AllTheBacteria turns 2.44 million genomes into an AI-ready resource for new antibiotics
shae_mcl · x · 2026-07-22
A quoted discussion argues that biology has far less labeled data than AI systems usually need: many disease-relevant protein targets have fewer than 20 binding datapoints, while deep learning often needs 1,000+ examples and balanced labels to generalize well.
The reply points to the preprint AllTheBacteria, which turns 2.44 million public bacterial and archaeal genomes into a uniformly processed, searchable, AI-ready resource. The paper uses that platform to find new peptide antibiotics, including ATB20, which reduced Acinetobacter baumannii burden in a mouse skin-abscess model with efficacy comparable to polymyxin B.
Related event: AllTheBacteria Standardizes 2.44M Genomes for AI, Finding New Antibiotics(3 posts)→
More from Research
- Marin's Open Scaling Law Extrapolates 300× and Predicts Loss Within 0.2% — dlwh · 2026-10-27
- Marin's dlwh Explains the Scaling Law Fit: Estimating the Loss Floor Early — dlwh · 2026-10-27
- Marin Shares Forecast-vs-Measured Plots: Paloma Hits 0.4% RMS Error — dlwh · 2026-10-27
- AW-0 hits 80.8% on RoboTwin tasks, beating strongest baseline by 16 points — trevordarrell · 2026-10-27
- AW-0's code stream fixes world model prediction: picks mango where baseline grabs apple — trevordarrell · 2026-10-27
- AW-0 debuts: one generative world action model plans in code, predicts, and controls robots — trevordarrell · 2026-10-27