End-to-End Learning of Pharmacological Assays from High-resolution Microscopy Images

Markus Hofmarcher; Elisabeth Rumetshofer; Markus Holzleitner; Bernhard Schäfl; Sepp Hochreiter; Günter Klambauer

End-to-End Learning of Pharmacological Assays from High-resolution Microscopy Images

Markus Hofmarcher, Elisabeth Rumetshofer, Markus Holzleitner, Bernhard Schäfl, Sepp Hochreiter, Günter Klambauer

Institute for Machine Learning

Research output: Chapter in Book/Report/Conference proceeding › Conference proceedings › peer-review

Abstract

Predicting the outcome of pharmacological assays based on high-resolution microscopy images of treated cells is a crucial task in drug discovery which tremendously increases discovery rates. However, end-to-end learning on these images with convolutional neural networks (CNNs) has not been ventured for this task because it has been considered infeasible and overly complex. On the largest available public dataset, we compare several state-of-the-art CNNs trained in an end-to-end fashion with models based on a cell-centric approach involving segmentation. We found that CNNs operating on full images containing hundreds of cells perform significantly better at assay prediction than networks operating on a single-cell level. Surprisingly, we could predict 29% of the 209 pharmacological assays at high predictive performance (AUC > 0.9).

Original language	English
Title of host publication	Neural Information Processing Systems (NIPS 2018)
Number of pages	1
Publication status	Published - 2018

Fields of science

303 Health Sciences
304 Medical Biotechnology
304003 Genetic engineering
305 Other Human Medicine, Health Sciences
101004 Biomathematics
101018 Statistics
102 Computer Sciences
102001 Artificial intelligence
102004 Bioinformatics
102010 Database systems
102015 Information systems
102019 Machine learning
106023 Molecular biology
106002 Biochemistry
106005 Bioinformatics
106007 Biostatistics
106041 Structural biology
301 Medical-Theoretical Sciences, Pharmacy
302 Clinical Medicine

JKU Focus areas

Computation in Informatics and Mathematics
Nano-, Bio- and Polymer-Systems: From Structure to Function
Medical Sciences (in general)
Health System Research
Clinical Research on Aging

Cite this

@inproceedings{d9508fb7cdef4cc6af27530be9420e85,

title = "End-to-End Learning of Pharmacological Assays from High-resolution Microscopy Images",

abstract = "Predicting the outcome of pharmacological assays based on high-resolution microscopy images of treated cells is a crucial task in drug discovery which tremendously increases discovery rates. However, end-to-end learning on these images with convolutional neural networks (CNNs) has not been ventured for this task because it has been considered infeasible and overly complex. On the largest available public dataset, we compare several state-of-the-art CNNs trained in an end-to-end fashion with models based on a cell-centric approach involving segmentation. We found that CNNs operating on full images containing hundreds of cells perform significantly better at assay prediction than networks operating on a single-cell level. Surprisingly, we could predict 29% of the 209 pharmacological assays at high predictive performance (AUC > 0.9).",

author = "Markus Hofmarcher and Elisabeth Rumetshofer and Markus Holzleitner and Bernhard Sch{\"a}fl and Sepp Hochreiter and G{\"u}nter Klambauer",

year = "2018",

language = "English",

booktitle = "Neural Information Processing Systems (NIPS 2018)",

}

TY - GEN

T1 - End-to-End Learning of Pharmacological Assays from High-resolution Microscopy Images

AU - Hofmarcher, Markus

AU - Rumetshofer, Elisabeth

AU - Holzleitner, Markus

AU - Schäfl, Bernhard

AU - Hochreiter, Sepp

AU - Klambauer, Günter

PY - 2018

Y1 - 2018

N2 - Predicting the outcome of pharmacological assays based on high-resolution microscopy images of treated cells is a crucial task in drug discovery which tremendously increases discovery rates. However, end-to-end learning on these images with convolutional neural networks (CNNs) has not been ventured for this task because it has been considered infeasible and overly complex. On the largest available public dataset, we compare several state-of-the-art CNNs trained in an end-to-end fashion with models based on a cell-centric approach involving segmentation. We found that CNNs operating on full images containing hundreds of cells perform significantly better at assay prediction than networks operating on a single-cell level. Surprisingly, we could predict 29% of the 209 pharmacological assays at high predictive performance (AUC > 0.9).

AB - Predicting the outcome of pharmacological assays based on high-resolution microscopy images of treated cells is a crucial task in drug discovery which tremendously increases discovery rates. However, end-to-end learning on these images with convolutional neural networks (CNNs) has not been ventured for this task because it has been considered infeasible and overly complex. On the largest available public dataset, we compare several state-of-the-art CNNs trained in an end-to-end fashion with models based on a cell-centric approach involving segmentation. We found that CNNs operating on full images containing hundreds of cells perform significantly better at assay prediction than networks operating on a single-cell level. Surprisingly, we could predict 29% of the 209 pharmacological assays at high predictive performance (AUC > 0.9).

M3 - Conference proceedings

BT - Neural Information Processing Systems (NIPS 2018)

ER -