OverviewThis repository contains the code and processed datasets for the manuscript: “Graph convolutional network model of CD4+ T cells provides an optimal single-cell clock for human age prediction”.This study demonstrates that utilizing single-cell Graph Convolutional Networks (scGCN) with gene-gene interaction graphs from CD4+ T cells achieves optimal age prediction performance compared to traditional machine learning models. Project WorkflowPlease run the scripts in the following folders sequentially: 01_seurat_analysis: Single-cell data preprocessing using Seurat (quality control, normalization, and cell-type extraction). 02_graph_construction: Building gene-gene interaction graphs based on the STRING database. 03_age_prediction_analysis: Training and comparing five distinct age prediction models across different cell types.
This deposit contains the field data, synthetic training datasets, trained network weights and analysis code supporting the article "Physics-informed neural network inversion of electrical resistivity tomography data: amortized optimization with field validation in the Moroccan M…
Data and Code to reproduce results in paper "A Systematic Literature Review on Graph-Based Models in Credit Risk Assessment" This repository contains the necessary codes to reproduce results in the paper: Baals, L. J., Liu, Y., Osterrieder, J., & Hadji-Misheva, B. (2025). A Syste…
The dataset was acquired from tests of a commercial LG INR18650 MJ1 lithium-ion cell (nominal capacity 3500 mAh).For equivalent-circuit parameterization, we used voltage responses to rectangular galvanostatic current pulses with durations from 9 to 144 s and amplitudes of approxi…
Machine Learning (ML) predictions of cement and concrete quality and subsequent data-driven mixture optimization has been advertised for almost three decades. However, supervised ML leverages correlations, not causal relationships. Aiming for hybrid models, we derive the first ca…