Mosaic integration and knowledge transfer of single-cell multimodal data with MIDAS
Open accessAbstract
Integrating single-cell datasets produced by multiple omics technologies is essential for defining cellular heterogeneity. Mosaic integration, in which different datasets share only some of the measured modalities, poses major challenges, particularly regarding modality alignment and batch effect removal. Here, we present a deep probabilistic framework for the mosaic integration and knowledge transfer (MIDAS) of single-cell multimodal data. MIDAS simultaneously achieves dimensionality reduction, imputation and batch correction of mosaic data by using self-supervised modality alignment and information-theoretic latent disentanglement. We demonstrate its superiority to 19 other methods and reliability by evaluating its performance in trimodal and mosaic integration tasks. We also constructed a single-cell trimodal atlas of human peripheral blood mononuclear cells and tailored transfer learning and reciprocal reference mapping schemes to enable flexible and accurate knowledge transfer from the atlas to new data. Applications in mosaic integration, pseudotime analysis and cross-tissue knowledge transfer on bone marrow mosaic datasets demonstrate the versatility and superiority of MIDAS. MIDAS is available at https://github.com/labomics/midas .
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
He et al. introduced MIDAS, a deep-learning method that enabled mosaic data integration of single-cell multimodal data and knowledge transfer into new datasets.
“He et al. introduced MIDAS, a deep-learning method that enabled mosaic data integration of single-cell multimodal data and knowledge transfer into new datasets [121].”
From Challenges in AI-driven Biomedical Multimodal Data Fusion and Analysis (2025) · cites this paper as [121]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
LeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126 · see citing works
Scikit-learn: Machine Learning in Python
Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Müller, A., Nothman, J., Louppe, G., et al. (2012) · arXiv · doi:10.48550/arxiv.1201.0490 · Cited by 71,016 · see citing works
clusterProfiler: an R Package for Comparing Biological Themes Among Gene Clusters
Yu, G., Wang, L.-G., Han, Y., & He, Q.-Y. (2012) · OMICS: A Journal of Integrative Biology · doi:10.1089/omi.2011.0118 · Cited by 36,259 · see citing works
PyTorch: An Imperative Style, High-Performance Deep Learning Library
Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., Antiga, L., et al. (2019) · arXiv · doi:10.48550/arxiv.1912.01703 · Cited by 31,473 · see citing works
Silhouettes: A graphical aid to the interpretation and validation of cluster analysis
Rousseeuw, P. J. (1987) · Journal of Computational and Applied Mathematics · doi:10.1016/0377-0427(87)90125-7 · Cited by 21,392 · see citing works
Auto-Encoding Variational Bayes
Kingma, D. P., & Welling, M. (2013) · arXiv · doi:10.48550/arxiv.1312.6114 · Cited by 20,067 · see citing works
Model-based Analysis of ChIP-Seq (MACS)
Zhang, Y., Liu, T., Meyer, C. A., Eeckhoute, J., Johnson, D. S., Bernstein, B. E., Nusbaum, C., Myers, R. M., Brown, M., Li, W., et al. (2008) · Genome Biology · doi:10.1186/gb-2008-9-9-r137 · Cited by 18,386 · see citing works
Integrated analysis of multimodal single-cell data
Hao, Y., Hao, S., Andersen-Nissen, E., Mauck, W. M., Zheng, S., Butler, A., Lee, M. J., Wilk, A. J., Darby, C., Zagar, M., et al. (2020) · doi:10.1101/2020.10.12.335331 · Cited by 15,508 · cited 3× · see citing works
“Such an atlas can serve as an encyclopedia, allowing researchers the ability to transfer knowledge to their new data and in-house studies 13–15 .”
Comprehensive Integration of Single-Cell Data
Stuart, T., Butler, A., Hoffman, P., Hafemeister, C., Papalexi, E., Mauck, W. M., Hao, Y., Stoeckius, M., Smibert, P., & Satija, R. (2019) · Cell · doi:10.1016/j.cell.2019.05.031 · Cited by 15,453 · see citing works
Gene Expression Omnibus: NCBI gene expression and hybridization array data repository
Edgar, R. (2002) · Nucleic Acids Research · doi:10.1093/nar/30.1.207 · Cited by 13,288 · see citing works
Fast, sensitive and accurate integration of single-cell data with Harmony
Korsunsky, I., Millard, N., Fan, J., Slowikowski, K., Zhang, F., Wei, K., Baglaenko, Y., Brenner, M., Loh, P.-R., & Raychaudhuri, S. (2019) · Nature Methods · doi:10.1038/s41592-019-0619-0 · Cited by 10,488 · cited 1× · see citing works
“Unlike iLISI that highlights the mixing of groups, cLISI values the separation of groups 61 .”
SCANPY: large-scale single-cell gene expression data analysis
Wolf, F. A., Angerer, P., & Theis, F. J. (2018) · Genome Biology · doi:10.1186/s13059-017-1382-0 · Cited by 8,881 · see citing works
UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction
McInnes, L., Healy, J., & Melville, J. (2018) · arXiv · doi:10.48550/arxiv.1802.03426 · Cited by 7,101 · see citing works
Objective Criteria for the Evaluation of Clustering Methods
Rand, W. M. (1971) · Journal of the American Statistical Association · doi:10.1080/01621459.1971.10482356 · Cited by 6,493 · see citing works
Reversed graph embedding resolves complex single-cell trajectories
Qiu, X., Mao, Q., Tang, Y., Wang, L., Chawla, R., Pliner, H. A., & Trapnell, C. (2017) · Nature Methods · doi:10.1038/nmeth.4402 · Cited by 5,070 · see citing works
The Gene Ontology (GO) database and informatics resource
Gene Ontology Consortium (2003) · Nucleic Acids Research · doi:10.1093/nar/gkh036 · Cited by 4,533 · cited 1× · see citing works
“Gene Ontology enrichment analysis 47 indicated that the inaccessible regions are related to T cell activation, cell adhesion and other immune functions.”
IEEE Transactions on Pattern Analysis and Machine Intelligence
(2004) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2004.1307293 · Cited by 3,708 · see citing works
Simultaneous epitope and transcriptome measurement in single cells
Stoeckius, M., Hafemeister, C., Stephenson, W., Houck-Loomis, B., Chattopadhyay, P. K., Swerdlow, H., Satija, R., & Smibert, P. (2017) · Nature Methods · doi:10.1038/nmeth.4380 · Cited by 3,098 · see citing works
An Introduction to Variational Autoencoders
Kingma, D. P., & Welling, M. (2019) · Foundations and Trends® in Machine Learning · doi:10.1561/2200000056 · Cited by 2,609 · see citing works
Current best practices in single-cell RNA-seq analysis: a tutorial
Luecken, M. D., & Theis, F. J. (2019) · Molecular Systems Biology · doi:10.15252/msb.20188746 · Cited by 2,231 · cited 1× · see citing works
“These outputs can be used for downstream analyses, such as clustering, cell typing and trajectory inference 39 .”
