Back

Mechanistic modeling and machine learning identifies optimum radiotherapy schedules to prevent treatment-induced metastasis

Graser, C.; Zhou, Z.; Schürch, M.; Moorhead, G.; Dean, J.; Lin, C.; Dean, J.; Kozono, D.; Lahav, G.; Michor, F.

2025-07-05 bioinformatics
10.1101/2025.07.02.662373 bioRxiv
Show abstract

Lung cancer patients often experience increased metastasis formation after radiotherapy. However, it is incompletely understood whether radiation affects the migratory behavior of tumor cells and how altered radiotherapy schedules might mitigate this risk. To address these questions, we performed live-cell microscopy experiments to profile changes in cell migration during radiation across 12 cancer cell lines and developed a predictive computational modeling platform describing tumor volume and dissemination during radiotherapy. Using this platform, we identified optimal fractionation schedules and then performed extensive in silico clinical trials, establishing that our optimized schedules substantially reduce metastatic seeding relative to the standard of care schedule. Training transformer models on the in silico clinical trial data enabled us to recover mechanistic parameters with high accuracy, demonstrating that the features determining optimal radiotherapy can be inferred from longitudinal tumor data. Our integrative predictive approach enables the rational design of optimum clinical trials across indications.

Matching journals

The top 6 journals account for 50% of the predicted probability mass.

1
Nature Communications
○ 5641 papers in training set
Top 17%
11.4%
Similar papers in this journal
2
Scientific Reports
○ 3612 papers in training set
Top 4%
10.1%
Similar papers in this journal
3
Physics in Medicine & Biology
○ 18 papers in training set
Top 0.1%
10.1%
Similar papers in this journal
4
Bioinformatics
◐ 1204 papers in training set
Top 3%
8.1%
Similar papers in this journal
5
eLife
● 5828 papers in training set
Top 19%
6.5%
Similar papers in this journal
6
Radiotherapy and Oncology
○ 19 papers in training set
Top 0.1%
5.6%
50% of probability mass above
7
International Journal of Radiation Oncology*Biology*Physics
○ 25 papers in training set
Top 0.2%
5.3%
8
PLOS Computational Biology
● 1863 papers in training set
Top 8%
4.2%
9
Cancer Research Communications
● 51 papers in training set
Top 0.3%
3.3%
10
JCO Clinical Cancer Informatics
● 22 papers in training set
Top 0.2%
3.3%
11
iScience
○ 1154 papers in training set
Top 8%
2.9%
12
Science Advances
● 1243 papers in training set
Top 14%
2.5%
13
Communications Biology
○ 993 papers in training set
Top 12%
2.0%
14
Cancers
○ 213 papers in training set
Top 3%
1.7%
15
Cancer Research
● 130 papers in training set
Top 2%
1.5%
16
PLOS ONE
● 5266 papers in training set
Top 51%
1.2%
17
Clinical and Translational Radiation Oncology
○ 10 papers in training set
Top 0.2%
0.9%
18
NeuroImage
○ 903 papers in training set
Top 6%
0.9%
19
Medical Physics
○ 14 papers in training set
Top 0.5%
0.9%
20
Computers in Biology and Medicine
○ 128 papers in training set
Top 4%
0.9%
21
Frontiers in Oncology
○ 103 papers in training set
Top 3%
0.6%
22
European Journal of Nuclear Medicine and Molecular Imaging
○ 20 papers in training set
Top 0.2%
0.6%
23
The Annals of Applied Statistics
● 19 papers in training set
Top 0.2%
0.6%
24
Proceedings of the National Academy of Sciences
● 2444 papers in training set
Top 43%
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.