DeepFusion: A Deep Learning Based Multi-Scale Feature Fusion Method for Predicting Drug-Target Interactions

Heterogeneous graph inference with range constrainted L2,1-collaborative matrix factorization for small molecule-miRNA association prediction

MicroRNAs (miRNAs) play a vital role in regulating gene expression and various biological processes. As a result, they have been identified as effective targets for small molecule (SM) drugs in disease treatment. Heterogeneous graph inference stands as a classical approach for predicting SM-miRNA associations, showcasing commendable convergence accuracy and speed. However, most existing methods do not adequately address the inherent sparsity in SM-miRNA association networks, and imprecise SM/miRNA similarity metrics reduce the accuracy of predicting SM-miRNA associations. In this research, we proposed a heterogeneous graph inference with range constrained L2,1-collaborative matrix factorization (HGIRCLMF) method to predict potential SM-miRNA associations. First, we computed the multi-source similarities of SM/miRNA and integrated these similarity information into a comprehensive SM/miRNA similarity. This step improved the accuracy of SM and miRNA similarity, ensuring reliability for the subsequent inference of the heterogeneity map. Second, we used a range constrained L2,1-collaborative matrix factorization (RCLMF) model to pre-populate the SM-miRNA association matrix with missing values. In this step, we developed a novel matrix decomposition method that enhances the robustness and formative nature of SM-miRNA edges between SM networks and miRNA networks. Next, we built a well-established SM-miRNA heterogeneous network utilizing the processed biological information. Finally, HGIRCLMF used this network data to infer unknown association pair scores. We implemented four cross-validation experiments on two distinct datasets, and HGIRCLMF acquired the highest areas under the curve, surpassing six state-of-the-art computational approaches. Furthermore, we performed three case studies to validate the predictive power of our method in practical application.

AIGO-DTI: Predicting Drug-Target Interactions Based on Improved Drug Properties Combined with Adaptive Iterative Algorithms

Artificial intelligence-based methods for predicting drug-target interactions (DTIs) aim to explore reliable drug candidate targets rapidly and cost-effectively to accelerate the drug development process. However, current methods are often limited by the topological regularities of drug molecules, making them difficult to generalize to a broader chemical space. Additionally, the use of similarity to measure DTI network links often introduces noise, leading to false DTI relationships and affecting the prediction accuracy. To address these issues, this study proposes an Adaptive Iterative Graph Optimization (AIGO)-DTI prediction framework. This framework integrates atomic cluster information and enhances molecular features through the design of functional group prompts and graph encoders, optimizing the construction of DTI association networks. Furthermore, the optimization of graph structure is transformed into a node similarity learning problem, utilizing multihead similarity metric functions to iteratively update the network structure to improve the quality of DTI information. Experimental results demonstrate the outstanding performance of AIGO-DTI on multiple public data sets and label reversal data sets. Case studies, molecular docking, and existing research validate its effectiveness and reliability. Overall, the method proposed in this study can construct comprehensive and reliable DTI association network information, providing new graphing and optimization strategies for DTI prediction, which contribute to efficient drug development and reduce target discovery costs.

Exploring a repurposed candidate with dual hIDO1/hTDO2 inhibitory potential for anticancer efficacy identified through pharmacophore-based virtual screening and in vitro evaluation