Single-cell RNA sequencing technologies and bioinformatics pipelines
Hwang, B., Lee, J. H., & Bang, D. (2018) · Experimental & Molecular Medicine · doi:10.1038/s12276-018-0071-8 · Cited by 1,793 · cited 1× · see citing works
“The batches can derive from different experiments or be generated by the application of different sequencing techniques (for example, single-cell RNA-sequencing (scRNA-seq) 38 , CITE-seq 5 , ASAP-seq 3 and TEA-seq 4 ) and thus can have different technical noise, modalities and features.”
Single-cell chromatin state analysis with Signac
Stuart, T., Srivastava, A., Madad, S., Lareau, C. A., & Satija, R. (2021) · Nature Methods · doi:10.1038/s41592-021-01282-5 · Cited by 1,769 · see citing works
Multi-Omics Factor Analysis—a framework for unsupervised integration of multi-omics data sets
Argelaguet, R., Velten, B., Arnol, D., Dietrich, S., Zenz, T., Marioni, J. C., Buettner, F., Huber, W., & Stegle, O. (2018) · Molecular Systems Biology · doi:10.15252/msb.20178124 · Cited by 1,510 · see citing works
Integrative single-cell analysis
Stuart, T., & Satija, R. (2019) · Nature Reviews Genetics · doi:10.1038/s41576-019-0093-7 · Cited by 1,460 · cited 1× · see citing works
“The growing size of scMulti-omics datasets necessitates the development of new computational tools to integrate massive high-dimensional data generated from different sources, thereby facilitating more comprehensive and reliable downstream analysis for knowledge mining 1,2,12 .”
Benchmarking atlas-level data integration in single-cell genomics
Luecken, M. D., Büttner, M., Chaichoompu, K., Danese, A., Interlandi, M., Mueller, M. F., Strobl, D. C., Zappia, L., Dugas, M., Colomé-Tatché, M., et al. (2022) · Nature Methods · doi:10.1038/s41592-021-01336-8 · Cited by 1,438 · cited 2× · see citing works
“…evaluation of the low-dimensional representations of different strategies performed with the widely used single-cell integration benchmarking (scIB) 43 tool, MIDAS had the highest batch correction, biological conservation and overall scores for the dogma-full and teadog-full datasets (Fig.”
InfluentialMethods and applications for single-cell and spatial multi-omics
Vandereyken, K., Sifrim, A., Thienpont, B., & Voet, T. (2023) · Nature Reviews Genetics · doi:10.1038/s41576-023-00580-2 · Cited by 1,244 · cited 3× · see citing works
“Recently emerged single-cell multimodal omics (scMulti-omics) sequencing technologies enable the simultaneous detection of multiple modalities, such as RNA expression, protein abundance and chromatin accessibility, in the same cell 1,2 .”
Single-Cell Multi-omic Integration Compares and Contrasts Features of Brain Cell Identity
Welch, J. D., Kozareva, V., Ferreira, A., Vanderburg, C., Martin, C., & Macosko, E. Z. (2019) · Cell · doi:10.1016/j.cell.2019.05.006 · Cited by 1,193 · see citing works
Chromatin Potential Identified by Shared Single-Cell Profiling of RNA and Chromatin
Ma, S., Zhang, B., LaFave, L. M., Earl, A. S., Chiang, Z., Hu, Y., Ding, J., Brack, A., Kartha, V. K., Tay, T., et al. (2020) · Cell · doi:10.1016/j.cell.2020.09.056 · Cited by 1,146 · see citing works
MOFA+: a statistical framework for comprehensive integration of multi-modal single-cell data
Argelaguet, R., Arnol, D., Bredikhin, D., Deloro, Y., Velten, B., Marioni, J. C., & Stegle, O. (2020) · Genome Biology · doi:10.1186/s13059-020-02015-1 · Cited by 1,091 · see citing works
Best practices for single-cell analysis across modalities
Heumos, L., Schaar, A. C., Lance, C., Litinetskaya, A., Drost, F., Zappia, L., Lücken, M. D., Strobl, D. C., Henao, J., Curion, F., et al. (2023) · Nature Reviews Genetics · doi:10.1038/s41576-023-00586-w · Cited by 1,051 · cited 1× · see citing works
“Therefore, flexible and general multimodal mosaic integration remains challenging 30–32 .”
The technological landscape and applications of single-cell multi-omics
Baysoy, A., Bai, Z., Satija, R., & Fan, R. (2023) · Nature Reviews Molecular Cell Biology · doi:10.1038/s41580-023-00615-w · Cited by 1,037 · cited 3× · see citing works
“Recently emerged single-cell multimodal omics (scMulti-omics) sequencing technologies enable the simultaneous detection of multiple modalities, such as RNA expression, protein abundance and chromatin accessibility, in the same cell 1,2 .”
BBKNN: fast batch alignment of single cell transcriptomes
Polański, K., Young, M. D., Miao, Z., Meyer, K. B., Teichmann, S. A., & Park, J.-E. (2020) · Bioinformatics · doi:10.1093/bioinformatics/btz625 · Cited by 932 · see citing works
High-throughput sequencing of the transcriptome and chromatin accessibility in the same cell
Chen, S., Lake, B. B., & Zhang, K. (2019) · Nature Biotechnology · doi:10.1038/s41587-019-0290-0 · Cited by 810 · cited 1× · see citing works
“These technologies, including the trimodal DOGMA-seq 3 and TEA-seq 4 and bimodal CITE-seq 5 and ASAP-seq 3 , among many others 6–11 , reveal not only cellular heterogeneity at multiple molecular layers, enabling more refined identification of cell characteristics, but also connections across omes,…”
The burgeoning family of unconventional T cells
Godfrey, D. I., Uldrich, A. P., McCluskey, J., Rossjohn, J., & Moody, D. B. (2015) · Nature Immunology · doi:10.1038/ni.3298 · Cited by 799 · cited 1× · see citing works
“Another T cell cluster, containing mucosa-associated invariant T cells and γδ T cells, was distinct from conventional T cells and was labeled unconventional T cells 45 .”
Bond-Taylor, S., Leach, A., Long, Y., & Willcocks, C. G. (2021) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2021.3116668 · Cited by 735 · cited 1× · see citing works
“The MIDAS model MIDAS is a deep generative model 35,36 that represents the joint distribution of incomplete single-cell multimodal data with assay for transposase-accessible chromatin (ATAC), RNA and antibody-derived tags (ADT) measurements.”
Three types of incremental learning
van de Ven, G. M., Tuytelaars, T., & Tolias, A. S. (2022) · Nature Machine Intelligence · doi:10.1038/s42256-022-00568-3 · Cited by 665 · cited 1× · see citing works
“Thus, using incremental learning 56 is an inevitable trend to achieve continuous mosaic integration without model retraining.”
GRNBoost2 and Arboreto: efficient and scalable inference of gene regulatory networks
Moerman, T., Aibar Santos, S., Bravo González-Blas, C., Simm, J., Moreau, Y., Aerts, J., & Aerts, S. (2019) · Bioinformatics · doi:10.1093/bioinformatics/bty916 · Cited by 621 · see citing works
Yang, F., Wang, W., Wang, F., Fang, Y., Tang, D., Huang, J., Lu, H., & Yao, J. (2021) · doi:10.1101/2021.12.05.471261 · Cited by 617 · cited 2× · see citing works
“…the reference data to infer the biological states for the query data 50,51 ) and (2) mapping the reference data onto the query space (that is, applying the model fine-tuned on the query data (see ‘Model transfer via transfer learning’) to infer the biological states for the reference data 14,52 ).”
