AbstractHere we present biVI, which combines the variational autoencoder framework of scVI with biophysical models describing the transcription and splicing kinetics of RNA molecules. We demonstrate on simulated and experimental single-cell RNA sequencing data that biVI retains the variational autoencoder’s ability to capture cell type structure in a low-dimensional space while further enabling genome-wide exploration of the biophysical mechanisms, such as system burst sizes and degradation rates, that underlie observations..

摘要在这里，我们介绍了biVI，它将scVI的可变自动编码器框架与描述RNA分子转录和剪接动力学的生物物理模型相结合。我们在模拟和实验单细胞RNA测序数据上证明，biVI保留了变分自动编码器在低维空间捕获细胞类型结构的能力，同时进一步实现了对生物物理机制的全基因组探索，例如系统爆发大小和降解率，这是观察的基础。。

Access through your institution

通过您的机构访问

Buy or subscribe

购买或订阅

This is a preview of subscription content, access via your institution

这是订阅内容的预览，可通过您的机构访问

Access options

访问选项

Access through your institution

通过您的机构访问

Access through your institution

通过您的机构访问

Change institution

变革机构

Buy or subscribe

购买或订阅

Access Nature and 54 other Nature Portfolio journalsGet Nature+, our best-value online-access subscription24,99 € / 30 dayscancel any timeLearn moreSubscription info for Chinese customersWe have a dedicated website for our Chinese customers. Please go to naturechina.com to subscribe to this journal.Go to naturechina.comBuy this articlePurchase on Springer LinkInstant access to full article PDFBuy nowPrices may be subject to local taxes which are calculated during checkout.

Access Nature和54篇其他Nature Portfolio journalsGet Nature+，我们最有价值的在线订阅24,99欧元/30天，随时为中国客户获取更多订阅信息我们为中国客户提供了一个专门的网站。请访问naturechina.com订阅本期刊。访问naturechina.comBuy本文在Springer link上购买即时访问完整文章PDFBuy now价格可能需要缴纳结帐时计算的地方税。

Additional access options:

其他访问选项：

Log in

登录

Learn about institutional subscriptions

了解机构订阅

Read our FAQs

阅读我们的常见问题

Contact customer support

联系客户支持

Fig. 1: biVI reinterprets and extends scVI to infer biophysical parameters.Fig. 2: biVI fits single-cell data from mouse primary motor cortex (Allen sample B08) and suggests the biophysical basis for expression differences.

图1:biVI重新解释和扩展scVI以推断生物物理参数。图2:biVI拟合了来自小鼠初级运动皮层（Allen样本B08）的单细胞数据，并提出了表达差异的生物物理基础。

Data availability

数据可用性

Previously published raw FASTQs for Allen samples were obtained from http://data.nemoarchive.org/biccn/grant/u19_zeng/zeng/transcriptome/scell/10x_v2/mouse/raw/MOp/ with associated metadata from http://data.nemoarchive.org/biccn/grant/u19_zeng/zeng/transcriptome/scell/10x_v3/mouse/processed/analysis/10X_cells_v3_AIBS/.

先前发布的艾伦样品的原始FASTQ来自http://data.nemoarchive.org/biccn/grant/u19_zeng/zeng/transcriptome/scell/10x_v2/mouse/raw/MOp/具有来自的关联元数据http://data.nemoarchive.org/biccn/grant/u19_zeng/zeng/transcriptome/scell/10x_v3/mouse/processed/analysis/10X_cells_v3_AIBS/.

For burst size validation, FASTQs were obtained at the Gene Expression Omnibus under accession number GSE176044 (ref. 35) and raw seqFISH+ data from Zenodo project 6693825 (ref. 36). The mm10 and GRCh38 (2020-A version) reference genomes from 10x Genomics were used for pseudoalignment (https://support.10xgenomics.com/single-cell-gene-expression/software/downloads/latest).

对于突发大小验证，FASTQ是在Gene Expression Omnibus获得的，登录号为GSE176044（参考文献35），原始seqFISH+数据来自Zenodo project 6693825（参考文献36）。来自10x Genomics的mm10和GRCh38（2020-A版）参考基因组用于假比对(https://support.10xgenomics.com/single-cell-gene-expression/software/downloads/latest)。

Raw data for validation of degradation rate inference is available at the Gene Expression Omnibus under accession number GSE128365 (ref. 23). All processed data and count matrices for analyses (simulated data, Allen samples, and data used for validation and Supplementary figures) are provided in a zipped file in Zenodo package 10530877 (ref.

