What does this equation mean?

High-throughput virtual screening takes the opposite approach: rather than proposing new compositions, it exhaustively scores a library that already exists. The clearest demonstration is ultra-large library docking, in which researchers computationally docked a library of 170 million make-on-demand compounds, built from 130 well-characterized reactions, against two protein targets: AmpC beta-lactamase and the D4 dopamine receptor [ 8 ] . Against AmpC, 99 million library members were scored, 51 top-ranked compounds were selected and 44 synthesized, yielding an 11% hit rate and, after optimization, a 77-nanomolar inhibitor among the most potent non-covalent AmpC inhibitors then known. Against D4, 138 million compounds were scored, 589 selected and 549 synthesized, and 122 bound the receptor — a hit rate that fell roughly monotonically as docking score worsened. That monotonic relationship is itself the interesting result, because it let the authors extrapolate a library-wide estimate rather than test everything directly: $\hat{N}_{\text{hits}} \;\approx\; \sum_{s} h(s)\, N(s)$. where h(s) is the hit rate measured directly among compounds actually synthesized and tested at docking-score bin s , and N(s) is the number of untested library members scored into that bin. Applying this to the D4 results produced an estimate of roughly 453,000 ligands across the full 138-million-compound library — a projection under an assumed score-to-hit-rate relationship, not a directly counted total. Confirmed hits included a 180-picomolar, subtype-selective D4 agonist, one of 81 new chemotypes with no prior literature precedent, 30 of which showed submicromolar activity. This is screening logic, not generative logic: nothing here proposes a molecule outside the pre-enumerated library, and the achievement is exhaustive search of a known space rather than invention of a new one.