A new era of mutation rate analyses: Concepts and methods

The mutation rate is a pivotal biological characteristic,intricately governed by natural selection and historically garnering considerable attention.Recent advances in high-throughput sequencing and analytical methodologies have profoundly transformed our understanding in this domain,ushering in an unprecedented era of mutation rate research.This paper aims to provide a comprehensive overview of the key concepts and methodologies frequently employed in the study of mutation rates.It examines various types of mutations,explores the evolutionary dynamics and associated theories,and synthesizes both classical and contemporary hypotheses.Furthermore,this review comprehensively explores recent advances in understanding germline and somatic mutations in animals and offers an overview of experimental methodologies,mutational patterns,molecular mechanisms,and driving forces influencing variations in mutation rates across species and tissues.Finally,it proposes several potential research directions and pressing questions for future investigations.

A semi-analytical model for coupled flow in stress-sensitive multi-scale shale reservoirs with fractal characteristics

A large number of nanopores and complex fracture structures in shale reservoirs results in multi-scale flow of oil. With the development of shale oil reservoirs, the permeability of multi-scale media undergoes changes due to stress sensitivity, which plays a crucial role in controlling pressure propagation and oil flow. This paper proposes a multi-scale coupled flow mathematical model of matrix nanopores, induced fractures, and hydraulic fractures. In this model, the micro-scale effects of shale oil flow in fractal nanopores, fractal induced fracture network, and stress sensitivity of multi-scale media are considered. We solved the model iteratively using Pedrosa transform, semi-analytic Segmented Bessel function, Laplace transform. The results of this model exhibit good agreement with the numerical solution and field production data, confirming the high accuracy of the model. As well, the influence of stress sensitivity on permeability, pressure and production is analyzed. It is shown that the permeability and production decrease significantly when induced fractures are weakly supported. Closed induced fractures can inhibit interporosity flow in the stimulated reservoir volume (SRV). It has been shown in sensitivity analysis that hydraulic fractures are beneficial to early production, and induced fractures in SRV are beneficial to middle production. The model can characterize multi-scale flow characteristics of shale oil, providing theoretical guidance for rapid productivity evaluation.

A rare missense PAX6 mutation causes atypical aniridia in a three-generation Chinese family

●AIM:To investigate the molecular diagnosis of a threegeneration Chinese family affected with aniridia,and further to identify clinically a PAX6 missense mutation in members with atypical aniridia.●METHODS:Eleven family members with and without atypical aniridia were recruited.All family members underwent comprehensive ophthalmic examinations.A combination of whole exome sequencing(WES)and direct Sanger sequencing were performed to uncover the causative mutation.●RESULTS:Among the 11 family members,8 were clinically diagnosed with congenital aniridia(atypical aniridia phenotype).A rare heterozygous mutation c.622C>T(p.Arg208Trp)in exon 8 of PAX6 was identified in all affected family members but not in the unaffected members or in healthy control subjects.●CONCLUSION:A rare missense mutation in the PAX6 gene is found in members of a three-generation Chinese family with congenital atypical aniridia.This result contributes to an increase in the phenotypic spectrum caused by PAX6 missense heterozygous variants and provides useful information for the clinical diagnosis of atypical aniridia,which may also contribute to genetic counselling and family planning.

Multi-scale physics-informed neural networks for solving high Reynolds number boundary layer flows based on matched asymptotic expansions

Multi-scale system remains a classical scientific problem in fluid dynamics,biology,etc.In the present study,a scheme of multi-scale Physics-informed neural networks is proposed to solve the boundary layer flow at high Reynolds numbers without any data.The flow is divided into several regions with different scales based on Prandtl's boundary theory.Different regions are solved with governing equations in different scales.The method of matched asymptotic expansions is used to make the flow field continuously.A flow on a semi infinite flat plate at a high Reynolds number is considered a multi-scale problem because the boundary layer scale is much smaller than the outer flow scale.The results are compared with the reference numerical solutions,which show that the msPINNs can solve the multi-scale problem of the boundary layer in high Reynolds number flows.This scheme can be developed for more multi-scale problems in the future.

