Applications of machine learning in computer-aided drug discovery

Turzo, SM Bargeen Alam; Hantz, Eric R.; Lindert, Steffen

doi:10.1017/qrd.2022.12

Cited by 5 publications

(2 citation statements)

References 189 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Both through the rapid development of new machine learning methods and better availability of binding affinity data, e.g. through PDBbind, KIBA,, and Davis, many different efforts have been explored to generate ML-based methods for BA. , …”

Section: Introductionmentioning

confidence: 99%

“…through PDBbind, 9 KIBA, 10 , and Davis, 11 many different efforts have been explored to generate ML-based methods for BA. 12,13 In this paper, we will look at some of these machine learning (ML) models for binding affinity predictions more closely to gain insights on how components of these models contribute to the performance of the binding affinity prediction task. Depending on the type of input data used during training, these deep learning (DL) methods can be broadly categorized as sequence-or complex-based methods.…”

Section: ■ Introductionmentioning

confidence: 99%

See 1 more Smart Citation

From Proteins to Ligands: Decoding Deep Learning Methods for Binding Affinity Prediction

Gorantla,

Kubincová,

Weiße

et al. 2023

J. Chem. Inf. Model.

View full text Add to dashboard Cite

Accurate in silico prediction of protein−ligand binding affinity is important in the early stages of drug discovery. Deep learning-based methods exist but have yet to overtake more conventional methods such as giga-docking largely due to their lack of generalizability. To improve generalizability, we need to understand what these models learn from input protein and ligand data. We systematically investigated a sequence-based deep learning framework to assess the impact of protein and ligand encodings on predicting binding affinities for commonly used kinase data sets. The role of proteins is studied using convolutional neural network-based encodings obtained from sequences and graph neural network-based encodings enriched with structural information from contact maps. Ligand-based encodings are generated from graph-neural networks. We test different ligand perturbations by randomizing node and edge properties. For proteins, we make use of 3 different protein contact generation methods (AlphaFold2, Pconsc4, and ESM-1b) and compare these with a random control. Our investigation shows that protein encodings do not substantially impact the binding predictions, with no statistically significant difference in binding affinity for KIBA in the investigated metrics (concordance index, Pearson's R Spearman's Rank, and RMSE). Significant differences are seen for ligand encodings with random ligands and random ligand node properties, suggesting a much bigger reliance on ligand data for the learning tasks. Using different ways to combine protein and ligand encodings did not show a significant change in performance.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: ■ Introductionmentioning

confidence: 99%

From Proteins to Ligands: Decoding Deep Learning Methods for Binding Affinity Prediction

Gorantla,

Kubincová,

Weiße

et al. 2023

J. Chem. Inf. Model.

View full text Add to dashboard Cite

show abstract

In silico drug design strategies for discovering novel tuberculosis therapeutics

Canales,

Pavan,

dos Santos

et al. 2024

Expert Opinion on Drug Discovery

View full text Add to dashboard Cite

From Proteins to Ligands: Decoding Deep Learning Methods for Binding Affinity Prediction

Gorantla

Kubincová

Weiße

et al. 2023

Preprint

View full text Add to dashboard Cite

Accuratein silicoprediction of protein-ligand binding affinity is important in the early stages of drug discovery. Deep learning-based methods exist but have yet to overtake more conventional methods such as giga-docking largely due to their lack of generalisability. To improve generalizability we need to understand what these models learn from input protein and ligand data. We systematically investigated a sequence-based deep learning framework to assess the impact of protein and ligand encodings on predicting binding affinities for commonly used kinase data sets. The role of proteins is studied using convolutional neural network-based encodings obtained from sequences and graph neural network-based encodings enriched with structural information from contact maps. Ligand-based encodings are generated from graph-neural networks. We test different ligand perturbations by randomizing node and edge properties. For proteins we make use of 3 different protein contact generation methods (AlphaFold2, Pconsc4, and ESM-1b) and compare these with a random control. Our investigation shows that protein encodings do not substantially impact the binding predictions, with no statistically significant difference in binding affinity for KIBA in the investigated metrics (concordance index, Pearson’s R Spearman’s Rank, and RMSE). Significant differences are seen for ligand encodings with random ligands and random ligand node properties, suggesting a much bigger reliance on ligand data for the learning tasks. Using different ways to combine protein and ligand encodings, did not show a significant change in performance.TOC Graphic

show abstract

Applications of machine learning in computer-aided drug discovery

Cited by 5 publications

References 189 publications

From Proteins to Ligands: Decoding Deep Learning Methods for Binding Affinity Prediction

From Proteins to Ligands: Decoding Deep Learning Methods for Binding Affinity Prediction

In silico drug design strategies for discovering novel tuberculosis therapeutics

From Proteins to Ligands: Decoding Deep Learning Methods for Binding Affinity Prediction

Contact Info

Product

Resources

About