Toxic responses of environmental concentrations of bifenthrin in larval freshwater snail Bellamya aeruginosa.

Bifenthrin (BF) is ubiquitous in aquatic environments, and studies have indicated that environmental concentrations of BF could cause neurotoxicity and oxidative damage in fish and decrease the abundance of aquatic insects. However, little information is available on the toxicity of BF in freshwater benthic mollusks. Bellamya aeruginosa (B. aeruginosa) is a key benthic fauna species in aquatic ecosystems, and has extremely high economic and ecological values. In this study, larval B. aeruginosa within 24 h of birth were exposed to 0, 30 or 300 ng/L of BF for 30 days, and then the toxic effects from molecular to individual levels were comprehensively evaluated in all the three treatment groups. It was found that BF at 300 ng/L caused the mortality of snails. Furthermore, BF affected snail behaviors, evidenced by reduced crawling distance and crawling speed. The hepatopancreas of snails in the two BF exposure groups showed significant pathological changes, including increase in the number of yellow granules and occurrence of hemocyte infiltration, epithelial cell thinning, and necrosis. The levels of ROS and MDA were significantly increased after exposure to 300 ng/L BF, and the activities of two antioxidant enzymes SOD and CAT were increased significantly. GSH content decreased significantly after BF exposure, indicating the occurrence of oxidative damage in snails. Transcriptomic results showed that differentially expressed genes (DEGs) were significantly enriched in pathways related to metabolism and neurotoxicity (e.g., oxidative phosphorylation and Parkinson disease), and these results were consistent with those in individual and biochemical levels above. The study indicates that environmental concentration of BF results in decreased survival rates, sluggish behavior, histopathological lesions, oxidative damage, and transcriptomic changes in the larvae of B. aeruginosa. Thus, exposure of larval snails to BF in the wild at concentrations similar to those used in this study might have adverse consequences at the population level. These findings provide a theoretical basis for further assessing the ecological risk of BF to aquatic gastropods.

Neuropilin-1-Targeted Nanomedicine for Spatiotemporal Tumor Suppression through Photodynamic Vascular Damage and Antiangiogenesis.

Antiangiogenic therapy is an effective way to disrupt nutrient supply and starve tumors, but it is restricted by poor efficacy and negative feedback-induced tumor relapse. In this study, a neuropilin-1 (NRP-1)-targeted nanomedicine (designated as FPPT@Axi) is reported for spatiotemporal tumor suppression by combining photodynamic therapy (PDT) with antiangiogenesis. In brief, FPPT@Axi is prepared by utilizing an NRP-1-targeting chimeric peptide (Fmoc-K(PpIX)-PEG8-TKPRR) to encapsulate the antiangiogenic drug Axitinib (Axi). Importantly, the NRP-1-mediated targeting property enables FPPT@Axi to selectively concentrate at vascular endothelial and breast cancer cells, facilitating the production of reactive oxygen species (ROS) in situ for specific vascular disruption and enhanced cell apoptosis under light stimulation. Moreover, the codelivered Axi can further inhibit vascular endothelial growth factor receptor (VEGFR) to impair the negative feedback of PDT-induced tumor neovascularization. Consequently, FPPT@Axi spatiotemporally restrains the tumor growth through blocking angiogenesis, destroying tumor vessels, and inducing tumor apoptosis. Such an NRP-1-mediated targeting codelivery system sheds light on constructing an appealing candidate with translational potential by using clinically approved PDT and chemotherapy.

Breaking Physical Barrier of Fibrotic Breast Cancer for Photodynamic Immunotherapy by Remodeling Tumor Extracellular Matrix and Reprogramming Cancer-Associated Fibroblasts.

Cancer-associated fibroblasts (CAFs) assist in breast cancer (BRCA) invasion and immune resistance by overproduction of extracellular matrix (ECM). Herein, we develop FPC@S, a photodynamic immunomodulator that targets the ECM, to improve the photodynamic immunotherapy for fibrotic BRCA. FPC@S combines a tumor ECM-targeting peptide, a photosensitizer (protoporphyrin IX) and an antifibrotic drug (SIS3). After anchoring to the ECM, FPC@S causes ECM remodeling and BRCA cell death by generating reactive oxygen species (ROS) in situ. Interestingly, the ROS-mediated ECM remodeling can normalize the tumor blood vessel to improve hypoxia and in turn facilitate more ROS production. Besides, upon the acidic tumor microenvironment, FPC@S will release SIS3 for reprograming CAFs to reduce their activity but not kill them, thus inhibiting fibrosis while preventing BRCA metastasis. The natural physical barrier formed by the dense ECM is consequently eliminated in fibrotic BRCA, allowing the drugs and immune cells to penetrate deep into tumors and have better efficacy. Furthermore, FPC@S can stimulate the immune system and effectively suppress primary, distant and metastatic tumors by combining with immune checkpoint blockade therapy. This study provides different insights for the development of fibrotic tumor targeted delivery systems and exploration of synergistic immunotherapeutic mechanisms against aggressive BRCA.

