Loading video...

Video Failed to Load

Go Home

Today in nature, we report MouseMapper: foundation-model AI to map disease perturbations across the entire mouse body cell-by-cell. In obesity, it revealed body-wide inflammation & unexpected facial nerve damage. 🧵👇🔉 led by Doris Kaltenecker & Ying Chen

erturklab's profile picture

Ali Max Erturk

90,548 subscribers

262,142 views • 2 months ago •via X (Twitter)

Health & WellnessScience & Technology
LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Imagine seeing a disease's impact on every cell in the body. Now, you can! We introduce MouseMapper, an AI tool to reveal system-wide disease perturbations. MouseMapper showed obesity-induced changes in facial nerves & body-wide inflammation 👉🏼🧵
1:31

Imagine seeing a disease's impact on every cell in the body. Now, you can! We introduce MouseMapper, an AI tool to reveal system-wide disease perturbations. MouseMapper showed obesity-induced changes in facial nerves & body-wide inflammation 👉🏼🧵

Ali Max Erturk

119,781 views • 1 year ago

An AI foundation whole-body 3D model that assesses perturbations (such as obesity) across multiple systems (such as immune, neural) at the cell level. This is MouseMapper. Imagine HumanMapper someday nature Ali Max Erturk
0:20

An AI foundation whole-body 3D model that assesses perturbations (such as obesity) across multiple systems (such as immune, neural) at the cell level. This is MouseMapper. Imagine HumanMapper someday nature Ali Max Erturk

Eric Topol

44,078 views • 2 months ago

A detailed map of mouse brain cell structure and connections, offering insights into how they relate to activity in the mouse brain, is revealed in a package of papers from MICrONS consortium in nature & Nature Methods: Allen Institute naturePortfolio
1:09

A detailed map of mouse brain cell structure and connections, offering insights into how they relate to activity in the mouse brain, is revealed in a package of papers from MICrONS consortium in nature & Nature Methods: Allen Institute naturePortfolio

Springer Nature

16,923 views • 1 year ago

Today in Nature Neuroscience, researchers led by Nowakowski_Lab, @ChangLabUCSF & Mircea Teodorescu (UC Santa Cruz Genomics Institute) demonstrate the first use of optogenetics to modulate seizure activity at the network level in human brain tissue: John UCSF Broad Stem Cell
0:30

Today in Nature Neuroscience, researchers led by Nowakowski_Lab, @ChangLabUCSF & Mircea Teodorescu (UC Santa Cruz Genomics Institute) demonstrate the first use of optogenetics to modulate seizure activity at the network level in human brain tissue: John UCSF Broad Stem Cell

UCSF Neurosurgery

68,471 views • 1 year ago

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

248,173 views • 5 months ago

Our new study shows that SARS-CoV-2 spike protein accumulates & persists in the body for years after infection, especially in the skull-meninges-brain axis, potentially driving long COVID. mRNA vaccines help but cannot stop it🔬🧠🦠🧵👇Cell Host & Microbe
1:33

Our new study shows that SARS-CoV-2 spike protein accumulates & persists in the body for years after infection, especially in the skull-meninges-brain axis, potentially driving long COVID. mRNA vaccines help but cannot stop it🔬🧠🦠🧵👇Cell Host & Microbe

Ali Max Erturk

1,987,455 views • 1 year ago

Wim Hof says depression is caused by inflammation in your body, not by a chemical imbalance in your brain. He says every modern disease starts in the same place. Inflammation builds up in the body over time, and depression is what happens when that inflammation reaches the brain. "All these diseases are based in inflammation. Depression is also caused by inflammation, and we are able to bring it down." Hof says his breath work brings down inflammation directly through three pathways: - Activates the autonomic nervous system - Improves the glymphatic system in the brain - Releases adrenaline that reduces inflammation He says this is why people who do the breathing for six weeks often report depression lifting on its own. The mood improvement is not the cause but the result of inflammation finally clearing out of the body. — Wim Hof (Wim Hof) on the Impulsive (IMPAULSIVE) podcast
0:23

Wim Hof says depression is caused by inflammation in your body, not by a chemical imbalance in your brain. He says every modern disease starts in the same place. Inflammation builds up in the body over time, and depression is what happens when that inflammation reaches the brain. "All these diseases are based in inflammation. Depression is also caused by inflammation, and we are able to bring it down." Hof says his breath work brings down inflammation directly through three pathways: - Activates the autonomic nervous system - Improves the glymphatic system in the brain - Releases adrenaline that reduces inflammation He says this is why people who do the breathing for six weeks often report depression lifting on its own. The mood improvement is not the cause but the result of inflammation finally clearing out of the body. — Wim Hof (Wim Hof) on the Impulsive (IMPAULSIVE) podcast

