GASP: A Pan-Specific Predictor of Family 1 Glycosyltransferase Acceptor Specificity Enabled by a Pipeline for Substrate Feature Generation and Large-Scale Experimental Screening.

Glycosylation represents a major chemical challenge; while it is one of the most common reactions in Nature, conventional chemistry struggles with stereochemistry, regioselectivity, and solubility issues. In contrast, family 1 glycosyltransferase (GT1) enzymes can glycosylate virtually any given nucleophilic group with perfect control over stereochemistry and regioselectivity. However, the appropriate catalyst for a given reaction needs to be identified among the tens of thousands of available sequences. Here, we present the glycosyltransferase acceptor specificity predictor (GASP) model, a data-driven approach to the identification of reactive GT1:acceptor pairs. We trained a random forest-based acceptor predictor on literature data and validated it on independent in-house generated data on 1001 GT1:acceptor pairs, obtaining an AUROC of 0.79 and a balanced accuracy of 72%. The performance was stable even in the case of completely new GT1s and acceptors not present in the training data set, highlighting the pan-specificity of GASP. Moreover, the model is capable of parsing all known GT1 sequences, as well as all chemicals, the latter through a pipeline for the generation of 153 chemical features for a given molecule taking the CID or SMILES as input (freely available at https://github.com/degnbol/GASP). To investigate the power of GASP, the model prediction probability scores were compared to GT1 substrate conversion yields from a newly published data set, with the top 50% of GASP predictions corresponding to reactions with >50% synthetic yields. The model was also tested in two comparative case studies: glycosylation of the antihelminth drug niclosamide and the plant defensive compound DIBOA. In the first study, the model achieved an 83% hit rate, outperforming a hit rate of 53% from a random selection assay. In the second case study, the hit rate of GASP was 50%, and while being lower than the hit rate of 83% using expert-selected enzymes, it provides a reasonable performance for the cases when an expert opinion is unavailable. The hierarchal importance of the generated chemical features was investigated by negative feature selection, revealing properties related to cyclization and atom hybridization status to be the most important characteristics for accurate prediction. Our study provides a GT1:acceptor predictor which can be trained on other data sets enabled by the automated feature generation pipelines. We also release the new in-house generated data set used for testing of GASP to facilitate the future development of GT1 activity predictors and their robust benchmarking.

CoVAMPnet: Comparative Markov State Analysis for Studying Effects of Drug Candidates on Disordered Biomolecules.

Computational study of the effect of drug candidates on intrinsically disordered biomolecules is challenging due to their vast and complex conformational space. Here, we developed a comparative Markov state analysis (CoVAMPnet) framework to quantify changes in the conformational distribution and dynamics of a disordered biomolecule in the presence and absence of small organic drug candidate molecules. First, molecular dynamics trajectories are generated using enhanced sampling, in the presence and absence of small molecule drug candidates, and ensembles of soft Markov state models (MSMs) are learned for each system using unsupervised machine learning. Second, these ensembles of learned MSMs are aligned across different systems based on a solution to an optimal transport problem. Third, the directional importance of inter-residue distances for the assignment to different conformational states is assessed by a discriminative analysis of aggregated neural network gradients. This final step provides interpretability and biophysical context to the learned MSMs. We applied this novel computational framework to assess the effects of ongoing phase 3 therapeutics tramiprosate (TMP) and its metabolite 3-sulfopropanoic acid (SPA) on the disordered Aß42 peptide involved in Alzheimer's disease. Based on adaptive sampling molecular dynamics and CoVAMPnet analysis, we observed that both TMP and SPA preserved more structured conformations of Aß42 by interacting nonspecifically with charged residues. SPA impacted Aß42 more than TMP, protecting α-helices and suppressing the formation of aggregation-prone ß-strands. Experimental biophysical analyses showed only mild effects of TMP/SPA on Aß42 and activity enhancement by the endogenous metabolization of TMP into SPA. Our data suggest that TMP/SPA may also target biomolecules other than Aß peptides. The CoVAMPnet method is broadly applicable to study the effects of drug candidates on the conformational behavior of intrinsically disordered biomolecules.

PredictONCO: a web tool supporting decision-making in precision oncology by extending the bioinformatics predictions with advanced computing and machine learning.

