AttABseq: an attention-based deep learning prediction method for antigen-antibody binding affinity changes based on protein sequences.

The optimization of therapeutic antibodies through traditional techniques, such as candidate screening via hybridoma or phage display, is resource-intensive and time-consuming. In recent years, computational and artificial intelligence-based methods have been actively developed to accelerate and improve the development of therapeutic antibodies. In this study, we developed an end-to-end sequence-based deep learning model, termed AttABseq, for the predictions of the antigen-antibody binding affinity changes connected with antibody mutations. AttABseq is a highly efficient and generic attention-based model by utilizing diverse antigen-antibody complex sequences as the input to predict the binding affinity changes of residue mutations. The assessment on the three benchmark datasets illustrates that AttABseq is 120% more accurate than other sequence-based models in terms of the Pearson correlation coefficient between the predicted and experimental binding affinity changes. Moreover, AttABseq also either outperforms or competes favorably with the structure-based approaches. Furthermore, AttABseq consistently demonstrates robust predictive capabilities across a diverse array of conditions, underscoring its remarkable capacity for generalization across a wide spectrum of antigen-antibody complexes. It imposes no constraints on the quantity of altered residues, rendering it particularly applicable in scenarios where crystallographic structures remain unavailable. The attention-based interpretability analysis indicates that the causal effects of point mutations on antibody-antigen binding affinity changes can be visualized at the residue level, which might assist automated antibody sequence optimization. We believe that AttABseq provides a fiercely competitive answer to therapeutic antibody optimization.

Comprehensive assessment of protein loop modeling programs on large-scale datasets: prediction accuracy and efficiency.

Protein loops play a critical role in the dynamics of proteins and are essential for numerous biological functions, and various computational approaches to loop modeling have been proposed over the past decades. However, a comprehensive understanding of the strengths and weaknesses of each method is lacking. In this work, we constructed two high-quality datasets (i.e. the General dataset and the CASP dataset) and systematically evaluated the accuracy and efficiency of 13 commonly used loop modeling approaches from the perspective of loop lengths, protein classes and residue types. The results indicate that the knowledge-based method FREAD generally outperforms the other tested programs in most cases, but encountered challenges when predicting loops longer than 15 and 30 residues on the CASP and General datasets, respectively. The ab initio method Rosetta NGK demonstrated exceptional modeling accuracy for short loops with four to eight residues and achieved the highest success rate on the CASP dataset. The well-known AlphaFold2 and RoseTTAFold require more resources for better performance, but they exhibit promise for predicting loops longer than 16 and 30 residues in the CASP and General datasets. These observations can provide valuable insights for selecting suitable methods for specific loop modeling tasks and contribute to future advancements in the field.

Comprehensive assessment of deep generative architectures for de novo drug design.

Recently, deep learning (DL)-based de novo drug design represents a new trend in pharmaceutical research, and numerous DL-based methods have been developed for the generation of novel compounds with desired properties. However, a comprehensive understanding of the advantages and disadvantages of these methods is still lacking. In this study, the performances of different generative models were evaluated by analyzing the properties of the generated molecules in different scenarios, such as goal-directed (rediscovery, optimization and scaffold hopping of active compounds) and target-specific (generation of novel compounds for a given target) tasks. In overall, the DL-based models have significant advantages over the baseline models built by the traditional methods in learning the physicochemical property distributions of the training sets and may be more suitable for target-specific tasks. However, both the baselines and DL-based generative models cannot fully exploit the scaffolds of the training sets, and the molecules generated by the DL-based methods even have lower scaffold diversity than those generated by the traditional models. Moreover, our assessment illustrates that the DL-based methods do not exhibit obvious advantages over the genetic algorithm-based baselines in goal-directed tasks. We believe that our study provides valuable guidance for the effective use of generative models in de novo drug design.

Knowledge-based BERT: a method to extract molecular features like computational chemists.

