Загрузка видео...

Не удалось загрузить видео

На главную

Blank Bio (Blank Bio) is building foundation models to power a computational toolkit for RNA therapeutics, starting with mRNA design and expanding to target ID, biomarker discovery, and more. Congrats on the launch, Jonny, Phil Fradkin & Ian Shi!

ycombinator's profile picture

Y Combinator

1,643,598 subscribers

96,901 просмотров • 1 год назад •via X (Twitter)

Здоровье и велнесНаука и технологииОбразование
LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

Beacon Health is building AI agents for primary care - starting with value-based care. They are on a mission to bring joy back to the practice of medicine. Congrats on the launch, Mark and Obi!
0:57

Beacon Health is building AI agents for primary care - starting with value-based care. They are on a mission to bring joy back to the practice of medicine. Congrats on the launch, Mark and Obi!

Y Combinator

19,920 просмотров • 6 месяцев назад

🚀 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

114,983 просмотров • 1 год назад

.Visibl Semiconductors is building the first coordination layer for chip design. As teams scale, workstreams drift out of sync, issues surface late and drive $XM+ delays and months of rework before tapeout. Visibl is building end-to-end AI to shrink chip design from years to weeks, starting where intent breaks first: coordination. Book a demo at Congrats on the launch Bryce N, and Jordon Kashanchi!
2:28

.Visibl Semiconductors is building the first coordination layer for chip design. As teams scale, workstreams drift out of sync, issues surface late and drive $XM+ delays and months of rework before tapeout. Visibl is building end-to-end AI to shrink chip design from years to weeks, starting where intent breaks first: coordination. Book a demo at Congrats on the launch Bryce N, and Jordon Kashanchi!

Y Combinator

22,189 просмотров • 6 месяцев назад

Beluga Labs (@belugalabsai) is building Rippling for content creators, starting with automated taxes & bookkeeping. They're already saving creators thousands in deductions. Congrats on the launch, @ACKForeverYoung and Jack Swisher!
0:59

Beluga Labs (@belugalabsai) is building Rippling for content creators, starting with automated taxes & bookkeeping. They're already saving creators thousands in deductions. Congrats on the launch, @ACKForeverYoung and Jack Swisher!

Y Combinator

27,868 просмотров • 1 год назад

We’re giving scientists, mathematicians, and engineers free access to our frontier models—starting with 10,000 researchers and expanding to 100,000 through 2027. ChatGPT for Academic Researchers is built to accelerate discovery across disciplines.
3:30

We’re giving scientists, mathematicians, and engineers free access to our frontier models—starting with 10,000 researchers and expanding to 100,000 through 2027. ChatGPT for Academic Researchers is built to accelerate discovery across disciplines.

OpenAI

3,514,594 просмотров • 1 месяц назад

AMBSE and the Arthur M. Blank Family Foundation are partnering with the USO Through a $1 million grant from the Arthur M. Blank Family Foundation, all USO Centers on U.S. Naval aircraft carriers will be outfitted and supported to benefit deployed service members at sea!
1:59

AMBSE and the Arthur M. Blank Family Foundation are partnering with the USO Through a $1 million grant from the Arthur M. Blank Family Foundation, all USO Centers on U.S. Naval aircraft carriers will be outfitted and supported to benefit deployed service members at sea!

Atlanta Falcons

39,811 просмотров • 1 год назад

.Cajal is massively scaling formal verification to accelerate scientific discovery. They deploy superhuman AI mathematicians to high-impact applied domains, starting with quantum computing and finance. Congrats on the launch, Luke & Pedro Nobre!
2:30

.Cajal is massively scaling formal verification to accelerate scientific discovery. They deploy superhuman AI mathematicians to high-impact applied domains, starting with quantum computing and finance. Congrats on the launch, Luke & Pedro Nobre!

Y Combinator

31,136 просмотров • 6 месяцев назад

.CellType is building the agentic drug company. AI agents + foundation models that simulate human biology. They've already discovered and validated a novel cancer treatment signal and work with Top 10 pharma. Congrats on the launch David van Dijk and Ivan Vrkic!
1:11

.CellType is building the agentic drug company. AI agents + foundation models that simulate human biology. They've already discovered and validated a novel cancer treatment signal and work with Top 10 pharma. Congrats on the launch David van Dijk and Ivan Vrkic!

Y Combinator

46,752 просмотров • 6 месяцев назад

.Tensorfuse (YC W24) is a testing and evaluation platform for LLM apps. They make it easy for developers to experiment with various prompts, models, and retrieval methods to find the most effective one. Congrats on the launch agam & samagra14!
0:54

.Tensorfuse (YC W24) is a testing and evaluation platform for LLM apps. They make it easy for developers to experiment with various prompts, models, and retrieval methods to find the most effective one. Congrats on the launch agam & samagra14!

