Improving Diagnosis, biomarkers & drug discovery

Cell morphology and machine learning

Dr Gautam Wali, long-term member of the HSP research team, has used skin cells to tell the difference between SPG4 and SPG7 without genetic testing.

Using machine learning to analyse more than 100 physical features (morphologies) of the skin cells, accurate diagnosis was achieved.

Gautam Wali

When treated with Noscapine, cell morphology changed differently between the two types of HSP, as expected. This technology also holds potential for biomarker development and drug discovery.

It is also worth noting that all this can be achieved from a skin cell sample with no need for blood, neural tissue or genetic testing. This is not only easier and more convenient for people with HSP, but may also help with the problem of at least 40% of gene testing currently failing to identify the responsible mutation.


A central need for neurodegenerative diseases is to find curative drugs for the many clinical subtypes, the causative gene for most cases being unknown. This requires the classification of disease cases at the genetic and cellular level, an understanding of disease aetiology in the subtypes and the development of phenotypic assays for high throughput screening of large compound libraries.

Herein we describe a method that facilitates these requirements based on cell morphology that is being increasingly used as a readout defining cell state. In patient-derived fibroblasts we quantified 124 morphological features in 100,000 cells from 15 people with two genotypes (SPAST and SPG7) of Hereditary Spastic Paraplegia (HSP) and matched controls. Using machine learning analysis, we distinguished between each genotype and separated them from controls. Cell morphologies changed with treatment with noscapine, a tubulin-binding drug, in a genotype-dependent manner, revealing a novel effect on one of the genotypes (SPG7).

These findings demonstrate a method for morphological profiling in fibroblasts, an accessible non-neural cell, to classify and distinguish between clinical subtypes of neurodegenerative diseases, for drug discovery, and potentially for biomarkers of disease severity and progression.

SOURCE: Sci Rep. 2021 Aug 17;11(1):16635. doi: 10.1038/s41598-021-95995-4. PMID: 34404843. © 2021. The Author(s).  

Single cell morphology distinguishes genotype and drug effect in Hereditary Spastic Paraplegia

Gautam Wali  1 Shlomo Berkovsky  2 Daniel R Whiten  3 Alan Mackay-Sim #  3   4 Carolyn M Sue #  3

1. Department of Neurogenetics, Kolling Institute of Medical Research, The University of Sydney, Sydney, NSW, 2065, Australia. [email protected].

2. Centre for Health Informatics, Macquarie University, Sydney, Australia.

3. Department of Neurogenetics, Kolling Institute of Medical Research, The University of Sydney, Sydney, NSW, 2065, Australia.

4. Griffith Institute for Drug Discovery, Griffith University, Brisbane, Australia.

#. Contributed equally.

Your email address will not be published. Required fields are marked *