Minji Kang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Minji Kang has a total of 55 co-authors. Here are the top co-authors by number of shared publications:
- Aaron M. Newman
Institute for Stem Cell Biology and Regenerative Medicine, Stanford University, Stanford, CA, USA.
5 shared publications - Erin L. Brown
Institute for Stem Cell Biology and Regenerative Medicine, Stanford University, Stanford, USA
4 shared publications - Aadel A. Chaudhuri
Department of Radiation Oncology, Mayo Clinic, Rochester, MN, USA.
3 shared publications - Andrew J. Gentles
Stanford University
3 shared publications Wubing Zhang
Institute for Stem Cell Biology and Regenerative Medicine, Stanford University, Stanford, CA, USA
3 shared publications- Abul Usmani
Department of Radiation Oncology, Washington University School of Medicine, St. Louis, USA
2 shared publications
Latest Publications
- Top Cited PapersOpen Access
- 6 May 2026
- Published by Springer Nature in Nature
- Vol. 654 (8120) , 1076-1087
Non-invasive profiling of the tumour microenvironment with spatial ecotypes
Multicellular programs in the tumour microenvironment (TME) drive cancer pathogenesis and response to therapy but remain challenging to identify and profile clinically1-3. Here, we present a machine-learning framework for multi-analyte profiling of spatially dependent cell states and multicellular ecosystems, termed spatial ecotypes (SEs). By integrating over 10 million single-cell and spot-level spatial transcriptomes from diverse human carcinomas and melanomas, we identified nine SEs with broad conservation, each of which has unique biology, geospatial features and clinical outcome associations, including several linked to immunotherapy response. Notably, SEs were distinguishable by DNA methylation profiling and were recoverable from plasma cell-free DNA (cfDNA) using deep learning. In cfDNA from nearly 100 patients with melanoma, SE levels exhibited striking associations with immunotherapy response. Our data reveal fundamental units of TME organization and demonstrate a multimodal platform for profiling solid and liquid TMEs, with implications for improved risk stratification and therapy personalization.
- 6 May 2026
- Published by Springer Nature in Nature
- Vol. 654 (8120) , 1076-1087
Top Cited PapersOpen AccessNon-invasive profiling of the tumour microenvironment with spatial ecotypes
Multicellular programs in the tumour microenvironment (TME) drive cancer pathogenesis and response to therapy but remain challenging to identify and profile clinically1-3. Here, we present a machine-learning framework for multi-analyte profiling of spatially dependent cell states and multicellular ecosystems, termed spatial ecotypes (SEs). By integrating over 10 million single-cell and spot-level spatial transcriptomes from diverse human carcinomas and melanomas, we identified nine SEs with broad conservation, each of which has unique biology, geospatial features and clinical outcome associations, including several linked to immunotherapy response. Notably, SEs were distinguishable by DNA methylation profiling and were recoverable from plasma cell-free DNA (cfDNA) using deep learning. In cfDNA from nearly 100 patients with melanoma, SE levels exhibited striking associations with immunotherapy response. Our data reveal fundamental units of TME organization and demonstrate a multimodal platform for profiling solid and liquid TMEs, with implications for improved risk stratification and therapy personalization.
- Top Cited PapersOpen Access
- 27 October 2025
- Published by Springer Nature in Nature Methods
- Vol. 22 (11) , 2258-2263
Improved reconstruction of single-cell developmental potential with CytoTRACE 2
While single-cell RNA sequencing has advanced our understanding of cell fate, identifying molecular hallmarks of potency—a cell’s ability to differentiate into other cell types—remains a challenge. Here we introduce CytoTRACE 2, an interpretable deep learning framework for predicting absolute developmental potential from single-cell RNA sequencing data. Across diverse platforms and tissues, CytoTRACE 2 outperformed previous methods in predicting developmental hierarchies, enabling detailed mapping of single-cell differentiation landscapes and expanding insights into cell potency.
