Multi-TransDTI: Transformer for Drug–Target Interaction Prediction Based on Simple Universal Dictionaries with Multi-View Strategy

Graph reasoning method enhanced by relational transformers and knowledge distillation for drug-related side effect prediction

Identifying the side effects related to drugs is beneficial for reducing the risk of drug development failure and saving the drug development cost. We proposed a graph reasoning method, RKDSP, to fuse the semantics of multiple connection relationships, the local knowledge within each meta-path, the global knowledge among multiple meta-paths, and the attributes of the drug and side effect node pairs. We constructed drug-side effect heterogeneous graphs consisting of the drugs, side effects, and their similarity and association connections. Multiple relational transformers were established to learn node features from diverse meta-path semantic perspectives. A knowledge distillation module was constructed to learn local and global knowledge of multiple meta-paths. Finally, an adaptive convolutional neural network-based strategy was presented to adaptively encode the attributes of each drug-side effect node pair. The experimental results demonstrated that RKDSP outperforms the compared state-of-the-art prediction approaches.

Machine Learning for Sequence and Structure-Based Protein-Ligand Interaction Prediction

Developing new drugs is too expensive and time -consuming. Accurately predicting the interaction between drugs and targets will likely change how the drug is discovered. Machine learning-based protein-ligand interaction prediction has demonstrated significant potential. In this paper, computational methods, focusing on sequence and structure to study protein-ligand interactions, are examined. Therefore, this paper starts by presenting an overview of the data sets applied in this area, as well as the various approaches applied for representing proteins and ligands. Then, sequence-based and structure-based classification criteria are subsequently utilized to categorize and summarize both the classical machine learning models and deep learning models employed in protein-ligand interaction studies. Moreover, the evaluation methods and interpretability of these models are proposed. Furthermore, delving into the diverse applications of protein-ligand interaction models in drug research is presented. Lastly, the current challenges and future directions in this field are addressed.

DNMG: Deep molecular generative model by fusion of 3D information for de novo drug design

Deep learning is improving and changing the process of de novo molecular design at a rapid pace. In recent years, great progress has been made in drug discovery and development by using deep generative models for de novo molecular design. However, most of the existing methods are string-based or graph-based and are limited by the lack of some very important properties, such as the three-dimensional information of molecules. We propose DNMG, a deep generative adversarial network (GAN) combined with transfer learning. Specifically, we use a Wasserstein-variant GAN based network architecture that considers the 3D grid spatial information of the ligand with atomic physicochemical properties to generate a representation of the molecule, which is then parsed into SMILES strings using an improved captioning network. Comprehensive in experiments demonstrate the ability of DNMG to generate valid and novel drug-like ligands. The DNMG model is used to design inhibitors for three targets, MK14, FNTA, and CDK2. The computational results show that the molecules generated by DNMG have better binding ability to the target proteins and better physicochemical properties. Overall, our deep generative model has excellent potential to generate molecules with high binding affinity for targets and explore the space of drug-like chemistry.

A mixed reality-based navigation method for dental implant navigation method: A pilot study

This in vitro study aimed to put forward the development and investigation of a novel Mixed Reality (MR)-based dental implant navigation method and evaluate implant accuracy. Data were collected using 3D-cone beam computed tomography. The MR-based navigation system included a Hololens headset, an NDI (Northern Digital Inc.) Polaris optical tracking system, and a computer. A software system was developed. Resin models of dentition defects were created for a randomized comparison study with the MR-based navigation implantation system (MR group, n = 25) and the conventional free-hand approach (FH group, n = 25). Implant surgery on the models was completed by an oral surgeon. The precision and feasibility of the MR-based navigation method in dental implant surgery were assessed and evaluated by calculating the entry deviation, middle deviation, apex deviation, and angular deviation values of the implant. The system, including both the hardware and software, for the MR-based dental implant navigation method were successfully developed and a workflow of the method was established. Three-Dimensional (3D) reconstruction and visualization of the surgical instruments, dentition, and jawbone were achieved. Real-time tracking of implant tools and jaw model, holographic display via the MR headset, surgical guidance, and visualization of the intraoperative implant trajectory deviation from the planned trajectory were captured by our system. The MR-based navigation system was with better precise than the free-hand approach for entry deviation (MR: 0.6914 ± 0.2507 mm, FH: 1.571 ± 0.5004 mm, P = 0.000), middle deviation (MR: 0.7156 ± 0.2127 mm, FH: 1.170 ± 0.3448 mm, P = 0.000), apex deviation (MR: 0.7869 ± 0.2298 mm, FH: 0.9190 ± 0.3319 mm, P = 0.1082), and angular deviation (MR: 1.849 ± 0.6120°, FH: 4.933 ± 1.650°, P = 0.000).

