Decision-Making AI For The Enterprise

InstaDeep delivers AI-powered decision-making systems for the Enterprise. With expertise in both machine intelligence research and concrete business deployments, we provide a competitive advantage to our customers in an AI-first world.

Learn More

Building AI systems for the industry

Leveraging its expertise in GPU-accelerated computing, deep learning and reinforcement learning, InstaDeep has built AI systems to tackle the most complex challenges across a range of industries and sectors.

Biology Biology

Biology

Read More
Logistics Logistics

Logistics

Read More
Electronic Design Electronic Design

Electronic Design

Read More
Energy Energy

Energy

Read More

Latest

Our latest updates from across our channels

InstaDeep at IndabaX Tunisia 2025 - Empowering Through Knowledge

InstaDeep at IndabaX Tunisia 2025 – Empowering Through Know...

on May 14, 2025 | 11:43am

Continuing our commitment to supporting AI talent in the region, InstaDeep was proud to sponsor and take part at the 6th edition of IndabaX Tunisia 2025, held on May 3-4 at the Hi...

Flexible antibody design with AbBFN2

Flexible antibody design with AbBFN2...

on May 06, 2025 | 10:42am

Disclaimer: All claims made are supported by our research paper: A Flexible Antibody Foundation Model Based on Bayesian Flow Networks unless explicitly cited otherwise. Antibod...

Enhancing Peptide Sequencing with AI

Enhancing Peptide Sequencing with AI...

on Mar 31, 2025 | 09:01am

AI is revolutionising proteomics and has the potential to unlock new frontiers in targeted healthcare and biomedical research. At the heart of this is peptide sequencing, an essen...

ProtBFN was developed to address this challenge. ProtBFN is a 650-million-parameter Bayesian Flow Network (BFN) trained on a curated dataset of 72 million biologically validated examples, optimised for generating new protein sequences.

Exploring the Proteome with ProtBFN...

on Mar 06, 2025 | 11:59am

Proteins are essential to life, driving nearly every biological process and performing critical functions in the human body—from building muscles to fighting diseases. Understan...

The AI Action Summit was an event that brought together world leaders, business experts and research luminaries as they uncovered the path ahead for the development of AI around the globe, and with the InstaDeep team being in the thick of the action throughout. Join us below as we share some of the highlights.

InstaDeep at the AI Action Summit, Grand Palais, Paris...

on Feb 20, 2025 | 11:45am

The AI Action Summit was an event that brought together world leaders, business experts and  research luminaries as they uncovered the path ahead for the development of AI around...

New heights - InstaGeo at the AI Action Summit 2025

New heights – InstaGeo at the AI Action Summit 2025...

on Feb 10, 2025 | 05:04pm

Learn how the InstaGeo team led the way in AI for Social Good at the AI Action Summit in Paris, where their work is gaining recognition for its tangible impact. As we step...

Building the Future of Food Security - GeoAI Hack

Building the Future of Food Security – GeoAI Hack...

on Feb 07, 2025 | 03:48pm

Bringing together over 100 participants from around the world in teams building novel AI-powered geospatial tools to solve real-world challenges in climate adaptation. The...

AI Action Summit - Coming Together to Build the Future of AI

AI Action Summit – Coming Together to Build the Future of A...

on Feb 04, 2025 | 10:47am

AI is evolving at an unprecedented rate. Worldwide, leaders are striving to grasp the implications of this transformative technology while ensuring its economic and societal benef...

The GeoAI Hackathon on 4-5 February 2025, co-organised by InstaDeep and datacraft, invites AI enthusiasts, developers, and innovators to create solutions that harness the transformative power of artificial intelligence and geospatial data.

GeoAI Hackathon: Tackling Africa’s Locust Crisis with AI Innova...

on Jan 23, 2025 | 01:09pm

Desert locust swarms represent one of the greatest threats to food security in Africa. Capable of consuming their weight in crops daily, these pests devastate livelihoods, destroy...