Discovering effective anti-cancer agents poses a formidable challenge given the limited efficacy of current therapeutic modalities against various cancer types due to intrinsic resistance mechanisms. Cancer immunochemotherapy is an alternative strategy for breast cancer treatment and overcoming cancer resistance. Human Indoleamine 2,3-dioxygenase (hIDO1) and human Tryptophan 2,3-dioxygenase 2 (hTDO2) play pivotal roles in tryptophan metabolism, leading to the generation of kynurenine and other bioactive metabolites. This process facilitates the de novo synthesis of Nicotinamide Dinucleotide (NAD), promoting cancer resistance. This study identified a new dual hIDO1/hTDO2 inhibitor using a drug repurposing strategy of FDA-approved drugs. Herein, we delineate the development of a ligand-based pharmacophore model based on a training set of 12 compounds with reported hIDO1/hTDO2 inhibitory activity. We conducted a pharmacophore search followed by high-throughput virtual screening of 2568 FDA-approved drugs against both enzymes, resulting in ten hits, four of them with high potential of dual inhibitory activity. For further in silico and in vitro biological investigation, the anti-hypercholesterolemic drug Pitavastatin deemed the drug of choice in this study. Molecular dynamics (MD) simulations demonstrated that Pitavastatin forms stable complexes with both hIDO1 and hTDO2 receptors, providing a structural basis for its potential therapeutic efficacy. At nanomolar (nM) concentration, it exhibited remarkable in vitro enzyme inhibitory activity against both examined enzymes. Additionally, Pitavastatin demonstrated potent cytotoxic activity against BT-549, MCF-7, and HepG2 cell lines (IC50 = 16.82, 9.52, and 1.84 µM, respectively). Its anticancer activity was primarily due to the induction of G1/S phase arrest as discovered through cell cycle analysis of HepG2 cancer cells. Ultimately, treating HepG2 cancer cells with Pitavastatin affected significant activation of caspase-3 accompanied by down-regulation of cellular apoptotic biomarkers such as IDO, TDO, STAT3, P21, P27, IL-6, and AhR.

An NLP-based technique to extract meaningful features from drug SMILES

NLP is a well-established field in ML for developing language models that capture the sequence of words in a sentence. Similarly, drug molecule structures can also be represented as sequences using the SMILES notation. However, unlike natural language texts, special characters in drug SMILES have specific meanings and cannot be ignored. We introduce a novel NLP-based method that extracts interpretable sequences and essential features from drug SMILES notation using N-grams. Our method compares these features to Morgan fingerprint bit-vectors using UMAP-based embedding, and we validate its effectiveness through two personalized drug screening (PSD) case studies. Our NLP-based features are sparse and, when combined with gene expressions and disease phenotype features, produce better ML models for PSD. This approach provides a new way to analyze drug molecule structures represented as SMILES notation, which can help accelerate drug discovery efforts. We have also made our method accessible through a Python library.

FOTF-CPI: A compound-protein interaction prediction transformer based on the fusion of optimal transport fragments

Compound-protein interaction (CPI) affinity prediction plays an important role in reducing the cost and time of drug discovery. However, the interpretability of how fragments function in CPI is impacted by the fact that current methods ignore the affinity relationships between fragments of compounds and fragments of proteins in CPI modeling. This article introduces an improved Transformer called FOTF-CPI (a Fusion of Optimal Transport Fragments compound-protein interaction prediction model). We use an optimal transport-based fragmentation approach to improve the model's understanding of compound and protein sequences. Additionally, a fused attention mechanism is employed, which combines the features of fragments to capture full affinity information. This fused attention redistributes higher attention scores to fragments with higher affinity. Experimental results show FOTF-CPI achieves an average 2% higher performance than other models on all three datasets. Furthermore, the visualization confirms the potential of FOTF-CPI for drug discovery applications.

MSCAN: multi-scale self- and cross-attention network for RNA methylation site prediction

BACKGROUND

Epi-transcriptome regulation through post-transcriptional RNA modifications is essential for all RNA types. Precise recognition of RNA modifications is critical for understanding their functions and regulatory mechanisms. However, wet experimental methods are often costly and time-consuming, limiting their wide range of applications. Therefore, recent research has focused on developing computational methods, particularly deep learning (DL). Bidirectional long short-term memory (BiLSTM), convolutional neural network (CNN), and the transformer have demonstrated achievements in modification site prediction. However, BiLSTM cannot achieve parallel computation, leading to a long training time, CNN cannot learn the dependencies of the long distance of the sequence, and the Transformer lacks information interaction with sequences at different scales. This insight underscores the necessity for continued research and development in natural language processing (NLP) and DL to devise an enhanced prediction framework that can effectively address the challenges presented.