- 27 October 2025
- Published by Springer Nature in Nature Methods
- Vol. 22 (11) , 2258-2263
Top Cited PapersOpen AccessImproved reconstruction of single-cell developmental potential with CytoTRACE 2
While single-cell RNA sequencing has advanced our understanding of cell fate, identifying molecular hallmarks of potency—a cell’s ability to differentiate into other cell types—remains a challenge. Here we introduce CytoTRACE 2, an interpretable deep learning framework for predicting absolute developmental potential from single-cell RNA sequencing data. Across diverse platforms and tissues, CytoTRACE 2 outperformed previous methods in predicting developmental hierarchies, enabling detailed mapping of single-cell differentiation landscapes and expanding insights into cell potency.
- Top Cited PapersOpen Access
Mapping single-cell developmental potential in health and disease with interpretable deep learning
Single-cell RNA sequencing (scRNA-seq) has transformed our understanding of cell fate in developmental systems. However, identifying the molecular hallmarks of potency – the capacity of a cell to differentiate into other cell types – has remained challenging. Here, we introduce CytoTRACE 2, an interpretable deep learning framework for characterizing potency and differentiation states on an absolute scale from scRNA-seq data. Across 31 human and mouse scRNA-seq datasets encompassing 28 tissue types, CytoTRACE 2 outperformed existing methods for recovering experimentally determined potency levels and differentiation states covering the entire range of cellular ontogeny. Moreover, it reconstructed the temporal hierarchy of mouse embryogenesis across 62 timepoints; identified pan-tissue expression programs that discriminate major potency levels; and facilitated discovery of cellular phenotypes in cancer linked to survival and immunotherapy resistance. Our results illuminate a fundamental feature of cell biology and provide a broadly applicable platform for delineating single-cell differentiation landscapes in health and disease.
Top Cited PapersOpen AccessMapping single-cell developmental potential in health and disease with interpretable deep learning
Single-cell RNA sequencing (scRNA-seq) has transformed our understanding of cell fate in developmental systems. However, identifying the molecular hallmarks of potency – the capacity of a cell to differentiate into other cell types – has remained challenging. Here, we introduce CytoTRACE 2, an interpretable deep learning framework for characterizing potency and differentiation states on an absolute scale from scRNA-seq data. Across 31 human and mouse scRNA-seq datasets encompassing 28 tissue types, CytoTRACE 2 outperformed existing methods for recovering experimentally determined potency levels and differentiation states covering the entire range of cellular ontogeny. Moreover, it reconstructed the temporal hierarchy of mouse embryogenesis across 62 timepoints; identified pan-tissue expression programs that discriminate major potency levels; and facilitated discovery of cellular phenotypes in cancer linked to survival and immunotherapy resistance. Our results illuminate a fundamental feature of cell biology and provide a broadly applicable platform for delineating single-cell differentiation landscapes in health and disease.
- Top Cited PapersOpen Access
- 6 March 2023
- Published by Springer Nature in Nature Biotechnology
- Vol. 41 (11) , 1543-1548
High-resolution alignment of single-cell and spatial transcriptomes with CytoSPACE
Recent studies have emphasized the importance of single-cell spatial biology, yet available assays for spatial transcriptomics have limited gene recovery or low spatial resolution. Here we introduce CytoSPACE, an optimization method for mapping individual cells from a single-cell RNA sequencing atlas to spatial expression profiles. Across diverse platforms and tissue types, we show that CytoSPACE outperforms previous methods with respect to noise tolerance and accuracy, enabling tissue cartography at single-cell resolution.
