Integrating Genetics, Transcriptomics, and Proteomics in Lung Tissue to Investigate Chronic Obstructive Pulmonary Disease.

The integration of transcriptomic and proteomic data from lung tissue with chronic obstructive pulmonary disease (COPD)-associated genetic variants could provide insight into the biological mechanisms of COPD. Here, we assessed associations between lung transcriptomics and proteomics with COPD in 98 subjects from the Lung Tissue Research Consortium. Low correlations between transcriptomics and proteomics were generally observed, but higher correlations were found for COPD-associated proteins. We integrated COPD risk SNPs or SNPs near COPD-associated proteins with lung transcripts and proteins to identify regulatory cis-quantitative trait loci (QTLs). Significant expression QTLs (eQTLs) and protein QTLs (pQTLs) were found regulating multiple COPD-associated biomarkers. We investigated mediated associations from significant pQTLs through transcripts to protein levels of COPD-associated proteins. We also attempted to identify colocalized effects between COPD genome-wide association studies and eQTL and pQTL signals. Evidence was found for colocalization between COPD genome-wide association study signals and a pQTL for RHOB and an eQTL for DSP. We applied weighted gene co-expression network analysis to find consensus COPD-associated network modules. Two network modules generated by consensus weighted gene co-expression network analysis were associated with COPD with a false discovery rate lower than 0.05. One network module is related to the catenin complex, and the other module is related to plasma membrane components. In summary, multiple cis-acting determinants of transcripts and proteins associated with COPD were identified. Colocalization analysis, mediation analysis, and correlation-based network analysis of multiple omics data may identify key genes and proteins that work together to influence COPD pathogenesis.

Screening gene signatures for clinical response subtypes of lung transplantation.

Lung is the most important organ in the human respiratory system, whose normal functions are quite essential for human beings. Under certain pathological conditions, the normal lung functions could no longer be maintained in patients, and lung transplantation is generally applied to ease patients' breathing and prolong their lives. However, several risk factors exist during and after lung transplantation, including bleeding, infection, and transplant rejections. In particular, transplant rejections are difficult to predict or prevent, leading to the most dangerous complications and severe status in patients undergoing lung transplantation. Given that most common monitoring and validation methods for lung transplantation rejections may take quite a long time and have low reproducibility, new technologies and methods are required to improve the efficacy and accuracy of rejection monitoring after lung transplantation. Recently, one previous study set up the gene expression profiles of patients who underwent lung transplantation. However, it did not provide a tool to predict lung transplantation responses. Here, a further deep investigation was conducted on such profiling data. A computational framework, incorporating several machine learning algorithms, such as feature selection methods and classification algorithms, was built to establish an effective prediction model distinguishing patient into different clinical subgroups, corresponding to different rejection responses after lung transplantation. Furthermore, the framework also screened essential genes with functional enrichments and create quantitative rules for the distinction of patients with different rejection responses to lung transplantation. The outcome of this contribution could provide guidelines for clinical treatment of each rejection subtype and contribute to the revealing of complicated rejection mechanisms of lung transplantation.

Artificial intelligence for diagnosing microvessels of precancerous lesions and superficial esophageal squamous cell carcinomas: a multicenter study.

BACKGROUND: Intrapapillary capillary loop (IPCL) is an important factor for predicting invasion depth of esophageal squamous cell carcinoma (ESCC). The invasion depth is closely related to the selection of treatment strategy. However, diagnosis of IPCLs is complicated and subject to interobserver variability. This study aimed to develop an artificial intelligence (AI) system to predict IPCLs subtypes of precancerous lesions and superficial ESCC. METHODS: Images of magnifying endoscopy with narrow band imaging from three hospitals were collected retrospectively. IPCLs subtypes were annotated on images by expert endoscopists according to Japanese Endoscopic Society classification. The performance of the AI system was evaluated using internal and external validation datasets (IVD and EVD) and compared with that of the 11 endoscopists. RESULTS: A total of 7094 images from 685 patients were used to train and validate the AI system. The combined accuracy of the AI system for diagnosing IPCLs subtypes in IVD and EVD was 91.3% and 89.8%, respectively. The AI system achieved better performance than endoscopists in predicting IPCLs subtypes and invasion depth. The ability of junior endoscopists to diagnose IPCLs subtypes (combined accuracy: 84.7% vs 78.2%, P < 0.0001) and invasion depth (combined accuracy: 74.4% vs 67.9%, P < 0.0001) were significantly improved with AI system assistance. Although there was no significant differences, the performance of senior endoscopists was slightly elevated. CONCLUSIONS: The proposed AI system could improve the diagnostic ability of endoscopists to predict IPCLs classification of precancerous lesions and superficial ESCC.