Y Combinator

14,195 просмотров • 2 лет назад

New Unsupervised Learning with Joshua Meier @ NeurIPS (Chai Discovery) on how AI x drug discovery is starting to inflect and: - The 3 waves of AI biotech - How AI models think differently than chemists - Building "Photoshop for molecules" - Deciding what to open source
0:38

New Unsupervised Learning with Joshua Meier @ NeurIPS (Chai Discovery) on how AI x drug discovery is starting to inflect and: - The 3 waves of AI biotech - How AI models think differently than chemists - Building "Photoshop for molecules" - Deciding what to open source

Jacob Effron

12,351 просмотров • 1 год назад

Refortifai is building Atrisa, agents for analog circuit design. It reasons hierarchically about your circuit, finds the right topologies for your specs, and does deep-dive debugging — all with awareness of parasitics, physical layout, reusability, and interference. Bring your existing PDKs, design docs, and toolkit and Atrisa will understand and adopt them. Congrats on the launch, Sayan Mitra, Rithik Jain, and Atman Kar!
1:36

Refortifai is building Atrisa, agents for analog circuit design. It reasons hierarchically about your circuit, finds the right topologies for your specs, and does deep-dive debugging — all with awareness of parasitics, physical layout, reusability, and interference. Bring your existing PDKs, design docs, and toolkit and Atrisa will understand and adopt them. Congrats on the launch, Sayan Mitra, Rithik Jain, and Atman Kar!

Y Combinator

12,926 просмотров • 2 месяцев назад

Gravy is building Agents for your money. Gravy (YC P26) connects to your banks, investments, email and more to explain your money and automate your financial tasks. Congrats on the launch, Ali Tabba & Max Church!
0:45

Gravy is building Agents for your money. Gravy (YC P26) connects to your banks, investments, email and more to explain your money and automate your financial tasks. Congrats on the launch, Ali Tabba & Max Church!

Y Combinator

44,820 просмотров • 2 месяцев назад

Can bio foundation models solve the most critical therapeutics problem, predicting which patients will respond to a therapy? Today, we share more details in a white paper on our recently reported results using NOETIK TARIO-2 to predict responders in an actual clinical trial setting with Agenus.
3:22

Can bio foundation models solve the most critical therapeutics problem, predicting which patients will respond to a therapy? Today, we share more details in a white paper on our recently reported results using NOETIK TARIO-2 to predict responders in an actual clinical trial setting with Agenus.

Ron Alfa (in NYC)

17,271 просмотров • 2 месяцев назад

What if you could generate all your colors, typography styles, sizes, radii, and more as variables and tokens with just one click? No manual setup, in few minutes go from blank page to a solid design system foundation. With option to present everything nicely for dev doc and more. With this Figma plugin, it’s actually that simple. ✨
1:46

What if you could generate all your colors, typography styles, sizes, radii, and more as variables and tokens with just one click? No manual setup, in few minutes go from blank page to a solid design system foundation. With option to present everything nicely for dev doc and more. With this Figma plugin, it’s actually that simple. ✨

vijay verma

26,263 просмотров • 7 месяцев назад

Chert (Chert) is building the infrastructure for teams to send, receive, and automate conversations over iMessage using APIs. They’re already working with B2C startups, customer experience teams, and sales teams to reach end users through trusted and conversational messaging. Congrats on the launch, Gary Gao & Ian Fong!
1:01

Chert (Chert) is building the infrastructure for teams to send, receive, and automate conversations over iMessage using APIs. They’re already working with B2C startups, customer experience teams, and sales teams to reach end users through trusted and conversational messaging. Congrats on the launch, Gary Gao & Ian Fong!

Y Combinator

37,405 просмотров • 3 месяцев назад

YC W24’s Paradigm is building AI agents to complete your repetitive tasks. They're starting with sales, automating everything from lead generation to personalized outreach. Congrats on the launch Anna Monaco and Claire Oxner!
0:23

YC W24’s Paradigm is building AI agents to complete your repetitive tasks. They're starting with sales, automating everything from lead generation to personalized outreach. Congrats on the launch Anna Monaco and Claire Oxner!

Y Combinator

42,065 просмотров • 2 лет назад

The key to building a good base is starting with a small and reliable structure. Then expanding it, section by section.
0:37

The key to building a good base is starting with a small and reliable structure. Then expanding it, section by section.

Rust

104,377 просмотров • 2 лет назад

SF Tensor (San Francisco Tensor Company) is building infrastructure for training foundation models, letting researchers focus on research and forget that the infrastructure layer even exists while saving 70% in training costs. Congrats on the launch, Ben Koska, Tom Koska, and Luk Koska!
1:35

SF Tensor (San Francisco Tensor Company) is building infrastructure for training foundation models, letting researchers focus on research and forget that the infrastructure layer even exists while saving 70% in training costs. Congrats on the launch, Ben Koska, Tom Koska, and Luk Koska!

Y Combinator

10,768 просмотров • 9 месяцев назад

⚡@DiodeInc (YC S24) is building an end-to-end circuit board design and ordering platform, to help you go from requirements to a working board in days instead of months. Congrats on the launch, Davide Asnaghi and Lenny Khazan!
0:28

⚡@DiodeInc (YC S24) is building an end-to-end circuit board design and ordering platform, to help you go from requirements to a working board in days instead of months. Congrats on the launch, Davide Asnaghi and Lenny Khazan!

Y Combinator

45,531 просмотров • 2 лет назад

Elodin (YC W24) is CI/CD for Aerospace — it helps aerospace engineers rapidly design, test, and simulate drones, satellites & control systems. Congrats to the team Elodin on the launch!
1:27

Elodin (YC W24) is CI/CD for Aerospace — it helps aerospace engineers rapidly design, test, and simulate drones, satellites & control systems. Congrats to the team Elodin on the launch!

Y Combinator

11,250 просмотров • 2 лет назад