The Role of Single-Cell Multi-omics and Artificial Intelligence in Guiding Precision Antibody-Drug Conjugate Therapies for Metastatic Breast Cancer.
Fuente:
Zenodo
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Recurso digital |
| Published: |
Zenodo
2025
|
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866901305882050560 |
|---|---|
| author | Krupa J Afreen Misbah Ajoy Shil Santanu Mandal |
| author_facet | Krupa J Afreen Misbah Ajoy Shil Santanu Mandal |
| contents | <p>Metastatic breast cancer (MBC) remains a leading cause of cancer mortality in women, complicated by extensive intratumoral heterogeneity and complex tumor microenvironments that fuel treatment resistance and progression. Antibody-drug conjugates (ADCs) offer targeted cytotoxic therapy combining monoclonal antibody specificity with potent payloads, improving efficacy and reducing systemic toxicity [1-9,12]. However, ADC effectiveness is often limited by factors like heterogeneous antigen expression, adaptive resistance, altered trafficking, and microenvironmental influences. Advances in single-cell multi-omics technologies, including scRNA-seq, spatial transcriptomics, proteomics, metabolomics, and epigenomics, enable high-resolution profiling of tumor cells and their microenvironment, revealing subclonal populations, lineage hierarchies, and cellular interactions critical to ADC response and resistance [8-16]. Spatially resolved data preserve tissue architecture to identify immune infiltration, stromal signaling, metabolic adaptations, and extracellular matrix remodeling that impact treatment outcomes, especially in triple-negative and hormone receptor-positive subtypes. Artificial intelligence (AI), through machine learning and deep learning, integrates these complex multi-omics datasets to discover predictive biomarkers, model therapy response, classify patients, and simulate tumor evolution under ADC therapy [17-22]. AI-driven models have identified resistance mechanisms, optimized treatment sequencing, and suggested synergistic combination therapies to enhance ADC efficacy. Clinically, these integrative approaches have stratified patients by molecular profiles, anticipated resistant clones longitudinally, and guided adaptive treatment strategies, as supported by expert consensus guidelines [23-24]. Challenges remain in standardizing single-cell workflows, harmonizing heterogeneous data, ensuring interpretability and clinical validation of AI models, and addressing ethical and regulatory issues. Nonetheless, the convergence of AI and single-cell multi-omics promises a paradigm shift in precision oncology, enabling fully personalized, adaptive ADC therapies that improve outcomes and foster next-generation drug development for metastatic breast cancer [1– 25].</p> |
| format | Recurso digital |
| id | zenodo_https___doi_org_10_5281_zenodo_17408427 |
| institution | Zenodo |
| language | |
| publishDate | 2025 |
| publisher | Zenodo |
| record_format | zenodo |
| spellingShingle | The Role of Single-Cell Multi-omics and Artificial Intelligence in Guiding Precision Antibody-Drug Conjugate Therapies for Metastatic Breast Cancer. Krupa J Afreen Misbah Ajoy Shil Santanu Mandal <p>Metastatic breast cancer (MBC) remains a leading cause of cancer mortality in women, complicated by extensive intratumoral heterogeneity and complex tumor microenvironments that fuel treatment resistance and progression. Antibody-drug conjugates (ADCs) offer targeted cytotoxic therapy combining monoclonal antibody specificity with potent payloads, improving efficacy and reducing systemic toxicity [1-9,12]. However, ADC effectiveness is often limited by factors like heterogeneous antigen expression, adaptive resistance, altered trafficking, and microenvironmental influences. Advances in single-cell multi-omics technologies, including scRNA-seq, spatial transcriptomics, proteomics, metabolomics, and epigenomics, enable high-resolution profiling of tumor cells and their microenvironment, revealing subclonal populations, lineage hierarchies, and cellular interactions critical to ADC response and resistance [8-16]. Spatially resolved data preserve tissue architecture to identify immune infiltration, stromal signaling, metabolic adaptations, and extracellular matrix remodeling that impact treatment outcomes, especially in triple-negative and hormone receptor-positive subtypes. Artificial intelligence (AI), through machine learning and deep learning, integrates these complex multi-omics datasets to discover predictive biomarkers, model therapy response, classify patients, and simulate tumor evolution under ADC therapy [17-22]. AI-driven models have identified resistance mechanisms, optimized treatment sequencing, and suggested synergistic combination therapies to enhance ADC efficacy. Clinically, these integrative approaches have stratified patients by molecular profiles, anticipated resistant clones longitudinally, and guided adaptive treatment strategies, as supported by expert consensus guidelines [23-24]. Challenges remain in standardizing single-cell workflows, harmonizing heterogeneous data, ensuring interpretability and clinical validation of AI models, and addressing ethical and regulatory issues. Nonetheless, the convergence of AI and single-cell multi-omics promises a paradigm shift in precision oncology, enabling fully personalized, adaptive ADC therapies that improve outcomes and foster next-generation drug development for metastatic breast cancer [1– 25].</p> |
| title | The Role of Single-Cell Multi-omics and Artificial Intelligence in Guiding Precision Antibody-Drug Conjugate Therapies for Metastatic Breast Cancer. |
| url | https://doi.org/10.5281/zenodo.17408427 |