Skip to content
DraconiticResearch
Search Sources API
190,860 studies31 sourcesUpdated 14 min ago
Peer-reviewedCC BYNPJ Parkinson's disease

Machine learning image analysis predicts Parkinson disease genotype and mitochondrial lysosomal abnormalities in iPS neurons.

  • Yan Li1,2,3
  • Maximilian Powell1,4
  • Jessica Chedid1,4
  • Ratneswary Sutharsan3
  • Adahir Labrador-Garrido1,4
  • Dad Abu-Bonsrah1,5,6
  • Chiara Pavan1,5
  • Tyra Fraser1,5
  • Dmitry Ovchinnikov1,5
  • Melanie Zhong4
  • Ryan Davis1,2
  • Dario Strbenac1,7
8 more authors
  • Jennifer A Johnston1,8
  • Lachlan H Thompson1,5,9
  • Deniz Kirik1,10
  • Clare L Parish1,5
  • Glenda M Halliday1,3,4
  • Carolyn M Sue1,2,3
  • Nicolas Dzamko11,12
  • Gautam Wali13,14,15
15 affiliations
  1. 1Aligning Science Across Parkinson's (ASAP) Collaborative Research Network, Chevy Chase, MD, USA.
  2. 2The University of Sydney, Kolling Institute & Faculty of Medicine and Health Northern Clinical School, Sydney, NSW, Australia.
  3. 3Neuroscience Research Australia, Sydney, NSW, Australia.
  4. 4The University of Sydney, Brain and Mind Centre & Faculty of Medicine and Health School of Medical Sciences, Sydney, NSW, Australia.
  5. 5The Florey Institute of Neuroscience and Mental Health & The University of Melbourne, Parkville, VIC, Australia.
  6. 6Department of Paediatrics, University of Melbourne, Parkville, Vic, Australia.
  7. 7The University of Sydney, School of Mathematics and Statistics, Sydney, NSW, Australia.
  8. 8NysnoBio, Mill Valley, CA, USA.
  9. 9The University of Sydney, Charles Perkins Centre & Faculty of Medicine and Health School of Medical Sciences, Sydney, NSW, Australia.
  10. 10BRAINS Unit, BMC D11, Lund University, Lund, Sweden.
  11. 11Aligning Science Across Parkinson's (ASAP) Collaborative Research Network, Chevy Chase, MD, USA. [email protected].
  12. 12The University of Sydney, Brain and Mind Centre & Faculty of Medicine and Health School of Medical Sciences, Sydney, NSW, Australia. [email protected].
  13. 13Aligning Science Across Parkinson's (ASAP) Collaborative Research Network, Chevy Chase, MD, USA. [email protected].
  14. 14The University of Sydney, Kolling Institute & Faculty of Medicine and Health Northern Clinical School, Sydney, NSW, Australia. [email protected].
  15. 15Neuroscience Research Australia, Sydney, NSW, Australia. [email protected].
Read full textPDFDOICite

Abstract

Mitochondrial and lysosomal dysfunction are central features of Parkinson's 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 in the relative contribution of mitochondrial and lysosomal features, 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.

Related

  1. A rare TMEM175 mutation drives Parkinson's disease pathology by disrupting proton gating and lysosomal acidification.
    Xiaotong Yang, Ping Li, Man Lv +17
    The Journal of clinical investigationPeer-reviewedCC BYFull textNeurologyEurope PMCPMC
  2. Glymphatic dysfunction predicts drooling severity in Parkinson’s disease
    Ting Huang, Youyong Tian, Yuting Xia +8
    BMC MedicinePeer-reviewedCC BY-NC-ND 4.0NeurologyCrossref
  3. Lysosomal polygenic risk score in Parkinson's disease across populations.
    W. Sun, K. Brockmann, I. Wurster +8
    medRxivPreprintCC BYFull textHuman geneticsmedRxiv
  4. Metformin improves mitophagy-related pathways and mitochondrial-lysosomal homeostasis in chromosome 21 trisomic fibroblasts.
    Nunzia Mollo, Rosalba Natale, Morena D'Ariano +11
    Cellular and molecular life sciences : CMLSPeer-reviewedCC BYFull textEpidemiology & public healthEurope PMCDOAJ
  5. Long-term donor and graft safety despite subclinical mitochondrial abnormalities: mechanistic insights from a 22-year follow-up of a carrier-to-MELAS kidney transplant.
    Shizuka Kobayashi, Tomokazu Shimizu, Shun Manabe +14
    BMC nephrologyPeer-reviewedCC BY-NC-NDFull textEpidemiology & public healthEurope PMCDOAJ

Cite

BibTeXRIS
BibTeX
@article{li2026machine,
  title = {{Machine learning image analysis predicts Parkinson disease genotype and mitochondrial lysosomal abnormalities in iPS neurons.}},
  author = {Yan Li and Maximilian Powell and Jessica Chedid and Ratneswary Sutharsan and Adahir Labrador-Garrido and Dad Abu-Bonsrah and Chiara Pavan and Tyra Fraser and Dmitry Ovchinnikov and Melanie Zhong and Ryan Davis and Dario Strbenac and Jennifer A Johnston and Lachlan H Thompson and Deniz Kirik and Clare L Parish and Glenda M Halliday and Carolyn M Sue and Nicolas Dzamko and Gautam Wali},
  journal = {NPJ Parkinson's disease},
  year = {2026},
  month = aug,
  doi = {10.1038/s41531-026-01458-w},
  url = {https://europepmc.org/article/MED/42897176},
  note = {CC BY},
}
RIS
TY  - JOUR
TI  - Machine learning image analysis predicts Parkinson disease genotype and mitochondrial lysosomal abnormalities in iPS neurons.
AU  - Yan Li
AU  - Maximilian Powell
AU  - Jessica Chedid
AU  - Ratneswary Sutharsan
AU  - Adahir Labrador-Garrido
AU  - Dad Abu-Bonsrah
AU  - Chiara Pavan
AU  - Tyra Fraser
AU  - Dmitry Ovchinnikov
AU  - Melanie Zhong
AU  - Ryan Davis
AU  - Dario Strbenac
AU  - Jennifer A Johnston
AU  - Lachlan H Thompson
AU  - Deniz Kirik
AU  - Clare L Parish
AU  - Glenda M Halliday
AU  - Carolyn M Sue
AU  - Nicolas Dzamko
AU  - Gautam Wali
PY  - 2026
DA  - 2026/08/01
JO  - NPJ Parkinson's disease
DO  - 10.1038/s41531-026-01458-w
UR  - https://europepmc.org/article/MED/42897176
AB  - Mitochondrial and lysosomal dysfunction are central features of Parkinson's 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 in the relative contribution of mitochondrial and lysosomal features, 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.
SN  - 2373-8057
ER  -