Discovery of potent small molecule inhibitors of histone lysine methyltransferase NSDs.

Nuclear receptor binding SET domain (NSD) proteins are a class of histone lysine methyltransferases and implicated in multiple cancer types with aberrant expression and involvement of cancer related signaling pathways. In this study, a series of small-molecule compounds including compound 2 and 3 are identified against the SET domain of NSDs through structure-based virtual screening. Our lead compound 3 exhibits potent inhibitory activities in vitro towards the NSD2-SET and NSD3-SET with an IC50 of 0.81 µM and 0.84 µM, respectively, and efficiently inhibits histone H3 lysine 36 dimethylation and decreases the expression of NSDs-targeted genes in non-small cell lung cancer cells at 100 nM. Compound 3 suppresses cell proliferation and reduces the clonogenicity in H460 and H1299 non-small cell lung cancer cells, and induces s-phase cell cycle arrest and apoptosis. These data establish our compounds as a valuable tool-kit for the study of the biological roles of NSDs in cancer.

Status and Prospects of Research on Deep Learning-based De Novo Generation of Drug Molecules.

Traditional molecular de novo generation methods, such as evolutionary algorithms, generate new molecules mainly by linking existing atomic building blocks. The challenging issues in these methods include difficulty in synthesis, failure to achieve desired properties, and structural optimization requirements. Advances in deep learning offer new ideas for rational and robust de novo drug design. Deep learning, a branch of machine learning, is more efficient than traditional methods for processing problems, such as speech, image, and translation. This study provides a comprehensive overview of the current state of research in de novo drug design based on deep learning and identifies key areas for further development. Deep learning-based de novo drug design is pivotal in four key dimensions. Molecular databases form the basis for model training, while effective molecular representations impact model performance. Common DL models (GANs, RNNs, VAEs, CNNs, DMs) generate drug molecules with desired properties. The evaluation metrics guide research directions by determining the quality and applicability of generated molecules. This abstract highlights the foundational aspects of DL-based de novo drug design, offering a concise overview of its multifaceted contributions. Consequently, deep learning in de novo molecule generation has attracted more attention from academics and industry. As a result, many deep learning-based de novo molecule generation types have been actively proposed.

Tumor Homing Chimeric Peptide Rhomboids to Improve Photodynamic Performance by Inhibiting Therapy-Upregulated Cyclooxygenase-2.

Negative therapeutic feedback of inflammation would extensively attenuate the antitumor effect of photodynamic therapy (PDT). In this work, tumor homing chimeric peptide rhomboids (designated as NP-Mel) are fabricated to improve photodynamic performance by inhibiting PDT-upregulated cyclooxygenase-2 (COX-2). The hydrophobic photosensitizer of protoporphyrin IX (PpIX) and palmitic acid are conjugated onto the neuropilin receptors (NRPs) targeting peptide motif (CGNKRTR) to obtain tumor homing chimeric peptide (Palmitic-K(PpIX)CGNKRTR), which can encapsulate the COX-2 inhibitor of meloxicam. The well dispersed NP-Mel not only improves the drug stability and reactive oxygen species (ROS) production ability, but also increase the breast cancer targeted drug delivery to intensify the PDT effect. In vitro and in vivo studies verify that NP-Mel will decrease the secretion of prostaglandin E2 (PGE2) after PDT treatment, inducing the downregulation of IL-6 and TNF-α expressions to suppress PDT induced inflammation. Ultimately, an improved PDT performance of NP-Mel is achieved without inducing obvious systemic toxicity, which might inspire the development of sophisticated nanomedicine in consideration of the feedback induced therapeutic resistance.

