Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

🧬 We have many foundation models or language models for DNAs, but can we control them? We introduce Ctrl-DNA: Controllable Cell-Type-Specific Regulatory DNA Design via Constrained RL — a reinforcement learning framework for controllable cis-regulatory sequence generation. Paper: Code: 🔬What’s the challenge? Designing regulatory DNA that is both highly...

BoWang87's profile picture

Bo Wang

13,208 subscribers

30,719 Aufrufe • vor 1 Jahr •via X (Twitter)

Gesundheit & WellnessWissenschaft & TechnologieBildung
LIVE

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

Today we introduced AlphaGenome, a new tool that can more comprehensively predict the impact of single variants or mutations in DNA 🧬 How, you ask? 🤔 tldr; Our AlphaGenome model takes a long DNA sequence as input, processes that data, and predicts thousands of molecular properties by characterizing its regulatory activity. For the full read ➡️
0:18

Today we introduced AlphaGenome, a new tool that can more comprehensively predict the impact of single variants or mutations in DNA 🧬 How, you ask? 🤔 tldr; Our AlphaGenome model takes a long DNA sequence as input, processes that data, and predicts thousands of molecular properties by characterizing its regulatory activity. For the full read ➡️

Google AI

83,048 Aufrufe • vor 1 Jahr

A cell videoed through a microscope. DNA in the nucleus (green) and the powerhouses/overlords of the cell, mitochondria (purple), are shown. #CellBiology
0:10

A cell videoed through a microscope. DNA in the nucleus (green) and the powerhouses/overlords of the cell, mitochondria (purple), are shown. #CellBiology

Dylan Burnette

100,613 Aufrufe • vor 1 Jahr

Moving DNA along histones, one turn at a time! Learn more at #science #biology #education #cell #DNA #animation #Edtech #STEM
0:10

Moving DNA along histones, one turn at a time! Learn more at #science #biology #education #cell #DNA #animation #Edtech #STEM

Smart Biology

22,840 Aufrufe • vor 8 Monaten

A cell videoed through a microscope. DNA in the nucleus (green) and mitochondria (purple) are shown. #CellBiology
0:10

A cell videoed through a microscope. DNA in the nucleus (green) and mitochondria (purple) are shown. #CellBiology

Dylan Burnette

52,607 Aufrufe • vor 2 Jahren

🔋 Mitochondria run their core power system using bacterial-style DNA. 🧬 But they need your nuclear DNA for support, repair, and growth. Think of it like a battery with its own mini-engine — it sparks on its own, but the car (your cell) builds and maintains it. Bottom line: Mitochondria are semi-independent — powered by ancient bacterial genes, guided by your human ones.
0:12

🔋 Mitochondria run their core power system using bacterial-style DNA. 🧬 But they need your nuclear DNA for support, repair, and growth. Think of it like a battery with its own mini-engine — it sparks on its own, but the car (your cell) builds and maintains it. Bottom line: Mitochondria are semi-independent — powered by ancient bacterial genes, guided by your human ones.

William A. Wallace, Ph.D.

109,766 Aufrufe • vor 8 Monaten

A cell videoed through a microscope. DNA (cyan), mitochondria (yellow), and VASP (magenta) are shown. #CellBiology
0:16

A cell videoed through a microscope. DNA (cyan), mitochondria (yellow), and VASP (magenta) are shown. #CellBiology

Dylan Burnette

119,340 Aufrufe • vor 3 Jahren

A melanoma cancer cell videoed through a microscope. DNA in the nucleus (yellow), mitochondria (cyan), and VASP (magenta) are shown. #CellBiology
0:20

A melanoma cancer cell videoed through a microscope. DNA in the nucleus (yellow), mitochondria (cyan), and VASP (magenta) are shown. #CellBiology

