Principal component analysis of blood microRNA datasets facilitates diagnosis of diverse diseases

MicroRNAs are associated with cardiac biomarkers, cardiac structure and function and incident outcomes in heart failure

AIMS

The association between microRNAs (miRNAs) and established cardiac biomarkers is largely unknown. We aimed to measure the association between plasma miRNAs and N-terminal pro-B-type natriuretic peptide (NT-proBNP), cardiac troponin I, soluble urokinase-type plasminogen activator receptor (suPAR), and galectin-3 with cardiac structure and function and clinical outcomes.

METHODS AND RESULTS

We quantified 32 plasma miRNAs using the FirePlex miRNA assay and measured biomarkers in 139 individuals with symptomatic heart failure (HF). We used principal component (PC) analysis and linear regression to evaluate the association between miRNAs and biomarkers with ventricular size and function by echocardiography and Cox modelling for the incidence of a first composite event of HF hospitalization, heart transplant, left ventricular assist device implant, or death. The mean (standard deviation) age at baseline was 64.3 (12.4) years, 33 (24%) were female, and 122 (88%) were White. A total of 45 events occurred over a median follow-up of 368 (interquartile range 234, 494) days. Baseline NT-proBNP (β = -2.0; P = 0.001) and miRNA PC2 (β = 2.6; P = 0.002) were associated with baseline left ventricular ejection fraction. NT-proBNP (β = 20.6; P = 0.0004), suPAR (β = -39.6; P = 0.005), and PC4 (β = 21.1; P = 0.02) were associated with baseline left ventricular end-diastolic volumes. NT-proBNP [hazard ratio (HR) 1.67, 95% confidence interval (CI) 1.28-2.18, P = 0.0002], galectin-3 (HR 2.02, 95% CI 1.05-3.91, P = 0.036), PC3 (HR 1.75, 95% CI 1.23-2.49, P = 0.002), and PC4 (HR 1.67, 95% CI 1.1-2.52, P = 0.016) were independently associated with incident events.

CONCLUSIONS

Biomarkers and miRNA PCs are associated with cardiac structure and function and incident cardiovascular outcomes. Combining information from miRNAs provides prognostic information beyond biomarkers in HF.

Circulating miRNA profiles in COVID-19 patients and meta-analysis: implications for disease progression and prognosis

We compared circulating miRNA profiles of hospitalized COVID-positive patients (n = 104), 27 with acute respiratory distress syndrome (ARDS) and age- and sex-matched healthy controls (n = 18) to identify miRNA signatures associated with COVID and COVID-induced ARDS. Meta-analysis incorporating data from published studies and our data was performed to identify a set of differentially expressed miRNAs in (1) COVID-positive patients versus healthy controls as well as (2) severe (ARDS+) COVID vs moderate COVID. Gene ontology enrichment analysis of the genes these miRNAs interact with identified terms associated with immune response, such as interferon and interleukin signaling, as well as viral genome activities associated with COVID disease and severity. Additionally, we observed downregulation of a cluster of miRNAs located on chromosome 14 (14q32) among all COVID patients. To predict COVID disease and severity, we developed machine learning models that achieved AUC scores between 0.81-0.93 for predicting disease, and between 0.71-0.81 for predicting severity, even across diverse studies with different sample types (plasma versus serum), collection methods, and library preparations. Our findings provide network and top miRNA feature insights into COVID disease progression and contribute to the development of tools for disease prognosis and management.

miR-603 promotes cell proliferation and differentiation by targeting TrkB in acute promyelocytic leukemia

Arsenic trioxide (ATO) treatment effectively prolongs the overall survival of patients with acute promyelocytic leukemia (APL). Mutations in the oncogene PML::RARA were found in patients with ATO-resistant and relapsed APL. However, some relapsed patients do not have such mutations. Here, we performed microarray analysis of samples from newly diagnosed and relapsed APL, and found different microRNA (miRNA) expression patterns between these two groups. Among the differentially expressed miRNAs, miR-603 was expressed at the lowest level in relapsed patients. The expression of miR-603 and its predicted target tropomyosin-related kinase B (TrkB) were determined by PCR and Western blot. Proliferation was measured using an MTT assay, while apoptosis, cell cycle and CD11b expression were analyzed using flow cytometry. In APL patients, the expression of miR-603 was negatively correlated with that of TrkB. miR-603 directly targeted TrkB and downregulated TrkB expression in the APL cell line NB4. miR-603 increased cell proliferation by promoting the differentiation and inhibiting the apoptosis of NB4 cells. This study shows that the miR-603/ TrkB axis may be a potent therapeutic target for relapsed APL.