RESULTS

This study presents a multi-scale self- and cross-attention network (MSCAN) to identify the RNA methylation site using an NLP and DL way. Experiment results on twelve RNA modification sites (m6A, m1A, m5C, m5U, m6Am, m7G, Ψ, I, Am, Cm, Gm, and Um) reveal that the area under the receiver operating characteristic of MSCAN obtains respectively 98.34%, 85.41%, 97.29%, 96.74%, 99.04%, 79.94%, 76.22%, 65.69%, 92.92%, 92.03%, 95.77%, 89.66%, which is better than the state-of-the-art prediction model. This indicates that the model has strong generalization capabilities. Furthermore, MSCAN reveals a strong association among different types of RNA modifications from an experimental perspective. A user-friendly web server for predicting twelve widely occurring human RNA modification sites (m6A, m1A, m5C, m5U, m6Am, m7G, Ψ, I, Am, Cm, Gm, and Um) is available at http://47.242.23.141/MSCAN/index.php .

CONCLUSIONS

A predictor framework has been developed through binary classification to predict RNA methylation sites.

MTTLm6A: A multi-task transfer learning approach for base-resolution mRNA m6A site prediction based on an improved transformer

N6-methyladenosine (m6A) is a crucial RNA modification involved in various biological activities. Computational methods have been developed for the detection of m6A sites in Saccharomyces cerevisiae at base-resolution due to their cost-effectiveness and efficiency. However, the generalization of these methods has been hindered by limited base-resolution datasets. Additionally, RMBase contains a vast number of low-resolution m6A sites for Saccharomyces cerevisiae, and base-resolution sites are often inferred from these low-resolution results through post-calibration. We propose MTTLm6A, a multi-task transfer learning approach for base-resolution mRNA m6A site prediction based on an improved transformer. First, the RNA sequences are encoded by using one-hot encoding. Then, we construct a multi-task model that combines a convolutional neural network with a multi-head-attention deep framework. This model not only detects low-resolution m6A sites, it also assigns reasonable probabilities to the predicted sites. Finally, we employ transfer learning to predict base-resolution m6A sites based on the low-resolution m6A sites. Experimental results on Saccharomyces cerevisiae m6A and Homo sapiens m1A data demonstrate that MTTLm6A respectively achieved area under the receiver operating characteristic (AUROC) values of 77.13% and 92.9%, outperforming the state-of-the-art models. At the same time, it shows that the model has strong generalization ability. To enhance user convenience, we have made a user-friendly web server for MTTLm6A publicly available at http://47.242.23.141/MTTLm6A/index.php.

TeM-DTBA: time-efficient drug target binding affinity prediction using multiple modalities with Lasso feature selection

Drug discovery, especially virtual screening and drug repositioning, can be accelerated through deeper understanding and prediction of Drug Target Interactions (DTIs). The advancement of deep learning as well as the time and financial costs associated with conventional wet-lab experiments have made computational methods for DTI prediction more popular. However, the majority of these computational methods handle the DTI problem as a binary classification task, ignoring the quantitative binding affinity that determines the drug efficacy to their target proteins. Moreover, computational space as well as execution time of the model is often ignored over accuracy. To address these challenges, we introduce a novel method, called Time-efficient Multimodal Drug Target Binding Affinity (TeM-DTBA), which predicts the binding affinity between drugs and targets by fusing different modalities based on compound structures and target sequences. We employ the Lasso feature selection method, which lowers the dimensionality of feature vectors and speeds up the proposed model training time by more than 50%. The results from two benchmark datasets demonstrate that our method outperforms state-of-the-art methods in terms of performance. The mean squared errors of 18.8% and 23.19%, achieved on the KIBA and Davis datasets, respectively, suggest that our method is more accurate in predicting drug-target binding affinity.

MATT-DDI: Predicting multi-type drug-drug interactions via heterogeneous attention mechanisms

The joint use of multiple drugs can result in adverse drug-drug interactions (DDIs) and side effects that harm the body. Accurate identification of DDIs is crucial for avoiding accidental drug side effects and understanding potential mechanisms underlying DDIs. Several computational methods have been proposed for multi-type DDI prediction, but most rely on the similarity profiles of drugs as the drug feature vectors, which may result in information leakage and overoptimistic performance when predicting interactions between new drugs. To address this issue, we propose a novel method, MATT-DDI, for predicting multi-type DDIs based on the original feature vectors of drugs and multiple attention mechanisms. MATT-DDI consists of three main modules: the top k most similar drug pair selection module, heterogeneous attention mechanism module and multi‑type DDI prediction module. Firstly, based on the feature vector of the input drug pair (IDP), k drug pairs that are most similar to the input drug pair from the training dataset are selected according to cosine similarity between drug pairs. Then, the vectors of k selected drug pairs are averaged to obtain a new drug pair (NDP). Next, IDP and NDP are fed into heterogeneous attention modules, including scaled dot product attention and bilinear attention, to extract latent feature vectors. Finally, these latent feature vectors are taken as input of the classification module to predict DDI types. We evaluated MATT-DDI on three different tasks. The experimental results show that MATT-DDI provides better or comparable performance compared to several state-of-the-art methods, and its feasibility is supported by case studies. MATT-DDI is a robust model for predicting multi-type DDIs with excellent performance and no information leakage.

