01955nas a2200397   4500000000100000008004100001260001500042100001500057700001400072700001500086700001700101700001300118700001400131700001700145700001400162700001500176700001500191700001700206700001700223700001600240700001200256700001500268700001700283700001100300700001500311700001600326700001200342700001700354700001400371700001500385245006800400856005600468300001300524490000800537520101200545       2026                            d  c2026-01-081 aYinjun Jia1 aBowen Gao1 aJiaxin Tan1 aJiqing Zheng1 aXin Hong1 aWenyu Zhu1 aHaichuan Tan1 aYuan Xiao1 aLiping Tan1 aHongyi Cai1 aYanwen Huang1 aZhiheng Deng1 aXiangwei Wu1 aYue Jin1 aYafei Yuan1 aJiekang Tian1 aWei He1 aWeiying Ma1 aYaqin Zhang1 aLei Liu1 aChuangye Yan1 aWei Zhang1 aYanyan Lan00aDeep contrastive learning enables genome-wide virtual screening  uhttps://www.science.org/doi/10.1126/science.ads9530  aeads95300 v3913 aRecent breakthroughs in protein structure prediction have opened new avenues for genome-wide drug discovery, yet existing virtual screening methods remain computationally prohibitive. We present DrugCLIP, a contrastive learning framework that achieves ultrafast and accurate virtual screening, up to 10 million times faster than docking, while consistently outperforming various baselines on in silico benchmarks. In wet-lab validations, DrugCLIP achieved a 15% hit rate for norepinephrine transporter, and structures of two identified inhibitors were determined in complex with the target protein. For thyroid hormone receptor interactor 12, a target that lacks holo structures and small-molecule binders, DrugCLIP achieved a 17.5% hit rate using only AlphaFold2-predicted structures. Finally, we released GenomeScreenDB, an open-access database providing precomputed results for ~10,000 human proteins screened against 500 million compounds, pioneering a drug discovery paradigm in the post-AlphaFold era.