Search research articles

关于 JoVE

概览领导团队博客 JoVE 帮助中心

作者

出版流程编辑委员会范围与政策同行评审常见问题投稿

图书馆员

用户评价订阅访问资源图书馆顾问委员会常见问题

研究

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments 存档

教育

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual 教师资源中心教师网站

使用条款与条件

相关概念视频

Antibiotic Selection

Antibiotic Selection

您也可能阅读

相关文章

通过共同作者、期刊和引用图与本文相关的文章。

排序

Same author

Quantifying Health-Related Risk Factors Associated with Breast and Prostate Cancer Burden: The Role of Trends and Disparities in Obesity and Cholesterol.

Iranian journal of public health·2026

Same author

Score Matching for Differential Abundance Testing of Compositional High-Throughput Sequencing Data.

Statistics in medicine·2026

Same author

Molecular genetic characterization of bacterial KH-domain proteins.

bioRxiv : the preprint server for biology·2026

Same author

The PceA-orthologous reductive dehalogenase of Dehalococcoides mccartyi CBDB1 is involved in 1,2,4-trichlorobenzene respiration.

FEMS microbiology ecology·2026

Same author

Early diagnosis of Alzheimer's disease based on brain morphological changes: A comprehensive approach combining voxel-based morphometry and deep learning.

Neuroimage. Reports·2026

Same author

Mechanisms of Antibiotic Resistance and Novel Therapeutic Approaches for <i>Mycobacterium tuberculosis</i>: A Narrative Review With a Focus on Tuberculosis Mutations in Iran.

Health science reports·2025

Search research articles

相关实验视频

Updated: May 15, 2025

High-throughput Identification of Synergistic Drug Combinations by the Overlap2 Method

High-throughput Identification of Synergistic Drug Combinations by the Overlap2 Method

Published on: May 21, 2018

预先训练的分子表示使抗微生物发现成为可能.

Roberto Olayo-Alarcon^1,2, Martin K Amstalden³, Annamaria Zannoni⁴

¹Department of Statistics, Ludwig-Maximilians-Universität München, Munich, Germany. roberto.olayo@lmu.de.

Nature communications

|April 10, 2025

概括

抗微生物耐药性是一种全球性威胁. 一种新的计算方法,MoleE,加速了新型抗微生物化合物的发现,包括对现有药物的重新用途.

更多相关视频

Semi-automated Biopanning of Bacterial Display Libraries for Peptide Affinity Reagent Discovery and Analysis of Resulting Isolates

Semi-automated Biopanning of Bacterial Display Libraries for Peptide Affinity Reagent Discovery and Analysis of Resulting Isolates

Published on: December 6, 2017

Biosensor-based High Throughput Biopanning and Bioinformatics Analysis Strategy for the Global Validation of Drug-protein Interactions

Biosensor-based High Throughput Biopanning and Bioinformatics Analysis Strategy for the Global Validation of Drug-protein Interactions

Published on: December 1, 2020

相关实验视频

Last Updated: May 15, 2025

High-throughput Identification of Synergistic Drug Combinations by the Overlap2 Method

High-throughput Identification of Synergistic Drug Combinations by the Overlap2 Method

Published on: May 21, 2018

Semi-automated Biopanning of Bacterial Display Libraries for Peptide Affinity Reagent Discovery and Analysis of Resulting Isolates

Semi-automated Biopanning of Bacterial Display Libraries for Peptide Affinity Reagent Discovery and Analysis of Resulting Isolates

Published on: December 6, 2017

Biosensor-based High Throughput Biopanning and Bioinformatics Analysis Strategy for the Global Validation of Drug-protein Interactions

Biosensor-based High Throughput Biopanning and Bioinformatics Analysis Strategy for the Global Validation of Drug-protein Interactions

Published on: December 1, 2020

科学领域:

计算化学是一种计算化学.
药物发现药物发现
机器学习机器学习

背景情况:

抗菌素耐药性 (AMR) 是一个日益严重的全球卫生危机,减少了现有的抗生素的有效性.
对抗微生物活性新型化合物的实验查是资源密集且缓慢的.
目前用于药物发现的深度学习模型通常需要广泛的定制培训数据.

研究的目的:

引入一种轻量级的计算策略,以加速抗微生物发现.
为了利用自我监督的学习来生成分子表示.
开发一种用于评估使用未标记化学结构的抗微生物潜力的预测模型.

主要方法:

利用了MoleE (通过冗余减少嵌入的分子表示),一个自我监督的深度学习框架.
结合了MoleE的学习分子表示与现有的化合物-细菌活动数据.
开发了一种用于评估抗微生物潜力的一般预测模型.

主要成果:

该模型成功地识别了与当前抗生素不同的新型增长抑制化合物.
发现并实验验证了三种现有的针对人类的药物作为黄金葡萄球菌的抑制剂.
证明了该模型评估化合物的抗菌潜力的能力.

结论:

拟议的计算框架提供了一种具有成本效益和可行的方法来加速抗生素发现.
这一策略可以通过利用未标记的化学数据,帮助识别新的抗菌剂.
这些发现突出了自我监督学习在解决抗药性抵抗危机方面的潜力.