Binding site matching in rational drug design: algorithms and applications

Naderi, Misagh; Lemoine, Jeffrey Mitchell; Govindaraj, Rajiv Gandhi; Kana, Omar Zade; Feinstein, Wei P.; Bryliński, Michał

doi:10.1093/bib/bby078

Cited by 41 publications

(42 citation statements)

References 154 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is therefore unsurprising that varied algorithms for pocket matching differ in the manner by which cavities are represented, or as to how different feature types are weighted in the resulting measure of similarity. We argue that a solution that is able to learn from data is expected to perform well since this offers the possibility to remove bias associated with hand-engineered protein pocket representations and their matching, others have also expressed this view (Naderi et al, 2018).…”

Section: Introductionmentioning

confidence: 92%

“…Increasingly, there is interest in applying pocket matching approaches to large datasets of protein structures to enable proteome-wide analysis (Holm and Sander, 1996;Hou et al, 2005;Degac et al, 2015;Meyers et al, 2016;Bhagavat et al, 2018). Existing approaches for quantifying the structural similarity between a pair of putative protein binding sites exhibit a range of handcrafted pocket representations, as well as a combination of alignmentdependent and alignment-free algorithms for comparison (Ehrt et al, 2016;Naderi et al, 2018).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

DeeplyTough: Learning Structural Comparison of Protein Binding Sites

Simonovsky

Meyers

2019

Preprint

View full text Add to dashboard Cite

Motivation: Protein binding site comparison (pocket matching) is of importance in drug discovery. Identification of similar binding sites can help guide efforts for hit finding, understanding polypharmacology and characterization of protein function. The design of pocket matching methods has traditionally involved much intuition, and has employed a broad variety of algorithms and representations of the input protein structures. We regard the high heterogeneity of past work and the recent availability of large-scale benchmarks as an indicator that a data-driven approach may provide a new perspective. Results: We propose DeeplyTough, a convolutional neural network that encodes a three-dimensional representation of protein binding sites into descriptor vectors that may be compared efficiently in an alignment-free manner by computing pairwise Euclidean distances. The network is trained with supervision: (i) to provide similar pockets with similar descriptors, (ii) to separate the descriptors of dissimilar pockets by a minimum margin, and (iii) to achieve robustness to nuisance variations. We evaluate our method using three large-scale benchmark datasets, on which it demonstrates excellent performance for held-out data coming from the training distribution and competitive performance when the trained network is required to generalize to datasets constructed independently.

show abstract

Section: Introductionmentioning

confidence: 92%

Section: Introductionmentioning

confidence: 99%

DeeplyTough: Learning Structural Comparison of Protein Binding Sites

Simonovsky

Meyers

2019

Preprint

View full text Add to dashboard Cite

show abstract

“…Recently, comparative analyses of binding sites have gained momentum due to their capacity to reveal ligandbinding similarities among proteins, regardless of their evolution (31,32). As different proteins can evolve to bind to the same ligand type (33) the accurate classification of binding sites has become an important tool for designing drugs and predicting their possible side effects through unwanted binding (34,35).…”

Section: Introductionmentioning

confidence: 99%

PickPocket : Pocket binding prediction for specific ligands family using neural networks.