Goku

223,328 views • 2 months ago

How does an embryo reliably "compute" its form - "cell by cell" - using only local interactions and mechanics, yet produce a precise global body plan? I’m excited to share our Nature Methods paper "MultiCell: geometric learning in multicellular development", presenting #AIxBiology research led by Haiqian Yang and the result of a great collaboration with Ming Guo, George Roy, Tomer Stern, Anh Nguyen and Dapeng Bi. A long-standing challenge in developmental biology is to predict how thousands of cells collectively self-organize as tissues fold, divide, and rearrange. In MultiCell, we represent a developing embryo as a dual graph that unifies two complementary views of tissue mechanics with single-cell resolution: cells as moving points (granular) and cells as a connected foam (junction network). This lets the model learn dynamics from both geometry and cell–cell connectivity. On whole-embryo 4D light-sheet movies of Drosophila gastrulation (~5,000 cells), our model predicts key cell behaviors and the timing of events, including junction loss, rearrangements, and divisions with high accuracy, at single-cell resolution. Beyond prediction, the same representation supports robust time alignment across embryos and offers interpretable activation maps that highlight the morphogenetic "drivers" of development. The broader goal is a foundation for cell-by-cell forecasting in more complex tissues, and eventually for detecting subtle dynamical signatures of disease. Kudos to the team for this inspiring collaboration with brilliant researchers to push the boundary of AI for biology! Citation: Yang, H., Roy, G., Nguyen, A.Q., Buehler, M.J., et al. MultiCell: geometric learning in multicellular development. Nature Methods (2025), DOI: 10.1038/s41592-025-02983-x Code/data links are in the manuscript.
0:46

How does an embryo reliably "compute" its form - "cell by cell" - using only local interactions and mechanics, yet produce a precise global body plan? I’m excited to share our Nature Methods paper "MultiCell: geometric learning in multicellular development", presenting #AIxBiology research led by Haiqian Yang and the result of a great collaboration with Ming Guo, George Roy, Tomer Stern, Anh Nguyen and Dapeng Bi. A long-standing challenge in developmental biology is to predict how thousands of cells collectively self-organize as tissues fold, divide, and rearrange. In MultiCell, we represent a developing embryo as a dual graph that unifies two complementary views of tissue mechanics with single-cell resolution: cells as moving points (granular) and cells as a connected foam (junction network). This lets the model learn dynamics from both geometry and cell–cell connectivity. On whole-embryo 4D light-sheet movies of Drosophila gastrulation (~5,000 cells), our model predicts key cell behaviors and the timing of events, including junction loss, rearrangements, and divisions with high accuracy, at single-cell resolution. Beyond prediction, the same representation supports robust time alignment across embryos and offers interpretable activation maps that highlight the morphogenetic "drivers" of development. The broader goal is a foundation for cell-by-cell forecasting in more complex tissues, and eventually for detecting subtle dynamical signatures of disease. Kudos to the team for this inspiring collaboration with brilliant researchers to push the boundary of AI for biology! Citation: Yang, H., Roy, G., Nguyen, A.Q., Buehler, M.J., et al. MultiCell: geometric learning in multicellular development. Nature Methods (2025), DOI: 10.1038/s41592-025-02983-x Code/data links are in the manuscript.

Markus J. Buehler

387,977 views • 7 months ago

1/n: 🔬We introduce NicheCompass (NC) a graph learning model to build spatial atlases across millions of cells, quantitatively characterize cell niches, infer cellular communication, and map new data into these atlases. NC can be used with various spatial technologies, ranging from cellular to subcellular resolution including even multimodal approaches. We have explored interesting biology by analyzing cell niches spanning from development to cancer. Led by Sebastian Birk in a fun colab with @cartalop: paper:
1:04

1/n: 🔬We introduce NicheCompass (NC) a graph learning model to build spatial atlases across millions of cells, quantitatively characterize cell niches, infer cellular communication, and map new data into these atlases. NC can be used with various spatial technologies, ranging from cellular to subcellular resolution including even multimodal approaches. We have explored interesting biology by analyzing cell niches spanning from development to cancer. Led by Sebastian Birk in a fun colab with @cartalop: paper:

Mo Lotfollahi

61,775 views • 2 years ago

There are now hundreds of genes associated with autism & neurodevelopmental disorders but what key processes in brain development they each disrupt remains unknown. In an article in nature today, we start tackling this question by combining forebrain #assembloids with CRISPR screens to map >400 disease genes onto stages of human cortical interneuron development. Using engineered lines, regionalized neural #organoids and over 1,000 #assembloids, we discovered a group of disease genes that interfere with GABAergic neuron generation or migration, including some surprising disease mechanisms. Check out the video below for details. This work was led by the fearless Xiangling Meng in the lab!! In collaboration with Bassik lab & Georgia Panagiotakos lab! Article here: Supported by the Stanford Brain Organogenesis Center Wu Tsai Neurosciences Institute Stanford Bio-X New York Stem Cell Foundation Research Institute Biohub
1:38

