Biology subjects

Cantore, T.

Publications and source records attributed to Cantore, T..

2 recordsLinked to original sources

bioRxiv2024

Path2Space: An AI Approach for Cancer Biomarker Discovery Via Histopathology Inferred Spatial Transcriptomics

Spatial transcriptomics (ST) is transforming our understanding of tumor heterogeneity by enabling high-resolution, location-specific mapping of gene expression across tumors and their microenvironment. However, the associated high cost of the assay has limited cohort size and hence large-scale biomarker discovery. Here we present Path2Space, a deep learning approach that predicts spatial gene expression directly from histopathology slides. Trained on substantial breast cancer ST data, it robustly predicts the spatial expression of over 4,300 genes in independent validations, markedly outperforming existing ST predictors. Path2Space additionally accurately infers cell-type abundances in the tumor microenvironment (TME) based on the inferred ST data. Applied to more than a thousand breast tumor histopathology slides from the TCGA, Path2Space characterizes their TME on an unprecedented scale and identifies three new spatially-grounded breast cancer subgroups with distinct survival rates. Path2Space-inferred TME landscapes enable more accurate predictions of patients response to chemotherapy and trastuzumab directly from H&E slides than those obtained by existing established sequencing-based biomarkers. Path2Space thus offers a transformative, fast and cost-effective approach to robustly delineate the TME directly from their histopathology slides, facilitating the development of spatially-grounded biomarkers to advance precision oncology.

cancer biology↗

bioRxiv2022

Bladder cancer organoids as a functional system to model different disease stages and therapy response

Bladder Cancer (BLCa) inter-patient heterogeneity is considered the primary cause of tumor reoccurrence and treatment failure, suggesting that BLCa patients could benefit from a more personalized treatment approach. Patient-derived organoids (PDOs) have been successfully used as a functional model for predicting drug response in different cancer types. In our study, we established BLCa PDO cultures from different BLCa stages. BLCa PDOs preserve the histological and molecular heterogeneity of the parental tumors, including their multiclonal genetic landscapes. BLCa PDOs consistently share key genetic alterations detected in parental tumors, mirroring tumor evolution in longitudinal sampling. Our drug screening pipeline was implemented using BLCa PDOs, testing both standard-of-care and additional FDA-approved compounds for other solid tumors. Integrative analysis of drug response profiles with matched PDO genomic analysis was used to determine enrichment thresholds for candidate markers of therapy resistance and sensitivity. By assessing the clinical history of longitudinally sampled cases, the clonal evolution of the disease could be determined and matched with drug response profiles. In conclusion, we have developed a clinically relevant pipeline for drug response profile assessment and discovery of candidate markers of therapy resistance.

cancer biology↗