Investigating the Use of Machine Learning Models to Understand the Drugs Permeability Across Placenta
Owing to limited drug testing possibilities in pregnant population, the development of computational algorithms is crucial to predict the fate of drugs in the placental barrier; it could serve as an alternative to animal testing. The ability of a molecule to effectively cross the placental barrier a...
Main Authors: | , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2023-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/10115411/ |
_version_ | 1797804858287325184 |
---|---|
author | Vaisali Chandrasekar Mohammed Yusuf Ansari Ajay Vikram Singh Shahab Uddin Kirthi S. Prabhu Sagnika Dash Souhaila Al Khodor Annalisa Terranegra Matteo Avella Sarada Prasad Dakua |
author_facet | Vaisali Chandrasekar Mohammed Yusuf Ansari Ajay Vikram Singh Shahab Uddin Kirthi S. Prabhu Sagnika Dash Souhaila Al Khodor Annalisa Terranegra Matteo Avella Sarada Prasad Dakua |
author_sort | Vaisali Chandrasekar |
collection | DOAJ |
description | Owing to limited drug testing possibilities in pregnant population, the development of computational algorithms is crucial to predict the fate of drugs in the placental barrier; it could serve as an alternative to animal testing. The ability of a molecule to effectively cross the placental barrier and reach the fetus determines the drug’s toxicological effects on the fetus. In this regard, our study aims to predict the permeability of molecules across the placental barrier. Based on publicly available datasets, several machine learning models are comprehensively analysed across different fingerprints and toolkits to find the best suitable models. Several dataset analysis models are utilised to study the data diversity. Further, this study demonstrates the application of neural network-based models to effectively predict the permeability. K-nearest neighbour (KNN), standard vector classifier (SVC) and Multi-layer perceptron (MLP) are found to be the best-performing models with a prediction percentage of 82%, 86.4% and 90.8%, respectively. Different models are compared to predict the chosen set of drugs, drugs like Aliskiren, some insulin secretagogues and glucocorticoids are found to be negative while predicting the permeability. |
first_indexed | 2024-03-13T05:43:19Z |
format | Article |
id | doaj.art-0edfb246b65e45278fc33b2cb9ee2f3c |
institution | Directory Open Access Journal |
issn | 2169-3536 |
language | English |
last_indexed | 2024-03-13T05:43:19Z |
publishDate | 2023-01-01 |
publisher | IEEE |
record_format | Article |
series | IEEE Access |
spelling | doaj.art-0edfb246b65e45278fc33b2cb9ee2f3c2023-06-13T23:00:23ZengIEEEIEEE Access2169-35362023-01-0111527265273910.1109/ACCESS.2023.327298710115411Investigating the Use of Machine Learning Models to Understand the Drugs Permeability Across PlacentaVaisali Chandrasekar0Mohammed Yusuf Ansari1Ajay Vikram Singh2Shahab Uddin3https://orcid.org/0000-0003-1886-6710Kirthi S. Prabhu4Sagnika Dash5Souhaila Al Khodor6Annalisa Terranegra7https://orcid.org/0000-0001-9274-5373Matteo Avella8Sarada Prasad Dakua9https://orcid.org/0000-0003-2979-0272Department of Surgery, Hamad Medical Corporation, Doha, QatarElectrcial and Computer Engineering, Texas A&M University, College Station, TX, USAGerman Federal Institute for Risk Assessment (BfR), Berlin, GermanyHamad Medical Corporation, Translational Research Institute, Academic Health System, Doha, QatarHamad Medical Corporation, Translational Research Institute, Academic Health System, Doha, QatarDepartment of Obstetrics and Gynecology, Apollo Clinic, Doha, QatarMaternal and Child Health Department, Research Branch, Sidra Medicine, Ar-Rayyan, Doha, QatarMaternal and Child Health Department, Research Branch, Sidra Medicine, Ar-Rayyan, Doha, QatarMaternal and Child Health Department, Research Branch, Sidra Medicine, Ar-Rayyan, Doha, QatarDepartment of Surgery, Hamad Medical Corporation, Doha, QatarOwing to limited drug testing possibilities in pregnant population, the development of computational algorithms is crucial to predict the fate of drugs in the placental barrier; it could serve as an alternative to animal testing. The ability of a molecule to effectively cross the placental barrier and reach the fetus determines the drug’s toxicological effects on the fetus. In this regard, our study aims to predict the permeability of molecules across the placental barrier. Based on publicly available datasets, several machine learning models are comprehensively analysed across different fingerprints and toolkits to find the best suitable models. Several dataset analysis models are utilised to study the data diversity. Further, this study demonstrates the application of neural network-based models to effectively predict the permeability. K-nearest neighbour (KNN), standard vector classifier (SVC) and Multi-layer perceptron (MLP) are found to be the best-performing models with a prediction percentage of 82%, 86.4% and 90.8%, respectively. Different models are compared to predict the chosen set of drugs, drugs like Aliskiren, some insulin secretagogues and glucocorticoids are found to be negative while predicting the permeability.https://ieeexplore.ieee.org/document/10115411/Placenta barriermachine learningdrug permeabilitydevelopmental toxicity |
spellingShingle | Vaisali Chandrasekar Mohammed Yusuf Ansari Ajay Vikram Singh Shahab Uddin Kirthi S. Prabhu Sagnika Dash Souhaila Al Khodor Annalisa Terranegra Matteo Avella Sarada Prasad Dakua Investigating the Use of Machine Learning Models to Understand the Drugs Permeability Across Placenta IEEE Access Placenta barrier machine learning drug permeability developmental toxicity |
title | Investigating the Use of Machine Learning Models to Understand the Drugs Permeability Across Placenta |
title_full | Investigating the Use of Machine Learning Models to Understand the Drugs Permeability Across Placenta |
title_fullStr | Investigating the Use of Machine Learning Models to Understand the Drugs Permeability Across Placenta |
title_full_unstemmed | Investigating the Use of Machine Learning Models to Understand the Drugs Permeability Across Placenta |
title_short | Investigating the Use of Machine Learning Models to Understand the Drugs Permeability Across Placenta |
title_sort | investigating the use of machine learning models to understand the drugs permeability across placenta |
topic | Placenta barrier machine learning drug permeability developmental toxicity |
url | https://ieeexplore.ieee.org/document/10115411/ |
work_keys_str_mv | AT vaisalichandrasekar investigatingtheuseofmachinelearningmodelstounderstandthedrugspermeabilityacrossplacenta AT mohammedyusufansari investigatingtheuseofmachinelearningmodelstounderstandthedrugspermeabilityacrossplacenta AT ajayvikramsingh investigatingtheuseofmachinelearningmodelstounderstandthedrugspermeabilityacrossplacenta AT shahabuddin investigatingtheuseofmachinelearningmodelstounderstandthedrugspermeabilityacrossplacenta AT kirthisprabhu investigatingtheuseofmachinelearningmodelstounderstandthedrugspermeabilityacrossplacenta AT sagnikadash investigatingtheuseofmachinelearningmodelstounderstandthedrugspermeabilityacrossplacenta AT souhailaalkhodor investigatingtheuseofmachinelearningmodelstounderstandthedrugspermeabilityacrossplacenta AT annalisaterranegra investigatingtheuseofmachinelearningmodelstounderstandthedrugspermeabilityacrossplacenta AT matteoavella investigatingtheuseofmachinelearningmodelstounderstandthedrugspermeabilityacrossplacenta AT saradaprasaddakua investigatingtheuseofmachinelearningmodelstounderstandthedrugspermeabilityacrossplacenta |