PETrans: De Novo Drug Design with Protein-Specific Encoding Based on Transfer Learning

Recent years have seen tremendous success in the design of novel drug molecules through deep generative models. Nevertheless, existing methods only generate drug-like molecules, which require additional structural optimization to be developed into actual drugs. In this study, a deep learning method for generating target-specific ligands was proposed. This method is useful when the dataset for target-specific ligands is limited. Deep learning methods can extract and learn features (representations) in a data-driven way with little or no human participation. Generative pretraining (GPT) was used to extract the contextual features of the molecule. Three different protein-encoding methods were used to extract the physicochemical properties and amino acid information of the target protein. Protein-encoding and molecular sequence information are combined to guide molecule generation. Transfer learning was used to fine-tune the pretrained model to generate molecules with better binding ability to the target protein. The model was validated using three different targets. The docking results show that our model is capable of generating new molecules with higher docking scores for the target proteins.

TripDesign: A DNA Triplex Design Approach Based on Interaction Forces

A DNA triplex has the advantages of improved nanostructure stability and pH environment responsiveness compared with single-stranded and double-stranded nucleic acids. However, sequence stability and low design efficiency hinder the application of DNA triplexes. Therefore, a DNA triplex design approach (TripDesign) based on interaction forces is proposed. First, we present the stacking force constraint, torsional stress constraint, and G-quadruplex motif constraint and then use an improved memetic algorithm to design triplex sequences under combinatorial constraints. Finally, to quantify the process of triplex formation, we also explore the minimum length of the triplex-forming oligos (TFOs) required to form the triplex and the factors that produce depletion in cyclic pH-jump experiments. The experimental results show that the sequences produced by TripDesign have high stability and reversibility, and the proposed approach achieves efficient and automatic sequence design. In addition, this study characterizes multiple basic parameters of DNA triplex formation and promotes the wider application of DNA triplexes in nanotechnology.

EFMSDTI: Drug-target interaction prediction based on an efficient fusion of multi-source data

Accurate identification of Drug Target Interactions (DTIs) is of great significance for understanding the mechanism of drug treatment and discovering new drugs for disease treatment. Currently, computational methods of DTIs prediction that combine drug and target multi-source data can effectively reduce the cost and time of drug development. However, in multi-source data processing, the contribution of different source data to DTIs is often not considered. Therefore, how to make full use of the contribution of different source data to predict DTIs for efficient fusion is the key to improving the prediction accuracy of DTIs. In this paper, considering the contribution of different source data to DTIs prediction, a DTIs prediction approach based on an effective fusion of drug and target multi-source data is proposed, named EFMSDTI. EFMSDTI first builds 15 similarity networks based on multi-source information networks classified as topological and semantic graphs of drugs and targets according to their biological characteristics. Then, the multi-networks are fused by selective and entropy weighting based on similarity network fusion (SNF) according to their contribution to DTIs prediction. The deep neural networks model learns the embedding of low-dimensional vectors of drugs and targets. Finally, the LightGBM algorithm based on Gradient Boosting Decision Tree (GBDT) is used to complete DTIs prediction. Experimental results show that EFMSDTI has better performance (AUROC and AUPR are 0.982) than several state-of-the-art algorithms. Also, it has a good effect on analyzing the top 1000 prediction results, while 990 of the first 1000DTIs were confirmed. Code and data are available at https://github.com/meng-jie/EFMSDTI.

Molormer: a lightweight self-attention-based method focused on spatial structure of molecular graph for drug-drug interactions prediction

Multi-drug combinations for the treatment of complex diseases are gradually becoming an important treatment, and this type of treatment can take advantage of the synergistic effects among drugs. However, drug-drug interactions (DDIs) are not just all beneficial. Accurate and rapid identifications of the DDIs are essential to enhance the effectiveness of combination therapy and avoid unintended side effects. Traditional DDIs prediction methods use only drug sequence information or drug graph information, which ignores information about the position of atoms and edges in the spatial structure. In this paper, we propose Molormer, a method based on a lightweight attention mechanism for DDIs prediction. Molormer takes the two-dimension (2D) structures of drugs as input and encodes the molecular graph with spatial information. Besides, Molormer uses lightweight-based attention mechanism and self-attention distilling to process spatially the encoded molecular graph, which not only retains the multi-headed attention mechanism but also reduces the computational and storage costs. Finally, we use the Siamese network architecture to serve as the architecture of Molormer, which can make full use of the limited data to train the model for better performance and also limit the differences to some extent between networks dealing with drug features. Experiments show that our proposed method outperforms state-of-the-art methods in Accuracy, Precision, Recall and F1 on multi-label DDIs dataset. In the case study section, we used Molormer to make predictions of new interactions for the drugs Aliskiren, Selexipag and Vorapaxar and validated parts of the predictions. Code and models are available at https://github.com/IsXudongZhang/Molormer.