Altered microRNA expression in patients with sarcoidosis

Background Sarcoidosis is a granulomatous multisystem disease of uncertain aetiology. The disease has major inflammatory and immune components; however, the immunopathogenesis is not well understood. Micro ribonucleic acids (microRNAs) are classes of miniature, single-stranded, non-coding RNAs. Their key recognised role includes mediating the silencing of target genes post-transcriptionally. Recently, the role of miRNAs has gained interest in numerous disorders, suggested as being involved in pathogenesis of those diseases and acting as disease markers. Very little is known about the role of miRNAs in sarcoidosis, with nothing known regarding miRNAs in South African patients. The main objective, therefore, was to investigate the serum expression of approximately 800 miRNAs in patients with sarcoidosis compared with race-, age- and gender-matched healthy controls. Methods A total of six patients and six matched controls participated in this study. Whole blood samples were collected in EDTA tubes, processed and the plasma retained. RNA was extracted from the stored plasma samples using the QIAGEN miRNeasy Mini Kit® and concentrated using a salt-ethanol precipitation. The extracted miRNA was profiled using an nCounter® miRNA human v3 expression assay and data analysed using the nSolver™ Analysis Software. Results After excluding one sample/control pair because of cellular RNA contamination, the remaining five patient and five matched control samples were analysed, and 145 miRNAs were found to be potentially differentially expressed. On applying a Bonferroni correction, the only miRNA that was significantly different was miRNA let-7a-5p, which was significantly overexpressed (141-fold change; p<0.0003) in patients compared with controls. Conclusion This is the first miRNA report of differentially expressed miRNAs in the serum of patients with sarcoidosis and matched healthy controls in South Africa. The results obtained suggest that miRNAs may play a role in sarcoidosis pathogenesis. Whether these molecules have diagnostic or prognostic implications, needs future studies recruiting larger patient cohorts.

A systematic review of non-coding RNA genes with differential expression profiles associated with autism spectrum disorders

AIMS

To identify differential expression of shorter non-coding RNA (ncRNA) genes associated with autism spectrum disorders (ASD).

BACKGROUND

ncRNA are functional molecules that derive from non-translated DNA sequence. The HUGO Gene Nomenclature Committee (HGNC) have approved ncRNA gene classes with alignment to the reference human genome. One subset is microRNA (miRNA), which are highly conserved, short RNA molecules that regulate gene expression by direct post-transcriptional repression of messenger RNA. Several miRNA genes are implicated in the development and regulation of the nervous system. Expression of miRNA genes in ASD cohorts have been examined by multiple research groups. Other shorter classes of ncRNA have been examined less. A comprehensive systematic review examining expression of shorter ncRNA gene classes in ASD is timely to inform the direction of research.

METHODS

We extracted data from studies examining ncRNA gene expression in ASD compared with non-ASD controls. We included studies on miRNA, piwi-interacting RNA (piRNA), small NF90 (ILF3) associated RNA (snaR), small nuclear RNA (snRNA), small nucleolar RNA (snoRNA), transfer RNA (tRNA), vault RNA (vtRNA) and Y RNA. The following electronic databases were searched: Cochrane Library, EMBASE, PubMed, Web of Science, PsycINFO, ERIC, AMED and CINAHL for papers published from January 2000 to May 2022. Studies were screened by two independent investigators with a third resolving discrepancies. Data was extracted from eligible papers.

RESULTS

Forty-eight eligible studies were included in our systematic review with the majority examining miRNA gene expression alone. Sixty-four miRNA genes had differential expression in ASD compared to controls as reported in two or more studies, but often in opposing directions. Four miRNA genes had differential expression in the same direction in the same tissue type in at least 3 separate studies. Increased expression was reported in miR-106b-5p, miR-155-5p and miR-146a-5p in blood, post-mortem brain, and across several tissue types, respectively. Decreased expression was reported in miR-328-3p in bloods samples. Seven studies examined differential expression from other classes of ncRNA, including piRNA, snRNA, snoRNA and Y RNA. No individual ncRNA genes were reported in more than one study. Six studies reported differentially expressed snoRNA genes in ASD. A meta-analysis was not possible because of inconsistent methodologies, disparate tissue types examined, and varying forms of data presented.

