Wisdom of Crowds for Supporting the Safety Evaluation of Nanomaterials - Data and results

This repository contains the input data and the generated results utilized as part of the research article titled "Wisdom of Crowds for Supporting the Safety Evaluation of Nanomaterials"  by Saarimäki & Fratello et al.

Data

This dataset includes anonymized responses of a panel of experts to a questionnaire focused on nanomaterials safety.

Additional Data Sources

This entry further includes additional data from the following sources:

Saarimäki et al. (2021): Preprocessed data and primary physicochemical characteristics are available on Zenodo.

Gallud et al. (2020): Data is available from the NCBI Gene Expression Omnibus (GEO) under accession number GSE148705.

del Giudice et al. (2023): The advanced descriptors are accessible through the associated Zenodo repository.

Labouta et al. (2019): The harmonized dataset of ENMs cell viability assays is available as supporting information of the reasearch article.


Outputs

Statistical modeling: The inferred parameters of the statistical model developed to analyze the expert responses and identify the consensus among the experts.

Machine Learning classifiers: The performances of several machine learning classifiers trained on the consensus responses to learn models that can predict safety concerns of new nanomaterials based on transcriptomics and physicochemical descriptors data.

Feature Importance: The relevant features extracted from the models analyzed to understand which aspects of the molecular responses to ENMs and which physicochemical properties are most important in driving the predictions.


Contents

data/Combined_cleaned_responses_anon.xlsx: Contains the anonymized responses from the expert panel.

data/enms_grouping.txt: Contains a categorization of the ENMs based on their core material.

data/expert_bibliographies_anon.pickle: Contains the anonymized bibliography of the experts to assess the multidisciplinarity of the panel assembled.

data/gex.csc.gz: Contains the gene expression after exposure to the ENMs.

data/phenodata.txt: Contains the meta-data of the experiments

data/physicochemical_descriptors.txt: Contains the physicochemical descriptors of the ENMs.

data/external/nn8b07562_si_001.xlsx: Contains a panel of harmonized ENMs cytotoxicity assays.

outputs/concern_scores.csv: Contains the consensus scores inferred by the statistical model.

outputs/cross_validation/: Contains the logs and performances of all the machine learning classification runs .

outputs/important_{genes,physchem}_weighted.xlsx: Feature relevance scores of both views.

outputs/model_inference_anon.nc: Inferred parameters of the statistical model.