Antonina Mitrofanova
Research Subjects
Antonina Mitrofanova has a total of 160 co-authors. Here are the top co-authors by number of shared publications:
- Cory Abate-Shen
Columbia University, New York, New York
35 shared publications - Andrea Califano
Department of Systems Biology, Columbia University, New York, USA
34 shared publications - Chee Wai Chua
Cancer Biology Group, Department of Anatomy and Departments of 2 Pathology and 3 Surgery, Faculty of Medicine, The University of Hong Kong, Hong Kong SAR, China
34 shared publications - Juan Martín Arriaga
Department of Molecular Pharmacology and Therapeutics, Vagelos College of Physicians and Surgeons, Columbia University Irving Medical Center, New York, USA
34 shared publications - Mark A. Rubin
Department for BioMedical Research, University of Bern, Bern, Switzerland
34 shared publications - Michael M. Shen
Department of Medicine, Columbia University Vagelos College of Physicians and Surgeons, New York, NY, USA.
34 shared publications
Latest Publications
- Open Access
- 17 August 2026
- Published by Frontiers Media SA in Frontiers in Genetics
- Vol. 17, 1813369
Integrating single-cell transcriptomics with deep learning for glioblastoma treatment
Glioblastomas are aggressive, heterogeneous tumors that present significant challenges in both diagnosis and treatment. Despite advances in surgical resection, radiotherapy, and chemotherapy with temozolomide (TMZ), the prognosis for glioblastoma patients remains poor, largely due to tumor heterogeneity and resistance mechanisms, such as genetic mutations in DNA repair pathways. To address these specific heterogenous qualities of glioblastoma, single-cell RNA sequencing (scRNA-seq) has emerged as a powerful tool for characterizing glioblastoma tumors, enabling the identification of subpopulations that respond differently to treatment. However, utilizing the vast amount of data generated by scRNA-seq poses challenges in clinical applications. To overcome this challenge, computational models have been introduced to more effectively process patient scRNA-seq data into more digestible information for clinicians. More specifically, advanced deep learning approaches show promise for processing and analyzing patient scRNA-seq data, enhancing informed treatment approaches for highly heterogenous glioblastoma. This review aims to explain how scRNA-seq can be used to identify important areas of glioblastoma treatment resistance, evaluate current glioblastoma scRNA-seq-based deep learning models, and outline relevant training datasets to overcome patient scRNA-seq data availability limitations. Ultimately, these deep learning models can be utilized by researchers and clinicians to provide more informed and precise treatment to glioblastoma patients.
- 17 August 2026
- Published by Frontiers Media SA in Frontiers in Genetics
- Vol. 17, 1813369
Open AccessIntegrating single-cell transcriptomics with deep learning for glioblastoma treatment
Glioblastomas are aggressive, heterogeneous tumors that present significant challenges in both diagnosis and treatment. Despite advances in surgical resection, radiotherapy, and chemotherapy with temozolomide (TMZ), the prognosis for glioblastoma patients remains poor, largely due to tumor heterogeneity and resistance mechanisms, such as genetic mutations in DNA repair pathways. To address these specific heterogenous qualities of glioblastoma, single-cell RNA sequencing (scRNA-seq) has emerged as a powerful tool for characterizing glioblastoma tumors, enabling the identification of subpopulations that respond differently to treatment. However, utilizing the vast amount of data generated by scRNA-seq poses challenges in clinical applications. To overcome this challenge, computational models have been introduced to more effectively process patient scRNA-seq data into more digestible information for clinicians. More specifically, advanced deep learning approaches show promise for processing and analyzing patient scRNA-seq data, enhancing informed treatment approaches for highly heterogenous glioblastoma. This review aims to explain how scRNA-seq can be used to identify important areas of glioblastoma treatment resistance, evaluate current glioblastoma scRNA-seq-based deep learning models, and outline relevant training datasets to overcome patient scRNA-seq data availability limitations. Ultimately, these deep learning models can be utilized by researchers and clinicians to provide more informed and precise treatment to glioblastoma patients.