Drug-drug interaction prediction based on local substructure features and their complements

The properties of drugs may undergo changes when multiple drugs are co-administered to treat co-existing or complex diseases, potentially leading to unforeseen drug-drug interactions (DDIs). Therefore, predicting potential drug-drug interactions has been an important task in pharmaceutical research. However, the following challenges remain: (1) existing methods do not work very well in cold-start scenarios, and (2) the interpretability of existing methods is not satisfactory. To address these challenges, we proposed a multi-channel feature fusion method based on local substructure features of drugs and their complements (LSFC). The local substructure features are extracted from each drug, interacted with those of another drug, and then integrated with the global features of two drugs for DDI prediction. We evaluated LSFC on two real-world DDI datasets in worm-start and cold-start scenarios. Comprehensive experiments demonstrate that LSFC consistently improved DDI prediction performance compared with the start-of-the-art methods. Moreover, visual inspection results showed that LSFC can detect crucial substructures of drugs for DDIs, providing interpretable DDI prediction. The source codes and data are available at https://github.com/Zhang-Yang-ops/LSFC.

Revolutionizing Medicinal Chemistry: The Application of Artificial Intelligence (AI) in Early Drug Discovery

Artificial intelligence (AI) has permeated various sectors, including the pharmaceutical industry and research, where it has been utilized to efficiently identify new chemical entities with desirable properties. The application of AI algorithms to drug discovery presents both remarkable opportunities and challenges. This review article focuses on the transformative role of AI in medicinal chemistry. We delve into the applications of machine learning and deep learning techniques in drug screening and design, discussing their potential to expedite the early drug discovery process. In particular, we provide a comprehensive overview of the use of AI algorithms in predicting protein structures, drug-target interactions, and molecular properties such as drug toxicity. While AI has accelerated the drug discovery process, data quality issues and technological constraints remain challenges. Nonetheless, new relationships and methods have been unveiled, demonstrating AI's expanding potential in predicting and understanding drug interactions and properties. For its full potential to be realized, interdisciplinary collaboration is essential. This review underscores AI's growing influence on the future trajectory of medicinal chemistry and stresses the importance of ongoing synergies between computational and domain experts.

Multiscale Feature-Learning with a Unified Model for Hyperspectral Image Classification

In the realm of hyperspectral image classification, the pursuit of heightened accuracy and comprehensive feature extraction has led to the formulation of an advance architectural paradigm. This study proposed a model encapsulated within the framework of a unified model, which synergistically leverages the capabilities of three distinct branches: the swin transformer, convolutional neural network, and encoder-decoder. The main objective was to facilitate multiscale feature learning, a pivotal facet in hyperspectral image classification, with each branch specializing in unique facets of multiscale feature extraction. The swin transformer, recognized for its competence in distilling long-range dependencies, captures structural features across different scales; simultaneously, convolutional neural networks undertake localized feature extraction, engendering nuanced spatial information preservation. The encoder-decoder branch undertakes comprehensive analysis and reconstruction, fostering the assimilation of both multiscale spectral and spatial intricacies. To evaluate our approach, we conducted experiments on publicly available datasets and compared the results with state-of-the-art methods. Our proposed model obtains the best classification result compared to others. Specifically, overall accuracies of 96.87%, 98.48%, and 98.62% were obtained on the Xuzhou, Salinas, and LK datasets.

