Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

Evo: a foundation model for genomics! Using a well suited architecture, Evo learns from billions of bp of genomic sequence and performs well on several zero-shot prediction tasks on RNA, DNA and protein. Beautiful paper from Brian Hie & Patrick Hsu at Arc Institute

JuliaBauman2's profile picture

Julia Bauman

10,458 subscribers

52,367 Aufrufe • vor 2 Jahren •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

14 Kommentare

Profilbild von Julia Bauman
Julia Baumanvor 2 Jahren

Preprint link here:

Profilbild von ksminnovation
ksminnovationvor 1 Jahr

Dr. Tal Patalon explores how AI mega initiatives like the $500B Stargate project & AI-powered genomic analysis by Illumina & NVIDIA are transforming healthcare. @TalPatalon @forbes @edengallery_ #AIinHealthcare #PrecisionMedicine #Multiomics #HealthTech

Profilbild von Matt Durrant
Matt Durrantvor 2 Jahren

@BrianHie @pdhsu @arcinstitute Thank you for highlighting our work!

Profilbild von Dmitry Penzar
Dmitry Penzarvor 2 Jahren

@BrianHie @pdhsu @arcinstitute What are you about the fact their model do activity prediction worse than gc-content?

Profilbild von Misha
Mishavor 2 Jahren

@BrianHie @pdhsu @arcinstitute very good presentation

Profilbild von Ashton C Trotman-Grant
Ashton C Trotman-Grantvor 2 Jahren

@BrianHie @pdhsu @arcinstitute Yes! Awesome summary Julia. This paper is so cool

Profilbild von Nishant Jha
Nishant Jhavor 2 Jahren

@BrianHie @pdhsu @arcinstitute Been noodling on a playground for evo here:

Profilbild von ريان
ريانvor 2 Jahren

@BrianHie @pdhsu @arcinstitute Julia — what do you think about the fact that they claim to generate functional CRISPR-Cas systems without experimental validation?

Profilbild von Julia Bauman
Julia Baumanvor 2 Jahren

@BrianHie @pdhsu @arcinstitute I think that they’re going to do the experimental validation :)

Profilbild von Dr Rob Leigh
Dr Rob Leighvor 2 Jahren

@BrianHie @pdhsu @arcinstitute Paging Dr @Cian_Smyth

Profilbild von Neuropunk
Neuropunkvor 2 Jahren

@BrianHie @pdhsu @arcinstitute Its about time we move to fully synthetic biology. This is where all the cures, improvements and the most deadly weapons of humanity lie

Profilbild von Ryan Metz
Ryan Metzvor 2 Jahren

@BrianHie @pdhsu @arcinstitute Great work

Profilbild von Sean Jackewicz, MD 🧬🛠️
Sean Jackewicz, MD 🧬🛠️vor 2 Jahren

@BrianHie @pdhsu @arcinstitute Oooooo this could be so cool

Profilbild von Bin Shao
Bin Shaovor 2 Jahren

Very nice video! I do hope some day people can create a similar one for our language model…

Ähnliche Videos

Evo 2, our fully open-source biological foundation model trained on trillions of DNA tokens spanning the entire tree of life, is out in nature today We & the scientific community have done a lot with this Arc Institute NVIDIA model in the last year! 🧵👇
0:50

Evo 2, our fully open-source biological foundation model trained on trillions of DNA tokens spanning the entire tree of life, is out in nature today We & the scientific community have done a lot with this Arc Institute NVIDIA model in the last year! 🧵👇

