AACFlow: an end-to-end model based on attention augmented convolutional neural network and flow-attention mechanism for identification of anticancer peptides.

MOTIVATION: Anticancer peptides (ACPs) have natural cationic properties and can act on the anionic cell membrane of cancer cells to kill cancer cells. Therefore, ACPs have become a potential anticancer drug with good research value and prospect. RESULTS: In this article, we propose AACFlow, an end-to-end model for identification of ACPs based on deep learning. End-to-end models have more room to automatically adjust according to the data, making the overall fit better and reducing error propagation. The combination of attention augmented convolutional neural network (AAConv) and multi-layer convolutional neural network (CNN) forms a deep representation learning module, which is used to obtain global and local information on the sequence. Based on the concept of flow network, multi-head flow-attention mechanism is introduced to mine the deep features of the sequence to improve the efficiency of the model. On the independent test dataset, the ACC, Sn, Sp, and AUC values of AACFlow are 83.9%, 83.0%, 84.8%, and 0.892, respectively, which are 4.9%, 1.5%, 8.0%, and 0.016 higher than those of the baseline model. The MCC value is 67.85%. In addition, we visualize the features extracted by each module to enhance the interpretability of the model. Various experiments show that our model is more competitive in predicting ACPs.

NeuroPred-ResSE: Predicting neuropeptides by integrating residual block and squeeze-excitation attention mechanism.

Neuropeptides play crucial roles in regulating neurological function acting as signaling molecules, which provide new opportunity for developing drugs for the treatment of neurological diseases. Therefore, it is very necessary to develop a rapid and accurate prediction model for neuropeptides. Although a few prediction tools have been developed, there is room for improvement in prediction accuracy by using deep learning approach. In this paper, we establish the NeuroPred-ResSE model based on residual block and squeeze-excitation attention mechanism. Firstly, we extract multi-features by using one-hot coding based on the NT5CT5 sequence, dipeptide deviation from expected mean and natural vector. Then, we integrate residual block and squeeze-excitation attention mechanism, which can capture and identify the most relevant attribute features. Finally, the accuracies of the training set and test set are 97.16 % and 96.60 % based on the 5-fold cross-validation and independent test, respectively, and other evaluation metrics have also obtained satisfactory results. The experimental results show that the performance of the NeuroPred-ResSE model outperforms those of existing state-of-the-art models, and our model is an effective, intelligent and robust prediction tool. The datasets and source codes are available at https://github.com/yunyunliang88/NeuroPred-ResSE.

Exosomal miR-673-5p from fibroblasts promotes Schwann cell-mediated peripheral neuron myelination by targeting the TSC2/mTORC1/SREBP2 axis.

Peripheral myelination is a complicated process, wherein Schwann cells (SCs) promote the formation of the myelin sheath around the axons of peripheral neurons. Fibroblasts are the second resident cells in the peripheral nerves; however, the precise function of fibroblasts in SC-mediated myelination has rarely been examined. Here, we show that exosomes derived from fibroblasts boost myelination-related gene expression in SCs. We used exosome sequencing, together with bioinformatic analysis, to demonstrate that exosomal microRNA miR-673-5p is capable of stimulating myelin gene expression in SCs. Subsequent functional studies revealed that miR-673-5p targets the regulator of mechanistic target of the rapamycin (mTOR) complex 1 (mTORC1) tuberous sclerosis complex 2 in SCs, leading to the activation of downstream signaling pathways including mTORC1 and sterol-regulatory element binding protein 2. In vivo experiments further confirmed that miR-673-5p activates the tuberous sclerosis complex 2/mTORC1/sterol-regulatory element binding protein 2 axis, thus promoting the synthesis of cholesterol and related lipids and subsequently accelerating myelin sheath maturation in peripheral nerves. Overall, our findings revealed exosome-mediated cross talk between fibroblasts and SCs that plays a pivotal role in peripheral myelination. We propose that exosomes derived from fibroblasts and miR-673-5p might be useful for promoting peripheral myelination in translational medicine.