A universal lesion detection method based on partially supervised learning

Partially supervised learning (PSL) is urgently necessary to explore to construct an efficient universal lesion detection (ULD) segmentation model. An annotated dataset is crucial but hard to acquire because of too many Computed tomography (CT) images and the lack of professionals in computer-aided detection/diagnosis (CADe/CADx). To address this problem, we propose a novel loss function to reduce the proportion of negative anchors which is extremely likely to classify the lesion area (positive samples) as a negative bounding box, further leading to an unexpected performance. Before calculating loss, we generate a mask to intentionally choose fewer negative anchors which will backward wrongful loss to the network. During the process of loss calculation, we set a parameter to reduce the proportion of negative samples, and it significantly reduces the adverse effect of misclassification on the model. Our experiments are implemented in a 3D framework by feeding a partially annotated dataset named DeepLesion, a large-scale public dataset for universal lesion detection from CT. We implement a lot of experiments to choose the most suitable parameter, and the result shows that the proposed method has greatly improved the performance of a ULD detector. Our code can be obtained at https://github.com/PLuld0/PLuldl.

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).

MARPPI: boosting prediction of protein-protein interactions with multi-scale architecture residual network

Protein-protein interactions (PPIs) are a major component of the cellular biochemical reaction network. Rich sequence information and machine learning techniques reduce the dependence of exploring PPIs on wet experiments, which are costly and time-consuming. This paper proposes a PPI prediction model, multi-scale architecture residual network for PPIs (MARPPI), based on dual-channel and multi-feature. Multi-feature leverages Res2vec to obtain the association information between residues, and utilizes pseudo amino acid composition, autocorrelation descriptors and multivariate mutual information to achieve the amino acid composition and order information, physicochemical properties and information entropy, respectively. Dual channel utilizes multi-scale architecture improved ResNet network which extracts protein sequence features to reduce protein feature loss. Compared with other advanced methods, MARPPI achieves 96.03%, 99.01% and 91.80% accuracy in the intraspecific datasets of Saccharomyces cerevisiae, Human and Helicobacter pylori, respectively. The accuracy on the two interspecific datasets of Human-Bacillus anthracis and Human-Yersinia pestis is 97.29%, and 95.30%, respectively. In addition, results on specific datasets of disease (neurodegenerative and metabolic disorders) demonstrate the ability to detect hidden interactions. To better illustrate the performance of MARPPI, evaluations on independent datasets and PPIs network suggest that MARPPI can be used to predict cross-species interactions. The above shows that MARPPI can be regarded as a concise, efficient and accurate tool for PPI datasets.

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.

SGAEMDA: Predicting miRNA-Disease Associations Based on Stacked Graph Autoencoder

MicroRNA (miRNA)-disease association (MDA) prediction is critical for disease prevention, diagnosis, and treatment. Traditional MDA wet experiments, on the other hand, are inefficient and costly.Therefore, we proposed a multi-layer collaborative unsupervised training base model called SGAEMDA (Stacked Graph Autoencoder-Based Prediction of Potential miRNA-Disease Associations). First, from the original miRNA and disease data, we defined two types of initial features: similarity features and association features. Second, stacked graph autoencoder is then used to learn unsupervised low-dimensional representations of meaningful higher-order similarity features, and we concatenate the association features with the learned low-dimensional representations to obtain the final miRNA-disease pair features. Finally, we used a multilayer perceptron (MLP) to predict scores for unknown miRNA-disease associations. SGAEMDA achieved a mean area under the ROC curve of 0.9585 and 0.9516 in 5-fold and 10-fold cross-validation, which is significantly higher than the other baseline methods. Furthermore, case studies have shown that SGAEMDA can accurately predict candidate miRNAs for brain, breast, colon, and kidney neoplasms.