There are now hundreds of genes associated with autism & neurodevelopmental disorders but what key processes in brain development they each disrupt remains unknown. In an article in nature today, we start tackling this question by combining forebrain #assembloids with CRISPR screens to map >400 disease genes onto stages of human cortical interneuron development. Using engineered lines, regionalized neural #organoids and over 1,000 #assembloids, we discovered a group of disease genes that interfere with GABAergic neuron generation or migration, including some surprising disease mechanisms. Check out the video below for details. This work was led by the fearless Xiangling Meng in the lab!! In collaboration with Bassik lab & Georgia Panagiotakos lab! Article here: Supported by the Stanford Brain Organogenesis Center Wu Tsai Neurosciences Institute Stanford Bio-X New York Stem Cell Foundation Research Institute Biohub

Sergiu P. Pasca

165,656 views • 2 years ago

Education will be one of the most transformed sectors by #AI. Microsoft's just revealed a groundbreaking #AI teaching assistant in India called Shiksha Copilot, & it's powered by Streamlit! 🤯 Great job Tanuja G + hat tip to Rowan Cheung for spotting it. Announcement 🧵👇
0:58

Education will be one of the most transformed sectors by #AI. Microsoft's just revealed a groundbreaking #AI teaching assistant in India called Shiksha Copilot, & it's powered by Streamlit! 🤯 Great job Tanuja G + hat tip to Rowan Cheung for spotting it. Announcement 🧵👇

Charly Wargnier

17,128 views • 2 years ago

Everyone says AI is going to kill SaaS. We're betting it rebuilds it. Today we're announcing Ergo's $2.8M seed, led by FundersClub with Y Combinator. We now manage $3B+ in pipeline for revenue teams. Ergo is the revenue infrastructure layer for AI-native GTM 🧵👇
1:31

Everyone says AI is going to kill SaaS. We're betting it rebuilds it. Today we're announcing Ergo's $2.8M seed, led by FundersClub with Y Combinator. We now manage $3B+ in pipeline for revenue teams. Ergo is the revenue infrastructure layer for AI-native GTM 🧵👇

Yash Dulla

28,147 views • 1 month ago

Today, we’re launching Claw 5.0 on The world’s 1st AI model purpose-built for Prediction Markets & Crypto, powered by Solana Claw 5.0 enables traders to make confident, smarter decisions through intelligent conversation. Let’s dive in 👇 (🧵/3)
1:15

Today, we’re launching Claw 5.0 on The world’s 1st AI model purpose-built for Prediction Markets & Crypto, powered by Solana Claw 5.0 enables traders to make confident, smarter decisions through intelligent conversation. Let’s dive in 👇 (🧵/3)

RaptorX

22,686 views • 5 months ago

Last night in Levittown, PA, there were no lights, & people were forced to vote by cell phone light. Today, in Bucks, we are seeing wait times of 5 + hours to vote. More of the same tonight! Bucks election officials did the bare minimum. VOTER SUPPRESSION! STAY IN LINE!
0:26

Last night in Levittown, PA, there were no lights, & people were forced to vote by cell phone light. Today, in Bucks, we are seeing wait times of 5 + hours to vote. More of the same tonight! Bucks election officials did the bare minimum. VOTER SUPPRESSION! STAY IN LINE!

Alex Meyer

1,344,475 views • 1 year ago

🔬 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

199,718 views • 2 years ago

"Statins Are Mass Murder...You Do Not Die From Too Much Cholesterol, You Die From Not Enough. Because We Know...Only Cholesterol Builds Healthy Cells." Dr Leonard Coldwell "I Have Healthy Patients With Cholesterol Levels Of 600...There Is No Such Thing As Too Much Cholesterol." 85% of cholesterol is made in the liver, according to our bodies needs at that time. Cholesterol does not cause arterial plaque or narrowing of the arteries...damage to the arterial wall does, the inflammatory cascade from lifestyle & environmental toxins causes atherosclerosis. Cholesterol is not a fuel source, it is a construction material to build every cell wall & every cell membrane & every hormone in the human body & we use it to make Vitamin D3 (Cholecalciferol)...the most important nutrient in the human body. Cholesterol is a nutrient & when this nutrient gets pushed low by a cholesterol lowering statin, you are buying consequences & illness...you are interrupting & halting cell walls, cell membranes, hormones & the production of Vitamin D3. You are lowering a vital nutrient & causing an entire cascade of illness & problems down the road. There is no correlation between cholesterol levels & cardiovascular disease. Serious Adverse Events From Cholesterol Lowering Statins: Aphasia Dementia & Alzheimer's Disease Cancer Pancreatitis Liver Inflammation & Damage New Onset Type 2 Diabetes Depression Drug Induced Lupus Parkinson's Disease Lou Gehrig's Disease (ALS) Deficiency Of All Hormones Neurological Damage Multiple Sclerosis Autoimmune Disease Widespread Muscle Pain Muscle Tearing (Rhabdomyolysis) Fatigue Weakness Neuropathy Heart Failure Vertigo Cognitive Impairment Drug Induced Fibromyalgia Heart health surrounds keeping triglycerides low & HDL high. Both of these are diet controlled. The ratio between the 2 levels should be less than 1.5 which indicates cardiovascular health. Triglycerides lower quickly when sugar, seed oils, ultra processed foods, artificial ingredients & processed carbs are eliminated from the diet. HDL can be raised by strength training & consuming animal sourced foods & saturated fats such as beef, bison, venison, eggs, butter, tallow & ghee. 👇Low LDL Causes 3X Hemorrhagic Strokes👇 👇Low Cholesterol Causes Heart Disease & Cancer👇 👇The Higher Your LDL, The Longer You Live👇 Speaker: Dr Leonard Coldwell
0:59

