CMOT: cross-modality optimal transport for multimodal inference
Open accessPublished version of a preprint
Abstract
Multimodal measurements of single-cell sequencing technologies facilitate a comprehensive understanding of specific cellular and molecular mechanisms. However, simultaneous profiling of multiple modalities of single cells is challenging, and data integration remains elusive due to missing modalities and cell-cell correspondences. To address this, we developed a computational approach, Cross-Modality Optimal Transport (CMOT), which aligns cells within available multi-modal data (source) onto a common latent space and infers missing modalities for cells from another modality (target) of mapped source cells. CMOT outperforms existing methods in various applications from developing brain, cancers to immunology, and provides biological interpretations improving cell-type or cancer classifications.
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?
A contrastive loss brings related modality pairs closer and distances unrelated pairs in a shared embedding space.
“The model is trained using a contrastive loss function to bring related modality pairs, like images and descriptions, closer in a shared embedding space while distancing unrelated pairs [179,180].”
From Multimodal fusion and vision–language models: A survey for robot vision (2026) · cites this paper as [179]
The Methods section (page unavailable) says CMOT projects modalities into a common manifold and minimizes distances between corresponding samples. It describes manifold alignment and optimal transport, not a contrastive loss that distances unrelated pairs; its examples concern single-cell modalities, not images and descriptions. (LLM, conf=0.88)
Experimental — accuracy not yet measured
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
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 · see citing works
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
Metascape provides a biologist-oriented resource for the analysis of systems-level datasets
Zhou, Y., Zhou, B., Pache, L., Chang, M., Khodabakhshi, A. H., Tanaseichuk, O., Benner, C., & Chanda, S. K. (2019) · Nature Communications · doi:10.1038/s41467-019-09234-6 · Cited by 14,611 · see citing works
Liu, F. T., Ting, K. M., & Zhou, Z.-H. (2008) · 2008 Eighth IEEE International Conference on Data Mining · doi:10.1109/icdm.2008.17 · Cited by 6,601 · see citing works
Hafemeister, C., & Satija, R. (2019) · Genome Biology · doi:10.1186/s13059-019-1874-1 · Cited by 4,479 · cited 2× · see citing works
“For scRNA, we performed normalization and variance stabilization using SCTransform [42] and picked the top 1000 most variable genes.”
MethodSimultaneous 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
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
Li, H., Courtois, E. T., Sengupta, D., Tan, Y., Chen, K. H., Goh, J. J. L., Kong, S. L., Chua, C., Hon, L. K., Tan, W. S., et al. (2017) · Nature Genetics · doi:10.1038/ng.3818 · Cited by 1,080 · see citing works
Optimal Transport for Domain Adaptation
Courty, N., Flamary, R., Tuia, D., & Rakotomamonjy, A. (2016) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2615921 · Cited by 1,027 · see citing works
Joint profiling of chromatin accessibility and gene expression in thousands of single cells
Cao, J., Cusanovich, D. A., Ramani, V., Aghamirzaie, D., Pliner, H. A., Hill, A. J., Daza, R. M., McFaline-Figueroa, J. L., Packer, J. S., Christiansen, L., et al. (2018) · Science · doi:10.1126/science.aau0730 · Cited by 938 · see citing works
Schiebinger, G., Shu, J., Tabaka, M., Cleary, B., Subramanian, V., Solomon, A., Gould, J., Liu, S., Lin, S., Berube, P., et al. (2019) · Cell · doi:10.1016/j.cell.2019.01.006 · Cited by 829 · 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 · see citing works
A Single-Cell Atlas of In Vivo Mammalian Chromatin Accessibility
Cusanovich, D. A., Hill, A. J., Aghamirzaie, D., Daza, R. M., Pliner, H. A., Berletch, J. B., Filippova, G. N., Huang, X., Christiansen, L., DeWitt, W. S., et al. (2018) · Cell · doi:10.1016/j.cell.2018.06.052 · Cited by 759 · see citing works
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
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 · see citing works
Reddy, T. E., Pauli, F., Sprouse, R. O., Neff, N. F., Newberry, K. M., Garabedian, M. J., & Myers, R. M. (2009) · Genome Research · doi:10.1101/gr.097022.109 · Cited by 543 · see citing works
Gromov–Wasserstein Distances and the Metric Approach to Object Matching
Mémoli, F. (2011) · Foundations of Computational Mathematics · doi:10.1007/s10208-011-9093-5 · Cited by 519 · see citing works
Trevino, A. E., Müller, F., Andersen, J., Sundaram, L., Kathiria, A., Shcherbina, A., Farh, K., Chang, H. Y., Pașca, A. M., Kundaje, A., et al. (2021) · Cell · doi:10.1016/j.cell.2021.07.039 · Cited by 478 · see citing works
