Predicts many kinds of biological activity for compounds from different chemical series based on their 2D structural formulas. PASS finds new targets mechanisms for some ligands. It can reveal new ligands for some biological targets. The tool can be used to analyze the occurrence, in a database, of compounds predicted to be active for a well-defined set of PASS activities.
Assesses bioactivities of ligands interacting with G protein-coupled receptors (GPCRs). WDL-RF is a web application based on a weighted deep learning (WDL) associated with a random forest (RF) regression model. The platform includes the possibility to install the software locally for allowing users to determine bioactivities of specific compounds against a GPCR target, elaborate their own virtual screening models or to create molecular fingerprints for new compounds.
Allows extraction of data from the ‘Open Pharmacological Space’ (OPS) developed by the Open PHACTS project. Collector is an application that extracts series of compounds from OPS, together with the result of pharmacological/toxicological experiments. The software applies customizable curation filters, produces series of compounds in a format well suited for the development of quantitative structure-activity relationships (QSAR models). It was used in the eTOX project for the development of QSAR models against targets considered of toxicological interest (anti-targets).
Consists of an approach to multiple kernel learning (MKL) in pairwise spaces. pairwiseMKL is a program based on a formulation of Kronecker decomposition of the centering operator which couples pairwise kernel weights optimization and pairwise model training. This software can be applied in quantitative drug bioactivity prediction to deduce anticancer potential of drug compounds or to determine drug-protein interactions.
Designed to predict the bioactivity of small molecules for drug discovery applications. AtomNet is a structure-based deep convolutional neural network (CNN) which combines information about the ligand with information about the structure of the target. The locally-constrained deep convolutional architecture allows the system to model the complex, non-linear phenomenon of molecular binding by hierarchically composing proximate basic chemical features into more intricate ones. The algorithm can predict new active molecules even for targets with no previously known modulators.
Annotates bioassay protocols by using semantic web terms. BioAssay Express enables searching, sorting, clustering and analyzing of assays without needing to read through the original text. This software exploits a Common Assay Template based on underlying vocabularies and semantic standards from BioAssay Ontology, Drug Target Ontology, Cell Line Ontology and others. Users can also identify similar assays and examine the similarity of assays between and within organizations.
0 - 0 of 0