DISCOVER

Proteomic biomarkers have the power to assess one’s current biological state, unlike genomics which can only provide a static snapshot of what could be - butterfly or caterpillar. We apply machine learning solutions to large biological datasets to discover relevent markers for the current biological state.



Product Summary

SoCal Bioinformatics provides end-to-end services supporting the entire proteomic biomarker discovery pipeline, from raw data processing through to predictive modeling to discover novel biomarker panels.


Motivation

The data pipeline for proteomic biomarker discovery is complex and often difficult to manage, particularly for firms that don't have in-house expertise in this area. To this end, SoCal Bioinformatics has developed a robust pipeline for the entire proteomic biomarker discovery process built from a decade of experience in the field. Read more here.


Process

Combine #

Aggregate experiments into a single study. Align molecular features by LC, normalize instrument signal intenisty and dynamic range across the study, cluster molecular features, and infer peptide IDs by cluster association.

Explore #

Explore predictive models using rigorous validation methods. Read more about how we avoid pitfalls and apply innovations.

Discover #

Produce candidate top performing biomarker panels, models and performance estimates.


CONSULT


Product Deliverable

Password protected account to access HDF5 files for downloading, and or CSV table extracts, supporting analysis reports, final predictive models and the associated biomarker panels.