Hexapartite steering based on a four-wave-mixing process with a spatially structured pump.

Multipartite Einstein-Podolsky-Rosen (EPR) steering has been widely studied, for realizing safer quantum communication. The steering properties of six spatially separated beams from the four-wave-mixing process with a spatially structured pump are investigated. Behaviors of all (1+i)/(i+1)-mode (i=1,2,3) steerings are understandable, if the role of the corresponding relative interaction strengths are taken into account. Moreover, stronger collective multipartite steerings including five modes can be obtained in our scheme, which has potential applications in ultra-secure multiuser quantum networks when the issue of trust is critical. By further discussing about all monogamy relations, it is noticed that the type-IV monogamy relations, which are naturally included in our model, are conditionally satisfied. Matrix representation is used to express the steerings for the first time, which is very useful to understand the monogamy relations intuitively. Different steering properties obtained in this compact phase-insensitive scheme have potential applications for different kinds of quantum communication tasks.

Identification of DNA N4-methylcytosine sites based on multi-source features and gradient boosting decision tree.

N4-methylcytosine (4 mC) is an important and common methylation which widely exists in prokaryotes. It plays a crucial role in correcting DNA replication errors and protecting host DNA against degradation by restrictive enzymes. Hence, the accurate identification for 4 mC sites is greatly significant for understanding biological functions and treating gene diseases. In this paper, a novel model is designed for identifying 4 mC sites. Firstly, we extract features from original sequences by multi-source feature representation methods, which are mono-nucleotide binary and k-mer frequency, dinucleotide binary and position-specific frequency, ring-function-hydrogen-chemical properties, dinucleotide-based DNA properties and trinucleotide-based DNA properties. Subsequently, gradient boosting decision tree is applied to select the optimal feature set and remove redundant information. Finally, support vector machine is employed to predict 4 mC or non-4mC sites. The accuracies of six datasets reach 0.851, 0.859, 0.801, 0.87, 0.859 and 0.901, respectively, which are superior to previous prediction methods. Therefore, the results show that our predictor is a feasible and effective tool for identifying 4 mC sites. Furthermore, an online web server is established at http://dnan4c.zhanglab.site.

Data driven adaptive Gaussian mixture model for solving Fokker-Planck equation.

The Fokker-Planck (FP) equation provides a powerful tool for describing the state transition probability density function of complex dynamical systems governed by stochastic differential equations (SDEs). Unfortunately, the analytical solution of the FP equation can be found in very few special cases. Therefore, it has become an interest to find a numerical approximation method of the FP equation suitable for a wider range of nonlinear systems. In this paper, a machine learning method based on an adaptive Gaussian mixture model (AGMM) is proposed to deal with the general FP equations. Compared with previous numerical discretization methods, the proposed method seamlessly integrates data and mathematical models. The prior knowledge generated by the assumed mathematical model can improve the performance of the learning algorithm. Also, it yields more interpretability for machine learning methods. Numerical examples for one-dimensional and two-dimensional SDEs with one and/or two noises are given. The simulation results show the effectiveness and robustness of the AGMM technique for solving the FP equation. In addition, the computational complexity and the optimization algorithm of the model are also discussed.

iPromoter-ET: Identifying promoters and their strength by extremely randomized trees-based feature selection.

Promoter is a region of DNA that determines the transcription of a particular gene. There are several σ factors in the RNA polymerase, which has the function of identifying the promoter and facilitating the binding of the RNA polymerase to the promoter. Owing to the importance of promoter in genome research, it is an urgent task to develop computational tool for effectively identifying promoters and their strength facing the avalanche of DNA sequences discovered in the post-genomic age. In this paper, we develop a model named iPromoter-ET using the k-mer nucleotide composition, binary encoding and dinucleotide property matrix-based distance transformation for features extraction, and extremely randomized trees (extra trees) for feature selection. Its 1st layer is used to identify whether a DNA sequence is of promoter or not, while its 2nd layer is to identify promoter samples as being strong or weak promoter. Support vector machine and the five cross-validation are used to perform identification and assess performance, respectively. The results indicate that our model remarkably outperforms the existing models in both the 1st and 2nd layers for accuracy and stability. We anticipate that our proposed model will become a very effective intelligent tool, or at the least, a complementary tool to the existing modes of identifying promoters and their strength. Moreover, the datasets and codes for iPromoter-ET are freely available at https://github.com/shengli0201/iPromoter-ET.