[Optimization of preparation technology for Acanthopanax senticosus total saponins microemulsion by D-optimal mixture design and intestinal absorption characteristics].

Following the preparation of Acanthopanax senticosus total saponins microemulsion, the formulation and preparation technology were optimized and the quality was evaluated. The absorption characteristics of A. senticosus total saponins microemulsion by the self-microemulsifying drug delivery system(SMEDDS) were investigated in the unidirectional intestinal perfusion model in vivo. The oil phase, mass ratio(K_m), number of revolutions, and drug concentration were subjected to single-factor investigation with the area of pseudo-ternary phase diagram as the index. The process was optimized by D-optimal mixture design with the particle size as the index, and then the appearance, morphology, and particle size were investigated. The mass concentrations of eleutherosides B and E in the microemulsion were determined. The results showed that the optimum formulation of A. senticosus total saponins microemulsion was determined as follows: 20.8% of water phase, 31.2% of isopropyl palmitate, and 48.0% of soybean phospholipid and absolute ethanol(K_m=1∶1). As revealed by the observation under a transmission electron microscope, the microemulsion exhibited homogeneous dispersion and was a spherical emulsion droplet in the water-in-oil type. At room temperature, the pH value was 5.19, the refractive index 1.416 5, the average particle size(26.47±0.04)nm, and the polydispersity index(PDI) 0.118±0.03. The content of the eleutherosides B and E was 0.038 9 and 0.166 4 mg·mL~(-1), respectively. The preliminary stability study showed that the solution was clear and transparent within 30 d, without stratification or content change, indicating good stability. The absorption of microemulsion in each intestinal segment was significantly improved as compared with that of the A. senticosus total saponins, with the best absorption effect detected in the ileum, which has laid a foundation for further development and utilization of A. senticosus.

Lung proteomic biomarkers associated with chronic obstructive pulmonary disease.

Identifying protein biomarkers for chronic obstructive pulmonary disease (COPD) has been challenging. Most previous studies have used individual proteins or preselected protein panels measured in blood samples. Mass spectrometry proteomic studies of lung tissue have been based on small sample sizes. We used mass spectrometry proteomic approaches to discover protein biomarkers from 150 lung tissue samples representing COPD cases and controls. Top COPD-associated proteins were identified based on multiple linear regression analysis with false discovery rate (FDR) < 0.05. Correlations between pairs of COPD-associated proteins were examined. Machine learning models were also evaluated to identify potential combinations of protein biomarkers related to COPD. We identified 4,407 proteins passing quality controls. Twenty-five proteins were significantly associated with COPD at FDR < 0.05, including interleukin 33, ferritin (light chain and heavy chain), and two proteins related to caveolae (CAV1 and CAVIN1). Multiple previously reported plasma protein biomarkers for COPD were not significantly associated with proteomic analysis of COPD in lung tissue, although RAGE was borderline significant. Eleven pairs of top significant proteins were highly correlated (r > 0.8), including several strongly correlated with RAGE (EHD2 and CAVIN1). Machine learning models using Random Forests with the top 5% of protein biomarkers demonstrated reasonable accuracy (0.707) and area under the curve (0.714) for COPD prediction. Mass spectrometry-based proteomic analysis of lung tissue is a promising approach for the identification of biomarkers for COPD.

