Search Results for "estimates"

In the regulatory assessment of chemicals (e.g. under REACH), Quantitative Structure Activity Models (QSAR) are playing an increasingly important role in predicting properties for hazard and risk assessment. This implies both a need to be able to identify relevant QSARs and to use them to derive estimates and/or have access to their precalculated estimates. To help meet these needs, the JRC QSAR Model Database is established and freely accessible through http://qsardb.jrc.ec.europa.eu/qmrf The QSAR Model Reporting Format (QMRF) is a harmonised template for summarising and reporting key information on QSAR models, including the results of any validation studies. ...

The GNNPCSAFT Web App is an implementation of our project that focuses on using Graph Neural Networks (GNN) to estimate the pure-component parameters of the Equation of State PC-SAFT. We developed this app so the scientific community can access the model's results easily. In this app, the estimated pure-component parameters can be used to calculate thermodynamic properties and compare them with experimental data from the ThermoML Archive. More info on github repository.

A GUI application which estimates toxic hazard of chemical compounds. The latest version includes the following toxicity prediction modules: -Cramer rules (oral toxicity) -Toxicity mode of action via Verhaar scheme -Skin irritation and Eye irritation prediction -Benigni / Bossa rulebase for mutagenicity and carcinogenicity prediction -START biodegradation and persistence prediction -Skin sensitisation reactivity domain -Kroes TTC Decision tree -SMARTCyp - Cytochrome P450-Mediated Drug Metabolism and metabolites prediction -Structure Alerts for the in vivo micronucleus assay in rodents (ISSMIC) -Structural Alerts for Functional Group Identification (ISSFUNC) -Structural alerts associated with covalent protein binding and DNA binding...

...Version 2 also includes code that facilitates combining localization data from two spectral channels using a locally-weighted quadratic 3D registration function Features - Double-Gaussian estimator is calibrated via an axial scan of bright immobile fluorescent emitters (e.g. beads) - DH localization is performed through template matching and subsequent double Gaussian fitting - Tiff stacks of SM images are analyzed using template matching followed by double-Gaussian fitting to extract estimates of the molecule positions - Two spectral channels are registered by generating a locally-weighted quadratic mapping function from control point pairs