Round Robin Consensus Prediction of Nanomaterials Zeta Potential

How four international research groups independently built ML models for the same endpoint and integrated them into a consensus scheme that outperforms any individual model — establishing a new standard for nanoinformatics model validation.

Beilstein Journal of Nanotechnology • 2024
View Publication

The Challenge

Validating Computational Models Across Research Groups

A major barrier to regulatory acceptance of in silico nanoinformatics models is the lack of standardised methods for comparing and validating modelling approaches across independent groups. In experimental science, Round Robin tests are the established method for demonstrating reproducibility.

No equivalent standardised approach existed for computational nanoinformatics. This study introduces the concept of consensus modelling as a "modelling equivalent" of the experimental Round Robin, where independent teams build models on the same dataset and integrate their results.

4
International research groups participating
5
Distinct ML models independently developed
IATA
Integrated Approach to Testing and Assessment

Our Approach

A multi-laboratory consensus modelling framework for nanoinformatics validation

Share a common dataset and protocol

A publicly available dataset of metal and metal oxide nanomaterials with measured zeta potential in aqueous medium was distributed to all four participating groups: NovaMechanics (Cyprus), NTUA (Greece), QSAR Lab (Poland), and DTC Lab (India).

Build independent ML models

Each group independently developed ML models using their own methodologies and algorithms, including Random Forest, AdaBoost, k-Nearest Neighbours, and read-across approaches, resulting in five distinct predictive models.

Evaluate individual model performance

Compared all models on common test data to assess their predictive accuracy, biases, and applicability domains, revealing the strengths and limitations of each individual approach.

Generate consensus predictions

Integrated the individual model predictions into a consensus modelling scheme that combines outputs from multiple models, enhancing predictive accuracy and reducing the biases inherent in any single approach.

Demonstrate consensus superiority

Showed that the consensus models consistently outperform individual models, providing more reliable predictions and establishing a new standard for increasing confidence in nanoinformatics model validity.

Results at a Glance

4 Groups
International Collaboration
Cyprus, Greece, Poland, and India research teams participated
5 Models
Independent Approaches
RF, AdaBoost, kNN, and read-across methods independently applied
Superior
Consensus Performance
Consensus scheme outperforms every individual model on test data
QMRF
Documented Models
All models documented in standardised QSAR model reporting format
NAMs
New Approach Methods
Supports regulatory acceptance of in silico methods for NM assessment
Open
Public Data
Common dataset and all model reports publicly available

Related Publication

Peer-Reviewed Paper

The round-robin approach applied to nanoinformatics: consensus prediction of nanomaterials zeta potential

Varsou D.-D., Banerjee A., Roy J., Roy K., Savvas G., Sarimveis H., Wyrzykowska E., Balicki M., Puzyn T., Melagraki G., Lynch I., Afantitis A. — Beilstein Journal of Nanotechnology, 2024, 15:1536–1553 — DOI: 10.3762/bjnano.15.121