用于验证降解率推断的原始数据可在Gene Expression Omnibus上获得，登录号为GSE128365（参考文献23）。用于分析的所有处理数据和计数矩阵（模拟数据，艾伦样本以及用于验证和补充数字的数据）都在Zenodo软件包10530877（参考文献）的压缩文件中提供。

37). Results (including inferred parameters) can be found in the same Zenodo package37..

37）。结果（包括推断的参数）可以在相同的Zenodo软件包37中找到。。

Code availability

代码可用性

All scripts and notebooks used to train models, run analyses and create figures are available at the GitHub repository at https://github.com/pachterlab/CGCCP_2023. The repository also contains the biVI source code, instructions for package installation and a Google Colaboratory notebook demonstrating the method.

所有用于训练模型、运行分析和创建数字的脚本和笔记本都可以在GitHub存储库中找到https://github.com/pachterlab/CGCCP_2023.该存储库还包含biVI源代码、软件包安装说明和演示该方法的Google协作笔记本。

All code is available under an open-source BSD-2-Clause license..

所有代码都可以在开源BSD-2条款许可下获得。。

ReferencesLa Manno, G. et al. RNA velocity of single cells. Nature 560, 494–498 (2018).Article

参考文献La Manno，G。等人。单细胞的RNA速度。自然560494-498（2018）。文章

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Melsted, P. et al. Modular, efficient and constant-memory single-cell RNA-seq preprocessing. Nat. Biotechnol. 39, 813–818 (2021).Article

Melsted，P。等人。模块化，高效和恒定记忆单细胞RNA-seq预处理。美国国家生物技术公司。39813-818（2021）。文章

CAS

中科院

PubMed

PubMed

Google Scholar

谷歌学者

Peterson, V. M. et al. Multiplexed quantification of proteins and transcripts in single cells. Nat. Biotechnol. 35, 936–939 (2017).Article

Peterson，V.M.等人。单细胞中蛋白质和转录物的多重定量。美国国家生物技术公司。35936-939（2017）。文章

CAS

中科院

PubMed

PubMed

Google Scholar

谷歌学者

Mimitou, E. P. et al. Multiplexed detection of proteins, transcriptomes, clonotypes and CRISPR perturbations in single cells. Nat. Methods 16, 409–412 (2019).Article

Mimitou，E.P.等人。单细胞中蛋白质，转录组，克隆型和CRISPR扰动的多重检测。自然方法16409-412（2019）。文章

CAS

中科院

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Stoeckius, M. et al. Simultaneous epitope and transcriptome measurement in single cells. Nat. Methods 14, 865–868 (2017).Article

Stoeckius，M.等人。单细胞中表位和转录组的同时测量。自然方法14865-868（2017）。文章

CAS

中科院

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Chung, H. et al. Joint single-cell measurements of nuclear proteins and RNA in vivo. Nat. Methods 18, 1204–1212 (2021).Article

Chung，H.等人。体内核蛋白和RNA的联合单细胞测量。自然方法181204-1212（2021）。文章

CAS

中科院

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Reyes, M., Billman, K., Hacohen, N. & Blainey, P. C. Simultaneous profiling of gene expression and chromatin accessibility in single cells. Adv. Biosyst. 3, 11 (2019).Article

Reyes，M.，Billman，K.，Hacohen，N。＆Blainey，P.C。同时分析单细胞中的基因表达和染色质可及性。高级生物系统。3，11（2019）。文章

Google Scholar

谷歌学者

De Rop, F. et al. HyDrop enables droplet based single-cell ATAC-seq and single-cell RNA-seq using dissolvable hydrogel beads. eLife 11, e73971 (2022).Article

De Rop，F。等人HyDrop使用可溶解的水凝胶珠粒实现了基于液滴的单细胞ATAC-seq和单细胞RNA-seq。eLife 11，e73971（2022）。文章

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Gorin, G., Vastola, J. J., Fang, M. & Pachter, L. Interpretable and tractable models of transcriptional noise for the rational design of single-molecule quantification experiments. Nat. Commun. 13, 7620 (2022).Article

Gorin，G.，Vastola，J.J.，Fang，M。＆Pachter，L。用于合理设计单分子定量实验的转录噪声的可解释和易处理模型。国家公社。137620（2022年）。文章

