Expression Classification Research Articles

Facial Expression Recognition-You Only Look Once-Neighborhood Coordinate Attention Mamba: Facial Expression Detection and Classification Based on Neighbor and Coordinates Attention Mechanism.

In studying the joint object detection and classification problem for facial expression recognition (FER) deploying the YOLOX framework, we introduce a novel feature extractor, called neighborhood coordinate attention Mamba (NCAMamba) to substitute for the original feature extractor in the Feature Pyramid Network (FPN). NCAMamba combines the background information reduction capabilities of Mamba, the local neighborhood relationship understanding of neighborhood attention, and the directional relationship understanding of coordinate attention. The resulting FER-YOLO-NCAMamba model, when applied to two unaligned FER benchmark datasets, RAF-DB and SFEW, obtains significantly improved mean average precision (mAP) scores when compared with those obtained by other state-of-the-art methods. Moreover, in ablation studies, it is found that the NCA module is relatively more important than the Visual State Space (VSS), a version of using Mamba for image processing, and in visualization studies using the grad-CAM method, it reveals that regions around the nose tip are critical to recognizing the expression; if it is too large, it may lead to erroneous prediction, while a small focused region would lead to correct recognition; this may explain why FER of unaligned faces is such a challenging problem.

Multiparametric MRI Radiomics With Machine Learning for Differentiating HER2-Zero, -Low, and -Positive Breast Cancer: Model Development, Testing, and Interpretability Analysis.

BACKGROUND: MRI radiomics has been explored for three-tiered classification of breast cancer HER2 expression (i.e., HER2-zero, HER2-low, or HER2-positive), although understanding of how such models reach their predictions is lacking. OBJECTIVE: To develop and test multiparametric MRI radiomics machine-learning models for differentiating three-tiered HER2 expression levels in patients with breast cancer, and to explain the contributions of model features through local and global interpretations using SHapley Additive exPlanation (SHAP) analysis. METHODS: This retrospective study included 737 patients (mean age, 54.1±10.6 years) with breast cancer from two centers (center 1: n=578; center 2: n=159), who underwent breast MRI and had HER2 expression determined after excisional biopsy. Analysis entailed two tasks: differentiating HER2-negative (i.e., HER2-zero or HER2-low) from HER2-positive tumors (task 1), and differentiating HER2-zero from HER2-low tumors (task 2). For each task, patients from center 1 were randomly assigned in 7:3 ratio to training (task 1: n=405; task 2: n=284) or internal test (task 1: n=173; task 2: n=122) sets; those from center 2 formed an external test set (task 1: n=159; task 2: n=105). Radiomics features were extracted from early-phase dynamic contrast-enhanced images (DCE), T2-weighted images (T2WI), and DWI. For each task, a support vector machine (SVM) was used for feature selection; a multiparametric radiomics score (radscore) was computed using feature weights from SVM correlation coefficients; conventional MRI and combined models were constructed; and model performances were evaluated. SHAP analysis was used to provide local and global interpretations for model outputs. RESULTS: In the external test set, for task 1, AUCs for the conventional MRI model, radscore, and combined model were 0.624, 0.757, and 0.762, respectively; for task 2, AUC for radscore was 0.754, and no conventional MRI model or combined model could be constructed. SHAP analysis identified early-phase DCE features as having the strongest influence for both tasks; T2WI features also had a prominent role for task 2. CONCLUSION: The findings indicate suboptimal performance of MRI radiomics models for noninvasive characterization of HER2 expression. CLINICAL IMPACT: The study provides an example of the use of SHAP interpretation analysis to better understand predictions of imaging-based machine learning models.

