Related Experiment Video
Updated: May 28, 2026
Nano-Differential Scanning Fluorimetry for Screening in Fragment-based Lead Discovery
Published on: May 16, 2021
A Molecular-Protein Fusion Framework for Rapid Virtual Screening: Accelerating Lead Discovery for "Undruggable''
Chenxi Zhou1, Yanni Zhu2, Chenrui Yang3
1College of Biotechnology and Pharmaceutical Engineering, Nanjing Tech University, 30 South Puzhu Road, Jiangbei New District, Nanjing 211816, China.
Abstract:
Background/Objectives: KRAS G12D is one of the most frequent oncogenic mutations in pancreatic ductal adenocarcinoma (PDAC) and remains challenging to target because of its limited druggable binding pockets. This study aimed to develop a machine learning-based framework for rapid virtual screening of potential KRAS G12D inhibitors. Methods: A molecular-protein fusion prediction framework, MPFF-IS, was constructed by integrating the ESM2 protein language model with an MPNN-GNN molecular graph network to enable joint representation learning of protein and compound features. The model was trained using a KRAS G12D inhibitor dataset and applied to screen compounds from multiple chemical libraries. AutoDock Vina docking and 300 ns GROMACS molecular dynamics simulations were subsequently performed for structural validation. Results: MPFF-IS achieved favorable predictive performance on the test dataset and identified 2663 candidate compounds from more than 134,000 screened molecules. Several candidate ligands exhibited favorable binding affinity, stable proteinligand interactions, and enhanced structural stability compared with reference inhibitors, including MRTX1133 and BI-2852. Molecular dynamics analyses further supported the stability of the predicted complexes and the involvement of key binding residues within the KRAS G12D pocket. Conclusions: These findings demonstrate that MPFF-IS can efficiently identify potential KRAS G12D inhibitors and may provide a useful computational framework for precision drug discovery targeting difficult oncogenic proteins.
Insights
A new machine learning framework, MPFF-IS, efficiently identifies potential KRAS G12D inhibitors for pancreatic cancer. This computational approach accelerates drug discovery for challenging oncogenic targets.
Area of Science:
- Computational chemistry
- Oncology
- Drug discovery
Background:
- KRAS G12D mutations are prevalent in pancreatic ductal adenocarcinoma (PDAC).
- Targeting KRAS G12D is difficult due to limited druggable pockets.
- Novel therapeutic strategies are urgently needed for PDAC.
Purpose of the Study:
- To develop a machine learning (ML) framework for rapid virtual screening of KRAS G12D inhibitors.
- To identify novel drug candidates targeting KRAS G12D mutations.
- To establish a computational tool for precision drug discovery.
Main Methods:
- Developed MPFF-IS, a molecular-protein fusion prediction framework integrating ESM2 and MPNN-GNN.
- Trained the model on a KRAS G12D inhibitor dataset and screened over 134,000 compounds.
- Validated top candidates using AutoDock Vina docking and GROMACS molecular dynamics simulations.
Main Results:
- MPFF-IS identified 2663 candidate KRAS G12D inhibitors with high predictive performance.
- Several identified compounds showed favorable binding affinity and stable interactions.
- Molecular dynamics confirmed the stability of predicted complexes and key binding residue interactions.
Conclusions:
- MPFF-IS effectively identifies potential KRAS G12D inhibitors.
- The framework offers a valuable computational tool for targeting difficult oncogenic proteins.
- This approach advances precision medicine for KRAS G12D-driven cancers.
