• 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

利用可解释人工智能对肠道微生物群中与自闭症相关的细菌进行个性化识别。

Personalized identification of autism-related bacteria in the gut microbiome using explainable artificial intelligence.

作者信息

Novielli Pierfrancesco, Romano Donato, Magarelli Michele, Diacono Domenico, Monaco Alfonso, Amoroso Nicola, Vacca Mirco, De Angelis Maria, Bellotti Roberto, Tangaro Sabina

机构信息

Dipartimento di Scienze del Suolo, della Pianta e degli Alimenti, Università degli Studi di Bari Aldo Moro, 70126 Bari, Italy.

Istituto Nazionale di Fisica Nucleare, Sezione di Bari, 70125 Bari, Italy.

出版信息

iScience. 2024 Aug 13;27(9):110709. doi: 10.1016/j.isci.2024.110709. eCollection 2024 Sep 20.

DOI:10.1016/j.isci.2024.110709
PMID:39286497
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC11402656/
Abstract

Autism spectrum disorder (ASD) affects social interaction and communication. Emerging evidence links ASD to gut microbiome alterations, suggesting that microbial composition may play a role in the disorder. This study employs explainable artificial intelligence (XAI) to examine the contributions of individual microbial species to ASD. By using local explanation embeddings and unsupervised clustering, the research identifies distinct ASD subgroups, underscoring the disorder's heterogeneity. Specific microbial biomarkers associated with ASD are revealed, and the best classifiers achieved an AU-ROC of 0.965 ± 0.005 and an AU-PRC of 0.967 ± 0.008. The findings support the notion that gut microbiome composition varies significantly among individuals with ASD. This work's broader significance lies in its potential to inform personalized interventions, enhancing precision in ASD management and classification. These insights highlight the importance of individualized microbiome profiles for developing tailored therapeutic strategies for ASD.

摘要

自闭症谱系障碍（ASD）会影响社交互动和沟通。新出现的证据将ASD与肠道微生物群改变联系起来，表明微生物组成可能在该疾病中起作用。本研究采用可解释人工智能（XAI）来研究个体微生物物种对ASD的影响。通过使用局部解释嵌入和无监督聚类，该研究确定了不同的ASD亚组，强调了该疾病的异质性。揭示了与ASD相关的特定微生物生物标志物，最佳分类器的AU-ROC为0.965±0.005，AU-PRC为0.967±0.008。这些发现支持了这样一种观点，即ASD个体之间的肠道微生物群组成存在显著差异。这项工作的更广泛意义在于其为个性化干预提供信息的潜力，提高ASD管理和分类的精准度。这些见解突出了个性化微生物组图谱对于制定针对ASD的定制治疗策略的重要性。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c24f/11402656/2824021a587e/gr10.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c24f/11402656/bc5d224ca81e/fx1.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c24f/11402656/fbd5507bde97/gr1.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c24f/11402656/0ec3af89cde9/gr2.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c24f/11402656/15aed8a58aa9/gr3.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c24f/11402656/8668980ac995/gr4.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c24f/11402656/c8e4163b6049/gr5.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c24f/11402656/7267aee4eb08/gr6.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c24f/11402656/e69729cac68e/gr7.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c24f/11402656/309848e60815/gr8.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c24f/11402656/4884066c67f3/gr9.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c24f/11402656/2824021a587e/gr10.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c24f/11402656/bc5d224ca81e/fx1.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c24f/11402656/fbd5507bde97/gr1.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c24f/11402656/0ec3af89cde9/gr2.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c24f/11402656/15aed8a58aa9/gr3.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c24f/11402656/8668980ac995/gr4.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c24f/11402656/c8e4163b6049/gr5.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c24f/11402656/7267aee4eb08/gr6.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c24f/11402656/e69729cac68e/gr7.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c24f/11402656/309848e60815/gr8.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c24f/11402656/4884066c67f3/gr9.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/c24f/11402656/2824021a587e/gr10.jpg