Patrick Hsu

248,156 Aufrufe • vor 4 Monaten

🚀 We're thrilled to introduce Orthrus 🧬🐕—a groundbreaking mature RNA foundation model designed to push the boundaries of RNA property prediction! 🔬 What is Orthrus? Orthrus is a Mamba-based RNA foundation model, pre-trained using a novel self-supervised contrastive learning objective with biologically inspired augmentations. It optimizes the similarity between splicing isoforms and orthologous transcripts, capturing functional and evolutionary relationships to enhance mature RNA property prediction accuracy. 📑 Preprint: 💻 Code: 🌐 Project Page: 📦 Model Weights: 🧠 Why Orthrus? Decoding the RNA regulatory code is key to understanding biology, but traditional experimental approaches are slow and costly. Existing genomic foundation models rely on techniques like masked language modeling or next-token prediction, which aren't fully aligned with the complexities of genomic data—leading to suboptimal results. 🌟 Orthrus Highlights: - Biologically-Informed Contrastive Learning 🧪: A novel contrastive learning objective designed specifically for genomics, maximizing similarity between splicing isoforms and orthologous transcripts across species. - Extensive Pre-training 📊: Trained on splicing annotations from 10 species and orthologous alignments from 400+ mammalian species (Zoonomia Project), with a focus on sequences of high functional importance. - Superior Representations🏅: Orthrus outperforms existing genomic models on 5 mRNA property prediction tasks, often surpassing supervised methods with just a simple linear transformation. - Efficiency in Low-Data Settings📉: Orthrus excels in low-data regimes, achieving state-of-the-art results with as few as 45 labeled examples for fine-tuning on RNA half-life prediction. Shoutout to the amazing leading authors Phil (Phil Fradkin) and Ian (Ian Shi)! Also the work is impossible without an outstanding collaboration by Karina (Karin(a) Isaev), Brendan (Brendan Frey) , Quaid (Quaid Morris), Leo J. Lee! Vector Institute University Health Network U of T Department of Computer Science Temerty Centre for AI in Medicine (T-CAIREM) Department of Laboratory Medicine & Pathobiology
0:53

🚀 We're thrilled to introduce Orthrus 🧬🐕—a groundbreaking mature RNA foundation model designed to push the boundaries of RNA property prediction! 🔬 What is Orthrus? Orthrus is a Mamba-based RNA foundation model, pre-trained using a novel self-supervised contrastive learning objective with biologically inspired augmentations. It optimizes the similarity between splicing isoforms and orthologous transcripts, capturing functional and evolutionary relationships to enhance mature RNA property prediction accuracy. 📑 Preprint: 💻 Code: 🌐 Project Page: 📦 Model Weights: 🧠 Why Orthrus? Decoding the RNA regulatory code is key to understanding biology, but traditional experimental approaches are slow and costly. Existing genomic foundation models rely on techniques like masked language modeling or next-token prediction, which aren't fully aligned with the complexities of genomic data—leading to suboptimal results. 🌟 Orthrus Highlights: - Biologically-Informed Contrastive Learning 🧪: A novel contrastive learning objective designed specifically for genomics, maximizing similarity between splicing isoforms and orthologous transcripts across species. - Extensive Pre-training 📊: Trained on splicing annotations from 10 species and orthologous alignments from 400+ mammalian species (Zoonomia Project), with a focus on sequences of high functional importance. - Superior Representations🏅: Orthrus outperforms existing genomic models on 5 mRNA property prediction tasks, often surpassing supervised methods with just a simple linear transformation. - Efficiency in Low-Data Settings📉: Orthrus excels in low-data regimes, achieving state-of-the-art results with as few as 45 labeled examples for fine-tuning on RNA half-life prediction. Shoutout to the amazing leading authors Phil (Phil Fradkin) and Ian (Ian Shi)! Also the work is impossible without an outstanding collaboration by Karina (Karin(a) Isaev), Brendan (Brendan Frey) , Quaid (Quaid Morris), Leo J. Lee! Vector Institute University Health Network U of T Department of Computer Science Temerty Centre for AI in Medicine (T-CAIREM) Department of Laboratory Medicine & Pathobiology

Bo Wang

114,913 Aufrufe • vor 1 Jahr

From sequence to structure, in one sentence.⚡ Today’s Agent Spotlight: Boltz-2 Structure Prediction Agent on ASI:One. Built on Massachusetts Institute of Technology (MIT)’s cutting-edge Boltz-2 model and deployed via NVIDIA's API, this agent generates 3D biomolecular structures just from a natural language prompt. Supports proteins, DNA, RNA, ligands, constraints, and even MSA data. Ideal for drug discovery, molecular biology, and biotech research. Try now: Link to Agent: Watch 👇
2:09

From sequence to structure, in one sentence.⚡ Today’s Agent Spotlight: Boltz-2 Structure Prediction Agent on ASI:One. Built on Massachusetts Institute of Technology (MIT)’s cutting-edge Boltz-2 model and deployed via NVIDIA's API, this agent generates 3D biomolecular structures just from a natural language prompt. Supports proteins, DNA, RNA, ligands, constraints, and even MSA data. Ideal for drug discovery, molecular biology, and biotech research. Try now: Link to Agent: Watch 👇