CAS

中科院

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Svensson, V., Vento-Tormo, R. & Teichmann, S. A. Exponential scaling of single-cell RNA-seq in the past decade. Nat. Protoc. 13, 599–604 (2018).Article

Svensson，V.，Vento-Tormo，R。＆Teichmann，S.A。在过去十年中单细胞RNA-seq的指数缩放。自然协议。13599-604（2018）。文章

CAS

中科院

PubMed

PubMed

Google Scholar

谷歌学者

Gayoso, A. et al. Joint probabilistic modeling of single-cell multi-omic data with totalVI. Nat. Methods 18, 272–282 (2021).Article

Gayoso，A.等人。使用totalVI对单细胞多组学数据进行联合概率建模。自然方法18272-282（2021）。文章

CAS

中科院

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Gayoso, A. et al. A Python library for probabilistic analysis of single-cell omics data. Nat. Biotechnol. 40, 163–166 (2022).Article

Gayoso，A。等人。用于单细胞组学数据概率分析的Python库。美国国家生物技术公司。40163-166（2022）。文章

CAS

中科院

PubMed

PubMed

Google Scholar

谷歌学者

Lin, X., Tian, T., Wei, Z. & Hakonarson, H. Clustering of single-cell multi-omics data with a multimodal deep learning method. Nat. Commun. 13, 7705 (2022).Article

Lin，X.，Tian，T.，Wei，Z。＆Hakonarson，H。使用多模式深度学习方法对单细胞多组学数据进行聚类。国家公社。137705（2022）。文章

CAS

中科院

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Lopez, R., Regier, J., Cole, M. B., Jordan, M. I. & Yosef, N. Deep generative modeling for single-cell transcriptomics. Nat. Methods 15, 1053–1058 (2018).Article

。自然方法151053-1058（2018）。文章

CAS

中科院

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Ashuach, T., Reidenbach, D. A., Gayoso, A. & Yosef, N. PeakVI: a deep generative model for single-cell chromatin accessibility analysis. Cell Rep. Methods 2, 100182 (2022).Article

Ashuach，T.，Reidenbach，D.A.，Gayoso，A。＆Yosef，N.PeakVI：单细胞染色质可及性分析的深度生成模型。细胞代表方法2100182（2022）。文章

CAS

中科院

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Raj, A., Peskin, C. S., Tranchina, D., Vargas, D. Y. & Tyagi, S. Stochastic mRNA synthesis in mammalian cells. PLoS Biol. 4, e309 (2006).Article

Raj，A.，Peskin，C.S.，Tranchina，D.，Vargas，D.Y。＆Tyagi，S。哺乳动物细胞中的随机mRNA合成。《公共科学图书馆·生物学》。4，e309（2006）。文章

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Dar, R. D. et al. Transcriptional burst frequency and burst size are equally modulated across the human genome. Proc. Natl Acad. Sci. USA 109, 17454–17459 (2012).Article

Dar，R.D.等人。转录突发频率和突发大小在整个人类基因组中受到同等调节。程序。国家科学院。科学。美国10917454-17459（2012）。文章

CAS

中科院

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Sanchez, A. & Golding, I. Genetic determinants and cellular constraints in noisy gene expression. Science 342, 1188–1193 (2013).Article

Sanchez，A。＆Golding，I。噪声基因表达中的遗传决定因素和细胞限制。科学3421188-1193（2013）。文章

CAS

中科院

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Singh, A. & Bokes, P. Consequences of mRNA transport on stochastic variability in protein levels. Biophys. J. 103, 1087–1096 (2012).Article

Singh，A。＆Bokes，P。mRNA转运对蛋白质水平随机变异的影响。生物物理。J、 1031087-1096（2012）。文章

CAS

中科院

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Gorin, G., Carilli, M., Chari, T. & Pachter, L. Spectral neural approximations for models of transcriptional dynamics. Biophys. J. https://doi.org/10.1016/j.bpj.2024.04.034 (2024).Pearl, J. Causal inference in statistics: an overview. Stat. Surveys 3, 96–146 (2009).Takei, Y. et al. High-resolution spatial multi-omics reveals cell-type specific nuclear compartments.

