Scalable crystal structure relaxation using an iteration-free deep generative model with uncertainty quantification.

In computational molecular and materials science, determining equilibrium structures is the crucial first step for accurate subsequent property calculations. However, the recent discovery of millions of new crystals and super large twisted structures has challenged traditional computational methods, both ab initio and machine-learning-based, due to their computationally intensive iterative processes. To address these scalability issues, here we introduce DeepRelax, a deep generative model capable of performing geometric crystal structure relaxation rapidly and without iterations. DeepRelax learns the equilibrium structural distribution, enabling it to predict relaxed structures directly from their unrelaxed ones. The ability to perform structural relaxation at the millisecond level per structure, combined with the scalability of parallel processing, makes DeepRelax particularly useful for large-scale virtual screening. We demonstrate DeepRelax's reliability and robustness by applying it to five diverse databases, including oxides, Materials Project, two-dimensional materials, van der Waals crystals, and crystals with point defects. DeepRelax consistently shows high accuracy and efficiency, validated by density functional theory calculations. Finally, we enhance its trustworthiness by integrating uncertainty quantification. This work significantly accelerates computational workflows, offering a robust and trustworthy machine-learning method for material discovery and advancing the application of AI for science.

MMFA-DTA: Multimodal Feature Attention Fusion Network for Drug-Target Affinity Prediction for Drug Repurposing Against SARS-CoV-2.

The continuous emergence of novel infectious diseases poses a significant threat to global public health security, necessitating the development of small-molecule inhibitors that directly target pathogens. The RNA-dependent RNA polymerase (RdRp) and main protease (Mpro) of SARS-CoV-2 have been validated as potential key antiviral drug targets for the treatment of COVID-19. However, the conventional new drug R&D cycle takes 10-15 years, failing to meet the urgent needs during epidemics. Here, we propose a general multimodal deep learning framework for drug repurposing, MMFA-DTA, to enable rapid virtual screening of known drugs and significantly improve discovery efficiency. By extracting graph topological and sequence features from both small molecules and proteins, we design attention mechanisms to achieve dynamic fusion across modalities. Results demonstrate the superior performance of MMFA-DTA in drug-target affinity prediction over several state-of-the-art baseline methods on Davis and KIBA data sets, validating the benefits of heterogeneous information integration for representation learning and interaction modeling. Further fine-tuning on COVID-19-relevant bioactivity data enhances model predictions for critical SARS-CoV-2 enzymes. Case studies screening the FDA-approved drug library successfully identify etacrynic acid as the potential lead compound against both RdRp and Mpro. Molecular dynamics simulations further confirm the stability and binding affinity of etacrynic acid to these targets. This study proves the great potential and advantages of deep learning and drug repurposing strategies in supporting antiviral drug discovery. The proposed general and rapid response computational framework holds significance for preparedness against future public health events.

De novo generation of SARS-CoV-2 antibody CDRH3 with a pre-trained generative large language model.

Artificial Intelligence (AI) techniques have made great advances in assisting antibody design. However, antibody design still heavily relies on isolating antigen-specific antibodies from serum, which is a resource-intensive and time-consuming process. To address this issue, we propose a Pre-trained Antibody generative large Language Model (PALM-H3) for the de novo generation of artificial antibodies heavy chain complementarity-determining region 3 (CDRH3) with desired antigen-binding specificity, reducing the reliance on natural antibodies. We also build a high-precision model antigen-antibody binder (A2binder) that pairs antigen epitope sequences with antibody sequences to predict binding specificity and affinity. PALM-H3-generated antibodies exhibit binding ability to SARS-CoV-2 antigens, including the emerging XBB variant, as confirmed through in-silico analysis and in-vitro assays. The in-vitro assays validate that PALM-H3-generated antibodies achieve high binding affinity and potent neutralization capability against spike proteins of SARS-CoV-2 wild-type, Alpha, Delta, and the emerging XBB variant. Meanwhile, A2binder demonstrates exceptional predictive performance on binding specificity for various epitopes and variants. Furthermore, by incorporating the attention mechanism inherent in the Roformer architecture into the PALM-H3 model, we improve its interpretability, providing crucial insights into the fundamental principles of antibody design.