PredictONCO 1.0 is a unique web server that analyzes effects of mutations on proteins frequently altered in various cancer types. The server can assess the impact of mutations on the protein sequential and structural properties and apply a virtual screening to identify potential inhibitors that could be used as a highly individualized therapeutic approach, possibly based on the drug repurposing. PredictONCO integrates predictive algorithms and state-of-the-art computational tools combined with information from established databases. The user interface was carefully designed for the target specialists in precision oncology, molecular pathology, clinical genetics and clinical sciences. The tool summarizes the effect of the mutation on protein stability and function and currently covers 44 common oncological targets. The binding affinities of Food and Drug Administration/ European Medicines Agency -approved drugs with the wild-type and mutant proteins are calculated to facilitate treatment decisions. The reliability of predictions was confirmed against 108 clinically validated mutations. The server provides a fast and compact output, ideal for the often time-sensitive decision-making process in oncology. Three use cases of missense mutations, (i) K22A in cyclin-dependent kinase 4 identified in melanoma, (ii) E1197K mutation in anaplastic lymphoma kinase 4 identified in lung carcinoma and (iii) V765A mutation in epidermal growth factor receptor in a patient with congenital mismatch repair deficiency highlight how the tool can increase levels of confidence regarding the pathogenicity of the variants and identify the most effective inhibitors. The server is available at https://loschmidt.chemi.muni.cz/predictonco.

Machine Learning-Guided Protein Engineering.

Recent progress in engineering highly promising biocatalysts has increasingly involved machine learning methods. These methods leverage existing experimental and simulation data to aid in the discovery and annotation of promising enzymes, as well as in suggesting beneficial mutations for improving known targets. The field of machine learning for protein engineering is gathering steam, driven by recent success stories and notable progress in other areas. It already encompasses ambitious tasks such as understanding and predicting protein structure and function, catalytic efficiency, enantioselectivity, protein dynamics, stability, solubility, aggregation, and more. Nonetheless, the field is still evolving, with many challenges to overcome and questions to address. In this Perspective, we provide an overview of ongoing trends in this domain, highlight recent case studies, and examine the current limitations of machine learning-based methods. We emphasize the crucial importance of thorough experimental validation of emerging models before their use for rational protein design. We present our opinions on the fundamental problems and outline the potential directions for future research.

In-depth analysis of biocatalysts by microfluidics: An emerging source of data for machine learning.

Nowadays, the vastly increasing demand for novel biotechnological products is supported by the continuous development of biocatalytic applications that provide sustainable green alternatives to chemical processes. The success of a biocatalytic application is critically dependent on how quickly we can identify and characterize enzyme variants fitting the conditions of industrial processes. While miniaturization and parallelization have dramatically increased the throughput of next-generation sequencing systems, the subsequent characterization of the obtained candidates is still a limiting process in identifying the desired biocatalysts. Only a few commercial microfluidic systems for enzyme analysis are currently available, and the transformation of numerous published prototypes into commercial platforms is still to be streamlined. This review presents the state-of-the-art, recent trends, and perspectives in applying microfluidic tools in the functional and structural analysis of biocatalysts. We discuss the advantages and disadvantages of available technologies, their reproducibility and robustness, and readiness for routine laboratory use. We also highlight the unexplored potential of microfluidics to leverage the power of machine learning for biocatalyst development.

SoluProtMutDB: A manually curated database of protein solubility changes upon mutations.

Protein solubility is an attractive engineering target primarily due to its relation to yields in protein production and manufacturing. Moreover, better knowledge of the mutational effects on protein solubility could connect several serious human diseases with protein aggregation. However, we have limited understanding of the protein structural determinants of solubility, and the available data have mostly been scattered in the literature. Here, we present SoluProtMutDB - the first database containing data on protein solubility changes upon mutations. Our database accommodates 33 000 measurements of 17 000 protein variants in 103 different proteins. The database can serve as an essential source of information for the researchers designing improved protein variants or those developing machine learning tools to predict the effects of mutations on solubility. The database comprises all the previously published solubility datasets and thousands of new data points from recent publications, including deep mutational scanning experiments. Moreover, it features many available experimental conditions known to affect protein solubility. The datasets have been manually curated with substantial corrections, improving suitability for machine learning applications. The database is available at loschmidt.chemi.muni.cz/soluprotmutdb.

CalFitter 2.0: Leveraging the power of singular value decomposition to analyse protein thermostability.

