Predicting drug-target interactions using matrix factorization with self-paced learning and dual similarity information.

BACKGROUND: Drug repositioning (DR) refers to a method used to find new targets for existing drugs. This method can effectively reduce the development cost of drugs, save time on drug development, and reduce the risks of drug design. The traditional experimental methods related to DR are time-consuming, expensive, and have a high failure rate. Several computational methods have been developed with the increase in data volume and computing power. In the last decade, matrix factorization (MF) methods have been widely used in DR issues. However, these methods still have some challenges. (1) The model easily falls into a bad local optimal solution due to the high noise and high missing rate in the data. (2) Single similarity information makes the learning power of the model insufficient in terms of identifying the potential associations accurately. OBJECTIVE: We proposed self-paced learning with dual similarity information and MF (SPLDMF), which introduced the self-paced learning method and more information related to drugs and targets into the model to improve prediction performance. METHODS: Combining self-paced learning first can effectively alleviate the model prone to fall into a bad local optimal solution because of the high noise and high data missing rate. Then, we incorporated more data into the model to improve the model's capacity for learning. RESULTS: Our model achieved the best results on each dataset tested. For example, the area under the receiver operating characteristic curve and the precision-recall curve of SPLDMF was 0.982 and 0.815, respectively, outperforming the state-of-the-art methods. CONCLUSION: The experimental results on five benchmark datasets and two extended datasets demonstrated the effectiveness of our approach in predicting drug-target interactions.

Efficacy of first-line treatment options beyond RET-TKIs in advanced RET-rearranged non-small cell lung cancer: A multi-center real-world study.

BACKGROUND: Although RET-tyrosine kinase inhibitors (RET-TKIs) are the preferred first-line therapy for advanced RET-arranged NSCLC, most patients cannot afford them. In this population, bevacizumab, immunotherapy, and chemotherapy are the most commonly used regimens. However, the optimal scheme beyond RET-TKIs has not been defined in the first-line setting. METHODS: This retrospective study included 86 stage IV NSCLC patients harboring RET rearrangement from six cancer centers between May 2017 and October 2022. RET-TKIs, chemotherapy, or one of the combination therapies (including immune checkpoint inhibitor (ICI) combined with chemotherapy (I + C), bevacizumab combined with chemotherapy (B + C), ICI and bevacizumab combined with chemotherapy (I + B + C)), were used as the first-line therapeutics. The clinical outcomes and safety were evaluated. RESULTS: Fourteen of the 86 patients received RET-TKIs, 57 received combination therapies, and 15 received chemotherapy alone. Their medium PFS (mPFS) were 16.92 months (95% CI: 5.9-27.9 months), 8.7 months (95% CI: 6.5-11.0 months), and 5.55 months (95% CI: 2.4-8.7 months) respectively. Among all the combination schemes, B + C (p = 0.007) or I + B + C (p = 0.025) gave beneficial PFS compared with chemotherapy, while I + C treatment (p = 0.169) generated comparable PFS with chemotherapy. In addition, I + B + C treatment had a numerically longer mPFS (12.21 months) compared with B + C (8.74 months) or I + C (7.89 months) schemes. In terms of safety, I + B + C treatment led to the highest frequency of hematological toxicity (50%) and vomiting (75%), but no ≥G3 adverse effect was observed. CONCLUSIONS: I + B + C might be a preferred option beyond RET-TKIs in the first-line therapy of RET-arranged NSCLC. Combination with Bevacizumab rather than with ICIs offered favorable survival compared with chemotherapy alone.

Bias-free driven ion assisted photoelectrochemical system for sustainable wastewater treatment.

Photoelectrochemical (PEC) systems have emerged as a prominent renewable energy-based technology for wastewater treatment, offering sustainable advantages such as eliminating dependence on fossil fuels or grid electricity compared to traditional electrochemical treatment methods. However, previous PEC systems often overlook the potential of ions present in wastewater as an alternative to externally applied bias voltage for enhancing carrier separation efficiency. Here we report a bias-free driven ion assisted photoelectrochemical (IAPEC) system by integration of an electron-ion acceptor cathode, which leverages its fast ion-electron coupling capability to significantly enhance the separation of electrons and holes at the photoanode. We demonstrate that Prussian blue analogues (PBAs) can serve as robust and reversible electron-ion acceptors that provide reaction sites for photoelectron coupling cations, thus driving the hole oxidation to produce strong oxidant free radicals at photoanode. Our IAPEC system exhibits superior degradation performance in wastewater containing chloride medium. This indicates that, in addition to the cations (e.g., Na+) accelerating the electron transfer rate, the presence of Cl- ions further enhance efficient and sustainable wastewater treatment. This work highlights the potential of utilizing abundant sodium chloride in seawater as a cost-effective additive for wastewater treatment, offering crucial insights into the use of local materials for effective, low-carbon, and sustainable treatment processes.