Viart

Lorenzi

Moriel‐Carretero³

et al. 2020

Preprint

View full text Add to dashboard Cite

Most of the protein biological functions occur through contacts with other proteins or ligands. The residues that constitute the contact surface of a ligand-binding pocket are usually located far away within its sequence.Therefore, the identification of such motifs is more challenging than the linear protein domains. To discover new binding sites, we developed a tool called PickPocket that focuses on a small set of user-defined ligands and PickPocket: Pocket binding prediction for specific ligand families using neural networks.uses neural networks to train a ligand-binding prediction model. We tested PickPocket on fatty acid-like ligands due to their structural similarities and their under-representation in the ligand-pocket binding literature.Our results show that for fatty acid-like molecules, pocket descriptors and secondary structures are enough to obtain predictions with accuracy >90% using a dataset of 1740 manually curated ligand-binding pockets. The trained model could also successfully predict the ligandbinding pockets using unseen structural data of two recently reported fatty acid-binding proteins. We think that the PickPocket tool can help to discover new protein functions by investigating the binding sites of specific ligand families. The source code and all datasets contained in this work are freely available at https://github.com/benjaminviart/PickPocket . Author Summary :Most of the protein biological functions are defined by its interactions with other proteins or ligands. The cavity of the protein structure that receives a ligand, also called a pocket, is made of residues that are usually located far away within its sequence. Therefore understanding the PickPocket: Pocket binding prediction for specific ligand families using neural networks.complementarity of pocket and ligand is a real challenge. To discover new binding sites, we developed a tool called PickPocket that focuses on a small set of user-defined ligands to train a prediction model. Our resultsshow that for fatty acid-like molecules, pocket descriptors ( such as volume, shape, hydrophobicity… ) and secondary structures are enough to obtain predictions with accuracy >90% using a dataset of 1740 manually curated ligand-binding pockets. The trained model could also successfully predict the ligand-binding pockets using unseen structural data of two recently reported fatty acid-binding proteins. We think that the PickPocket tool can help to discover new protein functions by investigating the binding sites of specific ligand families.

show abstract

“…In computational biology, a fundamental question remains to be answered: given a protein structure, can we accurately identify the atoms that form the ligand-binding sites (LBS) [27]? In cellular environment, most proteins perform biological functions by interacting with other ligands, which are small molecules ranging from metal ions, organic or inorganic molecules, to polymers such as polysaccharides and short peptides [33]. The accurate identification of LBS on protein surfaces is critical for understanding the functions of the protein [19], and in turn an indispensable step for rational structure-based drug design (SBDD) [2].…”

Section: Introductionmentioning

confidence: 99%

“…Formally, the protein LBS is defined as the heavy atoms on the protein that are within a certain distance (such as 6.5Å, denoted as definition radius) to any heavy atom of the ligand [6]. Till now, various approaches have been developed for the identification of protein LBS, which are comprehensively reviewed and summarized in [33,48,40,32,31,15,29,9,39,4,34,46]. In general, the existing methods can be mainly categorized into two classes: template-based methods and template-free methods.…”

Section: Introductionmentioning

confidence: 99%

PointSite: a point cloud segmentation tool for identification of protein ligand binding atoms

Wei

et al. 2019

Preprint

View full text Add to dashboard Cite

Accurate identifications of ligand binding sites (LBS) on protein structure is critical for understanding protein function and designing structurebased drug. As the previous pocket-centric methods are usually based on the investigation of pseudo surface points (PSPs) outside the protein structure, thus inherently cannot incorporate the local connectivity and global 3D geometrical information of the protein structure. In this paper, we propose a novel point clouds segmentation method, PointSite, for accurate identification of protein ligand binding atoms, which performs protein LBS identification at the atom-level in a protein-centric manner. Specifically, we first transfer the original 3D protein structure to point clouds and then conduct segmentation through Submanifold Sparse Convolution (SSC) based U-Net. With the fine-grained atom-level binding atoms representation and enhanced feature learning, PointSite can outperform previous methods in atom-IoU by a large margin. Furthermore, our segmented binding atoms can work as a filter on predictions achieved by previous pocket-centric approaches, which significantly decreases the false-positive of LBS candidates. Through cascaded filter and re-ranking aided by the segmented atoms, state-of-the-art performance can be achieved over various canonical benchmarks and CAMEO hard targets in terms of the commonly used DCA criteria. Our code is publicly available through https://github.com/PointSite.

show abstract

Binding site matching in rational drug design: algorithms and applications

Cited by 41 publications

References 154 publications

DeeplyTough: Learning Structural Comparison of Protein Binding Sites

DeeplyTough: Learning Structural Comparison of Protein Binding Sites

PickPocket : Pocket binding prediction for specific ligands family using neural networks.

PointSite: a point cloud segmentation tool for identification of protein ligand binding atoms

Contact Info

Product

Resources

About