The Promise of AI for DILI Prediction
Drug-induced liver injury (DILI) is a common reason for the withdrawal of a drug from the market. Early assessment of DILI risk is an essential part of drug development, but it is rendered challenging prior to clinical trials by the complex factors that give rise to liver damage. Artificial intellig...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Frontiers Media S.A.
2021-04-01
|
Series: | Frontiers in Artificial Intelligence |
Subjects: | |
Online Access: | https://www.frontiersin.org/articles/10.3389/frai.2021.638410/full |
id |
doaj-e1f44902053346b7a1624f6a220c0190 |
---|---|
record_format |
Article |
spelling |
doaj-e1f44902053346b7a1624f6a220c01902021-04-14T14:33:51ZengFrontiers Media S.A.Frontiers in Artificial Intelligence2624-82122021-04-01410.3389/frai.2021.638410638410The Promise of AI for DILI PredictionAndreu Vall0Andreu Vall1Yogesh Sabnis2Jiye Shi3Reiner Class4Sepp Hochreiter5Sepp Hochreiter6Sepp Hochreiter7Günter Klambauer8Günter Klambauer9LIT AI Lab, Johannes Kepler University Linz, Linz, AustriaInstitute for Machine Learning, Johannes Kepler University Linz, Linz, AustriaUCB Biopharma SRL, Braine-l'Alleud, BelgiumUCB Biopharma SRL, Braine-l'Alleud, BelgiumUCB Biopharma SRL, Braine-l'Alleud, BelgiumLIT AI Lab, Johannes Kepler University Linz, Linz, AustriaInstitute for Machine Learning, Johannes Kepler University Linz, Linz, AustriaInstitute of Advanced Research in Artificial Intelligence (IARAI), Vienna, AustriaLIT AI Lab, Johannes Kepler University Linz, Linz, AustriaInstitute for Machine Learning, Johannes Kepler University Linz, Linz, AustriaDrug-induced liver injury (DILI) is a common reason for the withdrawal of a drug from the market. Early assessment of DILI risk is an essential part of drug development, but it is rendered challenging prior to clinical trials by the complex factors that give rise to liver damage. Artificial intelligence (AI) approaches, particularly those building on machine learning, range from random forests to more recent techniques such as deep learning, and provide tools that can analyze chemical compounds and accurately predict some of their properties based purely on their structure. This article reviews existing AI approaches to predicting DILI and elaborates on the challenges that arise from the as yet limited availability of data. Future directions are discussed focusing on rich data modalities, such as 3D spheroids, and the slow but steady increase in drugs annotated with DILI risk labels.https://www.frontiersin.org/articles/10.3389/frai.2021.638410/fullartificial intelligencemachine learningneural networksdeep learningdrug-induced liver injury |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Andreu Vall Andreu Vall Yogesh Sabnis Jiye Shi Reiner Class Sepp Hochreiter Sepp Hochreiter Sepp Hochreiter Günter Klambauer Günter Klambauer |
spellingShingle |
Andreu Vall Andreu Vall Yogesh Sabnis Jiye Shi Reiner Class Sepp Hochreiter Sepp Hochreiter Sepp Hochreiter Günter Klambauer Günter Klambauer The Promise of AI for DILI Prediction Frontiers in Artificial Intelligence artificial intelligence machine learning neural networks deep learning drug-induced liver injury |
author_facet |
Andreu Vall Andreu Vall Yogesh Sabnis Jiye Shi Reiner Class Sepp Hochreiter Sepp Hochreiter Sepp Hochreiter Günter Klambauer Günter Klambauer |
author_sort |
Andreu Vall |
title |
The Promise of AI for DILI Prediction |
title_short |
The Promise of AI for DILI Prediction |
title_full |
The Promise of AI for DILI Prediction |
title_fullStr |
The Promise of AI for DILI Prediction |
title_full_unstemmed |
The Promise of AI for DILI Prediction |
title_sort |
promise of ai for dili prediction |
publisher |
Frontiers Media S.A. |
series |
Frontiers in Artificial Intelligence |
issn |
2624-8212 |
publishDate |
2021-04-01 |
description |
Drug-induced liver injury (DILI) is a common reason for the withdrawal of a drug from the market. Early assessment of DILI risk is an essential part of drug development, but it is rendered challenging prior to clinical trials by the complex factors that give rise to liver damage. Artificial intelligence (AI) approaches, particularly those building on machine learning, range from random forests to more recent techniques such as deep learning, and provide tools that can analyze chemical compounds and accurately predict some of their properties based purely on their structure. This article reviews existing AI approaches to predicting DILI and elaborates on the challenges that arise from the as yet limited availability of data. Future directions are discussed focusing on rich data modalities, such as 3D spheroids, and the slow but steady increase in drugs annotated with DILI risk labels. |
topic |
artificial intelligence machine learning neural networks deep learning drug-induced liver injury |
url |
https://www.frontiersin.org/articles/10.3389/frai.2021.638410/full |
work_keys_str_mv |
AT andreuvall thepromiseofaifordiliprediction AT andreuvall thepromiseofaifordiliprediction AT yogeshsabnis thepromiseofaifordiliprediction AT jiyeshi thepromiseofaifordiliprediction AT reinerclass thepromiseofaifordiliprediction AT sepphochreiter thepromiseofaifordiliprediction AT sepphochreiter thepromiseofaifordiliprediction AT sepphochreiter thepromiseofaifordiliprediction AT gunterklambauer thepromiseofaifordiliprediction AT gunterklambauer thepromiseofaifordiliprediction AT andreuvall promiseofaifordiliprediction AT andreuvall promiseofaifordiliprediction AT yogeshsabnis promiseofaifordiliprediction AT jiyeshi promiseofaifordiliprediction AT reinerclass promiseofaifordiliprediction AT sepphochreiter promiseofaifordiliprediction AT sepphochreiter promiseofaifordiliprediction AT sepphochreiter promiseofaifordiliprediction AT gunterklambauer promiseofaifordiliprediction AT gunterklambauer promiseofaifordiliprediction |
_version_ |
1721527319938465792 |