SurfPro-NN: A 3D point cloud neural network for the scoring of protein-protein docking models based on surfaces features and protein language models.

Protein-protein interactions (PPI) play a crucial role in numerous key biological processes, and the structure of protein complexes provides valuable clues for in-depth exploration of molecular-level biological processes. Protein-protein docking technology is widely used to simulate the spatial structure of proteins. However, there are still challenges in selecting candidate decoys that closely resemble the native structure from protein-protein docking simulations. In this study, we introduce a docking evaluation method based on three-dimensional point cloud neural networks named SurfPro-NN, which represents protein structures as point clouds and learns interaction information from protein interfaces by applying a point cloud neural network. With the continuous advancement of deep learning in the field of biology, a series of knowledge-rich pre-trained models have emerged. We incorporate protein surface representation models and language models into our approach, greatly enhancing feature representation capabilities and achieving superior performance in protein docking model scoring tasks. Through comprehensive testing on public datasets, we find that our method outperforms state-of-the-art deep learning approaches in protein-protein docking model scoring. Not only does it significantly improve performance, but it also greatly accelerates training speed. This study demonstrates the potential of our approach in addressing protein interaction assessment problems, providing strong support for future research and applications in the field of biology.

Tpgen: a language model for stable protein design with a specific topology structure.

BACKGROUND: Natural proteins occupy a small portion of the protein sequence space, whereas artificial proteins can explore a wider range of possibilities within the sequence space. However, specific requirements may not be met when generating sequences blindly. Research indicates that small proteins have notable advantages, including high stability, accurate resolution prediction, and facile specificity modification. RESULTS: This study involves the construction of a neural network model named TopoProGenerator(TPGen) using a transformer decoder. The model is trained with sequences consisting of a maximum of 65 amino acids. The training process of TopoProGenerator incorporates reinforcement learning and adversarial learning, for fine-tuning. Additionally, it encompasses a stability predictive model trained with a dataset comprising over 200,000 sequences. The results demonstrate that TopoProGenerator is capable of designing stable small protein sequences with specified topology structures. CONCLUSION: TPGen has the ability to generate protein sequences that fold into the specified topology, and the pretraining and fine-tuning methods proposed in this study can serve as a framework for designing various types of proteins.

PointDE: Protein Docking Evaluation Using 3D Point Cloud Neural Network.

Protein-protein interactions (PPIs) play essential roles in many vital movements and the determination of protein complex structure is helpful to discover the mechanism of PPI. Protein-protein docking is being developed to model the structure of the protein. However, there is still a challenge to selecting the near-native decoys generated by protein-protein docking. Here, we propose a docking evaluation method using 3D point cloud neural network named PointDE. PointDE transforms protein structure to the point cloud. Using the state-of-the-art point cloud network architecture and a novel grouping mechanism, PointDE can capture the geometries of the point cloud and learn the interaction information from the protein interface. On public datasets, PointDE surpasses the state-of-the-art method using deep learning. To further explore the ability of our method in different types of protein structures, we developed a new dataset generated by high-quality antibody-antigen complexes. The result in this antibody-antigen dataset shows the strong performance of PointDE, which will be helpful for the understanding of PPI mechanisms.

Empirical validation of ProteinMPNN's efficiency in enhancing protein fitness.

Introduction: Protein engineering, which aims to improve the properties and functions of proteins, holds great research significance and application value. However, current models that predict the effects of amino acid substitutions often perform poorly when evaluated for precision. Recent research has shown that ProteinMPNN, a large-scale pre-training sequence design model based on protein structure, performs exceptionally well. It is capable of designing mutants with structures similar to the original protein. When applied to the field of protein engineering, the diverse designs for mutation positions generated by this model can be viewed as a more precise mutation range. Methods: We collected three biological experimental datasets and compared the design results of ProteinMPNN for wild-type proteins with the experimental datasets to verify the ability of ProteinMPNN in improving protein fitness. Results: The validation on biological experimental datasets shows that ProteinMPNN has the ability to design mutation types with higher fitness in single and multi-point mutations. We have verified the high accuracy of ProteinMPNN in protein engineering tasks from both positive and negative perspectives. Discussion: Our research indicates that using large-scale pre trained models to design protein mutants provides a new approach for protein engineering, providing strong support for guiding biological experiments and applications in biotechnology.

De novo generation of dual-target ligands using adversarial training and reinforcement learning.