Molecular property prediction models based on machine learning algorithms have become important tools to triage unpromising lead molecules in the early stages of drug discovery. Compared with the mainstream descriptor- and graph-based methods for molecular property predictions, SMILES-based methods can directly extract molecular features from SMILES without human expert knowledge, but they require more powerful algorithms for feature extraction and a larger amount of data for training, which makes SMILES-based methods less popular. Here, we show the great potential of pre-training in promoting the predictions of important pharmaceutical properties. By utilizing three pre-training tasks based on atom feature prediction, molecular feature prediction and contrastive learning, a new pre-training method K-BERT, which can extract chemical information from SMILES like chemists, was developed. The calculation results on 15 pharmaceutical datasets show that K-BERT outperforms well-established descriptor-based (XGBoost) and graph-based (Attentive FP and HRGCN+) models. In addition, we found that the contrastive learning pre-training task enables K-BERT to 'understand' SMILES not limited to canonical SMILES. Moreover, the general fingerprints K-BERT-FP generated by K-BERT exhibit comparative predictive power to MACCS on 15 pharmaceutical datasets and can also capture molecular size and chirality information that traditional binary fingerprints cannot capture. Our results illustrate the great potential of K-BERT in the practical applications of molecular property predictions in drug discovery.

Out-of-the-box deep learning prediction of quantum-mechanical partial charges by graph representation and transfer learning.

Accurate prediction of atomic partial charges with high-level quantum mechanics (QM) methods suffers from high computational cost. Numerous feature-engineered machine learning (ML)-based predictors with favorable computability and reliability have been developed as alternatives. However, extensive expertise effort was needed for feature engineering of atom chemical environment, which may consequently introduce domain bias. In this study, SuperAtomicCharge, a data-driven deep graph learning framework, was proposed to predict three important types of partial charges (i.e. RESP, DDEC4 and DDEC78) derived from high-level QM calculations based on the structures of molecules. SuperAtomicCharge was designed to simultaneously exploit the 2D and 3D structural information of molecules, which was proved to be an effective way to improve the prediction accuracy of the model. Moreover, a simple transfer learning strategy and a multitask learning strategy based on self-supervised descriptors were also employed to further improve the prediction accuracy of the proposed model. Compared with the latest baselines, including one GNN-based predictor and two ML-based predictors, SuperAtomicCharge showed better performance on all the three external test sets and had better usability and portability. Furthermore, the QM partial charges of new molecules predicted by SuperAtomicCharge can be efficiently used in drug design applications such as structure-based virtual screening, where the predicted RESP and DDEC4 charges of new molecules showed more robust scoring and screening power than the commonly used partial charges. Finally, two tools including an online server (http://cadd.zju.edu.cn/deepchargepredictor) and the source code command lines (https://github.com/zjujdj/SuperAtomicCharge) were developed for the easy access of the SuperAtomicCharge services.

Genetic Algorithm-Based Receptor Ligand: A Genetic Algorithm-Guided Generative Model to Boost the Novelty and Drug-Likeness of Molecules in a Sampling Chemical Space.

Deep learning-based de novo molecular design has recently gained significant attention. While numerous DL-based generative models have been successfully developed for designing novel compounds, the majority of the generated molecules lack sufficiently novel scaffolds or high drug-like profiles. The aforementioned issues may not be fully captured by commonly used metrics for the assessment of molecular generative models, such as novelty, diversity, and quantitative estimation of the drug-likeness score. To address these limitations, we proposed a genetic algorithm-guided generative model called GARel (genetic algorithm-based receptor-ligand interaction generator), a novel framework for training a DL-based generative model to produce drug-like molecules with novel scaffolds. To efficiently train the GARel model, we utilized dense net to update the parameters based on molecules with novel scaffolds and drug-like features. To demonstrate the capability of the GARel model, we used it to design inhibitors for three targets: AA2AR, EGFR, and SARS-Cov2. The results indicate that GARel-generated molecules feature more diverse and novel scaffolds and possess more desirable physicochemical properties and favorable docking scores. Compared with other generative models, GARel makes significant progress in balancing novelty and drug-likeness, providing a promising direction for the further development of DL-based de novo design methodology with potential impacts on drug discovery.

DrugFlow: An AI-Driven One-Stop Platform for Innovative Drug Discovery.

Artificial intelligence (AI)-aided drug design has demonstrated unprecedented effects on modern drug discovery, but there is still an urgent need for user-friendly interfaces that bridge the gap between these sophisticated tools and scientists, particularly those who are less computer savvy. Herein, we present DrugFlow, an AI-driven one-stop platform that offers a clean, convenient, and cloud-based interface to streamline early drug discovery workflows. By seamlessly integrating a range of innovative AI algorithms, covering molecular docking, quantitative structure-activity relationship modeling, molecular generation, ADMET (absorption, distribution, metabolism, excretion and toxicity) prediction, and virtual screening, DrugFlow can offer effective AI solutions for almost all crucial stages in early drug discovery, including hit identification and hit/lead optimization. We hope that the platform can provide sufficiently valuable guidance to aid real-word drug design and discovery. The platform is available at https://drugflow.com.

