Skip to content
PesquisaDeepMindGoogle

Google DeepMind uses AI to discover 3 new antibiotic compounds

Manu Ramalho
Manu Ramalho

The AlphaProtein model identified promising compounds against resistant bacteria in just 48 hours of computing.

Loading audio…
Cover image for: Google DeepMind uses AI to discover 3 new antibiotic compounds

Google DeepMind today published a paper in Nature describing how its AlphaProtein model identified three promising compounds against antibiotic-resistant bacteria — a problem WHO classifies as one of the biggest threats to global public health.

The Problem

Antimicrobial resistance causes more than 1.2 million deaths per year. The traditional drug discovery pipeline takes on average 10-15 years and costs more than $1 billion per approved drug.

The approach

AlphaProtein combines two techniques:

  • Proteic structure prediction(AlphaFold evolution) to map bacterial targets
  • Targeted molecular generation to create molecules that bind specifically to these targets

    • In 48 hours of computing in a cluster of TPUs, the model evaluated more than 100 million potential candidates and identified 23 promising molecules. Of these, 3 showed significant efficacy in in vitro MRSA (methicillin-resistant Staphylococcus aureus).

    Next steps

    The three compounds now enter preclinical phase, with tests in animal models scheduled for the second half of 2026. If successful, the first human trials can begin in 2028.

    Demis Hassabis, CEO of DeepMind, stated: "This is exactly the kind of problem the AI was made for. We're not replacing scientists -- we're giving them superpowers."

    Share:

    Source: deepmind.google

    Manu Ramalho

    Written by

    Manu Ramalho

    Sou Manu Ramalho, publicitária com 16 anos de estrada conectando marcas e pessoas. Como fundadora da EME Marketing Digital, sempre busquei o marketing estratégico para gerar conexões autênticas. Aqui, mergulho na fronteira da inteligência artificial como analista de tendências. Meu foco é traduzir a complexidade de NLP, novos modelos de linguagem e papers acadêmicos para o mundo real, sempre com um olhar atento à regulamentação, ética e aos impactos sociais que essa tecnologia imprime na nossa sociedade.

    Related articles