Palladium-Catalyzed Decarbonylative Annulation of 2-Arylbenzoic Acids with Internal Alkynes toward Phenanthrenes.

A palladium-catalyzed decarbonylative annulation of 2-arylbenzoic acids with internal alkynes via C(sp2)-H activation has been developed. A series of phenanthrenes were produced in moderate to good yield with good functional group tolerance. The mechanism study indicated that the C(sp2)-H activation should be the rate-determining step during the reaction.

Recent progress of self-immobilizing and self-precipitating molecular fluorescent probes for higher-spatial-resolution imaging.

Flourished in the past two decades, fluorescent probe technology provides researchers with accurate and efficient tools for in situ imaging of biomarkers in living cells and tissues and may play a significant role in clinical diagnosis and treatment such as biomarker detection, fluorescence imaging-guided surgery, and photothermal/photodynamic therapy. In situ imaging of biomarkers depends on the spatial resolution of molecular probes. Nevertheless, the majority of currently available molecular fluorescent probes suffer from the drawback of diffusing from the target region. This leads to a rapid attenuation of the fluorescent signal over time and a reduction in spatial resolution. Consequently, the diffused fluorescent signal cannot accurately reflect the in situ information of the target. Self-immobilizing and self-precipitating molecular fluorescent probes can be used to overcome this problem. These probes ensure that the fluorescent signal remains at the location where the signal is generated for a long time. In this review, we introduce the development history of the two types of probes and classify them in detail according to different design strategies. In addition, we compare their advantages and disadvantages, summarize some representative studies conducted in recent years, and propose prospects for this field.

Nonfunctional ectopic adrenocortical carcinoma in the lung: A case report and literature review.

Background: Ectopic adrenocortical tissues and neoplasms are rare and usually found in the genitourinary system and abdominal cavity. The thorax is an extremely rare ectopic site. Here, we report the first case of nonfunctional ectopic adrenocortical carcinoma (ACC) in the lung. Case presentation: A 71-year-old Chinese man presented with vague left-sided chest pain and irritable cough for 1 month. Thoracic computed tomography revealed a heterogeneously enhancing 5.3 × 5.8 × 6.0-cm solitary mass in the left lung. Radiological findings suggested a benign tumor. The tumor was surgically excised upon detection. Histopathological examination using hematoxylin and eosin staining showed that the cytoplasm of the tumor cells was rich and eosinophilic. Immunohistochemical profiles (inhibin-a+, melan-A+, Syn+) indicated that the tumor had an adrenocortical origin. The patient showed no symptoms of hormonal hypersecretion. The final pathological diagnosis was non-functional ectopic ACC. The patient was disease-free for 22 months and is still under follow-up. Conclusions: Nonfunctional ectopic ACC in the lung is an extremely rare neoplasm that can be easily misdiagnosed as primary lung cancer or lung metastasis, both preoperatively and on postoperative pathological examination. This report may provide clues to clinicians and pathologists regarding the diagnosis and treatment of nonfunctional ectopic ACC.

Gram-Scale Room-Temperature Synthesis of Solid-State Fluorescent Carbon Nanodots for Bright Electroluminescent Light Emitting Diodes.

The reaction conditions of high temperature and high pressure will introduce structural defects, high energy consumption, and security risks, severely hindering the industrial application of organic carbon nanodots (CDs). Moreover, the aggregation caused quenching effect also fundamentally limits the CDs based electroluminescent light emitting diodes (LEDs). Herein, for the first time, a rapid one-step room temperature synthetic strategy is introduced to prepare highly emissive solid-state-fluorescent CDs (RT-CDs). A strong oxidizing agent, potassium periodate (KIO4 ), is adopted as a catalyst to facilitate the cyclization of o-phenylenediamine and 4-dimethylamino phenol in aqueous solution at room temperature for only 5 min. The resultant organic molecule, 2-(dimethylamino) phenazine, will self-assemble kinetically to generate supramolecular-structure CDs during crystallization. The elaborately arranged supramolecular structure (J aggregates) endows CDs with intense solid-state-fluorescence. Density functional theory (DFT) calculation shows that the excited state of RT-CDs exhibits charge transfer characteristic owing to the unique donor-Π-acceptor structure. A high-performance monochrome RT-CDs based electroluminescent LEDs (2967 cd m-2 and 1.38 cd A-1 ) were fabricated via systematic optimizations of device engineering. This work provides a concrete and feasible avenue for the rapid and massive preparation of CDs, advancing the commercialization of CDs based optoelectronic devices.