"Statins Are Mass Murder...You Do Not Die From Too Much Cholesterol, You Die From Not Enough. Because We Know...Only Cholesterol Builds Healthy Cells." Dr Leonard Coldwell "I Have Healthy Patients With Cholesterol Levels Of 600...There Is No Such Thing As Too Much Cholesterol." 85% of cholesterol is made in the liver, according to our bodies needs at that time. Cholesterol does not cause arterial plaque or narrowing of the arteries...damage to the arterial wall does, the inflammatory cascade from lifestyle & environmental toxins causes atherosclerosis. Cholesterol is not a fuel source, it is a construction material to build every cell wall & every cell membrane & every hormone in the human body & we use it to make Vitamin D3 (Cholecalciferol)...the most important nutrient in the human body. Cholesterol is a nutrient & when this nutrient gets pushed low by a cholesterol lowering statin, you are buying consequences & illness...you are interrupting & halting cell walls, cell membranes, hormones & the production of Vitamin D3. You are lowering a vital nutrient & causing an entire cascade of illness & problems down the road. There is no correlation between cholesterol levels & cardiovascular disease. Serious Adverse Events From Cholesterol Lowering Statins: Aphasia Dementia & Alzheimer's Disease Cancer Pancreatitis Liver Inflammation & Damage New Onset Type 2 Diabetes Depression Drug Induced Lupus Parkinson's Disease Lou Gehrig's Disease (ALS) Deficiency Of All Hormones Neurological Damage Multiple Sclerosis Autoimmune Disease Widespread Muscle Pain Muscle Tearing (Rhabdomyolysis) Fatigue Weakness Neuropathy Heart Failure Vertigo Cognitive Impairment Drug Induced Fibromyalgia Heart health surrounds keeping triglycerides low & HDL high. Both of these are diet controlled. The ratio between the 2 levels should be less than 1.5 which indicates cardiovascular health. Triglycerides lower quickly when sugar, seed oils, ultra processed foods, artificial ingredients & processed carbs are eliminated from the diet. HDL can be raised by strength training & consuming animal sourced foods & saturated fats such as beef, bison, venison, eggs, butter, tallow & ghee. 👇Low LDL Causes 3X Hemorrhagic Strokes👇 👇Low Cholesterol Causes Heart Disease & Cancer👇 👇The Higher Your LDL, The Longer You Live👇 Speaker: Dr Leonard Coldwell

Valerie Anne Smith

76,340 views • 9 months ago

3 months in, today is fun because we start to collaborate with builders. We have been hard at work. 🔥 Our goal by the end of year is to make the entire AI stack adaptable. Data is the foundation all AI progress has been built on. So, it is our natural starting point.
0:24

3 months in, today is fun because we start to collaborate with builders. We have been hard at work. 🔥 Our goal by the end of year is to make the entire AI stack adaptable. Data is the foundation all AI progress has been built on. So, it is our natural starting point.

Sara Hooker

42,742 views • 5 months ago

🎊 Massachusetts Passes Permanent #SchoolMealsforAll 🎊 Only 3 years ago, Project Bread & the #FeedKidsMA coalition began our efforts to address childhood hunger in Massachusetts by starting with what happens in schools. Today, we are so proud to announce that WE DID IT! ...🧵
0:54

🎊 Massachusetts Passes Permanent #SchoolMealsforAll 🎊 Only 3 years ago, Project Bread & the #FeedKidsMA coalition began our efforts to address childhood hunger in Massachusetts by starting with what happens in schools. Today, we are so proud to announce that WE DID IT! ...🧵

Project Bread

11,336 views • 3 years ago

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

47,117 views • 11 months ago