Assessing the performance of MM/PBSA and MM/GBSA methods. 10. Prediction reliability of binding affinities and binding poses for RNA-ligand complexes.

Ribonucleic acid (RNA)-ligand interactions play a pivotal role in a wide spectrum of biological processes, ranging from protein biosynthesis to cellular reproduction. This recognition has prompted the broader acceptance of RNA as a viable candidate for drug targets. Delving into the atomic-scale understanding of RNA-ligand interactions holds paramount importance in unraveling intricate molecular mechanisms and further contributing to RNA-based drug discovery. Computational approaches, particularly molecular docking, offer an efficient way of predicting the interactions between RNA and small molecules. However, the accuracy and reliability of these predictions heavily depend on the performance of scoring functions (SFs). In contrast to the majority of SFs used in RNA-ligand docking, the end-point binding free energy calculation methods, such as molecular mechanics/generalized Born surface area (MM/GBSA) and molecular mechanics/Poisson Boltzmann surface area (MM/PBSA), stand as theoretically more rigorous approaches. Yet, the evaluation of their effectiveness in predicting both binding affinities and binding poses within RNA-ligand systems remains unexplored. This study first reported the performance of MM/PBSA and MM/GBSA with diverse solvation models, interior dielectric constants (εin) and force fields in the context of binding affinity prediction for 29 RNA-ligand complexes. MM/GBSA is based on short (5 ns) molecular dynamics (MD) simulations in an explicit solvent with the YIL force field; the GBGBn2 model with higher interior dielectric constant (εin = 12, 16 or 20) yields the best correlation (Rp = -0.513), which outperforms the best correlation (Rp = -0.317, rDock) offered by various docking programs. Then, the efficacy of MM/GBSA in identifying the near-native binding poses from the decoys was assessed based on 56 RNA-ligand complexes. However, it is evident that MM/GBSA has limitations in accurately predicting binding poses for RNA-ligand systems, particularly compared with notably proficient docking programs like rDock and PLANTS. The best top-1 success rate achieved by MM/GBSA rescoring is 39.3%, which falls below the best results given by docking programs (50%, PLNATS). This study represents the first evaluation of MM/PBSA and MM/GBSA for RNA-ligand systems and is expected to provide valuable insights into their successful application to RNA targets.

Halogen-Bonded Organic Frameworks (XOFs) Based on N⋯Br+⋯N Bonds: Robust Organic Networks Constructed by Fragile Bonds.

Organic frameworks face a trade-off between the framework stability and the bonds dynamics, which necessitates the development of innovative linkages that enable stable frameworks without hindering efficient synthesis. While iodine(I)-based halogen-bonded organic frameworks (XOFs) have been developed, constructing XOFs based on bromine(I) is desirable yet challenging due to the high sensitivity of bromine(I) species. Here, we present the inaugural construction of stable bromine(I)-bridged two-dimensional (2D) halogen-bonded organic frameworks, XOF(Br)-TPy-BF4/OTf, based on sensitive [N…Br…N]+ halogen bonds. The formation of XOF(Br)-TPy-BF4/OTf was monitored by 1H NMR, XPS, IR, SEM, TEM, HR-TEM, SEAD. Their framework structures were established by the results from PXRD, theoretical simulations and SAXS. More importantly, XOF(Br) exhibited stable two-dimensional framework structures in various organic solvents and aqueous media, even over a wide pH range (pH 3-12), while the corresponding modelcompounds BrPy2BF4/OTf decomposed quickly even in the presence of minimal water. Furthermore, the influence of the counterions were investigated by replacing BF4 with OTf, which obviously improved the stability of XOF(Br). This characteristic enabled XOF(Br) to serve as efficient oxidizing reagents in aqueous environments, contrasting with the sensitivity of BrPy2BF4/OTf, which performed well only in organic media. This study opens new avenues for the development and application of multifunctional XOFs.

Multi-objective genetic algorithm for synchrotron radiation beamline optimization.