Multi-omics single-cell data integration and regulatory inference with graph-linked embedding
Cao, Z.-J., & Gao, G. (2022) · Nature Biotechnology · doi:10.1038/s41587-022-01284-4 · Cited by 616 · see citing works
Self-supervised learning in medicine and healthcare
Krishnan, R., Rajpurkar, P., & Topol, E. J. (2022) · Nature Biomedical Engineering · doi:10.1038/s41551-022-00914-1 · Cited by 605 · cited 1× · see citing works
“By using self-supervised learning 33 and information-theoretic approaches 34 , MIDAS simultaneously achieves modality alignment, imputation and batch correction for single-cell tri-modal mosaic data.”
Mapping single-cell data to reference atlases by transfer learning
Lotfollahi, M., Naghipourfar, M., Luecken, M. D., Khajavi, M., Büttner, M., Wagenstetter, M., Avsec, Ž., Gayoso, A., Yosef, N., Interlandi, M., et al. (2022) · Nature Biotechnology · doi:10.1038/s41587-021-01001-7 · Cited by 602 · cited 2× · see citing works
“…the reference data to infer the biological states for the query data 50,51 ) and (2) mapping the reference data onto the query space (that is, applying the model fine-tuned on the query data (see ‘Model transfer via transfer learning’) to infer the biological states for the reference data 14,52 ).”
Joint probabilistic modeling of single-cell multi-omic data with totalVI
Gayoso, A., Steier, Z., Lopez, R., Regier, J., Nazor, K. L., Streets, A., & Yosef, N. (2021) · Nature Methods · doi:10.1038/s41592-020-01050-x · Cited by 592 · cited 1× · see citing works
“16–18).”
Mimitou, E. P., Lareau, C. A., Chen, K. Y., Zorzetto-Fernandes, A. L., Hao, Y., Takeshima, Y., Luo, W., Huang, T.-S., Yeung, B. Z., Papalexi, E., et al. (2021) · Nature Biotechnology · doi:10.1038/s41587-021-00927-2 · Cited by 529 · see citing works
A test metric for assessing single-cell RNA-seq batch correction
Büttner, M., Miao, Z., Wolf, F. A., Teichmann, S. A., & Theis, F. J. (2019) · Nature Methods · doi:10.1038/s41592-018-0254-1 · Cited by 511 · see citing works
Computational principles and challenges in single-cell data integration
Argelaguet, R., Cuomo, A. S. E., Stegle, O., & Marioni, J. C. (2021) · Nature Biotechnology · doi:10.1038/s41587-021-00895-7 · Cited by 472 · see citing works
MultiVI: deep generative model for the integration of multi-modal data
Ashuach, T., Gabitto, M. I., Jordan, M. I., & Yosef, N. (2021) · doi:10.1101/2021.08.20.457057 · Cited by 385 · cited 1× · see citing works
“22 and 23).”
Differentiation of human dendritic cells from monocytes in vitro
Chapuis, F., Rosenzwajg, M., Yagello, M., Ekman, M., Biberfeld, P., & Gluckman, J. C. (1997) · European Journal of Immunology · doi:10.1002/eji.1830270213 · Cited by 338 · cited 1× · see citing works
“The separation of monocytes and DCs was difficult in some mosaic experiments, mainly because the latter originate from the former 49 and likely also because the monocyte population in the dogma dataset was small.”
Joint profiling of histone modifications and transcriptome in single cells from mouse brain
Zhu, C., Zhang, Y., Li, Y. E., Lucero, J., Behrens, M. M., & Ren, B. (2021) · Nature Methods · doi:10.1038/s41592-021-01060-3 · Cited by 301 · cited 1× · see citing works
“9).”
CD4+/CD8+ double-positive T cells: more than just a developmental stage?
Overgaard, N. H., Jung, J., Steptoe, R. J., & Wells, J. W. (2014) · Journal of Leukocyte Biology · doi:10.1189/jlb.1ru0814-382 · Cited by 298 · cited 1× · see citing works
“This phenomenon was also reported in previous studies 44 .”
Integrative Methods and Practical Challenges for Single-Cell Multi-omics
Ma, A., McDermaid, A., Xu, J., Chang, Y., & Ma, Q. (2020) · Trends in biotechnology · doi:10.1016/j.tibtech.2020.02.013 · Cited by 272 · cited 1× · see citing works
“Therefore, flexible and general multimodal mosaic integration remains challenging 30–32 .”
Swanson, E., Lord, C., Reading, J., Heubeck, A. T., Genge, P. C., Thomson, Z., Weiss, M. D., Li, X.-J., Savage, A. K., Green, R. R., et al. (2021) · eLife · doi:10.7554/elife.63632 · Cited by 267 · see citing works
Joint profiling of DNA methylation and chromatin architecture in single cells
Li, G., Liu, Y., Zhang, Y., Kubo, N., Yu, M., Fang, R., Kellis, M., & Ren, B. (2019) · Nature Methods · doi:10.1038/s41592-019-0502-z · Cited by 218 · see citing works
Cobolt: integrative analysis of multimodal single-cell sequencing data
Gong, B., Zhou, Y., & Purdom, E. (2021) · Genome Biology · doi:10.1186/s13059-021-02556-z · Cited by 168 · see citing works
BABEL enables cross-modality translation between multiomic profiles at single-cell resolution
Wu, K., Yost, K. E., Chang, H. Y., & Zou, J. (2021) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2023070118 · Cited by 164 · cited 2× · see citing works
“It has been previously used to evaluate the quality of ATAC predictions 65 .”
Clustering of single-cell multi-omics data with a multimodal deep learning method
Lin, X., Tian, T., Wei, Z., & Hakonarson, H. (2022) · Nature Communications · doi:10.1038/s41467-022-35031-9 · Cited by 135 · see citing works
A unified computational framework for single-cell data integration with optimal transport
Cao, K., Gong, Q., Hong, Y., & Wan, L. (2022) · Nature Communications · doi:10.1038/s41467-022-35094-8 · Cited by 105 · cited 2× · see citing works
“22 and 23).”
