Sentence examples for predictions for compounds from inspiring English sources

The models obtained can be employed to predict activities of the compounds designed and/or form predictions for compounds that exist and have not yet been examined with biological inhibitory assays.

The predictions for compounds that include Li, K, or Na are particularly illustrative.

In that analysis alone, we have swapped the signs of any predictions of positive log S values where this would reduce the error; this means that all such predictions for compounds with negative experimental log S values had their signs provisionally changed.

However, because all the models are developed in kNN QSAR modeling by interpolating activities of the nearest neighbor compounds only in the relevant training sets, a special applicability domain (i.e., similarity threshold) should be introduced to avoid making predictions for compounds that differ substantially from the training set molecules.

Therefore, the pharma industry is mainly working with compounds from the "drug-like" region of chemical space and the accuracy of prediction for compounds from this region is the most important for drug discovery.

We conclude that there are three SVM hyperparameters selection approaches worth using for activity prediction for compounds: libSVM heuristic (when only one set of hyperparameters is needed), random search (when we need a strong model quickly, using less than a few dozen iterations), a Bayesian approach (when we want the strongest model and can wait a bit longer).

Availability of chemical response-specific lists of genes (gene sets) for pharmacological and/or toxic effect prediction for compounds is limited.

However, existing modeling tools generally do not achieve good external accuracy of prediction for compounds not used in model development, and few QSAR models have been successful in predicting in vivo toxicity end points for diverse sets of environmental compounds (Benigni et al. 2007; Stouch et al. 2003).

Alternatively, there may be six very similar compounds which satisfy the first check on similarity; but of course if the predictions for these compounds are wrong, the model is not reliable in this specific case.

The reason is that predictions for new compounds, which have the parameter values in the ranges defined by the parameter values of tested compounds, can essentially be done using various model-free intrapolations.

However, further data accumulation is still needed to improve the assay performance because the eROS assay provided false predictions for some compounds.