Dynamic Mode Decomposition-Based Features for Ovarian Cancer Gene Expression Classification Using Machine Learning

Machine learning (ML) algorithms have been deployed in recent years as models for the analysis of complex data. The ubiquity of ML algorithms stems from their ability to learn the patterns and structures inherent in data. Additionally, they are adaptable to a wide range of data types, irrespective of size, which allows them to learn and predict the future pattern of data. In this work, dynamic mode decomposition (DMD), an ML algorithm, is deployed to analyse the pattern of gene expression data from patients with and without ovarian cancer. Ovarian cancer is one of the deadliest gynaecologic cancers worldwide. The obscure nature of the symptoms makes early detection of ovarian cancer difficult. Early diagnosis increases the chances of survival for patients. Furthermore, the modes computed from DMD are used as features and separately fed into three ML classifiers- support vector machine (SVM), decision tree (DecTr), and K- nearest neighbour (KNN) to classify the gene expression into either cancer or non-cancer categories. Multiple metrics- sensitivity, accuracy, precision, and error rate are used to assess the performance of the models, to have a balanced illustration of a model’s performance. The DecTr outperforms the other two classifiersSVM and KNN, across the metrics used in evaluating the performance of the models.

Figurative Language and Sensory Perception: Corpus-Based Computer-Assisted Study of the Nature and Motivation of Synesthetic Metaphors in Olive Oil Tasting Notes

ABSTRACT Meaning in sensory language is often built through figurative mechanisms, such as synesthetic metaphors, where a sensorial domain is used to talk about perceptions from a different sense, as in sweet [ taste ] texture [ touch ]. The motivation of synesthetic transfers of meaning has been studied in general and literary language, resulting in attempts to reveal universal patterns regarding the directionality of meaning transfer and sensorial conceptual preference. However, those universals have not been proven in any sensory Language for Specific Purposes (LSP). We a sensory LSP corpus of olive oil tasing notes in English to explore the nature of these metaphors, test existent models and explanatory accounts and identify tendencies present in synesthetic meaning transfers. The computer-assisted semi-automatic scalable methodology followed consists of the innovative quasi-simultaneous identification of semantic incongruences and the classification of synesthetic expressions in the discourse according to the source and target sensorial domains. Results show the inadequacy of existent models to explain synesthetic behavior in olive oil tasting language. The patterns found are discussed in the light of cognitive constraints and LSP genre analysis to conclude that a multi-causal approach is needed to explain the motivation of synesthetic transfers of meaning.

Valence sound symbolism facilitates classification of vowels and emotional facial expressions.

Research on iconicity or sound symbolism chronicles associations between aspects of word meaning and word form. In valence sound symbolism, specifically, vowels were demonstrated to be associated with valence, so that the vowel /i/ (as in English sea) is judged to fit positively valenced stimuli, whereas the vowel /o/ (as in German Boot) is judged to fit negatively valenced stimuli. However, because previous findings were based on judgments or name invention tasks, they may reflect deliberate strategies. The present research aims to demonstrate the automaticity of valence sound symbolism in online language processing by means of a speeded response task. A total of 163 participants performed a speeded categorization task in which they were requested to classify one of two simultaneously presented stimuli, pseudowords containing the vowels /i/ or /o/ and pictures with positive or negative emotional facial expressions. Thus, stimulus pairings could be either congruent (/i/-words and positive expressions; /o/-words and negative expressions) or incongruent (/i/-words and negative expressions; /o/-words and positive expressions). We observed faster and more accurate responses for congruent over incongruent combinations (the simple effects were significant for positive but not for negative expressions). Thus, sound symbolic congruency (vs. incongruency) of an irrelevant stimulus facilitated responses, which accords with an automatic process contributing to valence sound symbolism and indicates that valence sound symbolism is deeply engrained in the human cognitive system. (PsycInfo Database Record (c) 2024 APA, all rights reserved).