Celebrating Breakthroughs: Dr Andrija Sente Honoured During Nobel...

on Dec 16, 2024 | 10:27am

Each year in Stockholm, Nobel Prize Week celebrates the ideas and breakthroughs that have transformed our understanding of the world. In the same week (6–12 December), the Scien...

Research

Leveraging State Space Models in Long Range Genomics

Matvei Popov | Aymen Kallala | Anirudha Ramesh | Narimane Hennouni | Shivesh Khaitan | Rick Gentry | Alain-Sam Cohen

ICLR LMRL (2025) May 2025
Comparison of the extrapolation methods of state-space models and attention-based models on VEP eQTLs (AUROC). For NTv2, we also reported an inference-time extrapolation method: position interpolation. A dotted vertical line indicates the fine-tuning sequence length (12 kbp) of all models. Attention-based models collapse when processing sequences that are longer than what they have encountered at training time, whereas state-space models show an ability to generalize to sequences up to 10x longer. Lines that turn into dotted indicate values that we were unable to compute due to computational cost constraints and are therefore assumed based on trends.

Open-Source and FAIR Research Software for Proteomics

Lukas Käll | Yasset Perez-Riverol | Wout Bittremieux | William S. Noble | Lennart Martens | Aivett Bilbao | Michael R. Lazear | Bjorn Grüning | Daniel S. Katz | Michael J. MacCoss | Chengxin Dai | Jimmy K. Eng | Robbin Bouwmeester | Michael R. Shortreed | Enrique Audain | Timo Sachsenberg | Jeroen Van Goey | Georg Wallmann | Bo Wen | William E. Fondrie

May 2025
Open-source software (OSS), aligned with the FAIR Principles (Findable, Accessible, Interoperable, Reusable), offers a solution by promoting transparency, reproducibility, and community-driven development, which fosters collaboration and continuous improvement. In this manuscript, we explore the role of OSS in computational proteomics, its alignment with FAIR principles, and its potential to address challenges related to licensing, distribution, and standardization.

AbBFN2: A flexible antibody foundation model based on Bayesian Flow Networks

Bora Guloglu | Miguel Bragança | Alex Graves | Scott Cameron | Timothy Atkinson | Liviu Copoiu | Alexandre Laterre | Thomas D. Barrett

May 2025

Metalic: Meta-Learning In-Context with Protein Language Models

Jacob Beck | Shikha Surana | Manus McAuliffe | Oliver Bent | Thomas D. Barrett | Juan Jose Garau Luis | Paul Duckworth

ICLR 2025 Apr 2025
Our method, called Metalic (Meta-Learning In-Context), uses in-context learning and fine-tuning, when data is available, to adapt to new tasks.

Simple Guidance Mechanisms for Discrete Diffusion Models

Hugo Dalla-Torre | Sam Boshar | Bernardo P. de Almeida | Thomas Pierrot | Yair Schiff | Subham Sekhar Sahoo | Hao Phung | Guanghan Wang | Alexander Rush | Volodymyr Kuleshov

ICLR 2025 Apr 2025
Guidance mechanisms for discrete diffusion

De novo peptide sequencing with InstaNovo: Accurate, database-free peptide identification for large scale proteomics experiments

Kevin Eloff | Konstantinos Kalogeropoulos | Oliver Morell | Amandla Mabona | Jakob Berg Jespersen | Wesley WIlliams | Sam P. B. van Beljouw | Marcin Skwark | Andreas Hougaard Laustsen | Stan J. J. Brouns | Stan J. J. Brouns | Erwin M. Schoof | Jeroen Van Goey | Ulrich auf dem Keller | Karim Beguir | Nicolas Lopez Carranza | Timothy P. Jenkins

Nature Machine Intelligence Mar 2025

In the Press

Partners

InstaDeep
Privacy Overview

Please read our extensive Privacy policy here. You can also read our Privacy Notice and our Cookie Notice