Related Experiment Video
Updated: Aug 6, 2026
A Bilingual Computational Workflow for Identifying Potential PLK1 Inhibitors in American Sign Language and English
Published on: April 3, 2026
Integrated machine learning and structural bioinformatics guided identification of novel molecular scaffolds as renin
Shubham Krushna Talware1, Girdhar Bhati1, Gaurava Srivastava1
1Division of Biochemistry and Structural Biology, CSIR-Central Drug Research Institute, Jankipuram Extension, Sitapur Road, Lucknow, 226031, Uttar Pradesh, India.
Insights
Researchers developed novel scaffolds for direct renin inhibitors (DRIs) using machine learning and drug design. Four promising compounds were identified, with HTS00804 showing significant renin inhibition, offering a new starting point for antihypertensive drug development.
Area of Science:
- Medicinal Chemistry
- Computational Chemistry
- Pharmacology
Background:
- Cardiovascular diseases are a leading global cause of death, with hypertension as a key risk factor.
- The Renin-Angiotensin-Aldosterone-System (RAAS) is crucial for blood pressure regulation and a target for antihypertensive drugs.
- Aliskiren is the sole approved direct renin inhibitor (DRI), necessitating novel scaffolds with improved properties.
Purpose of the Study:
- To identify and characterize novel chemical scaffolds with renin inhibitory activity.
- To leverage an integrated approach combining machine learning (ML), ligand-based drug design (LBDD), and structure-based drug design (SBDD).
- To discover potential starting points for next-generation direct renin inhibitors (DRIs).
Main Methods:
- Development and validation of multiple ML models using molecular descriptors and SHAP analysis for interpretability.
- Construction of ligand-based pharmacophore models based on human renin crystal structure.
- Screening of the Maybridge library, followed by molecular docking, in vitro renin inhibition assays, molecular dynamics, and MM/PBSA calculations.
- Prediction and analysis of ADME properties for identified scaffolds.
Main Results:
- Four promising renin inhibitory scaffolds (HTS00804, HTS05294, BTB13902, RJC01726) were identified from the Maybridge library.
- All identified hits exhibited IC50 values ranging from 1.29 µM to 4.19 µM.
- HTS00804 demonstrated significant in vitro renin inhibition (53% at 1µM, 73% at 10µM) and favorable predicted ADME properties.
Conclusions:
- The integrated ML, LBDD, and SBDD approach successfully identified novel chemical scaffolds for renin inhibition.
- HTS00804 represents a promising starting scaffold for further medicinal chemistry optimization towards developing new DRIs.
- This study highlights the potential of computational methods in accelerating the discovery of novel antihypertensive agents.
Abstract:
Cardiovascular diseases (CVDs) remain the leading cause of death globally, with hypertension as its critical hallmark. The Renin-Angiotensin-Aldosterone-System (RAAS) plays a central role in regulating blood pressure, highlighting its relevance for antihypertensive drug development. Despite extensive research, Aliskiren remains the only clinically approved direct renin inhibitor (DRI), underscoring the necessity for novel scaffolds with improved pharmacokinetic profiles. In this study, we employed an integrated machine learning (ML), ligand-based (LBDD), and structure-based drug design (SBDD) approach to identify and characterize new chemical scaffolds with potential renin inhibitory activity. Multiple ML models were built using various molecular descriptors, followed by extensive feature selection, and data balancing with SMOTE. To enhance model interpretability, we performed SHAP analysis on the top ML models to reveal key descriptors and substructures associated with predictions for renin inhibition. In parallel, several ligand-based pharmacophore models were constructed using the crystal structure of human renin. Maybridge library was screened using the best models resulting from both approaches, and the consensus compounds were prioritized using molecular docking to assess their inhibitory potential through the renin inhibitory assay. Molecular dynamics, along with MM/PBSA, were then employed to evaluate the structural stability and binding persistence of the screened compounds with promising activity. The predicted ADME properties and structural analysis further established the relevance of the novel scaffolds identified through our robust integrated approach. From the 12 shortlisted compounds, our study identified 4 promising hits - HTS00804, HTS05294, BTB13902, and RJC01726 with diverse piperazine and piperidine-substituted scaffolds for renin inhibition. All four hits exhibited IC50 values between 1.29 µM and 4.19 µM. Among all, HTS00804 demonstrated 53 and 73% renin inhibition in vitro at 1µM and 10 µM concentrations, respectively and can be explored as a starting scaffold for further structural optimization through medicinal chemistry efforts to design next-generation direct renin inhibitors (DRIs).
