Nature Machine Intelligence

Iambic Therapeutics Announces New Research Published in Nature Machine Intelligence Demonstrating the Capabilities of Its Generative AI NeuralPLexer Technology to Predict Protein-Ligand Complex Structures

Retrieved on: 
Monday, February 12, 2024
Biotechnology, Pharmaceutical, Health, Therapy, EGFR, Doctor of Philosophy, Multimedia, NVIDIA, FDA, Therapeutic index, 3D, Nature Machine Intelligence, Business development, HER2, PDB, Protein, Movement, Iamb, State, IND, Benchmarking, Drug, Research, Protein Data Bank

Iambic Therapeutics, a biotechnology company developing novel therapeutics using its unique generative AI discovery platform, today announced the publication of research in Nature Machine Intelligence showing that its NeuralPLexer technology outperforms other state-of-the art systems in predicting the structure of protein-ligand complexes as well as the conformational changes to these structures from the addition of drug molecules.

Key Points: 
  • Iambic Therapeutics, a biotechnology company developing novel therapeutics using its unique generative AI discovery platform, today announced the publication of research in Nature Machine Intelligence showing that its NeuralPLexer technology outperforms other state-of-the art systems in predicting the structure of protein-ligand complexes as well as the conformational changes to these structures from the addition of drug molecules.
  • View the full release here: https://www.businesswire.com/news/home/20240212651244/en/
    A frame from the NeuralPLexer generative diffusion process, as it creates the predicted protein-ligand complex structure.
  • The Company today also released a white paper highlighting the improvements in its next-generation NeuralPLexer2.
  • In preclinical studies, IAM1363 has demonstrated over 1000-fold selectivity for HER2 compared to EGFR.

Announcing MedPerf Open Benchmarking Platform for Medical AI

Retrieved on: 
Monday, July 17, 2023
Technology, Semiconductor, Engineering, Health Technology, Software, Manufacturing, Networks, Hardware, Health, Artificial Intelligence, Brat, Benchmarking, Sage Bionetworks, Analytics, Ben Goertzel, University, Abram Ilyich Fet, Data science, Dana–Farber Cancer Institute, HF, API, Pathology, Nature Machine Intelligence, University of Pennsylvania, Microsoft, Multimedia, Research, Synapse, Nutanix, Privacy, Radiology, Assistant, Hospital, Machine learning, Intel, Informatics, Federated, Artificial intelligence, Microsoft Azure, AI, Bias, Medical device, Glioblastoma

(Graphic: Business Wire)

Key Points: 
  • (Graphic: Business Wire)
    MedPerf is an open benchmarking platform that efficiently evaluates AI models on diverse real world medical data and delivers clinical efficacy while prioritizing patient privacy and mitigating legal and regulatory risks.
  • MedPerf improves medical AI by making data across the world easily and safely accessible to AI researchers, which reduces bias and improves generalizability and clinical impact.
  • “Our goal is to use benchmarking as a tool to enhance medical AI,” said Dr. Alex Karargyris, MLCommons Medical co-chair.
  • MedPerf is a foundational step towards the MLCommons Medical Working Group’s mission to develop benchmarks and best practices to accelerate medical AI through an open, neutral, and scientific approach.

From self-driving cars to military surveillance: quantum computing can help secure the future of AI systems

Retrieved on: 
Saturday, May 27, 2023
People, Human, Industry, University, Life, Nature Machine Intelligence, Facial recognition, Computer, Government, Data, Machine learning, Algorithm, Physics, AI, Artificial intelligence, CSIRO, Quantum, Environment, Software, Medical device, Computer data storage, Microscope

Many systems that require strong security are either already underpinned by machine learning or soon will be.

Key Points: 
  • Many systems that require strong security are either already underpinned by machine learning or soon will be.
  • We propose that the integration of quantum computing in these models could yield new algorithms with strong resilience against adversarial attacks.