Improved Histogram of Oriented Gradient (HOG) Feature Extraction for Facial Expressions Classification

Facial expression classification system is one of the implementations of machine learning (ML) that takes facial expression datasets, undergoes training, and then utilizes the trained results to recognize facial expressions in new facial images. The recognized facial expressions include anger, contempt, disgust, fear, happy, sadness, and surprise expressions. The method employed for facial feature extraction utilizes histogram-oriented gradient (HOG). This study proposes an enhancement method for HOG feature extraction by reducing the feature dimension into multiple sub-features based on gradient orientation intervals, referred to as HOG channel (HOG-C). Classifier testing techniques are divided into two methods for comparison—support vector machines (SVM) with HOG features and SVM with HOG-C features. The testing results demonstrate that SVM with HOG achieves an accuracy of 99.9% with an average training time of 18.03 minutes, while SVM with HOG-C attains a 100% accuracy with an average training time of 18.09 minutes. The testing outcomes reveal that the implementation of SVM with HOG-C successfully enhances accuracy for facial expression classification.

Analysis of Expression and Regulation of AKR1C2 in HPV-Positive and -Negative Oropharyngeal Squamous Cell Carcinoma.

Head and Neck Squamous Cell Carcinoma (HNSCC), particularly Oropharyngeal Squamous Cell Carcinoma (OPSCC), is a major global health challenge due to its increasing incidence and high mortality rate. This study investigates the role of aldo-keto reductase 1C2 (AKR1C2) in OPSCC, focusing on its expression, correlation with Human Papillomavirus (HPV) status, oxidative stress status, and clinical outcomes, with an emphasis on sex-specific differences. We analyzed AKR1C2 expression using immunohistochemistry in formalin-fixed, paraffin-embedded tissue samples from 51 OPSCC patients. Additionally, we performed RT-qPCR in cultured HPV16-E6*I and HPV16-E6 overexpressing HEK293 cell lines (p53WT). Statistical analyses were performed to assess the correlation between AKR1C2 expression and patient data. Our results indicate a significant association between increased AKR1C2 expression and higher AJCC classification (p = 0.009) as well as positive HPV status (p = 0.008). Prognostic implications of AKR1C2 varied by sex, whereby female patients with high AKR1C2 expression had better overall survival, whereas male patients exhibited poorer outcomes. Additionally, AKR1C2 expression was linked to HPV status, suggesting a potential HPV-specific regulatory mechanism. These findings underscore the complex interplay among AKR1C2, HPV, and patient sex, highlighting the need for personalized treatment strategies for OPSCC. Targeted inhibition of AKR1C2, considering sex-specific differences, may enhance therapeutic outcomes. Future research should investigate these mechanisms to enhance treatment efficacy.

Facial Expression Recognition and Classification for Autism Spectrum Disorder based on SDFT Images using Deep Learning

Facial Expression Recognition and Classification for Autism Spectrum Disorder based on SDFT Images using Deep Learning

Clinical and pathological significance of Orai1 channel expression in human diabetic nephropathy.

Targeted therapies for diabetic nephropathy (DN) are lacking, partly due to their irreversible nature. The role of Orai1, a store-operated Ca2+ channel, in DN remains debated, with conflicting evidence on its effect on proteinuria in animal models. We aimed to elucidate the functional relevance of Orai1 expression for clinicopathological parameters in patients with DN. In this study, we included 93 patients diagnosed with DN between 2009 and 2019. Immunohistochemical staining for Orai1 was performed on paraffin-embedded kidney sections. The significance of Orai1 expression in human DN was assessed by examining its correlation with DN's pathological and clinical parameters using Pearson's correlation coefficient and univariate logistic regression. Orai1 was significantly overexpressed in DN patients compared to control. A strong correlation was observed between increased Orai1 expression and higher Renal Pathology Society DN classification, enhanced interstitial fibrosis and tubular atrophy scores. Positive correlations with serum creatinine levels and prognosis of chronic kidney disease (CKD) by glomerular filtration rate (GFR) and albuminuria category were noted but the estimated GFR was inversely related to Orai1 expression. Orai1's association with advanced CKD stages persisted even after adjusting for confounding variables in multivariate logistic regression analysis. Orai1 expression is closely associated with histological and clinical severities of DN, suggesting its potential as a predictive biomarker for disease progression and prognosis. These findings provide new perspectives on therapeutic interventions targeting Orai1 in DN.