- 6 March 2023
- Published by Springer Nature in Nature Biotechnology
- Vol. 41 (11) , 1543-1548
Top Cited PapersOpen AccessHigh-resolution alignment of single-cell and spatial transcriptomes with CytoSPACE
Recent studies have emphasized the importance of single-cell spatial biology, yet available assays for spatial transcriptomics have limited gene recovery or low spatial resolution. Here we introduce CytoSPACE, an optimization method for mapping individual cells from a single-cell RNA sequencing atlas to spatial expression profiles. Across diverse platforms and tissue types, we show that CytoSPACE outperforms previous methods with respect to noise tolerance and accuracy, enabling tissue cartography at single-cell resolution.
- Open Access
Robust alignment of single-cell and spatial transcriptomes with CytoSPACE
Recent studies have emphasized the importance of single-cell spatial biology, yet available assays for spatial transcriptomics have limited gene recovery or low spatial resolution. Here we introduce CytoSPACE, a method for aligning single-cell and spatial transcriptomes via convex linear optimization. Across diverse platforms and tissue types, we show that CytoSPACE outperforms previous methods with respect to noise-tolerance, accuracy, and efficiency, enabling improved analysis of spatial transcriptomics data at single-cell resolution.
Open AccessRobust alignment of single-cell and spatial transcriptomes with CytoSPACE
Recent studies have emphasized the importance of single-cell spatial biology, yet available assays for spatial transcriptomics have limited gene recovery or low spatial resolution. Here we introduce CytoSPACE, a method for aligning single-cell and spatial transcriptomes via convex linear optimization. Across diverse platforms and tissue types, we show that CytoSPACE outperforms previous methods with respect to noise-tolerance, accuracy, and efficiency, enabling improved analysis of spatial transcriptomics data at single-cell resolution.
- Open Access
- 5 May 2021
- Published by Springer Nature in Scientific Reports
- Vol. 11 (1) , 1-11
Deep hierarchical embedding for simultaneous modeling of GPCR proteins in a unified metric space
GPCR proteins belong to diverse families of proteins that are defined at multiple hierarchical levels. Inspecting relationships between GPCR proteins on the hierarchical structure is important, since characteristics of the protein can be inferred from proteins in similar hierarchical information. However, modeling of GPCR families has been performed separately for each of the family, subfamily, and sub-subfamily level. Relationships between GPCR proteins are ignored in these approaches as they process the information in the proteins with several disconnected models. In this study, we propose DeepHier, a deep learning model to simultaneously learn representations of GPCR family hierarchy from the protein sequences with a unified single model. Novel loss term based on metric learning is introduced to incorporate hierarchical relations between proteins. We tested our approach using a public GPCR sequence dataset. Metric distances in the deep feature space corresponded to the hierarchical family relation between GPCR proteins. Furthermore, we demonstrated that further downstream tasks, like phylogenetic reconstruction and motif discovery, are feasible in the constructed embedding space. These results show that hierarchical relations between sequences were successfully captured in both of technical and biological aspects.
- 5 May 2021
- Published by Springer Nature in Scientific Reports
- Vol. 11 (1) , 1-11
Open AccessDeep hierarchical embedding for simultaneous modeling of GPCR proteins in a unified metric space
GPCR proteins belong to diverse families of proteins that are defined at multiple hierarchical levels. Inspecting relationships between GPCR proteins on the hierarchical structure is important, since characteristics of the protein can be inferred from proteins in similar hierarchical information. However, modeling of GPCR families has been performed separately for each of the family, subfamily, and sub-subfamily level. Relationships between GPCR proteins are ignored in these approaches as they process the information in the proteins with several disconnected models. In this study, we propose DeepHier, a deep learning model to simultaneously learn representations of GPCR family hierarchy from the protein sequences with a unified single model. Novel loss term based on metric learning is introduced to incorporate hierarchical relations between proteins. We tested our approach using a public GPCR sequence dataset. Metric distances in the deep feature space corresponded to the hierarchical family relation between GPCR proteins. Furthermore, we demonstrated that further downstream tasks, like phylogenetic reconstruction and motif discovery, are feasible in the constructed embedding space. These results show that hierarchical relations between sequences were successfully captured in both of technical and biological aspects.