相似文献

1
Personalized identification of autism-related bacteria in the gut microbiome using explainable artificial intelligence.利用可解释人工智能对肠道微生物群中与自闭症相关的细菌进行个性化识别。
iScience. 2024 Aug 13;27(9):110709. doi: 10.1016/j.isci.2024.110709. eCollection 2024 Sep 20.
2
The Gut Microbiome in Autism: Study-Site Effects and Longitudinal Analysis of Behavior Change.自闭症中的肠道微生物群：研究地点效应及行为变化的纵向分析
mSystems. 2021 Apr 6;6(2):e00848-20. doi: 10.1128/mSystems.00848-20.
3
Underdevelopment of the gut microbiota and bacteria species as non-invasive markers of prediction in children with autism spectrum disorder.肠道微生物组和细菌种类发育不良作为自闭症谱系障碍儿童预测的非侵入性标志物。
Gut. 2022 May;71(5):910-918. doi: 10.1136/gutjnl-2020-324015. Epub 2021 Jul 26.
4
New and Preliminary Evidence on Altered Oral and Gut Microbiota in Individuals with Autism Spectrum Disorder (ASD): Implications for ASD Diagnosis and Subtyping Based on Microbial Biomarkers.自闭症谱系障碍（ASD）个体口腔和肠道微生物组改变的新证据和初步证据：基于微生物生物标志物的 ASD 诊断和亚型的意义。
Nutrients. 2019 Sep 6;11(9):2128. doi: 10.3390/nu11092128.
5
Explainable artificial intelligence for microbiome data analysis in colorectal cancer biomarker identification.用于结直肠癌生物标志物识别的微生物组数据分析的可解释人工智能
Front Microbiol. 2024 Feb 15;15:1348974. doi: 10.3389/fmicb.2024.1348974. eCollection 2024.
6
Gut Bacteria Shared by Children and Their Mothers Associate with Developmental Level and Social Deficits in Autism Spectrum Disorder.儿童与其母亲共有的肠道细菌与自闭症谱系障碍的发育水平和社交缺陷有关。
mSphere. 2020 Dec 2;5(6):e01044-20. doi: 10.1128/mSphere.01044-20.
7
A robust microbiome signature for autism spectrum disorder across different studies using machine learning.使用机器学习为自闭症谱系障碍建立稳健的微生物组特征：来自不同研究的证据。
Sci Rep. 2024 Jan 8;14(1):814. doi: 10.1038/s41598-023-50601-7.
8
Mapping the geographical distribution of the mucosa-associated gut microbiome in GI-symptomatic children with autism spectrum disorder.绘制患有自闭症谱系障碍且有胃肠道症状儿童的黏膜相关肠道微生物群的地理分布。
Am J Physiol Gastrointest Liver Physiol. 2024 Aug 1;327(2):G217-G234. doi: 10.1152/ajpgi.00101.2024. Epub 2024 Jun 18.
9
Robust, Generalizable, and Interpretable Artificial Intelligence-Derived Brain Fingerprints of Autism and Social Communication Symptom Severity.自闭症和社交沟通症状严重程度的稳健、可推广和可解释的人工智能衍生脑指纹。
Biol Psychiatry. 2022 Oct 15;92(8):643-653. doi: 10.1016/j.biopsych.2022.02.005. Epub 2022 Feb 16.
10
Oral microbiome activity in children with autism spectrum disorder.自闭症谱系障碍儿童的口腔微生物组活性。
Autism Res. 2018 Sep;11(9):1286-1299. doi: 10.1002/aur.1972. Epub 2018 Aug 14.

引用本文的文献

1
Diagnosing autism spectrum disorders using a double deep Q-Network framework based on social media footprints.基于社交媒体足迹，使用双深度Q网络框架诊断自闭症谱系障碍。
Front Med (Lausanne). 2025 Aug 20;12:1646249. doi: 10.3389/fmed.2025.1646249. eCollection 2025.
2
Personalized colorectal cancer risk assessment through explainable AI and Gut microbiome profiling.通过可解释的人工智能和肠道微生物群分析进行个性化结直肠癌风险评估。
Gut Microbes. 2025 Dec;17(1):2543124. doi: 10.1080/19490976.2025.2543124. Epub 2025 Aug 4.
3
Detection of breast cancer using machine learning and explainable artificial intelligence.