Artificial intelligence, such as deep generative methods, represents a promising solution to de novo design of molecules with the desired properties. However, generating new molecules with biological activities toward two specific targets remains an extremely difficult challenge. In this work, we conceive a novel computational framework, herein called dual-target ligand generative network (DLGN), for the de novo generation of bioactive molecules toward two given objectives. Via adversarial training and reinforcement learning, DLGN treats a sequence-based simplified molecular input line entry system (SMILES) generator as a stochastic policy for exploring chemical spaces. Two discriminators are then used to encourage the generation of molecules that belong to the intersection of two bioactive-compound distributions. In a case study, we employ our methods to design a library of dual-target ligands targeting dopamine receptor D2 and 5-hydroxytryptamine receptor 1A as new antipsychotics. Experimental results demonstrate that the proposed model can generate novel compounds with high similarity to both bioactive datasets in several structure-based metrics. Our model exhibits a performance comparable to that of various state-of-the-art multi-objective molecule generation models. We envision that this framework will become a generally applicable approach for designing dual-target drugs in silico.

Sequence-Based Deep Learning Frameworks on Enhancer-Promoter Interactions Prediction.

Enhancer-promoter interactions (EPIs) in the human genome are of great significance to transcriptional regulation, which tightly controls gene expression. Identification of EPIs can help us better decipher gene regulation and understand disease mechanisms. However, experimental methods to identify EPIs are constrained by funds, time, and manpower, while computational methods using DNA sequences and genomic features are viable alternatives. Deep learning methods have shown promising prospects in classification and efforts that have been utilized to identify EPIs. In this survey, we specifically focus on sequence-based deep learning methods and conduct a comprehensive review of the literature. First, we briefly introduce existing sequence- based frameworks on EPIs prediction and their technique details. After that, we elaborate on the dataset, pre-processing means, and evaluation strategies. Finally, we concluded with the challenges these methods are confronted with and suggest several future opportunities. We hope this review will provide a useful reference for further studies on enhancer-promoter interactions.

Predicting enhancer-promoter interactions by deep learning and matching heuristic.

Enhancer-promoter interactions (EPIs) play an important role in transcriptional regulation. Recently, machine learning-based methods have been widely used in the genome-scale identification of EPIs due to their promising predictive performance. In this paper, we propose a novel method, termed EPI-DLMH, for predicting EPIs with the use of DNA sequences only. EPI-DLMH consists of three major steps. First, a two-layer convolutional neural network is used to learn local features, and an bidirectional gated recurrent unit network is used to capture long-range dependencies on the sequences of promoters and enhancers. Second, an attention mechanism is used for focusing on relatively important features. Finally, a matching heuristic mechanism is introduced for the exploration of the interaction between enhancers and promoters. We use benchmark datasets in evaluating and comparing the proposed method with existing methods. Comparative results show that our model is superior to currently existing models in multiple cell lines. Specifically, we found that the matching heuristic mechanism introduced into the proposed model mainly contributes to the improvement of performance in terms of overall accuracy. Additionally, compared with existing models, our model is more efficient with regard to computational speed.

Comprehensive Review and Comparison for Anticancer Peptides Identification Models.

Anticancer peptides (ACPs) eliminate pathogenic bacteria and kill tumor cells, showing no hemolysis and no damages to normal human cells. This unique ability explores the possibility of ACPs as therapeutic delivery and its potential applications in clinical therapy. Identifying ACPs is one of the most fundamental and central problems in new antitumor drug research. During the past decades, a number of machine learning-based prediction tools have been developed to solve this important task. However, the predictions produced by various tools are difficult to quantify and compare. Therefore, in this article, we provide a comprehensive review of existing machine learning methods for ACPs prediction and fair comparison of the predictors. To evaluate current prediction tools, we conducted a comparative study and analyzed the existing ACPs predictor from 10 public literatures. The comparative results obtained suggest that Support Vector Machine-based model with features combination provided significant improvement in the overall performance, when compared to the other machine learning method-based prediction models.

Deep Collaborative Filtering for Prediction of Disease Genes.

