Machine learning phenomics (MLP) combining deep learning with time-lapse-microscopy for monitoring colorectal adenocarcinoma cells gene expression and drug-response
Problem
Monitoring how colorectal cancer cells respond to therapy and linking gene expression to cell behaviour required new high-throughput phenotyping methods.
Why it matters
Better drug-response phenotyping could speed up cancer therapy development and personalised treatment.
What the AI did
A machine-learning phenomics platform combined time-lapse microscopy with deep learning architectures to extract latent phenotypes and correlate gene expression with cell behaviour and drug response.
Results
not stated in source
Impact
The paper presents a proof-of-concept platform claiming a correlation between gene expression and cell phenotype, but no metrics are given in the abstract.
Record
| Venue | Scientific Reports |
|---|---|
| Published | 2022 |
| Work type | article |
| Authors | Michele D’Orazio, Michela Murdocca, Arianna Mencattini, Paola Casti, Joanna Filippi, Gianni Antonelli, Davide Di Giuseppe, Maria Colomba Comes et al. |
| Citations | 33 (OpenAlex, at import time) |
| References | 66 |
| Model or method | not stated in source |
| Organization | not stated in source |
| Primary source | https://doi.org/10.1038/s41598-022-12364-5 |
| Open access | gold |
| Keywords | deep learning, time-lapse microscopy, phenomics, colorectal cancer, drug response |
Importance rating
real but narrower advance
Proof-of-concept phenomics platform for cancer drug-response monitoring on cell lines; could aid therapy development and personalized treatment but no scale, metrics, or clinical evidence stated.