Jove
Visualize
联系我们
JoVE
x logofacebook logolinkedin logoyoutube logo
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 JournalMethods CollectionsJoVE Encyclopedia of Experiments存档
教育
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab Manual教师资源中心教师网站
使用条款与条件
隐私政策
政策

相关概念视频

Cluster Sampling Method01:20

Cluster Sampling Method

Appropriate sampling methods ensure that samples are drawn without bias and accurately represent the population. Because measuring the entire population in a study is not practical, researchers use samples to represent the population of interest.
To choose a cluster sample, divide the population into clusters (groups) and then randomly select some of the clusters. All the members from these clusters are in the cluster sample. For example, if you randomly sample four departments from your...

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

Pathway Representation via Intrinsic Structural Medoids (PRISM): A Structural Mapping Approach to Clustering Molecular Pathways.

bioRxiv : the preprint server for biology·2026
Same author

A New Family of Seniority-Restricted Coupled Cluster Methods.

The journal of physical chemistry. A·2026
Same author

Exploring New Construction Schemes for Extended-Hierarchy Configuration-Interaction Wave Functions.

The journal of physical chemistry. A·2026
Same author

Efficient exploration of peptide libraries using active learning with AlphaFold-based screening.

bioRxiv : the preprint server for biology·2026
Same author

Scaling <i>k</i>-Means for Multi-Million Frames: A Stratified NANI Approach for Large-Scale MD Simulations.

Journal of chemical information and modeling·2026
Same author

Best practices to cluster large molecular libraries.

bioRxiv : the preprint server for biology·2026

相关实验视频

Updated: Jun 30, 2026

Competitive Genomic Screens of Barcoded Yeast Libraries
11:59

Competitive Genomic Screens of Barcoded Yeast Libraries

Published on: August 11, 2011

18.2K

BitBIRCH:大分子库的高效集群.

Kenneth López Pérez1, Vicky Jung1, Lexin Chen1

  • 1Department of Chemistry & Quantum Theory Project, University of Florida Gainesville Florida 32611 USA quintana@chem.ufl.edu.

Digital discovery
|March 20, 2025
PubMed
概括

我们开发了BitBIRCH,这是一种快速且内存高效的集群算法,用于分析大型分子库. 这种机器学习方法显著加快了化学空间分析的速度,有效地处理数十亿个分子.

科学领域:

  • 计算化学是一种计算化学.
  • 化学信息学 化学信息学
  • 机器学习应用程序 机器学习应用程序

背景情况:

  • 机器学习 (ML) 对于分析大型化学数据集至关重要.
  • 聚类是探索化学空间的一个关键技术.
  • 现有的集群方法与现代分子图书馆的规模相抗衡.

研究的目的:

  • 为了介绍BitBIRCH,一个新的,高效的集群算法.
  • 解决目前用于大规模化学数据的方法的时间和内存限制.
  • 为了使数十亿分子数据集的分析.

主要方法:

  • BitBIRCH采用了一个树结构,用于O(N) 时间缩放,类似于BIRCH.
  • 它使用了对二进制指纹的即时相似性 (iSIM) 形式主义和Tanimoto相似性.
  • 并行和代近似用于处理极大的数据集.

主要成果:

  • 在BitBIRCH上,比特勒-布蒂纳对1.5M分子的速度提高了1000倍以上.
  • 该算法在不牺牲集群质量的情况下实现了高效率.
  • 在不到5个小时内完成了10亿个分子的聚类.

更多相关视频

Rapid High-throughput Species Identification of Botanical Material Using Direct Analysis in Real Time High Resolution Mass Spectrometry
11:14

Rapid High-throughput Species Identification of Botanical Material Using Direct Analysis in Real Time High Resolution Mass Spectrometry

Published on: October 2, 2016

11.5K
Using the Open-Source MALDI TOF-MS IDBac Pipeline for Analysis of Microbial Protein and Specialized Metabolite Data
09:29

Using the Open-Source MALDI TOF-MS IDBac Pipeline for Analysis of Microbial Protein and Specialized Metabolite Data

Published on: May 15, 2019

19.3K

相关实验视频

Last Updated: Jun 30, 2026

Competitive Genomic Screens of Barcoded Yeast Libraries
11:59

Competitive Genomic Screens of Barcoded Yeast Libraries

Published on: August 11, 2011

18.2K
Rapid High-throughput Species Identification of Botanical Material Using Direct Analysis in Real Time High Resolution Mass Spectrometry
11:14

Rapid High-throughput Species Identification of Botanical Material Using Direct Analysis in Real Time High Resolution Mass Spectrometry

Published on: October 2, 2016

11.5K
Using the Open-Source MALDI TOF-MS IDBac Pipeline for Analysis of Microbial Protein and Specialized Metabolite Data
09:29

Using the Open-Source MALDI TOF-MS IDBac Pipeline for Analysis of Microbial Protein and Specialized Metabolite Data

Published on: May 15, 2019

19.3K

结论:

  • BitBIRCH提供了一个可扩展和高效的解决方案,用于集群大规模的分子库.
  • 该方法克服了化学空间分析中的计算瓶.
  • 它为使用ML分析前所未有的大量化学数据集铺平了道路.