Interaction-Based Inductive Bias in Graph Neural Networks: Enhancing Protein-Ligand Binding Affinity Predictions From 3D Structures.

Inductive bias in machine learning (ML) is the set of assumptions describing how a model makes predictions. Different ML-based methods for protein-ligand binding affinity (PLA) prediction have different inductive biases, leading to different levels of generalization capability and interpretability. Intuitively, the inductive bias of an ML-based model for PLA prediction should fit in with biological mechanisms relevant for binding to achieve good predictions with meaningful reasons. To this end, we propose an interaction-based inductive bias to restrict neural networks to functions relevant for binding with two assumptions: (1) A protein-ligand complex can be naturally expressed as a heterogeneous graph with covalent and non-covalent interactions; (2) The predicted PLA is the sum of pairwise atom-atom affinities determined by non-covalent interactions. The interaction-based inductive bias is embodied by an explainable heterogeneous interaction graph neural network (EHIGN) for explicitly modeling pairwise atom-atom interactions to predict PLA from 3D structures. Extensive experiments demonstrate that EHIGN achieves better generalization capability than other state-of-the-art ML-based baselines in PLA prediction and structure-based virtual screening. More importantly, comprehensive analyses of distance-affinity, pose-affinity, and substructure-affinity relations suggest that the interaction-based inductive bias can guide the model to learn atomic interactions that are consistent with physical reality. As a case study to demonstrate practical usefulness, our method is tested for predicting the efficacy of Nirmatrelvir against SARS-CoV-2 variants. EHIGN successfully recognizes the changes in the efficacy of Nirmatrelvir for different SARS-CoV-2 variants with meaningful reasons.

MFTrans: A multi-feature transformer network for protein secondary structure prediction.

In the rapidly evolving field of computational biology, accurate prediction of protein secondary structures is crucial for understanding protein functions, facilitating drug discovery, and advancing disease diagnostics. In this paper, we propose MFTrans, a deep learning-based multi-feature fusion network aimed at enhancing the precision and efficiency of Protein Secondary Structure Prediction (PSSP). This model employs a Multiple Sequence Alignment (MSA) Transformer in combination with a multi-view deep learning architecture to effectively capture both global and local features of protein sequences. MFTrans integrates diverse features generated by protein sequences, including MSA, sequence information, evolutionary information, and hidden state information, using a multi-feature fusion strategy. The MSA Transformer is utilized to interleave row and column attention across the input MSA, while a Transformer encoder and decoder are introduced to enhance the extracted high-level features. A hybrid network architecture, combining a convolutional neural network with a bidirectional Gated Recurrent Unit (BiGRU) network, is used to further extract high-level features after feature fusion. In independent tests, our experimental results show that MFTrans has superior generalization ability, outperforming other state-of-the-art PSSP models by 3 % on average on public benchmarks including CASP12, CASP13, CASP14, TEST2016, TEST2018, and CB513. Case studies further highlight its advanced performance in predicting mutation sites. MFTrans contributes significantly to the protein science field, opening new avenues for drug discovery, disease diagnosis, and protein.

PSSP-MFFNet: A Multifeature Fusion Network for Protein Secondary Structure Prediction.

