Biology has no shortage of data. The challenge is to organize it well enough that scientists—and machines—can learn from it. Our latest preprint presents AllTheBacteria: an open, community-built platform that transforms 2.44 million public bacterial and archaeal genomes into a uniformly processed, searchable, and AI-ready resource. To demonstrate what becomes possible at this scale, we used the platform to discover new peptide antibiotics. One candidate, ATB20, reduced Acinetobacter baumannii burden in a murine skin-abscess model, with efficacy comparable to polymyxin B. More broadly, this work illustrates how open, standardized biological data can help us use machines to understand and engineer biology—and accelerate the discovery of new potential solutions for human health. Deeply grateful to the remarkable international team behind this work: Martin Hunt, Daniel Anderson, Maria Luiza Andreani, Josefin Blom, Michael B. Hall, Samuel T. Horsfield, Hyun-Su Lee, Leandro Lima, Neil MacAlasdair, William Matlock, Vignesh Ramnath, Vishnu Raghuram, Matthew J. Russell, Liam P. Shaw, Gerry Tonkin-Hill, Jackie Toussaint, Fangping Wan, Laura M. Carroll, Matthew A. Croxen, @mdt_torres, @happy_khan, @GB13Faithless, @fionabrinkman, @AndresFloto, @yekwah, @bfjia, @Jake_A_Lacey, @sudaraka_m, @Ahmed_Microbes, @rpetit3, @theosanderson, @TimoSaratto, @oschwengers1, @torstenseemann, @shenwei356, @nrt_thomson, @thanhleviet, @vWachsmann, @aaron_weimann, @WheatleyRM, @wiatrak_maciej, @ouli_xie, @johnlees6, and @ZaminIqbal. With colleagues across @sangerinstitute, @emblebi, @NDMOxford, @Penn, @TheQuadram, @TheCGPS, Universidade Estadual de Campinas, @Ucmr_sweden, @BHIresearch, @mbbsfu, @WCHRIUofA, @LKSIoV, @CC4AIM, @HLRI_Cambridge, @AlfredMonash_ID, @CentreImpactAMR, @UniNeuchatel, @TheDohertyInst, @PeterMacCC, @UniOslo, @MilnerCentre, @LSHTM, @jlugiessen, @BristolBiochem, @Cambridge_SBS, and Theiagen Genomics. biorxiv.org/content/10.1101/…