LECTINPred: web Server that Uses Complex Networks of Protein Structure for Prediction of Lectins with Potential Use as Cancer Biomarkers or in Parasite Vaccine Design

Abstract

Lectins (Ls) play an important role in many diseases such as different types of cancer, parasitic infections and other diseases. Interestingly, the Protein Data Bank (PDB) contains +3000 protein 3D structures with unknown function. Thus, we can in principle, discover new Ls mining non-annotated structures from PDB or other sources. However, there are no general models to predict new biologically relevant Ls based on 3D chemical structures. We used the MARCH-INSIDE software to calculate the Markov-Shannon 3D electrostatic entropy parameters for the complex networks of protein structure of 2200 different protein 3D structures, including 1200 Ls. We have performed a Linear Discriminant Analysis (LDA) using these parameters as inputs in order to seek a new Quantitative Structure-Activity Relationship (QSAR) model, which is able to discriminate 3D structure of Ls from other proteins. We implemented this predictor in the web server named LECTINPred, freely available at http://bio-aims.udc.es/LECTINPred.php. This web server showed the following goodness-of-fit statistics: Sensitivity=96.7 % (for Ls), Specificity=87.6 % (non-active proteins), and Accuracy=92.5 % (for all proteins), considering altogether both the training and external prediction series. In mode 2, users can carry out an automatic retrieval of protein structures from PDB. We illustrated the use of this server, in operation mode 1, performing a data mining of PDB. We predicted Ls scores for +2000 proteins with unknown function and selected the top-scored ones as possible lectins. In operation mode 2, LECTINPred can also upload 3D structural models generated with structure-prediction tools like LOMETS or PHYRE2. The new Ls are expected to be of relevance as cancer biomarkers or useful in parasite vaccine design.

Bio-AIMS Collection of Chemoinformatics Web Tools based on Molecular Graph Information and Artificial Intelligence Models

“…For example, some viruses use lectins to attach themselves to the cells of the host organism during infection. This tool presents a linear classifier based on Markov Shannon entropies of proteins and it can evaluate if a new protein can bind to sugars (this protein could be a lectin) with an accuracy over 90.00% [92]. Because there are +2000 proteins with 3D structure, but without a known function, LectinPred has been used to predict possible lectin proteins.…”

Prediction of druggable proteins using machine learning and functional enrichment analysis: a focus on cancer-related proteins and RNA-binding proteins

“…Classification models have been published for the prediction of protein activities such as anti-angiogenic [13], anti-cancer [14], enzyme class [15], epitope [16], signaling [17], lectins [18], anti-oxidant [19], and druggability [12, 20–26]. Therefore, the aim of this study was to build an effective machine learning classifier to predict druggability of breast cancer (BC) proteins, cancer-driving proteins and RNA-binding proteins (RBPs).…”

Prediction of breast cancer proteins using molecular descriptors and artificial neural networks: a focus on cancer immunotherapy proteins, metastasis driver proteins, and RNA-binding proteins

“…The classification model represents a quantitative structure-activity relationship (QSAR) between the protein structure and biological function [43]. Different classification models have been published for prediction of protein activities: anti-oxidant [44], lectins [45], signaling [46], anti-angiogenic [47], anti-cancer [48], and enzyme class [49]. Vilar et al [50] developed a QSAR model for alignment-free prediction of BC cancer biomarkers using linear discriminant analysis method, electrostatic potentials of protein pseudofolding HP-lattice networks as features, and 122 proteins related to BC and a control group of 200 proteins with classifications above 80%.…”