CONCLUSION

There is limited but promising evidence associating the expression of certain miRNA genes and ASD, although the studies are of variable methodological quality and the results are largely inconsistent. There is emerging evidence associating differential expression of snoRNA genes in ASD. It is not currently possible to say whether the reports of differential expression in ncRNA may relate to ASD aetiology, a response to shared environmental factors linked to ASD such as sleep and nutrition, other molecular functions, human diversity, or chance findings. To improve our understanding of any potential association, we recommend improved and standardised methodologies and reporting of raw data. Further high-quality research is required to shine a light on possible associations, which may yet yield important information.

Phenotypic subtyping via contrastive learning

Defining and accounting for subphenotypic structure has the potential to increase statistical power and provide a deeper understanding of the heterogeneity in the molecular basis of complex disease. Existing phenotype subtyping methods primarily rely on clinically observed heterogeneity or metadata clustering. However, they generally tend to capture the dominant sources of variation in the data, which often originate from variation that is not descriptive of the mechanistic heterogeneity of the phenotype of interest; in fact, such dominant sources of variation, such as population structure or technical variation, are, in general, expected to be independent of subphenotypic structure. We instead aim to find a subspace with signal that is unique to a group of samples for which we believe that subphenotypic variation exists (e.g., cases of a disease). To that end, we introduce Phenotype Aware Components Analysis (PACA), a contrastive learning approach leveraging canonical correlation analysis to robustly capture weak sources of subphenotypic variation. In the context of disease, PACA learns a gradient of variation unique to cases in a given dataset, while leveraging control samples for accounting for variation and imbalances of biological and technical confounders between cases and controls. We evaluated PACA using an extensive simulation study, as well as on various subtyping tasks using genotypes, transcriptomics, and DNA methylation data. Our results provide multiple strong evidence that PACA allows us to robustly capture weak unknown variation of interest while being calibrated and well-powered, far superseding the performance of alternative methods. This renders PACA as a state-of-the-art tool for defining de novo subtypes that are more likely to reflect molecular heterogeneity, especially in challenging cases where the phenotypic heterogeneity may be masked by a myriad of strong unrelated effects in the data.

Cellular miR-6741-5p as a Prognostic Biomarker Predicting Length of Hospital Stay among COVID-19 Patients

Wide variability exists with host response to SARS-CoV-2 infection among individuals. Circulatory micro RNAs (miRNAs) are being recognized as promising biomarkers for complex traits, including viral pathogenesis. We hypothesized that circulatory miRNAs at 48 h post hospitalization may predict the length of stay (LOS) and prognosis of COVID-19 patients. Plasma miRNA levels were compared between three groups: (i) healthy volunteers (C); (ii) COVID-19 patients treated with remdesivir (an antiviral) plus dexamethasone (a glucocorticoid) (with or without baricitinib, a Janus kinase inhibitor) on the day of hospitalization (I); and COVID-19 patients at 48 h post treatment (T). Results showed that circulatory miR-6741-5p expression levels were significantly different between groups C and I (p < 0.0000001); I and T (p < 0.0000001); and C and T (p = 0.001). Our ANOVA model estimated that all patients with less than 12.42 Log2 CPM had a short LOS, or a good prognosis, whereas all patients with over 12.42 Log2 CPM had a long LOS, or a poor prognosis. In sum, we show that circulatory miR-6741-5p may serve as a prognostic biomarker effectively predicting mortality risk and LOS of hospitalized COVID-19 patients.

Identification of neoplasm-specific signatures of miRNA interactions by employing a systems biology approach

MicroRNAs represent major regulatory components of the disease epigenome and they constitute powerful biomarkers for the accurate diagnosis and prognosis of various diseases, including cancers. The advent of high-throughput technologies facilitated the generation of a vast amount of miRNA-cancer association data. Computational approaches have been utilized widely to effectively analyze and interpret these data towards the identification of miRNA signatures for diverse types of cancers. Herein, a novel computational workflow was applied to discover core sets of miRNA interactions for the major groups of neoplastic diseases by employing network-based methods. To this end, miRNA-cancer association data from four comprehensive publicly available resources were utilized for constructing miRNA-centered networks for each major group of neoplasms. The corresponding miRNA-miRNA interactions were inferred based on shared functionally related target genes. The topological attributes of the generated networks were investigated in order to detect clusters of highly interconnected miRNAs that form core modules in each network. Those modules that exhibited the highest degree of mutual exclusivity were selected from each graph. In this way, neoplasm-specific miRNA modules were identified that could represent potential signatures for the corresponding diseases.

