fDETECT webserver: fast predictor of propensity for protein production, purification, and crystallization

Benchmarking protein language models for protein crystallization

The problem of protein structure determination is usually solved by X-ray crystallography. Several in silico deep learning methods have been developed to overcome the high attrition rate, cost of experiments and extensive trial-and-error settings, for predicting the crystallization propensities of proteins based on their sequences. In this work, we benchmark the power of open protein language models (PLMs) through the TRILL platform, a be-spoke framework democratizing the usage of PLMs for the task of predicting crystallization propensities of proteins. By comparing LightGBM / XGBoost classifiers built on the average embedding representations of proteins learned by different PLMs, such as ESM2, Ankh, ProtT5-XL, ProstT5, xTrimoPGLM, SaProt with the performance of state-of-the-art sequence-based methods like DeepCrystal, ATTCrys and CLPred, we identify the most effective methods for predicting crystallization outcomes. The LightGBM classifiers utilizing embeddings from ESM2 model with 30 and 36 transformer layers and 150 and 3000 million parameters respectively have performance gains by 3-[Formula: see text] than all compared models for various evaluation metrics, including AUPR (Area Under Precision-Recall Curve), AUC (Area Under the Receiver Operating Characteristic Curve), and F1 on independent test sets. Furthermore, we fine-tune the ProtGPT2 model available via TRILL to generate crystallizable proteins. Starting with 3000 generated proteins and through a step of filtration processes including consensus of all open PLM-based classifiers, sequence identity through CD-HIT, secondary structure compatibility, aggregation screening, homology search and foldability evaluation, we identified a set of 5 novel proteins as potentially crystallizable.

Accurate and Fast Prediction of Intrinsic Disorder Using flDPnn

Intrinsically disordered proteins (IDPs) that include one or more intrinsically disordered regions (IDRs) are abundant across all domains of life and viruses and play numerous functional roles in various cellular processes. Due to a relatively low throughput and high cost of experimental techniques for identifying IDRs, there is a growing need for fast and accurate computational algorithms that accurately predict IDRs/IDPs from protein sequences. We describe one of the leading disorder predictors, flDPnn. Results from a recent community-organized Critical Assessment of Intrinsic Disorder (CAID) experiment show that flDPnn provides fast and state-of-the-art predictions of disorder, which are supplemented with the predictions of several major disorder functions. This chapter provides a practical guide to flDPnn, which includes a brief explanation of its predictive model, descriptions of its web server and standalone versions, and a case study that showcases how to read and understand flDPnn's predictions.

Integrated computational characterization of valosin-containing protein double-psi β-barrel domain: Insights into structural stability, binding mechanisms, and evolutionary significance

Valosin-containing protein (VCP) plays a crucial role in various cellular processes, yet the molecular mechanisms and structural dynamics of its double-psi β-barrel (DPBB) domain, particularly in human, remain insufficiently explored. While previous studies have characterized the VCP_DPBB domain in other organisms, such as thermoplasma acidophilum and methanopyrus kandleri, its evolutionary conservation, binding potential, and stability in human require further investigation. To address this gap, we first employed all-atom molecular dynamics (AAMD) simulations to examine the structural dynamics of the human VCP_DPBB domain. We also assessed its amino acid interaction energies, stability, folding enthalpy, evolutionary conservation, solubility, and crystallizability using various computational frameworks. Additionally, to uncover the plausible biological function, protein-peptide docking was performed to evaluate the interactions between the DPBB domain and the C-terminal gp78 peptide of the E3 ubiquitin ligase. Further, AAMD and coarse-grained molecular dynamics (CGMD) simulations explored the binding preferences, fluctuations, and stability of human VCP_DPBB-gp78 complexes. Our findings indicate that, while thermoplasma acidophilum VCP_DPBB-gp78 showed stronger initial binding, the human VCP_DPBB-gp78 complex exhibited superior stability, binding affinity, and more stabilizing interactions. This integrated analysis provides valuable insights into the evolutionary significance and functionality of the DPBB domain, with potential therapeutic implications for VCP-related diseases.

