Discovery Technology | Magellan BA, Inc.

OUR DISCOVERY TECHNOLOGY

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.

Why is COMPASS needed?

Scientific research technologies often go through a cycle similar to the one described below. Advancements in hardware lead to larger amounts of data, which overwhelm current software's capacity to effectively analyze. Eventually, computational tools are developed to handle and analyze the new, larger data sets. This is when the full value of the research technology is realized.

Proteomics is stuck in the 'Information overload' phase. Mass-spec proteomics researchers throw out the majority of the data produced due to limitations in data analysis methods.

Magellan's COMPASS technology has been developed to alleviate this information overload, and harness the mass spec's true potential. Thanks to COMPASS, Magellan is analyzing proteomic data on an unprecedented scale.

Advantages of COMPASS

Proteomics at a large scale: >2.5M data points/sample

Unlike DNA, whose information if fixed, the proteomic analysis 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 outcomes

As Magellan's proteomic dataset and analytics grow, so too will its ability to detect, stage, predict, and guide therapy for various diseases - all from a single assay

COMPASS Process

DRAW BLOOD, PROCESS TO SERUM

Simple blood draw and conversion to serum

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

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

INTEGRATE MASS SPEC DATA WITH PATIENT DATA

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

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 decision making. 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:

Study the biology of the condition
Identify one or more molecules that are critical to the process
Develop an assay for detecting the identified molecules
Use the assay to try to predict the desired condition
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:

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
Extract blood, produce serum and perform Magellan's mass-spec analysis on all patients
Using machine learning, analyze >2.5M 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, faster, and less expensive than traditional approaches.