TopProperty: Robust Metaprediction of Transmembrane and Globular Protein Features Using Deep Neural Networks

Abstract

Transmembrane proteins (TMPs) are critical components of cellular life. However, due to experimental challenges, the number of experimentally resolved TMP structures is severely underrepresented in databases compared to their cellular abundance. Prediction of (per-residue) features such as transmembrane topology, membrane exposure, secondary structure, and solvent accessibility can be a useful starting point for experimental design or protein structure prediction but often requires different computational tools for different features or types of proteins. We present TopProperty, a metapredictor that predicts all of these features for TMPs or globular proteins. TopProperty is trained on datasets without bias toward a high number of sequence homologs, and the predictions are significantly better than the evaluated state-of-theart primary predictors on all quality metrics. TopProperty eliminates the need for protein type-or feature-tailored tools, specifically for TMPs. TopProperty is freely available as a web server and standalone at https://cpclab.uni-duesseldorf.de/topsuite/.

Machine learning in computational modelling of membrane protein sequences and structures: From methodologies to applications

“…Rather than focusing on single property prediction, a few studies have sought to predict a number of properties in combination, such as solvent accessibility, secondary structures, and torsion angles. These methods include AllesTM [242] , MASSP [243] , and TopProperty [244] , which all use deep learning methods to keep abreast of any possible advances in prediction performance ( Table 6 ). For example, in the AllesTM work, the ensemble of conventional machine learning methods (random forest) and deep learning methods (CNNs and bidirectional LSTM NNs) leads to superior performance in predicting Z-coordinates, flexibility, and topology, and its performance in predicting torsion angles, secondary structures, and monomer relative solvent accessibility is roughly similar to that of SPOT-1D.…”

Prospects for targeting ACKR1 in cancer and other diseases

“…Currently trials are ongoing for a CCR9 antagonist for Crohn’s disease and a CCR1 antagonist for rheumatoid arthritis ( 100 , 101 ). Reparixin, an allosteric CXCR1 and CXCR2 blocker, did not progress past a phase 3 trial as a drug adjuvant for pancreatic islet allotransplantation to treat type 1 diabetes, but it is still a candidate for ongoing trials for metastatic breast cancer and COVID-19 related acute lung injury ( 102 – 104 ). Alternatively, blocking chemokines may decrease autoinflammation, and an antibody drug bertilimumab targeting CCL11 was designed to prevent eosinophil-mediated autoimmune damage in bullous pemphigoid skin disorder and inflammatory bowel disease ( 105 , 106 ).…”

ProtRAP: Predicting Lipid Accessibility Together with Solvent Accessibility of Proteins in One Run

“…Several methods can predict the transmembrane region of the protein, thereby indirectly predicting LA. Property, 22 which can predict whether a residue is exposed to membranes, but the binary prediction is still not as compatible and informative as LA in complementing SA.…”

“…However, at that time, there was not much data available for training purposes (no more than 100 membrane protein structures in the data sets), and consequently the methods did not show satisfactory performance. Several methods can predict the transmembrane region of the protein, thereby indirectly predicting LA. − A recent binary prediction method was included in TopProperty, which can predict whether a residue is exposed to membranes, but the binary prediction is still not as compatible and informative as LA in complementing SA.…”