Establishment of a male fertility prediction model with sperm RNA markers in pigs as a translational animal model

BACKGROUND

Male infertility is an important issue that causes low production in the animal industry. To solve the male fertility crisis in the animal industry, the prediction of sperm quality is the most important step. Sperm RNA is the potential marker for male fertility prediction. We hypothesized that the expression of functional genes related to fertilization will be the best target for male fertility prediction markers. To investigate optimum male fertility prediction marker, we compared target genes expression level and a wide range of field data acquired from artificial insemination of boar semen.

RESULTS

Among the genes related to acrosomal vesicle exocytosis and sperm-oocyte fusion, equatorin (EQTN), zona pellucida sperm-binding protein 4 (ZP4), and sperm acrosome membrane-associated protein 3 exhibited high accuracy (70%, 90%, and 70%, respectively) as markers to evaluate male fertility. Combinations of EQTN-ZP4, ZP4-protein unc-13 homolog B, and ZP4-regulating synaptic membrane exocytosis protein 1 (RIMS1) showed the highest prediction value, and all these markers are involved in the acrosome reaction.

CONCLUSION

The EQTN-ZP4 model was efficient in clustering the high-fertility group and may be useful for selection of animal that has superior fertility in the livestock industry. Compared to the EQTN-ZP4 model, the ZP4-RIMS1 model was more efficient in clustering the low-fertility group and may be useful in the diagnosis of male infertility in humans and other animals. The appointed translational animal model and established biomarker combination can be widely used in various scientific fields such as biomedical science.

Physical exercise and the functions of microRNAs

MicroRNAs (miRNAs) control RNA translation and are a class of small, tissue-specific, non-protein-coding RNAs that maintain cellular homeostasis through negative gene regulation. Maintenance of the physiological environment depends on the proper control of miRNA expression, as these molecules influence almost all genetic pathways, from the cell cycle checkpoint to cell proliferation and apoptosis, with a wide range of target genes. Dysregulation of the expression of miRNAs is correlated with several types of diseases, acting as regulators of cardiovascular functions, myogenesis, adipogenesis, osteogenesis, hepatic lipogenesis, and important brain functions. miRNAs can be modulated by environmental factors or external stimuli, such as physical exercise, and can eventually induce specific and adjusted changes in the transcriptional response. Physical exercise is used as a preventive and non-pharmacological treatment for many diseases. It is well established that physical exercise promotes various benefits in the human body such as muscle hypertrophy, mental health improvement, cellular apoptosis, weight loss, and inhibition of cell proliferation. This review highlights the current knowledge on the main miRNAs altered by exercise in the skeletal muscle, cardiac muscle, bone, adipose tissue, liver, brain, and body fluids. In addition, knowing the modifications induced by miRNAs and relating them to the results of prescribed physical exercise with different protocols and intensities can serve as markers of physical adaptation to training and responses to the effects of physical exercise for some types of chronic diseases. This narrative review consists of randomized exercise training experiments with humans and/or animals, combined with analyses of miRNA modulation.

Multi-Method Diagnosis of Blood Microscopic Sample for Early Detection of Acute Lymphoblastic Leukemia Based on Deep Learning and Hybrid Techniques

Leukemia is one of the most dangerous types of malignancies affecting the bone marrow or blood in all age groups, both in children and adults. The most dangerous and deadly type of leukemia is acute lymphoblastic leukemia (ALL). It is diagnosed by hematologists and experts in blood and bone marrow samples using a high-quality microscope with a magnifying lens. Manual diagnosis, however, is considered slow and is limited by the differing opinions of experts and other factors. Thus, this work aimed to develop diagnostic systems for two Acute Lymphoblastic Leukemia Image Databases (ALL_IDB1 and ALL_IDB2) for the early detection of leukemia. All images were optimized before being introduced to the systems by two overlapping filters: the average and Laplacian filters. This study consists of three proposed systems as follows: the first consists of the artificial neural network (ANN), feed forward neural network (FFNN), and support vector machine (SVM), all of which are based on hybrid features extracted using Local Binary Pattern (LBP), Gray Level Co-occurrence Matrix (GLCM) and Fuzzy Color Histogram (FCH) methods. Both ANN and FFNN reached an accuracy of 100%, while SVM reached an accuracy of 98.11%. The second proposed system consists of the convolutional neural network (CNN) models: AlexNet, GoogleNet, and ResNet-18, based on the transfer learning method, in which deep feature maps were extracted and classified with high accuracy. All the models obtained promising results for the early detection of leukemia in both datasets, with an accuracy of 100% for the AlexNet, GoogleNet, and ResNet-18 models. The third proposed system consists of hybrid CNN–SVM technologies, consisting of two blocks: CNN models for extracting feature maps and the SVM algorithm for classifying feature maps. All the hybrid systems achieved promising results, with AlexNet + SVM achieving 100% accuracy, Goog-LeNet + SVM achieving 98.1% accuracy, and ResNet-18 + SVM achieving 100% accuracy.

