Recently I came across the paper "Deep generative design of RNA aptamers using structural predictions" by Wong et al. in Nat Comput Sci. I am pleased to see DSSR cited in this high-profile publication as below:

As secondary-structure constraints may provide useful information, RhoDesign concatenates the output of the GVP encoder with the contact map derived from secondary-structure information, which for PDB structures was produced using DSSR⁴² with default settings, and for RhoFold-predicted structures was produced using RhoFold (as detailed further below).

As discussed above, we leveraged experimentally determined structures from the PDB. We utilized DSSR⁴² with its default settings to extract contact maps from the PDB structures. These contact maps provide information about the spatial arrangement of base pairs within RNA molecules, augmenting model learning of structural features. Additionally, as discussed above, to address the limited availability of PDB data for training our models, we leveraged RhoFold-predicted structures for our model training. For these structures, the corresponding contact maps were directly generated by RhoFold.

Here DSSR was employed as a standard tool, with its default settings, for extracting RNA secondary structures from PDB coordinates. As noted in the 2015 paper "DSSR: an integrated software tool for dissecting the spatial structure of RNA",

The default cutoff values are based on extensive tests in real-world applications (6,7), and work well even for distorted structures.

Many efforts have been put into details of DSSR so that it works (mostly) in its default settings. It is gratifying to see DSSR cited in this manner in this Nat Comput Sci publication.