Self-Delivery Photodynamic Re-educator Enhanced Tumor Treatment by Inducing Immunogenic Cell Death and Improving Immunosuppressive Microenvironments.

Immunotherapy is known to be a promising strategy in the clinical treatment of malignant tumors, but it has received generally low response rates in various tumors because of the poor immunogenicity and multiple immunosuppressive microenvironments. A self-delivery photodynamic re-educator, denoted as CCXB, is synthesized through the self-assembly of chlorine e6 (Ce6) and celecoxib (CXB). As a carrier-free nanomedicine, CCXB shows a high drug loading rate, improved water stability, superior cellular uptake, and tumor accumulation capability. In comparison with free Ce6, CCXB triggers much stronger photodynamic therapy (PDT) to reduce the proliferation of breast cancer cells and activates robust immune responses via the induction of immunogenic cell death (ICD). Better yet, CXB-mediated cyclooxygenase 2 (COX-2) inhibition can decrease the level of synthesis of prostaglandin E2 (PGE2) to further improve immunosuppressive microenvironments. With the increase of cytotoxic T lymphocytes (CTLs) and decrease of regulatory T cells (Tregs) in tumor, in vivo antitumor immunity is significantly amplified to inhibit the metastasis of breast cancer. This study sheds light on developing drug codelivery systems with collaborative mechanisms for immunotherapy of metastatic tumors.

CoDock-Ligand: combined template-based docking and CNN-based scoring in ligand binding prediction.

For ligand binding prediction, it is crucial for molecular docking programs to integrate template-based modeling with a precise scoring function. Here, we proposed the CoDock-Ligand docking method that combines template-based modeling and the GNINA scoring function, a Convolutional Neural Network-based scoring function, for the ligand binding prediction in CASP15. Among the 21 targets, we obtained successful predictions in top 5 submissions for 14 targets and partially successful predictions for 4 targets. In particular, for the most complicated target, H1114, which contains 56 metal cofactors and small molecules, our docking method successfully predicted the binding of most ligands. Analysis of the failed systems showed that the predicted receptor protein presented conformational changes in the backbone and side chains of the binding site residues, which may cause large structural deviations in the ligand binding prediction. In summary, our hybrid docking scheme was efficiently adapted to the ligand binding prediction challenges in CASP15.

Impact of AlphaFold on structure prediction of protein complexes: The CASP15-CAPRI experiment.

We present the results for CAPRI Round 54, the 5th joint CASP-CAPRI protein assembly prediction challenge. The Round offered 37 targets, including 14 homodimers, 3 homo-trimers, 13 heterodimers including 3 antibody-antigen complexes, and 7 large assemblies. On average ~70 CASP and CAPRI predictor groups, including more than 20 automatics servers, submitted models for each target. A total of 21 941 models submitted by these groups and by 15 CAPRI scorer groups were evaluated using the CAPRI model quality measures and the DockQ score consolidating these measures. The prediction performance was quantified by a weighted score based on the number of models of acceptable quality or higher submitted by each group among their five best models. Results show substantial progress achieved across a significant fraction of the 60+ participating groups. High-quality models were produced for about 40% of the targets compared to 8% two years earlier. This remarkable improvement is due to the wide use of the AlphaFold2 and AlphaFold2-Multimer software and the confidence metrics they provide. Notably, expanded sampling of candidate solutions by manipulating these deep learning inference engines, enriching multiple sequence alignments, or integration of advanced modeling tools, enabled top performing groups to exceed the performance of a standard AlphaFold2-Multimer version used as a yard stick. This notwithstanding, performance remained poor for complexes with antibodies and nanobodies, where evolutionary relationships between the binding partners are lacking, and for complexes featuring conformational flexibility, clearly indicating that the prediction of protein complexes remains a challenging problem.

NLRP6 potentiates PI3K/AKT signalling by promoting autophagic degradation of p85α to drive tumorigenesis.

