search
AI Proteins
Trends
- 1Nobel Laureate Bets $94.6 Million on AI Protein Design▼Nobel Laureate Bets $94.6 Million on AI-Driven Protein Design Beyond Nature
A Nobel laureate is backing AI-driven protein design with a $94.6 million bet, aiming to create proteins that go beyond what exists in nature. The move signals growing confidence that artificial intelligence can engineer entirely new biological molecules, extending the breakthrough work in computational protein design that earned the Nobel Prize and attracting attention across science and investment circles.
- 2Pooled AlphaFold3 screening maps bacterial protein interactions 100 times faster▼Pooled AlphaFold3 screening maps a bacterium’s protein interactions 100 times faster
Researchers have developed a pooled screening approach using AlphaFold3 to map protein-protein interactions in a bacterium, reporting a speed-up of roughly 100 times compared with conventional methods. The technique demonstrates how AI structure prediction can be combined with multiplexed experiments to chart interaction networks far more efficiently, a result drawing attention from structural biology and bioengineering communities.
- 3AI Method Chooses Its Own Training Data to Improve Drug–Target Prediction▼AI Learns to Pick Its Own Lessons: Complexity-Aware Active Learning Boosts Drug–Target Prediction
Researchers report a complexity-aware active learning approach in which an AI system selects its own training examples, improving accuracy in drug–target interaction prediction. The method is described as a way to cut labelling costs and speed up early drug discovery by focusing computational effort on the most informative compounds and protein targets.
- 4Google DeepMind adds watermarks to AI-designed proteins▼Google DeepMind watermarks AI-designed proteins, and the first binders still bind
Google DeepMind has introduced a watermarking method for proteins designed by its AI systems, embedding markers into the molecular structures themselves. The key finding is that the watermark does not ruin the proteins' function: the first designed binders still bind to their targets as intended. The work addresses concerns around tracing and verifying AI-generated biological designs, and researchers are weighing its implications for safety and accountability in computational biology.
- 5Researchers propose function-preserving watermarks for AI-generated proteins▼Function-preserving watermarking of AI-generated proteins
A Nature paper describes a method for embedding watermarks into proteins designed by artificial intelligence without disrupting their biological function. The technique would let scientists mark AI-designed sequences so their origin can be verified, addressing growing concerns about accountability and safety in computational protein design. Researchers say such watermarking could help distinguish machine-generated biomolecules from natural ones as AI tools become widely used in biotechnology.
- 6AI-designed proteins shaping the future of medicine▼AI Proteins: Artificial Intelligence designing the future of medicine
Artificial intelligence is being used to design new proteins, a development that could speed up drug discovery and the treatment of disease. Reports highlight how AI tools can predict and create protein structures that scientists once spent years developing in the lab, opening the door to faster, cheaper medical breakthroughs.
- 7Google DeepMind watermarks AI-generated protein amid Biosec concerns▼Google DeepMind watermarks AI-generated protein as company chief AI scientist Demis Hassabis flags Biosec
Google DeepMind has applied a watermark to an AI-generated protein, with company chief AI scientist Demis Hassabis highlighting Biosec, a system for marking AI-designed biological structures. The move signals an effort to make AI-produced proteins identifiable and traceable, as debate grows over how to safely label and regulate biotechnology outputs generated by artificial intelligence.
- 8DeepGreenGO AI Model Targets Plant Protein Analysis▼AI Built for Green Life: DeepGreenGO Reads Plant Proteins Where Other Models Fail
A new AI system called DeepGreenGO has been developed specifically to analyse plant proteins, an area where existing protein-analysis models reportedly underperform. According to Bioengineer.org, the model is built for applications in plant biology and could support research in agriculture, crop improvement and green biotechnology. The announcement is drawing attention from researchers interested in machine learning tools tailored to biological data.
- 9
Researchers have introduced an AI model designed to fill in missing data in protein mutation maps, predicting how mutations affect protein function where experimental data is lacking. The approach could speed up work in protein engineering, drug development, and the study of genetic disease. Discussion is focused on how well such predictions can replace costly lab experiments.
- 10
Forbes examines how artificial intelligence is transforming the design of therapeutic antibodies, the lab-made proteins behind many modern medicines. AI tools are being used to predict antibody structures, optimise binding and shorten development timelines for new drug candidates. The article reflects growing pharma interest in machine learning to cut costs and speed up the pipeline of antibody-based therapies.
- 11Google tests AI watermarks for designed proteins with SynthID Bio●Google tests AI watermarks for proteins with SynthID Bio
Google DeepMind is extending its SynthID watermarking technology to biology with a tool called SynthID Bio, which embeds hidden markers into AI-designed proteins. The aim is to let researchers identify whether a protein sequence was generated by artificial intelligence, helping distinguish synthetic designs from natural ones and supporting safety and oversight in biotechnology research.
- 12DeepMind adds watermarks to AI-designed proteins▼‘An important piece of the puzzle’: DeepMind watermarks AI proteins
Google DeepMind has introduced a way to watermark proteins designed by its AI systems, which researchers describe as 'an important piece of the puzzle'. The technique embeds identifiable patterns into AI-generated protein structures, helping scientists distinguish synthetic designs from natural ones. The move is seen as a step toward safer, more transparent use of AI in biology and protein engineering.
- 13Google unveils protein watermarking to flag AI-designed bio-tools●Google unveils protein watermarking to flag AI‑designed bio‑tools 💡 If the watermark proves robust, it could become a de
Google has announced a watermarking method for AI-designed proteins, embedding detectable markers into protein structures generated by its models. The goal is to let researchers and regulators identify when a biological tool came from AI design systems. Observers say that if the watermark proves robust, it could become a de facto standard for responsible AI protein design and help distinguish benign research from potentially harmful applications.
- 14What Problems Has AI Actually Solved?●What Has AI Actually Solved? The Biggest Problems Where Machines Found Real Answers Exploring the biggest problems where
A new visualization highlights the concrete breakthroughs where artificial intelligence has delivered real answers, focusing on protein folding, antibiotic discovery, and materials science. The piece is prompting discussion about which scientific problems machines have genuinely cracked, rather than the usual hype, and where AI's practical impact on research has so far been limited.