- Open Access
- 3 February 2026
- Published by Springer Nature in Scientific Reports
- Vol. 16 (1)
Machine learning framework for mRNA alternative splicing analysis identifies a signature of progression in colorectal adenocarcinoma
Despite recent advances in genome-wide profiling and the discovery of novel therapeutic options for colorectal adenocarcinoma (COAD), effective patient classification for the risk of cancer progression remains underdeveloped. Recent research has highlighted the crucial role of mRNA alternative splicing (AS) in the development and progression of COAD, yet a genome-wide comprehensive evaluation of the role of AS in COAD progression has not been implemented. In this study, we present a robust machine-learning framework designed to uncover clinically relevant AS events associated with progression-free survival (PFS) in COAD patients. For this, we analyzed RNA sequencing data from the TCGA-COAD cohort (n = 266). We employed a machine learning approach integrating Cox Proportional Hazards (PH) analysis and Robust Likelihood-Based Survival (RBSURV) modeling that identified a five-event AS-PFS signature (spanning AS events in OR52K1, SPIN3, NDUFV1, BMPR1A, and ARPC4 genes). By leveraging this signature, we defined a risk score for each patient, categorizing them into low and high-risk groups. This signature and its risk score were further validated through Kaplan-Meier survival analysis and time-dependent receiver operating characteristic (ROC) analysis in the TCGA-COAD test set and independent patient cohort AC-ICAM (n = 348). Comparison to other markers and methods further confirmed the independent predictive value of the AS-PFS risk signature. We propose that this signature could be utilized in clinical settings to enhance patient stratification at diagnosis and further inform personalized treatment strategies.
- 3 February 2026
- Published by Springer Nature in Scientific Reports
- Vol. 16 (1)
Open AccessMachine learning framework for mRNA alternative splicing analysis identifies a signature of progression in colorectal adenocarcinoma
Despite recent advances in genome-wide profiling and the discovery of novel therapeutic options for colorectal adenocarcinoma (COAD), effective patient classification for the risk of cancer progression remains underdeveloped. Recent research has highlighted the crucial role of mRNA alternative splicing (AS) in the development and progression of COAD, yet a genome-wide comprehensive evaluation of the role of AS in COAD progression has not been implemented. In this study, we present a robust machine-learning framework designed to uncover clinically relevant AS events associated with progression-free survival (PFS) in COAD patients. For this, we analyzed RNA sequencing data from the TCGA-COAD cohort (n = 266). We employed a machine learning approach integrating Cox Proportional Hazards (PH) analysis and Robust Likelihood-Based Survival (RBSURV) modeling that identified a five-event AS-PFS signature (spanning AS events in OR52K1, SPIN3, NDUFV1, BMPR1A, and ARPC4 genes). By leveraging this signature, we defined a risk score for each patient, categorizing them into low and high-risk groups. This signature and its risk score were further validated through Kaplan-Meier survival analysis and time-dependent receiver operating characteristic (ROC) analysis in the TCGA-COAD test set and independent patient cohort AC-ICAM (n = 348). Comparison to other markers and methods further confirmed the independent predictive value of the AS-PFS risk signature. We propose that this signature could be utilized in clinical settings to enhance patient stratification at diagnosis and further inform personalized treatment strategies.
- Open Access
- 11 December 2025
- Published by American Association for Cancer Research (AACR)
Supplementary Figures S1-S11 from OncoLoop: A Network-Based Precision Cancer Medicine Framework
Figure S1: Genomic alterations in prostate cancer represented in the GEMMs (related to Fig. 2). Figure S2: Additional phenotypic analyses of the GEMMs (related to Fig. 2). Figure S3: Phenotypic analysis of allograft and organoid models (related to Fig. 2). Figure S4: Additional transcriptomic analyses of the GEMMs (related to Fig. 3). Figure S5: Analyses of AR activity in GEMMS (related to Fig. 3). Figure S6: Regulatory sub-networks of the GEMM clusters (related to Fig. 3). Figure S7. MR-match of prostate cancer cells lines to human PCa (related to Figs. 5). Figure S8. Drug perturbation protein activity profiles from DU145 cells (related to Figs. 5, 6, 7). Figure S9. LNCaP Pharmacotyping to patients and GEMMs (related to Figs. 5). Figure S10: Additional validation of drug candidates (related to Figs 6, 7). Figure S11: Additional validation of drug candidates (related to Figs 6).
- 11 December 2025
- Published by American Association for Cancer Research (AACR)
Open AccessSupplementary Figures S1-S11 from OncoLoop: A Network-Based Precision Cancer Medicine Framework
Figure S1: Genomic alterations in prostate cancer represented in the GEMMs (related to Fig. 2). Figure S2: Additional phenotypic analyses of the GEMMs (related to Fig. 2). Figure S3: Phenotypic analysis of allograft and organoid models (related to Fig. 2). Figure S4: Additional transcriptomic analyses of the GEMMs (related to Fig. 3). Figure S5: Analyses of AR activity in GEMMS (related to Fig. 3). Figure S6: Regulatory sub-networks of the GEMM clusters (related to Fig. 3). Figure S7. MR-match of prostate cancer cells lines to human PCa (related to Figs. 5). Figure S8. Drug perturbation protein activity profiles from DU145 cells (related to Figs. 5, 6, 7). Figure S9. LNCaP Pharmacotyping to patients and GEMMs (related to Figs. 5). Figure S10: Additional validation of drug candidates (related to Figs 6, 7). Figure S11: Additional validation of drug candidates (related to Figs 6).
