Biology subjects

Da Silva, M.

Publications and source records attributed to Da Silva, M..

3 recordsLinked to original sources

bioRxiv2025

Deep Learning Bridges Histology and Transcriptomics to Predict Molecular Subtypes and Outcomes in Muscle-Invasive Bladder Cancer

Muscle-Invasive Bladder Cancer (MIBC) is a heterogeneous disease with distinct molecular subtypes influencing prognosis and therapeutic response. However, molecular profiling through RNA sequencing remains costly, time-consuming and complicated by intratumoral heterogeneity. We developed a Deep Learning (DL) approach to infer molecular subtypes from routine histopathological slides and to evaluate its prognostic value in patients treated with neoadjuvant chemotherapy (NAC). We developed an DL-model predicting the expression of 848 subtype-associated genes from histological images of transurethral resection of bladder tumor, enabling spatial molecular subtyping at tile level. The model was trained on 297 NAC-treated patients from the VESPER clinical trial and evaluated on three independent cohorts (COBLAnCE, n=224; Saint-Louis, n=30 and TCGA, n=315), covering diverse staining protocols and scanner types. Spatial transcriptomics from six VESPER patients confirmed the spatial consistency of the inferred expression profiles. Our approach achieved a ROC AUC of 0.94 for molecular subtype prediction, with 95% of genes significantly predicted, demonstrating its ability to capture transcriptomic dysregulations from histological morphology. Predicted expression maps revealed spatially coherent patterns and intratumoral molecular heterogeneity. Importantly, tumors predicted with basal/squamous features (pure or mixed), were associated with significantly worse progression-free and overall survival after NAC (log-rank p=0.014 and 0.037, respectively). This DL-based framework enables accurate and spatially resolved inference of gene expression and molecular subtypes in MIBC without sequencing. These findings could improve patient stratification in clinical practice and support the design of more targeted clinical trials. Further validation in larger cohorts is needed before routine clinical implementation.

cancer biology↗

bioRxiv2024

Effects of conceptus proteins on endometrium and blood leukocytes of dairy cattle using transcriptome and meta-analysis

This study investigates the short and long-term effects of IFNT and PAG on the transcriptome of endometrium and blood leukocytes. Holstein heifers received intrauterine infusions of one of the following treatments: 20 mL of a 200 g/mL bovine serum albumin solution (BSA; vehicle) from day 14 to 16 of the estrous cycle (BSA), vehicle + 10 g/mL of IFNT from day 14 to 16 (IFNT3), vehicle + 10 g/mL of IFNT from day 14 to 19 (IFNT6), and vehicle + 10 g/mL of IFNT from day 14 to 16 followed by vehicle + 10 g/mL of IFNT + 5 g/mL of PAG from day 17 to 19 (IFNT+PAG). RNA-seq analysis was performed in endometrial biopsies and blood leukocytes collected after treatments. Acute IFNT signaling in the endometrium (IFNT3 vs BSA), induced differentially expressed genes (DEG) associated with interferon activation, immune response, inflammation, cell death, and inhibited vesicle transport and extracellular matrix remodeling. Prolonged IFNT signaling (IFNT6 vs IFNT3) altered gene expression related to cell invasion, retinoic acid signaling, and embryo implantation. In contrast, PAG induced numerous DEG in blood leukocytes but only 4 DEG in the endometrium. In blood leukocytes, PAG stimulated genes involved in development and TGFB signaling while inhibiting interferon signaling and cell migration. Overall, IFNT is a primary regulator of endometrial gene expression, while PAG predominantly affected the transcriptome of circulating immune cells during early pregnancy. Further research is essential to fully grasp the roles of identified DEG in both the endometrium and blood leukocytes. Graphic abstract O_FIG O_LINKSMALLFIG WIDTH=200 HEIGHT=70 SRC="FIGDIR/small/591148v1_ufig1.gif" ALT="Figure 1"> View larger version (32K): org.highwire.dtl.DTLVardef@b51110org.highwire.dtl.DTLVardef@173433dorg.highwire.dtl.DTLVardef@4368e5org.highwire.dtl.DTLVardef@19bd118_HPS_FORMAT_FIGEXP M_FIG C_FIG Main findingsO_LIAcute IFNT signaling in the endometrium activates genes involved in inflammation while inhibiting vesicle transport in cells and ECM remodeling. C_LIO_LIProlonged IFNT signaling in the endometrium regulates genes involved in cell invasion and retinoic acid signaling. C_LIO_LIPAG alter gene expression in blood leukocytes more than in endometrium and may stimulate leukocyte differentiation while inhibiting leukocyte extravasation. C_LI

physiology↗

bioRxiv2021

Benchmarking Geometric Deep Learning for Cortical Segmentation and Neurodevelopmental Phenotype Prediction

The emerging field of geometric deep learning extends the application of convolutional neural networks to irregular domains such as graphs, meshes and surfaces. Several recent studies have explored the potential for using these techniques to analyse and segment the cortical surface. However, there has been no comprehensive comparison of these approaches to one another, nor to existing Euclidean methods, to date. This paper benchmarks a collection of geometric and traditional deep learning models on phenotype prediction and segmentation of sphericalised neonatal cortical surface data, from the publicly available Developing Human Connectome Project (dHCP). Tasks include prediction of postmenstrual age at scan, gestational age at birth and segmentation of the cortical surface into anatomical regions defined by the M-CRIB-S atlas. Performance was assessed not only in terms of model precision, but also in terms of network dependence on image registration, and model interpretation via occlusion. Networks were trained both on sphericalised and anatomical cortical meshes. Findings suggest that the utility of geometric deep learning over traditional deep learning is highly task-specific, which has implications for the design of future deep learning models on the cortical surface. The code, and instructions for data access, are available from https://github.com/Abdulah-Fawaz/Benchmarking-Surface-DL.

neuroscience↗