Back

AI-Driven Plasma Denaturation Profiling for Multi-Cancer Detection

Tsvetkov, P. O.; Eyraud, R.; Ayache, S.; Baksheeva, V.; Bertucci, A.; Mogenet, A.; Tomasini, P.; de Rauglaudre, B.; Dahan, L.; Gaudy-Marquestre, C.; Kalidindi, S. S. S.; Buffat, C.; Dehais, C.; Astier, A.; Ouafik, L.; Gorokhova, S.; Tabouret, E.; Devred, F.

2025-03-27 oncology
10.1101/2025.03.26.25324680 medRxiv
Show abstract

Many cancers cannot be detected early due to lack of effective disease biomarkers, leading to poor prognosis. We applied an existing biophysical technology nanoDSF in a novel way to answer this unmet biomedical need. We developed a breakthrough digital biomarker method for cancer detection based on AI-classification of plasma denaturation profiles (PDPs) obtained by nanoDSF technology. PDPs from 300 plasma samples from patients with melanoma, brain, digestive or lung cancers were automatically distinguished from healthy profiles with an accuracy of 94%. Moreover, our method was able to distinguish different types of cancers from each other with an accuracy of 80%, making it an effective way to help cancer diagnosis and monitoring. Our technology thus paves the way for a long-sought multi-cancer early detection (MCED) test that is blood-based, cost-effective and easy-to-implement in any clinical setting.

Matching journals

The top 7 journals account for 50% of the predicted probability mass.

1
Nature Communications
○ 5641 papers in training set
Top 13%
14.7%
Similar papers in this journal
2
Cell Reports Methods
○ 165 papers in training set
Top 0.1%
11.6%
Similar papers in this journal
3
npj Precision Oncology
○ 53 papers in training set
Top 0.2%
6.6%
Similar papers in this journal
4
ACS Nano
● 113 papers in training set
Top 0.3%
6.6%
Similar papers in this journal
5
Scientific Reports
○ 3612 papers in training set
Top 20%
4.7%
Similar papers in this journal
6
iScience
○ 1154 papers in training set
Top 4%
4.2%
7
Communications Medicine
○ 113 papers in training set
Top 0.5%
3.9%
50% of probability mass above
8
Cell Reports Medicine
○ 153 papers in training set
Top 1%
3.2%
9
Cancer Cell
○ 42 papers in training set
Top 0.4%
3.1%
10
EMBO Molecular Medicine
○ 95 papers in training set
Top 0.4%
2.6%
11
eLife
● 5828 papers in training set
Top 43%
2.4%
12
Molecular Cancer
○ 16 papers in training set
Top 0.1%
2.1%
13
Communications Biology
○ 993 papers in training set
Top 11%
2.1%
14
Clinical Chemistry
◐ 22 papers in training set
Top 0.1%
2.1%
15
Analytical Chemistry
● 218 papers in training set
Top 1%
1.9%
16
Genome Medicine
○ 183 papers in training set
Top 3%
1.7%
17
npj Digital Medicine
○ 118 papers in training set
Top 2%
1.6%
18
Nucleic Acids Research
◐ 1281 papers in training set
Top 10%
1.4%
19
Heliyon
○ 152 papers in training set
Top 4%
1.4%
20
Proceedings of the National Academy of Sciences
● 2444 papers in training set
Top 33%
1.3%
21
Cancers
○ 213 papers in training set
Top 4%
1.1%
22
Nature Cancer
○ 39 papers in training set
Top 1%
1.0%
23
eBioMedicine
○ 183 papers in training set
Top 5%
1.0%
24
Biosensors and Bioelectronics
○ 57 papers in training set
Top 0.7%
1.0%
25
Clinical Cancer Research
● 64 papers in training set
Top 2%
0.8%
26
Nature Biotechnology
○ 172 papers in training set
Top 4%
0.8%
27
Angewandte Chemie International Edition
○ 93 papers in training set
Top 2%
0.6%
28
Small Methods
○ 29 papers in training set
Top 1.0%
0.6%

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.