Fetch.ai

13,972 Aufrufe • vor 1 Jahr

watch me realize in realtime that Greg Brockman is deadly serious about character-level tokenization and it's already working well for Patrick Hsu, Silvana Konermann, and Patrick Collison's Arc Institute 's 40B model that is the "GPT-1 of DNA" with biological language models (instead of natural language), we may finally be able to understand the causes of genetic conditions like Ehlers-Danlos syndrome, scanning the billions of base pairs of individual human DNA in a massively scaled up way only AI can do. Superintelligent healthcare may be the one thing that excites me more than superintelligent coding agents.
5:34

watch me realize in realtime that Greg Brockman is deadly serious about character-level tokenization and it's already working well for Patrick Hsu, Silvana Konermann, and Patrick Collison's Arc Institute 's 40B model that is the "GPT-1 of DNA" with biological language models (instead of natural language), we may finally be able to understand the causes of genetic conditions like Ehlers-Danlos syndrome, scanning the billions of base pairs of individual human DNA in a massively scaled up way only AI can do. Superintelligent healthcare may be the one thing that excites me more than superintelligent coding agents.

swyx

75,685 Aufrufe • vor 11 Monaten

Meet BFM-Zero: A Promptable Humanoid Behavioral Foundation Model w/ Unsupervised RL👉 🧩ONE latent space for ALL tasks ⚡Zero-shot goal reaching, tracking, and reward optimization (any reward at test time), from ONE policy 🤖Natural recovery & transition
1:17

Meet BFM-Zero: A Promptable Humanoid Behavioral Foundation Model w/ Unsupervised RL👉 🧩ONE latent space for ALL tasks ⚡Zero-shot goal reaching, tracking, and reward optimization (any reward at test time), from ONE policy 🤖Natural recovery & transition

Yitang Li

81,957 Aufrufe • vor 8 Monaten

Today we're introducing TRIBE v2 (Trimodal Brain Encoder), a foundation model trained to predict how the human brain responds to almost any sight or sound. Building on our Algonauts 2025 award-winning architecture, TRIBE v2 draws on 500+ hours of fMRI recordings from 700+ people to create a digital twin of neural activity and enable zero-shot predictions for new subjects, languages, and tasks. Try the demo and learn more here:
0:29

Today we're introducing TRIBE v2 (Trimodal Brain Encoder), a foundation model trained to predict how the human brain responds to almost any sight or sound. Building on our Algonauts 2025 award-winning architecture, TRIBE v2 draws on 500+ hours of fMRI recordings from 700+ people to create a digital twin of neural activity and enable zero-shot predictions for new subjects, languages, and tasks. Try the demo and learn more here:

AI at Meta

6,942,700 Aufrufe • vor 4 Monaten

Excited to release METAGENE-1, a 7B parameter metagenomic foundation model, built to aid in pathogen detection & pandemic monitoring. Pretrained on 1.5 trillion base pairs of DNA/RNA sequenced from wastewater. A collab w/ USC, Prime Intellect, & the Nucleic Acid Observatory. 🧵
0:29

Excited to release METAGENE-1, a 7B parameter metagenomic foundation model, built to aid in pathogen detection & pandemic monitoring. Pretrained on 1.5 trillion base pairs of DNA/RNA sequenced from wastewater. A collab w/ USC, Prime Intellect, & the Nucleic Acid Observatory. 🧵

Willie Neiswanger

13,390 Aufrufe • vor 1 Jahr

🚨David Friedberg: AI is starting to identify and solve problems on its own “I'll give you a science corner example: there's this Evo 2 model that they publish at the Arc Institute, which Patrick Collison, you know, is the main funder and chairman.” “So that Evo 2 model, they just ingested all the DNA data they could find in the world.” “Trillions and trillions of base paired data that they ingested and then they looked at patterns in DNA. And that's it.” “They had no context for what the DNA represented, they had no context for the concept of genes, none of the structured understanding of what that DNA does, what it is, and you know what it did?” “They fed in the BRCA gene variant and the thing output a warning saying, ‘I think that this is a pathogenic variant to DNA,’ without having any context.” “This is the breast cancer allele.” “And it didn't have any knowledge and it wasn't trained on that at all.” “It had no knowledge that there are pathogenic variants for cancer, and it identified that this was a genetic variant that can cause some sort of pathogenic outcome in the organism.” “That's a great example where there's a lack of understanding at the human level on what really drives some of the patterns in nature, the patterns in society, the patterns in behavior that are kind of emergent phenomena perhaps, that these AI models are starting to identify.”
1:03

