Resources & Software
The repositories behind our softwares are open source and available through GitHub.
Repositories
BINN
The BINN-package allows you to create a sparse neural network from a pathway and input file. The examples presented in docs use the Reactome pathway database and a proteomic dataset to generate the neural network. It also allows you to train and interpret the network using SHAP.
DPKS
DPKS is a comprehensive python library for statistical analysis and explainable machine learning for omics data. DPKS allows for easily configurable and reproducible analysis pipelines that will simplify workflows and allow for exploration. Additionally, it exposes advances explainable machine learning techniques with a simple API allowing them to be used by non-machine learning practicioners in the field.
gps
This is a python package for scoring SWATH-MS data using static generalizable machine learning models trained on large curated datasets. Current support is for OpenSwath, but could be expanded to other tools quite easily.
Datasets
Septic AKI
197 blood plasma DIA samples. Patients suffering from septic acute kidney injury. Divided into 2 PRIDE repositories.