Mutation in the Agrobacterium his I gene enhances transient expression in pepper

Agrobacterium-mediated plant transformation is widely used in plant genetic engineering.However,its efficiency is limited by plant immunity against Agrobacterium.Chili pepper(Capsicum annuum L.)is an important vegetable that is recalcitrant to Agrobacterium-mediated transformation.In this work,Agrobacterium was found to induce a strong immune response in pepper,which might be the reason for T-DNA being difficult to express in pepper.An Agrobacterium mutant screen was conducted and a point mutation in the hisI gene was identified due to a weak immune response and enhanced transient expression mediated by this Agrobacterium mutant in pepper leaves.Further genetic analysis revealed that histidine biosynthesis deficiency caused by mutations in many genes of this pathway led to reduced pepper cell death,presumably due to reduced bacterial growth.However,mutation analysis of threonine and tryptophan biosynthesis genes showed that the biosynthesis of different amino acids may play different roles in Agrobacterium growth and stimulating the pepper immune response.The possible application of Agrobacterium amino acid biosynthesis mutations in plant biology was discussed.

C634Y mutation in RET-induced multiple endocrine neoplasia type 2A:A case report

BACKGROUND Multiple endocrine neoplasia type 2(MEN2)is a rare,autosomal dominant endocrine disease.Currently,the RET proto-oncogene is the only gene implicated in MEN2A pathogenesis.Once an RET carrier is detected,family members should be screened to enable early detection of medullary thyroid carcinoma,pheochromocytoma,and hyperparatitity.Among these,medullary thyroid carcinoma is the main factor responsible for patient mortality.Accordingly,delineating strategies to inform clinical follow-up and treatment plans based on genes is paramount for clinical practitioners.CASE SUMMARY Herein,we present RET proto-oncogene mutations,clinical characteristics,and treatment strategies in a family with MEN2A.A family study was conducted on patients diagnosed with MEN2A.DNA was extracted from the peripheral blood of family members,and first-generation exon sequencing of the RET protooncogene was conducted.The C634Y mutation was identified in three family members spanning three generations.Two patients were sequentially diagnosed with pheochromocytomas and bilateral medullary thyroid carcinomas.A 9-yearold child harboring the gene mutation was diagnosed with medullary thyroid carcinoma.Surgical resection of the tumors was performed.All family members were advised to undergo complete genetic testing related to the C634Y mutation,and the corresponding treatments administered based on test results and associated clinical guidelines.CONCLUSION Advancements in MEN2A research are important for familial management,assessment of medullary thyroid cancer invasive risk,and deciding surgical timing.

Prevalence, risk factors, and BRAF mutation of colorectal sessile serrated lesions among Vietnamese patients

BACKGROUND Sessile serrated lesions(SSLs)are considered precancerous colorectal lesions that should be detected and removed to prevent colorectal cancer.Previous studies in Vietnam mainly investigated the adenoma pathway,with limited data on the serrated pathway.AIM To evaluate the prevalence,risk factors,and BRAF mutations of SSLs in the Vietnamese population.METHODS This is a cross-sectional study conducted on patients with lower gastrointestinal symptoms who underwent colonoscopy at a tertiary hospital in Vietnam.SSLs were diagnosed on histopathology according to the 2019 World Health Organi-zation classification.BRAF mutation analysis was performed using the Sanger DNA sequencing method.The multivariate logistic regression model was used to determine SSL-associated factors.RESULTS There were 2489 patients,with a mean age of 52.1±13.1 and a female-to-male ratio of 1:1.1.The prevalence of SSLs was 4.2%[95%confidence interval(CI):3.5-5.1].In the multivariate analysis,factors significantly associated with SSLs were age≥40[odds ratio(OR):3.303;95%CI:1.607-6.790],male sex(OR:2.032;95%CI:1.204-3.429),diabetes mellitus(OR:2.721;95%CI:1.551-4.772),and hypertension(OR:1.650,95%CI:1.045-2.605).The rate of BRAF mutations in SSLs was 35.5%.CONCLUSION The prevalence of SSLs was 4.2%.BRAF mutations were present in one-third of SSLs.Significant risk factors for SSLs included age≥40,male sex,diabetes mellitus,and hypertension.

