A new protein binding pocket similarity measure based on comparison of clouds of atoms in 3D: application to ligand prediction

Abstract

BackgroundPredicting which molecules can bind to a given binding site of a protein with known 3D structure is important to decipher the protein function, and useful in drug design. A classical assumption in structural biology is that proteins with similar 3D structures have related molecular functions, and therefore may bind similar ligands. However, proteins that do not display any overall sequence or structure similarity may also bind similar ligands if they contain similar binding sites. Quantitatively assessing the similarity between binding sites may therefore be useful to propose new ligands for a given pocket, based on those known for similar pockets.ResultsWe propose a new method to quantify the similarity between binding pockets, and explore its relevance for ligand prediction. We represent each pocket by a cloud of atoms, and assess the similarity between two pockets by aligning their atoms in the 3D space and comparing the resulting configurations with a convolution kernel. Pocket alignment and comparison is possible even when the corresponding proteins share no sequence or overall structure similarities. In order to predict ligands for a given target pocket, we compare it to an ensemble of pockets with known ligands to identify the most similar pockets. We discuss two criteria to evaluate the performance of a binding pocket similarity measure in the context of ligand prediction, namely, area under ROC curve (AUC scores) and classification based scores. We show that the latter is better suited to evaluate the methods with respect to ligand prediction, and demonstrate the relevance of our new binding site similarity compared to existing similarity measures.ConclusionsThis study demonstrates the relevance of the proposed method to identify ligands binding to known binding pockets. We also provide a new benchmark for future work in this field. The new method and the benchmark are available at http://cbio.ensmp.fr/paris/.

Identification of Similar Binding Sites to Detect Distant Polypharmacology

“…Some recent approaches have tried to escape from the positional bias of using atom coordinates. Among them, Baroni et al [86] use GRID force field analysis to locate minimal energy points, Hoffman et al [87] use of atomic densities, and Jalencas and Mestres [43] place pseudo-centres directly on the protein surface defining the binding site.…”

“…The binding site representation used in Cavbase [81,88] has been adopted by many other methods, such as MolLoc [89] or ProBiS [90] (see Table 1). In some cases, the features of the pseudo-centres have been expanded to include partial charges, [87] electrostatic potential, [85] positively (P) and negatively (N) charged regions, [91] or to differentiate between aromatic features in face and edge positions. [92] The use of pure geometric representations such as shape curvatures, spherical harmonics, wavelet coefficients or pocket frameworks has also been explored.…”

“…[112] Alternatively, Hoffman et al used a convolution kernel approach between two clouds of points. [87] Its main advantage is that it does not require a pair-wise alignment of those points, capturing instead similarities between atom densities. This allows for a smoother alignment and reflects the fact that atoms in different positions can have equivalent roles in ligand binding.…”

Isometrically invariant and allosterically aware description of deformable macromolecular surfaces: Application to the viral neuraminidase

“…Other approaches employ the spherical harmonics description of the molecular surface [10] or concern the projection of the molecular surface on Zernike functions [11]. Further, there are techniques that utilise the convolution kernel [12] or consider the heat propagation on the molecular surface [13] and [14]. Yet, all of these methods have the same drawback in that they fail to put disconnected regions into relation.…”

An Exhaustive Shape-Based Approach for Proteins' Secondary, Tertiary and Quaternary Structures Indexing, Retrieval and Docking

“…In their respective papers, (Wang et al, 2007) and (Hoffmann et al, 2010) propose to find the best global alignment, in terms of rigid transformations, in between two macromolecules. Wang et al define a cost function which evaluates the local discrepancy in between the shape of two macromolecules.…”