Several in-house developed descriptors and our in-house docking tool ActDock were
compared with virtual screening on the data set of useful decoys (DUD). The results were …

Advancements in neural machinery have led to a wide range of algorithmic solutions for
molecular property prediction. Two classes of models in particular have yielded promising …

Motivation: Molecular representation for small molecules has been routinely used in
QSAR/SAR, virtual screening, database search, ranking, drug ADME/T prediction and other …

We present three simple, yet effective data mining techniques for lazy structure− activity
relationships (SARs) of noncongeneric compounds. In lazy SARs, classifications are …

We outline an algorithm for construction of novel molecular descriptors from known structural
invariants or molecular properties viewed as descriptors. The novel descriptors are bond …

Quantifying imperfect symmetry of molecules can help explore the sources, roles and extent
of structural distortion. Based on the established methodology of continuous symmetry and …

Quantitative structure–activity relationship (QSAR) is a branch of computer aided drug
discovery that relates chemical structures to biological activity. Two well established and …

Discovering essential features shared by active compounds, an important step in drug-
design, is complicated by conformational flexibility. We present a new algorithm to efficiently …

Exchange of chemical information without disclosure of the respective structures would
greatly increase the data sets available for model building. Within the framework of the …

The calculation of structure descriptors is the first major step in building models that allow
the prediction of data or properties of chemical compounds from their structure by inductive …