NK-RCPP: a receptor-conditioned computational workflow for prioritizing neurokinin-receptor peptide candidates

NK-RCPP applied to 96 neurokinin-receptor peptide candidates found lower matched on-target REF15 scores than controls for 14/32 NK1R, 23/32 NK2R, and 6/32 NK3R candidates.

• Why it matters: Closely related neurokinin receptors require comparing target-directed scores with evidence from other structural contexts, but selection can shift with how neighbour information is incorporated.
• What they did: The workflow combined receptor-matched on-target REF15 scoring with 4,518 paired structural-neighbour comparisons across 82 candidates, then applied a neighbour-score criterion with a 0.75 threshold.
• The result: Adding neighbour scoring retained 16 of 33 evaluable on-target-favoured candidates, reducing the pool by 51.5%, and at matched shortlist sizes half the identities differed from on-target-only selection.