In beamline design, there are many floating parameters that need to be tuned; manual optimization is time-consuming and laborious work, and it is also difficult to obtain well optimized results. Moreover, there are always several objectives that need to be considered and optimized at the same time, making the problem more complicated. For example, asking for both the flux and energy to be as large as possible is a usual requirement, but the changing trends of these two variables are often contradictory. In this study, a novel optimization method based on a multi-objective genetic algorithm is introduced, the first attempt to optimize a beamline with multiple objectives. In order to verify this method, beamline ID17 of the European Synchrotron Radiation Facility (ESRF) is taken as an example for simulation, with energy and dose rate as objectives. The result shows that this method can be effective for beamline optimization, and an optimal solution set can be obtained within 30 generations. For the solutions whose objectives are both improved compared with those of ESRF beamline ID17, the maximums of energy and dose rate increase by around 7% and 20%, respectively.

DeepAtomicCharge: a new graph convolutional network-based architecture for accurate prediction of atomic charges.

Atomic charges play a very important role in drug-target recognition. However, computation of atomic charges with high-level quantum mechanics (QM) calculations is very time-consuming. A number of machine learning (ML)-based atomic charge prediction methods have been proposed to speed up the calculation of high-accuracy atomic charges in recent years. However, most of them used a set of predefined molecular properties, such as molecular fingerprints, for model construction, which is knowledge-dependent and may lead to biased predictions due to the representation preference of different molecular properties used for training. To solve the problem, we present a new architecture based on graph convolutional network (GCN) and develop a high-accuracy atomic charge prediction model named DeepAtomicCharge. The new GCN architecture is designed with only the atomic properties and the connection information between the atoms in molecules and can dynamically learn and convert molecules into appropriate atomic features without any prior knowledge of the molecules. Using the designed GCN architecture, substantial improvement is achieved for the prediction accuracy of atomic charges. The average root-mean-square error (RMSE) of DeepAtomicCharge is 0.0121 e, which is obviously more accurate than that (0.0180 e) reported by the previous benchmark study on the same two external test sets. Moreover, the new GCN architecture needs much lower storage space compared with other methods, and the predicted DDEC atomic charges can be efficiently used in large-scale structure-based drug design, thus opening a new avenue for high-performance atomic charge prediction and application.

CODD-Pred: A Web Server for Efficient Target Identification and Bioactivity Prediction of Small Molecules.

Target identification and bioactivity prediction are critical steps in the drug discovery process. Here we introduce CODD-Pred (COmprehensive Drug Design Predictor), an online web server with well-curated data sets from the GOSTAR database, which is designed with a dual purpose of predicting potential protein drug targets and computing bioactivity values of small molecules. We first designed a double molecular graph perception (DMGP) framework for target prediction based on a large library of 646 498 small molecules interacting with 640 human targets. The framework achieved a top-5 accuracy of over 80% for hitting at least one target on both external validation sets. Additionally, its performance on the external validation set comprising 200 molecules surpassed that of four existing target prediction servers. Second, we collected 56 targets closely related to the occurrence and development of cancer, metabolic diseases, and inflammatory immune diseases and developed a multi-model self-validation activity prediction (MSAP) framework that enables accurate bioactivity quantification predictions for small-molecule ligands of these 56 targets. CODD-Pred is a handy tool for rapid evaluation and optimization of small molecules with specific target activity. CODD-Pred is freely accessible at http://codd.iddd.group/.

Molecular Generation with Reduced Labeling through Constraint Architecture.

In the past few years, a number of machine learning (ML)-based molecular generative models have been proposed for generating molecules with desirable properties, but they all require a large amount of label data of pharmacological and physicochemical properties. However, experimental determination of these labels, especially bioactivity labels, is very expensive. In this study, we analyze the dependence of various multi-property molecule generation models on biological activity label data and propose Frag-G/M, a fragment-based multi-constraint molecular generation framework based on conditional transformer, recurrent neural networks (RNNs), and reinforcement learning (RL). The experimental results illustrate that, using the same number of labels, Frag-G/M can generate more desired molecules than the baselines (several times more than the baselines). Moreover, compared with the known active compounds, the molecules generated by Frag-G/M exhibit higher scaffold diversity than those generated by the baselines, thus making it more promising to be used in real-world drug discovery scenarios.

DeepChargePredictor: a web server for predicting QM-based atomic charges via state-of-the-art machine-learning algorithms.