The PI3K/AKT pathway plays an essential role in tumour development. NOD-like receptors (NLRs) regulate innate immunity and are implicated in cancer, but whether they are involved in PI3K/AKT pathway regulation is poorly understood. Here, we report that NLRP6 potentiates the PI3K/AKT pathway by binding and destabilizing p85α, the regulatory subunit of PI3K. Mechanistically, NLRP6 recruits the E3 ligase RBX1 to p85α and ubiquitinates lysine 256 on p85α, which is recognized by the autophagy cargo receptor OPTN, causing selective autophagic degradation of p85α and subsequent activation of the PI3K/AKT pathway by reducing PTEN stability. We further show that loss of NLRP6 suppresses cell proliferation, colony formation, cell migration, and tumour growth in glioblastoma cells in vitro and in vivo. Disruption of the NLRP6/p85α interaction using the Pep9 peptide inhibits the PI3K/AKT pathway and generates potent antitumour effects. Collectively, our results suggest that NLRP6 promotes p85α degradation via selective autophagy to drive tumorigenesis, and the interaction between NLRP6 and p85α can be a promising therapeutic target for tumour treatment.

UPLC-Q TOF-MS-Based metabolomics and anti-myocardial ischemia activity of Dioscoreae Nipponicae Rhizoma from different geographical origins.

The dried rhizome of Dioscorea nipponica Makino ("Chuanshanlong" in Chinese) is a medicinal herb with multiple major producing areas. The main objective of this study was the comparative profiling of Dioscoreae Nipponicae Rhizoma (DNR) from various geographical origins. A hypoxia/reoxygenation-induced H9c2 cell injury model was established, and the antimyocardial ischemia activity of DNR samples from different origins was detected using the cell counting kit-8 (CCK-8) method. The result showed that the antimyocardial ischemia potential of DNR samples from the Heilongjiang province was higher than that of the other studied samples. Subsequently, a plant metabolomics technique utilizing ultra-high performance liquid chromatography coupled with quadrupole time-of-flight mass spectrometry (UPLC-Q TOF-MS) was used to determine the differences in DNR samples from various geographical origins. Forty compounds, including steroidal saponins, free fatty acids, and organic acids, were tentatively identified based on UPLC-Q TOF-MS fragmentation pathways and via comparison with available reference standards. Partial least squares discriminant analysis was performed to estimate the differences in DNR samples from different origins. Five compounds were significantly up-regulated and correlated with antimyocardial ischemia in DNR samples from Heilongjiang province. Molecular docking was used to discern the interactions of key markers with the active sites of the target protein. The findings signified that UPLC-Q TOF-MS metabolomics coupled with molecular docking is a powerful tool to rapidly identify the quality control characteristics of DNR samples and their products. The research provides a direction for the rational utilization of DNR.

Tris(1,3-dichloro-2-propyl) Phosphate Inhibits Early Embryonic Development by Binding to Gsk-3ß Protein in Zebrafish.

Recently, several studies have reported that exposure to tris(1,3-dichloro-2-propyl) phosphate (TDCIPP) results in abnormal development of zebrafish embryos in blastocyst and gastrula stages, but molecular mechanisms are still not clear. This lacking strongly affects the interspecific extrapolation of embryonic toxicity induced by TDCIPP and hazard evaluation. In this study, zebrafish embryos were exposed to 100, 500 or 1000 µg/L TDCIPP, and 6-bromoindirubin-3'-oxime (BIO, 35.62 µg/L) was used as a positive control. Results demonstrated that treatment with TDCIPP or BIO caused an abnormal stacking of blastomere cells in mid blastula transition (MBT) stage, and subsequently resulted in epiboly delay of zebrafish embryos. TDCIPP and BIO up-regulated the expression of ß-catenin protein and increased its accumulation in nuclei of embryonic cells. This accumulation was considered as a driver for early embryonic developmental toxicity of TDCIPP. Furthermore, TDCIPP and BIO partly shared the same modes of action, and both of them could bind to Gsk-3ß protein, and then decreased the phosphorylation level of Gsk-3ß in TYR·216 site and lastly inhibited the activity of Gsk-3ß kinase, which was responsible for the increased concentrations of ß-catenin protein in embryonic cells and accumulation in nuclei. Our findings provide new mechanisms for clarifying the early embryonic developmental toxicity of TDCIPP in zebrafish.

Feedback-Elevated Antitumor Amplifier of Self-Delivery Nanomedicine by Suppressing Photodynamic Therapy-Caused Inflammation.

