Biology subjects

Baena, E.

Publications and source records attributed to Baena, E..

5 recordsLinked to original sources

bioRxiv2025

Multiple instance learning with spatial transcriptomics for interpretable patient-level predictions: application in glioblastoma

Accurate prediction of patient outcomes remains a major challenge in oncology. While recent machine learning (ML) approaches often rely on bulk omics lacking spatial resolution or histology-based multiple instance learning (MIL), spatial transcriptomics (SpT) provides a unique opportunity to capture both molecular content and tissue architecture. However, no generalizable ML framework has yet been established to exploit SpT for patient-level outcomes. We present SpaMIL, a flexible and interpretable MIL framework designed for SpT, with a distillation strategy that enables deployment for hematoxylin and eosin (H&E) slides alone. We evaluate the framework by predicting survival from glioblastoma (GBM) patients, a clinically compelling setting given its aggressiveness with a median survival of only 15 months and the lack of prognostic clinical variables. We analyzed 76 GBM cases from the MOSAIC dataset: 43 with matched SpT, H&E, single-nucleus RNA-seq (scRNA-seq), bulk RNA-seq, and clinical variables, and 33 with H&E for external validation. We developed two main architectures: abMIL, tailored to SpTs spatial molecular structure, and MabMIL, which distills SpT-derived representations into H&E. Model interpretability was achieved through a Shapley-based framework linking prognostic predictions to cell-type compositions via SpT deconvolution. In benchmarking across the five GBM MOSAIC modalities, SpT-based abMIL achieved unprecedented prognostic accuracy (median C-index: 0.72, standard deviation: 0.04), outperforming all other modalities, including established clinical predictors. PCA and deconvolution-based SpT representations surpassed recent foundation models, suggesting the need for further research on SpT foundation models. Our interpretability analysis highlighted malignant and non-malignant cell subpopulations associated with favorable or poor prognosis, consistent with recent reports. Finally, MabMIL maintained strong performance while enabling H&E-only deployment, with improved condorance index over H&E-only baselines in both internal (0.59 vs. 0.57) and external (0.62 vs. 0.55) cohorts.

cancer biology↗

bioRxiv2025

Histology and spatial transcriptomic integration revealed infiltration zone with specific cell composition as a prognostic hotspot in glioblastoma

BackgroundGlioblastoma (GBM), the most aggressive primary brain tumor, has a median survival of approximately 15 months. Twenty percent of patients survive beyond three years, but known clinical factors like age, performance status, resection extent, and MGMT promoter methylation status do not fully explain the observed outcomes. ObjectiveOur objective was to identify novel histology derived biomarkers associated with end-of-spectrum overall survival (OS) to provide novel biological insight with a translational potential. MethodsWe analyzed a total of 748 GBM patients from 3 different cohorts, uniquely enriched in long survivors (n=98 with overall survival (OS) > 5y including n=196 with OS[≥]3y), with clinical data and H&E slides obtained from the primary tumor at baseline. We propose an interpretable machine learning (ML) methodology for the discovery of histological biomarkers. Our method learned to segment each H&E slide into three distinct regions associated with long-term survival, short-term survival, and non-informative tissue. We characterized these regions by integrating unsupervised learning, nuclei segmentation, blood vessels detection, pathologist annotations, and multimodal data including spatial transcriptomics from n=31 patients of the GBM MOSAIC dataset to discover fully interpretable biomarkers. ResultsOur OS prediction model using histology and clinical data as input achieved an area under the curve (AUC) of 0.85 for the classification of patients between OS<2 and OS[≥]3y in external cohort validation, outperforming significantly models trained on clinical data or on histology alone (AUC of 0.76; 0.73, respectively). Two novel biomarkers were predicting poor survival: the presence of regions of lowly infiltrated white matter enriched in malignant cells with a mesenchymal-like phenotype, and lower levels of angiogenesis associated with higher hypoxia response in the main tumor regions. We also found that a subtype of immunosuppressive tumor macrophages - defined by high PLIN2 expression and lipid accumulation- is consistently enriched in histological areas predictive of poor prognosis. ConclusionOur interpretable ML methodology identified a novel prognostic impact of biological processes and cell types according to distinct tumor regions of GBM. These results pave the way for spatially-informed biomarkers to improve risk stratification and for personalized spatially-targeted therapeutic strategies. Key highlightsO_LIOur ML model identified histological biomarkers predicting prognosis independently from known clinical factors C_LIO_LIThe region of lowly infiltrated white matter enriched in malignant cells including a mesenchymal-like phenotype is predictive of poor prognosis C_LIO_LIAngiogenesis is increased in areas predictive of long survival in main non-necrotic tumor regions. C_LIO_LIThe subtype of macrophages expressing PLIN2 and associated with increased lipid metabolism was associated with poor prognosis in all GBM regions. C_LI Highlights O_FIG O_LINKSMALLFIG WIDTH=200 HEIGHT=116 SRC="FIGDIR/small/681087v4_ufig1.gif" ALT="Figure 1"> View larger version (43K): org.highwire.dtl.DTLVardef@45e619org.highwire.dtl.DTLVardef@105a4b0org.highwire.dtl.DTLVardef@17f257dorg.highwire.dtl.DTLVardef@7669b4_HPS_FORMAT_FIGEXP M_FIG C_FIG

cancer biology↗

bioRxiv2025

Bio-fabricated alginate tumor-like hydrogels to enhance understanding of prostate-specific micro-environments in vitro

