
ML Tech Lead for Virtual Cell @ArcInstitute
Joined October 2013
- Tweets289
- Following302
- Followers643
- Likes1.7K
Abhinav Adduri retweeted
We're excited to introduce Ladon, the best transcriptomic foundation model designed specifically to address the needs of the clinical community.
We focus our evaluations on clinically relevant tasks and like predicting progression-free survival. The model is trained jointly on bulk RNA and single-cell sequencing data to make the most of RNA.
This is a labor of love, so there is a lot of cool technical content, including cell type deconvolution, joint modeling of expression and isoform sequence, and tissue aware isoform prediction
Today, we are excited to introduce Ladon, a state-of-the-art biological foundation model that predicts disease trajectory and treatment response in patients. There is immense complexity in the individual biology of every patient. Two patients can have the same diagnosis and receive the same treatment, yet have very different outcomes: one responds well and lives for years, while the other’s disease continues to progress. Understanding and resolving this heterogeneity to predict outcomes is how we accelerate our delivery of medicines for patients and unlock clinical trial abundance.
Ladon is our first step towards this future: one where we can learn more from every patient enrolled so that we can run smaller, faster trials with higher success rates. We built it to give drug developers quantitative support on billion-dollar clinical trial decisions. Today we're excited to share Ladon's capabilities in our blog and technical report.
Ladon is a 3B parameter model trained on millions of RNA-seq samples spanning decades of technical and biological variation across tissues and species. Ladon beats gene expression baselines, established biomarkers, and existing RNA foundation models at predicting patient prognosis and therapeutic response in 140+ oncology tasks, including external validation on past clinical trials. This is significant because clinical trials are fundamentally generalization problems. We show that Ladon-derived predictions are robust across indications, treatments, and sequencing platforms.
Reach out if you’d like to get started with the model today!
Read more about Ladon in the blog: blank.bio/introducing-ladon
Find more technical details in the white paper: blank.bio/introducing-ladon
Abhinav Adduri retweeted
Today, we are excited to introduce Ladon, a state-of-the-art biological foundation model that predicts disease trajectory and treatment response in patients. There is immense complexity in the individual biology of every patient. Two patients can have the same diagnosis and receive the same treatment, yet have very different outcomes: one responds well and lives for years, while the other’s disease continues to progress. Understanding and resolving this heterogeneity to predict outcomes is how we accelerate our delivery of medicines for patients and unlock clinical trial abundance.
Ladon is our first step towards this future: one where we can learn more from every patient enrolled so that we can run smaller, faster trials with higher success rates. We built it to give drug developers quantitative support on billion-dollar clinical trial decisions. Today we're excited to share Ladon's capabilities in our blog and technical report.
Ladon is a 3B parameter model trained on millions of RNA-seq samples spanning decades of technical and biological variation across tissues and species. Ladon beats gene expression baselines, established biomarkers, and existing RNA foundation models at predicting patient prognosis and therapeutic response in 140+ oncology tasks, including external validation on past clinical trials. This is significant because clinical trials are fundamentally generalization problems. We show that Ladon-derived predictions are robust across indications, treatments, and sequencing platforms.
Reach out if you’d like to get started with the model today!
Read more about Ladon in the blog: blank.bio/introducing-ladon
Find more technical details in the white paper: blank.bio/introducing-ladon
Abhinav Adduri retweeted
We used coding agents to automatically build baselines for 36 "AI for science" deep learning methods from Nature, Science, and Cell-family publications. These baselines recovered a median of ~95% of the score of the published method, and beat them in 33% of cases.
Abhinav Adduri retweeted
Last night an AI agent performed brain surgery on a mouse.
We gave it 19 gene therapy vectors in a spreadsheet, a mouse model of epilepsy, access to a motorize surgery rig with cameras and one goal: reduce seizures.
It picked the drug. It picked the brain region. It derived the coordinates from three papers. Then it drove the stereotaxic arms into the brain and injected 250 nanolitres while watching the entry site through the rig camera for bleeding.
A licensed vet gated every irreversible step and held a physical kill switch to stop the AI agent.
Thread on what it decided, what it saw, and the moment it refused to let me override it.
[Writing this on the spot out of excitement, but I've been 18hrs in front of my laptop coding and coordinating this, so keeping it brief and descriptive, more cohesive thoughts on this soon...]
Abhinav Adduri retweeted
Programming where and when genes are expressed is a key goal in biology and therapeutic engineering. In a new preprint, @BrianHie, Alex Hao & team report Evo 2 can design enhancers to label single neuronal subtypes in live mouse brains when prompted with <100 example sequences.
Abhinav Adduri retweeted
Language models can learn new tasks from just a few examples in their prompt, with no retraining. This is called in-context learning (ICL). Now genome language models can do it too.
With a handful of examples, Evo 2 ICL generates proteins, de novo antibodies, CRISPR-Cas9 loci, mitochondrial genomes and entire bacteriophages.
We can even use the synthetic sequences iteratively to construct a chain-of-thought (CoT) and achieve harder design goals.
New work with Yukun A. Hao, @BrianHie and team 🧵
Abhinav Adduri retweeted
1/ I’m excited to share our latest preprint introducing COMPASS (COMPrehensive Atlas of Structured Sequences), an atlas of the “dark matter” within the prokaryotic noncoding sequence space, built with a genomic language model. 🧵
Abhinav Adduri retweeted
Excited to share Bolero, out on bioRxiv. @arcinstitute posted a great overview. Here I want to add another perspective that motivated it for us (also a few more higher resolution images).