Deep learning applications in protein crystallography

Deep learning techniques can recognize complex patterns in noisy, multidimensional data. In recent years, researchers have started to explore the potential of deep learning in the field of structural biology, including protein crystallography. This field has some significant challenges, in particular producing high-quality and well ordered protein crystals. Additionally, collecting diffraction data with high completeness and quality, and determining and refining protein structures can be problematic. Protein crystallographic data are often high-dimensional, noisy and incomplete. Deep learning algorithms can extract relevant features from these data and learn to recognize patterns, which can improve the success rate of crystallization and the quality of crystal structures. This paper reviews progress in this field.

Limited value of current and new in silico predicted oocyst-specific proteins of Toxoplasma gondii for source-attributing serology

Toxoplasma gondii is a zoonotic parasite infecting all warm-blooded animals, including humans. The contribution of environmental contamination by T. gondii oocysts to infections is understudied. The aim of the current work was to explore T. gondii serology as a means of attributing the source of infection using a robust stepwise approach. We identified in silico thirty-two promising oocyst-specific antigens from T. gondii ´omics data, recombinantly expressed and purified them and validated whether serology based on these proteins could discriminate oocyst- from tissue cyst-driven experimental infections. For this, three well-characterized serum panels, sampled from 0 to 6 weeks post-infection, from pigs and sheep experimentally infected with T. gondii oocysts or tissue cysts, were used. Candidate proteins were initially screened by Western blot with sera from pigs or sheep, infected for different times, either with oocysts or tissue cysts, as well as non-infected animals. Only the recombinant proteins TgCCp5A and TgSR1 provoked seroconversion upon infection and appeared to discriminate between oocyst- and tissue cyst-driven infections with pig sera. They were subsequently used to develop an enzyme-linked immunosorbent assay test for pigs. Based on this assay and Western blot analyses, a lack of stage specificity and low antigenicity was observed with all pig sera. The same was true for proteins TgERP, TgSporoSAG, TgOWP1 and TgOWP8, previously described as source-attributing antigens, when analyzed using the whole panels of sera. We conclude that there is currently no antigen that allows the discrimination of T. gondii infections acquired from either oocysts or tissue cysts by serological tests. This work provides robust new knowledge that can inform further research and development toward source-attributing T. gondii serology.

Identification of D-arabinan-degrading enzymes in mycobacteria

Bacterial cell growth and division require the coordinated action of enzymes that synthesize and degrade cell wall polymers. Here, we identify enzymes that cleave the D-arabinan core of arabinogalactan, an unusual component of the cell wall of Mycobacterium tuberculosis and other mycobacteria. We screened 14 human gut-derived Bacteroidetes for arabinogalactan-degrading activities and identified four families of glycoside hydrolases with activity against the D-arabinan or D-galactan components of arabinogalactan. Using one of these isolates with exo-D-galactofuranosidase activity, we generated enriched D-arabinan and used it to identify a strain of Dysgonomonas gadei as a D-arabinan degrader. This enabled the discovery of endo- and exo-acting enzymes that cleave D-arabinan, including members of the DUF2961 family (GH172) and a family of glycoside hydrolases (DUF4185/GH183) that display endo-D-arabinofuranase activity and are conserved in mycobacteria and other microbes. Mycobacterial genomes encode two conserved endo-D-arabinanases with different preferences for the D-arabinan-containing cell wall components arabinogalactan and lipoarabinomannan, suggesting they are important for cell wall modification and/or degradation. The discovery of these enzymes will support future studies into the structure and function of the mycobacterial cell wall.

GCmapCrys: Integrating graph attention network with predicted contact map for multi-stage protein crystallization propensity prediction

X-ray crystallography is the major approach for atomic-level protein structure determination. Since not all proteins can be easily crystallized, accurate prediction of protein crystallization propensity is critical to guiding the experimental design and improving the success rate of X-ray crystallography experiments. In this work, we proposed a new deep learning pipeline, GCmapCrys, for multi-stage crystallization propensity prediction through integrating graph attention network with predicted protein contact map. Experimental results on 1548 proteins with known crystallization records demonstrated that GCmapCrys increased the value of Matthew's correlation coefficient by 37.0% in average compared to state-of-the-art protein crystallization propensity predictors. Detailed analyses show that the major advantages of GCmapCrys lie in the efficiency of the graph attention network with predicted contact map, which effectively associates the residue-interaction knowledge with crystallization pattern. Meanwhile, the designed four sequence-based features can be complementary to further enhance crystallization propensity proprediction.