MSLF-Net: A Multi-Scale and Multi-Level Feature Fusion Net for Diabetic Retinopathy Segmentation

Diabetic Retinopathy (DR) is a diabetic complication that predisposes patients to visual impairments that could lead to blindness. Lesion segmentation using deep learning algorithms is an effective measure to screen and prevent early DR. However, there are several types of DR with varying sizes and high inter-class similarity, making segmentation difficult. In this paper, we propose a supervised segmentation method (MSLF-Net) based on multi-scale-multi-level feature fusion to achieve accurate end-to-end DR lesion segmentation. MSLF-Net builds a Multi-Scale Feature Extraction (MSFE) module to extract multi-scale information and provide more comprehensive features for segmentation. This paper further introduces the Multi-Level Feature Fusion (MLFF) module to improve feature fusion using a cross-layer structure. This structure only fuses low- and high-level features of the same class based on category supervision, avoiding feature contamination. Moreover, this paper produces additional masked images for the dataset and performs image enhancement operations to ensure that the proposed method is trainable and functional on small datasets. The extensive experiments are conducted on public datasets IDRID and e_ophtha. The results showed that our proposed feature enhancement method can perform feature fusion more effectively. Therefore, In the end-to-end DR segmentation neural network model, MSLF Net is superior to other similar models in segmentation, and can effectively improve the DR lesion segmentation performance.

Deep learning in drug discovery: an integrative review and future challenges

Recently, using artificial intelligence (AI) in drug discovery has received much attention since it significantly shortens the time and cost of developing new drugs. Deep learning (DL)-based approaches are increasingly being used in all stages of drug development as DL technology advances, and drug-related data grows. Therefore, this paper presents a systematic Literature review (SLR) that integrates the recent DL technologies and applications in drug discovery Including, drug-target interactions (DTIs), drug-drug similarity interactions (DDIs), drug sensitivity and responsiveness, and drug-side effect predictions. We present a review of more than 300 articles between 2000 and 2022. The benchmark data sets, the databases, and the evaluation measures are also presented. In addition, this paper provides an overview of how explainable AI (XAI) supports drug discovery problems. The drug dosing optimization and success stories are discussed as well. Finally, digital twining (DT) and open issues are suggested as future research challenges for drug discovery problems. Challenges to be addressed, future research directions are identified, and an extensive bibliography is also included.

MDDI-SCL: predicting multi-type drug-drug interactions via supervised contrastive learning

The joint use of multiple drugs may cause unintended drug-drug interactions (DDIs) and result in adverse consequence to the patients. Accurate identification of DDI types can not only provide hints to avoid these accidental events, but also elaborate the underlying mechanisms by how DDIs occur. Several computational methods have been proposed for multi-type DDI prediction, but room remains for improvement in prediction performance. In this study, we propose a supervised contrastive learning based method, MDDI-SCL, implemented by three-level loss functions, to predict multi-type DDIs. MDDI-SCL is mainly composed of three modules: drug feature encoder and mean squared error loss module, drug latent feature fusion and supervised contrastive loss module, multi-type DDI prediction and classification loss module. The drug feature encoder and mean squared error loss module uses self-attention mechanism and autoencoder to learn drug-level latent features. The drug latent feature fusion and supervised contrastive loss module uses multi-scale feature fusion to learn drug pair-level latent features. The prediction and classification loss module predicts DDI types of each drug pair. We evaluate MDDI-SCL on three different tasks of two datasets. Experimental results demonstrate that MDDI-SCL achieves better or comparable performance as the state-of-the-art methods. Furthermore, the effectiveness of supervised contrastive learning is validated by ablation experiment, and the feasibility of MDDI-SCL is supported by case studies. The source codes are available at https://github.com/ShenggengLin/MDDI-SCL.

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.

Deep Image Watermarking to JPEG Compression Based on Mixed-Frequency Channel Attention

Deep blind watermarking algorithms based on an end-to-end encoder-decoder architecture have recently been extensively studied as an important technology for protecting copyright. However, none of the existing algorithms can fully utilize the channel features of the image to improve the robustness against JPEG compression while obtaining high visual quality. Therefore, we propose firstly a mixed-frequency channel attention method in the encoder, which utilizes different frequency components of the 2D-DCT domain as weight coefficients during channel squeezing and excitation. Its essence is to suppress the useless feature maps and enhance the feature maps suitable for watermarking embedding by introducing frequency analysis in the channel dimension. The experimental results indicate that the PSNR of our method reaches over 38 and the BER is less than 0.01% under the JPEG compression with quality factor Q = 50. Besides, the proposed framework also obtains excellent robustness for a variety of common distortions, including Gaussian filter, crop, crop out, and drop out.