The importance of the quantitative description of protein unfolding and aggregation for the rational design of stability or understanding the molecular basis of protein misfolding diseases is well established. Protein thermostability is typically assessed by calorimetric or spectroscopic techniques that monitor different complementary signals during unfolding. The CalFitter webserver has already proved integral to deriving invaluable energy parameters by global data analysis. Here, we introduce CalFitter 2.0, which newly incorporates singular value decomposition (SVD) of multi-wavelength spectral datasets into the global fitting pipeline. Processed time- or temperature-evolved SVD components can now be fitted together with other experimental data types. Moreover, deconvoluted basis spectra provide spectral fingerprints of relevant macrostates populated during unfolding, which greatly enriches the information gains of the CalFitter output. The SVD analysis is fully automated in a highly interactive module, providing access to the results to users without any prior knowledge of the underlying mathematics. Additionally, a novel data uploading wizard has been implemented to facilitate rapid and easy uploading of multiple datasets. Together, the newly introduced changes significantly improve the user experience, making this software a unique, robust, and interactive platform for the analysis of protein thermal denaturation data. The webserver is freely accessible at https://loschmidt.chemi.muni.cz/calfitter.

Tools for computational design and high-throughput screening of therapeutic enzymes.

Therapeutic enzymes are valuable biopharmaceuticals in various biomedical applications. They have been successfully applied for fibrinolysis, cancer treatment, enzyme replacement therapies, and the treatment of rare diseases. Still, there is a permanent demand to find new or better therapeutic enzymes, which would be sufficiently soluble, stable, and active to meet specific medical needs. Here, we highlight the benefits of coupling computational approaches with high-throughput experimental technologies, which significantly accelerate the identification and engineering of catalytic therapeutic agents. New enzymes can be identified in genomic and metagenomic databases, which grow thanks to next-generation sequencing technologies exponentially. Computational design and machine learning methods are being developed to improve catalytically potent enzymes and predict their properties to guide the selection of target enzymes. High-throughput experimental pipelines, increasingly relying on microfluidics, ensure functional screening and biochemical characterization of target enzymes to reach efficient therapeutic enzymes.

Substrate inhibition by the blockage of product release and its control by tunnel engineering.

Substrate inhibition is the most common deviation from Michaelis-Menten kinetics, occurring in approximately 25% of known enzymes. It is generally attributed to the formation of an unproductive enzyme-substrate complex after the simultaneous binding of two or more substrate molecules to the active site. Here, we show that a single point mutation (L177W) in the haloalkane dehalogenase LinB causes strong substrate inhibition. Surprisingly, a global kinetic analysis suggested that this inhibition is caused by binding of the substrate to the enzyme-product complex. Molecular dynamics simulations clarified the details of this unusual mechanism of substrate inhibition: Markov state models indicated that the substrate prevents the exit of the halide product by direct blockage and/or restricting conformational flexibility. The contributions of three residues forming the possible substrate inhibition site (W140A, F143L and I211L) to the observed inhibition were studied by mutagenesis. An unusual synergy giving rise to high catalytic efficiency and reduced substrate inhibition was observed between residues L177W and I211L, which are located in different access tunnels of the protein. These results show that substrate inhibition can be caused by substrate binding to the enzyme-product complex and can be controlled rationally by targeted amino acid substitutions in enzyme access tunnels.

FireProtDB: database of manually curated protein stability data.

The majority of naturally occurring proteins have evolved to function under mild conditions inside the living organisms. One of the critical obstacles for the use of proteins in biotechnological applications is their insufficient stability at elevated temperatures or in the presence of salts. Since experimental screening for stabilizing mutations is typically laborious and expensive, in silico predictors are often used for narrowing down the mutational landscape. The recent advances in machine learning and artificial intelligence further facilitate the development of such computational tools. However, the accuracy of these predictors strongly depends on the quality and amount of data used for training and testing, which have often been reported as the current bottleneck of the approach. To address this problem, we present a novel database of experimental thermostability data for single-point mutants FireProtDB. The database combines the published datasets, data extracted manually from the recent literature, and the data collected in our laboratory. Its user interface is designed to facilitate both types of the expected use: (i) the interactive explorations of individual entries on the level of a protein or mutation and (ii) the construction of highly customized and machine learning-friendly datasets using advanced searching and filtering. The database is freely available at https://loschmidt.chemi.muni.cz/fireprotdb.

Development of Fluorescent Assay for Monitoring of Dehalogenase Activity.

The rapid accumulation of sequence data and powerful protein engineering techniques providing large mutant libraries have greatly heightened interest in efficient methods for biochemical characterization of proteins. Herein is reported a continuous assay for screening of enzymatic activity. The assay is developed and tested with the model enzymes haloalkane dehalogenases and relies upon a fluorescent change of a derivative of 8-hydroxypyrene-1,3,6-trisulphonic acid due to the pH drop associated with the dehalogenation reactions. The assay is performed in a microplate format using a purified enzyme, cell-free extract or intact cells, making the analysis quick and simple. The method exhibits high sensitivity with a limit of detection of 0.06 mM. The assay is successfully validated with gas chromatography and then applied for screening of 12 haloalkane dehalogenases with the environmental pollutant bis(2-chloroethyl) ether and chemical warfare agent sulfur mustard. Six enzymes exhibited detectable activity with both substrates. The within-day variability of the assay for five replicates (n = 5) was 21%.