Identify Gram-negative bacterial secreted protein types by incorporating different modes of PSSM into Chou's general PseAAC via Kullback-Leibler divergence.

Gram-negative bacterial secreted proteins are crucial for bacterial pathogenesis by making bacteria interact with their environments. Therefore, identification of bacterial secreted proteins becomes a significant process for the research of various diseases and the corresponding drugs. In this paper, we develop a feature design model named ACCP-KL-NMF by fusing PSSM-based auto-cross correlation analysis for features extraction and nonnegative matrix factorization algorithm based on Kullback-Leibler divergence for dimensionality reduction. Hence, a 150-dimensional feature vector is constructed on the training set. Then support vector machine is adopted as the classifier, and the most objective jackknife test is chosen for evaluating the accuracy. The ACCP-KL-NMF model yields the approving performance of the overall accuracy on the test set, and also outperforms the other three existing models. The numerical experimental results show that our model is effective and reliable for identification of Gram-negative bacterial secreted protein types. Moreover, it is anticipated that the proposed model could be beneficial for other biology sequence in future research.

Predicting apoptosis protein subcellular localization by integrating auto-cross correlation and PSSM into Chou's PseAAC.

The prediction of subcellular localization of an apoptosis protein is still a challenging task, and existing methods mainly based on protein primary sequences. In this study, we propose a novel model called MACC-PSSM by integrating Moran autocorrelation and cross correlation with PSSM. Then a 3600-dimensional feature vector is constructed to predict apoptosis protein subcellular localization. Finally, 210 features are selected using principal component analysis (PCA) on the ZW225 dataset, and support vector machine is adopted as classifier. To evaluate the performance of the proposed method, jackknife cross-validation tests are performed on two widely used benchmark datasets: ZW225 and CL317. Our model achieves competitive performance on prediction accuracies, especially for the overall prediction accuracies for datasets ZW225 and CL317, which reach 84.9% and 90.5%, respectively. Comparison of our results with other methods demonstrates that MACC-PSSM model can be used as a potential candidate for the accurate prediction of apoptosis protein subcellular localization.

Prediction of Apoptosis Protein's Subcellular Localization by Fusing Two Different Descriptors Based on Evolutionary Information.

The apoptosis protein has a central role in the development and the homeostasis of an organism. Obtaining information about the subcellular localization of apoptosis protein is very helpful to understand the apoptosis mechanism and the function of this protein. Prediction of apoptosis protein's subcellular localization is a challenging task, and currently the existing feature extraction methods mainly rely on the protein's primary sequence. In this paper we develop a feature extraction model based on two different descriptors of evolutionary information, which contains the 192 frequencies of triplet codons (FTC) in the RNA sequence derived from the protein's primary sequence and the 190 features from a detrended forward moving-average cross-correlation analysis (DFMCA) based on a position-specific scoring matrix (PSSM) generated by the PSI-BLAST program. Hence, this model is called FTC-DFMCA-PSSM. A 382-dimensional (382D) feature vector is constructed on the ZD98, ZW225 and CL317 datasets. Then a support vector machine is adopted as classifier, and the jackknife cross-validation test method is used for evaluating the accuracy. The overall prediction accuracies are further improved by an objective and rigorous jackknife test. Our model not only broadens the source of the feature information, but also provides a more accurate and reliable automated calculation method for the prediction of apoptosis protein's subcellular localization.

Tunable random polymer fiber laser.

