Transformer-based modeling of Clonal Selection and Expression Dynamics reveals resistance mechanisms in breast cancer
Abstract Understanding transcriptional heterogeneity in cancer cells and its implication for treatment response is critical to identify how resistance occurs and may be targeted. Such heterogeneity can be captured by in vitro studies through clonal barcoding methods. We present TraCSED (Transformer-...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-01-01
|
| Series: | npj Systems Biology and Applications |
| Online Access: | https://doi.org/10.1038/s41540-024-00485-8 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841544485311348736 |
|---|---|
| author | Nathan D Maulding Jun Zou Wei Zhou Ciara Metcalfe Joshua M Stuart Xin Ye Marc Hafner |
| author_facet | Nathan D Maulding Jun Zou Wei Zhou Ciara Metcalfe Joshua M Stuart Xin Ye Marc Hafner |
| author_sort | Nathan D Maulding |
| collection | DOAJ |
| description | Abstract Understanding transcriptional heterogeneity in cancer cells and its implication for treatment response is critical to identify how resistance occurs and may be targeted. Such heterogeneity can be captured by in vitro studies through clonal barcoding methods. We present TraCSED (Transformer-based modeling of Clonal Selection and Expression Dynamics), a dynamic deep learning approach for modeling clonal selection. Using single-cell gene expression and the fitness of barcoded clones, TraCSED identifies interpretable gene programs and the time points at which they are associated with clonal selection. When applied to cells treated with either giredestrant, a selective estrogen receptor (ER) antagonist and degrader, or palbociclib, a CDK4/6 inhibitor, pathways dynamically associated with resistance are revealed. For example, ER activity is associated with positive selection around day four under palbociclib treatment and this adaptive response can be suppressed by combining the drugs. Yet, in the combination treatment, one clone still emerged. Clustering based on partial least squares regression found that high baseline expression of both SNHG25 and SNCG genes was the primary marker of positive selection to co-treatment and thus potentially associated with innate resistance — an aspect that traditional differential analysis methods missed. In conclusion, TraCSED enables associating features with phenotypes in a time-dependent manner from scRNA-seq data. |
| format | Article |
| id | doaj-art-04a152f93e5440de893ccafdd00c6ded |
| institution | Kabale University |
| issn | 2056-7189 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | npj Systems Biology and Applications |
| spelling | doaj-art-04a152f93e5440de893ccafdd00c6ded2025-01-12T12:28:52ZengNature Portfolionpj Systems Biology and Applications2056-71892025-01-0111111210.1038/s41540-024-00485-8Transformer-based modeling of Clonal Selection and Expression Dynamics reveals resistance mechanisms in breast cancerNathan D Maulding0Jun Zou1Wei Zhou2Ciara Metcalfe3Joshua M Stuart4Xin Ye5Marc Hafner6gRED Computational Sciences, Genentech IncDiscovery Oncology, Genentech IncDiscovery Oncology, Genentech IncDiscovery Oncology, Genentech IncDepartment of Biomolecular Engineering and Bioinformatics, UC Santa CruzDiscovery Oncology, Genentech IncgRED Computational Sciences, Genentech IncAbstract Understanding transcriptional heterogeneity in cancer cells and its implication for treatment response is critical to identify how resistance occurs and may be targeted. Such heterogeneity can be captured by in vitro studies through clonal barcoding methods. We present TraCSED (Transformer-based modeling of Clonal Selection and Expression Dynamics), a dynamic deep learning approach for modeling clonal selection. Using single-cell gene expression and the fitness of barcoded clones, TraCSED identifies interpretable gene programs and the time points at which they are associated with clonal selection. When applied to cells treated with either giredestrant, a selective estrogen receptor (ER) antagonist and degrader, or palbociclib, a CDK4/6 inhibitor, pathways dynamically associated with resistance are revealed. For example, ER activity is associated with positive selection around day four under palbociclib treatment and this adaptive response can be suppressed by combining the drugs. Yet, in the combination treatment, one clone still emerged. Clustering based on partial least squares regression found that high baseline expression of both SNHG25 and SNCG genes was the primary marker of positive selection to co-treatment and thus potentially associated with innate resistance — an aspect that traditional differential analysis methods missed. In conclusion, TraCSED enables associating features with phenotypes in a time-dependent manner from scRNA-seq data.https://doi.org/10.1038/s41540-024-00485-8 |
| spellingShingle | Nathan D Maulding Jun Zou Wei Zhou Ciara Metcalfe Joshua M Stuart Xin Ye Marc Hafner Transformer-based modeling of Clonal Selection and Expression Dynamics reveals resistance mechanisms in breast cancer npj Systems Biology and Applications |
| title | Transformer-based modeling of Clonal Selection and Expression Dynamics reveals resistance mechanisms in breast cancer |
| title_full | Transformer-based modeling of Clonal Selection and Expression Dynamics reveals resistance mechanisms in breast cancer |
| title_fullStr | Transformer-based modeling of Clonal Selection and Expression Dynamics reveals resistance mechanisms in breast cancer |
| title_full_unstemmed | Transformer-based modeling of Clonal Selection and Expression Dynamics reveals resistance mechanisms in breast cancer |
| title_short | Transformer-based modeling of Clonal Selection and Expression Dynamics reveals resistance mechanisms in breast cancer |
| title_sort | transformer based modeling of clonal selection and expression dynamics reveals resistance mechanisms in breast cancer |
| url | https://doi.org/10.1038/s41540-024-00485-8 |
| work_keys_str_mv | AT nathandmaulding transformerbasedmodelingofclonalselectionandexpressiondynamicsrevealsresistancemechanismsinbreastcancer AT junzou transformerbasedmodelingofclonalselectionandexpressiondynamicsrevealsresistancemechanismsinbreastcancer AT weizhou transformerbasedmodelingofclonalselectionandexpressiondynamicsrevealsresistancemechanismsinbreastcancer AT ciarametcalfe transformerbasedmodelingofclonalselectionandexpressiondynamicsrevealsresistancemechanismsinbreastcancer AT joshuamstuart transformerbasedmodelingofclonalselectionandexpressiondynamicsrevealsresistancemechanismsinbreastcancer AT xinye transformerbasedmodelingofclonalselectionandexpressiondynamicsrevealsresistancemechanismsinbreastcancer AT marchafner transformerbasedmodelingofclonalselectionandexpressiondynamicsrevealsresistancemechanismsinbreastcancer |