Biology subjects

Quintela-Fandino, M.

Publications and source records attributed to Quintela-Fandino, M..

5 recordsLinked to original sources

bioRxiv2025

Generative AI Enables Breast Cancer Genomic Subtype Prediction from Histology Images

Breast cancer subtyping is essential for precision oncology, influencing prognosis, treatment selection, and clinical trial design. The Integrative Subtype Classification (IC) categorizes breast tumors into groups with distinct long-term outcomes based on genomic and correlated transcriptomic features. This method relies on sequencing data, which, despite decreasing costs, is not always available in research or clinical settings. Here we introduce PATH-IC, a computational pathology model that predicts ER+ breast cancer IC subtype risk of relapse categories from routine histology data. We enhance the current state-of-the-art computational pathology approach with BERGERON, which leverages generative AI to correct class imbalance and reduce overfitting, showing that synthetic data improves PATH-ICs performance by the equivalent of 41% more real training samples. PATH-IC achieves a testing AUROC of 0.814, with predictions correlating to Oncotype DX scores and long-term relapse risk. Using attention-based model interpretation and CRAWFORD, a novel embedding-to-image foundation model, we demonstrate that PATH-IC identifies expected tumor microenvironment patterns for IC subtypes and highlights heterochromatin condensation as a key feature of high-risk tumors. Matched single-cell spatial transcriptomics confirm IC subtype-specific gene expression patterns identified by PATH-IC, including active metabolic, proliferative, and proteostasis pathways in the high-risk group. PATH-IC advances computational pathology through generative AI, enabling subtype inference from histopathology data.

cancer biology↗

bioRxiv2025

A breast tissue-specific epigenetic clock provides accurate chronological age predictions and reveals de-correlation of age and DNA methylation in tumor-adjacent and tumor samples

Epigenetic clocks have been widely used to estimate biological age across various tissues, but their accuracy in breast tissue remains suboptimal. Pan-tissue models such as Horvaths and Hannums clocks, perform poorly in predicting chronological age in breast tissue, underscoring the need for a tissue-specific approach. In this study, we introduce a Breast Tissue-specific Epigenetic Clock (BTEC), developed using DNA methylation data from 553 healthy breast tissue samples across seven different studies. BTEC significantly outperformed pan-tissue clocks, demonstrating superior correlation with chronological age (r=0.88) and lower prediction errors (MAE=3.27 years) without requiring for dataset-specific regressions adjustments. BTECs chronological age predictions for tumor-adjacent samples showed distortions, with an average deviation of -1.76 years, which was even more pronounced in tumor samples, where the average difference between predicted and chronological age was -12.29 years. When analyzed by molecular subtype, the distortion was greater in the more aggressive HER2+ and TNBC tumors compared to HR+ tumors. The probes used by BTEC were associated with known oncogenes, genes involved in estrogen metabolism, cadherin binding and fibroblast growth factor binding. Despite the general rejuvenation observed in tumor tissue compared to normal breast, the correlation between BTECs predictions and cancer-related survival indicated that TNBC tumors with increased epigenetic ages had significant lower survival.

cancer biology↗

bioRxiv2025

QUICHE reveals structural definitions of anti-tumor responses in triple negative breast cancer

While recent innovations in spatial biology have driven new insights into how tissue organization is altered in disease, interpreting these datasets in a generalized and scalable fashion remains a challenge. Computational workflows for discovering condition-specific differences in tissue organization typically rely on pairwise comparisons or unsupervised clustering. In many cases, these approaches are computationally expensive, lack statistical rigor, and are insensitive to low-prevalence cellular niches that are nevertheless highly discriminative and predictive of patient outcomes. Here, we present QUICHE - an automated, scalable, and statistically robust method that can be used to discover cellular niches differentially enriched in spatial regions, longitudinal samples, or clinical patient groups. In contrast to existing methods, QUICHE combines local niche detection with interpretable statistical modeling using graph neighborhoods to detect differentially enriched cellular niches, even at low prevalence. Using in silico models and spatial proteomic imaging of human tissues, we demonstrate that QUICHE can accurately detect condition-specific cellular niches occurring at a frequency of 0.5% in fewer than 20% of patient samples, outperforming the next best method which required a patient prevalence of 60% for detection. To validate our approach and understand how tumor structure influences recurrence risk in triple negative breast cancer (TNBC), we used QUICHE to comprehensively profile the tumor microenvironment in a multi-center, spatial proteomics cohort consisting of primary surgical resections, analyzing over 2 million cells from 314 patients across 5 medical centers. We discovered cellular niches that were consistently enriched in key regions of the tumor microenvironment, including the tumor-immune border and extracellular matrix remodeling regions, as well as niches statistically-associated with patient outcomes, including recurrence status and recurrence-free survival. The majority of differential niches (74.2%) were specific to patients that did not relapse and formed a robust interconnected network enriched in monocytes, macrophages, APCs, and CD8T cells with tumor and stroma cells. In contrast, the interaction network for patients that relapsed was notably sparse and enriched in B cells, CD68 macrophages and neutrophils. We validated these findings using two independent cohorts, observing similar cellular interactions and predictive power. Collectively, these results suggest that salient, generalized profiles of productive anti-tumor immune responses are defined by a network of structural engagement between innate and adaptive immunity with tumor and stromal cells, rather than by any single specific cell population. We have made QUICHE freely available as a user-friendly open-source Python package at https://github.com/jranek/quiche.