Protein secondary structure prediction (PSSP) is a fundamental task in modern bioinformatics research and is particularly important for uncovering the functional mechanisms of proteins. To improve the accuracy of PSSP, various general and essential features generated from amino acid sequences are often used for predicting the secondary structure. In this paper, we propose PSSP-MFFNet, a deep learning-based multi-feature fusion network for PSSP, which incorporates a multi-view deep learning architecture with the multiple sequence alignment (MSA) Transformer to efficiently capture global and local features of protein sequences. In practice, PSSP-MFFNet adopts a multi-feature fusion strategy, integrating different features generated from protein sequences, including MSA, sequence information, evolutionary information, and hidden state information. Moreover, we employ the MSA Transformer to interleave row and column attention across the input MSA. A hybrid network architecture of convolutional neural networks and long short-term memory networks is applied to extract high-level features after feature fusion. Furthermore, we introduce a transformer encoder to enhance the extracted high-level features. Comparative experimental results on independent tests demonstrate that PSSP-MFFNet has excellent generalization ability, outperforming other state-of-the-art PSSP models by an average of 1% on public benchmarks, including CASP12, CASP13, CASP14, TEST2018, and CB513. Our method can contribute to a better understanding of the biological functions of proteins, which has significant implications for drug discovery, disease diagnosis, and protein engineering.

MRI-based automated machine learning model for preoperative identification of variant histology in muscle-invasive bladder carcinoma.

OBJECTIVES: It is essential yet highly challenging to preoperatively diagnose variant histologies such as urothelial carcinoma with squamous differentiation (UC w/SD) from pure UC in patients with muscle-invasive bladder carcinoma (MIBC), as their treatment strategy varies significantly. We developed a non-invasive automated machine learning (AutoML) model to preoperatively differentiate UC w/SD from pure UC in patients with MIBC. METHODS: A total of 119 MIBC patients who underwent baseline bladder MRI were enrolled in this study, including 38 patients with UC w/SD and 81 patients with pure UC. These patients were randomly assigned to a training set or a test set (3:1). An AutoML model was built from the training set, using 13 selected radiomic features from T2-weighted imaging, semantic features (ADC values), and clinical features (tumor length, tumor stage, lymph node metastasis status), and subsequent ten-fold cross-validation was performed. A test set was used to validate the proposed model. The AUC of the ROC curve was then calculated for the model. RESULTS: This AutoML model enabled robust differentiation of UC w/SD and pure UC in patients with MIBC in both training set (ten-fold cross-validation AUC = 0.955, 95% confidence interval [CI]: 0.944-0.965) and test set (AUC = 0.932, 95% CI: 0.812-1.000). CONCLUSION: The presented AutoML model, that incorporates the radiomic, semantic, and clinical features from baseline MRI, could be useful for preoperative differentiation of UC w/SD and pure UC. CLINICAL RELEVANCE STATEMENT: This MRI-based automated machine learning (AutoML) study provides a non-invasive and low-cost preoperative prediction tool to identify the muscle-invasive bladder cancer patients with variant histology, which may serve as a useful tool for clinical decision-making. KEY POINTS: • It is important to preoperatively diagnose variant histology from urothelial carcinoma in patients with muscle-invasive bladder carcinoma (MIBC), as their treatment strategy varies significantly. • An automated machine learning (AutoML) model based on baseline bladder MRI can identify the variant histology (squamous differentiation) from urothelial carcinoma preoperatively in patients with MIBC. • The developed AutoML model is a non-invasive and low-cost preoperative prediction tool, which may be useful for clinical decision-making.

LDCNet: Lightweight dynamic convolution network for laparoscopic procedures image segmentation.

Medical image segmentation is fundamental for modern healthcare systems, especially for reducing the risk of surgery and treatment planning. Transanal total mesorectal excision (TaTME) has emerged as a recent focal point in laparoscopic research, representing a pivotal modality in the therapeutic arsenal for the treatment of colon & rectum cancers. Real-time instance segmentation of surgical imagery during TaTME procedures can serve as an invaluable tool in assisting surgeons, ultimately reducing surgical risks. The dynamic variations in size and shape of anatomical structures within intraoperative images pose a formidable challenge, rendering the precise instance segmentation of TaTME images a task of considerable complexity. Deep learning has exhibited its efficacy in Medical image segmentation. However, existing models have encountered challenges in concurrently achieving a satisfactory level of accuracy while maintaining manageable computational complexity in the context of TaTME data. To address this conundrum, we propose a lightweight dynamic convolution Network (LDCNet) that has the same superior segmentation performance as the state-of-the-art (SOTA) medical image segmentation network while running at the speed of the lightweight convolutional neural network. Experimental results demonstrate the promising performance of LDCNet, which consistently exceeds previous SOTA approaches. Codes are available at github.com/yinyiyang416/LDCNet.

