• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利：CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法，用中文像聊天一样搜索，搜遍4000万医学文献。AI智能推荐，让科研检索更轻松。

立即免费搜索

文件翻译

保留排版，准确专业，支持PDF/Word/PPT等文件格式，支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述，25分钟生成高质量综述，智能提取关键信息，辅助科研写作。

立即免费体验

神经网络方法，包括使用拓扑数据分析，可根据处理条件增强对人类诱导多能干细胞集落的分类。

Neural network approaches, including use of topological data analysis, enhance classification of human induced pluripotent stem cell colonies by treatment condition.

作者信息

de Perez Alexander Ruys, Anderson Paul E, Dimitrova Elena S, Kemp Melissa L

机构信息

Mathematics Department, Bailey College of Science and Mathematics, California Polytechnic State University - San Luis Obispo, San Luis Obispo, California, United States of America.

School of Mathematics, Georgia Institute of Technology, Atlanta, Georgia, United States of America.

出版信息

PLoS Comput Biol. 2025 Jul 11;21(7):e1012801. doi: 10.1371/journal.pcbi.1012801. eCollection 2025 Jul.

DOI:10.1371/journal.pcbi.1012801
PMID:40644508
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC12270303/
Abstract

Understanding how stem cells organize to form early tissue layers remains an important open question in developmental biology. Helpful in understanding this process are biomarkers or features that signal when a significant transition or decision occurs. We show such features from the spatial layout of the cells in a colony are sufficient to train neural networks to classify stem cell colonies according to differentiation protocol treatments each colony has received. We use topological data analysis to derive input information about the cells' positions to a four-layer feedforward neural network. We find that despite the simplicity of this approach, such a network has performance similar to the traditional image classifier ResNet. We also find that network performance may reveal the time window during which differentiation occurs across multiple conditions.

摘要

了解干细胞如何组织形成早期组织层仍然是发育生物学中一个重要的悬而未决的问题。有助于理解这一过程的是生物标志物或特征，它们能在发生重大转变或决策时发出信号。我们表明，来自集落中细胞空间布局的此类特征足以训练神经网络，根据每个集落所接受的分化方案处理对干细胞集落进行分类。我们使用拓扑数据分析来推导关于细胞位置的输入信息，输入到一个四层前馈神经网络中。我们发现，尽管这种方法很简单，但这样的网络性能与传统图像分类器ResNet相似。我们还发现，网络性能可能揭示了在多种条件下发生分化的时间窗口。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/838b/12270303/dc9ed3e5ea67/pcbi.1012801.g014.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/838b/12270303/7794fd4a32f5/pcbi.1012801.g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/838b/12270303/6159edf77292/pcbi.1012801.g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/838b/12270303/fb0b28e280b7/pcbi.1012801.g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/838b/12270303/0d84fbb0c66a/pcbi.1012801.g004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/838b/12270303/3a41523d6313/pcbi.1012801.g005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/838b/12270303/619bd5c96225/pcbi.1012801.g006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/838b/12270303/a95e1d42192c/pcbi.1012801.g007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/838b/12270303/c127b68f9a1c/pcbi.1012801.g008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/838b/12270303/ba43efa4254e/pcbi.1012801.g009.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/838b/12270303/32955b76aa8c/pcbi.1012801.g010.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/838b/12270303/6e43aa5eaf87/pcbi.1012801.g011.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/838b/12270303/61bbe9b98b23/pcbi.1012801.g012.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/838b/12270303/99a1f6b0f1d6/pcbi.1012801.g013.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/838b/12270303/dc9ed3e5ea67/pcbi.1012801.g014.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/838b/12270303/7794fd4a32f5/pcbi.1012801.g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/838b/12270303/6159edf77292/pcbi.1012801.g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/838b/12270303/fb0b28e280b7/pcbi.1012801.g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/838b/12270303/0d84fbb0c66a/pcbi.1012801.g004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/838b/12270303/3a41523d6313/pcbi.1012801.g005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/838b/12270303/619bd5c96225/pcbi.1012801.g006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/838b/12270303/a95e1d42192c/pcbi.1012801.g007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/838b/12270303/c127b68f9a1c/pcbi.1012801.g008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/838b/12270303/ba43efa4254e/pcbi.1012801.g009.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/838b/12270303/32955b76aa8c/pcbi.1012801.g010.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/838b/12270303/6e43aa5eaf87/pcbi.1012801.g011.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/838b/12270303/61bbe9b98b23/pcbi.1012801.g012.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/838b/12270303/99a1f6b0f1d6/pcbi.1012801.g013.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/838b/12270303/dc9ed3e5ea67/pcbi.1012801.g014.jpg