本文引用的文献

1
Microbiome preterm birth DREAM challenge: Crowdsourcing machine learning approaches to advance preterm birth research.微生物组早产 DREAM 挑战赛：众包机器学习方法以推进早产研究。
Cell Rep Med. 2024 Jan 16;5(1):101350. doi: 10.1016/j.xcrm.2023.101350. Epub 2023 Dec 21.
2
Machine learning approaches in microbiome research: challenges and best practices.微生物组研究中的机器学习方法：挑战与最佳实践
Front Microbiol. 2023 Sep 22;14:1261889. doi: 10.3389/fmicb.2023.1261889. eCollection 2023.
3
Metagenomics revealed a correlation of gut phageome with autism spectrum disorder.
利用机器学习和可解释人工智能检测乳腺癌。
Sci Rep. 2025 Jul 24;15(1):26931. doi: 10.1038/s41598-025-12644-w.
4
Low Back Pain in Italian Nurses: A Statistical Analysis of Disability and Work Productivity Impairment-An Observational Study.意大利护士的腰痛：残疾与工作效率受损的统计分析——一项观察性研究
Healthcare (Basel). 2025 Apr 28;13(9):1016. doi: 10.3390/healthcare13091016.
5
Leveraging explainable AI to predict soil respiration sensitivity and its drivers for climate change mitigation.利用可解释人工智能预测土壤呼吸敏感性及其对缓解气候变化的驱动因素。
Sci Rep. 2025 Apr 11;15(1):12527. doi: 10.1038/s41598-025-96216-y.
6
Explainable artificial intelligence for microbiome data analysis in colorectal cancer biomarker identification.用于结直肠癌生物标志物识别的微生物组数据分析的可解释人工智能
Front Microbiol. 2024 Feb 15;15:1348974. doi: 10.3389/fmicb.2024.1348974. eCollection 2024.
宏基因组学揭示了肠道噬菌体组与自闭症谱系障碍之间的相关性。
Gut Pathog. 2023 Aug 4;15(1):39. doi: 10.1186/s13099-023-00561-0.
4
Leveraging explainable AI for gut microbiome-based colorectal cancer classification.利用可解释人工智能进行基于肠道微生物组的结直肠癌分类。
Genome Biol. 2023 Feb 9;24(1):21. doi: 10.1186/s13059-023-02858-4.
5
Explainable artificial intelligence model for identifying COVID-19 gene biomarkers.用于识别 COVID-19 基因生物标志物的可解释人工智能模型。
Comput Biol Med. 2023 Mar;154:106619. doi: 10.1016/j.compbiomed.2023.106619. Epub 2023 Feb 1.
6
Worldwide impact of lifestyle predictors of dementia prevalence: An eXplainable Artificial Intelligence analysis.痴呆症患病率生活方式预测因素的全球影响：可解释人工智能分析
Front Big Data. 2022 Dec 8;5:1027783. doi: 10.3389/fdata.2022.1027783. eCollection 2022.
7
DiviK: divisive intelligent K-means for hands-free unsupervised clustering in big biological data.DiviK：用于生物大数据无监督聚类的可分离智能 K 均值算法。
BMC Bioinformatics. 2022 Dec 12;23(1):538. doi: 10.1186/s12859-022-05093-z.
8
Gut microbiome: A potential indicator for predicting treatment outcomes in major depressive disorder.肠道微生物群：预测重度抑郁症治疗结果的潜在指标。
Front Neurosci. 2022 Jul 22;16:813075. doi: 10.3389/fnins.2022.813075. eCollection 2022.
9
A robust framework to investigate the reliability and stability of explainable artificial intelligence markers of Mild Cognitive Impairment and Alzheimer's Disease.一个用于研究轻度认知障碍和阿尔茨海默病可解释人工智能标志物的可靠性和稳定性的强大框架。
Brain Inform. 2022 Jul 26;9(1):17. doi: 10.1186/s40708-022-00165-5.
10
Gut firmicutes: Relationship with dietary fiber and role in host homeostasis.肠道Firmicutes：与膳食纤维的关系及其在宿主稳态中的作用。
Crit Rev Food Sci Nutr. 2023 Nov;63(33):12073-12088. doi: 10.1080/10408398.2022.2098249. Epub 2022 Jul 12.