DANCE: a deep learning library and benchmark platform for single-cell analysis
ESICCC: A systematic computational framework for evaluation, selection and integration of cell-cell communication inference methods
Source code, notebooks, and documentation of Crecerelle, a probabilistic deep learning framework for learning cell embeddings from single-cell gene expression and alternative splicing-induced transcript usage. Please read our accompanying paper for details.
This project explores single-cell RNA sequencing (scRNA-seq) data using advanced machine learning techniques. By applying dimensionality reduction and graph-based models, we analyze high-dimensional scRNA-seq data to uncover cellular heterogeneity and reveal underlying biological processes at the single-cell level.
Predicting nab-paclitaxel and pembrolizumab response in early-stage HR+ breast cancer using unsupervised ML and scRNA-seq to identify immune cell clusters and predictive transcriptomic biomarkers.
Uses clustering methods, tree edit distance, maximum likelihood based tree inference techniques to construct trees of tumor progression history from single cell RNA sequencing datasets
Benchmarking AE, VAE, and scVI autoencoders to predict optimal latent dimension from cell-type complexity (K) in single-cell RNA-seq, using a trust-aware evidence framework across 5 curated datasets from PBMC to atlas-scale.
Pretrained scRNA-seq toolkit for generating cell embeddings and depth-enriched gene expression directly from raw UMI counts.
scRNA-seq and machine learning framework for EMT state classification in HGSOC using XGBoost, AUCell, CytoTRACE2, and pseudotime analysis.
This toolkit provides Python code for preprocessing, quality control, clustering, and visualization of single-cell RNA sequencing data using Scanpy. Ideal for deep insights into cell populations and gene expression.
This repository enables the reproducible analysis of an important developmental neuroscience dataset on hypothalamus neuron differentiation. It performs quality control, clustering, trajectory analysis, and identification of marker genes to characterize the differentiation trajectories of glutamatergic and GABAergic Onecut3+ neuronal subtypes.
A personal archive organizing my study notes and foundational codes for computational medicine and AI.
Repository of the master project in Bioinformatics at Lund University
A high-resolution single-cell computational pipeline evaluating T-cell exhaustion, immunosuppressive trajectories, and manifold learning within the solid tumor microenvironment.
Collection of scripts generated in the analysis of sex and gender difference in the human brain transcriptome at single-cell level
Retinal ganglion cells regeneration in 2 days post optic nerve crush retina | Lydia Tai | Dong Feng Chen Lab collaboration | Schepens Eye Research Institute, Mass General Hospital, Harvard Medical School
Systematic analysis of WLS (GPR177) expression in human Dental Pulp Stem Cells using public single-cell RNA sequencing datasets
To associate your repository with the single-cell-rna-sequencing topic, visit your repo's landing page and select "manage topics."