Discovery of Kinetin in inhibiting colorectal cancer progression via enhancing PSMB1-mediated RAB34 degradation.

Colorectal cancer (CRC) is one of the most prevalent malignancies worldwide. Understanding the underlying mechanism driving CRC progression and identifying potential therapeutic drug targets are of utmost urgency. We previously utilized LC-MS-based proteomic profiling to identify proteins associated with postoperative progression in stage II/III CRC. Here, we revealed that proteasome subunit beta type-1 (PSMB1) is an independent predictor for postoperative progression in stage II/III CRC. Mechanistically, PSMB1 binds directly to onco-protein RAB34 and promotes its proteasome-dependent degradation, potentially leading to the inactivation of the MEK/ERK signaling pathway and inhibition of CRC progression. To further identify potential anticancer drugs, we screened a library of 2509 FDA-approved drugs using computer-aided drug design (CADD) and identified Kinetin as a potentiating agent for PSMB1. Functional assays confirmed that Kinetin enhanced the interaction between PSMB1 and RAB34, hence facilitated the degradation of RAB34 protein and decreased the MEK/ERK phosphorylation. Kinetin suppresses CRC progression in patient-derived xenograft (PDX) and liver metastasis models. Conclusively, our study identifies PSMB1 as a potential biomarker and therapeutic target for CRC, and Kinetin as an anticancer drug by enhancing proteasome-dependent onco-protein degradation.

Equivariant Flexible Modeling of the Protein-Ligand Binding Pose with Geometric Deep Learning.

Flexible modeling of the protein-ligand complex structure is a fundamental challenge for in silico drug development. Recent studies have improved commonly used docking tools by incorporating extra-deep learning-based steps. However, such strategies limit their accuracy and efficiency because they retain massive sampling pressure and lack consideration for flexible biomolecular changes. In this study, we propose FlexPose, a geometric graph network capable of direct flexible modeling of complex structures in Euclidean space without the following conventional sampling and scoring strategies. Our model adopts two key designs: scalar-vector dual feature representation and SE(3)-equivariant network, to manage dynamic structural changes, as well as two strategies: conformation-aware pretraining and weakly supervised learning, to boost model generalizability in unseen chemical space. Benefiting from these paradigms, our model dramatically outperforms all tested popular docking tools and recently advanced deep learning methods, especially in tasks involving protein conformation changes. We further investigate the impact of protein and ligand similarity on the model performance with two conformation-aware strategies. Moreover, FlexPose provides an affinity estimation and model confidence for postanalysis.

TCMBank: bridges between the largest herbal medicines, chemical ingredients, target proteins, and associated diseases with intelligence text mining.

Traditional Chinese Medicine (TCM) has long been viewed as a precious source of modern drug discovery. AI-assisted drug discovery (AIDD) has been investigated extensively. However, there are still two challenges in applying AIDD to guide TCM drug discovery: the lack of a large amount of standardized TCM-related information and AIDD is prone to pathological failures in out-of-domain data. We have released TCM Database@Taiwan in 2011, and it has been widely disseminated and used. Now, we developed TCMBank, the largest systematic free TCM database, which is an extension of TCM Database@Taiwan. TCMBank contains 9192 herbs, 61 966 ingredients (unduplicated), 15 179 targets, 32 529 diseases, and their pairwise relationships. By integrating multiple data sources, TCMBank provides 3D structure information of ingredients and provides a standard list and detailed information on herbs, ingredients, targets and diseases. TCMBank has an intelligent document identification module that continuously adds TCM-related information retrieved from the literature in PubChem. In addition, driven by TCMBank big data, we developed an ensemble learning-based drug discovery protocol for identifying potential leads and drug repurposing. We take colorectal cancer and Alzheimer's disease as examples to demonstrate how to accelerate drug discovery by artificial intelligence. Using TCMBank, researchers can view literature-driven relationship mapping between herbs/ingredients and genes/diseases, allowing the understanding of molecular action mechanisms for ingredients and identification of new potentially effective treatments. TCMBank is available at https://TCMBank.CN/.