Lu, N. Z., Wardell, S. E., Burnstein, K. L., DeFranco, D. B., Fuller, P. J., Giguère, V., Hochberg, R. B., McKay, L. I., Renoir, J., Weigel, N. L., et al. (2006) · Pharmacological Reviews · doi:10.1124/pr.58.4.9 · Cited by 425 · see citing works
Trevino, A. E., Müller, F., Andersen, J., Sundaram, L., Kathiria, A. S., Shcherbina, A., Farh, K., Chang, H. Y., Pașca, A. M., Kundaje, A., et al. (2020) · bioRxiv · doi:10.1101/2020.12.29.424636 · Cited by 407 · see citing works
Gromov-Wasserstein Alignment of Word Embedding Spaces
Alvarez-Melis, D., & Jaakkola, T. (2018) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/d18-1214 · Cited by 287 · see citing works
Manifold Learning Theory and Applications
Ma, Y., & Fu, Y. (2011) · CRC Press eBooks · doi:10.1201/b11431 · Cited by 258 · see citing works
Unbalanced optimal transport: Dynamic and Kantorovich formulations
Chizat, L., Peyré, G., Schmitzer, B., et al. (2018) · Journal of Functional Analysis · doi:10.1016/j.jfa.2018.03.008 · Cited by 254 · see citing works
Deconvolution of single-cell multi-omics layers reveals regulatory heterogeneity
Liu, L., Liu, C., Quintero, A., Wu, L., Yuan, Y., Wang, M., Cheng, M., Leng, L., Xu, L., Dong, G., et al. (2019) · Nature Communications · doi:10.1038/s41467-018-08205-7 · Cited by 243 · see citing works
SCOT: Single-Cell Multi-Omics Alignment with Optimal Transport
Demetçi, P., Santorella, R., Sandstede, B., Noble, W. S., & Singh, R. (2022) · Journal of Computational Biology · doi:10.1089/cmb.2021.0446 · Cited by 177 · see citing works
Jin, S., Zhang, L., & Nie, Q. H. (2020) · Genome biology · doi:10.1186/s13059-020-1932-8 · Cited by 174 · see citing works
Reddy, T. E., Gertz, J., Crawford, G. E., Garabedian, M. J., & Myers, R. M. (2012) · Molecular and Cellular Biology · doi:10.1128/mcb.00062-12 · Cited by 149 · see citing works
Bittencourt, D., Wu, D., Jeong, K. W., Gerke, D. S., Herviou, L., Ianculescu, I., Chodankar, R., Siegmund, K. D., & Stallcup, M. R. (2012) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1211803109 · Cited by 140 · see citing works
Unsupervised topological alignment for single-cell multi-omics integration
Cao, K., Bai, X., Hong, Y., & Wan, L. (2020) · Bioinformatics · doi:10.1093/bioinformatics/btaa443 · Cited by 130 · see citing works
Manifold alignment for heterogeneous single-cell multi-omics data integration using Pamona
Cao, K., Hong, Y., & Wan, L. (2021) · Bioinformatics · doi:10.1093/bioinformatics/btab594 · Cited by 106 · see citing works
Computational Optimal TransportPreprint
Peyré, G., & Cuturi, M. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1803.00567 · Cited by 96 · see citing works
Jointly embedding multiple single-cell omics measurementsPreprint
Liu, J., Huang, Y., Singh, R., Vert, J., & Noble, W. S. (2019) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/644310 · Cited by 73 · see citing works
Jointly Embedding Multiple Single-Cell Omics Measurements
Liu, J., Huang, Y., Singh, R., Vert, J., & Noble, W. S. (2019) · PubMed · doi:10.4230/lipics.wabi.2019.10 · Cited by 67 · see citing works
Bi-order multimodal integration of single-cell data
Dou, J., Liang, S., Mohanty, V., Miao, Q., Huang, Y., Liang, Q., Cheng, X., Kim, S., Choi, J., Li, Y., et al. (2022) · Genome biology · doi:10.1186/s13059-022-02679-x · Cited by 62 · see citing works
Single-Cell Multiomics Techniques: From Conception to Applications
Dimitriu, M. A., Lazar-Contes, I., Roszkowski, M., & Mansuy, I. M. (2022) · Frontiers in Cell and Developmental Biology · doi:10.3389/fcell.2022.854317 · Cited by 52 · see citing works
Optimal transport improves cell–cell similarity inference in single-cell omics data
Huizing, G.-J., Gabriel Peyré, A., & Cantini, L. (2022) · Bioinformatics · doi:10.1093/bioinformatics/btac084 · Cited by 42 · see citing works
Consistent cross-modal identification of cortical neurons with coupled autoencoders
Gala, R., Budzillo, A., Baftizadeh, F., Miller, J. A., Gouwens, N. W., Arkhipov, A. S., Murphy, G. J., Tasic, B., Zeng, H., Hawrylycz, M., et al. (2021) · Nature Computational Science · doi:10.1038/s43588-021-00030-1 · Cited by 40 · see citing works
The Unbalanced Gromov Wasserstein Distance: Conic Formulation and RelaxationPreprint
Séjourné, T., Vialard, F., & Gabriel Peyré, A. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2009.04266 · Cited by 39 · see citing works
Nguyen, N. D., Blaby, I. K., & Wang, D. (2019) · BMC Genomics · doi:10.1186/s12864-019-6329-2 · Cited by 30 · see citing works
Self-citationLearning Disentangled Representations with Reference-Based Variational AutoencodersPreprint
Ruiz, A., Martínez, O., Binefa, X., & Verbeek, J. J. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1901.08534 · Cited by 19 · see citing works
Huang, J., Sheng, J., & Wang, D. (2021) · Communications Biology · doi:10.1038/s42003-021-02807-6 · Cited by 13 · see citing works
Self-citationDemetçi, P., Santorella, R., Sandstede, B., et al. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-04749-7_1 · Cited by 8 · see citing works
On Monge's “Mémoire sur la Théorie des Déblais et des Remblais.”
