basis for its physiological functions. Across all organisms, roughly a third of the proteome comprises proteins that contain highly unstructured or intrinsically disordered regions. Proteins comprising or containing extensive unstructured regions are referred to as intrinsically disordered proteins (IDPs). IDPs are believed to participate in complex physiological processes through refolding of IDP regions, dependent on their binding to a diverse array of potential protein partners. They thus play critical roles in the assembly and function of protein complexes. Recent advances in experimental and computational analyses predicted multiple interacting partners for the disordered regions of proteins, implying critical roles in signal transduction and regulation of biological processes. Numerous disordered proteins are sequestered into aggregates in neurodegenerative diseases such as Alzheimer's disease (AD) where they are enriched even in serum, making them good candidates for serum biomarkers to enable early detection of AD.

InterPepRank: Assessment of Docked Peptide Conformations by a Deep Graph Network

Peptide-protein interactions between a smaller or disordered peptide stretch and a folded receptor make up a large part of all protein-protein interactions. A common approach for modeling such interactions is to exhaustively sample the conformational space by fast-Fourier-transform docking, and then refine a top percentage of decoys. Commonly, methods capable of ranking the decoys for selection fast enough for larger scale studies rely on first-principle energy terms such as electrostatics, Van der Waals forces, or on pre-calculated statistical potentials. We present InterPepRank for peptide-protein complex scoring and ranking. InterPepRank is a machine learning-based method which encodes the structure of the complex as a graph; with physical pairwise interactions as edges and evolutionary and sequence features as nodes. The graph network is trained to predict the LRMSD of decoys by using edge-conditioned graph convolutions on a large set of peptide-protein complex decoys. InterPepRank is tested on a massive independent test set with no targets sharing CATH annotation nor 30% sequence identity with any target in training or validation data. On this set, InterPepRank has a median AUC of 0.86 for finding coarse peptide-protein complexes with LRMSD < 4Å. This is an improvement compared to other state-of-the-art ranking methods that have a median AUC between 0.65 and 0.79. When included as a selection-method for selecting decoys for refinement in a previously established peptide docking pipeline, InterPepRank improves the number of medium and high quality models produced by 80% and 40%, respectively. The InterPepRank program as well as all scripts for reproducing and retraining it are available from: http://wallnerlab.org/InterPepRank.

flDPnn: Accurate intrinsic disorder prediction with putative propensities of disorder functions

Identification of intrinsic disorder in proteins relies in large part on computational predictors, which demands that their accuracy should be high. Since intrinsic disorder carries out a broad range of cellular functions, it is desirable to couple the disorder and disorder function predictions. We report a computational tool, flDPnn, that provides accurate, fast and comprehensive disorder and disorder function predictions from protein sequences. The recent Critical Assessment of protein Intrinsic Disorder prediction (CAID) experiment and results on other test datasets demonstrate that flDPnn offers accurate predictions of disorder, fully disordered proteins and four common disorder functions. These predictions are substantially better than the results of the existing disorder predictors and methods that predict functions of disorder. Ablation tests reveal that the high predictive performance stems from innovative ways used in flDPnn to derive sequence profiles and encode inputs. flDPnn's webserver is available at http://biomine.cs.vcu.edu/servers/flDPnn/.

iterb-PPse: Identification of transcriptional terminators in bacterial by incorporating nucleotide properties into PseKNC

Terminator is a DNA sequence that gives the RNA polymerase the transcriptional termination signal. Identifying terminators correctly can optimize the genome annotation, more importantly, it has considerable application value in disease diagnosis and therapies. However, accurate prediction methods are deficient and in urgent need. Therefore, we proposed a prediction method "iterb-PPse" for terminators by incorporating 47 nucleotide properties into PseKNC-Ⅰ and PseKNC-Ⅱ and utilizing Extreme Gradient Boosting to predict terminators based on Escherichia coli and Bacillus subtilis. Combing with the preceding methods, we employed three new feature extraction methods K-pwm, Base-content, Nucleotidepro to formulate raw samples. The two-step method was applied to select features. When identifying terminators based on optimized features, we compared five single models as well as 16 ensemble models. As a result, the accuracy of our method on benchmark dataset achieved 99.88%, higher than the existing state-of-the-art predictor iTerm-PseKNC in 100 times five-fold cross-validation test. Its prediction accuracy for two independent datasets reached 94.24% and 99.45% respectively. For the convenience of users, we developed a software on the basis of "iterb-PPse" with the same name. The open software and source code of "iterb-PPse" are available at https://github.com/Sarahyouzi/iterb-PPse.