Hybrid neural network approaches to predict drug-target binding affinity for drug repurposing: screening for potential leads for Alzheimer's disease.

Alzheimer's disease (AD) is a neurodegenerative disease that primarily affects elderly individuals. Recent studies have found that sigma-1 receptor (S1R) agonists can maintain endoplasmic reticulum stress homeostasis, reduce neuronal apoptosis, and enhance mitochondrial function and autophagy, making S1R a target for AD therapy. Traditional experimental methods are costly and inefficient, and rapid and accurate prediction methods need to be developed, while drug repurposing provides new ways and options for AD treatment. In this paper, we propose HNNDTA, a hybrid neural network for drug-target affinity (DTA) prediction, to facilitate drug repurposing for AD treatment. The study combines protein-protein interaction (PPI) network analysis, the HNNDTA model, and molecular docking to identify potential leads for AD. The HNNDTA model was constructed using 13 drug encoding networks and 9 target encoding networks with 2506 FDA-approved drugs as the candidate drug library for S1R and related proteins. Seven potential drugs were identified using network pharmacology and DTA prediction results of the HNNDTA model. Molecular docking simulations were further performed using the AutoDock Vina tool to screen haloperidol and bromperidol as lead compounds for AD treatment. Absorption, distribution, metabolism, excretion, and toxicity (ADMET) evaluation results indicated that both compounds had good pharmacokinetic properties and were virtually non-toxic. The study proposes a new approach to computer-aided drug design that is faster and more economical, and can improve hit rates for new drug compounds. The results of this study provide new lead compounds for AD treatment, which may be effective due to their multi-target action. HNNDTA is freely available at https://github.com/lizhj39/HNNDTA.

3D graph neural network with few-shot learning for predicting drug-drug interactions in scaffold-based cold start scenario.

Understanding drug-drug interactions (DDI) of new drugs is critical for minimizing unexpected adverse drug reactions. The modeling of new drugs is called a cold start scenario. In this scenario, Only a few structural information or physicochemical information about new drug is available. The 3D conformation of drug molecules usually plays a crucial role in chemical properties compared to the 2D structure. 3D graph network with few-shot learning is a promising solution. However, the 3D heterogeneity of drug molecules and the discretization of atomic distributions lead to spatial confusion in few-shot learning. Here, we propose a 3D graph neural network with few-shot learning, Meta3D-DDI, to predict DDI events in cold start scenario. The 3DGNN ensures rotation and translation invariance by calculating atomic pairwise distances, and incorporates 3D structure and distance information in the information aggregation stage. The continuous filter interaction module can continuously simulate the filter to obtain the interaction between the target atom and other atoms. Meta3D-DDI further develops a FSL strategy based on bilevel optimization to transfer meta-knowledge for DDI prediction tasks from existing drugs to new drugs. In addition, the existing cold start setting may cause the scaffold structure information in the training set to leak into the test set. We design scaffold-based cold start scenario to ensure that the drug scaffolds in the training set and test set do not overlap. The extensive experiments demonstrate that our architecture achieves the SOTA performance for DDI prediction under scaffold-based cold start scenario on two real-world datasets. The visual experiment shows that Meta3D-DDI significantly improves the learning for DDI prediction of new drugs. We also demonstrate how Meta3D-DDI can reduce the amount of data required to make meaningful DDI predictions.

