2021
DOI: 10.1177/2472555220950245
|View full text |Cite
|
Sign up to set email alerts
|

Comparison of Approaches for Determining Bioactivity Hits from High-Dimensional Profiling Data

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1

Citation Types

0
12
0

Year Published

2021
2021
2024
2024

Publication Types

Select...
9
1

Relationship

1
9

Authors

Journals

citations
Cited by 24 publications
(12 citation statements)
references
References 44 publications
0
12
0
Order By: Relevance
“…In a second step, we aimed to evaluate the relevance of our morphological feature selection in the development of a predictive DILI model that could be used to assess the potential of a compound to induce DILI based on its Cell Painting profile. So far, Cell Painting data have been used for cytotoxicity or for DILI prediction , and concentration-response modeling approaches to estimate drug bioactivity thresholds. With the improvement of machine learning strategies observed these past years, many studies have shown that in silico models can be trained to predict the toxicity outcomes of hundreds of chemicals using image-based profiling .…”
Section: Discussionmentioning
confidence: 99%
“…In a second step, we aimed to evaluate the relevance of our morphological feature selection in the development of a predictive DILI model that could be used to assess the potential of a compound to induce DILI based on its Cell Painting profile. So far, Cell Painting data have been used for cytotoxicity or for DILI prediction , and concentration-response modeling approaches to estimate drug bioactivity thresholds. With the improvement of machine learning strategies observed these past years, many studies have shown that in silico models can be trained to predict the toxicity outcomes of hundreds of chemicals using image-based profiling .…”
Section: Discussionmentioning
confidence: 99%
“…Potential uses for this dataset include HCS and image-processing method development, MoA studies, informer set design, and compound triage 52,53 . These data can be re-analyzed by alternative methods such as focusing on individual features or more complex analyses such as the point-of-departure metric 20,54 .…”
Section: Discussionmentioning
confidence: 99%
“…Feature-level and global concentration-response modeling of well-level CP data were performed as previously described ( Nyffeler et al, 2021 ). For feature-level modeling, the tcplfit2 package in R statistical software was used to model each of the 1,300 features to nine functions, constant, Hill, poly1, poly2, power, and exp2-5.…”
Section: Methodsmentioning
confidence: 99%