Prognostic genome and transcriptome signatures in colorectal cancers

Colorectal cancer is caused by a sequence of somatic genomic alterations affecting driver genes in core cancer pathways1. Here, to understand the functional and prognostic impact of cancer-causing somatic mutations, we analysed the whole genomes and transcriptomes of 1,063 primary colorectal cancers in a population-based cohort with long-term follow-up. From the 96 mutated driver genes, 9 were not previously implicated in colorectal cancer and 24 had not been linked to any cancer. Two distinct patterns of pathway co-mutations were observed, timing analyses identified nine early and three late driver gene mutations, and several signatures of colorectal-cancer-specific mutational processes were identified. Mutations in WNT, EGFR and TGFβ pathway genes, the mitochondrial CYB gene and 3 regulatory elements along with 21 copy-number variations and the COSMIC SBS44 signature correlated with survival. Gene expression classification yielded five prognostic subtypes with distinct molecular features, in part explained by underlying genomic alterations. Microsatellite-instable tumours divided into two classes with different levels of hypoxia and infiltration of immune and stromal cells. To our knowledge, this study constitutes the largest integrated genome and transcriptome analysis of colorectal cancer, and interlinks mutations, gene expression and patient outcomes. The identification of prognostic mutations and expression subtypes can guide future efforts to individualize colorectal cancer therapy.

Combined Transcriptome and Circulating Tumor DNA Longitudinal Biomarker Analysis Associates With Clinical Outcomes in Advanced Solid Tumors Treated With Pembrolizumab.

Immune gene expression signatures are emerging as potential biomarkers for immunotherapy (IO). VIGex is a 12-gene expression classifier developed in both nCounter (Nanostring) and RNA sequencing (RNA-seq) assays and analytically validated across laboratories. VIGex classifies tumor samples into hot, intermediate-cold (I-Cold), and cold subgroups. VIGex-Hot has been associated with better IO treatment outcomes. Here, we investigated the performance of VIGex and other IO biomarkers in an independent data set of patients treated with pembrolizumab in the INSPIRE phase II clinical trial (ClinicalTrials.gov identifier: NCT02644369). Patients with advanced solid tumors were treated with pembrolizumab 200 mg IV once every 3 weeks. Tumor RNA-seq data from baseline tumor samples were classified by the VIGex algorithm. Circulating tumor DNA (ctDNA) was measured at baseline and start of cycle 3 using the bespoke Signatera assay. VIGex-Hot was compared with VIGex I-Cold + Cold and four groups were defined on the basis of the combination of VIGex subgroups and the change in ctDNA at cycle 3 from baseline (ΔctDNA). Seventy-six patients were enrolled, including 16 ovarian, 12 breast, 12 head and neck cancers, 10 melanoma, and 26 other tumor types. Objective response rate was 24% in VIGex-Hot and 10% in I-Cold/Cold. VIGex-Hot subgroup was associated with higher overall survival (OS) and progression-free survival (PFS) when included in a multivariable model adjusted for tumor type, tumor mutation burden, and PD-L1 immunohistochemistry. The addition of ΔctDNA improved the predictive performance of the baseline VIGex classification for both OS and PFS. Our data indicate that the addition of ΔctDNA to baseline VIGex may refine prediction for IO.