🚨David Friedberg: AI is starting to identify and solve problems on its own “I'll give you a science corner example: there's this Evo 2 model that they publish at the Arc Institute, which Patrick Collison, you know, is the main funder and chairman.” “So that Evo 2 model, they just ingested all the DNA data they could find in the world.” “Trillions and trillions of base paired data that they ingested and then they looked at patterns in DNA. And that's it.” “They had no context for what the DNA represented, they had no context for the concept of genes, none of the structured understanding of what that DNA does, what it is, and you know what it did?” “They fed in the BRCA gene variant and the thing output a warning saying, ‘I think that this is a pathogenic variant to DNA,’ without having any context.” “This is the breast cancer allele.” “And it didn't have any knowledge and it wasn't trained on that at all.” “It had no knowledge that there are pathogenic variants for cancer, and it identified that this was a genetic variant that can cause some sort of pathogenic outcome in the organism.” “That's a great example where there's a lack of understanding at the human level on what really drives some of the patterns in nature, the patterns in society, the patterns in behavior that are kind of emergent phenomena perhaps, that these AI models are starting to identify.”

The All-In Podcast

79,718 Aufrufe • vor 1 Jahr

Introducing a small portion of proprietary phenomics data from Recursion into the training of MolGPS, our foundation model for molecular property prediction, led to massive performance increases on new & existing benchmarks. Learn more about the impact of data & scale.
1:46

Introducing a small portion of proprietary phenomics data from Recursion into the training of MolGPS, our foundation model for molecular property prediction, led to massive performance increases on new & existing benchmarks. Learn more about the impact of data & scale.

Valence Labs

10,091 Aufrufe • vor 1 Jahr

Happy to share what I’ve been working on since joining Genesis! GENE-26.5 is a one-of-a-kind, robotics-native multimodal foundation model that learns from diverse, in-the-wild data across modalities and outputs actions enabling a 54-DoF robot system to perform the most dexterous, long-horizon manipulation tasks to date—approaching human-level capability. This is the result of innovations across the full stack—data collection and processing, robot systems, model architecture, training strategies, and scalable evaluation infrastructure.
2:23

Happy to share what I’ve been working on since joining Genesis! GENE-26.5 is a one-of-a-kind, robotics-native multimodal foundation model that learns from diverse, in-the-wild data across modalities and outputs actions enabling a 54-DoF robot system to perform the most dexterous, long-horizon manipulation tasks to date—approaching human-level capability. This is the result of innovations across the full stack—data collection and processing, robot systems, model architecture, training strategies, and scalable evaluation infrastructure.

Zu Wang

19,493 Aufrufe • vor 2 Monaten

Cerebras and Mayo Clinic are proud to announce a new state-of-the-art foundation model for genomics. The breakthrough was made possible by combining Mayo Clinic's extensive patient data with the Cerebras AI platform, training on over a trillion tokens to create complex genomic models that can guide personalized treatment decisions. Read more:
0:23

Cerebras and Mayo Clinic are proud to announce a new state-of-the-art foundation model for genomics. The breakthrough was made possible by combining Mayo Clinic's extensive patient data with the Cerebras AI platform, training on over a trillion tokens to create complex genomic models that can guide personalized treatment decisions. Read more:

Cerebras

44,578 Aufrufe • vor 1 Jahr

What good is a science communication channel if you don't get to talk about your own papers on it occasionally, right?😊 We developed a method to simultaneously sequence single-cell DNA and RNA targets, enabling association of genomic variants (including non-coding!) with gene expression changes. Out today in Nature Methods, from Lars Steinmetz lab led by Dominik Lindenhofer! Link below⬇️
2:10

What good is a science communication channel if you don't get to talk about your own papers on it occasionally, right?😊 We developed a method to simultaneously sequence single-cell DNA and RNA targets, enabling association of genomic variants (including non-coding!) with gene expression changes. Out today in Nature Methods, from Lars Steinmetz lab led by Dominik Lindenhofer! Link below⬇️

Julia Bauman

47,074 Aufrufe • vor 11 Monaten

A healthy liver enhances overall well-being. Glimpses from the 'Healthy Liver-Healthy India’ programme organised by the Institute of Liver and Biliary Science on World Liver Day.
0:52

A healthy liver enhances overall well-being. Glimpses from the 'Healthy Liver-Healthy India’ programme organised by the Institute of Liver and Biliary Science on World Liver Day.

