The molecular information encoding into molecular descriptors is the first step into in silico Chemoinformatics
methods in Drug Design. The Machine Learning methods are a complex solution to find prediction models for specific
biological properties of molecules. These models connect the molecular structure information such as atom connectivity
(molecular graphs) or physical-chemical properties of an atom/group of atoms to the molecular activity (Quantitative
Structure - Activity Relationship, QSAR). Due to the complexity of the proteins, the prediction of their activity is a
complicated task and the interpretation of the models is more difficult. The current review presents a series of 11
prediction models for proteins, implemented as free Web tools on an Artificial Intelligence Model Server in Biosciences,
Bio-AIMS (http://bio-aims.udc.es/TargetPred.php). Six tools predict protein activity, two models evaluate drug - protein
target interactions and the other three calculate protein - protein interactions. The input information is based on the protein
3D structure for nine models, 1D peptide amino acid sequence for three tools and drug SMILES formulas for two servers.
The molecular graph descriptor-based Machine Learning models could be useful tools for in silico screening of new
peptides/proteins as future drug targets for specific treatments.
Keywords: Molecular information, machine Learning, protein graphs, python scripts, QSAR models, Web tools.
Rights & PermissionsPrintExport