OctSurf: Efficient hierarchical voxel-based molecular surface representation for protein-ligand affinity prediction.

Voxel-based 3D convolutional neural networks (CNNs) have been applied to predict protein-ligand binding affinity. However, the memory usage and computation cost of these voxel-based approaches increase cubically with respect to spatial resolution and sometimes make volumetric CNNs intractable at higher resolutions. Therefore, it is necessary to develop memory-efficient alternatives that can accelerate the convolutional operation on 3D volumetric representations of the protein-ligand interaction. In this study, we implement a novel volumetric representation, OctSurf, to characterize the 3D molecular surface of protein binding pockets and bound ligands. The OctSurf surface representation is built based on the octree data structure, which has been widely used in computer graphics to efficiently represent and store 3D object data. Vanilla 3D-CNN approaches often divide the 3D space of objects into equal-sized voxels. In contrast, OctSurf recursively partitions the 3D space containing the protein-ligand pocket into eight subspaces called octants. Only those octants containing van der Waals surface points of protein or ligand atoms undergo the recursive subdivision process until they reach the predefined octree depth, whereas unoccupied octants are kept intact to reduce the memory cost. Resulting non-empty leaf octants approximate molecular surfaces of the protein pocket and bound ligands. These surface octants, along with their chemical and geometric features, are used as the input to 3D-CNNs. Two kinds of CNN architectures, VGG and ResNet, are applied to the OctSurf representation to predict binding affinity. The OctSurf representation consumes much less memory than the conventional voxel representation at the same resolution. By restricting the convolution operation to only octants of the smallest size, our method also alleviates the overall computational overhead of CNN. A series of experiments are performed to demonstrate the disk storage and computational efficiency of the proposed learning method. Our code is available at the following GitHub repository: https://github.uconn.edu/mldrugdiscovery/OctSurf.

Effect of three-dimensional porosity gradients of biomimetic coatings on their bonding strength and cell behavior.

Surface modification techniques are often used to enhance the properties of Ti-based materials as hard-tissue replacements. While the microstructure of the coating and the quality of the interface between the substrate and coating are essential to evaluate the reliability and applicability of the surface modification. In this study, both a hydroxyapatite (HA) coating and a collagen-hydroxyapatite (Col-HA) composite coating were deposited onto a Ti-6Al-4V substrate using a biomimetic coating process. Importantly, a gradient cross-sectional structure with a porous coating toward the surface, while a dense layer adjacent to the interface between the coating and substrate was observed in three-dimensional (3D) from both the HA and Col-HA coatings via a dual-beam focused ion beam-scanning electron microscope (FIB-SEM). Moreover, the pore distributions within the entire coatings were reconstructed in 3D using Avizo, and the pores size distributions along the coating depth were calculated using RStudio. By evaluating the mechanical property and biocompatibility of these materials and closely observing the cross-sectional cell-coating-substrate interfaces using FIB-SEM, it was revealed that the porous surface created by both coatings well supports osteoblast cell adhesion while the dense inner layer facilitates a good bonding between the coating and the substrate. Although the mechanical property of the coating decreased with the addition of collagen, it is still strong enough for implant handling and the biocompatibility was promoted.

Benchmark on Indexing Algorithms for Accelerating Molecular Similarity Search.

Structurally similar analogues of given query compounds can be rapidly retrieved from chemical databases by the molecular similarity search approaches. However, the computational cost associated with the exhaustive similarity search of a large compound database will be quite high. Although the latest indexing algorithms can greatly speed up the search process, they cannot be readily applicable to molecular similarity search problems due to the lack of Tanimoto similarity metric implementation. In this paper, we first implement Python or C++ codes to enable the Tanimoto similarity search via several recent indexing algorithms, such as Hnsw and Onng. Moreover, there are increasing interests in computational communities to develop robust benchmarking systems to access the performance of various computational algorithms. Here, we provide a benchmark to evaluate the molecular similarity searching performance of these recent indexing algorithms. To avoid the potential package dependency issues, two separate benchmarks are built based on currently popular container technologies, Docker and Singularity. The Singularity container is a rather new container framework specifically designed for the high-performance computing (HPC) platform and does not need the privileged permissions or the separated daemon process. Both benchmarking methods are extensible to incorporate other new indexing algorithms, benchmarking data sets, and different customized parameter settings. Our results demonstrate that the graph-based methods, such as Hnsw and Onng, consistently achieve the best trade-off between searching effectiveness and searching efficiencies. The source code of the entire benchmark systems can be downloaded from https://github.uconn.edu/mldrugdiscovery/MssBenchmark.