# A Comparative Study of Deep Learning and Classical Modeling Approaches for Protein–Ligand Binding Pose and Affinity Prediction in Coronavirus Main Proteases

## TL;DR

This study compares deep learning and traditional methods for predicting how drugs bind to coronavirus proteins, finding that deep learning models like AlphaFold3 perform best.

## Contribution

The paper introduces a new machine learning-based scoring method (LRIP-SF) and benchmarks deep learning models for pose and affinity prediction in coronavirus proteases.

## Key findings

- AlphaFold3 achieved 88.1% success rate in pose prediction with an average LRMSD of 1.12 Å.
- LRIP-SF achieved MAE of 0.606 and RMSE of 0.813 for MERS-CoV Mpro and 0.724 and 0.894 for SARS-CoV-2 Mpro.
- FlexS provided competitive potency predictions with lower computational cost despite lower pose accuracy.

## Abstract

The accurate prediction
of protein–ligand binding poses
and affinities is central to structure-based drug design. In this
study, we first benchmarked three distinct pose generation strategies
for data sets from the ASAP Antiviral Challenge 2025: molecular docking
(Glide and AutoDock Vina), ligand-based superposition (FlexS), and
deep learning-based modeling (AlphaFold3, Boltz-2, DiffDock and Gnina).
We evaluated their performance on binding pose prediction for ligands
targeting SARS-CoV-2 and MERS-CoV main protease (Mpro). For binding
affinity estimation, we implemented a machine learning-based scoring
approach called ligand–residue interaction profile scoring
function (LRIP-SF), which integrates molecular mechanics generalized
Born surface area (MM-GBSA) energy decomposition with machine learning
algorithms. Our results showed that deep learning-based modeling with
AlphaFold3 achieved the highest pose prediction accuracy with a success
rate of 88.1% and an average ligand root-mean-square deviation (LRMSD)
of 1.12 Å. Moreover, binding poses predicted by AlphaFold3 enabled
the most accurate potency predictions by LRIP-SF, with the lowest
mean absolute error (MAE) and root-mean-square error (RMSE) in pIC50 units across both targets: the MAE and RMSE are 0.606 and
0.813, respectively, for MERS-CoV Mpro and 0.724 and 0.894 respectively
for SARS-CoV-2 Mpro. Although ligand-based superposition method (FlexS)
was less accurate in pose prediction, it offered competitive potency
prediction performance with significantly lower computational cost.
To interpret model predictions by LRIP-SF and identify critical binding
determinants, we performed global sensitivity analysis (GSA), revealing
key residues that contributed most significantly to ligand binding.
These findings highlight the importance of pose quality and interaction
profiling in affinity prediction and demonstrate the great potential
of deep learning-based methods for drug discovery, especially in the
absence of cocrystal structures.