Ferroptosis biomarkers predict tumor mutation burden's impact on prognosis in HER2-positive breast cancer

BACKGROUND Ferroptosis has recently been associated with multiple degenerative diseases.Ferroptosis induction in cancer cells is a feasible method for treating neoplastic diseases.However,the association of iron proliferation-related genes with prognosis in HER2+breast cancer(BC)patients is unclear.AIM To identify and evaluate fresh ferroptosis-related biomarkers for HER2+BC.METHODS First,we obtained the mRNA expression profiles and clinical information of HER2+BC patients from the TCGA and METABRIC public databases.A four gene prediction model comprising PROM2,SLC7A11,FANCD2,and FH was subsequently developed in the TCGA cohort and confirmed in the METABRIC cohort.Patients were stratified into high-risk and low-risk groups based on their median risk score,an independent predictor of overall survival(OS).Based on these findings,immune infiltration,mutations,and medication sensitivity were analyzed in various risk groupings.Additionally,we assessed patient prognosis by combining the tumor mutation burden(TMB)with risk score.Finally,we evaluated the expression of critical genes by analyzing single-cell RNA sequencing(scRNA-seq)data from malignant vs normal epithelial cells.RESULTS We found that the higher the risk score was,the worse the prognosis was(P<0.05).We also found that the immune cell infiltration,mutation,and drug sensitivity were different between the different risk groups.The highrisk subgroup was associated with lower immune scores and high TMB.Moreover,we found that the combination of the TMB and risk score could stratify patients into three groups with distinct prognoses.HRisk-HTMB patients had the worst prognosis,whereas LRisk-LTMB patients had the best prognosis(P<0.0001).Analysis of the scRNAseq data showed that PROM2,SLC7A11,and FANCD2 were significantly differentially expressed,whereas FH was not,suggesting that these genes are expressed mainly in cancer epithelial cells(P<0.01).CONCLUSION Our model helps guide the prognosis of HER2+breast cancer patients,and its combination with the TMB can aid in more accurate assessment of patient prognosis and provide new ideas for further diagnosis and treatment.

Ovarian Tumors in Senegalese Women: Impact of D-Loop Mutations between Healthy and Cancerous Tissues

In Senegal in particular, ovarian cancer, which is one of the most common gynecological cancers, accounts for 2.8% of deaths. The most important risk factor is genetic, with 10% of cases occurring in a context of genetic predisposition. The sequencing of the human genome, which has led to the discovery of millions of sequence variations, makes it possible to study variations within sequences. These variations are limited to Single Nucleotide Polymorphisms (SNPs) and this common form of polymorphism occurs approximately every 1000 bases in the human genome and 1.8 million SNPs are currently listed according to [1]. The aim of this study is to gain a better understanding of the impact of mutations in the D-loop region of mtDNA on ovarian cancer in Senegalese women. This study involved searching for mutations in our study population after DNA extraction and sequencing. Mutations were found after a comparison of our sequences with the Cambridge reference sequence (NC_012920). The mutations found in the DNA studied extend from position 7 to position 16568 and most of these mutations are located in the hypervariate zones (HV1 and HV2). Heteroplasmy with three mutant alleles was also found in certain variants. Common mutations were found in both healthy and cancerous tissues, with almost identical frequencies in both types of tissue. This enabled us to understand the spread of tumor cells throughout the ovary.