The dangers of data manipulation attacks

    • However, they’re also highly vulnerable to data manipulation attacks, which can pose serious security risks.
    • Data manipulation attacks – which involve the very subtle manipulation of image data – can be launched in several ways.
    • Read more:
      AI to Z: all the terms you need to know to keep up in the AI hype age

      Either way, the consequences of data manipulation attacks can be severe.

How quantum computing can help

    • In our article, we describe how integrating quantum computing with machine learning could give rise to secure algorithms called quantum machine learning models.
    • Beyond this, quantum machine learning could allow for faster algorithmic training and more accuracy in learning features.

So how would it work?

    • In classical computers, which follow the laws of classical physics, bits are represented as binary numbers – specifically 0s and 1s.
    • Information in quantum computers is stored and processed as qubits (quantum bits) which can exist as 0, 1, or a combination of both at once.
    • On the other, quantum computers could be used to generate powerful adversarial attacks, capable of easily deceiving even state-of-the-art conventional machine learning models.

Limitations to overcome

    • The current evidence suggests we’re still some years away from quantum machine learning becoming a reality, due to limitations in the current generation of quantum processors.
    • Today’s quantum computers are relatively small (with fewer than 500 qubits) and their error rates are high.
    • This month the Australian government launched the National Quantum Strategy, aimed at growing the nation’s quantum industry and commercialising quantum technologies.

Evozyne Announces Multi-Target Research Collaboration and License Agreement with Takeda to Develop Next-Generation Gene Therapies

Retrieved on: 
Tuesday, April 5, 2022
Paragon, Degenerative disease, Therapy, Protein engineering, Patient, Research, Takeda, Lists of diseases, Review, Transgene, Hope, Machine learning, Deep learning, Nature, AI, Protein, Nature Machine Intelligence, Partnership, Pharmaceutical industry, Vaccine

CHICAGO, April 5, 2022  /PRNewswire/ -- Evozyne, Inc., an adaptive biology company pioneering evolution-based design of proteins, founded by Paragon Biosciences, announced today that it has entered into a strategic research collaboration and license agreement with Takeda to research and develop proteins that could be incorporated into next-generation gene therapies for up to four rare disease targets. This new agreement builds upon an earlier, separate agreement with Takeda and demonstrates the potential of Evozyne's protein engineering platform.

Key Points: 
  • This new agreement builds upon an earlier, separate agreement with Takeda and demonstrates the potential of Evozyne's protein engineering platform.
  • In partnership with Takeda, Evozyne will create novel protein sequences for advancement as gene therapies.
  • At completion and review of certain research deliverables, Takeda has the option to obtain an exclusive license to develop and commercialize the novel protein sequences as part of its gene therapy program.
  • Under the terms of the agreement, Evozyne will receive double-digit million dollars in upfront and research funding payments.

'Plug and Play Topeka' Selects 12 Startups for Third Round of Accelerator Program

Retrieved on: 
Tuesday, February 22, 2022
Climate change, Health, Plant, Evergy, Nature Machine Intelligence, Silicon, AG, Partnership, Animal, Hill, CO2, PHA, PETS, Hill's Pet Nutrition, Innovation, Plug, Plastic, Vaccine, Artificial intelligence, Kansas City metropolitan area, Food, Cargill, Economic development, Solution, Program, Plug and play, Video game, Agriculture, Video game console, Landfill, Renewable energy

Entrepreneurs will participate in a three-month-long accelerator program aimed at connecting them with resources to help launch and grow their businesses.

Key Points: 
  • Entrepreneurs will participate in a three-month-long accelerator program aimed at connecting them with resources to help launch and grow their businesses.
  • Learn more about the 12 startups selected for the program:
    Adrich Connects brands and retailers through a smart-packaging and post-sales data analytics platform.
  • "We're excited to invite these 12 startups to participate in our Plug and Play Topeka accelerator," said Lindsay Lebahn, program manager for Plug and Play Topeka.
  • Since the start of the program in spring of 2021, 20 startups have graduated from the Plug and Play Topeka accelerator program.