SUMMARY: High-level quantum mechanics (QM) methods are no doubt the most reliable approaches for the prediction of atomic charges, but it usually needs very large computational resources, which apparently hinders the use of high-quality atomic charges in large-scale molecular modeling, such as high-throughput virtual screening. To solve this problem, several algorithms based on machine-learning (ML) have been developed to fit high-level QM atomic charges. Here, we proposed DeepChargePredictor, a web server that is able to generate the high-level QM atomic charges for small molecules based on two state-of-the-art ML algorithms developed in our group, namely AtomPathDescriptor and DeepAtomicCharge. These two algorithms were seamlessly integrated into the platform with the capability to predict three kinds of charges (i.e. RESP, AM1-BCC and DDEC) widely used in structure-based drug design. Moreover, we have comprehensively evaluated the performance of these charges generated by DeepChargePredictor for large-scale drug design applications, such as end-point binding free energy calculations and virtual screening, which all show reliable or even better performance compared with the baseline methods. AVAILABILITY AND IMPLEMENTATION: The data in the article can be obtained on the web page http://cadd.zju.edu.cn/deepchargepredictor/publication. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Organic Compound Synthetic Accessibility Prediction Based on the Graph Attention Mechanism.

Accurate estimation of the synthetic accessibility of small molecules is needed in many phases of drug discovery. Several expert-crafted scoring methods and descriptor-based quantitative structure-activity relationship (QSAR) models have been developed for synthetic accessibility assessment, but their practical applications in drug discovery are still quite limited because of relatively low prediction accuracy and poor model interpretability. In this study, we proposed a data-driven interpretable prediction framework called GASA (Graph Attention-based assessment of Synthetic Accessibility) to evaluate the synthetic accessibility of small molecules by distinguishing compounds to be easy- (ES) or hard-to-synthesize (HS). GASA is a graph neural network (GNN) architecture that makes self-feature deduction by applying an attention mechanism to automatically capture the most important structural features related to synthetic accessibility. The sampling around the hypothetical classification boundary was used to improve the ability of GASA to distinguish structurally similar molecules. GASA was extensively evaluated and compared with two descriptor-based machine learning methods (random forest, RF; eXtreme gradient boosting, XGBoost) and four existing scores (SYBA: SYnthetic Bayesian Accessibility; SCScore: Synthetic Complexity score; RAscore: Retrosynthetic Accessibility score; SAscore: Synthetic Accessibility score). Our analysis demonstrates that GASA achieved remarkable performance in distinguishing similar molecules compared with other methods and had a broader applicability domain. In addition, we show how GASA learns the important features that affect molecular synthetic accessibility by assigning attention weights to different atoms. An online prediction service for GASA was offered at http://cadd.zju.edu.cn/gasa/.

Fast and accurate prediction of partial charges using Atom-Path-Descriptor-based machine learning.

MOTIVATION: Partial atomic charges are usually used to calculate the electrostatic component of energy in many molecular modeling applications, such as molecular docking, molecular dynamics simulations, free energy calculations and so forth. High-level quantum mechanics calculations may provide the most accurate way to estimate the partial charges for small molecules, but they are too time-consuming to be used to process a large number of molecules for high throughput virtual screening. RESULTS: We proposed a new molecule descriptor named Atom-Path-Descriptor (APD) and developed a set of APD-based machine learning (ML) models to predict the partial charges for small molecules with high accuracy. In the APD algorithm, the 3D structures of molecules were assigned with atom centers and atom-pair path-based atom layers to characterize the local chemical environments of atoms. Then, based on the APDs, two representative ensemble ML algorithms, i.e. random forest (RF) and extreme gradient boosting (XGBoost), were employed to develop the regression models for partial charge assignment. The results illustrate that the RF models based on APDs give better predictions for all the atom types than those based on traditional molecular fingerprints reported in the previous study. More encouragingly, the models trained by XGBoost can improve the predictions of partial charges further, and they can achieve the average root-mean-square error 0.0116 e on the external test set, which is much lower than that (0.0195 e) reported in the previous study, suggesting that the proposed algorithm is quite promising to be used in partial charge assignment with high accuracy. AVAILABILITY AND IMPLEMENTATION: The software framework described in this paper is freely available at https://github.com/jkwang93/Atom-Path-Descriptor-based-machine-learning. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Halogen-Bonded Organic Framework (XOF) Based on Iodonium-Bridged N⋠⋠⋠I+ ⋠⋠⋠N Interactions: A Type of Diphase Periodic Organic Network.