We have demonstrated the realization of on-line temperature-controlled random lasers (RLs) in the polyhedral oligomeric silsesquioxanes (POSS) nanoparticles (NPs) as well as Pyrromethene 597 (PM597) laser dye, Fe3O4/SiO2 NPs as well as PM597, and only PM597 doped polymer optical fibers (POFs), respectively. The RLs can be obtained from the gained POFs system caused by multiple scattering of emitted light. The refractive index of the fiber core materials can be easily tuned via temperature due to the polymer with large thermo-optic coefficient. Meanwhile, the scattering mean free path of core in the POFs, which is the key role for the emission wavelength of RLs, is strongly dependent on the matrix refractive index. Thus emission wavelength of RLs in the POF temperature can be controlled through changing the temperature. With the increasing the temperature, the RL emission wavelength has occurred red-shift effect for the POFs.

Polarized random laser emission from an oriented disorder polymer optical fiber.

We demonstrate the realization of a polarized random polymer fiber laser (RPFL) in the different disordered gain media doped polymer optical fibers (POFs). Multiple scattering of disordered media in the orientated POF was experimentally verified to account for polarized lasing observed in our RPFL system. This Letter presents a new avenue for fabricating polarized RPFLs in a large scale. Meanwhile, the polarization-maintaining property of random lasing for different disorder POF are researched, which will open a window to designing a polarization-maintaining random fiber laser.

Wavelength control of random polymer fiber laser based on adaptive disorder.

We demonstrate the realization of two different kinds of random polymer optical fiber lasers to control the random lasing wavelength by changing the disorder of polymer optical fibers (POFs). One is a long-range disorder POF based on copolymer refractive-index inhomogeneity, and the other is a short-range disorder POF based on polyhedral oligomeric silsesquioxanes scattering. By end pumped both disorder POFs, the coherent random lasing for both is observed. Meanwhile, the random lasing wavelength of the short-range disorder POF because of a small scattering mean-free path has been found to be blue shifted with respect to the long-range disorder POF, which will give a way to control the random lasing wavelength.

Improving the prediction accuracy of protein structural class: approached with alternating word frequency and normalized Lempel-Ziv complexity.

Prediction of protein structural class for low-similarity sequences remains a challenging problem. In this study, the new computational method has been developed to predict protein structural class by incorporating alternating word frequency and normalized Lempel-Ziv complexity. To evaluate the performance of the proposed method, jackknife cross-validation tests are performed on three widely used benchmark datasets, 25PDB, 1189 and 640, respectively. We report 83.6%, 81.8% and 83.6% prediction accuracies for 25PDB, 1189 and 640 benchmarks, respectively. Comparison of our results with other methods shows that the proposed method is very promising and may provide a cost-effective alternative to predict protein structural class in particular for low-similarity datasets and may at least play an important complementary role to existing methods.

TMSC-m7G: A transformer architecture based on multi-sense-scaled embedding features and convolutional neural network to identify RNA N7-methylguanosine sites.

RNA N7-methylguanosine (m7G) is a crucial chemical modification of RNA molecules, whose principal duty is to maintain RNA function and protein translation. Studying and predicting RNA N7-methylguanosine sites aid in comprehending the biological function of RNA and the development of new drug therapy regimens. In the present scenario, the efficacy of techniques, specifically deep learning and machine learning, stands out in the prediction of RNA N7-methylguanosine sites, leading to improved accuracy and identification efficiency. In this study, we propose a model leveraging the transformer framework that integrates natural language processing and deep learning to predict m7G sites, called TMSC-m7G. In TMSC-m7G, a combination of multi-sense-scaled token embedding and fixed-position embedding is used to replace traditional word embedding for the extraction of contextual information from sequences. Moreover, a convolutional layer is added in the encoder to make up for the shortage of local information acquisition in transformer. The model's robustness and generalization are validated through 10-fold cross-validation and an independent dataset test. Results demonstrate outstanding performance in comparison to the most advanced models available. Among them, the Accuracy of TMSC-m7G reaches 98.70% and 92.92% on the benchmark dataset and independent dataset, respectively. To facilitate the popularization and use of the model, we have developed an intuitive online prediction tool, which is easily accessible for free at http://39.105.212.81/.

