In silico screening of 15 polyphenols and reference compounds against MMP-1 + SIRT1 for topical photoaging: real Boltz-2 data positions EMB-3 at the top of the panel; Resveratrol leads SIRT1 axis; classical references (vitamin C, niacinamide, ferulic acid) rank low

Photoaging — UV-induced premature dermal change including wrinkle formation, elastosis, pigment irregularity — is mediated by MMP-1 (interstitial collagenase, the principal photoaging effector) and SIRT1 (NAD-dependent deacetylase, longevity / DNA-repair regulator), among other targets. We screen 15 compounds against MMP-1 + SIRT1 using Boltz-2 cofold (cached MSAs) and ADMET-AI v2.0.1. FBN1, mTOR, and elastin were NOT screened (cached MSAs absent) — substantially narrowing the photoaging-target panel. Real Boltz-2 results identify EMB-3 (the AI-derived embelin scaffold-hop from companion preprint [3]) as top mean affinity (0.621) — even surpassing the parent Embelin (0.601) — driven by paired moderate engagement of MMP-1 (0.610) and SIRT1 (0.632). Resveratrol leads SIRT1 axis (0.588), consistent with the established resveratrol–SIRT1 pharmacology. EGCG scores moderately (mean 0.520; MMP-1 0.570; SIRT1 0.470) — substantially lower than the v0.1 fabricated values (claimed 0.71 and 0.65 respectively). Classical antioxidant references (vitamin C, niacinamide, ferulic acid) rank low (mean 0.331 – 0.394), consistent with Boltz-2's underranking of fragment-size compounds. The v0.1 framing of EGCG as a "universal compound" engaging 12 targets at probability ≥ 0.50 was synthesized from non-real numbers and is explicitly retracted. EGCG remains a moderate multi-target topical-cosmeceutical candidate but is not exceptional in our actual screen. All results are in silico.