Appropriate Combination of Crossover Operator and Mutation Operator in Genetic Algorithms for the Travelling Salesman Problem

Genetic algorithms(GAs)are very good metaheuristic algorithms that are suitable for solving NP-hard combinatorial optimization problems.AsimpleGAbeginswith a set of solutions represented by a population of chromosomes and then uses the idea of survival of the fittest in the selection process to select some fitter chromosomes.It uses a crossover operator to create better offspring chromosomes and thus,converges the population.Also,it uses a mutation operator to explore the unexplored areas by the crossover operator,and thus,diversifies the GA search space.A combination of crossover and mutation operators makes the GA search strong enough to reach the optimal solution.However,appropriate selection and combination of crossover operator and mutation operator can lead to a very good GA for solving an optimization problem.In this present paper,we aim to study the benchmark traveling salesman problem(TSP).We developed several genetic algorithms using seven crossover operators and six mutation operators for the TSP and then compared them to some benchmark TSPLIB instances.The experimental studies show the effectiveness of the combination of a comprehensive sequential constructive crossover operator and insertion mutation operator for the problem.The GA using the comprehensive sequential constructive crossover with insertion mutation could find average solutions whose average percentage of excesses from the best-known solutions are between 0.22 and 14.94 for our experimented problem instances.

MSD-Net: Pneumonia Classification Model Based on Multi-Scale Directional Feature Enhancement

Computer-aided diagnosis of pneumonia based on deep learning is a research hotspot.However,there are some problems that the features of different sizes and different directions are not sufficient when extracting the features in lung X-ray images.A pneumonia classification model based on multi-scale directional feature enhancement MSD-Net is proposed in this paper.The main innovations are as follows:Firstly,the Multi-scale Residual Feature Extraction Module(MRFEM)is designed to effectively extract multi-scale features.The MRFEM uses dilated convolutions with different expansion rates to increase the receptive field and extract multi-scale features effectively.Secondly,the Multi-scale Directional Feature Perception Module(MDFPM)is designed,which uses a three-branch structure of different sizes convolution to transmit direction feature layer by layer,and focuses on the target region to enhance the feature information.Thirdly,the Axial Compression Former Module(ACFM)is designed to perform global calculations to enhance the perception ability of global features in different directions.To verify the effectiveness of the MSD-Net,comparative experiments and ablation experiments are carried out.In the COVID-19 RADIOGRAPHY DATABASE,the Accuracy,Recall,Precision,F1 Score,and Specificity of MSD-Net are 97.76%,95.57%,95.52%,95.52%,and 98.51%,respectively.In the chest X-ray dataset,the Accuracy,Recall,Precision,F1 Score and Specificity of MSD-Net are 97.78%,95.22%,96.49%,95.58%,and 98.11%,respectively.This model improves the accuracy of lung image recognition effectively and provides an important clinical reference to pneumonia Computer-Aided Diagnosis.

Multi-scale context-aware network for continuous sign language recognition

The hands and face are the most important parts for expressing sign language morphemes in sign language videos.However,we find that existing Continuous Sign Language Recognition(CSLR)methods lack the mining of hand and face information in visual backbones or use expensive and time-consuming external extractors to explore this information.In addition,the signs have different lengths,whereas previous CSLR methods typically use a fixed-length window to segment the video to capture sequential features and then perform global temporal modeling,which disturbs the perception of complete signs.In this study,we propose a Multi-Scale Context-Aware network(MSCA-Net)to solve the aforementioned problems.Our MSCA-Net contains two main modules:(1)Multi-Scale Motion Attention(MSMA),which uses the differences among frames to perceive information of the hands and face in multiple spatial scales,replacing the heavy feature extractors;and(2)Multi-Scale Temporal Modeling(MSTM),which explores crucial temporal information in the sign language video from different temporal scales.We conduct extensive experiments using three widely used sign language datasets,i.e.,RWTH-PHOENIX-Weather-2014,RWTH-PHOENIX-Weather-2014T,and CSL-Daily.The proposed MSCA-Net achieve state-of-the-art performance,demonstrating the effectiveness of our approach.