Amit Shah

660,730 Aufrufe • vor 1 Jahr

DARPA—who developed the Operation Warp Speed Death Jabs (see tweet 2)—now wants to inject people with "protein complexes" that, when hit with "different wavelengths of light" will "synthesize specific DNA or RNA sequences on demand." DARPA = literal Nazis. Nuremberg for DARPA! ----------------Partial transcription of clip--------------- "Synthetic DNA and RNA molecules could enable a host of next-generation technologies crucial for national security and global well-being. However, current methods for creating these molecules from scratch face significant limitations in terms of their scale, complexity, and use of hazardous chemicals. DARPA's Generative Optogenetics Program. "GO seeks to harness the power of light to direct the synthesis of DNA and RNA directly within living cells. If successful, this high-risk, high-reward research program has the potential to revolutionize medicine, agriculture, and manufacturing. "GO aims to unlock an era of programmable biology where we can communicate with and direct cell behavior with unprecedented speed, precision, and reach via optical signals. Performers on GO will design protein complexes that, when expressed in a living cell, use light-triggered signaling to deliver genetic information, instructing cells to incorporate specific building blocks based on different wavelengths of light to synthesize specific DNA or RNA sequences on demand. "The GO program focuses on two main research objectives. The first is achieving the core capability of synthesizing DNA or RNA directly in living cells using optical signals. The second focuses on developing error-mitigation methods that ensure high-fidelity nucleic acid synthesis."
1:26

DARPA—who developed the Operation Warp Speed Death Jabs (see tweet 2)—now wants to inject people with "protein complexes" that, when hit with "different wavelengths of light" will "synthesize specific DNA or RNA sequences on demand." DARPA = literal Nazis. Nuremberg for DARPA! ----------------Partial transcription of clip--------------- "Synthetic DNA and RNA molecules could enable a host of next-generation technologies crucial for national security and global well-being. However, current methods for creating these molecules from scratch face significant limitations in terms of their scale, complexity, and use of hazardous chemicals. DARPA's Generative Optogenetics Program. "GO seeks to harness the power of light to direct the synthesis of DNA and RNA directly within living cells. If successful, this high-risk, high-reward research program has the potential to revolutionize medicine, agriculture, and manufacturing. "GO aims to unlock an era of programmable biology where we can communicate with and direct cell behavior with unprecedented speed, precision, and reach via optical signals. Performers on GO will design protein complexes that, when expressed in a living cell, use light-triggered signaling to deliver genetic information, instructing cells to incorporate specific building blocks based on different wavelengths of light to synthesize specific DNA or RNA sequences on demand. "The GO program focuses on two main research objectives. The first is achieving the core capability of synthesizing DNA or RNA directly in living cells using optical signals. The second focuses on developing error-mitigation methods that ensure high-fidelity nucleic acid synthesis."

Sense Receptor

50,875 Aufrufe • vor 7 Monaten

We're thrilled to present ESM3 in Science Magazine. ESM3 is a generative language model that reasons over the three fundamental properties of proteins: sequence, structure, and function. Today we're making ESM3 available free to researchers worldwide via the public beta of an API for biological intelligence. Trained with over a trillion teraflops of compute, this is the first time a model of this scale has been trained for biology, pushing the frontier of AI for biological discovery and engineering. ESM3 learns to represent the immense complexity of protein biology, learning from billions of natural proteins. From this training it developed the capability to design proteins, responding to complex prompts combining atomic level details and high level instructions to generate new proteins. ESM3 can explore protein space far beyond natural evolution. We prompted ESM3 to generate a fluorescent protein at a far distance from any known fluorescent proteins, searching an unknown region of protein space, to discover a new fluorescent protein. We estimate this is equivalent to simulating five hundred million years of evolution.
1:31

