Table 2_QSAR-guided discovery of novel KRAS inhibitors for lung cancer therapy.xlsx

Introduction<p>KRAS mutations are key oncogenic drivers in lung cancer, yet effective pharmacological targeting has remained a major challenge due to the protein's elusive and dynamic binding pockets. Computational modeling offers a promising route to identify novel inhibitors with improv...

وصف كامل

محفوظ في:
التفاصيل البيبلوغرافية
المؤلف الرئيسي: Osasan Stephen Adebayo (22630082) (author)
مؤلفون آخرون: George Oche Ambrose (17661786) (author), Daramola Olusola (22630085) (author), Adefolalu Oluwafemi (22630088) (author), Hind A. Alzahrani (17689671) (author), Abdulkarim Hasan (16378311) (author)
منشور في: 2025
الموضوعات:
الوسوم: إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
_version_ 1852014806594224128
author Osasan Stephen Adebayo (22630082)
author2 George Oche Ambrose (17661786)
Daramola Olusola (22630085)
Adefolalu Oluwafemi (22630088)
Hind A. Alzahrani (17689671)
Abdulkarim Hasan (16378311)
author2_role author
author
author
author
author
author_facet Osasan Stephen Adebayo (22630082)
George Oche Ambrose (17661786)
Daramola Olusola (22630085)
Adefolalu Oluwafemi (22630088)
Hind A. Alzahrani (17689671)
Abdulkarim Hasan (16378311)
author_role author
dc.creator.none.fl_str_mv Osasan Stephen Adebayo (22630082)
George Oche Ambrose (17661786)
Daramola Olusola (22630085)
Adefolalu Oluwafemi (22630088)
Hind A. Alzahrani (17689671)
Abdulkarim Hasan (16378311)
dc.date.none.fl_str_mv 2025-11-17T06:27:09Z
dc.identifier.none.fl_str_mv 10.3389/fbinf.2025.1663846.s005
dc.relation.none.fl_str_mv https://figshare.com/articles/dataset/Table_2_QSAR-guided_discovery_of_novel_KRAS_inhibitors_for_lung_cancer_therapy_xlsx/30634049
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Bioinformatics
KRAS mutations
QSAR
de novo design
GA-MLR model
KRAS inhibitor
dc.title.none.fl_str_mv Table 2_QSAR-guided discovery of novel KRAS inhibitors for lung cancer therapy.xlsx
dc.type.none.fl_str_mv Dataset
info:eu-repo/semantics/publishedVersion
dataset
description Introduction<p>KRAS mutations are key oncogenic drivers in lung cancer, yet effective pharmacological targeting has remained a major challenge due to the protein's elusive and dynamic binding pockets. Computational modeling offers a promising route to identify novel inhibitors with improved potency and selectivity.</p>Methods<p>A quantitative structure–activity relationship (QSAR) modeling approach was developed to predict the inhibitory potency (pIC<sub>50</sub>) of KRAS inhibitors and support de novo drug design. Molecular descriptors for 62 inhibitors retrieved from the ChEMBL database (CHEMBL4354832) were computed using Chemopy. Following descriptor normalization and dimensionality reduction, five machine learning algorithm spartial least squares (PLS), random forest (RF), stepwise multiple linear regression (MLR), genetic algorithm optimized MLR (GA-MLR), and XGBoost were applied. Model performance was evaluated using R<sup>2</sup>, RMSE, and MAE, while permutation-based importance and SHAP analyses provided feature interpretability.</p>Results<p>Among the models tested, PLS exhibited the best predictive performance (R<sup>2</sup> = 0.851; RMSE = 0.292), followed by RF (R<sup>2</sup> = 0.796). The GA-MLR model, based on eight optimized molecular descriptors, achieved good interpretability and robust internal validation (R<sup>2</sup> = 0.677). Virtual screening of 56 de novo designed compounds within the model's applicability domain identified compound C9 with a predicted pIC<sub>50</sub>) of 8.11 as the most promising hit.</p>Discussion<p>This integrative QSAR modeling and de novo design framework effectively predicted the bioactivity of KRAS inhibitors and facilitated the identification of novel candidate molecules. The findings demonstrate the utility of combining interpretable machine learning models with virtual screening to accelerate the discovery of potent KRAS inhibitors for lung cancer therapy.</p>