YOLO-MFD:Remote Sensing Image Object Detection with Multi-Scale Fusion Dynamic Head

Remote sensing imagery,due to its high altitude,presents inherent challenges characterized by multiple scales,limited target areas,and intricate backgrounds.These inherent traits often lead to increased miss and false detection rates when applying object recognition algorithms tailored for remote sensing imagery.Additionally,these complexities contribute to inaccuracies in target localization and hinder precise target categorization.This paper addresses these challenges by proposing a solution:The YOLO-MFD model(YOLO-MFD:Remote Sensing Image Object Detection withMulti-scale Fusion Dynamic Head).Before presenting our method,we delve into the prevalent issues faced in remote sensing imagery analysis.Specifically,we emphasize the struggles of existing object recognition algorithms in comprehensively capturing critical image features amidst varying scales and complex backgrounds.To resolve these issues,we introduce a novel approach.First,we propose the implementation of a lightweight multi-scale module called CEF.This module significantly improves the model’s ability to comprehensively capture important image features by merging multi-scale feature information.It effectively addresses the issues of missed detection and mistaken alarms that are common in remote sensing imagery.Second,an additional layer of small target detection heads is added,and a residual link is established with the higher-level feature extraction module in the backbone section.This allows the model to incorporate shallower information,significantly improving the accuracy of target localization in remotely sensed images.Finally,a dynamic head attentionmechanism is introduced.This allows themodel to exhibit greater flexibility and accuracy in recognizing shapes and targets of different sizes.Consequently,the precision of object detection is significantly improved.The trial results show that the YOLO-MFD model shows improvements of 6.3%,3.5%,and 2.5%over the original YOLOv8 model in Precision,map@0.5 and map@0.5:0.95,separately.These results illustrate the clear advantages of the method.

Transfer learning framework for multi-scale crack type classification with sparse microseismic networks

Rock fracture mechanisms can be inferred from moment tensors(MT)inverted from microseismic events.However,MT can only be inverted for events whose waveforms are acquired across a network of sensors.This is limiting for underground mines where the microseismic stations often lack azimuthal coverage.Thus,there is a need for a method to invert fracture mechanisms using waveforms acquired by a sparse microseismic network.Here,we present a novel,multi-scale framework to classify whether a rock crack contracts or dilates based on a single waveform.The framework consists of a deep learning model that is initially trained on 2400000+manually labelled field-scale seismic and microseismic waveforms acquired across 692 stations.Transfer learning is then applied to fine-tune the model on 300000+MT-labelled labscale acoustic emission waveforms from 39 individual experiments instrumented with different sensor layouts,loading,and rock types in training.The optimal model achieves over 86%F-score on unseen waveforms at both the lab-and field-scale.This model outperforms existing empirical methods in classification of rock fracture mechanisms monitored by a sparse microseismic network.This facilitates rapid assessment of,and early warning against,various rock engineering hazard such as induced earthquakes and rock bursts.

MSC-YOLO:Improved YOLOv7 Based on Multi-Scale Spatial Context for Small Object Detection in UAV-View

Accurately identifying small objects in high-resolution aerial images presents a complex and crucial task in thefield of small object detection on unmanned aerial vehicles(UAVs).This task is challenging due to variations inUAV flight altitude,differences in object scales,as well as factors like flight speed and motion blur.To enhancethe detection efficacy of small targets in drone aerial imagery,we propose an enhanced You Only Look Onceversion 7(YOLOv7)algorithm based on multi-scale spatial context.We build the MSC-YOLO model,whichincorporates an additional prediction head,denoted as P2,to improve adaptability for small objects.We replaceconventional downsampling with a Spatial-to-Depth Convolutional Combination(CSPDC)module to mitigatethe loss of intricate feature details related to small objects.Furthermore,we propose a Spatial Context Pyramidwith Multi-Scale Attention(SCPMA)module,which captures spatial and channel-dependent features of smalltargets acrossmultiple scales.This module enhances the perception of spatial contextual features and the utilizationof multiscale feature information.On the Visdrone2023 and UAVDT datasets,MSC-YOLO achieves remarkableresults,outperforming the baseline method YOLOv7 by 3.0%in terms ofmean average precision(mAP).The MSCYOLOalgorithm proposed in this paper has demonstrated satisfactory performance in detecting small targets inUAV aerial photography,providing strong support for practical applications.