Accurate prioritization of potential disease genes is a fundamental challenge in biomedical research. Various algorithms have been developed to solve such problems. Inductive Matrix Completion (IMC) is one of the most reliable models for its well-established framework and its superior performance in predicting gene-disease associations. However, the IMC method does not hierarchically extract deep features, which might limit the quality of recovery. In this case, the architecture of deep learning, which obtains high-level representations and handles noises and outliers presented in large-scale biological datasets, is introduced into the side information of genes in our Deep Collaborative Filtering (DCF) model. Further, for lack of negative examples, we also exploit Positive-Unlabeled (PU) learning formulation to low-rank matrix completion. Our approach achieves substantially improved performance over other state-of-the-art methods on diseases from the Online Mendelian Inheritance in Man (OMIM) database. Our approach is 10 percent more efficient than standard IMC in detecting a true association, and significantly outperforms other alternatives in terms of the precision-recall metric at the top-k predictions. Moreover, we also validate the disease with no previously known gene associations and newly reported OMIM associations. The experimental results show that DCF is still satisfactory for ranking novel disease phenotypes as well as mining unexplored relationships. The source code and the data are available at https://github.com/xzenglab/DCF.

An efficient isothermal PCR method for on-site detection of nucleic acid.

Convective PCR (CPCR) is an isothermal nucleic acid amplification technology; however, natural convection exhibits a chaotic and multiplex flow state, resulting in low amplification efficiency and specificity. We placed a polycarbonate strip (p-strip) inside reaction tubes to induce circumfluence by blocking the inner ring that originally allowed fluid to flow at suboptimal temperatures. Moreover, we constructed a dual-temperature instrument to provide appropriate denaturing and annealing zones for CPCR. Tubes containing p-strips exhibited significantly improved efficiency, sensitivity and specificity. For real-time detection, the variation coefficients of three replicates having the same concentrations were less than 2% in more than half of the cases, indicating improved CPCR amplification and potential as a commercial on-site nucleic acid diagnosis tool.

[PSO+: nonlinear fitting fluorescence data based on particle swarm optimizing combine with other iteration algorithm].

The convective polymerase chain reaction (CCPCR) uses the principle of thermal convection to allow the reagent to flow in the test tube and achieve the purpose of amplification by the temperature difference between the upper and lower portions of the test tube. In order to detect the amplification effect in real time, we added a fluorophore to the reagent system to reflect the amplification in real time through the intensity of fluorescence. The experimental results show that the fluorescence curve conforms to the S-type trend of the amplification curve, but there is a certain jitter condition due to the instability of the thermal convection, which is not conducive to the calculation of the cycle threshold (CT value). In order to solve this problem, this paper uses the dynamic method, using the double S-type function model to fit the curve, so that the fluorescence curve is smooth and the initial concentration of the nucleic acid can be deduced better to achieve the quantitative purpose based on the curve. At the same time, the PSO+ algorithm is used to solve the double s-type function parameters, that is, particle swarm optimization (PSO) algorithm combined with Levenberg-Marquardt, Newton-CG and other algorithms for curve fitting. The proposed method effectively overcoms PSO randomness and the shortcoming of traditional algorithms such as Levenberg-Marquardt and Newton-CG which are easy to fall into the local optimal solution. The R 2 of the data fitting result can reach 0.999 8. This study is of guiding significance for the future quantitative detection of real-time fluorescent heat convection amplification.

A point of care platform based on microfluidic chip for nucleic acid extraction in less than 1 minute.

In view of the complex procedure of nucleic acid extraction, there exists a huge challenge for the widespread use of point-of-care diagnostics for nucleic acid testing. To achieve point-of-care applications in a more rapid and cost-efficient manner, we designed a snake pipe-shaped microfluidic chip so as to accomplish reagents-prestored, time-saving, operation-simple nucleic acid extraction. All reagents needed for this process, including lysis buffer, wash buffer, elution buffer, and so on, were preloaded in the snake pipe and securely isolated by membrane valves, without the need for using any specialized equipment. By an integrated chip and a powerful ultrasonic, this device could complete virus nucleic acid extraction from sophisticated serum samples in less than 1 min. We used hepatitis B virus (HBV) and human immunodeficiency virus (HIV) mixed with different sources of serum as samples to be extracted. The coefficient of variation of HBV and HIV extraction on-chip was 1.32% and 2.74%, respectively, and there were no significant differences between on-chip and commercial instrument extraction (P > 0.05, α = 0.05) in different dilution ratios, which showed that the extraction device we established had excellent stability and sensitivity.

An automated microfluidic chemiluminescence immunoassay platform for quantitative detection of biomarkers.