Lakkis, J., Schroeder, A., Su, K., Lee, M. Y. Y., Bashore, A. C., Reilly, M. P., & Li, M. (2022) · Nature Machine Intelligence · doi:10.1038/s42256-022-00545-w · Cited by 105 · see citing works
Characterizing cellular heterogeneity in chromatin state with scCUT&Tag-pro
Zhang, B., Srivastava, A., Mimitou, E., Stuart, T., Raimondi, I., Hao, Y., Smibert, P., & Satija, R. (2022) · Nature Biotechnology · doi:10.1038/s41587-022-01250-0 · Cited by 104 · cited 1× · see citing works
“These technologies, including the trimodal DOGMA-seq 3 and TEA-seq 4 and bimodal CITE-seq 5 and ASAP-seq 3 , among many others 6–11 , reveal not only cellular heterogeneity at multiple molecular layers, enabling more refined identification of cell characteristics, but also connections across omes,…”
Stabilized mosaic single-cell data integration using unshared features
Ghazanfar, S., Guibentif, C., & Marioni, J. C. (2023) · Nature Biotechnology · doi:10.1038/s41587-023-01766-z · Cited by 101 · see citing works
Xiong, L., Tian, K., Li, Y., Ning, W., Gao, X., & Zhang, Q. C. (2022) · Nature Communications · doi:10.1038/s41467-022-33758-z · Cited by 99 · cited 2× · see citing works
“…query data onto the reference space (that is, applying the model pretrained on the reference data to infer the biological states for the query data 50,51 ) and (2) mapping the reference data onto the query space (that is, applying the model fine-tuned on the query data (see ‘Model transfer via…”
Kriebel, A. R., & Welch, J. D. (2022) · Nature Communications · doi:10.1038/s41467-022-28431-4 · Cited by 85 · see citing works
Enhancing scientific discoveries in molecular biology with deep generative models
Lopez, R., Gayoso, A., & Yosef, N. (2020) · Molecular Systems Biology · doi:10.15252/msb.20199198 · Cited by 82 · cited 1× · see citing works
“The MIDAS model MIDAS is a deep generative model 35,36 that represents the joint distribution of incomplete single-cell multimodal data with assay for transposase-accessible chromatin (ATAC), RNA and antibody-derived tags (ADT) measurements.”
Choi, J. H., Yarishkin, O. V., Kim, E., Bae, Y., Kim, A., Kim, S. C., Ryoo, K., Cho, C., Hwang, E. M., & Park, J. (2018) · Experimental & Molecular Medicine · doi:10.1038/s12276-018-0172-4 · Cited by 75 · see citing works
Single-cell profiling of proteins and chromatin accessibility using PHAGE-ATAC
Fiskin, E., Lareau, C. A., Ludwig, L. S., Eraslan, G., Liu, F., Ring, A. M., Xavier, R. J., & Regev, A. (2022) · Nature Biotechnology · doi:10.1038/s41587-021-01065-5 · Cited by 68 · see citing works
Contrastive learning enables rapid mapping to multimodal single-cell atlas of multimillion scale
Yang, M., Yang, Y., Xie, C., Ni, M., Liu, J., Yang, H., Mu, F., & Wang, J. (2022) · Nature Machine Intelligence · doi:10.1038/s42256-022-00518-z · Cited by 64 · cited 2× · see citing works
“…data onto the reference space (that is, applying the model pretrained on the reference data to infer the biological states for the query data 50,51 ) and (2) mapping the reference data onto the query space (that is, applying the model fine-tuned on the query data (see ‘Model transfer via…”
Self-citationIntegration and Querying of Multimodal Single-Cell Data with PoE-VAE
Litinetskaya, A., Shulman, M., Curion, F., Szałata, A., Omidi, A., Lotfollahi, M., & Theis, F. J. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-90252-9_36 · Cited by 64 · see citing works
Unsupervised manifold alignment for single-cell multi-omics data
Singh, R., Demetçi, P., Bonora, G., Ramani, V., Lee, C., Fang, H., Duan, Z., Deng, X., Shendure, J., Distèche, C. M., et al. (2020) · ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics (ACM-BCB) · doi:10.1145/3388440.3412410 · Cited by 64 · see citing works
scMoMaT jointly performs single cell mosaic integration and multi-modal bio-marker detection
Zhang, Z., Sun, H., Mariappan, R., Chen, X. X., Chen, X., Jain, M. S., Efremova, M., Teichmann, S. A., Rajan, V., & Zhang, X. (2023) · Nature Communications · doi:10.1038/s41467-023-36066-2 · Cited by 60 · see citing works
Du, J., Cai, Z., & Roeder, K. (2022) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2214414119 · Cited by 48 · see citing works
Effect of imputation on gene network reconstruction from single-cell RNA-seq data
Ly, L.-H., & Vingron, M. (2021) · Patterns · doi:10.1016/j.patter.2021.100414 · Cited by 22 · cited 1× · see citing works
“https://doi.org/10.1038/s41587-023-02040-y deteriorate the accuracy of gene regulatory inference in many cases 48 , we evaluated the consistency of downstream analysis results obtained with the performance of different mosaic integration tasks with the dogma datasets.”
InfluentialInformation-Theoretic Methods in Deep Neural Networks: Recent Advances and Emerging Opportunities
Yu, S., Giraldo, L. S., & Príncipe, J. C. (2021) · doi:10.24963/ijcai.2021/633 · Cited by 20 · cited 2× · see citing works
“To better disentangle the biological state c and the technical noise u , we adopt an information-theoretic approach, the information bottleneck (IB) 34 , to control information flow during inference.”
Defining the Pathways of Early Adult Hematopoiesis
Murre, C. (2007) · Cell stem cell · doi:10.1016/j.stem.2007.09.008 · Cited by 18 · cited 1× · see citing works
“This differentiation trajectory is consistent with the well-known developmental pathways of myeloid cells in bone marrow 53 , demonstrating that MIDAS’s 32-dimensional biological state latent variables can be applied to trajectory inference of cell differentiation.”
CD3-Positive B Cells: A Storage-Dependent Phenomenon
Nagel, A. K., Möbs, C., Raifer, H., Wiendl, H., Hertl, M., & Eming, R. (2014) · PLoS ONE · doi:10.1371/journal.pone.0110138 · Cited by 17 · cited 1× · see citing works
“However, it should be noted that certain technical issues of single-cell sequencing may also lead to the emergence of these cells 46 .”
Flagged first, then by citations
1 of the 74 references couldn’t be matched to a known paper.
Research works printed but not linked: 3
- [29]Lotfollahi, M., Litinetskaya, A. & Theis, F. J. Multigrate: single-cell multi-omic data integration. Preprint at bioRxiv10.1101/2022.03.16.484643 (2022).
- [57]Wu, M. & Goodman, N. Multimodal generative models for scalable weakly-supervised learning. In Advances in Neural Information Processing Systems (eds Bengio, S. et al.) 5575–5585 (Curran Associates, 2018).
- [75]Loshchilov, I. & Hutter, F. Decoupled weight decay regularization. In International Conference on Learning Representations https://openreview.net/forum?id=Bkg6RiCqY7 (2019).
Cited by
Sorted by citations
Baião, A. R., Cai, Z., Poulos, R. C., Robinson, P. J., Reddel, R. R., Zhong, Q., Vinga, S., & Gonçalves, E. (2025) · Briefings in Bioinformatics · doi:10.1093/bib/bbaf355 · Cited by 249 · see citing works
“MIDAS [51] is a MVAE employing the PoE approach for mosaic integration of single-cell data.”
InfluentialFoundation models in bioinformatics
Guo, F., Guan, R., Li, Y., Liu, Q., Wang, X., Yang, C., & Wang, J. (2025) · National Science Review · doi:10.1093/nsr/nwaf028 · Cited by 121 · see citing works
“MIDAS [90 ] uses a modular encoder network and a decoder network to integrate and transfer multimodal data from single cells.”
