Over the past two decades, statistical machine learning methods have been successfully employed in the structural, functional and interaction profiles research of proteins and peptides. The structural and physicochemical descriptors have been intensively applied in the research of protein structure and functionalities, including
and many more challenging biological problems. Sequence-derived structural and physicochemical descriptors are critically important for these tasks.
Here we present ProtrWeb, a web server based on our R package protr, dedicated to compute such structural and physicochemical descriptors. Currently, ProtrWeb offers twelve types of the commonly used descriptors presented in the protr package.
The protr package offers more proteochemometric modeling descriptors, miscellaneous tools and datasets, and more customized descriptors could be crafted by using the protr package directly.