Pharmacokinetics and Comparative Bioavailability of Test or Reference Capecitabine and Discrepant Pharmacokinetics Among Various Tumors in Chinese Solid Cancer Patients.

The main objective of this study was to compare the pharmacokinetic (PK) bioequivalence of two capecitabine tablets and explore the different PK profiles of various tumors in Chinese patients with cancer. All 76 patients with a confirmed cancer diagnosis were included in this study. A single dose of 2000 mg of test or reference capecitabine (Xeloda, Hoffmann-La Roche) was orally administered postprandially. After 24 hours of washout, the patients were administered the test or the reference capecitabine alternately. PK samples were taken at the time of predose up to 6 hours postdose. Bioequivalence evaluation was performed using the geometric mean ratios of peak concentration in plasma (Cmax) , area under the concentration-time curve from time 0 to 6 h (AUC0-t) , and area under the concentration-time curve from time 0 to infinity (AUC0-∞ ) for capecitabine and 5-fluorouracil (5-FU). In this study, 90% confidence intervals of test/reference mean ratios of Cmax , AUC0-t , AUC0-∞ of capecitabine and 5-FU were in the range of 80%-125%. Both the test and reference capecitabine regimens were well tolerated in this study. Furthermore, we found that patients with esophageal-gastrointestinal cancers had higher exposure to capecitabine and a shorter time to Cmax (Tmax) than those with breast cancer. In conclusion, a single oral dose of 2000 mg of test capecitabine tablets after postprandial administration was bioequivalent to the reference drug.

Improved Computational Drug-Repositioning by Self-Paced Non-Negative Matrix Tri-Factorization.

Drug repositioning (DR) is a strategy to find new targets for existing drugs, which plays an important role in reducing the costs, time, and risk of traditional drug development. Recently, the matrix factorization approach has been widely used in the field of DR prediction. Nevertheless, there are still two challenges: 1) Learning ability deficiencies, the model cannot accurately predict more potential associations. 2) Easy to fall into a bad local optimal solution, the model tends to get a suboptimal result. In this study, we propose a self-paced non-negative matrix tri-factorization (SPLNMTF) model, which integrates three types of different biological data from patients, genes, and drugs into a heterogeneous network through non-negative matrix tri-factorization, thereby learning more information to improve the learning ability of the model. In the meantime, the SPLNMTF model sequentially includes samples into training from easy (high-quality) to complex (low-quality) in the soft weighting way, which effectively alleviates falling into a bad local optimal solution to improve the prediction performance of the model. The experimental results on two real datasets of ovarian cancer and acute myeloid leukemia (AML) show that SPLNMTF outperforms the other eight state-of-the-art models and gets better prediction performance in drug repositioning. The data and source code are available at: https://github.com/qi0906/SPLNMTF.

Synthesis of Fluoride-Substituted Layered Perovskites ZnMoO4 with an Enhanced Photocatalytic Activity.

Oxyfluorides possess considerable attention for their multiple excellent properties, but the conventional high-temperature solid-state syntheses have seen bottlenecks in the synthesis of new compounds. Herein, we report a novel layered oxyfluoride ZnMoO4:F, which is prepared by a facile hydrothermal method using ZnF2 as the fluoride source. The fluoride anions are successfully introduced into the oxygen sublattice, which is confirmed by a combined analysis using XRD, STEM, and TGA techniques. The as-synthesized ZnMoO4:F has an absorption edge at around 550 nm, indicating a red shift of Eg to the visible region compared to the oxide counterpart. The layered oxyfluoride exhibits an enhanced photocatalytic active for hydrogen evolution under simulated sunlight (λ > 350 nm), and the activity of ZnMoO4:F (651.9 µmol g-1) was 2 times higher than that of ZnMoO4 (309.7 µmol g-1). Further electrochemical analysis has shown that the conduction band position plays a critical role in the high performances of ZnMoO4:F. This work sheds new light on the future design and synthesis of novel fluoride-doped materials for photocatalysis applications.