XRRpred: Accurate Predictor of Crystal Structure Quality from Protein Sequence

MOTIVATION

X-ray crystallography was used to produce nearly 90% of protein structures. These efforts were supported by numerous sequence-based tools that accurately predict crystallizable proteins. However, protein structures vary widely in their quality, typically measured with resolution and R-free. This impacts the ability to use these structures for some applications including rational drug design and molecular docking and motivates development of methods that accurately predict structure quality.

RESULTS

We introduce XRRpred, the first predictor of the resolution and R-free values from protein sequences. XRRpred relies on original sequence profiles, hand-crafted features, empirically selected and parametrized regressors, and modern resampling techniques. Using an independent test dataset, we show that XRRpred provides accurate predictions of resolution and R-free. We demonstrate that XRRpred's predictions correctly model relationship between the resolution and R-free and reproduce structure quality relations between structural classes of proteins. We also show that XRRpred significantly outperforms indirect alternative ways to predict the structure quality that include predictors of crystallization propensity and an alignment-based approach. XRRpred is available as a convenient webserver that allows batch predictions and offers informative visualization of the results.

AVAILABILITY

http://biomine.cs.vcu.edu/servers/XRRPred/.

Accurate multistage prediction of protein crystallization propensity using deep-cascade forest with sequence-based features

X-ray crystallography is the major approach for determining atomic-level protein structures. Because not all proteins can be easily crystallized, accurate prediction of protein crystallization propensity provides critical help in guiding experimental design and improving the success rate of X-ray crystallography experiments. This study has developed a new machine-learning-based pipeline that uses a newly developed deep-cascade forest (DCF) model with multiple types of sequence-based features to predict protein crystallization propensity. Based on the developed pipeline, two new protein crystallization propensity predictors, denoted as DCFCrystal and MDCFCrystal, have been implemented. DCFCrystal is a multistage predictor that can estimate the success propensities of the three individual steps (production of protein material, purification and production of crystals) in the protein crystallization process. MDCFCrystal is a single-stage predictor that aims to estimate the probability that a protein will pass through the entire crystallization process. Moreover, DCFCrystal is designed for general proteins, whereas MDCFCrystal is specially designed for membrane proteins, which are notoriously difficult to crystalize. DCFCrystal and MDCFCrystal were separately tested on two benchmark datasets consisting of 12 289 and 950 proteins, respectively, with known crystallization results from various experimental records. The experimental results demonstrated that DCFCrystal and MDCFCrystal increased the value of Matthew's correlation coefficient by 199.7% and 77.8%, respectively, compared to the best of other state-of-the-art protein crystallization propensity predictors. Detailed analyses show that the major advantages of DCFCrystal and MDCFCrystal lie in the efficiency of the DCF model and the sensitivity of the sequence-based features used, especially the newly designed pseudo-predicted hybrid solvent accessibility (PsePHSA) feature, which improves crystallization recognition by incorporating sequence-order information with solvent accessibility of residues. Meanwhile, the new crystal-dataset constructions help to train the models with more comprehensive crystallization knowledge.

CLPred: a sequence-based protein crystallization predictor using BLSTM neural network

MOTIVATION

Determining the structures of proteins is a critical step to understand their biological functions. Crystallography-based X-ray diffraction technique is the main method for experimental protein structure determination. However, the underlying crystallization process, which needs multiple time-consuming and costly experimental steps, has a high attrition rate. To overcome this issue, a series of in silico methods have been developed with the primary aim of selecting the protein sequences that are promising to be crystallized. However, the predictive performance of the current methods is modest.

RESULTS

We propose a deep learning model, so-called CLPred, which uses a bidirectional recurrent neural network with long short-term memory (BLSTM) to capture the long-range interaction patterns between k-mers amino acids to predict protein crystallizability. Using sequence only information, CLPred outperforms the existing deep-learning predictors and a vast majority of sequence-based diffraction-quality crystals predictors on three independent test sets. The results highlight the effectiveness of BLSTM in capturing non-local, long-range inter-peptide interaction patterns to distinguish proteins that can result in diffraction-quality crystals from those that cannot. CLPred has been steadily improved over the previous window-based neural networks, which is able to predict crystallization propensity with high accuracy. CLPred can also be improved significantly if it incorporates additional features from pre-extracted evolutional, structural and physicochemical characteristics. The correctness of CLPred predictions is further validated by the case studies of Sox transcription factor family member proteins and Zika virus non-structural proteins.

