Researchers unveiled SMRTnet, a deep‑learning framework that predicts small molecule–RNA interactions using RNA secondary structure and multimodal modeling, bypassing the need for tertiary structural data. The model identified 40 candidate small molecules with nanomolar‑to‑micromolar binding across disease‑associated RNA targets and validated hits that modulate MYC IRES activity. SMRTnet significantly expands the feasible RNA target space for small‑molecule discovery and offers medicinal chemists an in silico prioritization tool to accelerate hit finding against noncoding and structured RNAs.