Accurate protein-ligand binding affinity estimation is pivotal in pharmaceuticals and disease research. It fuels drug discovery by identifying potent drug candidates, optimizing drug design, and uncovering new therapeutic targets. Computational methods, such as molecular docking, molecular dynamics simulations, and accurate energy estimation via quantum methods had shown to significantly improve the prediction of protein-ligand binding affinities. The integration of AI and big data is further revolutionizing the field. The precise estimation of protein-ligand binding affinities significantly impacts pharmaceutical advancements, enabling the development of safer and more effective drugs and enhancing our understanding of the molecular basis of diseases.
The goal of this Research Topic is to bring together a collection of papers that individually and collectively utilize docking, molecular dynamics, quantum methods and AI to improve protein-ligand binding affinity predictions. In so doing, significant impacts will progress towards pharmaceutical advancements, enabling the development of safer and more effective drugs and enhancing our understanding of the molecular basis of diseases.
We welcome the submission of manuscripts including, but not limited to, the following topics: Special focus will be given (but is not restricted) to:
• Machine Learning and Deep Learning Approaches:
o Developing and improving machine learning and deep learning models for predicting binding affinities.
o Incorporating various features such as protein-ligand interaction fingerprints, structural information, sequence-based features, electron densities into predictive models.
• Free Energy Calculation Methods:
o Advancing free energy calculation methods, such as molecular dynamics simulations and free energy perturbation, to accurately estimate binding affinities.
o Developing enhanced sampling techniques to improve the efficiency of free energy calculations.
• Machine Learning Fairness and Bias:
o Addressing fairness and bias concerns in binding affinity prediction models to ensure equitable and unbiased predictions for different populations.
Keywords:
Protein-ligand Binding Affinity, Potency prediction, AI for potency prediction, Machine Leaning and big data for potency, FEP
Important Note:
All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.
Accurate protein-ligand binding affinity estimation is pivotal in pharmaceuticals and disease research. It fuels drug discovery by identifying potent drug candidates, optimizing drug design, and uncovering new therapeutic targets. Computational methods, such as molecular docking, molecular dynamics simulations, and accurate energy estimation via quantum methods had shown to significantly improve the prediction of protein-ligand binding affinities. The integration of AI and big data is further revolutionizing the field. The precise estimation of protein-ligand binding affinities significantly impacts pharmaceutical advancements, enabling the development of safer and more effective drugs and enhancing our understanding of the molecular basis of diseases.
The goal of this Research Topic is to bring together a collection of papers that individually and collectively utilize docking, molecular dynamics, quantum methods and AI to improve protein-ligand binding affinity predictions. In so doing, significant impacts will progress towards pharmaceutical advancements, enabling the development of safer and more effective drugs and enhancing our understanding of the molecular basis of diseases.
We welcome the submission of manuscripts including, but not limited to, the following topics: Special focus will be given (but is not restricted) to:
• Machine Learning and Deep Learning Approaches:
o Developing and improving machine learning and deep learning models for predicting binding affinities.
o Incorporating various features such as protein-ligand interaction fingerprints, structural information, sequence-based features, electron densities into predictive models.
• Free Energy Calculation Methods:
o Advancing free energy calculation methods, such as molecular dynamics simulations and free energy perturbation, to accurately estimate binding affinities.
o Developing enhanced sampling techniques to improve the efficiency of free energy calculations.
• Machine Learning Fairness and Bias:
o Addressing fairness and bias concerns in binding affinity prediction models to ensure equitable and unbiased predictions for different populations.
Keywords:
Protein-ligand Binding Affinity, Potency prediction, AI for potency prediction, Machine Leaning and big data for potency, FEP
Important Note:
All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.