DeepPocket: Ligand Binding Site Detection and Segmentation using 3D Convolutional Neural Networks

Aggarwal, Rishal; Gupta, Akash; Chelur, Vineeth; Jawahar, C. V.

doi:10.26434/chemrxiv.14611146

Cited by 11 publications

(21 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Such a tool could provide more freedom of choice for this parameter. The work of Aggarwal et al (2021), among others, has shown that many pieces of software for pocket identification tend to identify large pockets without segmentation techniques. Segmentation could be used to find subpockets that are better suited to virtual screening and docking.…”

Section: Discussionmentioning

confidence: 99%

“…Here, the focus is on characterizing protein-protein interfaces (PPI) to allow designing of PPI disruptors. The capabilities of convolutional neural networks were boosted by pocket segmentation in Aggarwal et al (2021). This work and others [e.g., Stepniewska-Dziubinska et al (2020)] demonstrated that both prediction and other activities, such as segmentation, are beneficial, so one can devise a more complex framework than a pure predictor.…”

Section: Introductionmentioning

confidence: 93%

See 1 more Smart Citation

Probabilistic Pocket Druggability Prediction via One-Class Learning

et al. 2022

View full text Add to dashboard Cite

The choice of target pocket is a key step in a drug discovery campaign. This step can be supported by in silico druggability prediction. In the literature, druggability prediction is often approached as a two-class classification task that distinguishes between druggable and non-druggable (or less druggable) pockets (or voxels). Apart from obvious cases, however, the non-druggable class is conceptually ambiguous. This is because any pocket (or target) is only non-druggable until a drug is found for it. It is therefore more appropriate to adopt a one-class approach, which uses only unambiguous information, namely, druggable pockets. Here, we propose using the import vector domain description (IVDD) algorithm to support this task. IVDD is a one-class probabilistic kernel machine that we previously introduced. To feed the algorithm, we use customized DrugPred descriptors computed via NanoShaper. Our results demonstrate the feasibility and effectiveness of the approach. In particular, we can remove or mitigate biases chiefly due to the labeling.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 93%

Probabilistic Pocket Druggability Prediction via One-Class Learning

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Traditional computational methods for scanning proteins for their most "druggable" areas have leveraged various views such as utilizing the protein's 3D structure or/and residue sequence, extracting geometric features, building large template libraries, or relying on energy-based models (Macari et al, 2019). Recently, DL changed this paradigm, e.g., using 3D CNNs (Aggarwal et al, 2021;Jiménez et al, 2017;Torng & Altman, 2019b) or sequence models (Sankararaman et al, 2010).…”

Section: Related Workmentioning

confidence: 99%

EquiBind: Geometric Deep Learning for Drug Binding Structure Prediction

Stark¹,

Ganea²,

Pattanaik³

et al. 2022

Preprint

View full text Add to dashboard Cite

Predicting how a drug-like molecule binds to a specific protein target is a core problem in drug discovery. An extremely fast computational binding method would enable key applications such as fast virtual screening or drug engineering. Existing methods are computationally expensive as they rely on heavy candidate sampling coupled with scoring, ranking, and fine-tuning steps. We challenge this paradigm with EQUIBIND, an SE(3)-equivariant geometric deep learning model performing direct-shot prediction of both i) the receptor binding location (blind docking) and ii) the ligand's bound pose and orientation. EquiBind achieves significant speed-ups and better quality compared to traditional and recent baselines. Further, we show extra improvements when coupling it with existing fine-tuning techniques at the cost of increased running time. Finally, we propose a novel and fast fine-tuning model that adjusts torsion angles of a ligand's rotatable bonds based on closed-form global minima of the von Mises angular distance to a given input atomic point cloud, avoiding previous expensive differential evolution strategies for energy minimization.

show abstract

“…Inspired by the previous studies [15][16][17], in this work, we mainly focused on rebuilding the CNN model using a more accurate model, and enlarging the training set to further optimize the model performance. Previous reports adopted different versions of scPDB dataset for training the deep learning model [15][16][17]20].…”

Section: Introductionmentioning

confidence: 99%

DUnet: A deep learning guided protein-ligand binding pocket prediction

Wang

Zhao

Yang

et al. 2022

Preprint

View full text Add to dashboard Cite

Investigating protein-ligand binding sites is the key step in engineering protein/enzyme activity and selectivity. In this study, we developed a 3D convolutional neural network DUnet that derived from DenseNet and UNet for predicting the protein-ligand binding sites. To train DUnet, the features of protein 3D structure were extracted by describing the atomic physical characters, and the ligand binding sites were used as training labels. DUnet was trained using three dataset, the scPDB dataset (collecting of protein-ligand complexes from Protein Data Bank), scPDB and SC6K (collecting of protein-ligand complexes deposited after January 1st, 2018 from Protein Data Bank) datasets, and scPDB and its derived dataset by rotating the samples in the dataset. DUnet displayed better performance than the current state-of-art methods during the benchmark test using independent validation sets, and enlarging the training set contributed to better accuracy. We developed a small dataset contains commonly used industrial enzymes for testing DUnet and found that it was also accurate in predicting the substrate binding sites. We experimentally characterized the substrate binding sites of microbial transglutaminase according to the prediction and showed the significance of these sites. Finally, DUnet was used to predict the ligand binding sites of Swiss-Prot annotated proteins.

show abstract

DeepPocket: Ligand Binding Site Detection and Segmentation using 3D Convolutional Neural Networks

Cited by 11 publications

References 36 publications

Probabilistic Pocket Druggability Prediction via One-Class Learning

Probabilistic Pocket Druggability Prediction via One-Class Learning

EquiBind: Geometric Deep Learning for Drug Binding Structure Prediction

DUnet: A deep learning guided protein-ligand binding pocket prediction

Contact Info

Product

Resources

About