Predicting gene phenotype by multi-label multi-class model based on essential functional features.

Phenotype is one of the most significant concepts in genetics, which is used to describe all the characteristics of a research object that can be observed. Considering that phenotype reflects the integrated features of genotype and environment factors, it is hard to define phenotype characteristics, even difficult to predict unknown phenotypes. Restricted by current biological techniques, it is still quite expensive and time-consuming to obtain sufficient structural information of large-scale phenotype-associated genes/proteins. Various bioinformatics methods have been presented to solve such problem, and researchers have confirmed the efficacy and prediction accuracy of functional network-based prediction. But general functional descriptions have highly complicated inner structures for phenotype prediction. To further address this issue and improve the efficacy of phenotype prediction on more than ten kinds of phenotypes, we first extract functional enrichment features from GO and KEGG, and then use node2vec to learn functional embedding features of genes from a gene-gene network. All these features are analyzed by some feature selection methods (Boruta, minimum redundancy maximum relevance) to generate a feature list. Such list is fed into the incremental feature selection, incorporating some multi-label classifiers built by RAkEL and some classic base classifiers, to build an optimum multi-label multi-class classification model for phenotype prediction. According to recent researches, our method has indeed identified many literature-supported genes/proteins and their associated phenotypes, and even some candidate genes with re-assigned new phenotypes, which provide a new computational tool for the accurate and effective phenotypic prediction.

Increased S1P induces S1PR2 internalization to blunt the sensitivity of colorectal cancer to 5-fluorouracil via promoting intracellular uracil generation.

Sphingosine-1-phosphate (S1P), the backbone of most sphingolipids, activating S1P receptors (S1PRs) and the downstream G protein signaling has been implicated in chemoresistance. In this study we investigated the role of S1PR2 internalization in 5-fluorouracil (5-FU) resistance in human colorectal cancer (CRC). Clinical data of randomly selected 60 CRC specimens showed the correlation between S1PR2 internalization and increased intracellular uracil (P < 0.001). Then we explored the regulatory mechanisms in CRC model of villin-S1PR2-/- mice and CRC cell lines. We showed that co-administration of S1P promoted S1PR2 internalization from plasma membrane (PM) to endoplasmic reticulum (ER), thus blunted 5-FU efficacy against colorectal tumors in WT mice, compared to that in S1PR2-/- mice. In HCT116 and HT-29 cells, application of S1P (10 µM) empowered S1PR2 to internalize from PM to ER, thus inducing 5-FU resistance, whereas the specific S1PR2 inhibitor JTE-013 (10 µM) effectively inhibited S1P-induced S1PR2 internalization. Using Mag-Fluo-AM-labeling [Ca2+]ER and LC-ESI-MS/MS, we revealed that internalized S1PR2 triggered elevating [Ca2+]ER levels to activate PERK-eLF2α-ATF4 signaling in HCT116 cells. The activated ATF4 upregulated RNASET2-mediated uracil generation, which impaired exogenous 5-FU uptake to blunt 5-FU therapy. Overall, this study reveals a previously unrecognized mechanism of 5-FU resistance resulted from S1PR2 internalization-upregulated uracil generation in colorectal cancer, and provides the novel insight into the significance of S1PR2 localization in predicting the benefit of CRC patients from 5-FU-based chemotherapy.

Chiral separation materials based on derivatives of 6-amino-6-deoxyamylose.

