AI4OP

AI4OP is a 3 year project (2020-2023) funded by the plan Cancer via the INSERM-MIC program.

The objective of this project is to create a universal and non-invasive method to help diagnose cancers. The proposed method is based on the existence of unique plasma denaturation profiles (signatures) for different cancers. The plasma denaturation profile represents the total denaturation curve (under the influence of temperature) of its constituent proteins. Due to homeostasis, the plasma denaturation profiles of healthy individuals do not vary significantly. However, due to disease, the composition of the blood or the thermal stability of circulating proteins may change, thus altering the plasma denaturation profile.

In the context of the project presented, we plan to demonstrate : (1) that nanoDSF can unambiguously distinguish several cancers using developed machine learning methods from a simple plasma sample; (2) that the new nanoDSF instrument (Tycho) is as sensitive as the research oriented Prometheus NT.Plex for determining plasma denaturation profiles as an aid to diagnosis.

In order to achieve these objectives, we work closely with oncologists to select cohorts of blood plasma from patients different types of cancers, including melanoma, lung, colorectal cancer, gliobastoma, acromegaly, etc., as well as from healthy donors. We determine the denaturation profiles for all plasma samples using the PEAQ-DSC instruments (our reference) and Prometheus NT.Plex and Tycho instruments. The profiles generated by each tool are stored in a developed in this project database with web interface and automatically classified using machine learning methods design in the frame of the proposed project.

The methodology of the project can be divided in four parts:

1. Clinical (plasma collection)
2. Biophysical (obtaining plasma denaturation profiles)
3. Mathematical (development/adaptation algorithms of machine learning)
4. IT (creation of software tool that allow to join all parts together)