Enzymatic reactions are crucial to explore the mechanistic function of metabolites and proteins in cellular processes and to understand the etiology of diseases. The increasing number of interconnected metabolic reactions allows the development of in silico deep learning-based methods to discover new enzymatic reaction links between metabolites and proteins to further expand the landscape of existing metabolite-protein interactome. Computational approaches to predict the enzymatic reaction link by metabolite-protein interaction (MPI) prediction are still very limited. In this study, we developed a Variational Graph Autoencoders (VGAE)-based framework to predict MPI in genome-scale heterogeneous enzymatic reaction networks across ten organisms. By incorporating molecular features of metabolites and proteins as well as neighboring information in the MPI networks, our MPI-VGAE predictor achieved the best predictive performance compared to other machine learning methods. Moreover, when applying the MPI-VGAE framework to reconstruct hundreds of metabolic pathways, functional enzymatic reaction networks and a metabolite-metabolite interaction network, our method showed the most robust performance among all scenarios. To the best of our knowledge, this is the first MPI predictor by VGAE for enzymatic reaction link prediction. Furthermore, we implemented the MPI-VGAE framework to reconstruct the disease-specific MPI network based on the disrupted metabolites and proteins in Alzheimer's disease and colorectal cancer, respectively. A substantial number of novel enzymatic reaction links were identified. We further validated and explored the interactions of these enzymatic reactions using molecular docking. These results highlight the potential of the MPI-VGAE framework for the discovery of novel disease-related enzymatic reactions and facilitate the study of the disrupted metabolisms in diseases.

The ubiquitous availability of genome sequencing data explains the popularity of machine learning-based methods for the prediction of protein properties from their amino acid sequences. Over the years, while revising our own work, reading submitted manuscripts as well as published papers, we have noticed several recurring issues, which make some reported findings hard to understand and replicate. We suspect this may be due to biologists being unfamiliar with machine learning methodology, or conversely, machine learning experts may miss some of the knowledge needed to correctly apply their methods to proteins. Here, we aim to bridge this gap for developers of such methods. The most striking issues are linked to a lack of clarity: how were annotations of interest obtained; which benchmark metrics were used; how are positives and negatives defined. Others relate to a lack of rigor: If you sneak in structural information, your method is not sequence-based; if you compare your own model to "state-of-the-art," take the best methods; if you want to conclude that some method is better than another, obtain a significance estimate to support this claim. These, and other issues, we will cover in detail. These points may have seemed obvious to the authors during writing; however, they are not always clear-cut to the readers. We also expect many of these tips to hold for other machine learning-based applications in biology. Therefore, many computational biologists who develop methods in this particular subject will benefit from a concise overview of what to avoid and what to do instead.

MOTIVATION: Although structured proteins adopt their lowest free energy conformation in physiological conditions, the individual residues are generally not in their lowest free energy conformation. Residues that are stability weaknesses are often involved in functional regions, whereas stability strengths ensure local structural stability. The detection of strengths and weaknesses provides key information to guide protein engineering experiments aiming to modulate folding and various functional processes. RESULTS: We developed the SWOTein predictor which identifies strong and weak residues in proteins on the basis of three types of statistical energy functions describing local interactions along the chain, hydrophobic forces and tertiary interactions. The large-scale analysis of the different types of strengths and weaknesses demonstrated their complementarity and the enhancement of the information they provide. Moreover, a good average correlation was observed between predicted and experimental strengths and weaknesses obtained from native hydrogen exchange data. SWOTein application to three test cases further showed its suitability to predict and interpret strong and weak residues in the context of folding, conformational changes and protein-protein binding. In summary, SWOTein is both fast and accurate and can be applied at small and large scale to analyze and modulate folding and molecular recognition processes. AVAILABILITY: The SWOTein webserver provides the list of predicted strengths and weaknesses and a protein structure visualization tool that facilitates the interpretation of the predictions. It is freely available for academic use at http://babylone.ulb.ac.be/SWOTein/.