Polyethyleneimine-assisted co-deposition of polydopamine coating with enhanced stability and efficient secondary modification.

The stability and grafting efficiency are important for polydopamine (pDA) coatings used as platforms for secondary grafting. In this work, polyethyleneimine (PEI) was co-deposited with dopamine on various materials (PP, PTFE and PVC), then immersed in a 1.0 M HCl solution or 1.0 M NaOH solution to investigate the detachment of the coatings using UV-vis spectroscopy, SEM, FTIR spectroscopy and XPS, and the effect of PEI molecular weight on the secondary grafting of heparin on the pDA/PEI coating was investigated through clotting time tests. The results showed that the detachment rates of the pDA/PEI coating (14.6%, 23.7%) co-deposited on PTFE in 1.0 M HCl or 1.0 M NaOH solutions were both lower than that of the pDA coating (35.0%, 74.6%), indicating that pDA/PEI coatings could better remain on substrates in a 1.0 M NaOH solution. Besides, pDA/PEI coatings on a PP membrane with both a higher deposition density and stability could be obtained when the mass ratio of DA/PEI was 2 : 1-1 : 1 and PEI molecular weight was 600 Da. After grafting heparin, it was found that the pDA/PEI coating with lower molecular weight (600 Da and 1800 Da) PEI could achieve a higher grafting density of heparin with a longer clotting time. Thus, the results provided better understanding about the stability of pDA/PEI coatings and efficiency of heparin grafting.

Corrigendum: Predicting multiple types of associations between miRNAs and diseases based on graph regularized weighted tensor decomposition.

[This corrects the article DOI: 10.3389/fbioe.2022.911769.].

Predicting multiple types of miRNA-disease associations using adaptive weighted nonnegative tensor factorization with self-paced learning and hypergraph regularization.

More and more evidence indicates that the dysregulations of microRNAs (miRNAs) lead to diseases through various kinds of underlying mechanisms. Identifying the multiple types of disease-related miRNAs plays an important role in studying the molecular mechanism of miRNAs in diseases. Moreover, compared with traditional biological experiments, computational models are time-saving and cost-minimized. However, most tensor-based computational models still face three main challenges: (i) easy to fall into bad local minima; (ii) preservation of high-order relations; (iii) false-negative samples. To this end, we propose a novel tensor completion framework integrating self-paced learning, hypergraph regularization and adaptive weight tensor into nonnegative tensor factorization, called SPLDHyperAWNTF, for the discovery of potential multiple types of miRNA-disease associations. We first combine self-paced learning with nonnegative tensor factorization to effectively alleviate the model from falling into bad local minima. Then, hypergraphs for miRNAs and diseases are constructed, and hypergraph regularization is used to preserve the high-order complex relations of these hypergraphs. Finally, we innovatively introduce adaptive weight tensor, which can effectively alleviate the impact of false-negative samples on the prediction performance. The average results of 5-fold and 10-fold cross-validation on four datasets show that SPLDHyperAWNTF can achieve better prediction performance than baseline models in terms of Top-1 precision, Top-1 recall and Top-1 F1. Furthermore, we implement case studies to further evaluate the accuracy of SPLDHyperAWNTF. As a result, 98 (MDAv2.0) and 98 (MDAv2.0-2) of top-100 are confirmed by HMDDv3.2 dataset. Moreover, the results of enrichment analysis illustrate that unconfirmed potential associations have biological significance.

Incidence risk of peripheral edema in cancer patients treated with PD-1/PD-L1 inhibitors: A PRISMA guideline systematic review and meta-analysis.

PURPOSE: To elucidate the relationship between peripheral edema and programmed cell death-1/programmed cell death ligand 1 (PD-1/PD-L1) inhibitors, the meta-analysis was performed. METHOD: Following the guidelines of Preferred Reporting Items for Systematic Reviews and Meta-analyses, all-grade and grade 3-5 of peripheral edema data extracted from clinical trials were taken into account for the final comprehensive assessments. RESULTS: Twenty-seven PD-1/PD-L1-related clinical trials with peripheral edema data were collected. Compared with chemotherapy (PD-1/PD-L1 vs chemotherapy), the risk of developing peripheral edema for all-grade was much lower (odds ratio [OR] = 0.36, 95% confidence interval [CI]: [0.23, 0.56], Z = 4.55 [P < .00001]). When PD-1/PD-L1 plus chemotherapy were compared with chemotherapy, no significant analysis results for all-grade was found (OR = 1.15, 95% CI:[0.93, 1.44], I2 = 25%, Z = 1.27 [P = .20]). Similar risk trends could also be found when the incidence risk of peripheral edema for grade 3-5 was evaluated. No obvious publication bias was identified throughout the total analysis process. CONCLUSION: The effect of PD-1/PD-L1 inhibitor on the risk of developing peripheral edema was weaker than that of chemotherapy, and the combination with chemotherapy slightly increased the incidence risk of developing peripheral edema without statistical significance.