In order to develop new type of chiral separation materials, in this study, 6-amino-6-deoxyamylose was used as chiral starting material with which 10 derivatives were synthesized. The amino group in 6-amino-6-deoxyamylose was selectively acylated and then the hydroxyl groups were carbamoylated yielding amylose 6-amido-6-deoxy-2,3-bis(phenylcarbamate)s, which were employed as chiral selectors (CSs) for chiral stationary phases of high-performance liquid chromatography. The resulted 6-amido-6-deoxyamyloses and amylose 6-amido-6-deoxy-2,3-bis(phenylcarbamate)s were characterized by IR, 1 H NMR, and elemental analysis. Enantioseparation evaluations indicated that most of the CSs demonstrated a moderate chiral recognition capability. The 6-nonphenyl (6-nonPh) CS of amylose 6-cyclohexylformamido-6-deoxy-2,3-bis(3,5-dimethylphenylcarbamate) showed the highest enantioselectivity towards the tested chiral analytes; the phenyl-heterogeneous (Ph-hetero) CS of amylose 6-(4-methylbenzamido)-6-deoxy-2,3-bis(3,5-dimethylphenylcarbamate) baseline separated the most chiral analytes; the phenyl-homogeneous (Ph-homo) CS of amylose 6-(3,5-dimethylbenzamido)-6-deoxy-2,3-bis(3,5-dimethylphenylcarbamate) also exhibited a good enantioseparation capability among the developed CSs. Regarding Ph-hetero CSs, the enantioselectivity depended on the combination of the substituent at 6-position and that at 2- and 3-positions; as for Ph-homo CSs, the enantioselectivity was related to the substituent at 2-, 3-, and 6-positions; with respect to 6-nonPh CSs, the retention factor of most analytes on the corresponding CSPs was lower than that on Ph-hetero and Ph-homo CSPs in the same mobile phases, indicating π-π interactions did occur during enantioseparation. Although the substituent at 6-position could not provide π-π interactions, the 6-nonPh CSs demonstrated an equivalent or even higher enantioselectivity compared with the Ph-homo and Ph-hetero CSs.

Identifying the RNA signatures of coronary artery disease from combined lncRNA and mRNA expression profiles.

Coronary artery disease (CAD) is the most common cardiovascular disease. CAD research has greatly progressed during the past decade. mRNA is a traditional and popular pipeline to investigate various disease, including CAD. Compared with mRNA, lncRNA has better stability and thus may serve as a better disease indicator in blood. Investigating potential CAD-related lncRNAs and mRNAs will greatly contribute to the diagnosis and treatment of CAD. In this study, a computational analysis was conducted on patients with CAD by using a comprehensive transcription dataset with combined mRNA and lncRNA expression data. Several machine learning algorithms, including feature selection methods and classification algorithms, were applied to screen for the most CAD-related RNA molecules. Decision rules were also reported to provide a quantitative description about the effect of these RNA molecules on CAD progression. These new findings (CAD-related RNA molecules and rules) can help understand mRNA and lncRNA expression levels in CAD.

Investigating the gene expression profiles of cells in seven embryonic stages with machine learning algorithms.

The development of embryonic cells involves several continuous stages, and some genes are related to embryogenesis. To date, few studies have systematically investigated changes in gene expression profiles during mammalian embryogenesis. In this study, a computational analysis using machine learning algorithms was performed on the gene expression profiles of mouse embryonic cells at seven stages. First, the profiles were analyzed through a powerful Monte Carlo feature selection method for the generation of a feature list. Second, increment feature selection was applied on the list by incorporating two classification algorithms: support vector machine (SVM) and repeated incremental pruning to produce error reduction (RIPPER). Through SVM, we extracted several latent gene biomarkers, indicating the stages of embryonic cells, and constructed an optimal SVM classifier that produced a nearly perfect classification of embryonic cells. Furthermore, some interesting rules were accessed by the RIPPER algorithm, suggesting different expression patterns for different stages.

Lithium-Lanthanide Bimetallic Metal-Organic Frameworks towards Negative Electrode Materials for Lithium-Ion Batteries.