相似文献

1
Neural network approaches, including use of topological data analysis, enhance classification of human induced pluripotent stem cell colonies by treatment condition.神经网络方法，包括使用拓扑数据分析，可根据处理条件增强对人类诱导多能干细胞集落的分类。
PLoS Comput Biol. 2025 Jul 11;21(7):e1012801. doi: 10.1371/journal.pcbi.1012801. eCollection 2025 Jul.
2
Short-Term Memory Impairment短期记忆障碍
3
Sexual Harassment and Prevention Training性骚扰与预防培训
4
The Lived Experience of Autistic Adults in Employment: A Systematic Search and Synthesis.成年自闭症患者的就业生活经历：系统检索与综述
Autism Adulthood. 2024 Dec 2;6(4):495-509. doi: 10.1089/aut.2022.0114. eCollection 2024 Dec.
5
Idiopathic (Genetic) Generalized Epilepsy特发性（遗传性）全身性癫痫
6
Stem cell insights into human trophoblast lineage differentiation.干细胞对人类滋养层谱系分化的研究。
Hum Reprod Update. 2016 Dec;23(1):77-103. doi: 10.1093/humupd/dmw026. Epub 2016 Sep 2.
7
"In a State of Flow": A Qualitative Examination of Autistic Adults' Phenomenological Experiences of Task Immersion.“心流状态”：对自闭症成年人任务沉浸现象学体验的质性研究
Autism Adulthood. 2024 Sep 16;6(3):362-373. doi: 10.1089/aut.2023.0032. eCollection 2024 Sep.
8
Derivation of trophoblast stem cells from naïve human pluripotent stem cells.从原始人多能干细胞中衍生滋养层干细胞。
Elife. 2020 Feb 12;9:e52504. doi: 10.7554/eLife.52504.
9
Assessing the comparative effects of interventions in COPD: a tutorial on network meta-analysis for clinicians.评估慢性阻塞性肺疾病干预措施的比较效果：面向临床医生的网状Meta分析教程
Respir Res. 2024 Dec 21;25(1):438. doi: 10.1186/s12931-024-03056-x.
10
The health economics of insulin therapy: How do we address the rising demands, costs, inequalities and barriers to achieving optimal outcomes.胰岛素治疗的卫生经济学：我们如何应对不断增长的需求、成本、不平等现象以及实现最佳治疗效果的障碍。
Diabetes Obes Metab. 2025 Jul;27 Suppl 5(Suppl 5):24-35. doi: 10.1111/dom.16488. Epub 2025 Jun 4.

本文引用的文献

1
Is the aspect ratio of cells important in deep learning? A robust comparison of deep learning methods for multi-scale cytopathology cell image classification: From convolutional neural networks to visual transformers.细胞的长宽比在深度学习中重要吗？用于多尺度细胞病理学细胞图像分类的深度学习方法的稳健比较：从卷积神经网络到视觉Transformer。
Comput Biol Med. 2022 Feb;141:105026. doi: 10.1016/j.compbiomed.2021.105026. Epub 2021 Nov 11.
2
Deep neural net tracking of human pluripotent stem cells reveals intrinsic behaviors directing morphogenesis.深度神经网络追踪人类多能干细胞揭示了指导形态发生的内在行为。
Stem Cell Reports. 2021 May 11;16(5):1317-1330. doi: 10.1016/j.stemcr.2021.04.008.
3
Topological data analysis of collective and individual epithelial cells using persistent homology of loops.
利用环的持久同调对集体和个体上皮细胞进行拓扑数据分析。
Soft Matter. 2021 May 5;17(17):4653-4664. doi: 10.1039/d1sm00072a.
4
Structural basis for distinct roles of SMAD2 and SMAD3 in FOXH1 pioneer-directed TGF-β signaling.SMAD2 和 SMAD3 在 FOXH1 先驱指导的 TGF-β 信号中的不同作用的结构基础。
Genes Dev. 2019 Nov 1;33(21-22):1506-1524. doi: 10.1101/gad.330837.119. Epub 2019 Oct 3.
5
Intelligent Image-Activated Cell Sorting.智能图像激活细胞分选
Cell. 2018 Sep 20;175(1):266-276.e13. doi: 10.1016/j.cell.2018.08.028. Epub 2018 Aug 27.
6
Prospective identification of hematopoietic lineage choice by deep learning.通过深度学习对造血谱系选择的前瞻性鉴定。
Nat Methods. 2017 Apr;14(4):403-406. doi: 10.1038/nmeth.4182. Epub 2017 Feb 20.
7
A multi-scale convolutional neural network for phenotyping high-content cellular images.用于高内涵细胞图像表型分析的多尺度卷积神经网络。
Bioinformatics. 2017 Jul 1;33(13):2010-2019. doi: 10.1093/bioinformatics/btx069.
8
Cell population structure prior to bifurcation predicts efficiency of directed differentiation in human induced pluripotent cells.分叉前的细胞群体结构可预测人类诱导多能干细胞定向分化的效率。
Proc Natl Acad Sci U S A. 2017 Feb 28;114(9):2271-2276. doi: 10.1073/pnas.1621412114. Epub 2017 Feb 6.
9
Prediction of Differentiation Tendency Toward Hepatocytes from Gene Expression in Undifferentiated Human Pluripotent Stem Cells.从未分化的人类多能干细胞的基因表达预测向肝细胞的分化趋势
Stem Cells Dev. 2016 Dec 15;25(24):1884-1897. doi: 10.1089/scd.2016.0099. Epub 2016 Nov 8.
10
Using persistent homology and dynamical distances to analyze protein binding.利用持久同调与动态距离分析蛋白质结合。
Stat Appl Genet Mol Biol. 2016 Mar;15(1):19-38. doi: 10.1515/sagmb-2015-0057.