Gorin，G.，Carilli，M.，Chari，T。＆Pachter，L。转录动力学模型的光谱神经近似。生物物理。J。https://doi.org/10.1016/j.bpj.2024.04.034（2024年）。Pearl，J。统计学中的因果推断：概述。统计调查3，96–146（2009）。Takei，Y.等人。高分辨率空间多组学揭示了细胞类型特异性核区室。

Preprint at bioRxiv https://doi.org/10.1101/2023.05.07.539762 (2023).Battich, N. et al. Sequencing metabolically labeled transcripts in single cells reveals mRNA turnover strategies. Science 367, 1151–1156 (2020).Article .

bioRxiv预印本https://doi.org/10.1101/2023.05.07.539762。Battich，N。等人。对单细胞中代谢标记的转录本进行测序揭示了mRNA周转策略。科学3671151-1156（2020）。文章。

CAS

中科院

PubMed

PubMed

Google Scholar

谷歌学者

Yao, Z. et al. A transcriptomic and epigenomic cell atlas of the mouse primary motor cortex. Nature 598, 103–110 (2021).Article

Yao，Z。等人。小鼠初级运动皮层的转录组学和表观基因组细胞图谱。自然598103-110（2021）。文章

CAS

中科院

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Kuang, X. L. et al. Spatio-temporal expression of a novel neuron-derived neurotrophic factor (NDNF) in mouse brains during development. BMC Neurosci. 11, 137 (2010).Article

Kuang，X.L.等人。一种新型神经元源性神经营养因子（NDNF）在小鼠大脑发育过程中的时空表达。。11137（2010）。文章

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Ulland, T. K. & Colonna, M. Trem2 – a key player in microglial biology and alzheimer disease. Nat. Rev. Neurol. 14, 667–675 (2018).Article

Ulland，T.K.＆Colonna，M.Trem2–小胶质细胞生物学和阿尔茨海默病的关键参与者。神经病学杂志。14667-675（2018）。文章

CAS

中科院

PubMed

PubMed

Google Scholar

谷歌学者

Munsky, B., Li, G., Fox, Z. R., Shepherd, D. P. & Neuert, G. Distribution shapes govern the discovery of predictive models for gene regulation. Proc. Natl Acad. Sci. USA 115, 7533–7538 (2018).Article

Munsky，B.，Li，G.，Fox，Z.R.，Shepherd，D.P。＆Neuert，G。分布形状决定了基因调控预测模型的发现。程序。国家科学院。科学。美国1157533-7538（2018）。文章

CAS

中科院

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Ham, L., Brackston, R. D. & Stumpf, M. P. H. Extrinsic noise and heavy-tailed laws in gene expression. Phys. Rev. Lett. 124, 108101 (2020).Article

Ham，L.，Brackston，R.D。和Stumpf，M.P.H。基因表达中的外在噪音和重尾定律。物理。Lett牧师。124108101（2020）。文章

CAS

中科院

PubMed

PubMed

Google Scholar

谷歌学者

Elowitz, M. B., Levine, A. J., Siggia, E. D. & Swain, P. S. Stochastic gene expression in a single cell. Science 297, 1183–1186 (2002).Article

Elowitz，M.B.，Levine，A.J.，Siggia，E.D。和Swain，P.S。单细胞中的随机基因表达。科学2971183-1186（2002）。文章

CAS

中科院

PubMed

PubMed

Google Scholar

谷歌学者

Gorin, G. & Pachter, L. Length biases in single-cell RNA sequencing of pre-mRNA. Biophys. Rep. 3, 100097 (2023).CAS

Gorin，G。＆Pachter，L。前mRNA单细胞RNA测序中的长度偏差。Biophys。。中科院

Google Scholar

谷歌学者

Svensson, V., Gayoso, A., Yosef, N. & Pachter, L. Interpretable factor models of single-cell RNA-seq via variational autoencoders. Bioinformatics 36, 3418–3421 (2020).Article

Svensson，V.，Gayoso，A.，Yosef，N。＆Pachter，L。通过变分自动编码器的单细胞RNA-seq的可解释因子模型。生物信息学363418-3421（2020）。文章

CAS

中科院

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Wang, J. et al. Gene expression distribution deconvolution in single-cell RNA sequencing. Proc. Natl Acad. Sci. USA 115, E6437–E6446 (2018).CAS

Wang，J。等人。单细胞RNA测序中的基因表达分布反卷积。程序。国家科学院。科学。美国115，E6437–E6446（2018）。中科院

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Paszke, A. et al. PyTorch: an imperative style, high-performance deep learning library. In Advances in Neural Information Processing Systems 32 (eds Wallach, H. et al.) 8024–8035 (Curran Associates, 2019).Wolf, F. A., Angerer, P. & Theis, F. J. SCANPY: large-scale single-cell gene expression data analysis.