EACVP: An ESM-2 LM Framework Combined CNN and CBAM Attention to Predict Anti-coronavirus Peptides.

BACKGROUND: The novel coronavirus pneumonia (COVID-19) outbreak in late 2019 killed millions worldwide. Coronaviruses cause diseases such as severe acute respiratory syndrome (SARS-Cov) and SARS-COV-2. Many peptides in the host defense system have antiviral activity. How to establish a set of efficient models to identify anti-coronavirus peptides is a meaningful study. METHODS: Given this, a new prediction model EACVP is proposed. This model uses the evolutionary scale language model (ESM-2 LM) to characterize peptide sequence information. The ESM model is a natural language processing model trained by machine learning technology. It is trained on a highly diverse and dense dataset (UR50/D 2021_04) and uses the pre-trained language model to obtain peptide sequence features with 320 dimensions. Compared with traditional feature extraction methods, the information represented by ESM-2 LM is more comprehensive and stable. Then, the features are input into the convolutional neural network (CNN), and the convolutional block attention module (CBAM) lightweight attention module is used to perform attention operations on CNN in space dimension and channel dimension. To verify the rationality of the model structure, we performed ablation experiments on the benchmark and independent test datasets. We compared the EACVP with existing methods on the independent test dataset. RESULTS: Experimental results show that ACC, F1-score, and MCC are 3.95%, 35.65% and 0.0725 higher than the most advanced methods, respectively. At the same time, we tested EACVP on ENNAVIA-C and ENNAVIA-D data sets, and the results showed that EACVP has good migration and is a powerful tool for predicting anti-coronavirus peptides. CONCLUSION: The results prove that this model EACVP could fully characterize the peptide information and achieve high prediction accuracy. It can be generalized to different data sets. The data and code of the article have been uploaded to https://github.- com/JYY625/EACVP.git.

HemoFuse: multi-feature fusion based on multi-head cross-attention for identification of hemolytic peptides.

Hemolytic peptides are therapeutic peptides that damage red blood cells. However, therapeutic peptides used in medical treatment must exhibit low toxicity to red blood cells to achieve the desired therapeutic effect. Therefore, accurate prediction of the hemolytic activity of therapeutic peptides is essential for the development of peptide therapies. In this study, a multi-feature cross-fusion model, HemoFuse, for hemolytic peptide identification is proposed. The feature vectors of peptide sequences are transformed by word embedding technique and four hand-crafted feature extraction methods. We apply multi-head cross-attention mechanism to hemolytic peptide identification for the first time. It captures the interaction between word embedding features and hand-crafted features by calculating the attention of all positions in them, so that multiple features can be deeply fused. Moreover, we visualize the features obtained by this module to enhance its interpretability. On the comprehensive integrated dataset, HemoFuse achieves ideal results, with ACC, SP, SN, MCC, F1, AUC, and AP of 0.7575, 0.8814, 0.5793, 0.4909, 0.6620, 0.8387, and 0.7118, respectively. Compared with HemoDL proposed by Yang et al., it is 3.32%, 3.89%, 5.93%, 10.6%, 8.17%, 5.88%, and 2.72% higher. Other ablation experiments also prove that our model is reasonable and efficient. The codes and datasets are accessible at https://github.com/z11code/Hemo .

iACVP-MR: Accurate Identification of Anti-coronavirus Peptide based on Multiple Features Information and Recurrent Neural Network.

