There are 4 repositories under qsar topic.
A Deep Learning Toolkit for DTI, Drug Property, PPI, DDI, Protein Function Prediction (Bioinformatics)
OpenChem: Deep Learning toolkit for Computational Chemistry and Drug Design Research
Code for the paper Enhancing Activity Prediction Models in Drug Discovery with the Ability to Understand Human Language
An R package to calculate indices and theoretical physicochemical properties of peptides and protein sequences.
QSARtuna: QSAR model building with the optuna framework
Chemical representation learning paper in Digital Discovery
The backend services of the GenUI framework. The backend provides the REST API used for molecular generation, QSAR modelling and chemical space visualization.
Automated QSAR based on multiple small molecule descriptors
PyTorch implementation of the paper "Automatic Chemical Design Using a Data-Driven Continuous Representation of Molecules"
Generate Boltzmann-weighted Sterimol Steric Parameters for Conformationally-Flexible Substituents
A cheminformatics package to perform Applicability Domain of molecular fingerprints based in similarity calculation.
Automated framework for the curation of chemogenomics data and to develop QSAR models for virtual screening using the open-source KNIME software
GenUI frontend application. It provides a GUI to the GenUI REST API web services.
MolEnc: a molecular encoder using rdkit and OCaml.
drugdesign.org source of truth
Classification models for hemolytic nature and hemolytic activity predictions in peptide/protein sequences
Simple web application for prediction of reaction rate constant through machine learning models using molecular fingerprints.
Code for "Enhance Information Propagation for Graph Neural Network by Heterogeneous Aggregations"
Application for detecting functional groups of a molecules.
QSAR models and putative agents identified against SARS-CoV-2
LigEGFR: Spatial graph embedding and molecular descriptors assisted bioactivity prediction of ligand molecules for epidermal growth factor receptor on a cell line-based dataset
This repository contains a QSAR model that predicts the ability of a chemical compound to inhibit the gene associated with Alzheimer's, Beta-Secratese 1
The diversity of RNA structural elements and their documented role in human diseases make RNA an attractive therapeutic target. However, progress in drug discovery and development has been hindered by challenges in the determination of high-resolution RNA structures and a limited understanding of the parameters that drive RNA recognition by small molecules, including a lack of validated quantitative structure-activity relationships (QSAR). Herein, we developed QSAR models that quantitatively predict both thermodynamic and kinetic-based binding parameters of small molecules and the HIV-1 TAR model system. Small molecules bearing diverse scaffolds was screened against the HIV-1 TAR using surface plasmon resonance. Then multiple linear regression (MLR) combined with feature selection was performed to afford robust models that allowed direct interpretation of properties critical for both binding strength and kinetic rate constants. These models were externally validated with new molecules and their accurate performance confirmed via comparison to ensemble tree methods.
A package to perform fingerprints from spectroscopy datas.
Secure multiparty computation for privacy-preserving drug discovery
Reference implementation of the Distance-Based Boolean Applicability Domain for HTS datasets
Allows to visualize and analyze if the molecules of the test set and of an external set are contained in the convex hull defined by the molecules of the training set.
A repository to build and deploy GenUI docker images. GenUI is a collection of web services for interactive molecular generation, QSAR modelling and chemical space visualization.
Reference implementation of the Vanishing Ranking Kernels (VRK) method
A computational tool for the prediction and identification of metabolites.
A modular inverse QSAR pipeline