Autoencoder neural networks enable low dimensional structure analyses of microbial growth dynamics.

Autoencoder neural networks enable low dimensional structure analyses of microbial growth dynamics.
复制标题

DOI:
10.1038/s41467-023-43455-0
复制
发表时间:
2023-12-01
影响因子:
16.6
通讯作者:
You, Lingchong
You, Lingchong
中科院分区:
综合性期刊1区
文献类型:
--
作者:
Baig, Yasa;Ma, Helena R.;Xu, Helen;You, Lingchong

文献摘要

参考文献

相似文献

有效地表示微生物组动态的能力是其定量分析和工程中的一个关键挑战。通过使用自动编码神经网络,我们证明了微生物生长动力学可以被压缩到低维表示并以高保真的方式重建。这些低维嵌入在识别细菌菌株、预测抗生素耐药性等特征和预测群落动态等任务中与原始数据一样有效,甚至更好。此外,我们还证明了这些系统的基本动力学信息可以用比传统力学模型少得多的变量来捕捉。我们的工作表明,机器学习可以创建高维微生物组动力学的简明表示,以促进数据分析和获得新的生物学见解。在这里,作者应用自动编码器神经网络来展示微生物生长动力学可以被压缩到低维表示并以高保真度重建,便于定量预测和推断潜在的机制。
The ability to effectively represent microbiome dynamics is a crucial challenge in their quantitative analysis and engineering. By using autoencoder neural networks, we show that microbial growth dynamics can be compressed into low-dimensional representations and reconstructed with high fidelity. These low-dimensional embeddings are just as effective, if not better, than raw data for tasks such as identifying bacterial strains, predicting traits like antibiotic resistance, and predicting community dynamics. Additionally, we demonstrate that essential dynamical information of these systems can be captured using far fewer variables than traditional mechanistic models. Our work suggests that machine learning can enable the creation of concise representations of high-dimensional microbiome dynamics to facilitate data analysis and gain new biological insights. Here, the authors apply autoencoder neural networks to show that microbial growth dynamics can be compressed into low-dimensional representations and reconstructed with high fidelity, facilitating quantitative predictions and deduction of potential mechanisms.
DOI: 10.7554/elife.25950
发表时间: 2017-11-01
期刊: eLife
影响因子: 7.7
作者:
Cooper RM;Tsimring L;Hasty J
通讯作者: Hasty J
DOI: 10.1126/science.177.4047.393
发表时间: 1972-01-01
期刊: SCIENCE
影响因子: 56.9
作者:
ANDERSON, PW
通讯作者: ANDERSON, PW
在抗生素处理过程中,映射对种群级动力学的单细胞响应
DOI: 10.15252/msb.202211475
发表时间: 2023-05-10
影响因子: 9.9
作者:
Kim, Kyeri;Wang, Teng;Ma, Helena R.;Simsek, Emrah;Li, Boyan;Andreani, Virgile;You, Lingchong
通讯作者: You, Lingchong
DOI: 10.1038/s43018-020-0079-6
发表时间: 2020-06-01
期刊: NATURE CANCER
影响因子: 22.7
作者:
Bozic, Ivana;Wu, Catherine J.
通讯作者: Wu, Catherine J.
DOI: 10.1038/s41467-021-22938-y
发表时间: 2021-05-31
影响因子: 16.6
作者:
Clark RL;Connors BM;Stevenson DM;Hromada SE;Hamilton JJ;Amador-Noguez D;Venturelli OS
通讯作者: Venturelli OS