Dylan Burnette

23,484 Aufrufe • vor 2 Jahren

Biomni Lab lets biologists collaborate with AI agents to finish complex tasks end-to-end. Here are 15 popular use cases, each link is a full replay so you can watch the agent work through every step: 1. Spatial transcriptomics analysis: map gene expression across tissue architecture from spatial transcriptomics data, with spatial clustering and neighborhood analysis. 2. Binder design: design de novo protein binders against a target structure using computational protein design tools. 3. Biomarker panel design: identify and optimize a multi-marker diagnostic or prognostic panel from omics data. 4. Clinical trial landscaping: search and summarize the trial landscape for a disease area, mapping phase, endpoints, and sponsor activity. 5. Survival analysis: pull clinical and expression data, fit Cox models, generate Kaplan-Meier curves, and identify prognostic markers. 6. scRNA-seq processing and annotation: from raw counts to UMAP clustering, marker gene detection, and automated cell type labeling. 7. Cell-cell communication: infer ligand-receptor interactions between cell types from single-cell data and map intercellular signaling networks. 8. Primer design for novel Cas13: analyze a putative Cas13 protein from a metagenomic screen—verify the ORF, identify HEPN domains, and design cloning primers with restriction sites and a FLAG 9. Proteomics differential expression: normalize mass spec data, run statistical tests, and visualize differentially abundant proteins. 10. Gene regulatory network inference: reconstruct transcription factor-target gene networks from expression data and identify key regulators. 11. Gene co-expression network analysis: build weighted co-expression networks, identify gene modules, and correlate them with phenotypic traits. 12. Microbiome analysis: process 16S/metagenomic sequencing data to profile microbial communities, diversity, and differential abundance. 13. Polygenic risk scores: compute and evaluate PRS from GWAS summary statistics against a target cohort. 14. Variant annotation: annotate genetic variants with functional predictions, allele frequencies, and clinical significance. 15. Fine-mapping: narrow GWAS loci to credible causal variants using statistical fine-mapping methods. Each of these would normally take days to weeks of scripting, debugging, and iteration. In Biomni Lab, the agent handles the full execution while you steer the science. Learn more:
0:15

Biomni Lab lets biologists collaborate with AI agents to finish complex tasks end-to-end. Here are 15 popular use cases, each link is a full replay so you can watch the agent work through every step: 1. Spatial transcriptomics analysis: map gene expression across tissue architecture from spatial transcriptomics data, with spatial clustering and neighborhood analysis. 2. Binder design: design de novo protein binders against a target structure using computational protein design tools. 3. Biomarker panel design: identify and optimize a multi-marker diagnostic or prognostic panel from omics data. 4. Clinical trial landscaping: search and summarize the trial landscape for a disease area, mapping phase, endpoints, and sponsor activity. 5. Survival analysis: pull clinical and expression data, fit Cox models, generate Kaplan-Meier curves, and identify prognostic markers. 6. scRNA-seq processing and annotation: from raw counts to UMAP clustering, marker gene detection, and automated cell type labeling. 7. Cell-cell communication: infer ligand-receptor interactions between cell types from single-cell data and map intercellular signaling networks. 8. Primer design for novel Cas13: analyze a putative Cas13 protein from a metagenomic screen—verify the ORF, identify HEPN domains, and design cloning primers with restriction sites and a FLAG 9. Proteomics differential expression: normalize mass spec data, run statistical tests, and visualize differentially abundant proteins. 10. Gene regulatory network inference: reconstruct transcription factor-target gene networks from expression data and identify key regulators. 11. Gene co-expression network analysis: build weighted co-expression networks, identify gene modules, and correlate them with phenotypic traits. 12. Microbiome analysis: process 16S/metagenomic sequencing data to profile microbial communities, diversity, and differential abundance. 13. Polygenic risk scores: compute and evaluate PRS from GWAS summary statistics against a target cohort. 14. Variant annotation: annotate genetic variants with functional predictions, allele frequencies, and clinical significance. 15. Fine-mapping: narrow GWAS loci to credible causal variants using statistical fine-mapping methods. Each of these would normally take days to weeks of scripting, debugging, and iteration. In Biomni Lab, the agent handles the full execution while you steer the science. Learn more:

Kexin Huang

27,189 Aufrufe • vor 3 Monaten

DimensionX: Create Any 3D and 4D Scenes from a Single Image with Controllable Video Diffusion TL;DR: Create 3/4DGS from Video Diffusion Note: Some first inference code released (not all yet). Contributions (cited): • We present DimensionX, a novel framework for generating photorealistic 3D and 4D scenes from only a single image using controllable video diffusion. • We propose ST-Director, which decouples the spatial and temporal priors in video diffusion models by learning (spatial and temporal) dimension-aware modules with our curated datasets. We further enhance the hybriddimension control with a training-free composition approach according to the essence of video diffusion denoising process. • To bridge the gap between video diffusion and real-world scenes, we design a trajectory-aware mechanism for 3D generation and an identity-preserving denoising approach for 4D generation, enabling more realistic and controllable scene synthesis. • Extensive experiments manifest that our DimensionX delivers superior performance in video, 3D, and 4D generation compared with baseline methods.
0:18

DimensionX: Create Any 3D and 4D Scenes from a Single Image with Controllable Video Diffusion TL;DR: Create 3/4DGS from Video Diffusion Note: Some first inference code released (not all yet). Contributions (cited): • We present DimensionX, a novel framework for generating photorealistic 3D and 4D scenes from only a single image using controllable video diffusion. • We propose ST-Director, which decouples the spatial and temporal priors in video diffusion models by learning (spatial and temporal) dimension-aware modules with our curated datasets. We further enhance the hybriddimension control with a training-free composition approach according to the essence of video diffusion denoising process. • To bridge the gap between video diffusion and real-world scenes, we design a trajectory-aware mechanism for 3D generation and an identity-preserving denoising approach for 4D generation, enabling more realistic and controllable scene synthesis. • Extensive experiments manifest that our DimensionX delivers superior performance in video, 3D, and 4D generation compared with baseline methods.