Sensitive operation of enzyme-based biodevices by advanced signal processing.

Analytical devices that combine sensitive biological component with a physicochemical detector hold a great potential for various applications, e.g., environmental monitoring, food analysis or medical diagnostics. Continuous efforts to develop inexpensive sensitive biodevices for detecting target substances typically focus on the design of biorecognition elements and their physical implementation, while the methods for processing signals generated by such devices have received far less attention. Here, we present fundamental considerations related to signal processing in biosensor design and investigate how undemanding signal treatment facilitates calibration and operation of enzyme-based biodevices. Our signal treatment approach was thoroughly validated with two model systems: (i) a biodevice for detecting chemical warfare agents and environmental pollutants based on the activity of haloalkane dehalogenase, with the sensitive range for bis(2-chloroethyl) ether of 0.01-0.8 mM and (ii) a biodevice for detecting hazardous pesticides based on the activity of γ-hexachlorocyclohexane dehydrochlorinase with the sensitive range for γ-hexachlorocyclohexane of 0.01-0.3 mM. We demonstrate that the advanced signal processing based on curve fitting enables precise quantification of parameters important for sensitive operation of enzyme-based biodevices, including: (i) automated exclusion of signal regions with substantial noise, (ii) derivation of calibration curves with significantly reduced error, (iii) shortening of the detection time, and (iv) reliable extrapolation of the signal to the initial conditions. The presented simple signal curve fitting supports rational design of optimal system setup by explicit and flexible quantification of its properties and will find a broad use in the development of sensitive and robust biodevices.

CalFitter: a web server for analysis of protein thermal denaturation data.

Despite significant advances in the understanding of protein structure-function relationships, revealing protein folding pathways still poses a challenge due to a limited number of relevant experimental tools. Widely-used experimental techniques, such as calorimetry or spectroscopy, critically depend on a proper data analysis. Currently, there are only separate data analysis tools available for each type of experiment with a limited model selection. To address this problem, we have developed the CalFitter web server to be a unified platform for comprehensive data fitting and analysis of protein thermal denaturation data. The server allows simultaneous global data fitting using any combination of input data types and offers 12 protein unfolding pathway models for selection, including irreversible transitions often missing from other tools. The data fitting produces optimal parameter values, their confidence intervals, and statistical information to define unfolding pathways. The server provides an interactive and easy-to-use interface that allows users to directly analyse input datasets and simulate modelled output based on the model parameters. CalFitter web server is available free at https://loschmidt.chemi.muni.cz/calfitter/.

Computer-assisted engineering of hyperstable fibroblast growth factor 2.

Fibroblast growth factors (FGFs) serve numerous regulatory functions in complex organisms, and their corresponding therapeutic potential is of growing interest to academics and industrial researchers alike. However, applications of these proteins are limited due to their low stability. Here we tackle this problem using a generalizable computer-assisted protein engineering strategy to create a unique modified FGF2 with nine mutations displaying unprecedented stability and uncompromised biological function. The data from the characterization of stabilized FGF2 showed a remarkable prediction potential of in silico methods and provided insight into the unfolding mechanism of the protein. The molecule holds a considerable promise for stem cell research and medical or pharmaceutical applications.

Exploration of Protein Unfolding by Modelling Calorimetry Data from Reheating.

Studies of protein unfolding mechanisms are critical for understanding protein functions inside cells, de novo protein design as well as defining the role of protein misfolding in neurodegenerative disorders. Calorimetry has proven indispensable in this regard for recording full energetic profiles of protein unfolding and permitting data fitting based on unfolding pathway models. While both kinetic and thermodynamic protein stability are analysed by varying scan rates and reheating, the latter is rarely used in curve-fitting, leading to a significant loss of information from experiments. To extract this information, we propose fitting both first and second scans simultaneously. Four most common single-peak transition models are considered: (i) fully reversible, (ii) fully irreversible, (iii) partially reversible transitions, and (iv) general three-state models. The method is validated using calorimetry data for chicken egg lysozyme, mutated Protein A, three wild-types of haloalkane dehalogenases, and a mutant stabilized by protein engineering. We show that modelling of reheating increases the precision of determination of unfolding mechanisms, free energies, temperatures, and heat capacity differences. Moreover, this modelling indicates whether alternative refolding pathways might occur upon cooling. The Matlab-based data fitting software tool and its user guide are provided as a supplement.