Journal of Cheminformatics

Table 3 Ames data breakdown

From: Using test-time augmentation to investigate explainable AI: inconsistencies between method, model and human intuition

	Size	Scaffold split			Random split
	Size	Training	Validation	Test	Training	Validation	Test
Toxic		2511	373	753	2470	391	776
Non-toxic		2248	297	535	2139	297	644
Total	6717	4759	670	1288	4609	688	1420

Back to article page

ISSN: 1758-2946

Contact us

Submission enquiries: journalsubmissions@springernature.com