Home Technology peripherals AI Login to Science, drug affinity increased 37 times, AI performs unsupervised optimization of protein and antibody complexes

Login to Science, drug affinity increased 37 times, AI performs unsupervised optimization of protein and antibody complexes

Jul 18, 2024 pm 10:22 PM
AI machine learning protein theory Antibody drug

Login to Science, drug affinity increased 37 times, AI performs unsupervised optimization of protein and antibody complexes

Editor | Radish skin

Proteins are involved in many biological functions such as cell composition, muscle contraction, digestion of food, and identification of viruses.

In order to design better proteins (including antibodies), scientists often repeatedly mutate amino acids (arranging the units that make up proteins in a certain order) at different positions until the protein obtains the required function.

But there are more amino acid sequences than there are grains of sand in the world, so finding the best protein, and thus the best potential drug, is often difficult. When faced with this challenge, scientists often spend millions of dollars and test on miniaturized, simplified versions of biological systems.

“This requires a lot of guesswork and verification.” Brian L. Hie, assistant professor of chemical engineering at Stanford University and innovation fellow at the Arc Institute, said, “The goal of many intelligent algorithms is to take the guesswork out of it.”

Stanford University scientists have developed a new method based on machine learning that can predict molecular changes that lead to better antibody drugs faster and more accurately. Combining the 3D structure of the protein backbone with a large language model based on the amino acid sequence, the researchers were able to find rare and desirable mutations in minutes.

The study was titled "Unsupervised evolution of protein and antibody complexes with a structure-informed language model" and was published in "Science" on July 4, 2024.

Login to Science, drug affinity increased 37 times, AI performs unsupervised optimization of protein and antibody complexes

Despite huge advances in protein structure prediction, linking sequence to function remains key to protein computer engineering for a variety of tasks.

Large language models trained solely on sequence information can learn high-level principles of protein design. However, in addition to sequence, the three-dimensional structure of proteins determines their specific function, activity, and evolvability.

For antibody engineering problems, researchers at Stanford University applied structurally informed protein language models to predict high-fitness sequences constrained by known antibody or antibody-antigen complex structures.

Research shows that a universal protein language model augmented with protein structural backbone coordinates can guide the evolution of different proteins without the need to model individual functional tasks.

Login to Science, drug affinity increased 37 times, AI performs unsupervised optimization of protein and antibody complexes

Illustration: Using structure-guided language models to guide the evolution of multiple proteins. (Source: Paper)
  1. Structure-guided paradigm:

    • does not model an explicit definition of protein function or fitness.
    • Focus on regions that retain protein backbone folding and indirectly explore the fitness landscape.
    • Assume evolution within a high sequence likelihood range is a valid prior for high fitness variants.
  2. Wide application:

    • can indirectly study the fitness landscape of proteins in different environments, such as enzyme catalysis, antibiotic resistance and chemotherapy resistance.
  3. Protein complex design:

    • ESM-IF1 trained only on single-chain structures can be extended to design protein complexes.
    • Shows that structural information language models can implicitly learn to combine features and generalize to polyproteins.
  4. Human Antibody Evolution:

    • This method is particularly valuable for the evolution of human antibodies and can be used to treat a variety of diseases.
    • Antibodies provide protection by binding to target antigens.
  5. Replace large amounts of data:

    • Structures can replace large amounts of data and the computer can still learn.
    • More antibodies have optimization opportunities.
  6. Directed evolution:

    • This method is used to experimentally guide directed evolution activities of multiple proteins.
    • Generate designs with functional activity superior to wild-type proteins.
    • No need to analyze labeled fitness data or task-specific model supervision.

      Login to Science, drug affinity increased 37 times, AI performs unsupervised optimization of protein and antibody complexes

      Illustration: Evolving antibodies using structural information language models can improve neutralizing potency and resilience. (Source: paper)

With this method, the team screened about 30 candidates for two therapeutic clinical antibodies for the treatment of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection. Variants. At the same time, the researchers achieved a 25-fold increase in neutralization and a 37-fold increase in affinity against BQ.1.1 and XBB.1.5 antibody-escape virus variants, respectively.

In conclusion, This tool will help quickly respond to new or developing diseases. It also lowers the barriers to making more effective drugs. Stronger drugs mean lower doses are needed, meaning more patients can benefit from a given dose.

論文連結:https://www.science.org/doi/10.1126/science.adk8946

相關報告:https://phys.org/news/2024-07-ai-approach-optimizes-approach-optimizes-approach-optimizes-approach-optimizes-approach-optimizes- antibody-drugs.html

The above is the detailed content of Login to Science, drug affinity increased 37 times, AI performs unsupervised optimization of protein and antibody complexes. For more information, please follow other related articles on the PHP Chinese website!