Targeting Intrinsically Disordered Proteins through Dynamic Interactions

Intrinsically disordered proteins (IDPs) are over-represented in major disease pathways and have attracted significant interest in understanding if and how they may be targeted using small molecules for therapeutic purposes. While most existing studies have focused on extending the traditional structure-centric drug design strategies and emphasized exploring pre-existing structure features of IDPs for specific binding, several examples have also emerged to suggest that small molecules could achieve specificity in binding IDPs and affect their function through dynamic and transient interactions. These dynamic interactions can modulate the disordered conformational ensemble and often lead to modest compaction to shield functionally important interaction sites. Much work remains to be done on further elucidation of the molecular basis of the dynamic small molecule-IDP interaction and determining how it can be exploited for targeting IDPs in practice. These efforts will rely critically on an integrated experimental and computational framework for disordered protein ensemble characterization. In particular, exciting advances have been made in recent years in enhanced sampling techniques, Graphic Processing Unit (GPU)-computing, and protein force field optimization, which have now allowed rigorous physics-based atomistic simulations to generate reliable structure ensembles for nontrivial IDPs of modest sizes. Such de novo atomistic simulations will play crucial roles in exploring the exciting opportunity of targeting IDPs through dynamic interactions.

rawMSA: End-to-end Deep Learning using raw Multiple Sequence Alignments

In the last decades, huge efforts have been made in the bioinformatics community to develop machine learning-based methods for the prediction of structural features of proteins in the hope of answering fundamental questions about the way proteins function and their involvement in several illnesses. The recent advent of Deep Learning has renewed the interest in neural networks, with dozens of methods being developed taking advantage of these new architectures. However, most methods are still heavily based pre-processing of the input data, as well as extraction and integration of multiple hand-picked, and manually designed features. Multiple Sequence Alignments (MSA) are the most common source of information in de novo prediction methods. Deep Networks that automatically refine the MSA and extract useful features from it would be immensely powerful. In this work, we propose a new paradigm for the prediction of protein structural features called rawMSA. The core idea behind rawMSA is borrowed from the field of natural language processing to map amino acid sequences into an adaptively learned continuous space. This allows the whole MSA to be input into a Deep Network, thus rendering pre-calculated features such as sequence profiles and other features calculated from MSA obsolete. We showcased the rawMSA methodology on three different prediction problems: secondary structure, relative solvent accessibility and inter-residue contact maps. We have rigorously trained and benchmarked rawMSA on a large set of proteins and have determined that it outperforms classical methods based on position-specific scoring matrices (PSSM) when predicting secondary structure and solvent accessibility, while performing on par with methods using more pre-calculated features in the inter-residue contact map prediction category in CASP12 and CASP13. Clearly demonstrating that rawMSA represents a promising development that can pave the way for improved methods using rawMSA instead of sequence profiles to represent evolutionary information in the coming years. Availability: datasets, dataset generation code, evaluation code and models are available at: https://bitbucket.org/clami66/rawmsa.

A combined drug discovery strategy based on machine learning and molecular docking

Data mining methods based on machine learning play an increasingly important role in drug design and discovery. In the current work, eight machine learning methods including decision trees, k-Nearest neighbor, support vector machines, random forests, extremely randomized trees, AdaBoost, gradient boosting trees, and XGBoost were evaluated comprehensively through a case study of ACC inhibitor data sets. Internal and external data sets were employed for cross-validation of the eight machine learning methods. Results showed that the extremely randomized trees model performed best and was adopted as the first step of virtual screening. Together with structure-based virtual screening in the second step, this combined strategy obtained desirable results. This work indicates that the combination of machine learning methods with traditional structure-based virtual screening can effectively strengthen the ability in finding potential hits from large compound database for a given target.

Structural Perspective on Revealing and Altering Molecular Functions of Genetic Variants Linked with Diseases

Structural information of biological macromolecules is crucial and necessary to deliver predictions about the effects of mutations-whether polymorphic or deleterious (i.e., disease causing), wherein, thermodynamic parameters, namely, folding and binding free energies potentially serve as effective biomarkers. It may be emphasized that the effect of a mutation depends on various factors, including the type of protein (globular, membrane or intrinsically disordered protein) and the structural context in which it occurs. Such information may positively aid drug-design. Furthermore, due to the intrinsic plasticity of proteins, even mutations involving radical change of the structural and physico⁻chemical properties of the amino acids (native vs. mutant) can still have minimal effects on protein thermodynamics. However, if a mutation causes significant perturbation by either folding or binding free energies, it is quite likely to be deleterious. Mitigating such effects is a promising alternative to the traditional approaches of designing inhibitors. This can be done by structure-based in silico screening of small molecules for which binding to the dysfunctional protein restores its wild type thermodynamics. In this review we emphasize the effects of mutations on two important biophysical properties, stability and binding affinity, and how structures can be used for structure-based drug design to mitigate the effects of disease-causing variants on the above biophysical properties.

Decision-Tree Based Meta-Strategy Improved Accuracy of Disorder Prediction and Identified Novel Disordered Residues Inside Binding Motifs

Using computational techniques to identify intrinsically disordered residues is practical and effective in biological studies. Therefore, designing novel high-accuracy strategies is always preferable when existing strategies have a lot of room for improvement. Among many possibilities, a meta-strategy that integrates the results of multiple individual predictors has been broadly used to improve the overall performance of predictors. Nonetheless, a simple and direct integration of individual predictors may not effectively improve the performance. In this project, dual-threshold two-step significance voting and neural networks were used to integrate the predictive results of four individual predictors, including: DisEMBL, IUPred, VSL2, and ESpritz. The new meta-strategy has improved the prediction performance of intrinsically disordered residues significantly, compared to all four individual predictors and another four recently-designed predictors. The improvement was validated using five-fold cross-validation and in independent test datasets.