Paszke，A。et al。PyTorch：一个命令式、高性能的深度学习库。神经信息处理系统进展32（eds Wallach，H.等人）8024-8035（Curran Associates，2019）。Wolf，F.A.，Angerer，P。＆Theis，F.J。SCANPY：大规模单细胞基因表达数据分析。

Genome Biol. 19, 15 (2018).Article .

基因组生物学。19,15（2018）。文章。

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Desai, R. V. et al. A DNA repair pathway can regulate transcriptional noise to promote cell fate transitions. Science 373, eabc6506 (2021).Article

Desai，R.V。等人。DNA修复途径可以调节转录噪声以促进细胞命运转变。科学373，eabc6506（2021）。文章

CAS

中科院

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Takei, Y., Yang, Y. & Cai, L. High-resolution spatial multi-omics datasets. Zenodo https://doi.org/10.5281/zenodo.7693825 (2023).Carilli, M., Gorin, G., Choi, Y., Chari, T. & Pachter, L. biVI supporting data. Zenodo https://doi.org/10.5281/zenodo.10530877 (2024).Download referencesAcknowledgementsG.G., T.C.

Takei，Y.，Yang，Y。＆Cai，L。高分辨率空间多组学数据集。泽诺多https://doi.org/10.5281/zenodo.7693825。Carilli，M.，Gorin，G.，Choi，Y.，Chari，T。＆Pachter，L。biVI支持数据。泽诺多https://doi.org/10.5281/zenodo.10530877（2024年）。。G、 ，T.C。

and L.P. were partially funded by National Institutes of Health (NIH) 5UM1HG012077-02 and NIH U19MH114830. M.C. is supported by the National Science Foundation Graduate Research Fellowship Program under grant no. 2139433 and the Amazon AI4Science Fellowship. Y.C. was partially funded by T32 GM007377.

和L.P.部分由美国国立卫生研究院（NIH）5UM1HG012077-02和NIH U19MH114830资助。M、 C.得到了美国国家科学基金会研究生研究奖学金计划（批准号2139433）和亚马逊AI4Science奖学金的支持。Y、 C.部分资金由T32 GM007377提供。

M.C. thanks N. Battich and M. Fang for helpful communications on degradation rate validation. G.G. thanks I. Golding and H. Xu for the inspiration leading to the explanatory model for the zero-inflated negative binomial distribution described in Supplementary Information. The RNA illustrations used in Fig.

M、 C.感谢N.Battich和M.Fang就降解率验证进行的有益沟通。G、 G.感谢I.Golding和H.Xu的灵感，为补充信息中描述的零膨胀负二项分布提供了解释模型。图中使用的RNA插图。

1 and Supplementary Figs. 2 and 3 were derived from the DNA Twemoji by Twitter/X, used under CC BY 4.0 license. We thank the Caltech Bioinformatics Resource Center for GPU resources that helped in performing the analyses.Author informationAuthor notesGennady GorinPresent address: Fauna Bio, Emeryville, CA, USAThese authors contributed equally: Maria Carilli, Gennady Gorin.Authors and AffiliationsDivision of Biology and Biological Engineering, California Institute of Technology, Pasadena, CA, USAMaria Carilli, Tara Chari & Lior PachterDivision of Chemistry and Chemical Engineering, California Institute of Technology, Pasadena, CA, USAGennady GorinDepartment of Biomedical Engineering, University of California, Davis, Davis, CA, USAYongin ChoiGenome Center, University of California, Davis, Davis, CA, USAYongin ChoiDepartment of Computing and Mathematical S.