Insomnia subtypes characterised by objective sleep duration and NREM spectral power and the effect of acute sleep restriction: an exploratory analysis

Insomnia disorder (ID) is a heterogeneous disorder with proposed subtypes based on objective sleep duration. We speculated that insomnia subtyping with additional power spectral analysis and measurement of response to acute sleep restriction may be informative in overall assessment of ID. To explore alternative classifications of ID subtypes, insomnia patients (n = 99) underwent two consecutive overnight sleep studies: (i) habitual sleep opportunity (polysomnography, PSG) and, (ii) two hours less sleep opportunity (electroencephalography, EEG), with the first night compared to healthy controls (n = 25). ID subtypes were derived from data-driven classification of PSG, EEG spectral power and interhemispheric EEG asymmetry index. Three insomnia subtypes with different sleep duration and NREM spectral power were identified. One subtype (n = 26) had shorter sleep duration and lower NREM delta power than healthy controls (short-sleep delta-deficient; SSDD), the second subtype (n = 51) had normal sleep duration but lower NREM delta power than healthy controls (normal-sleep delta-deficient; NSDD) and a third subtype showed (n = 22) no difference in sleep duration or delta power from healthy controls (normal neurophysiological sleep; NNS). Acute sleep restriction improved multiple objective sleep measures across all insomnia subtypes including increased delta power in SSDD and NSDD, and improvements in subjective sleep quality for SSDD (p = 0.03), with a trend observed for NSDD (p = 0.057). These exploratory results suggest evidence of novel neurophysiological insomnia subtypes that may inform sleep state misperception in ID and with further research, may provide pathways for personalised care.

CRPGCN: predicting circRNA-disease associations using graph convolutional network based on heterogeneous network

BACKGROUND

The existing studies show that circRNAs can be used as a biomarker of diseases and play a prominent role in the treatment and diagnosis of diseases. However, the relationships between the vast majority of circRNAs and diseases are still unclear, and more experiments are needed to study the mechanism of circRNAs. Nowadays, some scholars use the attributes between circRNAs and diseases to study and predict their associations. Nonetheless, most of the existing experimental methods use less information about the attributes of circRNAs, which has a certain impact on the accuracy of the final prediction results. On the other hand, some scholars also apply experimental methods to predict the associations between circRNAs and diseases. But such methods are usually expensive and time-consuming. Based on the above shortcomings, follow-up research is needed to propose a more efficient calculation-based method to predict the associations between circRNAs and diseases.

RESULTS

In this study, a novel algorithm (method) is proposed, which is based on the Graph Convolutional Network (GCN) constructed with Random Walk with Restart (RWR) and Principal Component Analysis (PCA) to predict the associations between circRNAs and diseases (CRPGCN). In the construction of CRPGCN, the RWR algorithm is used to improve the similarity associations of the computed nodes with their neighbours. After that, the PCA method is used to dimensionality reduction and extract features, it makes the connection between circRNAs with higher similarity and diseases closer. Finally, The GCN algorithm is used to learn the features between circRNAs and diseases and calculate the final similarity scores, and the learning datas are constructed from the adjacency matrix, similarity matrix and feature matrix as a heterogeneous adjacency matrix and a heterogeneous feature matrix.

CONCLUSIONS

After 2-fold cross-validation, 5-fold cross-validation and 10-fold cross-validation, the area under the ROC curve of the CRPGCN is 0.9490, 0.9720 and 0.9722, respectively. The CRPGCN method has a valuable effect in predict the associations between circRNAs and diseases.