A rapid, sensitive and quantitative biomarker detection platform is of great importance to the small clinic or point-of-care (POC) diagnosis. In this work, we realize that an automated diagnostic platform mainly includes two components: (1) an instrument that can complete all steps of the chemiluminescence immunoassay automatically and (2) an integrated microfluidic chip which is disposable and harmless. In the instrument, we adopt vacuum suction cups which are driven by linear motor to realize a simple, effective and convenient control. The method of acridine esterification chemiluminescence is adopted to achieve a quantitative detection, and a photomultiplier tube is used to detect photons from acridine ester producing in alkaline conditions. We use the laser cutting machine and hot press machine to accomplish the product of microfluidic chips. The automated microfluidics-based system is demonstrated by implementation of a chemiluminescence immunoassay for quantitative detection of ferritin. We observe alinear relationship between CL intensity and the concentration of ferritin from 5.1 to 1300 ng mL -1and the limit of detection (LoD) is 2.55 ng mL -1. At the same time, we also used the automated microfluidics-based system to test clinical serum samples. The whole process of chemiluminescence experiment can complete within 45 min. We realize that this lab-on-a-chip chemiluminescence immunoassay platform with features of automation and quantitation provides a promising strategy for POC diagnosis.

Prediction of Drug-Gene Interaction by Using Metapath2vec.

Heterogeneous information networks (HINs) currently play an important role in daily life. HINs are applied in many fields, such as science research, e-commerce, recommendation systems, and bioinformatics. Particularly, HINs have been used in biomedical research. Algorithms have been proposed to calculate the correlations between drugs and targets and between diseases and genes. Recently, the interaction between drugs and human genes has become an important subject in the research on drug efficacy and human genomics. In previous studies, numerous prediction methods using machine learning and statistical prediction models were proposed to explore this interaction on the biological network. In the current work, we introduce a representation learning method into the biological heterogeneous network and use the representation learning models metapath2vec and metapath2vec++ on our dataset. We combine the adverse drug reaction (ADR) data in the drug-gene network with causal relationship between drugs and ADRs. This article first presents an analysis of the importance of predicting drug-gene relationships and discusses the existing prediction methods. Second, the skip-gram model commonly used in representation learning for natural language processing tasks is explained. Third, the metapath2vec and metapath2vec++ models for the example of drug-gene-ADR network are described. Next, the kernelized Bayesian matrix factorization algorithm is used to complete the prediction. Finally, the experimental results of both models are compared with Katz, CATAPULT, and matrix factorization, the prediction visualized using the receiver operating characteristic curves are presented, and the area under the receiver operating characteristic values for three varying algorithm parameters are calculated.

Using MOEA with Redistribution and Consensus Branches to Infer Phylogenies.

In recent years, to infer phylogenies, which are NP-hard problems, more and more research has focused on using metaheuristics. Maximum Parsimony and Maximum Likelihood are two effective ways to conduct inference. Based on these methods, which can also be considered as the optimal criteria for phylogenies, various kinds of multi-objective metaheuristics have been used to reconstruct phylogenies. However, combining these two time-consuming methods results in those multi-objective metaheuristics being slower than a single objective. Therefore, we propose a novel, multi-objective optimization algorithm, MOEA-RC, to accelerate the processes of rebuilding phylogenies using structural information of elites in current populations. We compare MOEA-RC with two representative multi-objective algorithms, MOEA/D and NAGA-II, and a non-consensus version of MOEA-RC on three real-world datasets. The result is, within a given number of iterations, MOEA-RC achieves better solutions than the other algorithms.

Predict the Relationship between Gene and Large Yellow Croaker's Economic Traits.

The importance of a gene's impact on traits is well appreciated. Gene expression will affect the growth, immunity, reproduction and environmental resistance of some fish, and then affect the economic performance of fish-related business. Studying the connection between gene and character can help elucidate the growth of fishes. Thus far, a collected database containing large yellow croaker (Larimichthys crocea) genes does not exist. The gene having to do with the growth efficiency of fish will have a huge impact on research. For example, the protein encoded by the IFIH1 gene is associated with the function of viral infection in the immune system, which affects the survival rate of large yellow croakers. Thus, we collected data through the published literature and combined them with a biological genetic database related to the large yellow croaker. Based on the data, we can predict new gene-trait associations which have not yet been discovered. This work will contribute to research on the growth of large yellow croakers.