Self-citationNetwork-based multi-omics integrative analysis methods in drug discovery: a systematic review
Jiang, W., Ye, W., Tan, X., & Bao, Y. (2025) · BioData Mining · doi:10.1186/s13040-025-00442-z · Cited by 107 · see citing works
“Another promising trend is the adoption of self-supervised learning and transfer learning [130, 131].”
Challenges in AI-driven Biomedical Multimodal Data Fusion and Analysis
Liu, J., Cen, X., Yi, C., Wang, F.-A., Ding, J., Cheng, J., Wu, Q., Gai, B., Zhou, Y., He, R., et al. (2025) · Genomics, Proteomics & Bioinformatics · doi:10.1093/gpbjnl/qzaf011 · Cited by 75 · see citing works
“He et al. introduced MIDAS, a deep-learning method that enabled mosaic data integration of single-cell multimodal data and knowledge transfer into new datasets [121].”
New horizons at the interface of artificial intelligence and translational cancer research
Yates, J., & Allen, E. M. V. (2025) · Cancer Cell · doi:10.1016/j.ccell.2025.03.018 · Cited by 55 · see citing works
TMO-Net: an explainable pretrained multi-omics model for multi-task learning in oncology
Wang, F.-A., Zhuang, Z., Gao, F., He, R., Zhang, S., Wang, L., Liu, J., & Li, Y. (2024) · Genome Biology · doi:10.1186/s13059-024-03293-9 · Cited by 51 · see citing works
Chang, L.-C., Liu, J., Zhu, J.-L., Guo, S., Wang, Y., Zhou, Z., & Wei, X. (2025) · Cancer Biology and Medicine · doi:10.20892/j.issn.2095-3941.2024.0376 · Cited by 72 · see citing works
“Mosaic integration and knowledge transfer (MIDAS), a crucial technology for integrating genomics, spatial transcriptomics, and other multimodal genomics data, uses a deep probabilistic framework for MIDAS to achieve flexible and accurate integration of multi-omics data 38 .”
Benchmarking single-cell multi-modal data integrations
Fu, S., Wang, S.-G., Si, D., Li, G., Gao, Y., & Liu, Q. (2025) · Nature Methods · doi:10.1038/s41592-025-02737-9 · Cited by 46 · see citing works
“For this condition, we adapted AUPR for imputation accuracy evaluation instead of the ATAC AUROC metric applied in another paper studying MIDAS 19 , which is less biased for unbalanced labels.”
Synthetic augmentation of cancer cell line multi-omic datasets using unsupervised deep learning
Cai, Z., Apolinário, S., Baião, A. R., Pacini, C., Sousa, M. D., Vinga, S., Reddel, R. R., Robinson, P. J., Garnett, M. J., Zhong, Q., et al. (2024) · Nature Communications · doi:10.1038/s41467-024-54771-4 · Cited by 44 · see citing works
Modal-nexus auto-encoder for multi-modality cellular data integration and imputation
Tang, Z., Chen, G., Chen, S., Yao, J., You, L., & Chen, C. Y. (2024) · Nature Communications · doi:10.1038/s41467-024-53355-6 · Cited by 37 · see citing works
Levesque, S., Cosentino, A., Verma, A., Genovese, P., & Bauer, D. E. (2024) · Nature Biotechnology · doi:10.1038/s41587-024-02266-4 · Cited by 34 · see citing works
Machine learning integrative approaches to advance computational immunology
Curion, F., & Theis, F. J. (2024) · Genome Medicine · doi:10.1186/s13073-024-01350-3 · Cited by 35 · see citing works
“MIDAS [103], a recent deep generative framework for the integration of mosaic data, was demonstrated to disentangle two rare unconventional T-cell populations [104, 105] and successfully predict the differentiation trajectory of myeloid cells in the bone marrow [106] from the inferred embedding.…”
BackgroundLoers, J. U., & Vermeirssen, V. (2024) · Briefings in Bioinformatics · doi:10.1093/bib/bbae382 · Cited by 33 · see citing works
“With increasingly available paired multi-omics data, mosaic integration, where only a subset of cells and/or features can serve as anchors, becomes feasible [86, 87].”
BackgroundWang, G., Zhao, J., Lin, Y., Liu, T., Zhao, Y., & Zhao, H. (2025) · Nature Communications · doi:10.1038/s41467-025-60333-z · Cited by 29 · see citing works
Self-citationLi, L., Li, X., & Wu, H. (2025) · Briefings in Bioinformatics · doi:10.1093/bib/bbaf289 · Cited by 23 · see citing works
“The MIDAS [84] algorithm integrates single-cell multi-omics data through generative artificial intelligence, successfully solving the problems of batch effects and mode loss.”
Mosaic integration of spatial multi-omics with SpaMosaic
Yan, X., Ang, K. S., Ang, K. S., van Olst, L., Edwards, A., Watson, T., Zheng, R., Zhang, D., Fan, R., Li, M., et al. (2026) · Nature Genetics · doi:10.1038/s41588-026-02573-3 · Cited by 23 · see citing works
Moinfar, A. A., & Theis, F. J. (2024) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2024.11.06.622266 · Cited by 20 · see citing works
Zhang, J., Li, M., Meng, D., Xu, S., Teame, T., Yao, Y., Yang, Y., Zhang, Z., Ran, C., Jijakli, M. H., et al. (2025) · Journal of Nutrition · doi:10.1016/j.tjnut.2025.08.019 · Cited by 10 · see citing works
Reliable imputation of spatial transcriptomes with uncertainty estimation and spatial regularization
Qiao, C., & Huang, Y. (2024) · Patterns · doi:10.1016/j.patter.2024.101021 · Cited by 9 · see citing works
A hitchhiker's guide to single‐cell epigenomics: Methods and applications for cancer research
Moreno‐Gonzalez, M., Sierra, I., & Kind, J. (2024) · International Journal of Cancer · doi:10.1002/ijc.35307 · Cited by 10 · see citing works
“Alternatively, in the case of multi-omic data, the joint analysis of multiple molecular layers may allow for imputation or translation between modalities, 91 or offer insights impossible to appreciate when studying exclusively one sparse epigenomic profile.”
Advances in high-throughput drug screening based on pharmacotranscriptomics
Qiao, L., Huo, X., Huang, W., Wang, Z., Ren, Y., Liu, Y., Li, Q., & Zhang, Y. (2025) · Journal of Advanced Research · doi:10.1016/j.jare.2025.09.006 · Cited by 10 · see citing works
“…transcriptomics, proteomics, and metabolomics, would also promote the novel data analysis method, which could draw on the data integrated analysis of single-cell multi-omics analysis with the mosaic integration of paired pharmaco-omics analysis based on variational autoencoder architecture [149].”
Wei, Y., Hong, F., Xie, S., Luo, X., Li, X., Dao, F., Deng, K., Lin, H., & Lv, H. (2025) · International Journal of Molecular Sciences · doi:10.3390/ijms262211005 · Cited by 8 · see citing works
“Batch effects represent an inevitable source of technical noise in single-cell omics data analysis, primarily arising from non-biological factors such as variations in experimental conditions, sample processing times, differences in sequencing platforms, or changes in operators [52–55].”