- 28 January 2020
- Published by The Microbiological Society of Korea in Journal of Microbiology
- Vol. 58 (4) , 314-319
Lactobacillus plantarum lipoteichoic acid disrupts mature Enterococcus faecalis biofilm
Apical periodontitis is caused by biofilm-mediated root canal infection. Early phase oral bacterial biofilms are inhibited by Lactobacillus plantarum lipoteichoic acid (Lp.LTA). However, mature biofilms that develop over 3 weeks are more resistant to traditional endodontic medicaments. Therefore, this study examined the effectiveness of Lp.LTA on disrupting mature Enterococcus faecalis biofilms, and on enhancing the effects of endodontic medicaments. LTA was purified from L. plantarum through butanol extraction followed by hydrophobic and ion-exchange chromatography. E. faecalis biofilms were formed over 3 weeks on glass bottom dishes and in dentin blocks obtained from human single-rooted premolars. These mature biofilms were treated with or without Lp.LTA for 1 h, followed by additional treatment with either chlorhexidine digluconate (CHX), calcium hydroxide (CH), or triple antibiotics for 24 h. Biofilms on glass were live/dead stained and quantified by ZEN through confocal laser microscopy. Bio-films in dentin were fixed, sputter coated and analyzed by ImageJ with scanning electron microscopy. Preformed E. faecalis mature biofilms on the culture dishes were dose-dependently disrupted by Lp.LTA. Lp.LTA potentiated the effects of CHX or CH on the disruption of mature biofilm. Interestingly, CHX-induced disruption of preformed E. faecalis mature biofilms was synergistically enhanced only when pre-treated with Lp.LTA. Furthermore, in the dentin block model, Lp.LTA alone reduced E. faecalis mature biofilm and pre-treatment with Lp.LTA promoted the anti-biofilm activity of CHX. Lp.LTA could be an anti-biofilm or supplementary agent that can be effective for E. faecalis-biofilm-induced diseases.
- 28 January 2020
- Published by The Microbiological Society of Korea in Journal of Microbiology
- Vol. 58 (4) , 314-319
Lactobacillus plantarum lipoteichoic acid disrupts mature Enterococcus faecalis biofilm
Apical periodontitis is caused by biofilm-mediated root canal infection. Early phase oral bacterial biofilms are inhibited by Lactobacillus plantarum lipoteichoic acid (Lp.LTA). However, mature biofilms that develop over 3 weeks are more resistant to traditional endodontic medicaments. Therefore, this study examined the effectiveness of Lp.LTA on disrupting mature Enterococcus faecalis biofilms, and on enhancing the effects of endodontic medicaments. LTA was purified from L. plantarum through butanol extraction followed by hydrophobic and ion-exchange chromatography. E. faecalis biofilms were formed over 3 weeks on glass bottom dishes and in dentin blocks obtained from human single-rooted premolars. These mature biofilms were treated with or without Lp.LTA for 1 h, followed by additional treatment with either chlorhexidine digluconate (CHX), calcium hydroxide (CH), or triple antibiotics for 24 h. Biofilms on glass were live/dead stained and quantified by ZEN through confocal laser microscopy. Bio-films in dentin were fixed, sputter coated and analyzed by ImageJ with scanning electron microscopy. Preformed E. faecalis mature biofilms on the culture dishes were dose-dependently disrupted by Lp.LTA. Lp.LTA potentiated the effects of CHX or CH on the disruption of mature biofilm. Interestingly, CHX-induced disruption of preformed E. faecalis mature biofilms was synergistically enhanced only when pre-treated with Lp.LTA. Furthermore, in the dentin block model, Lp.LTA alone reduced E. faecalis mature biofilm and pre-treatment with Lp.LTA promoted the anti-biofilm activity of CHX. Lp.LTA could be an anti-biofilm or supplementary agent that can be effective for E. faecalis-biofilm-induced diseases.