AVAILABILITY AND IMPLEMENTATION

https://github.com/xuanwenjing/CLPred.

BCrystal: an interpretable sequence-based protein crystallization predictor

MOTIVATION

X-ray crystallography has facilitated the majority of protein structures determined to date. Sequence-based predictors that can accurately estimate protein crystallization propensities would be highly beneficial to overcome the high expenditure, large attrition rate, and to reduce the trial-and-error settings required for crystallization.

RESULTS

In this study, we present a novel model, BCrystal, which uses an optimized gradient boosting machine (XGBoost) on sequence, structural and physio-chemical features extracted from the proteins of interest. BCrystal also provides explanations, highlighting the most important features for the predicted crystallization propensity of an individual protein using the SHAP algorithm. On three independent test sets, BCrystal outperforms state-of-the-art sequence-based methods by more than 12.5% in accuracy, 18% in recall and 0.253 in Matthew's correlation coefficient, with an average accuracy of 93.7%, recall of 96.63% and Matthew's correlation coefficient of 0.868. For relative solvent accessibility of exposed residues, we observed higher values to associate positively with protein crystallizability and the number of disordered regions, fraction of coils and tripeptide stretches that contain multiple histidines associate negatively with crystallizability. The higher accuracy of BCrystal enables it to accurately screen for sequence variants with enhanced crystallizability.

AVAILABILITY AND IMPLEMENTATION

Our BCrystal webserver is at https://machinelearning-protein.qcri.org/ and source code is available at https://github.com/raghvendra5688/BCrystal.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Prediction of Ion Channels and their Types from Protein Sequences: Comprehensive Review and Comparative Assessment

BACKGROUND

Ion channels are a large and growing protein family. Many of them are associated with diseases, and consequently, they are targets for over 700 drugs. Discovery of new ion channels is facilitated with computational methods that predict ion channels and their types from protein sequences. However, these methods were never comprehensively compared and evaluated.

OBJECTIVE

We offer first-of-its-kind comprehensive survey of the sequence-based predictors of ion channels. We describe eight predictors that include five methods that predict ion channels, their types, and four classes of the voltage-gated channels. We also develop and use a new benchmark dataset to perform comparative empirical analysis of the three currently available predictors.

RESULTS

While several methods that rely on different designs were published, only a few of them are currently available and offer a broad scope of predictions. Support and availability after publication should be required when new methods are considered for publication. Empirical analysis shows strong performance for the prediction of ion channels and modest performance for the prediction of ion channel types and voltage-gated channel classes. We identify a substantial weakness of current methods that cannot accurately predict ion channels that are categorized into multiple classes/types.

CONCLUSION

Several predictors of ion channels are available to the end users. They offer practical levels of predictive quality. Methods that rely on a larger and more diverse set of predictive inputs (such as PSIONplus) are more accurate. New tools that address multi-label prediction of ion channels should be developed.

Tools to Ease the Choice and Design of Protein Crystallisation Experiments

The process of macromolecular crystallisation almost always begins by setting up crystallisation trials using commercial or other premade screens, followed by cycles of optimisation where the crystallisation cocktails are focused towards a particular small region of chemical space. The screening process is relatively straightforward, but still requires an understanding of the plethora of commercially available screens. Optimisation is complicated by requiring both the design and preparation of the appropriate secondary screens. Software has been developed in the C3 lab to aid the process of choosing initial screens, to analyse the results of the initial trials, and to design and describe how to prepare optimisation screens.

Computational Prediction of Intrinsic Disorder in Protein Sequences with the disCoP Meta-predictor

Intrinsically disordered proteins are either entirely disordered or contain disordered regions in their native state. These proteins and regions function without the prerequisite of a stable structure and were found to be abundant across all kingdoms of life. Experimental annotation of disorder lags behind the rapidly growing number of sequenced proteins, motivating the development of computational methods that predict disorder in protein sequences. DisCoP is a user-friendly webserver that provides accurate sequence-based prediction of protein disorder. It relies on meta-architecture in which the outputs generated by multiple disorder predictors are combined together to improve predictive performance. The architecture of disCoP is presented, and its accuracy relative to several other disorder predictors is briefly discussed. We describe usage of the web interface and explain how to access and read results generated by this computational tool. We also provide an example of prediction results and interpretation. The disCoP's webserver is publicly available at http://biomine.cs.vcu.edu/servers/disCoP/ .