MOTIVATION: Antibodies play an important role in clinical research and biotechnology, with their specificity determined by the interaction with the antigen's epitope region, as a special type of protein-protein interaction (PPI) interface. The ubiquitous availability of sequence data, allows us to predict epitopes from sequence in order to focus time-consuming wet-lab experiments toward the most promising epitope regions. Here, we extend our previously developed sequence-based predictors for homodimer and heterodimer PPI interfaces to predict epitope residues that have the potential to bind an antibody. RESULTS: We collected and curated a high quality epitope dataset from the SAbDab database. Our generic PPI heterodimer predictor obtained an AUC-ROC of 0.666 when evaluated on the epitope test set. We then trained a random forest model specifically on the epitope dataset, reaching AUC 0.694. Further training on the combined heterodimer and epitope datasets, improves our final predictor to AUC 0.703 on the epitope test set. This is better than the best state-of-the-art sequence-based epitope predictor BepiPred-2.0. On one solved antibody-antigen structure of the COVID19 virus spike receptor binding domain, our predictor reaches AUC 0.778. We added the SeRenDIP-CE Conformational Epitope predictors to our webserver, which is simple to use and only requires a single antigen sequence as input, which will help make the method immediately applicable in a wide range of biomedical and biomolecular research. AVAILABILITY AND IMPLEMENTATION: Webserver, source code and datasets at www.ibi.vu.nl/programs/serendipwww/. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: The solubility of a protein is often decisive for its proper functioning. Lack of solubility is a major bottleneck in high-throughput structural genomic studies and in high-concentration protein production, and the formation of protein aggregates causes a wide variety of diseases. Since solubility measurements are time-consuming and expensive, there is a strong need for solubility prediction tools. RESULTS: We have recently introduced solubility-dependent distance potentials that are able to unravel the role of residue-residue interactions in promoting or decreasing protein solubility. Here, we extended their construction by defining solubility-dependent potentials based on backbone torsion angles and solvent accessibility, and integrated them, together with other structure- and sequence-based features, into a random forest model trained on a set of Escherichia coli proteins with experimental structures and solubility values. We thus obtained the SOLart protein solubility predictor, whose most informative features turned out to be folding free energy differences computed from our solubility-dependent statistical potentials. SOLart performances are very good, with a Pearson correlation coefficient between experimental and predicted solubility values of almost 0.7 both in cross-validation on the training dataset and in an independent set of Saccharomyces cerevisiae proteins. On test sets of modeled structures, only a limited drop in performance is observed. SOLart can thus be used with both high-resolution and low-resolution structures, and clearly outperforms state-of-art solubility predictors. It is available through a user-friendly webserver, which is easy to use by non-expert scientists. AVAILABILITY AND IMPLEMENTATION: The SOLart webserver is freely available at http://babylone.ulb.ac.be/SOLART/. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Interpretation of ubiquitous protein sequence data has become a bottleneck in biomolecular research, due to a lack of structural and other experimental annotation data for these proteins. Prediction of protein interaction sites from sequence may be a viable substitute. We therefore recently developed a sequence-based random forest method for protein-protein interface prediction, which yielded a significantly increased performance than other methods on both homomeric and heteromeric protein-protein interactions. Here, we present a webserver that implements this method efficiently. RESULTS: With the aim of accelerating our previous approach, we obtained sequence conservation profiles by re-mastering the alignment of homologous sequences found by PSI-BLAST. This yielded a more than 10-fold speedup and at least the same accuracy, as reported previously for our method; these results allowed us to offer the method as a webserver. The web-server interface is targeted to the non-expert user. The input is simply a sequence of the protein of interest, and the output a table with scores indicating the likelihood of having an interaction interface at a certain position. As the method is sequence-based and not sensitive to the type of protein interaction, we expect this webserver to be of interest to many biological researchers in academia and in industry. AVAILABILITY AND IMPLEMENTATION: Webserver, source code and datasets are available at www.ibi.vu.nl/programs/serendipwww/. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Genome sequencing is producing an ever-increasing amount of associated protein sequences. Few of these sequences have experimentally validated annotations, however, and computational predictions are becoming increasingly successful in producing such annotations. One key challenge remains the prediction of the amino acids in a given protein sequence that are involved in protein-protein interactions. Such predictions are typically based on machine learning methods that take advantage of the properties and sequence positions of amino acids that are known to be involved in interaction. In this paper, we evaluate the importance of various features using Random Forest (RF), and include as a novel feature backbone flexibility predicted from sequences to further optimise protein interface prediction. RESULTS: We observe that there is no single sequence feature that enables pinpointing interacting sites in our Random Forest models. However, combining different properties does increase the performance of interface prediction. Our homomeric-trained RF interface predictor is able to distinguish interface from non-interface residues with an area under the ROC curve of 0.72 in a homomeric test-set. The heteromeric-trained RF interface predictor performs better than existing predictors on a independent heteromeric test-set. We trained a more general predictor on the combined homomeric and heteromeric dataset, and show that in addition to predicting homomeric interfaces, it is also able to pinpoint interface residues in heterodimers. This suggests that our random forest model and the features included capture common properties of both homodimer and heterodimer interfaces. AVAILABILITY AND IMPLEMENTATION: The predictors and test datasets used in our analyses are freely available ( http://www.ibi.vu.nl/downloads/RF_PPI/ ). CONTACT: [email protected]. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

BACKGROUND: Protein families participating in protein-protein interactions may contain sub-families that have different binding characteristics, ranging from right binding to showing no interaction at all. Composition differences at the sequence level in these sub-families are often decisive to their differential functional interaction. Methods to predict interface sites from protein sequences typically exploit conservation as a signal. Here, instead, we provide proof of concept that the sequence specificity between interacting versus non-interacting groups can be exploited to recognise interaction sites. RESULTS: We collected homodimeric and monomeric proteins and formed homologous groups, each having an interacting (homodimer) subgroup and a non-interacting (monomer) subgroup. We then compiled multiple sequence alignments of the proteins in the homologous groups and identified compositional differences between the homodimeric and monomeric subgroups for each of the alignment positions. Our results show that this specificity signal distinguishes interface and other surface residues with 40.9% recall and up to 25.1% precision. CONCLUSIONS: To our best knowledge, this is the first large scale study that exploits sequence specificity between interacting and non-interacting homologs to predict interaction sites from sequence information only. The performance obtained indicates that this signal contains valuable information to identify protein-protein interaction sites.