Cayley (1882) · Proceedings of the London Mathematical Society · doi:10.1112/plms/s1-14.1.139 · Cited by 7 · see citing works
Semi-supervised single-cell cross-modality translation using PolarbearPreprint
Zhang, R., Meng-Papaxanthos, L., Vert, J., et al. (2021) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2021.11.18.467517 · Cited by 6 · see citing works
Flagged first, then by citations
Research works printed but not linked: 7
- [36]Kantorovitch L. On the Translocation of Masses. Available: https://www.jstor.org/stable/2626967.
- [38]Flamary R, et al. POT: Python Optimal Transport. J Mach Learn Res. 2021;22(78):1–8.
- [40]Pedregosa et al. Scikit-learn: Machine Learning in Python. JMLR 12. Available: https://scikit-learn.org/stable/about.html#citing-scikit-learn.
- [45]Keahey K, Anderson JH, Zhen Z, Riteau P, Ruth P, Stanzione DC, et al. “Lessons Learned from the Chameleon Testbed.” USENIX Annual Technical Conference. 2020.
- [46]Alatkar SA, Wang D. CMOT: Cross Modality Optimal Transport for multimodal inference. Available: https://github.com/daifengwanglab/CMOT. PMC10334579 37434182
- [49]Chen S, Lake BB, Zhang K. High-throughput sequencing of the transcriptome and chromatin accessibility in the same cell. Gene Expression Omnibus. Available: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE126074. PMC6893138 31611697
- [50]Cao J, Cusanovich DA, Ramani V, Aghamirzaie D et al. Joint profiling of chromatin accessibility and gene expression in thousands of single cells. Gene Expression Omnibus. Available: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE117089. PMC6571013 30166440
Cited by
Sorted by citations
Multimodal Deep Learning Approaches for Precision Oncology: A Comprehensive Review
Yang, H., Yang, M., Chen, J., Yao, G., Zou, Q., & Jia, L. (2024) · Briefings in Bioinformatics · doi:10.1093/bib/bbae699 · Cited by 115 · see citing works
Multimodal fusion and vision–language models: A survey for robot vision
Han, X., Chen, S., Fu, Z., Feng, Z., Fan, L., An, D., Wang, C., Guo, L., Meng, W., Zhang, X., et al. (2026) · Information Fusion · doi:10.1016/j.inffus.2025.103652 · Cited by 41 · see citing works
“…model employs specialized encoders (e.g., convolutional neural networks for visual data, transformer architectures for text and audio data) [178, 179] to extract features from different modalities, and then interacts and integrates these features through cross-modal alignment mechanisms [180, 181].”
- Authors
- Alatkar, S. A., & Wang, D.
- Affiliations
- University of Wisconsin–Madison (US)
- Corresponding author
- Wang, Daifeng
- Venue
- Genome biology
- Published
- 2023-07-11
- Volume
- 24
- Issue
- 1
- Pages
- 163-163
- ISSN
- 1465-6906 (ISSN-L)
- 1474-760X
- PMC
- PMC10334579
- OpenAlex
- W4383878671
- Cited by
- 24
- References
- 44
- Citations by year
- 2026: 6 · 2025: 7 · 2024: 8 · 2023: 3
- FWCI
- 2.14
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Locations
- Genome biology (publishedVersion, cc-by)
- bioRxiv (Cold Spring Harbor Laboratory) (acceptedVersion)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- National Science Foundation (2144475)
- University of Wisconsin-Madison
- Waisman Center (P50HD105353)
- National Institutes of Health (1r21ns128761-01)
- National Institute on Aging (R01AG067025)
- National Institute of Mental Health (U01MH116492)
- National Cancer Institute (R21CA237955)
- National Institute of Neurological Disorders and Stroke (R21NS128761, R03NS123969, R21NS127432)
- Division of Graduate Education
- Eunice Kennedy Shriver National Institute of Child Health and Human Development (P50HD105353)
- 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
- multimodal single-cell data, cell alignment, latent space embedding, data integration, cell type classification, cancer classification
- MeSH terms
- 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