Drug Design by Pharmacophore and Virtual Screening Approach

Computer-aided drug discovery techniques reduce the time and the costs needed to develop novel drugs. Their relevance becomes more and more evident with the needs due to health emergencies as well as to the diffusion of personalized medicine. Pharmacophore approaches represent one of the most interesting tools developed, by defining the molecular functional features needed for the binding of a molecule to a given receptor, and then directing the virtual screening of large collections of compounds for the selection of optimal candidates. Computational tools to create the pharmacophore model and to perform virtual screening are available and generated successful studies. This article describes the procedure of pharmacophore modelling followed by virtual screening, the most used software, possible limitations of the approach, and some applications reported in the literature.

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

Prediction on drug–target interaction has always been a crucial link for drug discovery and repositioning, which have witnessed tremendous progress in recent years. Despite many efforts made, the existing representation learning or feature generation approaches of both drugs and proteins remain complicated as well as in high dimension. In addition, it is difficult for current methods to extract local important residues from sequence information while remaining focused on global structure. At the same time, massive data is not always easily accessible, which makes model learning from small datasets imminent. As a result, we propose an end-to-end learning model with SUPD and SUDD methods to encode drugs and proteins, which not only leave out the complicated feature extraction process but also greatly reduce the dimension of the embedding matrix. Meanwhile, we use a multi-view strategy with a transformer to extract local important residues of proteins for better representation learning. Finally, we evaluate our model on the BindingDB dataset in comparisons with different state-of-the-art models from comprehensive indicators. In results of 100% BindingDB, our AUC, AUPR, ACC, and F1-score reached 90.9%, 89.8%, 84.2%, and 84.3% respectively, which successively exceed the average values of other models by 2.2%, 2.3%, 2.6%, and 2.6%. Moreover, our model also generally surpasses their performance on 30% and 50% BindingDB datasets.

A Novel Attention-Mechanism Based Cox Survival Model by Exploiting Pan-Cancer Empirical Genomic Information

Cancer prognosis is an essential goal for early diagnosis, biomarker selection, and medical therapy. In the past decade, deep learning has successfully solved a variety of biomedical problems. However, due to the high dimensional limitation of human cancer transcriptome data and the small number of training samples, there is still no mature deep learning-based survival analysis model that can completely solve problems in the training process like overfitting and accurate prognosis. Given these problems, we introduced a novel framework called SAVAE-Cox for survival analysis of high-dimensional transcriptome data. This model adopts a novel attention mechanism and takes full advantage of the adversarial transfer learning strategy. We trained the model on 16 types of TCGA cancer RNA-seq data sets. Experiments show that our module outperformed state-of-the-art survival analysis models such as the Cox proportional hazard model (Cox-ph), Cox-lasso, Cox-ridge, Cox-nnet, and VAECox on the concordance index. In addition, we carry out some feature analysis experiments. Based on the experimental results, we concluded that our model is helpful for revealing cancer-related genes and biological functions.

TransPhos: A Deep-Learning Model for General Phosphorylation Site Prediction Based on Transformer-Encoder Architecture

Protein phosphorylation is one of the most critical post-translational modifications of proteins in eukaryotes, which is essential for a variety of biological processes. Plenty of attempts have been made to improve the performance of computational predictors for phosphorylation site prediction. However, most of them are based on extra domain knowledge or feature selection. In this article, we present a novel deep learning-based predictor, named TransPhos, which is constructed using a transformer encoder and densely connected convolutional neural network blocks, for predicting phosphorylation sites. Data experiments are conducted on the datasets of PPA (version 3.0) and Phospho. ELM. The experimental results show that our TransPhos performs better than several deep learning models, including Convolutional Neural Networks (CNN), Long-term and short-term memory networks (LSTM), Recurrent neural networks (RNN) and Fully connected neural networks (FCNN), and some state-of-the-art deep learning-based prediction tools, including GPS2.1, NetPhos, PPRED, Musite, PhosphoSVM, SKIPHOS, and DeepPhos. Our model achieves a good performance on the training datasets of Serine (S), Threonine (T), and Tyrosine (Y), with AUC values of 0.8579, 0.8335, and 0.6953 using 10-fold cross-validation tests, respectively, and demonstrates that the presented TransPhos tool considerably outperforms competing predictors in general protein phosphorylation site prediction.