Leveraging hybrid 1D-CNN and RNN approach for classification of brain cancer gene expression

Leveraging deep learning (DL) approaches in genomics data has led to significant advances in cancer prediction. The continuous availability of gene expression datasets over the preceding years has made them one of the most accessible sources of genome-wide data, advancing cancer bioinformatics research and advanced prediction of cancer genomic data. To contribute to this topic, the proposed work is based on DL prediction in both convolutional neural network (CNN) and recurrent neural network (RNN) for five classes in brain cancer using gene expression data obtained from Curated Microarray Database (CuMiDa). This database is used for cancer classification and is publicly accessible on the official CuMiDa website. This paper implemented DL approaches using a One Dimensional-Convolutional Neural Network (1D-CNN) followed by an RNN classifier with and without Bayesian hyperparameter optimization (BO). The accuracy of this hybrid model combination of (BO + 1D-CNN + RNN) produced the highest classification accuracy of 100% instead of the 95% for the ML model in prior work and 90% for the (1D-CNN + RNN) algorithm considered in the paper. Therefore, the classification of brain cancer gene expression according to the hybrid model (BO + 1D-CNN + RNN) provides more accurate and useful assessments for patients with different types of brain cancers. Thus, gene expression data are used to create a DL classification-based- hybrid model that will hold senior promise in the treatment of brain cancer.

Sensing Human Emotion using Emerging Machine Learning Techniques

Human emotion recognition using machine learning is a new field that has the potential to improve user experience, lower crime, and target advertising. The ability of today's emotion detection systems to identify human emotions is essential. Applications ranging from security cameras to emotion detection are readily accessible. Machine learning-based emotion detection recognises and deciphers human emotions from text and visual data. In this study, we use convolutional neural networks and natural language processing approaches to create and assess models for emotion detection. Instead of speaking clearly, these human face expressions visually communicate a lot of information. Recognising facial expressions is important for human-machine interaction. Applications for automatic facial expression recognition systems are numerous and include, but are not limited to, comprehending human conduct, identifying mental health issues, and creating artificial human emotions. It is still difficult for computers to recognise facial expressions with a high recognition rate. Geometry and appearance-based methods are two widely used approaches for automatic FER systems in the literature. Pre-processing, face detection, feature extraction, and expression classification are the four steps that typically make up facial expression recognition. The goal of this research is to recognise the seven main human emotions anger, disgust, fear, happiness, sadness, surprise, and neutrality using a variety of deep learning techniques (convolutional neural networks).

Gene expression signature for predicting homologous recombination deficiency in triple-negative breast cancer

Triple-negative breast cancers (TNBCs) are a subset of breast cancers that have remained difficult to treat. A proportion of TNBCs arising in non-carriers of BRCA pathogenic variants have genomic features that are similar to BRCA carriers and may also benefit from PARP inhibitor treatment. Using genomic data from 129 TNBC samples from the Malaysian Breast Cancer (MyBrCa) cohort, we developed a gene expression-based machine learning classifier for homologous recombination deficiency (HRD) in TNBCs. The classifier identified samples with HRD mutational signature at an AUROC of 0.93 in MyBrCa validation datasets and 0.84 in TCGA TNBCs. Additionally, the classifier strongly segregated HRD-associated genomic features in TNBCs from TCGA, METABRIC, and ICGC. Thus, our gene expression classifier may identify triple-negative breast cancer patients with homologous recombination deficiency, suggesting an alternative method to identify individuals who may benefit from treatment with PARP inhibitors or platinum chemotherapy.

A Real-Time and Privacy-Preserving Facial Expression Recognition System Using an AI-Powered Microcontroller

This study proposes an edge computing-based facial expression recognition system that is low cost, low power, and privacy preserving. It utilizes a minimally obtrusive cap-based system designed for the continuous and real-time monitoring of a user’s facial expressions. The proposed method focuses on detecting facial skin deformations accompanying changes in facial expressions. A multi-zone time-of-flight (ToF) depth sensor VL53L5CX, featuring an 8 × 8 depth image, is integrated into the front brim of the cap to measure the distance between the sensor and the user’s facial skin surface. The distance values corresponding to seven universal facial expressions (neutral, happy, disgust, anger, surprise, fear, and sad) are transmitted to a low-power STM32F476 microcontroller (MCU) as an edge device for data preprocessing and facial expression classification tasks utilizing an on-device pre-trained deep learning model. Performance evaluation of the system is conducted through experiments utilizing data collected from 20 subjects. Four deep learning algorithms, including Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNN), Long Short-Term Memory (LSTM) networks, and Deep Neural Networks (DNN), are assessed. These algorithms demonstrate high accuracy, with CNN yielding the best result, achieving an accuracy of 89.20% at a frame rate of 15 frames per second (fps) and a maximum latency of 2 ms.