Statement of this Website
The content of this article is voluntarily contributed by netizens, and the copyright belongs to the original author. This site does not assume corresponding legal responsibility. If you find any content suspected of plagiarism or infringement, please contact admin@php.cn

Hot AI Tools

Undresser.AI Undress

Undresser.AI Undress

AI-powered app for creating realistic nude photos

AI Clothes Remover

AI Clothes Remover

Online AI tool for removing clothes from photos.

Undress AI Tool

Undress AI Tool

Undress images for free

Clothoff.io

Clothoff.io

AI clothes remover

Video Face Swap

Video Face Swap

Swap faces in any video effortlessly with our completely free AI face swap tool!

Hot Tools

Notepad++7.3.1

Notepad++7.3.1

Easy-to-use and free code editor

SublimeText3 Chinese version

SublimeText3 Chinese version

Chinese version, very easy to use

Zend Studio 13.0.1

Zend Studio 13.0.1

Powerful PHP integrated development environment

Dreamweaver CS6

Dreamweaver CS6

Visual web development tools

SublimeText3 Mac version

SublimeText3 Mac version

God-level code editing software (SublimeText3)

Hot Topics

Java Tutorial
1663
14
PHP Tutorial
1263
29
C# Tutorial
1237
24
Bytedance Cutting launches SVIP super membership: 499 yuan for continuous annual subscription, providing a variety of AI functions Bytedance Cutting launches SVIP super membership: 499 yuan for continuous annual subscription, providing a variety of AI functions Jun 28, 2024 am 03:51 AM

This site reported on June 27 that Jianying is a video editing software developed by FaceMeng Technology, a subsidiary of ByteDance. It relies on the Douyin platform and basically produces short video content for users of the platform. It is compatible with iOS, Android, and Windows. , MacOS and other operating systems. Jianying officially announced the upgrade of its membership system and launched a new SVIP, which includes a variety of AI black technologies, such as intelligent translation, intelligent highlighting, intelligent packaging, digital human synthesis, etc. In terms of price, the monthly fee for clipping SVIP is 79 yuan, the annual fee is 599 yuan (note on this site: equivalent to 49.9 yuan per month), the continuous monthly subscription is 59 yuan per month, and the continuous annual subscription is 499 yuan per year (equivalent to 41.6 yuan per month) . In addition, the cut official also stated that in order to improve the user experience, those who have subscribed to the original VIP

Breaking through the boundaries of traditional defect detection, 'Defect Spectrum' achieves ultra-high-precision and rich semantic industrial defect detection for the first time. Breaking through the boundaries of traditional defect detection, 'Defect Spectrum' achieves ultra-high-precision and rich semantic industrial defect detection for the first time. Jul 26, 2024 pm 05:38 PM

In modern manufacturing, accurate defect detection is not only the key to ensuring product quality, but also the core of improving production efficiency. However, existing defect detection datasets often lack the accuracy and semantic richness required for practical applications, resulting in models unable to identify specific defect categories or locations. In order to solve this problem, a top research team composed of Hong Kong University of Science and Technology Guangzhou and Simou Technology innovatively developed the "DefectSpectrum" data set, which provides detailed and semantically rich large-scale annotation of industrial defects. As shown in Table 1, compared with other industrial data sets, the "DefectSpectrum" data set provides the most defect annotations (5438 defect samples) and the most detailed defect classification (125 defect categories

NVIDIA dialogue model ChatQA has evolved to version 2.0, with the context length mentioned at 128K NVIDIA dialogue model ChatQA has evolved to version 2.0, with the context length mentioned at 128K Jul 26, 2024 am 08:40 AM

The open LLM community is an era when a hundred flowers bloom and compete. You can see Llama-3-70B-Instruct, QWen2-72B-Instruct, Nemotron-4-340B-Instruct, Mixtral-8x22BInstruct-v0.1 and many other excellent performers. Model. However, compared with proprietary large models represented by GPT-4-Turbo, open models still have significant gaps in many fields. In addition to general models, some open models that specialize in key areas have been developed, such as DeepSeek-Coder-V2 for programming and mathematics, and InternVL for visual-language tasks.

