Learn Protein Design, From Theory to Practical - Part 1
Learn Protein Design: From Theory to Practical Welcome to this comprehensive lecture on the Theoretical Foundations of Protein Design. In this video, we explore the revolutionary shift from classical biology to modern computational design, focusing on how AI is redefining our ability to create functional proteins from scratch. What You Will Learn: The Evolution of Structure Prediction: A look at the CASP (Critical Assessment of Protein Structure Prediction) timeline, from homology modeling in 2012 to the groundbreaking release of AlphaFold2 during the COVID-19 pandemic. The 2024 Nobel Prize Impact: Understanding why the work of David Baker, Demis Hassabis, and John Jumper on computational protein design and structure prediction earned the Nobel Prize in Chemistry.AI Models in Proteomics: An introduction to Machine Learning (ML), Deep Learning (ANN), and the use of Large Language Models (LLM) in protein engineering.Generative AI & Diffusion Models: How we use the "reverse noise process" to refine random noise into meaningful protein backbones trained on the Protein Data Bank (PDB).De Novo Design Workflow:RFDiffusion: Ensuring the backbone takes your required shape or fold. ProteinMPNN: Assigning high-confidence amino acid sequences to your 3D shapes.Validation: Remodeling and testing using AlphaFold2 or 3.Practical Application: A walkthrough using the extracellular lipase SrLip (PDB ID: 5MAL) to design more stable, high-temperature resistant enzymes.Computing Resources: How to tackle the computational costs of protein design using Personal Workstations (GPU/RAM), Cloud Computing (Google Colab), and dedicated servers. The Design Paradigm Shift: The classic biological dogma moves from DNA → mRNA → Protein. Modern protein design flips this script: we start with the desired Function, design the Protein structure to fit that function, and finally determine the necessary Sequence. #ProteinDesign #Bioinformatics #AlphaFold #GenAI #ComputationalBiology #ScienceEducation #StructuralBiology #DrAshfaqAhmad #Bioinformaticsinsights

AlphaFold - The Most Useful Thing AI Has Ever Done
![Yann LeCun's $1B Bet Against LLMs [Part 1]](https://i.ytimg.com/vi/kYkIdXwW2AE/hqdefault.jpg?sqp=-oaymwEjCNACELwBSFryq4qpAxUIARUAAAAAGAElAADIQj0AgKJDeAE=&rs=AOn4CLDbV4izF3i-wxevCVIn7FJjoy1vlA)
Yann LeCun's $1B Bet Against LLMs [Part 1]

The Art of Scaling Reinforcement Learning Compute for LLMs | Bonnie Li (Google Deepmind)

How to Understand and Interpret Molecular Dynamics Results?

How AI Cracked the Protein Folding Code and Won a Nobel Prize

Cognitive Memory for Coding Agents: Reusable Reasoning Across Platforms

Reinventing Entropy | Compression is Intelligence Part 1

Learn Protein Design, From Theory To Practice Part 2

Training Sand to Think: Artificial General Intelligence & Future of Physics

The most beautiful formula not enough people understand

Inside Anthropic, the $965 Billion AI Juggernaut | The Circuit

Turing Award Winner: Disagreeing with Google, Postgres, Future Problems | Mike Stonebraker

But how do AI images and videos actually work? | Guest video by Welch Labs

START YOUR TUESDAY WITH FAITH | TODAY GOD IS GIVING YOU UNEXPECTED OPPORTUNITIES | FATHER FREDDY ...

The French Do Not Care About Work

Andrej Karpathy: From Vibe Coding to Agentic Engineering w/ Stephanie Zhan

The Uncomfortable Truth About AI “Reasoning” | World Science Festival

Yann LeCun: World Models: Enabling the next AI revolution

Ex-Google Recruiter Explains Why "Lying" Gets You Hired