Prevention of thromboembolic events after radical prostatectomy in patients with hereditary thrombophilia due to a factor V Leiden mutation by multidisciplinary coagulation management

Objective:To examine the perioperative impact of factor V Leiden mutation on thromboembolic events'risk in radical prostatectomy(RP)patients.With an incidence of about 5%,factor V Leiden mutation is the most common hereditary hypercoagulability among Caucasians and rarer in Asia.The increased risk of thromboembolic events is three-to seven-fold in heterozygous and to 80-fold in homozygous patients.Methods:Within our prospectively collected database,we analysed 33006 prostate cancer patients treated with RP between December 2001 and December 2020.Of those,patients with factor V Leiden mutation were identified.All patients received individualised recommendation of haemostaseologists for perioperative anticoagulation.Thromboembolic complications(deep vein thrombosis and pulmonary embolism)were assessed during hospital stay,as well as according to patient reported outcomes within the first 3 months after RP.Results:Overall,85(0.3%)patients with known factor V Leiden mutation were identified.Median age was 65(interquartile range:61-68)years.There was at least one thrombosis in 53(62.4%)patients and 31(36.5%)patients had at least one embolic event in their medical history before RP.Within all 85 patients with factor V Leiden mutation,we experienced no thromboembolic complications within the first 3 months after surgery.Conclusion:In our cohort of patients with factor V Leiden mutation,no thromboembolic events were observed after RP with an individualised perioperative coagulation management concept.This may reassure patients with this hereditary condition who are counselled for RP.

Multi-scale Modeling and Finite Element Analyses of Thermal Conductivity of 3D C/SiC Composites Fabricating by Flexible-Oriented Woven Process

Thermal conductivity is one of the most significant criterion of three-dimensional carbon fiber-reinforced SiC matrix composites(3D C/SiC).Represent volume element(RVE)models of microscale,void/matrix and mesoscale proposed in this work are used to simulate the thermal conductivity behaviors of the 3D C/SiC composites.An entirely new process is introduced to weave the preform with three-dimensional orthogonal architecture.The 3D steady-state analysis step is created for assessing the thermal conductivity behaviors of the composites by applying periodic temperature boundary conditions.Three RVE models of cuboid,hexagonal and fiber random distribution are respectively developed to comparatively study the influence of fiber package pattern on the thermal conductivities at the microscale.Besides,the effect of void morphology on the thermal conductivity of the matrix is analyzed by the void/matrix models.The prediction results at the mesoscale correspond closely to the experimental values.The effect of the porosities and fiber volume fractions on the thermal conductivities is also taken into consideration.The multi-scale models mentioned in this paper can be used to predict the thermal conductivity behaviors of other composites with complex structures.

Genetically modified pigs with CD163 point mutation are resistant to HP-PRRSV infection

Porcine reproductive and respiratory syndrome(PRRS)is a globally prevalent contagious disease caused by the positive-strand RNA PRRS virus(PRRSV),resulting in substantial economic losses in the swine industry.Modifying the CD163 SRCR5 domain,either through deletion or substitution,can eff1ectively confer resistance to PRRSV infection in pigs.However,large fragment modifications in pigs inevitably raise concerns about potential adverse effects on growth performance.Reducing the impact of genetic modifications on normal physiological functions is a promising direction for developing PRRSV-resistant pigs.In the current study,we identified a specific functional amino acid in CD163 that influences PRRSV proliferation.Viral infection experiments conducted on Marc145 and PK-15CD163 cells illustrated that the mE535G or corresponding pE529G mutations markedly inhibited highly pathogenic PRRSV(HP-PRRSV)proliferation by preventing viral binding and entry.Furthermore,individual viral challenge tests revealed that pigs with the E529G mutation had viral loads two orders of magnitude lower than wild-type(WT)pigs,confirming effective resistance to HP-PRRSV.Examination of the physiological indicators and scavenger function of CD163 verified no significant differences between the WT and E529G pigs.These findings suggest that E529G pigs can be used for breeding PRRSV-resistant pigs,providing novel insights into controlling future PRRSV outbreaks.

