B

bioinformatics

OTP, One Touch Pipeline, Documentation at https://one-touch-pipeline.gitlab.io/otp/

Splicing analysis: Extract from mapped RNA-Seq-reads information on intron removal-order for exons genome-wide, and estimate their PSI values (percent-spliced-in) and PIR values (percent-intron-retention) of their flanking introns.

Armadillo: fast C++ library for linear algebra (matrix maths) & scientific computing - https://arma.sourceforge.net

Common Workflow Language - computational workflows @ UNLOCK

Materials on various sections in Computer Science (CS). 🎓

An implementation of Bayesian latent class model to estimate assays' performance with observed assay results, and latent true disease status.

A bioinformatic pipeline for identifying giant viruses and Preplasmiviricota viruses in metagenomic data.

🔬 Robust ML model selector with 95% CI guarantee for medical AI | Keratoconus detection achieving 84.3% recall, 3× variance reduction | Python/XGBoost | MIT License | Published research implementation 🏥📊

This repository provides a curated collection of datasets released for exploratory analysis, research, and reproducibility purposes.

The datasets included here are derived from public and/or processed sources and are published to support transparency, data reuse, and downstream analytical workflows such as exploration, feature engineering, and biomarker research.

Little utilities to work with fasta files.

A nextflow workflow to find Gene-Protein-Reaction relations

A workflow to identify gene-protein-reaction relations in Common Workflow Language

Software to compute the melting temperature of nucleic acid duplexes

Automated drug repurposing workflow for rare diseases – using Flask, Monarch API, DGIdb API and XGboost.

BioInterface is a Biopython based package that extracts Protein-DNA interfaces in a PDB structures.

PDBNucleicAcids is a Biopython based package that constructs and represent all nucleic acids in a PDB structure, with a special focus on base-pair representation.

SeqExtract searches annotated genomes for keywords and extract corresponding fasta records

Bioinformatics pipeline for LONELY gene family analysis across plant species

This project classifies brain cancer using gene expression data. It includes preprocessing, class balancing, feature selection, and training models (Random Forest, XGBoost, SVM) in pipelines to compare performance to better insights in biomedical informatics and cancer research.

A simple bash script to install bioinformatics tools that require x86_64 architecture.