Reproducibility of c-Met Immunohistochemical Scoring (Clone SP44) for Non-Small Cell Lung Cancer Using Conventional Light Microscopy and Whole Slide Imaging.

Emerging therapies for non-small cell lung cancer targeting c-Met overexpression have recently demonstrated promising results. However, the evaluation of c-Met expression can be challenging. We aimed to study the inter and intraobserver reproducibility of c-Met expression evaluation. One hundred ten cases with non-small cell lung cancer (40 biopsies and 70 surgical specimens) were retrospectively selected in a single laboratory (LPCE) and evaluated for c-Met expression. Six pathologists (4 seniors and 2 juniors) evaluated the H-score and made a 3-tier classification of c-Met expression for all cases, using conventional light microscopy (CLM) and whole slide imaging (WSI). The interobserver reproducibility with CLM gave global Cohen Kappa coefficients (ƙ) ranging from 0.581 (95% CI: 0.364-0.771) to 0.763 (95% CI: 0.58-0.92) using the c-Met 3-tier classification and H-score, respectively. ƙ was higher for senior pathologists and biopsy samples. The interobserver reproducibility with WSI gave a global ƙ ranging from 0.543 (95% CI: 0.33-0.724) to 0.905 (95% CI: 0.618-1) using the c-Met H-score and 2-tier classification (≥25% 3+), respectively. ƙ for intraobserver reproducibility between CLM and WSI ranged from 0.713 to 0.898 for the c-Met H-score and from 0.600 to 0.779 for the c-Met 3-tier classification. We demonstrated a moderate to excellent interobserver agreement for c-Met expression with a substantial to excellent intraobserver agreement between CLM and WSI, thereby supporting the development of digital pathology. However, some factors (scoring method, type of tissue samples, and expertise level) affect reproducibility. Our findings highlight the importance of establishing a consensus definition and providing further training, particularly for inexperienced pathologists, for c-Met immunohistochemistry assessment in clinical practice.

The impact of estrogen receptor and L1 cell adhesion molecule expression on endometrial cancer outcome correlates with clinicopathological risk group and molecular subgroup

ObjectiveTo assess the risk stratification of clinicopathologically and molecularly classified endometrial cancer based on estrogen receptor (ER) and L1 cell adhesion molecule (L1CAM) expression. MethodsThis was a retrospective study of patients who underwent primary treatment at a single tertiary center. Carcinomas were classified into 5 clinicopathological risk groups, as per European guidelines. Immunohistochemistry and polymerase-ϵ sequencing were conducted for molecular classification and determination of ER and L1CAM expression. ResultsData from 1044 patients were analyzed. The median follow-up was 67.5 months. In univariable analyses, ER expression correlated with improved disease-specific survival (DSS) in the “no specific molecular profile” (NSMP) (P < 0.001) and mismatch repair deficient (MMRd) (P = 0.002) subgroups. Negative L1CAM expression was associated with enhanced DSS in the NSMP subgroup alone (P < 0.001). ER (hazard ratio [HR] 0.18), but not L1CAM, exhibited prognostic significance within NSMP when controlling for parameters available at the time of diagnosis (tumor histotype, grade, age). ER and L1CAM were not independently associated with DSS within NSMP when controlling for parameters available after surgery (clinicopathological risk groups, age, adjuvant therapy). However, in high-risk–advanced-metastatic cases, both ER (HR 0.26) and L1CAM (HR 3.9) independently correlated with DSS. Similarly, within MMRd, ER was associated with improved DSS in high-risk–advanced-metastatic carcinomas (HR 0.42). ConclusionThe prognostic significance of ER and L1CAM varies across clinicopathological risk groups and molecular subgroups of endometrial cancer. Notably, risk assessment for high-risk–advanced-metastatic NSMP and MMRd subtype carcinomas can be refined by ER status.