We're thrilled to present ESM3 in Science Magazine. ESM3 is a generative language model that reasons over the three fundamental properties of proteins: sequence, structure, and function. Today we're making ESM3 available free to researchers worldwide via the public beta of an API for biological intelligence. Trained with over a trillion teraflops of compute, this is the first time a model of this scale has been trained for biology, pushing the frontier of AI for biological discovery and engineering. ESM3 learns to represent the immense complexity of protein biology, learning from billions of natural proteins. From this training it developed the capability to design proteins, responding to complex prompts combining atomic level details and high level instructions to generate new proteins. ESM3 can explore protein space far beyond natural evolution. We prompted ESM3 to generate a fluorescent protein at a far distance from any known fluorescent proteins, searching an unknown region of protein space, to discover a new fluorescent protein. We estimate this is equivalent to simulating five hundred million years of evolution.

Alex Rives

227,314 Aufrufe • vor 1 Jahr

🔬 Exciting News! Our manuscript, "scGPT: toward building a foundation model for single-cell multi-omics using generative AI" is now finally published in Nature Methods (Nature Methods) 🎉 !!! (Re-)Introducing scGPT: A transformative foundation model engineered for single-cell omics analysis. Developed through the analysis of over 33 million human cells, scGPT sets a new benchmark for application versatility, offering both fine-tuning and zero-shot capabilities. Since its preprint in May 2023, scGPT has significantly impacted the field, evidenced by 13K+ installations, 600+ GitHub stars 🌟, and 40+ citations before its official publication! scGPT has been validated by numerous benchmark studies as a leading foundation model in single-cell analysis. Its pre-trained embeddings extend its utility beyond single-cell studies, enhancing a variety of downstream tasks including protein enrichment and genetic perturbation predictions. Some key updates lately: ---Expanded zero-shot applications for efficient reference mapping and integration, now with CellXGene census integration. ---Advanced perturbation analysis capabilities, including genome-scale perturb-seq data analysis and bulk sequencing data generalization. ---Upgraded scGPT package, offering versatile model loading compatible with PyTorch and flash-attn, for both GPU and CPU. ---Cloud-based scGPT applications for reference mapping, cell annotation, and gene regulatory network inference are available on ---Integration with Hugging Face for easier model training. Limitations: scGPT is an early foray into foundation models for single-cell omics, facing challenges like limited zero-shot learning in some tasks, pretraining constraints, data quality issues, and evaluation limitations. See our Supplementary Notes for details. 🚀 Future Work? Short-Term Goals: 1. Releasing a Mouse Model for broader analysis. 2. Developing a comprehensive evaluation suite for foundation models in single-cell analysis. 3. Creating a foundation model for single-cell spatial omics. 4. Enhancing zero-shot capacity by integrating scGPT with RAG (e.g., knowledge graphs). Long-Term Goals: 1. Expanding scGPT for comprehensive single-cell multi-omics analysis. 2. Developing an in-silico perturbation model for predicting genetic perturbation effects. 3. Merging scGPT with multi-modal genomic sequence models for a deeper understanding of cell biology. 📚 Access the paper on Nature Methods: 🔬Preprint in Bioarixv: 💻 All our codes/data/weights are open source: Wholehearted congratulations to all the authors, especially the two co-first authors, Haotian (Haotian Cui ) and Chloe (ChloeXWang), who are really the emerging superstars in AI and biology! Vector Institute Peter Munk Cardiac Centre AI U of T Department of Computer Science Department of Laboratory Medicine & Pathobiology University Health Network University of Toronto #scGPT #GenerativeAI #AI4Science #Combio #opensource
0:52