Predicting Multiple Types of Associations Between miRNAs and Diseases Based on Graph Regularized Weighted Tensor Decomposition.

Many studies have indicated miRNAs lead to the occurrence and development of diseases through a variety of underlying mechanisms. Meanwhile, computational models can save time, minimize cost, and discover potential associations on a large scale. However, most existing computational models based on a matrix or tensor decomposition cannot recover positive samples well. Moreover, the high noise of biological similarity networks and how to preserve these similarity relationships in low-dimensional space are also challenges. To this end, we propose a novel computational framework, called WeightTDAIGN, to identify potential multiple types of miRNA-disease associations. WeightTDAIGN can recover positive samples well and improve prediction performance by weighting positive samples. WeightTDAIGN integrates more auxiliary information related to miRNAs and diseases into the tensor decomposition framework, focuses on learning low-rank tensor space, and constrains projection matrices by using the L 2,1 norm to reduce the impact of redundant information on the model. In addition, WeightTDAIGN can preserve the local structure information in the biological similarity network by introducing graph Laplacian regularization. Our experimental results show that the sparser datasets, the more satisfactory performance of WeightTDAIGN can be obtained. Also, the results of case studies further illustrate that WeightTDAIGN can accurately predict the associations of miRNA-disease-type.

Rapid detection of SARS-CoV-2 RNA in saliva via Cas13.

Rapid nucleic acid testing is central to infectious disease surveillance. Here, we report an assay for rapid COVID-19 testing and its implementation in a prototype microfluidic device. The assay, which we named DISCoVER (for diagnostics with coronavirus enzymatic reporting), involves extraction-free sample lysis via shelf-stable and low-cost reagents, multiplexed isothermal RNA amplification followed by T7 transcription, and Cas13-mediated cleavage of a quenched fluorophore. The device consists of a single-use gravity-driven microfluidic cartridge inserted into a compact instrument for automated running of the assay and readout of fluorescence within 60 min. DISCoVER can detect severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) in saliva with a sensitivity of 40 copies µl-1, and was 94% sensitive and 100% specific when validated (against quantitative PCR) using total RNA extracted from 63 nasal-swab samples (33 SARS-CoV-2-positive, with cycle-threshold values of 13-35). The device correctly identified all tested clinical saliva samples (10 SARS-CoV-2-positive out of 13, with cycle-threshold values of 23-31). Rapid point-of-care nucleic acid testing may broaden the use of molecular diagnostics.

Study of the microstructure of chitosan aerogel beads prepared by supercritical CO2 drying and the effect of long-term storage.

In order to investigate the pore properties and effect of storage time on the microstructure of CO2-dried aerogels, chitosan aerogel beads were obtained from chitosan hydrogels with an initial concentration in the range of 1.5-3.0 wt% through SCCO2 drying and freeze-drying (as a comparison). The SCCO2-dried chitosan aerogels showed a three-dimensional network structure, and had higher BET surface area (200 m2 g-1) and higher crystallinity (0.62/XRD, 0.80/ATR-FTIR) than the freeze-dried aerogels. The stability of the microstructure of the SCCO2-dried chitosan aerogel beads during 10 months was studied. The BET surface area of the aerogel beads at each concentration declined by 30.5% at 2 months, 56.7% at 6 months and 67.2% at 10 months. Accelerated aging tests of the chitosan aerogel beads were carried out to study the effect of humidity on the chitosan aerogel beads. The average diameter of the chitosan aerogel decreased from 2.3 mm to 0.9 mm when stored at 65 °C with 90% relative humidity (RH). In contrast, there was no obvious change during storage at 65 °C with 20% RH. The amount of adsorbed water increased from 4% to 12% at 65 °C with 90% RH for 96 h, and the bound water content of the aerogel beads gradually increased. This study demonstrates that SCCO2-dried chitosan aerogel beads could be better at maintaining their mesoporous structure, and the adsorption of water from the surrounding air had a significant effect on the microstructure and shrinkage of the chitosan aerogel beads.

