What does this research mean for the field?

Random Forest-based in silico models that incorporate vehicle effects and specific molecular descriptors can effectively predict human dermal absorption rates without underestimation, offering a viable tool for chemical exposure and photosafety risk assessments. Novelty: ClaimNovelty.METHODOLOGICAL. Consensus alignment: ConsensusAlignment.NEUTRAL.

What question did this study set out to answer?

To develop machine learning models for predicting dermal absorption rates of chemicals, accounting for vehicle effects and key descriptors.

May 29, 2026NAM journal.Open Access

Development and Application of Machine Learning Models for Predicting Dermal Absorption with Consideration of Vehicle Effects

View Full Paper

Ask AI

Bookmark

Authors

TATomomi Atobe KIKosuke Imai THTomoka Hisaki

Discussion

Member takes

Overview

Randomized trial assesses the prediction of dermal absorption in chemicals, suggesting new risk assessment methods.

Key Points

To develop machine learning models for predicting dermal absorption rates of chemicals, accounting for vehicle effects and key descriptors.
Constructed a database with 639 log Kp and 135 log D values from in vitro dermal absorption data.
Performed comparative analysis of machine learning algorithms, identifying Random Forest as the optimal method.
Developed models using descriptors such as molecular weight, log P of chemicals and vehicles, and topological polar surface area.
Predicted dermal absorption rates for 25 chemicals with minimal underestimation compared to in vitro values.
56% of chemicals were predicted within a ten-fold range of experimental data, while 44% were overpredicted by over ten-fold.
Predictions of Kp rankings for benzophenone derivatives were in agreement with published data.

Cite This Study

Atobe et al. (2026) studied this question.

synapsesocial.com/papers/6a192cf8fab5b468c4415b98 https://doi.org/10.1016/j.namjnl.2026.100101

View Full Paper

Ask AI

Bookmark

May 29, 2026NAM journal.Open Access

Development and Application of Machine Learning Models for Predicting Dermal Absorption with Consideration of Vehicle Effects

View Full Paper

Ask AI

Bookmark

Authors

TATomomi Atobe KIKosuke Imai THTomoka Hisaki

Discussion

Member takes

Overview

Randomized trial assesses the prediction of dermal absorption in chemicals, suggesting new risk assessment methods.

Key Points

To develop machine learning models for predicting dermal absorption rates of chemicals, accounting for vehicle effects and key descriptors.
Constructed a database with 639 log Kp and 135 log D values from in vitro dermal absorption data.
Performed comparative analysis of machine learning algorithms, identifying Random Forest as the optimal method.
Developed models using descriptors such as molecular weight, log P of chemicals and vehicles, and topological polar surface area.
Predicted dermal absorption rates for 25 chemicals with minimal underestimation compared to in vitro values.
56% of chemicals were predicted within a ten-fold range of experimental data, while 44% were overpredicted by over ten-fold.
Predictions of Kp rankings for benzophenone derivatives were in agreement with published data.

Cite This Study

Atobe et al. (2026) studied this question.

synapsesocial.com/papers/6a192cf8fab5b468c4415b98 https://doi.org/10.1016/j.namjnl.2026.100101

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

View Full Paper

Ask AI

Bookmark