Discovery of Novel 4,5-Dihydropyrrolo[3,4-<i>c</i>]pyrazol-6(<i>2H</i>)-one-Based Tubulin Inhibitors Targeting Colchicine Binding Site with Potent Anti-Ovarian Cancer Activity

To address the toxicity of current microtubule inhibitors, we employed the GeminiMol deep learning model to screen the Zinc20 database, identifying a novel 4,5-dihydropyrrolo[3,4-<i>c</i>]pyrazol-6(2<i>H</i>)-one scaffold (<b>Y1</b>) targeting the colchicine binding site. Subsequent optimization culminated in <b>Y60s</b>, a potent antiproliferative agent (SKOV3 IC₅₀ = 0.025 μM) that inhibits clonogenic formation, migration, and invasion of ovarian cancer cells. <b>Y60s</b> inhibited tubulin polymerization which in turn induced G2/M arrest and apoptosis in SKOV3 cells. <b>Y60s</b> demonstrated potent antitumor activity without observable toxicity in an SKOV3 xenograft model. The cocrystal structure of <b>Y8</b> in complex with tubulin was resolved, confirming the key binding mode of 4,5-dihydropyrrolo[3,4-<i>c</i>]pyrazol-6(2<i>H</i>)-one compounds. This work showcases <b>Y60s</b> as a promising novel tubulin inhibitor and highlights the utility of deep learning model for rapid identification of bioactive compounds from large chemical databases.