MrNeRF

17,052 Aufrufe • vor 1 Jahr

📢Paper alert📢our collaborative work led by Dr Roy IIT Hyderabad got published in Nucleic Acids Research. A DNA end-binder (DEB) that selectively binds to DNA termini and inhibits DNA repair, ideal for targeting DNA breaks Congrats Saanya Yadav et al
0:16

📢Paper alert📢our collaborative work led by Dr Roy IIT Hyderabad got published in Nucleic Acids Research. A DNA end-binder (DEB) that selectively binds to DNA termini and inhibits DNA repair, ideal for targeting DNA breaks Congrats Saanya Yadav et al

Himanshu Joshi

14,282 Aufrufe • vor 9 Monaten

Strands of DNA-like thread coil, loop, and spill upward, evoking the genome's dynamic three-dimensional architecture within the nucleus of a living cell. This special issue, with papers in Science and Science Advances, features single-cell and multiomic studies from the National Institutes of Health Common Fund's 4D Nucleome Program, which examines a fourth dimension of nuclear organization—how this folded structure shapes cell identity, shifts across development and aging, and goes awry in disease. Learn more:
0:10

Strands of DNA-like thread coil, loop, and spill upward, evoking the genome's dynamic three-dimensional architecture within the nucleus of a living cell. This special issue, with papers in Science and Science Advances, features single-cell and multiomic studies from the National Institutes of Health Common Fund's 4D Nucleome Program, which examines a fourth dimension of nuclear organization—how this folded structure shapes cell identity, shifts across development and aging, and goes awry in disease. Learn more:

Science Magazine

63,072 Aufrufe • vor 5 Tagen

Happy GPT 5.6 day! We dream of fighting disease with this kind of intelligence. In that spirit, here is a first preview of Cell Cinema, the future cell token for AI models. And a first for humanity: we recorded ferroptosis label-free, in real-time. A huge feat for biosciences.
0:15

Happy GPT 5.6 day! We dream of fighting disease with this kind of intelligence. In that spirit, here is a first preview of Cell Cinema, the future cell token for AI models. And a first for humanity: we recorded ferroptosis label-free, in real-time. A huge feat for biosciences.

Precigenetics

286,984 Aufrufe • vor 19 Tagen

Some microbes carry a protein, called SNIPE, that "chops up" phage DNA as it's being injected into the cell. This is a new mechanism for phage defense! CRISPR–Cas and restriction enzymes also evolved to fight against phages, but they work by recognizing sequences. SNIPE works, instead, by sensing "touch." SNIPE is a protein with about 500 amino acids. After it's made by the ribosome, it latches onto ManYZ, two proteins which sit on the cell's inner membrane. (ManYZ is an importer; it brings mannose and other sugars into the cell.) Once attached to ManYZ, SNIPE sits and waits for an invading phage. Some phages, including lambda, actually infect cells by pushing their DNA through this ManYZ channel. Lambda uses its "tail" to reach inside the protein channel, basically, and inject its DNA. When this physical touch happens, though, SNIPE is waiting. As soon as the phage DNA starts entering the cell, and passes through ManYZ and SNIPE, it gets immediately destroyed. This means that SNIPE is the first phage defense system discovered, so far, that uses spatial positioning at the injection site to destroy invaders. But there are caveats, of course. If you untether SNIPE from ManYZ, such that it can freely diffuse through the cell, it will chew up the bacterium's genome. It is not a highly discerning nuclease! Also, SNIPE is not found in most bacteria. A prior pangenome study, which sequenced lots of different microbes, found that roughly a third of well-studied bacterial lineages had at least one member with a SNIPE-like protein. (For this paper, they just ported one of those homologs into an E. coli laboratory strain.) And finally, because SNIPE's mechanism is tightly tied to ManYZ, it cannot be used to defend against phages that enter the cell through different routes. T4 phages, for example, inject their DNA straight through the cell membrane and into the cytoplasm, without interacting with ManYZ. This is a nice basic science paper. Applications TBD. (Just remember that scientists figured out that bacteria had a phage defense system, called CRISPR-Cas, many years before it was repurposed into a gene-editing tool.) P.S. The video below shows how cells with the SNIPE gene (middle row) kill invading phages, and thus continue growing and dividing. Empty vector (top row) refers to bacteria carrying a plasmid with no SNIPE gene; this is a control group. And SNIPE E414A refers to cells which received a mutated SNIPE gene, where the glutamate at position 414 has been changed to an alanine, thus destroying the protein's nuclease activity. These cells also die when they get infected with a phage.
0:10