Prediction of Intrinsic Disorder with Quality Assessment Using QUARTER

Intrinsically disordered regions (IDRs) are estimated to be highly abundant in nature. While only several thousand proteins are annotated with experimentally derived IDRs, computational methods can be used to predict IDRs for the millions of currently uncharacterized protein chains. Several dozen disorder predictors were developed over the last few decades. While some of these methods provide accurate predictions, unavoidably they also make some mistakes. Consequently, one of the challenges facing users of these methods is how to decide which predictions can be trusted and which are likely incorrect. This practical problem can be solved using quality assessment (QA) scores that predict correctness of the underlying (disorder) predictions at a residue level. We motivate and describe a first-of-its-kind toolbox of QA methods, QUARTER (QUality Assessment for pRotein inTrinsic disordEr pRedictions), which provides the scores for a diverse set of ten disorder predictors. QUARTER is available to the end users as a free and convenient webserver at http://biomine.cs.vcu.edu/servers/QUARTER/ . We briefly describe the predictive architecture of QUARTER and provide detailed instructions on how to use the webserver. We also explain how to interpret results produced by QUARTER with the help of a case study.

DeepCrystal: a deep learning framework for sequence-based protein crystallization prediction

Motivation

Protein structure determination has primarily been performed using X-ray crystallography. To overcome the expensive cost, high attrition rate and series of trial-and-error settings, many in-silico methods have been developed to predict crystallization propensities of proteins based on their sequences. However, the majority of these methods build their predictors by extracting features from protein sequences, which is computationally expensive and can explode the feature space. We propose DeepCrystal, a deep learning framework for sequence-based protein crystallization prediction. It uses deep learning to identify proteins which can produce diffraction-quality crystals without the need to manually engineer additional biochemical and structural features from sequence. Our model is based on convolutional neural networks, which can exploit frequently occurring k-mers and sets of k-mers from the protein sequences to distinguish proteins that will result in diffraction-quality crystals from those that will not.

Results

Our model surpasses previous sequence-based protein crystallization predictors in terms of recall, F-score, accuracy and Matthew’s correlation coefficient (MCC) on three independent test sets. DeepCrystal achieves an average improvement of 1.4, 12.1% in recall, when compared to its closest competitors, Crysalis II and Crysf, respectively. In addition, DeepCrystal attains an average improvement of 2.1, 6.0% for F-score, 1.9, 3.9% for accuracy and 3.8, 7.0% for MCC w.r.t. Crysalis II and Crysf on independent test sets.

Availability and implementation

The standalone source code and models are available at https://github.com/elbasir/DeepCrystal and a web-server is also available at https://deeplearning-protein.qcri.org.

Supplementary information

Supplementary data are available at Bioinformatics online.

Taxonomic Landscape of the Dark Proteomes: Whole-Proteome Scale Interplay Between Structural Darkness, Intrinsic Disorder, and Crystallization Propensity

Growth rate of the protein sequence universe dramatically exceeds the speed of expansion for the protein structure universe, generating an immense dark proteome that includes proteins with unknown structure. A whole-proteome scale analysis of 5.4 million proteins from 987 proteomes in the three domains of life and viruses to systematically dissect an interplay between structural coverage, degree of putative intrinsic disorder, and predicted propensity for structure determination is performed. It has been found that Archaean and Bacterial proteomes have relatively high structural coverage and low amounts of disorder, whereas Eukaryotic and Viral proteomes are characterized by a broad spread of structural coverage and higher disorder levels. The analysis reveals that dark proteomes (i.e., proteomes containing high fractions of proteins with unknown structure) have significantly elevated amounts of intrinsic disorder and are predicted to be difficult to solve structurally. Although the majority of dark proteomes are of viral origin, many dark viral proteomes have at least modest crystallization propensity and only a handful of them are enriched in the intrinsic disorder. The disorder, structural coverage, and propensity are mapped for structural determination onto a novel proteome-level sequence similarity network to analyze the interplay of these characteristics in the taxonomic landscape.