Risk of Rash in PD-1 or PD-L1-Related Cancer Clinical Trials: A Systematic Review and Meta-Analysis.

Background: Given that immune-related rash was the most frequently reported PD-1 or PD-L1-related skin toxicity, this systematic review and meta-analysis were conducted to elucidate its incidence risk. Methods: The meta-analysis was carried out according to the PRISMA guidelines. The random effect model was used in the process of all analyses. Skin rash of all grades and grades 3-5 were calculated and gathered in the final comprehensive analyses. Results: The study included 86 clinical trials classified into 15 groups. Compared with chemotherapy, PD-1 or PD-L1 inhibitors significantly strengthened the risk of developing rash across all grades (OR = 1.66, 95% CI: [1.31, 2.11]; p < 0.0001). This trend was significantly stronger when the control group was placebo (OR = 2.62, 95% CI: [1.88, 3.65]; p < 0.00001). Similar results were observed when PD-1 or PD-L1 inhibitors were given together with chemotherapy (OR = 1.87, 95% CI: [1.59, 2.20]; p < 0.00001), even in patients with grades 3-5. As with other combination therapies, the risk of developing rash for all grades was enhanced when PD-1 or PD-L1 was given together with chemotherapy as the second-line option (OR = 2.98, 95% CI: [1.87, 4.75]; p=0.05). No statistically significant differences could be found in skin rash between the PD-1 and PD-L1-related subgroups. Conclusion: Whether PD-1 or PD-L1 inhibitors were given alone or together with others, the risk of developing rash would be enhanced. Furthermore, the risk of developing rash appeared to be higher when PD-1 or PD-L1 inhibitors together with other antitumor drugs were given as the second-line options. No statistically significant results of developing rash between PD-1 and PD-L1 subgroups were obtained owing to the participation of PD-1 or PD-L1 inhibitors.

Sparse principal component analysis based on genome network for correcting cell type heterogeneity in epigenome-wide association studies.

In epigenome-wide association studies (EWAS), the mixed methylation expression caused by the combination of different cell types may lead the researchers to find the false methylation site related to the phenotype of interest. To correct the EWAS false discovery, some non-reference models based on sparse principal component analysis (sparse PCA) have been proposed. These models assume that all methylation sites have the same priori probability in each PC load. However, it is known that there already has gene network structure corresponding to the methylation site. How to integrate this genome network knowledge into the sparse PCA models to enhance the performance of existing models is an open research problem. We introduce GN-ReFAEWAS, a non-reference analysis model which integrates the prior gene network structure into the PCA framework to control the false discovery in EWAS. We used one simulated data set, three real data sets, and three additional tests for experiments and compared with four existing models. Experimental results show that the GN-ReFAEWAS model is better than the existing model by 2-90% in the indicators of sensitivity, specificity, genomic control factor λ, and correlation coefficient factor cov with known cell phenotype ratio.

Dynamic Meta-data Network Sparse PCA for Cancer Subtype Biomarker Screening.

Previous research shows that each type of cancer can be divided into multiple subtypes, which is one of the key reasons that make cancer difficult to cure. Under these circumstances, finding a new target gene of cancer subtypes has great significance on developing new anti-cancer drugs and personalized treatment. Due to the fact that gene expression data sets of cancer are usually high-dimensional and with high noise and have multiple potential subtypes' information, many sparse principal component analysis (sparse PCA) methods have been used to identify cancer subtype biomarkers and subtype clusters. However, the existing sparse PCA methods have not used the known cancer subtype information as prior knowledge, and their results are greatly affected by the quality of the samples. Therefore, we propose the Dynamic Metadata Edge-group Sparse PCA (DM-ESPCA) model, which combines the idea of meta-learning to solve the problem of sample quality and uses the known cancer subtype information as prior knowledge to capture some gene modules with better biological interpretations. The experiment results on the three biological data sets showed that the DM-ESPCA model can find potential target gene probes with richer biological information to the cancer subtypes. Moreover, the results of clustering and machine learning classification models based on the target genes screened by the DM-ESPCA model can be improved by up to 22-23% of accuracies compared with the existing sparse PCA methods. We also proved that the result of the DM-ESPCA model is better than those of the four classic supervised machine learning models in the task of classification of cancer subtypes.