GNAS mutations suppress cell invasion by activating MEG3 in growth hormone–secreting pituitary adenoma

Approximately 30%–40%of growth hormone–secreting pituitary adenomas(GHPAs)harbor somatic activating mutations in GNAS(αsubunit of stimulatory G protein).Mutations in GNAS are associated with clinical features of smaller and less invasive tumors.However,the role of GNAS mutations in the invasiveness of GHPAs is unclear.GNAS mutations were detected in GHPAs using a standard polymerase chain reaction(PCR)sequencing procedure.The expression of mutation-associated maternally expressed gene 3(MEG3)was evaluated with RT-qPCR.MEG3 was manipulated in GH3 cells using a lentiviral expression system.Cell invasion ability was measured using a Transwell assay,and epithelial–mesenchymal transition(EMT)-associated proteins were quantified by immunofluorescence and western blotting.Finally,a tumor cell xenograft mouse model was used to verify the effect of MEG3 on tumor growth and invasiveness.The invasiveness of GHPAs was significantly decreased in mice with mutated GNAS compared with that in mice with wild-type GNAS.Consistently,the invasiveness of mutant GNASexpressing GH3 cells decreased.MEG3 is uniquely expressed at high levels in GHPAs harboring mutated GNAS.Accordingly,MEG3 upregulation inhibited tumor cell invasion,and conversely,MEG3 downregulation increased tumor cell invasion.Mechanistically,GNAS mutations inhibit EMT in GHPAs.MEG3 in mutated GNAS cells prevented cell invasion through the inactivation of the Wnt/β-catenin signaling pathway,which was further validated in vivo.Our data suggest that GNAS mutations may suppress cell invasion in GHPAs by regulating EMT through the activation of the MEG3/Wnt/β-catenin signaling pathway.

Improved multi-scale inverse bottleneck residual network based on triplet parallel attention for apple leaf disease identification

Accurate diagnosis of apple leaf diseases is crucial for improving the quality of apple production and promoting the development of the apple industry. However, apple leaf diseases do not differ significantly from image texture and structural information. The difficulties in disease feature extraction in complex backgrounds slow the related research progress. To address the problems, this paper proposes an improved multi-scale inverse bottleneck residual network model based on a triplet parallel attention mechanism, which is built upon ResNet-50, while improving and combining the inception module and ResNext inverse bottleneck blocks, to recognize seven types of apple leaf(including six diseases of alternaria leaf spot, brown spot, grey spot, mosaic, rust, scab, and one healthy). First, the 3×3 convolutions in some of the residual modules are replaced by multi-scale residual convolutions, the convolution kernels of different sizes contained in each branch of the multi-scale convolution are applied to extract feature maps of different sizes, and the outputs of these branches are multi-scale fused by summing to enrich the output features of the images. Second, the global layer-wise dynamic coordinated inverse bottleneck structure is used to reduce the network feature loss. The inverse bottleneck structure makes the image information less lossy when transforming from different dimensional feature spaces. The fusion of multi-scale and layer-wise dynamic coordinated inverse bottlenecks makes the model effectively balances computational efficiency and feature representation capability, and more robust with a combination of horizontal and vertical features in the fine identification of apple leaf diseases. Finally, after each improved module, a triplet parallel attention module is integrated with cross-dimensional interactions among channels through rotations and residual transformations, which improves the parallel search efficiency of important features and the recognition rate of the network with relatively small computational costs while the dimensional dependencies are improved. To verify the validity of the model in this paper, we uniformly enhance apple leaf disease images screened from the public data sets of Plant Village, Baidu Flying Paddle, and the Internet. The final processed image count is 14,000. The ablation study, pre-processing comparison, and method comparison are conducted on the processed datasets. The experimental results demonstrate that the proposed method reaches 98.73% accuracy on the adopted datasets, which is 1.82% higher than the classical ResNet-50 model, and 0.29% better than the apple leaf disease datasets before preprocessing. It also achieves competitive results in apple leaf disease identification compared to some state-ofthe-art methods.