A joint analysis of single cell transcriptomics and proteomics using transformer
Chen, Y., Fan, X., Shi, C., Shi, Z., & Wang, C. (2025) · npj Systems Biology and Applications · doi:10.1038/s41540-024-00484-9 · Cited by 7 · see citing works
“Consequently, many related studies use them as benchmarks to evaluate model performance 23,30 – 32 , as does this paper.”
Self-citationDeep learning methods and applications in single-cell multimodal data integration
Nunes, F. V. M., Behrens, L. M. P., Weimer, R. D., Gonçalves, G. F., Fernandes, G. D. S., & Dorn, M. (2025) · Molecular Omics · doi:10.1039/d5mo00062a · Cited by 7 · see citing works
Biswas, S., Nandy, A., & Naskar, A. K. (2025) · IEEE Transactions on Emerging Topics in Computational Intelligence · doi:10.1109/tetci.2025.3616054 · Cited by 7 · see citing works
“Depth information is extracted using the Intel DPT-Large Trans-former [27], which predicts per-pixel depth values from RGB inputs to construct structural representations of scene geometry.”
Benchmarking single-cell cross-omics imputation methods for surface protein expression
Li, C., Hong, Y.-J., Li, B., & Zhang, X.-F. (2025) · Genome biology · doi:10.1186/s13059-025-03514-9 · Cited by 5 · see citing works
“Therefore, there is an urgent need to enhance these methods to effectively handle large datasets [35].”
NeMO Analytics: a compendium of transcriptomic data for the exploration of neocortical development
Sonthalia, S., Herb, B. R., Adkins, R. S., Orvis, J., Liu, J., Liao, X., Yu, Q., Mato-Blanco, X., Casella, A. M., Liu, J., et al. (2026) · Nature Neuroscience · doi:10.1038/s41593-026-02204-4 · Cited by 7 · see citing works
Zhang, Y., Ming, W., Yu, B., Wang, L., Lu, K., Xu, L., Ni, Y., Deng, R., & Chen, D. (2025) · Cell Genomics · doi:10.1016/j.xgen.2025.101105 · Cited by 5 · see citing works
“22 For instance, markers such as CD28 and CD40LG, which indicated T cells in RNA data, were absent in protein data.”
Decoding disease and therapy through multiomics integration and systems analysis
Mathew, M. J., Mathew, J., Chacko, R. M., Bayry, J., & Zagury, J. (2026) · Briefings in Bioinformatics · doi:10.1093/bib/bbag311 · Cited by 5 · see citing works
“DeepBID and MIDAS are examples of such integrated methods that uses a deep learning framework for simultaneous denoising, batch handling, and dimensionality reduction of single-cell RNA-seq data [ 80, 81].”
Li, D., Liao, K., Yan, B., Huang, J., Zhang, J., Chen, Y., Zhu, J., Zhi, S., & Chen, P. (2025) · Frontiers in Oncology · doi:10.3389/fonc.2025.1622600 · Cited by 4 · see citing works
“In parallel, generative approaches such as MIDAS (24) employ variational autoencoders (VAEs) to impute missing omics modalities in single-cell data, demonstrating the feasibility of cross-modality reconstruction.”
Self-citationIntegrating single-cell multi-omics data through self-supervised clustering
Zeng, Y., Chen, J., Pan, Z., Yu, W., & Yang, Y. (2024) · Applied Soft Computing · doi:10.1016/j.asoc.2024.112541 · Cited by 4 · see citing works
Machine learning predictions surpass individual mRNAs as a proxy of single-cell protein expression
Fisher, J., Wood, O., Bullers, S. J., Murray, L., Li, L., & Jackson, M. A. (2026) · Genome biology · doi:10.1186/s13059-026-04083-1 · Cited by 4 · see citing works
Li, S., & Zou, J. (2026) · Computational Biology and Chemistry · doi:10.1016/j.compbiolchem.2026.108951 · Cited by 4 · see citing works
Interpretable modality-aware mapping of gene regulation in single-cell multiomics with scMAGCA
Wang, Y., Zhou, Liu, W., Zhang, P., Cheng, Y., Su, Y., Wang, F., Wong, K., & Li, X. (2026) · Nature Communications · doi:10.1038/s41467-026-73055-7 · Cited by 3 · see citing works
Multi-Omics Meets Premalignancy: Paving the Way for Early Prevention of Cancer
Zhang, F., Zhou, Z., Zhang, P., & Li, S. (2025) · Research · doi:10.34133/research.0930 · Cited by 4 · see citing works
Ding, Y., Jiang, Y., Wang, J., Tan, D., Su, Y., & Zheng, C. (2026) · Briefings in Bioinformatics · doi:10.1093/bib/bbag005 · Cited by 3 · see citing works
“The integration of single-cell multi-omics data can facilitate the study of complex biological information [15, 16], and researchers have been developing single-cell multi-omics integration methods using machine learning and bioinformatics techniques [17, 18].”
Self-citationZhang, B., Lan, X., Tan, S., Xie, Z., Zhu, L., Gong, X., Dai, X., Fang, X., & Xu, W. (2025) · TrAC Trends in Analytical Chemistry · doi:10.1016/j.trac.2025.118170 · Cited by 3 · see citing works
Joas, M. J., Jurenaite, N., Praščević, D., Scherf, N., & Ewald, J. (2025) · Nature Computational Science · doi:10.1038/s43588-025-00916-4 · Cited by 3 · see citing works
“For future versions of AUTOENCODIX, current architectures will serve as building blocks of new developments such as VAEs for mosaic integration 25 , uncoupled VAE with regularized inverse optimal transport 26 or masked VAEs for imputation.”
Biologically Informed Variational Inference Enables Interpretable Cell Phenotyping and DiscoveryPreprint
Arnoldt, L., zu Belzen, J. U., Herrmann, L., Nguyen, K. P., Ishaque, N., Theis, F. J., Wild, B., & Eils, R. (2025) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2025.06.10.657924 · Cited by 4 · see citing works
“We did not conduct hyperparameter optimization for MIDAS, as its training time exceeded that of the other benchmarked methods by up to an order of magnitude and was thus impractical, and likewise skipped optimization for WNN, as it lacks commonly tuned hyperparameters in practice.”
Single-cell mosaic integration and cell state transfer with auto-scaling self-attention mechanism
Rong, Z., Song, J., Yu, Y., Mi, L., Qiu, M., Song, Y., & Hou, Y. (2024) · Briefings in Bioinformatics · doi:10.1093/bib/bbae540 · Cited by 2 · see citing works
“A series of new analysis methods based on deep neural networks have demonstrated their tremendous potential in the biomedical field [15–19].”