BACKGROUND: Over the years, viruses have caused human illness and threatened human health. Therefore, it is pressing to develop anti-coronavirus infection drugs with clear function, low cost, and high safety. Anti-coronavirus peptide (ACVP) is a key therapeutic agent against coronavirus. Traditional methods for finding ACVP need a great deal of money and man power. Hence, it is a significant task to establish intelligent computational tools to able rapid, efficient and accurate identification of ACVP. METHODS: In this paper, we construct an excellent model named iACVP-MR to identify ACVP based on multiple features and recurrent neural networks. Multiple features are extracted by using reduced amino acid component and dipeptide component, compositions of k-spaced amino acid pairs, BLOSUM62 encoder according to the N5C5 sequence, as well as second-order moving average approach based on 16 physicochemical properties. Then, two recurrent neural networks named long-short term memory (LSTM) and bidirectional gated recurrent unit (BiGRU) combined attention mechanism are used for feature fusion and classification, respectively. RESULTS: The accuracies of ENNAVIA-C and ENNAVIA-D datasets under the 10-fold cross-validation are 99.15% and 98.92%, respectively, and other evaluation indexes have also obtained satisfactory results. The experimental results show that our model is superior to other existing models. CONCLUSION: The iACVP-MR model can be viewed as a powerful and intelligent tool for the accurate identification of ACVP. The datasets and source codes for iACVP-MR are freely downloaded at https://github.com/yunyunliang88/iACVP-MR.

A deep learning model for anti-inflammatory peptides identification based on deep variational autoencoder and contrastive learning.

As a class of biologically active molecules with significant immunomodulatory and anti-inflammatory effects, anti-inflammatory peptides have important application value in the medical and biotechnology fields due to their unique biological functions. Research on the identification of anti-inflammatory peptides provides important theoretical foundations and practical value for a deeper understanding of the biological mechanisms of inflammation and immune regulation, as well as for the development of new drugs and biotechnological applications. Therefore, it is necessary to develop more advanced computational models for identifying anti-inflammatory peptides. In this study, we propose a deep learning model named DAC-AIPs based on variational autoencoder and contrastive learning for accurate identification of anti-inflammatory peptides. In the sequence encoding part, the incorporation of multi-hot encoding helps capture richer sequence information. The autoencoder, composed of convolutional layers and linear layers, can learn latent features and reconstruct features, with variational inference enhancing the representation capability of latent features. Additionally, the introduction of contrastive learning aims to improve the model's classification ability. Through cross-validation and independent dataset testing experiments, DAC-AIPs achieves superior performance compared to existing state-of-the-art models. In cross-validation, the classification accuracy of DAC-AIPs reached around 88%, which is 7% higher than previous models. Furthermore, various ablation experiments and interpretability experiments validate the effectiveness of DAC-AIPs. Finally, a user-friendly online predictor is designed to enhance the practicality of the model, and the server is freely accessible at http://dac-aips.online .

iAVPs-ResBi: Identifying antiviral peptides by using deep residual network and bidirectional gated recurrent unit.

Human history is also the history of the fight against viral diseases. From the eradication of viruses to coexistence, advances in biomedicine have led to a more objective understanding of viruses and a corresponding increase in the tools and methods to combat them. More recently, antiviral peptides (AVPs) have been discovered, which due to their superior advantages, have achieved great impact as antiviral drugs. Therefore, it is very necessary to develop a prediction model to accurately identify AVPs. In this paper, we develop the iAVPs-ResBi model using k-spaced amino acid pairs (KSAAP), encoding based on grouped weight (EBGW), enhanced grouped amino acid composition (EGAAC) based on the N5C5 sequence, composition, transition and distribution (CTD) based on physicochemical properties for multi-feature extraction. Then we adopt bidirectional long short-term memory (BiLSTM) to fuse features for obtaining the most differentiated information from multiple original feature sets. Finally, the deep model is built by combining improved residual network and bidirectional gated recurrent unit (BiGRU) to perform classification. The results obtained are better than those of the existing methods, and the accuracies are 95.07, 98.07, 94.29 and 97.50% on the four datasets, which show that iAVPs-ResBi can be used as an effective tool for the identification of antiviral peptides. The datasets and codes are freely available at https://github.com/yunyunliang88/iAVPs-ResBi.