←
Tiago Costa462 posts
Tiago Costa avatar

Tiago Costa

@CostaT_Lab

Associate Professor and Group Leader @imperialcollege. We study the architecture and function of molecular machines that drive AMR dissemination and virulence.

◷ Joined November 2017▧ 13 Photos and videos
Tiago Costa avatar
Tiago Costa@CostaT_Lab·Aug 10

We have reflect on how AI could reshape scientific reasoning and discovery - not by replacing scientists, but by helping us escape our own biases, expand the hypothesis space, and consider mechanisms we might never have imagined. 🔗sciencedirect.com/science/ar…

Tiago Costa avatar
Tiago Costa@CostaT_Lab·Jun 5

📢 We are recruiting! I’m looking for a Research Associate in Structural Biology to join my lab at Imperial College London to study horizontal gene transfer using cryo-EM, biochemistry and microbiology. Please share with interested candidates! Apply: shorturl.at/gmJGS

Tiago Costa avatar
Tiago Costa@CostaT_Lab·May 28

Our new study on how bacterial toxins are physically captured through a sequential, concentration-dependent assembly mechanism before secretion via the T6SS. Congrats to all co-authors, especially Patricia & Ambre for leading this work. shorturl.at/O31Vn

RTP Notícias avatar
⟳ Tiago Costa retweeted
RTP Notícias@RTPNoticias·May 27

A Inteligência Artificial está a poupar anos de investigação e validação científica. Isso mesmo acaba de ser comprovado num estudo da resistência aos antibióticos de um investigador português. rtp.pt/noticias/pais/ia-na-i…

Vivek Natarajan avatar
⟳ Tiago Costa retweeted
Vivek Natarajan@vivnat·May 19

Out of all the announcements at @Google I/O today, this is the one closest to my heart - our foundational research on Co-Scientist was published in @Nature and we announced its broad availability via @GeminiApp for Science. When you are suffering from a disease, time is everything. As our collaborator and @StanfordMed Professor Dr. Gary Peltz reminds us, there are thousands of diseases out there with zero treatments. There is simply so much left to solve. Our goal with Co-Scientist has been to give scientists superpowers and help them get to these answers faster - compressing the scientific process from months and years down to hours and days. Much like Galileo's telescope helped us look into the stars, Co-Scientist is designed to help us make sense of the vast complexity of biological and scientific data. It is among the first examples of a truly general-purpose multi-agent system for scientific discovery. The core research question behind it was: How can an AI system engage in the rigorous, structured thinking that’s the hallmark of science and scientists? To tackle this, Co-Scientist builds on the principles of self-play and self-improvement underpinning @GoogleDeepMind breakthroughs like AlphaGo, generalizing them to scientific reasoning through self-debates. Since our preprint last year, we have further improved its capabilities and have been validating it in collaborations with scientists across over 100 institutions globally, spanning both academia and industry. And we are thrilled to see the emergence of a new form of AI-human scientist collaboration that's already leading to important new insights, discoveries and peer reviewed publications - from understanding antimicrobial resistance (published in @CellCellPress) to decoding plant immunity, to identifying new treatments for liver fibrosis (Advanced Science), cancer, neurodegenerative diseases like ALS and the grand challenge of aging. I have always believed AI's greatest promise is accelerating scientific discovery and advancing human health. My genuine hope for the future is that AI tools like Co-Scientist help democratize science, giving anyone, anywhere the means to pursue their child-like curiosity and change the world. This work was done with stellar team mates spanning @GoogleDeepMind @GoogleResearch, @googlecloud and @GoogleLabs especially Juro Gottweis (@Mysiak ), who is the heart and soul of this effort. Special thanks also to all our wonderful collaborators: Gary Peltz, @CostaT_Lab, @jrpenades, @_e_d_v_ , @iambyronic, @OpsBug, @jgooten, @omarabudayyeh Ritu Raman, Ryan Flynn, Filippo Menolascina, Velia Siciliano, Clare Bryant, Matt Onsum, Katherine Labbé and more. Nature paper link - lnkd.in/e8qBEJFv Google DeepMind blog - lnkd.in/etYeahMy Gemini for Science - labs.google/science.

6:27
Vivek Natarajan avatar
⟳ Tiago Costa retweeted
Vivek Natarajan@vivnat·Mar 18

Great to see this feature in Nature Medicine! When our team at @GoogleDeepMind @GoogleResearch introduced the AI Co-Scientist in our February 2025 preprint, we knew we were on the cusp of a fundamental shift in how research is done. To see the work inspire the community and catalyze a global movement to accelerate scientific discovery in such a short time is incredibly thrilling. Huge shoutout to our amazing collaborators Prof @jrpenades @CostaT_Lab of @ImperialCollege and Prof Gary Peltz at @StanfordMed Medicine who took the leap with us and pushed the boundaries to validate this new paradigm of human-AI collaboration in science. So much momentum and so much more to come, rather soon 😊 Link: rdcu.be/e8xmk With @Mysiak @alan_karthi and so many incredible Google teammates behind AI Co-Scientist.

Post attachmentPost attachmentPost attachmentPost attachment
Tiago Costa avatar
Tiago Costa@CostaT_Lab·Mar 4

Please RT:📢We are hiring a Post-Doc in Structural Biology to join our multidisciplinary team. Project: study molecular mechanisms of horizontal gene transfer using cryo-EM and integrative structural biology. Apply: shorturl.at/ecrVL #StructuralBiology #CryoEM #Postdoc

Tiago Costa avatar
⟳ Tiago Costa retweeted
Tiago Costa@CostaT_Lab·30 Nov 2025

🚨 PhD Opportunity in my lab🚨 Harnessing Phage Satellites for Next-Generation Biological Crop Protection 🗓 Deadline: 12 Jan 🔗 Apply: tinyurl.com/425x8ahj 🔗 Project : tinyurl.com/22uanm86 Interested in Structural Microbiology, Phage Biology & SynBio - Apply Now!

Yossi Matias avatar
⟳ Tiago Costa retweeted
Yossi Matias@ymatias·10 Dec 2025

The multi-agent AI co-scientist system (employing Generation, Reflection, Ranking and Evolution agents) has three key attributes: simulation of scientific debate between pairwise combinations of generated hypotheses, test-time compute scaling to improve outputs, and an internal auto-evaluation metric. Research collaboration with academic partners confirms its potential for drug repurposing for Acute Myeloid Leukemia, and for insights related to Liver Fibrosis.

As 2025 wraps up, we're sharing some highlights✨ Last month we unveiled generative UI, a capability allowing AI models to create immersive, interactive experiences for any prompt (trip planning, redecorating, etc) — available in the Gemini app via an experiment called dynamic view & in AI Mode in Google Search. For example, check out this Little Chemists Lab experience: generativeui.github.io/stati…

Yossi Matias avatar
⟳ Tiago Costa retweeted
Yossi Matias@ymatias·10 Dec 2025

In a panel with @CostaT_Lab, our partner from Imperial College London, and with @vivnat we’ve discussed how Google’s co-scientist demonstrated AI’s core reasoning capability by performing novel reasoning on lab’s unpublished on a complex antimicrobial resistance mechanism, Picture from the panel

Post attachment
IEEE Spectrum avatar
⟳ Tiago Costa retweeted
IEEE Spectrum@IEEESpectrum·25 Sep 2025

The AI co-scientist from @GoogleAI is proving itself more than a novelty. In two bio studies, it generated promising, testable hypotheses that could have taken years of lab work to uncover. With insights from @vivnat, @KyleWSwanson, and other experts. spectrum.ieee.org/ai-co-scie…