Inflammation activation is accompanied by tumor growth, migration, and differentiation. Photodynamic therapy (PDT) can trigger an inflammatory response to cause negative feedback of tumor inhibition. In this paper, a feedback-elevated antitumor amplifier is developed by constructing self-delivery nanomedicine for PDT and cascade anti-inflammation therapy. Based on the photosensitizer chlorin e6 (Ce6) and COX-2 inhibitor indomethacin (Indo), the nanomedicine is prepared via molecular self-assembly technology without additional drug carriers. It is exciting that the optimized nanomedicine (designated as CeIndo) possesses favorable stability and dispersibility in the aqueous phase. Moreover, the drug delivery efficiency of CeIndo is significantly improved, which could be effectively accumulated at the tumor site and internalized by tumor cells. Importantly, CeIndo not only exhibits a robust PDT efficacy on tumor cells but also drastically decreases the PDT-induced inflammatory response in vivo, resulting in feedback-elevated tumor inhibition. By virtue of the synergistic effect of PDT and cascade inflammation suppression, CeIndo tremendously reduces tumor growth and leads to a low side effect. This study presents a paradigm for the development of codelivery nanomedicine for enhanced tumor therapy through inflammation suppression.

Carrier-Free Nano-PROTACs to Amplify Photodynamic Therapy Induced DNA Damage through BRD4 Degradation.

Therapy-induced DNA damage is the most common strategy to inhibit tumor cell proliferation, but the therapeutic efficacy is limited by DNA repair machinery. Carrier-free nanoproteolysis targeting chimeras (PROTACs), designed as SDNpros, have been developed to enhance photodynamic therapy (PDT) by blocking the DNA damage repair pathway through BRD4 degradation. Specifically, SDNpros are constructed through noncovalent interactions between the photosensitizer of chlorine e6 (Ce6) and PROTACs of BRD4 degrader (dBET57) via self-assembly. SDNpro has favorable dispersibility and a uniform nanosize distribution without drug excipients. Upon light irradiation, SDNpro produces abundant reactive oxygen species (ROS) to induce DNA oxidative damage. Meanwhile, the DNA repair pathway would be interrupted by the concurrent degradation of BRD4, which could intensify the oxidative DNA damage and elevate PDT efficiency. Beneficially, SDNpro suppresses tumor growth and avoids systemic side effects, providing a promising strategy to promote the clinical translation of PROTACs for tumor treatment.

Antibody sequences assembly method based on weighted de Bruijn graph.

With the development of next-generation protein sequencing technologies, sequence assembly algorithm has become a key technology for de novo sequencing process. At present, the existing methods can address the assembly of an unknown single protein chain. However, for monoclonal antibodies with light and heavy chains, the assembly is still an unsolved question. To address this problem, we propose a new assembly method, DBAS, which integrates the quality scores and sequence alignment scores from de novo sequencing peptides into a weighted de Bruijn graph to assemble the final protein sequences. The established method is used to assembling sequences from two datasets with mixed light and heavy chains from antibodies. The results show that the DBAS can assemble long antibody sequences for both mixed light and heavy chains and single chains. In addition, DBAS is able to distinguish the light and heavy chains by using BLAST sequence alignment. The results show that the algorithm has good performance for both target sequence coverage and contig assembly accuracy.

nCoVDock2: a docking server to predict the binding modes between COVID-19 targets and its potential ligands.

The rapid emergence of SARS-CoV-2 variants with multi-sites mutations is considered as a major obstacle for the development of drugs and vaccines. Although most of the functional proteins essential for SARS-CoV-2 have been determined, the understanding of the COVID-19 target-ligand interactions remains a key challenge. The old version of this COVID-19 docking server was built in 2020, and free and open to all users. Here, we present nCoVDock2, a new docking server to predict the binding modes for targets from SARS-CoV-2. First, the new server supports more targets. We replaced the modeled structures with newly resolved structures and added more potential targets of COVID-19, especially for the variants. Second, for small molecule docking, Autodock Vina was upgraded to the latest version 1.2.0, and a new scoring function was added for peptide or antibody docking. Third, the input interface and molecular visualization were updated for a better user experience. The web server, together with an extensive help and tutorial, are freely available at: https://ncovdock2.schanglab.org.cn.

Paraptosis Inducer to Effectively Trigger Immunogenic Cell Death for Metastatic Tumor Immunotherapy with IDO Inhibition.