BackgroundMethodArtificial intelligence in radiobiology: Bridging mechanisms and data analysis
Wang, Y., Li, W., Xu, N., Xie, D., Huang, X., & Zhou, P. (2025) · Radiation Medicine and Protection · doi:10.1016/j.radmp.2025.12.005 · Cited by 2 · see citing works
Yu, Y., Long, M., Song, J., Cao, K., Luo, M., Liu, W. T., Rong, Z., & Hou, Y. (2026) · Briefings in Bioinformatics · doi:10.1093/bib/bbag218 · Cited by 2 · see citing works
Fu, Z., Li, L., Perry, C. J., Ghali, F., Tan, W. S., Kim, I. Y., & Mu, P. (2026) · Gene · doi:10.1016/j.gene.2026.150293 · Cited by 2 · see citing works
Wu, W., Li, G., Wang, K., Xu, H., Xiao, H., Hu, C., Liu, S., Tang, C., Liu, F., Zou, Z., et al. (2026) · Nature Computational Science · doi:10.1038/s43588-026-01026-5 · Cited by 2 · see citing works
MRLF-DDI: A Multi-View Representation Learning Framework for Drug-Drug Interaction Event Prediction
Zhong, J., Zhao, H., Liang, X., Zhao, Q., & Wang, J. (2025) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2025.3592643 · Cited by 2 · see citing works
“Amulti-sourcestrategyoffersapromisingsolu-tiontomitigatetheriskoferroneousknowledgetransfer[49], [50], [51].”
Self-citationChung, H. M., & Huang, Y. (2025) · Genome biology · doi:10.1186/s13059-025-03803-3 · Cited by 1 · see citing works
“When the prior in the latent space is Gaussian, this model is called a deep latent Gaussian model or DLGM. Demonstrated by previous studies [27–30] on VAE in solving other biological problems, this latent space can effectively identify covariances in the distribution of input data that are unclear…”
Jiang, G., Song, K., Fonseca, G. J., Wagner, D. E., Clark, I. C., Wang, H., & Ding, J. (2025) · Nature Communications · doi:10.1038/s41467-025-66644-5 · Cited by 1 · see citing works
“A signi fi cant challenge in the fi eld is mosaic integration 70,71 , where separate dual-omics datasets are integrated into comprehensive “ tri-omics ” or higher-order multimodal representations that provide more complete cellular characterization 72,73 . scGALA addresses this challenge by…”
Leveraging AI for cell biology discovery
Simizo, A., de Morais, M., Vesco, M. F. [., & Nakaya, H. I. (2026) · Biochemical Society Transactions · doi:10.1042/bst20253023 · Cited by 1 · see citing works
“MIDAS [39], a deep probabilistic framework, achieves simultaneous dimensionality reduction, imputation, and batch correction of mosaic data through self-supervised modality alignment.”
scII: Dual-Threshold Adaptive Integration of Single-Cell Multiomics Data Driven by Imputation
Zhang, Y., Li, Y., Jin, Z., Tian, Y., & Su, C. (2026) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.5c02396 · Cited by 1 · see citing works
Dissecting spatial patterning and signaling with directional diffusion in spatial multi-omics
Wang, H., Yuan, Z., Su, Y., Zheng, C., & Sun, X. (2026) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2517283123 · Cited by 2 · see citing works
“Although various single - cell multi - omics integration methods [e.g., Seurat WNN (11), MultiVI (12), totalVI (13), scMM (14), StabMap (15), scAI (16), MIDAS (17), and scMoMat (18)] have been developed, they do not consider the spatial information of cells, which is inherently lost in single - cell sequencing data.”
Zheng, X., Huang, X., Zhou, X., Meng, D., Qiao, Z., Yuan, Z., & Cheng, L. (2026) · Advanced Science · doi:10.1002/advs.75478 · Cited by 1 · see citing works
“Mosaic integration entails integrating partial omics modalities, which are incomplete due to budget constraints or technical perturbations [ 28–30 ].”
Spatial multi-omics imputation and embedding with SpaMIE
Liu, W., Xiang, D.-W., Jiang, X., Bai, Y.-H., Li, S., Li, W., Lv, S.-X., Li, Q., Jiang, J.-K., & Liu, J. (2026) · Cell Reports Methods · doi:10.1016/j.crmeth.2026.101456
“18 Nevertheless, these methods are tailored to dissociated single-cell data and do not account for the spatial structure that is intrinsic to spatial omics datasets.”
scMonica: Single-cell Mosaic Omics Nonlinear Integration and Clustering Analysis
Li, X., Zhang, R., Aslam, S., Li, H., Chen, Y., Zhang, Z., Huang, R. S., & Wu, H. (2024) · IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm62325.2024.10822866 · Cited by 1 · see citing works
“For instance, MIDAS [1], scVAEIT [2] presents deep probabilistic frameworks that achieve dimensionality reduction, imputation, and batch correction. scMo-MaT [3] employs matrix tri-factorization to integrate single-cell multi-omics data, which can be effective but may struggle with scalability and…”
Self-citationOOD Generalization of GNNs Through Causal Stabilization Learning
Liu, L. (2025) · Lecture notes in computer science · doi:10.1007/978-981-95-0006-2_11 · Cited by 1 · see citing works
Chung, H. M., & Huang, Y. (2024) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2024.07.04.602109 · Cited by 1 · see citing works
“…[21], a kind of generative factor analysis neural network model, in solving numerous challenging biological problems, such as predicting cell transition [22, 23, 24] and integrating knowledge from different omics [25], we tried to apply VAE to identifying single-cell mutation patterns of SNPs.”
MethodMulti-omics integration and batch correction using a modality-agnostic deep learning frameworkPreprint
Larizgoitia, J. I. A., Partel, G., Venturelli, L., Zhang, W., Spotbeen, X., Vanuytven, S., Kint, S., Vandereyken, K., Wouters, D., Ismail, A., et al. (2025) · bioRxiv · doi:10.1101/2025.10.21.683449 · Cited by 3 · see citing works
Toward Computationally Complete Spatial OmicsPreprint
Li, W., Mao, L., Liu, Y., Peng, F., Sachs, N., Wu, W., Yiu, S. P. T., Yan, H., Schroeder, A. R., Yu, X., et al. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2026.03.03.709303 · Cited by 1 · see citing works
Breathing new life into in vivo lung editing
(2024) · Nature Biotechnology · doi:10.1038/s41587-024-02338-5
Continual integration of single-cell multimodal data with MIRACLE
Zhou, J., Wang, J., Hu, S., Kan, T., Feng, C., Qiang, X., Dong, G., Shi, J., Liu, R., Bo, X., et al. (2026) · Nature Computational Science · doi:10.1038/s43588-026-01030-9
“It leverages MIDAS 19 as a base model to support the integration of multimodal mosaic data, enabling online updates across diverse omics.”
Self-citationACE: a versatile contrastive learning framework for single-cell mosaic integrationPreprint
Yan, X., Chen, J., Zheng, R., & Li, M. (2024) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2024.11.28.625798
ACE: A Versatile Contrastive Learning Framework for Single-cell Mosaic Integration
Yan, X., Chen, J., Zheng, R., & Li, M. (2025) · Genomics Proteomics & Bioinformatics · doi:10.1093/gpbjnl/qzaf062
“When the dataset supports evaluation of modality alignment metrics, we used w bio ¼ 0 : 4, w batch ¼ 0 : 3, and w modAlign ¼ 0 : 3, following the single-cell Multimodal Integration Benchmarking (scMIB) benchmarking proposed by MIDAS [30].”
Single Cell Mosaic Integration via Regulatory Graph Guided Variational Cross-modal Fusion
Lv, J., Wang, Z., Zhou, Z., & Zhang, Y. (2025) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn64981.2025.11227268
“Nevertheless, the recently proposed MIDAS [20], based on a deep generative framework of multimodal variational autoencoders, has achieved good results.”
