FAQ#
We put Q&A here on a regular basis according to users’ questions.
Usually, computational analysis and modelling of transmembrane protein sequences and structures involve a wide range of procedures and requires different kinds of tools. For this reason, we developed TMKit, to simply address any of such procedures with a unified interface and significantly reduce the workload.
A window of any size is applied to get the identifiers of serially ordered neighbouring residues of a residue/residue pairs of interest.
TMKit integrates seqNetRR, which is a high-performance computing library for constructing a variety of sets of residue connections and assigning features. It runs in linear time with respect to the number of residue pairs used. seqNetRR is mainly designed to learn the surrounding information of residues/residue pairs of interest for machine learning modelling.
seqNetRR works as a module in TMKit.