NHGNN-DTA: a node-adaptive hybrid graph neural network for interpretable drug-target binding affinity prediction.

MOTIVATION: Large-scale prediction of drug-target affinity (DTA) plays an important role in drug discovery. In recent years, machine learning algorithms have made great progress in DTA prediction by utilizing sequence or structural information of both drugs and proteins. However, sequence-based algorithms ignore the structural information of molecules and proteins, while graph-based algorithms are insufficient in feature extraction and information interaction. RESULTS: In this article, we propose NHGNN-DTA, a node-adaptive hybrid neural network for interpretable DTA prediction. It can adaptively acquire feature representations of drugs and proteins and allow information to interact at the graph level, effectively combining the advantages of both sequence-based and graph-based approaches. Experimental results have shown that NHGNN-DTA achieved new state-of-the-art performance. It achieved the mean squared error (MSE) of 0.196 on the Davis dataset (below 0.2 for the first time) and 0.124 on the KIBA dataset (3% improvement). Meanwhile, in the case of cold start scenario, NHGNN-DTA proved to be more robust and more effective with unseen inputs than baseline methods. Furthermore, the multi-head self-attention mechanism endows the model with interpretability, providing new exploratory insights for drug discovery. The case study on Omicron variants of SARS-CoV-2 illustrates the efficient utilization of drug repurposing in COVID-19. AVAILABILITY AND IMPLEMENTATION: The source code and data are available at https://github.com/hehh77/NHGNN-DTA.

Retrosynthesis prediction using an end-to-end graph generative architecture for molecular graph editing.

Retrosynthesis planning, the process of identifying a set of available reactions to synthesize the target molecules, remains a major challenge in organic synthesis. Recently, computer-aided synthesis planning has gained renewed interest and various retrosynthesis prediction algorithms based on deep learning have been proposed. However, most existing methods are limited to the applicability and interpretability of model predictions, and further improvement of predictive accuracy to a more practical level is still required. In this work, inspired by the arrow-pushing formalism in chemical reaction mechanisms, we present an end-to-end architecture for retrosynthesis prediction called Graph2Edits. Specifically, Graph2Edits is based on graph neural network to predict the edits of the product graph in an auto-regressive manner, and sequentially generates transformation intermediates and final reactants according to the predicted edits sequence. This strategy combines the two-stage processes of semi-template-based methods into one-pot learning, improving the applicability in some complicated reactions, and also making its predictions more interpretable. Evaluated on the standard benchmark dataset USPTO-50k, our model achieves the state-of-the-art performance for semi-template-based retrosynthesis with a promising 55.1% top-1 accuracy.

Meta Learning With Graph Attention Networks for Low-Data Drug Discovery.

Finding candidate molecules with favorable pharmacological activity, low toxicity, and proper pharmacokinetic properties is an important task in drug discovery. Deep neural networks have made impressive progress in accelerating and improving drug discovery. However, these techniques rely on a large amount of label data to form accurate predictions of molecular properties. At each stage of the drug discovery pipeline, usually, only a few biological data of candidate molecules and derivatives are available, indicating that the application of deep neural networks for low-data drug discovery is still a formidable challenge. Here, we propose a meta learning architecture with graph attention network, Meta-GAT, to predict molecular properties in low-data drug discovery. The GAT captures the local effects of atomic groups at the atom level through the triple attentional mechanism and implicitly captures the interactions between different atomic groups at the molecular level. GAT is used to perceive molecular chemical environment and connectivity, thereby effectively reducing sample complexity. Meta-GAT further develops a meta learning strategy based on bilevel optimization, which transfers meta knowledge from other attribute prediction tasks to low-data target tasks. In summary, our work demonstrates how meta learning can reduce the amount of data required to make meaningful predictions of molecules in low-data scenarios. Meta learning is likely to become the new learning paradigm in low-data drug discovery. The source code is publicly available at: https://github.com/lol88/Meta-GAT.