Song, S., & Villoutreix, P. (2025) · PLoS Computational Biology · doi:10.1371/journal.pcbi.1012352
PRISM: Niche-informed Deciphering of Incomplete Spatial Multi-Omics DataPreprint
Mu, S., Wang, Z., Liao, Y., Liang, J., Zhang, D., Wang, C., Xie, J., Sheng, X., Zhang, T. Q., Huang, W., et al. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2026.02.03.703456
Dual Adaptive Disentangled Representation Learning With Multimodal Data for Disease Diagnosis
Chen, X., Pan, W., Wang, T., Zhang, X., Xiong, W., Tian, T., Feng, Q., & Huang, M. (2026) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2026.3664047
Achieving spatial multi-omics integration from unaligned serial sections with DIMEPreprint
Sun, P., Huang, X., Mou, T., & Zheng, X. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2026.02.25.707961
Rahman, E., Saklayen, G., Rao, P., Nassif, A. D., Joseph, J. H., & Webb, W. R. (2026) · Toxicon · doi:10.1016/j.toxicon.2026.109060
IMAS resolves perturbation-sensitive regulatory architectures from matched tumour multiomicsPreprint
Deyang, W., Yamashiro, T., & Inubushi, T. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2026.04.09.717444
CHAMPOLLION: Robust Multi-Omics Integration via Inverse Optimal Transport Using Paired CellsPreprint
Samaran, J., Gabriel Peyré, A., & Cantini, L. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2026.04.28.721317
Robust integration of single-cell datasets with imbalanced modality composition
Sheng, Q., Zhou, Y., Zhu, F., Xu, L., & Jin, S. (2026) · Nature Communications · doi:10.1038/s41467-026-72933-4
“MIDAS 25 was executed using the Python script provided at https://github. com/labomics/midas/tree/reproducibility/.”
InfluentialA systematic review of algorithmic challenges in noise modelling for multimodal single-cell
Mallampalli, S. S., Madan, A., & Jain, C. K. (2026) · Computational Biology and Chemistry · doi:10.1016/j.compbiolchem.2026.109161
A deep learning architecture for combining and imputing heterogeneous metabolomics datasets
Çelik, S., Can, B., Erdogan, M. A., & Cakmak, A. (2026) · BMC Bioinformatics · doi:10.1186/s12859-026-06560-7
“Mosaic-integration (MI) methods [7, 8, 11, 25, 29] and domain adaptation techniques [6, 18] aim to embed multi-omics data into shared latent spaces, primarily in single-cell contexts.”
Mapping ovarian cellular and molecular landscape across the lifespan of women: a scoping review
Obukhova, D., Loid, M., Schor, M., Brunner, H. G., Salumets, A., & Esteki, M. Z. (2026) · Human Reproduction Update · doi:10.1093/humupd/dmag018
“This flexibility allows for imputing missing values, taking properties of the observed data into consideration (Du et al. , 2022; He et al. , 2024; Bai ~ ao et al. , 2025).”
Turki, T., & Taguchi, Y. (2026) · Scientific Reports · doi:10.1038/s41598-026-64531-7
A patient’s longitudinal history reconstructs their unmeasured molecular profile
Tanis, S., Alvarez, S. L., & Davidson, N. R. (2026) · Nature Computational Science · doi:10.1038/s43588-026-01024-7
Lin, X., Sun, Y., Wang, X., Zhang, P., Zhang, Y., Li, Y., Wang, Y., Hu, P., Zhang, Y., Chen, H., et al. (2026) · Information Fusion · doi:10.1016/j.inffus.2026.104738
Self-citationDeng, H., Zhao, X., & Yuan, L. (2026) · Molecular Aspects of Medicine · doi:10.1016/j.mam.2026.101503
Unifying multimodal single-cell data with a mixture-of-experts β-variational autoencoder frameworkPreprint
Ashford, A. J., Enright, T., Somers, J., Nikolova, O. H., & Demir, E. (2026) · Genome Research · doi:10.1101/gr.281431.125
Noori, A., Fishman, N., Fang, A., Fesser, L., & Žitnik, M. (2026) · Cell · doi:10.1016/j.cell.2026.08.032 · Cited by 2 · see citing works
When label-free morphology is sufficient for targeted cellular measurementsPreprint
Li, M., Zhu, J., Li, B., Zhang, C., Tang, Z., Wang, J., Xing, W., Zhang, B., Xu, J., Meng, L., et al. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2026.09.22.753654
Self-citationAUDA: An Analytical Workflow for Sparse and Heterogeneous Plastic-Related Data
Chen, Z., Liu, B., & Chen, C. (2026) · Data · doi:10.3390/data11100266
Dai, J., Xu, Y., Wang, X., Zhang, L., Ma, M., 饶凯锋, & 王子健 (2026) · ACS ES&T Toxicology · doi:10.1021/acsesttox.6c00052
Liu, Y., Wu, Q., Ye, K., He, X., & Tian, T. (2026) · doi:10.1109/cvprf71909.2026.00815
“The Swin Transformer was selected not only for its ability to capture long-range dependencies, characteristic of Transformer architectures, but also because its hierarchical design effectively extracts multi-scale visual features, which is crucial for identifying complex histopathological patterns.”
Vejandla, S. C., & Tiwari, H. K. (2026) · Research Square · doi:10.21203/rs.3.rs-11144436/v1
- Authors
- He, Z., Hu, S., Chen, Y., An, S., Zhou, J., Liu, R., Shi, J., Wang, J., Dong, G., Shi, J., Zhao, J., Ou-Yang, L., Zhu, Y., Bo, X., & Ying, X.
- Affiliations
- Institute of Basic Medical Sciences of the Chinese Academy of Medical Sciences (CN)
- Shenzhen University (CN)
- China University of Geosciences (CN)
- Institute of Health Service and Transfusion Medicine (CN)
- Corresponding author
- Bo, Xiaochen
- Ying, Xiaomin
- ORCID
- Venue
- Nature Biotechnology
- Published
- 2024-01-23
- Volume
- 42
- Issue
- 10
- Pages
- 1594-1605
- ISSN
- 0733-222X (ISSN-L)
- 1087-0156
- 1546-1696
- PMC
- PMC11471558
- OpenAlex
- W4391168615
- Cited by
- 84
- References
- 74
- Citations by year
- 2026: 38 · 2025: 31 · 2024: 15
- FWCI
- 11.44
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Locations
- Nature Biotechnology (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- Funders
- National Key R&D Program of China
- National Natural Science Foundation of China (62303488)
- Topics
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Single-cell and spatial transcriptomics
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Bioinformatics and Genomic Networks
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Gene Regulatory Network Analysis
- Keywords
- knowledge transfer, MIDAS, modality alignment, batch effect correction, self-supervised learning, dimensionality reduction, missing data imputation, transfer learning, peripheral blood mononuclear cells, bone marrow, pseudotime, cellular heterogeneity
- MeSH terms
- Humans, Leukocytes, Mononuclear, Software, Reproducibility of Results, Computational Biology, Single-Cell Analysis
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