Paraptosis is characterized by the extensive vacuolization of endoplasmic reticulum (ER) and mitochondria, which will cause the release of damage-associated molecular patterns to promote immunogenic cell death (ICD). However, the tumor can develop an immunosuppressive microenvironment to affect the ICD activation for the purpose of immune escape. Herein, a paraptosis inducer (CMN) is constructed to amplify the ICD effect for efficient immunotherapy by inhibiting the activity of indoleamine 2,3-dioxygenase (IDO). Initially, CMN is prepared by the assembly of copper ions (Cu2+), morusin (MR), and IDO inhibitor (NLG919) through noncovalent interactions. Without the need for extra drug carriers, CMN possesses very high drug contents and exhibits a favorable GSH responsiveness for disassembly. Subsequently, the released MR can trigger paraptosis to cause extensive vacuolization of ER and mitochondria, contributing to activating ICD for immunotherapy. Moreover, NLG919 would inhibit IDO to remodel the tumor microenvironment and promote the activation of cytotoxic T cells, leading to an intensive antitumor immunity. Abundant in vivo studies indicate that CMN is superior in suppressing the proliferations of not only primary tumor but also metastatic and rechallenged tumors. Such a GSH-responsive paraptosis inducer might provide a promising strategy to trigger ICD and enhance tumor immunotherapy.

Docking guided phase display to develop fusion protein with novel scFv and alkaline phosphatase for one-step ELISA salbutamol detection.

Introduction: Salbutamol (SAL) is a ß2 adrenergic receptor agonist which has potential hazardous effects for human health. It is very important to establish a sensitive and convenient method to monitor SAL. Methods: Here we introduce a method to combine the information from docking and site specific phage display, with the aim to obtain scFv with high affinity to SAL. First, single chain variable fragment (scFv) antibodies against SAL were generated through phage display. By using molecular docking approach, the complex structure of SAL with antibody was predicted and indicated that H3 and L3 contribute to the binding. Then new libraries were created by randomization specific residues located on H3 and L3 according to the docking results. Results and discussion: Anti-SAL scFv antibodies with high efficiency were finally identified. In addition, the selected scFv was fused with alkaline phosphatase and expressed in E coli to develop a rapid and low-cost one step ELISA to detect SAL.

Exposure to environmentally relevant concentrations of TnBP results in tissue-specific bio-accumulation and inhibits growth of silver carp (Hypophthalmichthys molitrix).

Tri-n-butyl phosphate (TnBP) is commonly used as flame retardant and rubber plasticizer, and has been widely detected in aquatic organisms and natural waters. However, the potential toxicity of TnBP in fish remains unclear. In the present study, silver carp (Hypophthalmichthys molitrix) larvae were treated with environmentally relevant concentrations (100 or 1000 ng/L) of TnBP for 60 d and then they were depurated in clean water for 15 d, and the accumulation and depuration of the chemical in six tissues of silver carp were measured. Furthermore, effects on growth were evaluated and potential molecular mechanisms were explored. Results indicated that TnBP could be rapidly accumulated and depurated in silver carp tissues. In addition, the bio-accumulation of TnBP displayed tissue-specificity, where intestine contained the greatest and vertebra had the smallest level of TnBP. Furthermore, exposure to environmentally relevant concentrations of TnBP led to time- and concentration-dependent growth inhibition of silver carp, even though TnBP was completely depurated in tissues. Mechanistic studies suggested that exposure to TnBP up- and down-regulated the expression of ghr and igf1 in liver, respectively, and increased GH contents in plasma of silver carp. TnBP exposure also up-regulated the expression of ugt1ab and dio2 in liver, as well as decreased T4 contents in plasma of silver carp. Our findings provide direct evidence of health hazards of TnBP to fish in natural waters, calling for more attention of environmental risks of TnBP in aquatic environment.

Generating new protein sequences by using dense network and attention mechanism.

Protein engineering uses de novo protein design technology to change the protein gene sequence, and then improve the physical and chemical properties of proteins. These newly generated proteins will meet the needs of research better in properties and functions. The Dense-AutoGAN model is based on GAN, which is combined with an Attention mechanism to generate protein sequences. In this GAN architecture, the Attention mechanism and Encoder-decoder can improve the similarity of generated sequences and obtain variations in a smaller range on the original basis. Meanwhile, a new convolutional neural network is constructed by using the Dense. The dense network transmits in multiple layers over the generator network of the GAN architecture, which expands the training space and improves the effectiveness of sequence generation. Finally, the complex protein sequences are generated on the mapping of protein functions. Through comparisons of other models, the generated sequences of Dense-AutoGAN verify the model performance. The new generated proteins are highly accurate and effective in chemical and physical properties.