DSIL-DDI: A Domain-Invariant Substructure Interaction Learning for Generalizable Drug-Drug Interaction Prediction.

Drug-drug interactions (DDIs) trigger unexpected pharmacological effects in vivo, often with unknown causal mechanisms. Deep learning methods have been developed to better understand DDI. However, learning domain-invariant representations for DDI remains a challenge. Generalizable DDI predictions are closer to reality than source domain predictions. For existing methods, it is difficult to achieve out-of-distribution (OOD) predictions. In this article, focusing on substructure interaction, we propose DSIL-DDI, a pluggable substructure interaction module that can learn domain-invariant representations of DDIs from source domain. We evaluate DSIL-DDI on three scenarios: the transductive setting (all drugs in test set appear in training set), the inductive setting (test set contains new drugs that were not present in training set), and OOD generalization setting (training set and test set belong to two different datasets). The results demonstrate that DSIL-DDI improve the generalization and interpretability of DDI prediction modeling and provides valuable insights for OOD DDI predictions. DSIL-DDI can help doctors ensuring the safety of drug administration and reducing the harm caused by drug abuse.

Multitask deep learning with dynamic task balancing for quantum mechanical properties prediction.

Predicting quantum mechanical properties (QMPs) is very important for the innovation of material and chemistry science. Multitask deep learning models have been widely used in QMPs prediction. However, existing multitask learning models often train multiple QMPs prediction tasks simultaneously without considering the internal relationships and differences between tasks, which may cause the model to overfit easy tasks. In this study, we first proposed a multiscale dynamic attention graph neural network (MDGNN) for molecular representation learning. The MDGNN was designed in a multitask learning fashion that can solve multiple learning tasks at the same time. We then introduced a dynamic task balancing (DTB) strategy combining task differences and difficulties to reduce overfitting across multiple tasks. Finally, we adopted gradient-weighted class activation mapping (Grad-CAM) to analyze a deep learning model for frontier molecular orbital, highest occupied molecular orbital (HOMO) and lowest unoccupied molecular orbital (LUMO) energy level predictions. We evaluated our approach using two large QMPs datasets and compared the proposed method to the state-of-the-art multitask learning models. The MDGNN outperforms other multitask learning approaches on two datasets. The DTB strategy can further improve the performance of MDGNN significantly. Moreover, we show that Grad-CAM creates explanations that are consistent with the molecular orbitals theory. These advantages demonstrate that the proposed method improves the generalization and interpretation capability of QMPs prediction modeling.

FusionDTA: attention-based feature polymerizer and knowledge distillation for drug-target binding affinity prediction.

The prediction of drug-target affinity (DTA) plays an increasingly important role in drug discovery. Nowadays, lots of prediction methods focus on feature encoding of drugs and proteins, but ignore the importance of feature aggregation. However, the increasingly complex encoder networks lead to the loss of implicit information and excessive model size. To this end, we propose a deep-learning-based approach namely FusionDTA. For the loss of implicit information, a novel muti-head linear attention mechanism was utilized to replace the rough pooling method. This allows FusionDTA aggregates global information based on attention weights, instead of selecting the largest one as max-pooling does. To solve the redundancy issue of parameters, we applied knowledge distillation in FusionDTA by transfering learnable information from teacher model to student. Results show that FusionDTA performs better than existing models for the test domain on all evaluation metrics. We obtained concordance index (CI) index of 0.913 and 0.906 in Davis and KIBA dataset respectively, compared with 0.893 and 0.891 of previous state-of-art model. Under the cold-start constrain, our model proved to be more robust and more effective with unseen inputs than baseline methods. In addition, the knowledge distillation did save half of the parameters of the model, with only 0.006 reduction in CI index. Even FusionDTA with half the parameters could easily exceed the baseline on all metrics. In general, our model has superior performance and improves the effect of drug-target interaction (DTI) prediction. The visualization of DTI can effectively help predict the binding region of proteins during structure-based drug design.