OUR DISCOVERY TECHNOLOGY

Logo background removed.png

COMPASS

Mass Spec Method + Proprietary AI Software

Magellan has licensed a mass spec protocol from a research university, and paired it with an internally developed AI software.  Together, we call this technology COMPASS. Both parts of this technology are explained below. 

HIGH-CONTENT INFORMATION IN  SERUM: Our unique data source

Magellan isolates and anazlyes the low molecular weight (LMW) fraction of serum, where we’ve found over 120K distinct peptides, lipids, small molecules, and proteolytic fragments of proteins.  The contents are present as a result of cellular activities, which dynamically change due to age, disease, and future onset of disease. 

 

As health status alters cellular processes, expression of biomolecule products changes. Our COMPASS technology was developed to detect and exploit these expression changes.  The analysis of the LMW fraction of sera is technically challenging, but Magellan has licensed a sample prep and Mass Spec method that allows us to do so. 

Low Molecular Weight Fraction:

>120,000 potential markers

The advantages of COMPASS:

  • Considers a large number of unique species: >120,000 peptides, small molecules, and lipids

  • Unlike DNA, whose information if fixed. The information analyzed by COMPASS is dynamic and reflects changing health status

  • COMPASS is agnostic to biological function, allowing exploitation of biomarkers that have not been previously characterized or known to be associated with certain indications, treatments, or treatment outocomes

COMPASS Process

1.

DRAW BLOOD, PROCESS TO SERUM

Simple blood draw and conversion to serum

2.

RECOVER HIGH-INFORMATION BIOMOLECULES 

There are approximately 30 highly abundant , low-information molecules that occur more that 10 million times more frequently in serum than high-information molecules. These are removed according to Magellan's licensed protocol

3.

ANALYZE BY MASS SPECTROMETRY

Mass spectrometry identifies molecular mass (m/z) and retention time (rt) for the remaining high-information biomolecules. The result is quantitative expression data for each high-information species.

4.

INTEGRATE MASS SPEC DATA WITH PATIENT DATA

The mass-spec output is then integrate with patient health information, including treatment outcomes. We can integrate other data types, including the outcomes of other analyses.

5.

APPLY MACHINE LEARNING TO DEVELOP A PREDICTIVE MARKER SET

Our proprietary algorithms are applied to the combined data set. We deliver: 1) a list all differentially expressed species, and 2) a trained  machine learning classifier , including which specific species are critical to its decisionmaking. We can also perform molecular identification of these species, revealing biological connections.

Discovery Process

The standard approach for discovering predictive markers usually follows these steps:

 

  1. Study the biology of the condition

  2. Identify one or more molecules that are critical to the process

  3. Develop an assay for detecting the identified molecules

  4. Use the assay to try to predict the desired condition

  5. If this did not work, restart at step 1

The above process requires significant biological skill, capabilities, time, and expense

 

The Magellan approach works differently:

 

  1. Identify a set of patient the exhibit the condition or may exhibit the condition in the future, as well as a set of control patients

  2. Extract blood, produce serum and perform Magellan's mass-spec analysis on all patients

  3. Using machine learning, analyze >120,000 unique species, and develop a classifier for the desired outcome

In some cases, the identity of the markers can be elucidated by further mass-spec analysis.   

 

The Magellan method does not require an underlying understanding of the biology, is target agnostic, and is faster, less expensive than traditional approaches.

© 2018 by Magellan Bioanalytics