English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Background: Pharmacokinetic evaluation is one of the key processes in drugdiscovery and development. However, current absorption, distribution,metabolism, excretion prediction models still have limited accuracy. Aim: Thisstudy aims to construct an integrated transfer learning and multitask learningapproach for developing quantitative structure-activity relationship models topredict four human pharmacokinetic parameters. Methods: A pharmacokineticdataset included 1104 U.S. FDA approved small molecule drugs. The datasetincluded four human pharmacokinetic parameter subsets (oral bioavailability,plasma protein binding rate, apparent volume of distribution at steady-stateand elimination half-life). The pre-trained model was trained on over 30million bioactivity data. An integrated transfer learning and multitasklearning approach was established to enhance the model generalization. Results:The pharmacokinetic dataset was split into three parts (60:20:20) for training,validation and test by the improved Maximum Dissimilarity algorithm with therepresentative initial set selection algorithm and the weighted distancefunction. The multitask learning techniques enhanced the model predictiveability. The integrated transfer learning and multitask learning modeldemonstrated the best accuracies, because deep neural networks have the generalfeature extraction ability, transfer learning and multitask learning improvedthe model generalization. Conclusions: The integrated transfer learning andmultitask learning approach with the improved dataset splitting algorithm wasfirstly introduced to predict the pharmacokinetic parameters. This method canbe further employed in drug discovery and development.

An Integrated Transfer Learning and Multitask Learning Approach for Pharmacokinetic Parameter Prediction