Novel lithium-lanthanide (Ln: cerium and praseodymium) bimetallic coordination polymers with formulas C10 H2 LnLiO8 (Ln: Ce (CeLipma) and Pr (PrLipma)) and C10 H3 CeO8 (Cepma) were prepared through a simple hydrothermal method. The three compounds were characterized by means of FTIR spectroscopy, X-ray diffraction, single-crystal X-ray diffraction, SEM, TEM, and X-ray photoelectron spectroscopy. The results of structural refinement show that they belong to triclinic symmetry and P 1 ‾ space group with cerium (or praseodymium) and lithium cations, forming coordination bonds to oxygen atoms from different pyromellitic acid molecules, and leading to the construction of 3D structures. It is interesting to note that the frameworks exclude any coordination water and lattice water. As an electrode material for lithium-ion batteries, CeLipma exhibits a maximum capacity of 800.5 mAh g-1 and a retention of 91.4 % after 50 cycles at a current density of 100 mA g-1 . The favorable electrochemical properties of the lanthanide coordination polymers show potential application prospects in the field of electrode materials.

S1PR2 inhibitors potently reverse 5-FU resistance by downregulating DPD expression in colorectal cancer.

In this study, S1PR2 was reckoned as a brand-new GPCR target for designing inhibitors to reverse 5-FU resistance. Herein a series of pyrrolidine pyrazoles as the S1PR2 inhibitors were designed, synthesized and evaluated for their activities of anti-FU-resistance. Among them, the most promising compound JTE-013, exhibited excellent inhibition on DPD expression and potent anti-FU-resistance activity in various human cancer cell lines, along with the in vivo HCT116DPD cells xenograft model, in which the inhibition rate of 5-FU was greatly increased from 13.01%-75.87%. The underlying mechanism was uncovered that JTE-013 demonstrated an anti-FU-resistance activity by blocking S1PR2 internalization to the endoplasmic reticulum (ER), which inhibited the degradation of 5-FU into α-fluoro-ß-alanine (FBAL) by downregulating tumoral DPD expression. Overall, JTE-013 could serve as the lead compound for the discovery of new anti-FU-resistance drugs. SIGNIFICANCE: This study provides novel insights that S1PR2 inhibitors could sensitize 5-FU therapy in colorectal cancer.

Risk factors for distal migration of biliary plastic stents and related duodenal injury.

BACKGROUND: The risk factors of duodenal injury from distal migrated biliary plastic stents remain uncertain. The aim of this study was to determine the risk factors of distal migration and its related duodenal injury in patients who underwent placement of a single biliary plastic stent for biliary strictures. METHODS: We retrospectively reviewed all patients with biliary strictures who underwent endoscopic placement of a single biliary plastic stent from January 2006 to October 2017. RESULTS: Two hundred forty-eight patients with 402 endoscopic retrograde cholangiopancreatography procedures were included. The incidence of distal migration was 6.2%. The frequency of duodenal injury was 2.2% in all cases and 36% in cases with distal migration. Benign biliary strictures (BBS), length of the stent above the proximal end of the stricture (> 2 cm), and duration of stent retention (< 3 months) were independently associated with distal migration (p = 0.018, p = 0.009, and p = 0.016, respectively). Duodenal injury occurred more commonly in cases with larger angle (≥ 30°) between the distal end of the stent and the centerline of the patient's body (p = 0.018) or in cases with stent retention < 3 months (p = 0.031). CONCLUSIONS: The risk factors of distal migration are BBS and the length of the stent above the proximal end of the stricture. The risk factor of duodenal injury due to distal migration is large angle (≥ 30°) between the distal end of the stent and the centerline of the patient's body. Distal migration and related duodenal injury are more likely to present during the early period after biliary stenting.

Inferring novel genes related to oral cancer with a network embedding method and one-class learning algorithms.

Oral cancer (OC) is one of the most common cancers threatening human lives. However, OC pathogenesis has yet to be fully uncovered, and thus designing effective treatments remains difficult. Identifying genes related to OC is an important way for achieving this purpose. In this study, we proposed three computational models for inferring novel OC-related genes. In contrast to previously proposed computational methods, which lacked the learning procedures, each proposed model adopted a one-class learning algorithm, which can provide a deep insight into features of validated OC-related genes. A network embedding algorithm (i.e., node2vec) was applied to the protein-protein interaction network to produce the representation of genes. The features of the OC-related genes were used in the training of the one-class algorithm, and the performance of the final inferring model was improved through a feature selection procedure. Then, candidate genes were produced by applying the trained inferring model to other genes. Three tests were performed to screen out the important candidate genes. Accordingly, we obtained three inferred gene sets, any two of which were different. The inferred genes were also different from previous reported genes and some of them have been included in the public Oral Cancer Gene Database. Finally, we analyzed several inferred genes to confirm whether they are novel OC-related genes.