Leveraging publicly available coronavirus data to identify new therapeutic targets for COVID-19

Many important questions remain regarding severe acute respiratory syndrome coronavirus-2 (SARS-CoV-2), the viral pathogen responsible for COVID-19. These questions include the mechanisms explaining the high percentage of asymptomatic but highly infectious individuals, the wide variability in disease susceptibility, and the mechanisms of long-lasting debilitating effects. Bioinformatic analysis of four coronavirus datasets representing previous outbreaks (SARS-CoV-1 and MERS-CoV), as well as SARS-CoV-2, revealed evidence of diverse host factors that appear to be coopted to facilitate virus-induced suppression of interferon-induced innate immunity, promotion of viral replication and subversion and/or evasion of antiviral immune surveillance. These host factors merit further study given their postulated roles in COVID-19-induced loss of smell and brain, heart, vascular, lung, liver, and gut dysfunction.

A deep network designed for segmentation and classification of leukemia using fusion of the transfer learning models

White blood cells (WBCs) are a portion of the immune system which fights against germs. Leukemia is the most common blood cancer which may lead to death. It occurs due to the production of a large number of immature WBCs in the bone marrow that destroy healthy cells. To overcome the severity of this disease, it is necessary to diagnose the shapes of immature cells at an early stage that ultimately reduces the modality rate of the patients. Recently different types of segmentation and classification methods are presented based upon deep-learning (DL) models but still have some limitations. This research aims to propose a modified DL approach for the accurate segmentation of leukocytes and their classification. The proposed technique includes two core steps: preprocessing-based classification and segmentation. In preprocessing, synthetic images are generated using a generative adversarial network (GAN) and normalized by color transformation. The optimal deep features are extracted from each blood smear image using pretrained deep models i.e., DarkNet-53 and ShuffleNet. More informative features are selected by principal component analysis (PCA) and fused serially for classification. The morphological operations based on color thresholding with the deep semantic method are utilized for leukemia segmentation of classified cells. The classification accuracy achieved with ALL-IDB and LISC dataset is 100% and 99.70% for the classification of leukocytes i.e., blast, no blast, basophils, neutrophils, eosinophils, lymphocytes, and monocytes, respectively. Whereas semantic segmentation achieved 99.10% and 98.60% for average and global accuracy, respectively. The proposed method achieved outstanding outcomes as compared to the latest existing research works.

Multiclass diagnosis of stages of Alzheimer's disease using linear discriminant analysis scoring for multimodal data

Alzheimer's disease (AD) is a progressive neurodegenerative disease, and mild cognitive impairment (MCI) is a transitional stage between normal control (NC) and AD. A multiclass classification of AD is a difficult task because there are multiple similarities between neighboring groups. The performance of classification can be improved by using multimodal data, but the improvement could be limited with inefficient fusion of multimodal data. This study aims to develop a framework for AD multiclass diagnosis with a linear discriminant analysis (LDA) scoring method to fuse multimodal data more efficiently. Magnetic resonance imaging, positron emission tomography, cerebrospinal fluid biomarkers, and genetic features were first preprocessed by performing age correction, feature selection, and feature reduction. Then, they were individually scored using LDA, and the scores that represent the AD pathological progress in different modalities were obtained. Finally, an extreme learning machine-based decision tree was established to perform multiclass diagnosis using these scores. The experiments were conducted on the AD Neuroimaging Initiative dataset, and accuracies of 66.7% and 57.3% and F1-scores of 64.9% and 55.7% were achieved in three- and four-way classifications, respectively. The results also showed that the proposed framework achieved a better performance than the method that did not score multimodal data and the methods in previous studies, thereby indicating that the LDA scoring strategy is an efficient way for multimodalities fusion in AD multiclass classification.

Copper Content Inversion of Copper Ore Based on Reflectance Spectra and the VTELM Algorithm

Copper is an important national resource, which is widely used in various sectors of the national economy. The traditional detection of copper content in copper ore has the disadvantages of being time-consuming and high cost. Due to the many drawbacks of traditional detection methods, this paper proposes a new method for detecting copper content in copper ore, that is, through the spectral information of copper ore content detection method. First of all, we use chemical methods to analyze the copper content in a batch of copper ores, and accurately obtain the copper content in those ores. Then we do spectrometric tests on this batch of copper ore, and get accurate spectral data of copper ore. Based on the data obtained, we propose a new two hidden layer extreme learning machine algorithm with variable hidden layer nodes and use the regularization standard to constrain the extreme learning machine. Finally, the prediction model of copper content in copper ore is established by using the algorithm. Experiments show that this method of detecting copper ore content using spectral information is completely feasible, and the algorithm proposed in this paper can detect the copper content in copper ores faster and more accurately.