The scientist using AI to hunt for antibiotics just about everywhere

2026-02-16 · Source: MIT Technology Review · Field: Health & Wellbeing — Pharmaceuticals & Biotechnology, Health & Medical Research, Medical Devices & Health Technology · Depth: Intermediate, medium

Summary

César de la Fuente, an associate professor at the University of Pennsylvania, leads the Machine Biology Group in using artificial intelligence to discover new antibiotics. His team trains AI tools to scan genomes for peptides with antimicrobial properties, aiming to assemble novel peptide configurations to combat drug-resistant infections. This research has identified promising candidates from diverse sources, including ancient single-celled organisms like archaea, animal venoms, and even extinct species such as woolly mammoths and Neanderthals, leading to compounds like mammuthusin-2. De la Fuente's work addresses the growing crisis of antimicrobial resistance, which causes over 4 million deaths annually and is projected to exceed 8 million by 2050. His group is developing a multimodal AI model called ApexOracle to analyze pathogens, identify genetic weaknesses, and predict the efficacy of peptide-based antibiotics, pushing the field from discovery towards clinical testing.

Key takeaway

For AI Researchers and Bioengineers focused on drug discovery, your efforts in applying generative AI to biological "code" are critical. The ability to design novel antimicrobial peptides from diverse, even extinct, genetic sources represents a significant shift from traditional brute-force methods. You should prioritize developing multimodal AI models like ApexOracle to accelerate candidates toward clinical testing, potentially saving decades of research time and addressing the looming post-antibiotic era.

Key insights

AI-driven peptide discovery from diverse biological sources offers a novel approach to combat antimicrobial resistance.

Principles

• Biology functions as an information source or "code."
• Antimicrobial peptides (AMPs) offer multimodal action.
• Generative AI can design novel therapeutic molecules.

Method

Train AI models to recognize antimicrobial peptide sequences within genetic code, then synthesize and test these peptides, including those from extinct species, to develop new antibiotics.

In practice

• Scan ancient genomes for novel antimicrobial peptides.
• Design synthetic peptides using generative AI models.
• Develop multimodal AI for pathogen analysis and drug prediction.

Topics

• Antimicrobial Resistance
• AI Drug Discovery
• Antimicrobial Peptides
• Genomic Mining
• Machine Biology

Best for: AI Researcher, AI Scientist, Research Scientist

Related on AIssential

• 3 Questions: Using AI to accelerate the discovery and design of therapeutic drugs — AI, particularly deep learning and generative models, significantly accelerates novel antibiotic discovery and design.
• Data-driven surrogates of rational design enable antimicrobial peptide optimization — Generative AI and data-driven surrogates enable rapid optimization of antimicrobial peptides against drug resistance.
• Using synthetic biology and AI to address global antimicrobial resistance threat — Synthetic biology and AI can develop programmable antibacterials to combat rising antimicrobial resistance.
• Using AI to outsmart drug-resistant bacteria — AI tools significantly accelerate antibiotic discovery by identifying non-intuitive biological patterns and generating novel therapeutic ideas.
• The hunt for the next antibiotics — Antimicrobial resistance threatens global health, necessitating urgent, diverse research into new antibiotics and resistance mitigation.
• 🗞️ Techie uses ChatGPT and AlphaFold to build DIY mRNA cancer vaccine, saves dog — AI tools empower individuals without specialized training to conduct complex scientific research and develop novel solutions.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by MIT Technology Review.