HIV infection alters the human epigenetic landscape.

Many complex diseases or traits are the results of both genetic and environmental factors. The environmental factors affect the human body by modifying its epigenetics, which controls the activity of genomes without mutating it. Viral infection is one of the common environmental factors for complex diseases. For example, the human immunodeficiency virus (HIV) infection can cause acquired immune deficiency syndrome (AIDS), HBV, and HCV infections are associated with hepatocellular carcinoma, and human papillomavirus infection is a causal factor in cervical carcinoma. In this study, to investigate how HIV infection affects DNA methylation, we analyzed the blood DNA methylation data of 485 512 sites in 44 HIV- and 142 HIV + patients. Several advanced computational methods were applied to identify the core distinctive features that were different between the HIV patients and the healthy controls. These methods can be used for differentiating HIV-infected patients from uninfected ones. These core distinctive DNA methylation features were confirmed to be functionally connected to premature aging and abnormal immune regulation, two typical pathological symptoms of HIV infection, revealing the potential regulatory mechanisms of HIV infection on the DNA methylation status of the host cells and provided novel insights on the pathogenesis of HIV infection and AIDS.

Tissue differences revealed by gene expression profiles of various cell lines.

Mechanisms through which tissues are formed and maintained remain unknown but are fundamental aspects in biology. Tissue-specific gene expression is a valuable tool to study such mechanisms. But in many biomedical studies, cell lines, rather than human body tissues, are used to investigate biological mechanisms Whether or not cell lines maintain their tissue-specific characteristics after they are isolated and cultured outside the human body remains to be explored. In this study, we applied a novel computational method to identify core genes that contribute to the differentiation of cell lines from various tissues. Several advanced computational techniques, such as Monte Carlo feature selection method, incremental feature selection method, and support vector machine (SVM) algorithm, were incorporated in the proposed method, which extensively analyzed the gene expression profiles of cell lines from different tissues. As a result, we extracted a group of functional genes that can indicate the differences of cell lines in different tissues and built an optimal SVM classifier for identifying cell lines in different tissues. In addition, a set of rules for classifying cell lines were also reported, which can give a clearer picture of cell lines in different issues although its performance was not better than the optimal SVM classifier. Finally, we compared such genes with the tissue-specific genes identified by the Genotype-tissue Expression project. Results showed that most expression patterns between tissues remained in the derived cell lines despite some uniqueness that some genes show tissue specificity.

Identification of synthetic lethality based on a functional network by using machine learning algorithms.

Synthetic lethality is the synthesis of mutations leading to cell death. Tumor-specific synthetic lethality has been targeted in research to improve cancer therapy. With the advances of techniques in molecular biology, such as RNAi and CRISPR/Cas9 gene editing, efforts have been made to systematically identify synthetic lethal interactions, especially for frequently mutated genes in cancers. However, elucidating the mechanism of synthetic lethality remains a challenge because of the complexity of its influencing conditions. In this study, we proposed a new computational method to identify critical functional features that can accurately predict synthetic lethal interactions. This method incorporates several machine learning algorithms and encodes protein-coding genes by an enrichment system derived from gene ontology terms and Kyoto Encyclopedia of Genes and Genomes pathways to represent their functional features. We built a random forest-based prediction engine by using 2120 selected features and obtained a Matthews correlation coefficient of 0.532. We examined the top 15 features and found that most of them have potential roles in synthetic lethality according to previous studies. These results demonstrate the ability of our proposed method to predict synthetic lethal interactions and provide a basis for further characterization of these particular genetic combinations.