Training with millions of crystal data to solve the crystallographic phase problem, the deep learning method PhAI is published in Science Training with millions of crystal data to solve the crystallographic phase problem, the deep learning method PhAI is published in Science Aug 08, 2024 pm 09:22 PM

Editor |KX To this day, the structural detail and precision determined by crystallography, from simple metals to large membrane proteins, are unmatched by any other method. However, the biggest challenge, the so-called phase problem, remains retrieving phase information from experimentally determined amplitudes. Researchers at the University of Copenhagen in Denmark have developed a deep learning method called PhAI to solve crystal phase problems. A deep learning neural network trained using millions of artificial crystal structures and their corresponding synthetic diffraction data can generate accurate electron density maps. The study shows that this deep learning-based ab initio structural solution method can solve the phase problem at a resolution of only 2 Angstroms, which is equivalent to only 10% to 20% of the data available at atomic resolution, while traditional ab initio Calculation

Google AI won the IMO Mathematical Olympiad silver medal, the mathematical reasoning model AlphaProof was launched, and reinforcement learning is so back Google AI won the IMO Mathematical Olympiad silver medal, the mathematical reasoning model AlphaProof was launched, and reinforcement learning is so back Jul 26, 2024 pm 02:40 PM

For AI, Mathematical Olympiad is no longer a problem. On Thursday, Google DeepMind's artificial intelligence completed a feat: using AI to solve the real question of this year's International Mathematical Olympiad IMO, and it was just one step away from winning the gold medal. The IMO competition that just ended last week had six questions involving algebra, combinatorics, geometry and number theory. The hybrid AI system proposed by Google got four questions right and scored 28 points, reaching the silver medal level. Earlier this month, UCLA tenured professor Terence Tao had just promoted the AI ​​Mathematical Olympiad (AIMO Progress Award) with a million-dollar prize. Unexpectedly, the level of AI problem solving had improved to this level before July. Do the questions simultaneously on IMO. The most difficult thing to do correctly is IMO, which has the longest history, the largest scale, and the most negative

PRO | Why are large models based on MoE more worthy of attention? PRO | Why are large models based on MoE more worthy of attention? Aug 07, 2024 pm 07:08 PM

In 2023, almost every field of AI is evolving at an unprecedented speed. At the same time, AI is constantly pushing the technological boundaries of key tracks such as embodied intelligence and autonomous driving. Under the multi-modal trend, will the situation of Transformer as the mainstream architecture of AI large models be shaken? Why has exploring large models based on MoE (Mixed of Experts) architecture become a new trend in the industry? Can Large Vision Models (LVM) become a new breakthrough in general vision? ...From the 2023 PRO member newsletter of this site released in the past six months, we have selected 10 special interpretations that provide in-depth analysis of technological trends and industrial changes in the above fields to help you achieve your goals in the new year. be prepared. This interpretation comes from Week50 2023

To provide a new scientific and complex question answering benchmark and evaluation system for large models, UNSW, Argonne, University of Chicago and other institutions jointly launched the SciQAG framework To provide a new scientific and complex question answering benchmark and evaluation system for large models, UNSW, Argonne, University of Chicago and other institutions jointly launched the SciQAG framework Jul 25, 2024 am 06:42 AM

Editor |ScienceAI Question Answering (QA) data set plays a vital role in promoting natural language processing (NLP) research. High-quality QA data sets can not only be used to fine-tune models, but also effectively evaluate the capabilities of large language models (LLM), especially the ability to understand and reason about scientific knowledge. Although there are currently many scientific QA data sets covering medicine, chemistry, biology and other fields, these data sets still have some shortcomings. First, the data form is relatively simple, most of which are multiple-choice questions. They are easy to evaluate, but limit the model's answer selection range and cannot fully test the model's ability to answer scientific questions. In contrast, open-ended Q&A

The accuracy rate reaches 60.8%. Zhejiang University's chemical retrosynthesis prediction model based on Transformer was published in the Nature sub-journal The accuracy rate reaches 60.8%. Zhejiang University's chemical retrosynthesis prediction model based on Transformer was published in the Nature sub-journal Aug 06, 2024 pm 07:34 PM

Editor | KX Retrosynthesis is a critical task in drug discovery and organic synthesis, and AI is increasingly used to speed up the process. Existing AI methods have unsatisfactory performance and limited diversity. In practice, chemical reactions often cause local molecular changes, with considerable overlap between reactants and products. Inspired by this, Hou Tingjun's team at Zhejiang University proposed to redefine single-step retrosynthetic prediction as a molecular string editing task, iteratively refining the target molecular string to generate precursor compounds. And an editing-based retrosynthetic model EditRetro is proposed, which can achieve high-quality and diverse predictions. Extensive experiments show that the model achieves excellent performance on the standard benchmark data set USPTO-50 K, with a top-1 accuracy of 60.8%.

See all articles