Some microbes carry a protein, called SNIPE, that "chops up" phage DNA as it's being injected into the cell. This is a new mechanism for phage defense! CRISPR–Cas and restriction enzymes also evolved to fight against phages, but they work by recognizing sequences. SNIPE works, instead, by sensing "touch." SNIPE is a protein with about 500 amino acids. After it's made by the ribosome, it latches onto ManYZ, two proteins which sit on the cell's inner membrane. (ManYZ is an importer; it brings mannose and other sugars into the cell.) Once attached to ManYZ, SNIPE sits and waits for an invading phage. Some phages, including lambda, actually infect cells by pushing their DNA through this ManYZ channel. Lambda uses its "tail" to reach inside the protein channel, basically, and inject its DNA. When this physical touch happens, though, SNIPE is waiting. As soon as the phage DNA starts entering the cell, and passes through ManYZ and SNIPE, it gets immediately destroyed. This means that SNIPE is the first phage defense system discovered, so far, that uses spatial positioning at the injection site to destroy invaders. But there are caveats, of course. If you untether SNIPE from ManYZ, such that it can freely diffuse through the cell, it will chew up the bacterium's genome. It is not a highly discerning nuclease! Also, SNIPE is not found in most bacteria. A prior pangenome study, which sequenced lots of different microbes, found that roughly a third of well-studied bacterial lineages had at least one member with a SNIPE-like protein. (For this paper, they just ported one of those homologs into an E. coli laboratory strain.) And finally, because SNIPE's mechanism is tightly tied to ManYZ, it cannot be used to defend against phages that enter the cell through different routes. T4 phages, for example, inject their DNA straight through the cell membrane and into the cytoplasm, without interacting with ManYZ. This is a nice basic science paper. Applications TBD. (Just remember that scientists figured out that bacteria had a phage defense system, called CRISPR-Cas, many years before it was repurposed into a gene-editing tool.) P.S. The video below shows how cells with the SNIPE gene (middle row) kill invading phages, and thus continue growing and dividing. Empty vector (top row) refers to bacteria carrying a plasmid with no SNIPE gene; this is a control group. And SNIPE E414A refers to cells which received a mutated SNIPE gene, where the glutamate at position 414 has been changed to an alanine, thus destroying the protein's nuclease activity. These cells also die when they get infected with a phage.

Niko McCarty.

20,516 Aufrufe • vor 5 Monaten

Reinforcement Learning (RL) has long been the dominant method for fine-tuning, powering many state-of-the-art LLMs. Methods like PPO and GRPO explore in action space. But can we instead explore directly in parameter space? YES we can. We propose a scalable framework for full-parameter fine-tuning using Evolution Strategies (ES). By skipping gradients and optimizing directly in parameter space, ES achieves more accurate, efficient, and stable fine-tuning. Paper: Code:
0:16

Reinforcement Learning (RL) has long been the dominant method for fine-tuning, powering many state-of-the-art LLMs. Methods like PPO and GRPO explore in action space. But can we instead explore directly in parameter space? YES we can. We propose a scalable framework for full-parameter fine-tuning using Evolution Strategies (ES). By skipping gradients and optimizing directly in parameter space, ES achieves more accurate, efficient, and stable fine-tuning. Paper: Code:

Yulu Gan

415,255 Aufrufe • vor 9 Monaten

The most detailed 3D reconstruction of a cell ever created. Blows my mind every time. But what exactly are we looking at here? The average human cell contains: ~ 15-20 total distinct organelle types, totalling between ~1-10 million working together per cell. All these nano-machines in the cell are made up of proteins. ~ 8,000-10,000 distinct types of unique proteins, adding up to between 40 million - 10 trillion total proteins making up all those cellular systems. ~ 10,000 - 15,000 distinct types of RNA shuttling information around the cell, totalling up to ~10 million RNA molecules moving around the cell simultaneously. ~ Billions of Lipid molecules packed together into the cell membrane, which is also packed tightly with millions more protein-based nano-machines. And let's not forget billions of lines of DNA information to build and run it all. That's TRILLIONS of of individual molecular pieces working together to make a single cell function. That means there is more complexity in a single cell than humanity's largest cities. And people still believe this wasn't Divinely Designed. This is God's Glory on Display. But to make the point. A cell couldn't have evolved from some nebulous simpler "protocell" because even the simplest cells still require massive complexity. The "simplest" cell ever created was engineered by scientists knocking out pieces of a functional cell until it stopped functioning. Here is what they found is the absolute necessary minimal requirements of a cell to function: - Over ~531,000 lines of coded DNA information - 473 total genes to create hundreds of unique protein products (they later added 19 genes back in because the cell was so weak) - Hundreds of thousands of total proteins all working together - Extensive regulatory networks guiding all these interactions If the cell doesn't have all these systems in place, from the start... it doesn't live. Cell rely on an intricate network of complex systems, which are themselves built from complex interconnected pieces woven together into an incomprehensibly complex web of functionilty. Only intelligence has ever been observed creation vast interconnected systems like this. Life was clearly Created. It couldn't happen any other way.
0:17

The most detailed 3D reconstruction of a cell ever created. Blows my mind every time. But what exactly are we looking at here? The average human cell contains: ~ 15-20 total distinct organelle types, totalling between ~1-10 million working together per cell. All these nano-machines in the cell are made up of proteins. ~ 8,000-10,000 distinct types of unique proteins, adding up to between 40 million - 10 trillion total proteins making up all those cellular systems. ~ 10,000 - 15,000 distinct types of RNA shuttling information around the cell, totalling up to ~10 million RNA molecules moving around the cell simultaneously. ~ Billions of Lipid molecules packed together into the cell membrane, which is also packed tightly with millions more protein-based nano-machines. And let's not forget billions of lines of DNA information to build and run it all. That's TRILLIONS of of individual molecular pieces working together to make a single cell function. That means there is more complexity in a single cell than humanity's largest cities. And people still believe this wasn't Divinely Designed. This is God's Glory on Display. But to make the point. A cell couldn't have evolved from some nebulous simpler "protocell" because even the simplest cells still require massive complexity. The "simplest" cell ever created was engineered by scientists knocking out pieces of a functional cell until it stopped functioning. Here is what they found is the absolute necessary minimal requirements of a cell to function: - Over ~531,000 lines of coded DNA information - 473 total genes to create hundreds of unique protein products (they later added 19 genes back in because the cell was so weak) - Hundreds of thousands of total proteins all working together - Extensive regulatory networks guiding all these interactions If the cell doesn't have all these systems in place, from the start... it doesn't live. Cell rely on an intricate network of complex systems, which are themselves built from complex interconnected pieces woven together into an incomprehensibly complex web of functionilty. Only intelligence has ever been observed creation vast interconnected systems like this. Life was clearly Created. It couldn't happen any other way.

Divinely Designed

165,874 Aufrufe • vor 1 Monat

They are not an unlikely duo, but rather a perfect, complementary pair! DNA and RNA are very similar, but they have unique biological roles. RNA and DNA are both a type of molecule called a nucleic acid, but their structures are different in subtle ways.
0:13

They are not an unlikely duo, but rather a perfect, complementary pair! DNA and RNA are very similar, but they have unique biological roles. RNA and DNA are both a type of molecule called a nucleic acid, but their structures are different in subtle ways.

National Human Genome Research Institute

16,528 Aufrufe • vor 1 Jahr

We get the players that are meant to be here. We are not for everyone and everyone is not for us. We want guys with #TheHardWay DNA. The future is bright with this freshman class.
0:10

We get the players that are meant to be here. We are not for everyone and everyone is not for us. We want guys with #TheHardWay DNA. The future is bright with this freshman class.

Thomas Hammock

55,716 Aufrufe • vor 3 Jahren

🧬 👽 "23andme DNA researchers claim to have a found disturbing discovery related to American DNA. Researchers claim that most American samples contain an average 0.7% unidentifiable genes, not being able to be assigned to any racial group and not appearing to be Human at all. Researchers claim that the amount of this anomalous DNA in the American genome grows year after year and is only found in American samples."
0:10

🧬 👽 "23andme DNA researchers claim to have a found disturbing discovery related to American DNA. Researchers claim that most American samples contain an average 0.7% unidentifiable genes, not being able to be assigned to any racial group and not appearing to be Human at all. Researchers claim that the amount of this anomalous DNA in the American genome grows year after year and is only found in American samples."

UAP ★ Luigi ★👁️⃤ 🇺🇸 κρυπτός W.👽MJ12 SOM1-01🫈

1,860,386 Aufrufe • vor 3 Monaten