Due to the fascinating structures and wide applications, porous materials with open frameworks have attracted more and more attentions. Herein, a novel two-dimensional (2D) halogen-bonded organic framework (XOF-TPPE) was successfully designed and fabricated by iodonium-bridged N⋅⋅⋅I+ ⋅⋅⋅N interactions between pyridyl groups and I+ for the first time. The formation of XOF-TPPE and its linear analogue was monitored by 1 H NMR, UV-Vis, X-ray photoelectron spectroscopy (XPS), IR, SEM, TEM, HRTEM and selected-area electron diffraction (SAED). The structural model of XOF-TPPE was established based on powder X-ray diffraction (PXRD) data and theoretical simulations. Significantly, synchrotron small-angle X-ray scattering (SAXS), DLS and UV-Vis spectroscopy experiments suggested that XOF-TPPE still maintains a stable 2D framework structure in solutions. This research opens up a novel avenue for the development of organic frameworks materials, and may bring new promising applications for the field of porous materials.

Nanoreactor based on single-atom nanoenzymes promotes ferroptosis for cancer immunotherapy.

Immunotherapy is a promising mainstream approach in anti-tumor therapy. It boasts advantages such as durable responses and lower side effects. However, there are still some limitations to be addressed. Current cancer immunotherapy has shown low response rates due to inadequate immunogenicity of certain tumor cells. To address these challenges, an acid-specific nanoreactor was developed, designed to induce immunogenicity by triggering ferroptosis in tumor cells. The nanoreactor integrates glucose oxidase (GOx) with a single-atom nanoenzyme (SAE), which exhibits high peroxidase (POD)-like activity in the acidic tumor microenvironment (TME). This specific acid-sensitivity transforms endogenous hydrogen peroxide (H2O2) into cytotoxic hydroxyl radicals (•OH). GOx enhances the POD-like SAE activity in the nanoreactor by metabolizing glucose in tumor cells, producing gluconic acid and H2O2. This nanoreactor induces high levels of oxidative stress within tumor cells through the synergistic action of SAE and GOx, leading to depletion of GSH and subsequently triggering ferroptosis. The resulting nanoreactor-induced ferroptosis leads to immunogenic cell death (ICD) and significantly recruits T lymphocyte infiltration in tumor tissues. This study was designed with the concept of triggering ferroptosis-dependent ICD mechanism in bladder cancer cells, and developed an acid-specific nanoreactor to enhance the immunotherapy efficacy for bladder cancer, which introduces a novel approach for immunotherapy of bladder cancer.

Insights into the Electrochemical Production of Hydrogen Peroxide over Single-Atom Co-N-C Catalysts with the Introduction of Carbon Vacancy Defect near the Co-N4 Site.

With the introduction of carbon divacancy, trivacancy, and tetravacancy defects near the Co-N4 site, we have explored the 2e- ORR activity at the Co-N4 site from the perspective of spatial structure and the atomic orbital by DFT calculations. We demonstrate the hybridization strength between Co 3dyz (3dxz) and O 2py (2px) orbitals is the origin of 2e- ORR activity at the Co-N4 site and the hybridization strength relates to the height of the Co 3d projected orbital in the Z direction. The bond length (LCo-O, LO-O), the charge transfer from the Co site to the *OOH adsorbate (ΔQCo-O), the d-band center of the Co site (εd), and the ICOHP value between Co 3d and O 2p orbitals as descriptors can well predict the 2e- ORR activity at the Co-N4 site. This work provides original insights into the 2e- ORR activity over the single-atom Co-N-C catalysts.

Combining multi-objective genetic algorithm and neural network dynamically for the complex optimization problems in physics.

Neural network (NN) has been tentatively combined into multi-objective genetic algorithms (MOGAs) to solve the optimization problems in physics. However, the computationally complex physical evaluations and limited computing resources always cause the unsatisfied size of training set, which further results in the combined algorithms handling strict constraints ineffectively. Here, the dynamically used NN-based MOGA (DNMOGA) is proposed for the first time, which includes dynamically redistributing the number of evaluated individuals to different operators and some other improvements. Radio frequency cavity is designed by this algorithm as an example, in which four objectives and an equality constraint (a sort of strict constraint) are considered simultaneously. Comparing with the baseline algorithms, both the number and competitiveness of the final feasible individuals of DNMOGA are considerably improved. In general, DNMOGA is instructive for dealing with the complex situations of strict constraints and preference in multi-objective optimization problems in physics.