Small data materials design with machine learning: When the average model knows best

Abstract

People interested in the research are advised to contact the author for the final version of the publication, or visit the DOI to the publisher's website.• The final author version and the galley proof are versions of the publication after peer review.• The final published version features the final layout of the paper including the volume, issue and page numbers. Link to publication General rightsCopyright and moral rights for the publications made accessible in the public portal are retained by the authors and/or other copyright owners and it is a condition of accessing publications that users recognise and abide by the legal requirements associated with these rights.• Users may download and print one copy of any publication from the public portal for the purpose of private study or research. • You may not further distribute the material or use it for any profit-making activity or commercial gain • You may freely distribute the URL identifying the publication in the public portal.If the publication is distributed under the terms of Article 25fa of the Dutch Copyright Act, indicated by the "Taverne" license above, please follow below link for the End User Agreement:

Theoretical Studies on the Molecular Properties, Toxicity, and Biological Efficacy of 21 New Chemical Entities

“…The optimized structures of the 21 selected drugs lascufloxacin (1), pretomanid (2), relebactam (3), triclabendazole (4), esaxerenone (5), voxelotor (6), cenobamate (7), lasmiditan (8), mirogabalin (9), remimazolam (10), solriamfetol (11), ubrogepant (12), benvitimod (13), trifarotene (14), upadacitinib (15), sotagliflozin (16), alpelisib (17), erdafitinib (18), zanubrutinib (19), relugolix (20), and elexacaftor (21) are given in Figure 2, and the SMILES notations and chemical formulas are given in Table 1.…”

“…The significant contribution of computational and theoretical studies of quantum chemistry has allowed medicinal chemists to obtain more precise molecular properties and bioactivity of drugs in a shorter time. − Due to the evolution of computing data storage and higher processor performance, molecular modeling has been very efficient to solve drug-related issues without compromising the accuracy of the predicted data. − Investigation of the mechanism of action of drugs on therapeutic targets can be carried out using structure–activity relationship (SAR) and quantitative structure–activity relationship (QSAR) models. The structures of drugs and their activities or properties are studied using molecular modeling methods and statistical methods.…”

High-Throughput Routes to Biomaterials Discovery

“…Vanpoucke et al. has recently highlighted the powers of machine learning for materials design, suggesting a novel “ensemble-average” model for use with smaller data sets specifically …”

“…Vanpoucke et al has recently highlighted the powers of machine learning for materials design, suggesting a novel "ensemble-average" model for use with smaller data sets specifically. 525 In the case of linear regression, two important assumptions are made: (1) the outcome is a continuous variable and (2) that it is normally distributed. However, in reality, this is not always the case.…”

Accelerating the Design of Photocatalytic Surfaces for Antimicrobial Application: Machine Learning Based on a Sparse Dataset

“…The datasets generated during human-driven experiments vary between 5 and 20 data points resulting from a limited set of experimental conditions decided by the researcher or based on trials and errors. As a general rule, small datasets must be treated using low complexity models to avoid overfitting and are often well handled using polynomial fitting techniques [29]. Still, experimentally-generated small datasets might carry a high correlation and complexity level, requiring analysis using ML methods.…”