A Smartphone-Based Genotyping Method for Hepatitis B Virus at Point-of-Care Settings.

We reported a rapid, convenient, and easy-to-use genotyping method for hepatitis B virus (HBV) based on the smartphone at point-of-care (POC) settings. To perform HBV genotyping especially for genotypes A, B, C, and D, a smartphone is used to image and analyze a one-step immunoassay lateral flow strip functionalized with genotype-specific monoclonal antibodies (mAbs) on multiple capture lines. A light-emitting diode (LED) positioned on the top of the lateral flow strip is used to shine the multiple capture lines for excitation. Fluorescence detection is obtained with a smartphone whose camera is used to take the fluorescent images. An intelligent algorithm is developed to first identify each capture line from the fluorescent image and then determine the HBV genotype based on a genotyping model. Based on the pattern of the detection signal from different samples, a custom HBV genotyping model is developed. Custom application software running on a smartphone is developed with Java to collect and analyze the fluorescent image, display the genotyping result, and transmit it if necessary. Compared with the existing methods with nucleic acid analysis, more convenient, instant, and efficient HBV genotyping with significantly lower cost and a simpler procedure can be obtained with the developed smartphone POC HBV genotyping method.

WITHDRAWN: Benchmarking swarm intelligence clustering algorithms with case study of medical data.

This article has been withdrawn at the request of the author(s) and/or editor. The Publisher apologizes for any inconvenience this may cause. The full Elsevier Policy on Article Withdrawal can be found at http://www.elsevier.com/locate/withdrawalpolicy.

A fast and low-cost genotyping method for hepatitis B virus based on pattern recognition in point-of-care settings.

A fast and low-cost method for HBV genotyping especially for genotypes A, B, C and D was developed and tested. A classifier was used to detect and analyze a one-step immunoassay lateral flow strip functionalized with genotype-specific monoclonal antibodies (mAbs) on multiple capture lines in the form of pattern recognition for point-of-care (POC) diagnostics. The fluorescent signals from the capture lines and the background of the strip were collected via multiple optical channels in parallel. A digital HBV genotyping model, whose inputs are the fluorescent signals and outputs are a group of genotype-specific digital binary codes (0/1), was developed based on the HBV genotyping strategy. Meanwhile, a companion decoding table was established to cover all possible pairing cases between the states of a group of genotype-specific digital binary codes and the HBV genotyping results. A logical analyzing module was constructed to process the detected signals in parallel without program control, and its outputs were used to drive a set of LED indicators, which determine the HBV genotype. Comparing to the nucleic acid analysis to HBV viruses, much faster HBV genotyping with significantly lower cost can be obtained with the developed method.

Rapid fluorescent lateral-flow immunoassay for hepatitis B virus genotyping.

Hepatitis B virus (HBV) genotyping plays an important role in the clinical management of chronic hepatitis B (CHB) patients. However, the current nucleic acid based techniques are expensive, time-consuming, and inconvenient. Here, we developed a novel DNA-independent HBV genotyping tool based on a one-step fluorescent lateral flow immunoassay (LFIA). Epitope-targeting immunization and screening techniques were used to develop HBV genotype specific monoclonal antibodies (mAbs). These mAbs were used to develop a multitest LFIA with a matched scanning luminoscope for HBV genotyping (named the GT-LFIA). The performance of this novel assay was carefully evaluated in well-characterized clinical cohorts. The GT-LFIA, which can specifically differentiate HBV genotypes A, B, C, and D in a pretreatment-free single test, was successfully developed using four genotype specific mAbs. The detection limits of the GT-LFIA for HBV genotypes A, B, C, and D were 2.5-10.0 IU HBV surface antigen/mL, respectively. Among the sera from 456 CHB patients, 439 (96.3%; 95% confidence interval (CI), 94.1-97.8%) were genotype-differentiable by the GT-LFIA and 437 (99.5%; 95% CI, 98.4-99.9%) were consistent with viral genome sequencing. In the 21 patients receiving nucleos(t)ide analogue therapy, for end-of-treatment specimens that were HBV DNA undetectable and were not applicable for DNA-dependent genotyping, the GT-LFIA presented genotyping results that were consistent with those obtained in pretreatment specimens by viral genome sequencing and the GT-LFIA. In conclusion, the novel GT-LFIA is a convenient, fast, and reliable tool for differential HBV genotyping, especially in patients with low or undetectable HBV DNA levels.