Scientific Services
We help scientists turn data into discovery through powerful software, databases, and machine learning pipelines tailored for omics analysis.
🧬 Bioinformatics
We developed analysis pipelines for phosphoproteomics using fuzzy clustering and visualization tools. This example from our publication "Phosphoproteome dynamics of Saccharomyces cerevisiae under heat shock and cold stress" highlights temporal clustering of phosphosites and stress response dynamics.
Expertise: proteomics, time-series clustering, fuzzy c-means, GO enrichment, visualization.
📈 ML & Quality Control
We built MHCvalidator, a machine-learning tool for assessing peptide identifications in immunopeptidomics. The model was trained on curated datasets to detect low-confidence hits and flag potential contaminants.
Expertise: SVMs, peptide classification, confidence estimation, quality scoring.
🗄️ Scientific Databases
Our live Django-based database sysquan.com provides a search and visualization platform for targeted proteomics quantification data.
Expertise: Django, PostgreSQL, peptide mapping, quantitative data linking.
🌐 Web Applications
We built MhcVizPipe — a standalone quality control web tool for immunopeptidomics workflows. It's designed for fast review of large-scale dataset integrity and class I/II distribution.
Expertise: Streamlit, standalone apps, PSM visualization, allele distribution plots.
🛠️ Pipeline & Server Setup
Need help setting up a scalable analysis environment? We deploy pipelines to Linux VPS (e.g. Hetzner, OVH), install Conda/Docker environments, configure automated runs, and integrate backup systems.
🧪 Custom Scientific Projects
We bring >15 years of experience across mass spectrometry, bioinformatics, and AI-driven data analysis. I’ve worked on time-series phosphoproteomics, immunopeptidomics benchmarking, MRM panel design, and multi-cohort ML pipelines.