Back

Machine learning-based image analysis of Parkinson's disease iPS-derived neurons predicts genotype and reveals mitochondria-lysosome abnormalities

Li, Y.; Powell, M.; Chedid, J.; Sutharsan, R.; Garrido, A. L.; Abu-Bonsrah, D.; Pavan, C.; Fraser, T.; Ovchinnikov, D.; Zhong, M.; Davis, R.; Strbenac, D.; Johnston, J. A.; Thompson, L. H.; Kirik, D.; Parish, C. L.; Halliday, G. M.; Sue, C. M.; Dzamko, N.; Wali, G.

2026-01-29 neuroscience
10.64898/2026.01.28.702423 bioRxiv
Show abstract

Mitochondrial and lysosomal dysfunction are central features of Parkinsons disease (PD) across major genetic forms including PRKN, SNCA, and LRRK2. We applied cell morphomics, a machine-learning-based framework combining high-content imaging with quantitative feature extraction, to analyse mitochondrial and lysosomal morphology at single-cell resolution in iPS cell-derived cortical neurons from PD patients and healthy controls (13 lines total). Supervised machine-learning models distinguished PD neurons from controls with high accuracy (AUC = 0.87) and reliably separated individual genotypes. Feature importance and attribution analysis revealed genotype-specific organelle biases, with mitochondrial features dominating classification in PRKN neurons, balanced mitochondrial and lysosomal contributions in SNCA neurons, and a greater lysosomal contribution in LRRK2 neurons. Multi-class models retained strong performance, and findings were reproduced across two independent laboratories using different dyes and imaging conditions. These results demonstrate that morphomics provides a robust and scalable framework to quantify genotype-specific organelle abnormalities in PD neurons and supports its application for cellular stratification and biomarker discovery.

Matching journals

The top 2 journals account for 50% of the predicted probability mass.

1
npj Parkinson's Disease
89 papers in training set
Top 0.1%
38.4%
2
Brain
154 papers in training set
Top 0.3%
15.0%
50% of probability mass above
3
Nature Communications
4913 papers in training set
Top 35%
4.4%
4
Acta Neuropathologica
51 papers in training set
Top 0.2%
4.0%
5
Advanced Science
249 papers in training set
Top 5%
3.7%
6
Brain Communications
147 papers in training set
Top 1%
1.9%
7
EMBO Molecular Medicine
85 papers in training set
Top 2%
1.5%
8
Movement Disorders
62 papers in training set
Top 0.7%
1.5%
9
Scientific Reports
3102 papers in training set
Top 63%
1.4%
10
Nature Aging
51 papers in training set
Top 1%
1.2%
11
Annals of Neurology
57 papers in training set
Top 1%
1.2%
12
Cell Reports
1338 papers in training set
Top 28%
1.2%
13
eBioMedicine
130 papers in training set
Top 2%
1.2%
14
eLife
5422 papers in training set
Top 50%
1.1%
15
Science Translational Medicine
111 papers in training set
Top 4%
1.0%
16
Alzheimer's & Dementia
143 papers in training set
Top 2%
1.0%
17
Neurobiology of Disease
134 papers in training set
Top 4%
0.9%
18
Neuropathology and Applied Neurobiology
14 papers in training set
Top 0.5%
0.9%
19
Communications Biology
886 papers in training set
Top 20%
0.8%
20
NeuroImage: Clinical
132 papers in training set
Top 3%
0.8%
21
Science Advances
1098 papers in training set
Top 28%
0.8%
22
Experimental Neurology
57 papers in training set
Top 1%
0.8%
23
Molecular Neurodegeneration
49 papers in training set
Top 0.9%
0.8%
24
Neurobiology of Aging
95 papers in training set
Top 2%
0.7%
25
iScience
1063 papers in training set
Top 36%
0.7%
26
Proceedings of the National Academy of Sciences
2130 papers in training set
Top 47%
0.7%
27
Cell Reports Medicine
140 papers in training set
Top 10%
0.5%
28
Cell Death & Disease
126 papers in training set
Top 3%
0.5%
29
PLOS ONE
4510 papers in training set
Top 73%
0.5%
30
Genome Medicine
154 papers in training set
Top 10%
0.5%