In-silico Binding, Stability, Pharmacokinetics, and Toxicity Studies on Natural (-)-ambrox Metabolites as Binding Ligands to Luminal B and Triple-negative/basal-like Proteins for Breast Cancer Therapy

Background:: Breast cancer is the most prevalent malignant tumour in women of all races and is the second largest cause of cancer-related death in the majority of races. Based on the pattern of gene expression, five intrinsic or molecular classifications for breast tumours are frequently used. Our research, which is presently being utilized to treat breast cancer and has the potential to significantly change the course of the illness, is focused on two of them: luminal B breast cancer and triplenegative/ basal-like breast cancer. Methods:: Screening a database containing millions of drug molecules or phytochemicals has become rapid and simple due to computer-aided drug design (CADD) techniques. In the current work, nine natural compounds were screened for ambrox from a sperm whale using docking research. Results:: Following docking studies, nine substances were discovered to interact with basal-like and luminal B breast cancer proteins. All nine metabolites, however, adhered to Lipinski's rule of five and had sufficient oral bioavailability. The greatest binding affinities were demonstrated by 13,14,15,16-tetranorlabdane-3-oxo-8,12-diol, 6-β-hydroxy ambrox, 1-α-hydroxy-3-oxoambrox, and 2-α-3-β-dihydroxy ambrox. Conclusion:: Therefore, it can be concluded that research on molecular docking and pharmacological mimics may hasten the discovery of new medications. The use of ambrox metabolites in the treatment of breast cancer also requires future perspectives on their therapeutic use.

DeepCBA: A deep learning framework for gene expression prediction in maize based on DNA sequences and chromatin interactions

Chromatin interactions create spatial proximity between distal regulatory elements and target genes in the genome, which has an important impact on gene expression, transcriptional regulation, and phenotypic traits. To date, several methods have been developed for predicting gene expression. However, existing methods do not take into consideration the effect of chromatin interactions on target gene expression, thus potentially reducing the accuracy of gene expression prediction and mining of important regulatory elements. In this study, we developed a highly accurate deep learning-based gene expression prediction model (DeepCBA) based on maize chromatin interaction data. Compared with existing models, DeepCBA exhibits higher accuracy in expression classification and expression value prediction. The average Pearson correlation coefficients (PCCs) for predicting gene expression using gene promoter proximal interactions, proximal-distal interactions, and both proximal and distal interactions were 0.818, 0.625, and 0.929, respectively, representing an increase of 0.357, 0.16, and 0.469 over the PCCs obtained with traditional methods that use only gene proximal sequences. Some important motifs were identified through DeepCBA; they were enriched in open chromatin regions and expression quantitative trait loci and showed clear tissue specificity. Importantly, experimental results for the maize flowering-related gene ZmRap2.7 and the tillering-related gene ZmTb1 demonstrated the feasibility of DeepCBA for exploration of regulatory elements that affect gene expression. Moreover, promoter editing and verification of two reported genes (ZmCLE7 and ZmVTE4) demonstrated the utility of DeepCBA for the precise design of gene expression and even for future intelligent breeding. DeepCBA is available at http://www.deepcba.com/ or http://124.220.197.196/.

Hybrid arithmetic optimization algorithm with deep transfer learning based microarray gene expression classification model

Hybrid arithmetic optimization algorithm with deep transfer learning based microarray gene expression classification model