Engineered three-dimensional (3D) in vitro models are useful tools for closely mimic human tissue-specific tumor microenvironments (TME) and to provide key information on cell-material interactions. In this work we aimed at engineering prostate-specific in vitro models to help in discerning specific cell-material interactions at the interface during prostate cancer (PCa) progression, focusing on modelling both biomechanical and biochemical traits of the prostate extracellular matrix (ECM) within PCa progression. Here, we functionalized alginates and obtained PCa-specific hydrogels for 3D culture and ease evaluation of markers used to assess PCa progression in human prostate cancer cells (i.e., PC-3 cells). Alginate-based hydrogels were modified with laminin-like peptides (i.e., IKVAV, AG73) and tailored in physical and mechanical properties to closely mimic the PCa ECM, with mechanical properties in the range of 2.5-13 kPa (the stiffer value matching advanced/metastatic PCa). To engineer the heterogeneity of advanced PCa, cancer-associated fibroblasts (hTERT PF179T CAF) were selected as stromal cellular component and co/cultured with PC-3 cells. We formulated prostate bioinks for extrusion-based bioprinting (EBB) and 3D printed engineered PCa in vitro models to study the effect of the microenvironment on the expression of key markers in PC-3 cells, considering the pivotal role of epithelial-to-mesenchymal transition (EMT) in PCa progression. Cells cultured in prostate-specific hydrogels showed higher cell proliferation and viability, whereas CD44 and Vimentin expression evidenced a higher metastatic potential in PC-3 cells cultured in stiffer and laminin-enriched hydrogels. The selected PCa TMEs used in this work showed PC-3 cells expressing increased levels of Vimentin when co-cultured with CAFs, which also correlates with CD44 expression. Results suggests positive correlations with clinical findings, underlying that tumor biomechanics holds potential for better understand cancer pathobiology and that new 3D in vitro models are urged to unveil how ECM traits regulate PCa progression. O_FIG O_LINKSMALLFIG WIDTH=200 HEIGHT=142 SRC="FIGDIR/small/671451v1_ufig1.gif" ALT="Figure 1"> View larger version (23K): org.highwire.dtl.DTLVardef@6a923borg.highwire.dtl.DTLVardef@a68087org.highwire.dtl.DTLVardef@14029a8org.highwire.dtl.DTLVardef@16ef509_HPS_FORMAT_FIGEXP M_FIG O_FLOATNOGraphical AbstractC_FLOATNO C_FIG

bioengineering↗

bioRxiv2025

Stochastic modelling of prostate progenitor architecture

Prostate cancer is a significant global health concern. Experimental and clinical research have contributed to the improvement of treatment outcomes dramatically in the past decade. However, much of the structure of the prostate and its constituent cell types remains unclear: observations of phenotypic switching between basal and luminal cells, as well as intermediate cell types between them, make classifying the components of the prostate an ongoing challenge. Importantly, a tumours cell type of origin seems to play a role in the aggressiveness and genetic heterogeneity of the cancer. To understand how different structures between cell types impact the emergence and treatment of prostate cancer, we model the emergence of a tumour by a fit mutant arising amongst healthy cells via a compartmental modelling approach. We label cells in different compartments based on their phenotype and allow for phenotypic switching between them. We measure the time until and probability of invasion and extinction of this mutant in healthy prostates through individual-based simulations. We find that less-tight population size regulation of the luminal compartment allows for the explosive population growth associated with cancer. Tumours arising in the basal compartment require more time to spread but are more strongly embedded within the prostate, explaining the longer latency and higher aggressiveness and persistence associated with these tumours. Interestingly, the inclusion of a hybrid compartment does not qualitatively change the observations, raising questions as to what mechanistic role intermediate phenotypes play in prostate cancer emergence, if any. Our model contributes to dissecting the relationship between prostate structure and outcomes for cancers arising therein.

evolutionary biology↗

bioRxiv2020

RUNX1 marks a luminal castration resistant lineage established at the onset of prostate development

The characterization of prostate epithelial hierarchy and lineage heterogeneity is critical to understand its regenerative properties and malignancies. Here, we report that the transcription factor RUNX1 marks a specific subpopulation of proximal luminal cells (PLCs), enriched in the periurethral region of the developing and adult mouse prostate, and distinct from the previously identified NKX3.1+ luminal castration resistant cells. Using scRNA-seq profiling and genetic lineage tracing, we show that RUNX1+ PLCs are unaffected by androgen deprivation, and do not contribute to the regeneration of the distal luminal compartments. Furthermore, we demonstrate that a transcriptionally similar RUNX1+ population emerges at the onset of embryonic prostate specification to populate the proximal region of the ducts. Collectively, our results reveal that RUNX1+ PLCs is an intrinsic castration-resistant and self-sustained lineage that emerges early during prostate development and provide new insights into the lineage relationships of the prostate epithelium.

developmental biology↗