Nanosafety-data-reusability-34-datasets

Learning from the Machine: Uncovering Sustainable Nanoparticle Design Rules (2020)

Original Study Abstract

Machines consisting of bags of artificial neural networks (ANNs) have been constructed to connect nanoparticle features to the viability of a broad class of organisms upon exposure. The optimization of these machines is based on a relatively small data set. However, through consensus across a bag of ANNs, these machines predict at a level of confidence comparable to the experiment and perform better than chance. The mining of the machine across the feature space allows for the discovery of design rules for nanoparticles with increased viability. As such, we demonstrate the efficacy of inversion as an approach to learn from the machine in the context of designing sustainable nanoparticles. For example, we find that increased manganese content in lithium NiMnCo oxide nanoparticles is associated with greater viability, carbon dots reduce viability less than quantum dots, and gold nanoparticle coatings can significantly affect viability at high concentration.

Data Sample

Type Carbon Nitrogen Phosphorus Hydrogen Titanium Gold Lithium Nickel Cobalt Manganese Oxygen Cadmium Selenium Sulfur Silicon Platinum Zinc Total Composition Knowledge Particle Diameter Dimension 1 (nm) Particle Diameter Dimension 2 (nm) Particle Diameter Dimension 3 (nm) Capping Agent Shape Concentration (mg/L) Exposed NMC Surface Area (m2/g) pH Medium Natural Organic Matter (mg/L) Purification Method Total Centrifugation Steps Exposure Time (min) Bacteria Gram Identity Mutation Viability Method Viability Fraction
Nanodiamond 1 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 T 15 15 15 PAH Amorphous 3,75 0 7,4 HEPES Buffer 0 Dialysis 0 10 Yes Negative Shewanella oneidensis MR-1 Growth Based Viability 0,105666667
Nanodiamond 1 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 T 15 15 15 PAH Amorphous 3,75 0 7,4 HEPES Buffer 0,5 Dialysis 0 10 Yes Negative Shewanella oneidensis MR-1 Growth Based Viability 0,054333333
Nanodiamond 1 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 T 15 15 15 PAH Amorphous 3,75 0 7,4 HEPES Buffer 1 Dialysis 0 10 Yes Negative Shewanella oneidensis MR-1 Growth Based Viability 0,053
Nanodiamond 1 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 T 15 15 15 PAH Amorphous 3,75 0 7,4 HEPES Buffer 2 Dialysis 0 10 Yes Negative Shewanella oneidensis MR-1 Growth Based Viability 0,123
Nanodiamond 1 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 T 15 15 15 PAH Amorphous 3,75 0 7,4 HEPES Buffer 3 Dialysis 0 10 Yes Negative Shewanella oneidensis MR-1 Growth Based Viability 0,205666667

Data Summary

Variable Count (unique values)
Source (Not used by ANNs) 206
Type 11
Carbon 8
Nitrogen 12
Phosphorus 11
Hydrogen 12
Titanium 1
Gold 2
Lithium 2
Nickel 3
Cobalt 9
Manganese 10
Oxygen 8
Cadmium 14
Selenium 5
Sulfur 5
Silicon 1
Platinum 11
Zinc 11
Total Composition Knowledge 4
Particle Diameter Dimension 1 (nm) 2
Particle Diameter Dimension 2 (nm) 16
Particle Diameter Dimension 3 (nm) 27
Capping Agent 27
Shape 4
Concentration (mg/L) 5
Exposed NMC Surface Area (m2/g) 74
pH 8
Medium 4
Natural Organic Matter (mg/L) 5
Purification Method 7
Total Centrifugation Steps 8
Exposure Time (min) 4
Bacteria 8
Gram 2
Identity 3
Mutation 7
Viability Method 10