1和补充图2和3来自Twitter/X的DNA Twemoji，在CC by 4.0许可下使用。我们感谢加州理工学院生物信息学资源中心提供的GPU资源，这些资源有助于进行分析。作者信息作者注Gennady Gorin目前的地址：美国加利福尼亚州埃默里维尔的动物生物研究所这些作者做出了同样的贡献：Maria Carilli，Gennady Gorin。作者和附属机构加利福尼亚理工学院生物与生物工程系，加利福尼亚州帕萨迪纳，USAMaria Carilli，Tara Chari＆Lior PachterDivision of Chemistry and Chemical Engineering，加利福尼亚州帕萨迪纳，USAGennady Gorin加利福尼亚大学戴维斯分校生物医学工程系，加利福尼亚州戴维斯，USAYongin ChoiGenome Center，加利福尼亚大学戴维斯，加利福尼亚州，USAYongin Choi计算与数学系。

PubMed Google ScholarGennady GorinView author publicationsYou can also search for this author in

PubMed Google ScholarGennady GorinView作者出版物您也可以在

PubMed Google ScholarYongin ChoiView author publicationsYou can also search for this author in

PubMed Google ScholarYongin ChoiView作者出版物您也可以在

PubMed Google ScholarTara ChariView author publicationsYou can also search for this author in

PubMed Google ScholarTara ChariView作者出版物您也可以在

PubMed Google ScholarLior PachterView author publicationsYou can also search for this author in

PubMed Google ScholarLior PachterView作者出版物您也可以在

PubMed Google ScholarContributionsG.G. conceptualized the project and provided detailed feedback and project direction. G.G., M.C. and Y.C. implemented the strategy. M.C. ran analyses. T.C. and L.P. provided guidance and suggestions throughout. M.C., G.G., T.C. and L.P. wrote the paper.Corresponding authorCorrespondence to.

PubMed谷歌学术贡献。G、 对项目进行概念化，并提供详细的反馈和项目方向。G、 G.，M.C.和Y.C.实施了该战略。M、 C.运行分析。T、 C.和L.P.全程提供指导和建议。M、 C.，G.G.，T.C.和L.P.写了这篇论文。对应作者对应。

Lior Pachter.Ethics declarations

莱奥·帕奇特。道德宣言

Competing interests

相互竞争的利益

G.G. is an employee at Fauna Bio. The other authors declare no competing interests.

G、 G.是Fanus Bio的员工。其他作者声明没有利益冲突。

Peer review

同行评审

Peer review information

同行评审信息

Nature Methods thanks Lukas Simon, Wing Wong and the other, anonymous, reviewer(s) for their contribution to the peer review of this work. Peer reviewer reports are available. Primary Handling Editor: Lin Tang, in collaboration with the Nature Methods team.

Nature Methods感谢Lukas Simon，Wing Wong和另一位匿名审稿人对这项工作的同行评审做出的贡献。同行评审报告可供查阅。。

Additional informationPublisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.Supplementary informationSupplementary InformationSupplementary Methods and Figs. 1–16.Reporting SummaryPeer Review FileRights and permissionsSpringer Nature or its licensor (e.g.

Additional informationPublisher的注释Springer Nature在已发布的地图和机构隶属关系中的管辖权主张方面保持中立。补充信息补充信息补充方法和图1-16。报告摘要同行评审文件权利和权限原告性质或其许可人（例如。

a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.Reprints and permissionsAbout this articleCite this articleCarilli, M., Gorin, G., Choi, Y.

协会或其他合作伙伴）根据与作者或其他权利持有人的出版协议对本文拥有专有权；本文接受稿件版本的作者自行存档仅受此类出版协议和适用法律的条款管辖。转载和许可本文引用本文Carilli，M.，Gorin，G.，Choi，Y。

et al. Biophysical modeling with variational autoencoders for bimodal, single-cell RNA sequencing data..

等。使用变分自动编码器对双峰单细胞RNA测序数据进行生物物理建模。。

Nat Methods (2024). https://doi.org/10.1038/s41592-024-02365-9Download citationReceived: 02 May 2023Accepted: 27 June 2024Published: 25 July 2024DOI: https://doi.org/10.1038/s41592-024-02365-9Share this articleAnyone you share the following link with will be able to read this content:Get shareable linkSorry, a shareable link is not currently available for this article.Copy to clipboard.

Nat方法（2024）。https://doi.org/10.1038/s41592-024-02365-9Download引文接收日期：2023年5月2日接收日期：2024年6月27日发布日期：2024年7月25日OI：https://doi.org/10.1038/s41592-024-02365-9Share本文与您共享以下链接的任何人都可以阅读此内容：获取可共享链接对不起，本文目前没有可共享的链接。复制到剪贴板。

Provided by the Springer Nature SharedIt content-sharing initiative

由Springer Nature SharedIt内容共享计划提供