Back to Programs

Science and medicine

Wellcome Sanger Tree of Life

Genome analysis for all species

javascriptnextflowpythonrustcloudmachine learningnlp

Participation history

3 GSoC years

2025

4 projects

Official year page

Building a Machine Learning Taxon Classifier for Malaria Mosquitoes

Project with MalariaGEN focuses on building a machine-learning tool to classify species of Anopheles mosquitoes (the main carriers of malaria) using...

Implementing a user interface to KinFin for interactive exploration of protein clustering data.

KinFin is a powerful tool for protein clustering analysis, but its current command-line interface limits accessibility and ease of use. This project...

Cloud-Native Tools for Detecting Novel Insecticide Resistance in Malaria Mosquitoes

This project develops cloud-native tools to detect novel insecticide resistance in African malaria mosquitoes. Current PLINK-based methods are...

Nextflow Pipelines for Variant Analyses

This project developed scalable Nextflow pipelines for variant analyses across diverse eukaryotic genomes. The workflows support calling germline and...

2024

3 projects

Official year page

Integrating KinFin Proteome Cluster analyses into Genome Browsing environments

The project aims to integrate KinFin, a tool for analysing protein family clusters, into genome browsing environments like Ensembl and GenomeHubs....

Natural language search across the tree of life (GoaT NLP)

The Tree of Life project at the Wellcome Sanger Institute contributes to the Earth BioGenome Project (EBP), aiming to sequence genomes of all Earth's...

Pathogen focused multiple mapping Nextflow pipeline

This proposal aims to address the dated codebase of the existing multiple_mappings_to_bam.py pipeline in pathogen genomics by developing a new...

2022

1 project

Official year page

Conversion of the BlobToolKit pipeline to Nextflow

The BlobToolKit, implemented with Snakemake, is a pipeline designed to obtain quality metrics for eukaryotic genome assemblies. BlobToolKit is also...