🔬 Exciting News! Our manuscript, "scGPT: toward building a foundation model for single-cell multi-omics using generative AI" is now finally published in Nature Methods (Nature Methods) 🎉 !!! (Re-)Introducing scGPT: A transformative foundation model engineered for single-cell omics analysis. Developed through the analysis of over 33 million human cells, scGPT sets a new benchmark for application versatility, offering both fine-tuning and zero-shot capabilities. Since its preprint in May 2023, scGPT has significantly impacted the field, evidenced by 13K+ installations, 600+ GitHub stars 🌟, and 40+ citations before its official publication! scGPT has been validated by numerous benchmark studies as a leading foundation model in single-cell analysis. Its pre-trained embeddings extend its utility beyond single-cell studies, enhancing a variety of downstream tasks including protein enrichment and genetic perturbation predictions. Some key updates lately: ---Expanded zero-shot applications for efficient reference mapping and integration, now with CellXGene census integration. ---Advanced perturbation analysis capabilities, including genome-scale perturb-seq data analysis and bulk sequencing data generalization. ---Upgraded scGPT package, offering versatile model loading compatible with PyTorch and flash-attn, for both GPU and CPU. ---Cloud-based scGPT applications for reference mapping, cell annotation, and gene regulatory network inference are available on ---Integration with Hugging Face for easier model training. Limitations: scGPT is an early foray into foundation models for single-cell omics, facing challenges like limited zero-shot learning in some tasks, pretraining constraints, data quality issues, and evaluation limitations. See our Supplementary Notes for details. 🚀 Future Work? Short-Term Goals: 1. Releasing a Mouse Model for broader analysis. 2. Developing a comprehensive evaluation suite for foundation models in single-cell analysis. 3. Creating a foundation model for single-cell spatial omics. 4. Enhancing zero-shot capacity by integrating scGPT with RAG (e.g., knowledge graphs). Long-Term Goals: 1. Expanding scGPT for comprehensive single-cell multi-omics analysis. 2. Developing an in-silico perturbation model for predicting genetic perturbation effects. 3. Merging scGPT with multi-modal genomic sequence models for a deeper understanding of cell biology. 📚 Access the paper on Nature Methods: 🔬Preprint in Bioarixv: 💻 All our codes/data/weights are open source: Wholehearted congratulations to all the authors, especially the two co-first authors, Haotian (Haotian Cui ) and Chloe (ChloeXWang), who are really the emerging superstars in AI and biology! Vector Institute Peter Munk Cardiac Centre AI U of T Department of Computer Science Department of Laboratory Medicine & Pathobiology University Health Network University of Toronto #scGPT #GenerativeAI #AI4Science #Combio #opensource

Bo Wang

199,711 Aufrufe • vor 2 Jahren

Grok 3 now available in beta in the Box AI Studio, and it performs extremely well at single and multi-doc Q&A as well as enterprise data extraction. Here's a test with Box AI where it generates a comprehensive report based on a number of earnings documents.
1:22

Grok 3 now available in beta in the Box AI Studio, and it performs extremely well at single and multi-doc Q&A as well as enterprise data extraction. Here's a test with Box AI where it generates a comprehensive report based on a number of earnings documents.

Aaron Levie

46,104 Aufrufe • vor 1 Jahr

A NEW episode of The Four Horsemen is streaming everywhere now! Thorin, Richard Lewis, and MonteCristo go in-depth on SonicFox's response to Saudi Arabia's Evo acquisition, Gaimin Gladiators withdrawing from TI, and the "superfan experience" at EWC.
2:18:42

A NEW episode of The Four Horsemen is streaming everywhere now! Thorin, Richard Lewis, and MonteCristo go in-depth on SonicFox's response to Saudi Arabia's Evo acquisition, Gaimin Gladiators withdrawing from TI, and the "superfan experience" at EWC.

Last Free Nation

18,584 Aufrufe • vor 10 Monaten

ODesign: A World Model for Biomolecular Interaction Design | Odin Zhang et al. - "ODesign allows scientists to specify epitopes on arbitrary targets and generate diverse classes of binding partners with fine-grained control. Across entity-, token-, and atom-level benchmarks in the protein modality, ODesign demonstrates superior controllability and performance to modality-specific baselines. Extending beyond proteins, it generalizes to nucleic acid and small-molecule design, enabling interaction types such as protein-binding RNA/DNA and RNA/DNA-binding ligands that were previously inaccessible." Technical Report: Project Page:
1:32

ODesign: A World Model for Biomolecular Interaction Design | Odin Zhang et al. - "ODesign allows scientists to specify epitopes on arbitrary targets and generate diverse classes of binding partners with fine-grained control. Across entity-, token-, and atom-level benchmarks in the protein modality, ODesign demonstrates superior controllability and performance to modality-specific baselines. Extending beyond proteins, it generalizes to nucleic acid and small-molecule design, enabling interaction types such as protein-binding RNA/DNA and RNA/DNA-binding ligands that were previously inaccessible." Technical Report: Project Page:

Leo Zang

17,064 Aufrufe • vor 9 Monaten