eu_rights_str_mv openAccess
id Manara_ff75dbce99c48020c0eb9ff57f2bbab8
identifier_str_mv 10.3389/fbinf.2025.1663846.s005
network_acronym_str Manara
network_name_str ManaraRepo
oai_identifier_str oai:figshare.com:article/30634049
publishDate 2025
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling Table 2_QSAR-guided discovery of novel KRAS inhibitors for lung cancer therapy.xlsxOsasan Stephen Adebayo (22630082)George Oche Ambrose (17661786)Daramola Olusola (22630085)Adefolalu Oluwafemi (22630088)Hind A. Alzahrani (17689671)Abdulkarim Hasan (16378311)BioinformaticsKRAS mutationsQSARde novo designGA-MLR modelKRAS inhibitorIntroduction<p>KRAS mutations are key oncogenic drivers in lung cancer, yet effective pharmacological targeting has remained a major challenge due to the protein's elusive and dynamic binding pockets. Computational modeling offers a promising route to identify novel inhibitors with improved potency and selectivity.</p>Methods<p>A quantitative structure–activity relationship (QSAR) modeling approach was developed to predict the inhibitory potency (pIC<sub>50</sub>) of KRAS inhibitors and support de novo drug design. Molecular descriptors for 62 inhibitors retrieved from the ChEMBL database (CHEMBL4354832) were computed using Chemopy. Following descriptor normalization and dimensionality reduction, five machine learning algorithm spartial least squares (PLS), random forest (RF), stepwise multiple linear regression (MLR), genetic algorithm optimized MLR (GA-MLR), and XGBoost were applied. Model performance was evaluated using R<sup>2</sup>, RMSE, and MAE, while permutation-based importance and SHAP analyses provided feature interpretability.</p>Results<p>Among the models tested, PLS exhibited the best predictive performance (R<sup>2</sup> = 0.851; RMSE = 0.292), followed by RF (R<sup>2</sup> = 0.796). The GA-MLR model, based on eight optimized molecular descriptors, achieved good interpretability and robust internal validation (R<sup>2</sup> = 0.677). Virtual screening of 56 de novo designed compounds within the model's applicability domain identified compound C9 with a predicted pIC<sub>50</sub>) of 8.11 as the most promising hit.</p>Discussion<p>This integrative QSAR modeling and de novo design framework effectively predicted the bioactivity of KRAS inhibitors and facilitated the identification of novel candidate molecules. The findings demonstrate the utility of combining interpretable machine learning models with virtual screening to accelerate the discovery of potent KRAS inhibitors for lung cancer therapy.</p>2025-11-17T06:27:09ZDatasetinfo:eu-repo/semantics/publishedVersiondataset10.3389/fbinf.2025.1663846.s005https://figshare.com/articles/dataset/Table_2_QSAR-guided_discovery_of_novel_KRAS_inhibitors_for_lung_cancer_therapy_xlsx/30634049CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/306340492025-11-17T06:27:09Z
spellingShingle Table 2_QSAR-guided discovery of novel KRAS inhibitors for lung cancer therapy.xlsx
Osasan Stephen Adebayo (22630082)
Bioinformatics
KRAS mutations
QSAR
de novo design
GA-MLR model
KRAS inhibitor
status_str publishedVersion
title Table 2_QSAR-guided discovery of novel KRAS inhibitors for lung cancer therapy.xlsx
title_full Table 2_QSAR-guided discovery of novel KRAS inhibitors for lung cancer therapy.xlsx
title_fullStr Table 2_QSAR-guided discovery of novel KRAS inhibitors for lung cancer therapy.xlsx
title_full_unstemmed Table 2_QSAR-guided discovery of novel KRAS inhibitors for lung cancer therapy.xlsx
title_short Table 2_QSAR-guided discovery of novel KRAS inhibitors for lung cancer therapy.xlsx
title_sort Table 2_QSAR-guided discovery of novel KRAS inhibitors for lung cancer therapy.xlsx
topic Bioinformatics
KRAS mutations
QSAR
de novo design
GA-MLR model
KRAS inhibitor