Identification of the copy number variant biomarkers for breast cancer subtypes.

Breast cancer is a common and threatening malignant disease with multiple biological and clinical subtypes. It can be categorized into subtypes of luminal A, luminal B, Her2 positive, and basal-like. Copy number variants (CNVs) have been reported to be a potential and even better biomarker for cancer diagnosis than mRNA biomarkers, because it is considerably more stable and robust than gene expression. Thus, it is meaningful to detect CNVs of different cancers. To identify the CNV biomarker for breast cancer subtypes, we integrated the CNV data of more than 2000 samples from two large breast cancer databases, METABRIC and The Cancer Genome Atlas (TCGA). A Monte Carlo feature selection-based and incremental feature selection-based computational method was proposed and tested to identify the distinctive core CNVs in different breast cancer subtypes. We identified the CNV genes that may contribute to breast cancer tumorigenesis as well as built a set of quantitative distinctive rules for recognition of the breast cancer subtypes. The tenfold cross-validation Matthew's correlation coefficient (MCC) on METABRIC training set and the independent test on TCGA dataset were 0.515 and 0.492, respectively. The CNVs of PGAP3, GRB7, MIR4728, PNMT, STARD3, TCAP and ERBB2 were important for the accurate diagnosis of breast cancer subtypes. The findings reported in this study may further uncover the difference between different breast cancer subtypes and improve the diagnosis accuracy.

Identifying Methylation Pattern and Genes Associated with Breast Cancer Subtypes.

Breast cancer is regarded worldwide as a severe human disease. Various genetic variations, including hereditary and somatic mutations, contribute to the initiation and progression of this disease. The diagnostic parameters of breast cancer are not limited to the conventional protein content and can include newly discovered genetic variants and even genetic modification patterns such as methylation and microRNA. In addition, breast cancer detection extends to detailed breast cancer stratifications to provide subtype-specific indications for further personalized treatment. One genome-wide expression-methylation quantitative trait loci analysis confirmed that different breast cancer subtypes have various methylation patterns. However, recognizing clinically applied (methylation) biomarkers is difficult due to the large number of differentially methylated genes. In this study, we attempted to re-screen a small group of functional biomarkers for the identification and distinction of different breast cancer subtypes with advanced machine learning methods. The findings may contribute to biomarker identification for different breast cancer subtypes and provide a new perspective for differential pathogenesis in breast cancer subtypes.

Analysis of Expression Pattern of snoRNAs in Different Cancer Types with Machine Learning Algorithms.

Small nucleolar RNAs (snoRNAs) are a new type of functional small RNAs involved in the chemical modifications of rRNAs, tRNAs, and small nuclear RNAs. It is reported that they play important roles in tumorigenesis via various regulatory modes. snoRNAs can both participate in the regulation of methylation and pseudouridylation and regulate the expression pattern of their host genes. This research investigated the expression pattern of snoRNAs in eight major cancer types in TCGA via several machine learning algorithms. The expression levels of snoRNAs were first analyzed by a powerful feature selection method, Monte Carlo feature selection (MCFS). A feature list and some informative features were accessed. Then, the incremental feature selection (IFS) was applied to the feature list to extract optimal features/snoRNAs, which can make the support vector machine (SVM) yield best performance. The discriminative snoRNAs included HBII-52-14, HBII-336, SNORD123, HBII-85-29, HBII-420, U3, HBI-43, SNORD116, SNORA73B, SCARNA4, HBII-85-20, etc., on which the SVM can provide a Matthew's correlation coefficient (MCC) of 0.881 for predicting these eight cancer types. On the other hand, the informative features were fed into the Johnson reducer and repeated incremental pruning to produce error reduction (RIPPER) algorithms to generate classification rules, which can clearly show different snoRNAs expression patterns in different cancer types. The analysis results indicated that extracted discriminative snoRNAs can be important for identifying cancer samples in different types and the expression pattern of snoRNAs in different cancer types can be partly uncovered by quantitative recognition rules.