bioinformatics↗

bioRxiv2024

Epigenetic age prediction drifts resulting from next-generation methylation arrays

BackgroundEpigenetic clocks based on DNA methylation data are routinely used to obtain surrogate measures of biological age and estimate epigenetic age acceleration rates. These tools are mathematical models that rely on the methylation state of specific sets of CpG islands quantified using microarrays. The set of CpG islands probed in the microarrays differed between the models. Thus, as new methylation microarrays are developed and older models are discontinued, existing epigenetic clocks might become obsolete. Here, we explored the effects of the changes introduced in the new DNA methylation array from Illumina (EPICv2) on existing epigenetic clocks. MethodsWe compiled a whole-blood DNA methylation dataset of 10835 samples to test the performance of four epigenetic clocks on the probe set of the EPICv2 array. We then used the same data to train a new epigenetic age prediction model compatible across the 450k, EPICv1 and EPICv2 microarrays. We compiled a validation dataset of 2095 samples to compare our model with a state-of-the-art epigenetic clock. Using two datasets with repeated samples from the same subjects, we computed an estimate of the contribution of technical noise and intra-subject variation to the variation of epigenetic age predictions from each of the models tested. We used a dataset of cancer survivors who had undergone different types of therapy, a dataset of breast cancer patients and controls, and a dataset from an exercise-based interventional study to test the ability of our model to detect alterations in epigenetic age acceleration. ResultsWe found that the results of the four epigenetic clocks tested are significantly distorted by the absence of specific probes in the EPICv2 microarray, causing an average difference of up to 25 years. We developed an epigenetic age prediction model compatible with the 450k, EPICv1 and EPICv2 microarrays. Our model produced highly accurate chronological age predictions that were comparable to those of a state-of-the-art epiclock. We obtained estimates for the variation of epigenetic age acceleration on normal, non-pathological populations associated with each of the models tested. These parameters provide thresholds to evaluate the relevance of epigenetic age alterations. In all cases, the estimated technical noise and intra-subject variability were smaller than the population-based epigenetic age prediction variability. Finally, we used our new models to reproduce previous results showing increased epigenetic age acceleration in cancer patients and in survivors who had been treated with radiation therapy, as well as a lack of changes as a result of exercise-based interventions. ConclusionOur work demonstrated that existing epigenetic clocks need to be updated to be applicable to data generated with the new EPICv2 microarray, which has phased out the 450k and EPICv1 models. To overcome this technical hurdle, we developed a new model that translates the capabilities of state-of-the-art epigenetic clocks to the new EPICv2 platform and is cross-compatible with the 450k and EPICv1 microarrays. Our characterization of the variation of epigenetic age predictions provides useful metrics to contextualize the biological relevance of epigenetic age alterations. The analysis of data from subjects influenced by radiation, cancer and exercise-based interventions shows that despite being good predictors of chronological age, neither a pathological state like breast cancer, a hazardous environmental factor (radiation) or exercise (a beneficial intervention) caused significant changes in the values of the "epigenetic age" determined by these first-generation models.

molecular biology↗

bioRxiv2021

RANK is an independent biomarker of poor prognosis in estrogen receptor-negative breast cancer and a therapeutic target in patient-derived xenografts

Despite strong preclinical data, the therapeutic benefit of the RANKL inhibitor denosumab in BC patients, beyond its bone-related effects, is unclear. Here, we investigated the prognostic value of RANK expression and its functionality in human BC. We analyzed RANK and RANKL expression in more than 1500 BC cases (777 being estrogen receptor-negative (ER-)) from four independent cohorts. We confirmed that RANK is more frequently expressed in ER- tumors, but it is also found in a subset of ER+ tumors. In ER- BC, RANK expression was independently associated with poor outcome, especially in postmenopausal patients and those who received adjuvant chemotherapy. Gene expression analyses unraveled distinct biology associated with RANK in relation to ER expression and menopause, and evidenced enhanced RANK activation in ER- postmenopausal tumors, together with regulation of metabolic pathways. Functional studies and transcriptomic analyses in ER- RANK+ patients-derived orthoxenografts demonstrated that activation of RANK signaling pathway promotes tumor cell proliferation and stemness, and regulates multiple biological processes including tumor immune surveillance and metabolism. Our results demonstrate that RANK expression is an independent poor prognosis biomarker in postmenopausal ER- BC patients and support the rational of using RANK pathway inhibitors in combination with chemotherapy in ER- BC.

cancer biology↗