A collection of UNet and hybrid architectures in PyTorch for 2D and 3D Biomedical Image segmentation

Image-to-image regression with uncertainty quantification in PyTorch. Take any dataset and train a model to regress images to images with rigorous, distribution-free uncertainty quantification.

Machine-learning based pipeline relying on LambdaMART currently used in PubMed for relevance (Best Match) searches

Ultimate ATAC-seq Data Processing & Quantification Workflow. A Snakemake implementation of the BSF's ATAC-seq Data Processing Pipeline extended by downstream quantification and annotation steps using bash and Python.

Knee Osteoarthritis Analysis with X-ray Images using CNN

A Python library for biomedical statistical shape and appearance modelling.

A Snakemake workflow for performing genomic region set and gene set enrichment analyses using LOLA, GREAT, GSEApy, pycisTarget and RcisTarget.

Unsupervised domain adaptation method for relation extraction

Analysis code for knowledge discovery project

Deep learning model of depression detection from activity sensor data

A Snakemake workflow for easy visualization of genome browser tracks of aligned BAM files (e.g., RNA-seq, ATAC-seq, scRNA-seq, ...) powered by the wrapper gtracks for the package pyGenomeTracks, and IGV-reports.

Toolkit for analyzing physiologic data collected via Biopac AcqKnowledge software.

A Snakemake workflow to split, filter, normalize, integrate and select highly variable features of count matrices resulting from experiments with sequencing readout (e.g., RNA-seq, ATAC-seq, ChIP-seq, Methyl-seq, miRNA-seq,...) including diagnostic visualizations.

Biomedical Feature Selection for Machine Learning Models

A text summarization framework to identify major opinions from healthcare text

NLP Term Project for Autumn 2019. Named Entity Recognition in Biomedical Corpus.

Draw periodogram of real EEG data

Named Entity Recognition using BERT

EEG spectrum mean of 84 records