Abhinav Adduri retweeted
As agents take on longer workflows, the next step is to encode our judgment into their workflows and the infrastructure they run on.
Thank you @abhinadduri of @arcinstitute, @ivanburazin of @daytonaio, Maggie Chung of Voio, and @FHaskaraman of @felicis for the discussion at the MIT AI Conference at @ComputerHistory.
Abhinav Adduri retweeted
Introducing Omnii-1, our most powerful genome language model, and a major step toward general biological intelligence
In a world first, Omnii-1 designed the first AI-generated bacteriophages to be administered to a human patient with an antibiotic-resistant infection under compassionate use
Great work by @i_m_rive !!!
This is my first ever post on X!
And I’d love to share my first ever preprinted work PIE - Perturbation is Everything!
Generalizing across unseen cellular and experimental conditions is challenging but essential to therapeutics discovery. Our latest model PIE addresses this challenge by simplifying the learning objective and leveraging curated biological knowledge from public databases. PIE generalizes across a combinatorial space of perturbation studies, unseen cell lines and unseen perturbations.
Check out the preprint at doi.org/10.64898/2026.10.02.…
Huge shoutout to the team at @arcinstitute for driving this project:@abhinadduri , @beabevi_ , @basak_ersln , @davey_burke , @genophoria , @yusufroohani .
1
2
323
Abhinav Adduri retweeted
We're hosting a small event to discuss the latest advances in AI and biology this Friday evening, featuring @arcinstitute researchers and others. Apply if interested! forms.gle/1fh1GpHrimqu1HkEA
Abhinav Adduri retweeted
Genomes are full of dark matter of unknown functions.
We present Minerva, a new method for discovery guided by genome language models. Minerva reveals the interactions hidden in non-coding DNA, pointing to hundreds of new putative RNAs and repetitive elements per bacterial genome. Minerva allows us to find and study elements invisible to traditional methods at orders of magnitude greater scale than before.
Abhinav Adduri retweeted
Evolution builds genes by recombining domains from existing ones. Innovation Investigator @Roth_Lab and colleagues introduce DESynR, a platform that does this on demand, creating new genes that outperform their natural counterparts in human CAR T cells.
Abhinav Adduri retweeted
GenBio was founded with the audacious goal of simulating all of biology. The natural starting point for biological simulation is the cell: the smallest unit of life. Today we're sharing a preview of our first version of that simulator, AIDO Cell.
Abhinav Adduri retweeted
An internal version of Astra, @OpenAI’s next major model family, solved 10 major open problems in mathematics, quantum complexity, and theoretical computer science.
We believe it will be a major step for scientific reasoning. openai.com/index/ten-advance…
Abhinav Adduri retweeted
Statistical estimation is being absorbed into context.
In a new 90-page review, we provide a unified view of statistical and foundation models through the lens of context-adaptive inference! ...
sweet work by the team! slowly the AIxBio platform stack is being built out. application layer is going to be very exciting in the coming years
Imagine programming protein, DNA, and RNA systems like you would write computer code, or even by natural language prompting of an AI agent. @brianhie and team just made this a reality with Proto: a high-level programming language for generative biology.
Abhinav Adduri retweeted
Biological engineering has long aimed to design living systems with the programmability of software, but the tools to do so rarely fit together.
Today, we’re sharing our preprint introducing Proto, a high-level programming language for generative biology that composes models and design tools across DNA, RNA, and proteins to optimize towards user-specified functional objectives.
Nice read from Xiaotong Fu et al
How much biology can we recover from single-cell latent representations? 🧬
Latent spaces have become the backbone of modern single-cell analysis. They power atlas integration, foundation models, and increasingly perturbation prediction and Virtual Cell approaches.
Yet there is a surprisingly basic question that has received little attention:
👉 How well can we reconstruct gene expression from these latent representations?
In our new work, we introduce ReconEval, a benchmark for gene expression reconstruction across more than 100 million cells. We systematically evaluate three settings:
🔹 End-to-end reconstruction (PCA, autoencoders, VAEs)
🔹 Foundation model reconstruction (a new benchmark task for single-cell foundation models, asking how much gene-level information can be recovered from pretrained embeddings)
🔹 Latent shift reconstruction (evaluating reconstruction after perturbation prediction models operate in latent space)
A few takeaways:
📊 Autoencoders (not VAEs) achieve the strongest stand-alone reconstruction performance. This is perhaps not surprising, as reconstruction is exactly their training objective.
🧠 Foundation model embeddings retain substantial recoverable gene-level information, although performance depends strongly on the decoder and pretraining strategy.
🔬 The optimal latent representation depends on the downstream task. What works best for reconstruction is not necessarily what works best after perturbation prediction.
As the field moves toward increasingly sophisticated Virtual Cell models, reconstruction deserves more attention as an evaluation axis ie another task to evaluate. Ultimately, biological interpretation happens in gene expression space, not in latent coordinates.
Congratulations to Xiaotong Fu for driving this project and to all collaborators involved in making this benchmark possible. 👏
📄 Preprint: biorxiv.org/content/10.64898…
💻 Code: github.com/theislab/ReconEva…
#SingleCell #ComputationalBiology #VirtualCell
3
536






























