Coloring Molecules with Explainable Artificial Intelligence for Preclinical Relevance Assessment

Jiménez-Luna, José; Škalič, Miha; Weskamp, Nils; Schneider, Gisbert

doi:10.1021/acs.jcim.0c01344

Cited by 68 publications

(67 citation statements)

References 92 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Such models are often considered as black boxes and understanding the mechanism in the hidden layers is a challenge. However, research undertaken in this direction aims at deciphering what the algorithm has learned [ 101 , 174 ]. This may also be important in detecting bias in the data [ 121 ].…”

Section: Conclusion and Discussionmentioning

confidence: 99%

Deep Learning in Virtual Screening: Recent Applications and Developments

Kimber

Chen

Volkamer

2021

IJMS

145

View full text Add to dashboard Cite

Drug discovery is a cost and time-intensive process that is often assisted by computational methods, such as virtual screening, to speed up and guide the design of new compounds. For many years, machine learning methods have been successfully applied in the context of computer-aided drug discovery. Recently, thanks to the rise of novel technologies as well as the increasing amount of available chemical and bioactivity data, deep learning has gained a tremendous impact in rational active compound discovery. Herein, recent applications and developments of machine learning, with a focus on deep learning, in virtual screening for active compound design are reviewed. This includes introducing different compound and protein encodings, deep learning techniques as well as frequently used bioactivity and benchmark data sets for model training and testing. Finally, the present state-of-the-art, including the current challenges and emerging problems, are examined and discussed.

show abstract

Section: Conclusion and Discussionmentioning

confidence: 99%

Deep Learning in Virtual Screening: Recent Applications and Developments

Kimber

Chen

Volkamer

2021

IJMS

145

View full text Add to dashboard Cite

show abstract

“…This allows to visualize the atoms that are considered "mostly responsible" for modulating the activity. Some approaches exploit integrated gradients (IG) [Sundararajan et al, 2017] to generate input-attributions on the atoms [Jiménez-Luna et al, 2021]. Although XAI methods do a good job in attributing specific atoms, it is difficult for them to refer to functional groups.…”

Section: Related Workmentioning

confidence: 99%

Semi-Supervised GCN for learning Molecular Structure-Activity Relationships

Ragno¹,

Savoia²,

Capobianco³

2022

Preprint

View full text Add to dashboard Cite

Since the introduction of artificial intelligence in medicinal chemistry, the necessity has emerged to analyse how molecular property variation is modulated by either single atoms or chemical groups. In this paper, we propose to train graph-tograph neural network using semi-supervised learning for attributing structureproperty relationships. As initial case studies we apply the method to solubility and molecular acidity while checking its consistency in comparison with known experimental chemical data. As final goal, our approach could represent a valuable tool to deal with problems such as activity cliffs, lead optimization and de-novo drug design.

show abstract

“…There are four major approaches for explaining a prediction from a black-box model: 17 identifying which features contribute the most, [18][19][20][21][22] identifying which training data contributes the most, 23 tting a locally interpretable model around the prediction, 24 and providing contrastive or counterfactual points. 25 Feature importance analysis provides per-feature weights that identify how each feature contributed to the nal prediction.…”

Section: Introductionmentioning

confidence: 99%