- Open Access
- 11 December 2025
- Published by American Association for Cancer Research (AACR)
Table S6 from OncoLoop: A Network-Based Precision Cancer Medicine Framework
Supplementary Table 6. OncoLoop summary table
- 11 December 2025
- Published by American Association for Cancer Research (AACR)
Open AccessTable S6 from OncoLoop: A Network-Based Precision Cancer Medicine Framework
Supplementary Table 6. OncoLoop summary table
- Open Access
- 11 December 2025
- Published by American Association for Cancer Research (AACR)
Table S5 from OncoLoop: A Network-Based Precision Cancer Medicine Framework
Supplementary Table 5. Drug perturbation and OncoTreat analysis A. Summary of drugs and concentrations used B. Drug perturbation data for DU145 C. OncoTreat for drugs to SU2C patients using DU145 D. OncoTreat for drugs to GEMMs using DU145
- 11 December 2025
- Published by American Association for Cancer Research (AACR)
Open AccessTable S5 from OncoLoop: A Network-Based Precision Cancer Medicine Framework
Supplementary Table 5. Drug perturbation and OncoTreat analysis A. Summary of drugs and concentrations used B. Drug perturbation data for DU145 C. OncoTreat for drugs to SU2C patients using DU145 D. OncoTreat for drugs to GEMMs using DU145
- Open Access
- 11 December 2025
- Published by American Association for Cancer Research (AACR)
Detailed Materials and Methods from OncoLoop: A Network-Based Precision Cancer Medicine Framework
Detailed Materials and Methods
- 11 December 2025
- Published by American Association for Cancer Research (AACR)
Open AccessDetailed Materials and Methods from OncoLoop: A Network-Based Precision Cancer Medicine Framework
Detailed Materials and Methods
- Open Access
- 11 December 2025
- Published by American Association for Cancer Research (AACR)
Table S1 from OncoLoop: A Network-Based Precision Cancer Medicine Framework
Supplementary Table 1: Phenotypic analysis of the GEMMs
- 11 December 2025
- Published by American Association for Cancer Research (AACR)
Open AccessTable S1 from OncoLoop: A Network-Based Precision Cancer Medicine Framework
Supplementary Table 1: Phenotypic analysis of the GEMMs
- Open Access
- 11 December 2025
- Published by American Association for Cancer Research (AACR)
Table S4 from OncoLoop: A Network-Based Precision Cancer Medicine Framework
Supplementary Table 4: OncoMatch A. OncoMatch TCGA B. OncoMatch SU2C
- 11 December 2025
- Published by American Association for Cancer Research (AACR)
Open AccessTable S4 from OncoLoop: A Network-Based Precision Cancer Medicine Framework
Supplementary Table 4: OncoMatch A. OncoMatch TCGA B. OncoMatch SU2C
- Open Access
- 11 December 2025
- Published by American Association for Cancer Research (AACR)
Table S3 from OncoLoop: A Network-Based Precision Cancer Medicine Framework
Supplementary Table 3: Transcriptomic analyses of the human patient samples A. TCGA Interactome B. SU2C Interactome C. Protein activity TCGA D. Protein Activity SU2C
- 11 December 2025
- Published by American Association for Cancer Research (AACR)
Open AccessTable S3 from OncoLoop: A Network-Based Precision Cancer Medicine Framework
Supplementary Table 3: Transcriptomic analyses of the human patient samples A. TCGA Interactome B. SU2C Interactome C. Protein activity TCGA D. Protein Activity SU2C
- Open Access
- 11 December 2025
- Published by American Association for Cancer Research (AACR)
Table S7 from OncoLoop: A Network-Based Precision Cancer Medicine Framework
Supplementary Table 7. Transcriptomic analyses of the PDX models A. PDX interactome B. OncoTreat for drugs to PDX using DU145 cell perturbation data
- 11 December 2025
- Published by American Association for Cancer Research (AACR)
Open AccessTable S7 from OncoLoop: A Network-Based Precision Cancer Medicine Framework
Supplementary Table 7. Transcriptomic analyses of the PDX models A. PDX interactome B. OncoTreat for drugs to PDX using DU145 cell perturbation data