Inner-View of Nanomaterial Incited Protein Conformational Changes: Insights into Designable Interaction

Nanoparticle bioreactivity critically depends upon interaction between proteins and nanomaterials (NM). The formation of the "protein corona" (PC) is the effect of such nanoprotein interactions. PC has a wide usage in pharmaceuticals, drug delivery, medicine, and industrial biotechnology. Therefore, a detailed in-vitro, in-vivo, and in-silico understanding of nanoprotein interaction is fundamental and has a genuine contemporary appeal. NM surfaces can modify the protein conformation during interaction, or NMs themselves can lead to self-aggregations. Both phenomena can change the whole downstream bioreactivity of the concerned nanosystem. The main aim of this review is to understand the mechanistic view of NM-protein interaction and recapitulate the underlying physical chemistry behind the formation of such complicated macromolecular assemblies, to provide a critical overview of the different models describing NM induced structural and functional modification of proteins. The review also attempts to point out the current limitation in understanding the field and highlights the future scopes, involving a plausible proposition of how artificial intelligence could be aided to explore such systems for the prediction and directed design of the desired NM-protein interactions.

RFAmyloid: A Web Server for Predicting Amyloid Proteins

Amyloid is an insoluble fibrous protein and its mis-aggregation can lead to some diseases, such as Alzheimer’s disease and Creutzfeldt–Jakob’s disease. Therefore, the identification of amyloid is essential for the discovery and understanding of disease. We established a novel predictor called RFAmy based on random forest to identify amyloid, and it employed SVMProt 188-D feature extraction method based on protein composition and physicochemical properties and pse-in-one feature extraction method based on amino acid composition, autocorrelation pseudo acid composition, profile-based features and predicted structures features. In the ten-fold cross-validation test, RFAmy’s overall accuracy was 89.19% and F-measure was 0.891. Results were obtained by comparison experiments with other feature, classifiers, and existing methods. This shows the effectiveness of RFAmy in predicting amyloid protein. The RFAmy proposed in this paper can be accessed through the URL http://server.malab.cn/RFAmyloid/.

Deciphering RNA-Recognition Patterns of Intrinsically Disordered Proteins

Intrinsically disordered regions (IDRs) and protein (IDPs) are highly flexible owing to their lack of well-defined structures. A subset of such proteins interacts with various substrates; including RNA; frequently adopting regular structures in the final complex. In this work; we have analysed a dataset of protein–RNA complexes undergoing disorder-to-order transition (DOT) upon binding. We found that DOT regions are generally small in size (less than 3 residues) for RNA binding proteins. Like structured proteins; positively charged residues are found to interact with RNA molecules; indicating the dominance of electrostatic and cation-π interactions. However, a comparison of binding frequency shows that interface hydrophobic and aromatic residues have more interactions in only DOT regions than in a protein. Further; DOT regions have significantly higher exposure to water than their structured counterparts. Interactions of DOT regions with RNA increase the sheet formation with minor changes in helix forming residues. We have computed the interaction energy for amino acids–nucleotide pairs; which showed the preference of His–G; Asn–U and Ser–U at for the interface of DOT regions. This study provides insights to understand protein–RNA interactions and the results could also be used for developing a tool for identifying DOT regions in RNA binding proteins.

Salt-bridge networks within globular and disordered proteins: characterizing trends for designable interactions

There has been considerable debate about the contribution of salt bridges to the stabilization of protein folds, in spite of their participation in crucial protein functions. Salt bridges appear to contribute to the activity-stability trade-off within proteins by bringing high-entropy charged amino acids into close contacts during the course of their functions. The current study analyzes the modes of association of salt bridges (in terms of networks) within globular proteins and at protein-protein interfaces. While the most common and trivial type of salt bridge is the isolated salt bridge, bifurcated salt bridge appears to be a distinct salt-bridge motif having a special topology and geometry. Bifurcated salt bridges are found ubiquitously in proteins and interprotein complexes. Interesting and attractive examples presenting different modes of interaction are highlighted. Bifurcated salt bridges appear to function as molecular clips that are used to stitch together large surface contours at interacting protein interfaces. The present work also emphasizes the key role of salt-bridge-mediated interactions in the partial folding of proteins containing long stretches of disordered regions. Salt-bridge-mediated interactions seem to be pivotal to the promotion of "disorder-to-order" transitions in small disordered protein fragments and their stabilization upon binding. The results obtained in this work should help to guide efforts to elucidate the modus operandi of these partially disordered proteins, and to conceptualize how these proteins manage to maintain the required amount of disorder even in their bound forms. This work could also potentially facilitate explorations of geometrically specific designable salt bridges through the characterization of composite salt-bridge networks. Graphical abstract ᅟ.