generating-transcriptional-regulation-view-transcriptomic-features

Generating the Transcriptional Regulation View of Transcriptomic Features for Prediction Task and Dark Biomarker Detection on Small Datasets

Transcriptome represents the expression levels of many genes in a sample and has been widely used in biological research and clinical practice. ...

Jilin University

The rate of brucellosis, a zoonotic disease, has rapidly increased in humans brucellosis(HB) in recent years. In 1950-2018, a total of 684,380 HB cases (median 2274/year (interquartile range (IQR) 966-8325)) were reported to the National Infectious Disease Surveillance System in mainland China. The incidence of HB peaked in 2014 (4.32/100,000), and then showed a downward trend; we predict that it will maintain a steady downward trend in 2019-2020. Since 2015, the incidence of HB has shown opposite trends in the north and south of China; rates in the north have fallen and rates in the south have increased. In 2004-2018, the most significant increases in incidence of HB were in Yunnan (IQR 0.002-0.463/100,000), Hubei (IQR 0.000-0.338/100,000), and Guangdong (IQR 0.015-0.350/100,000). The areas where HB occurs have little overlap with areas with high per capita GDP in China. The "high-high" clusters of HB are located in northeastern China (Inner Mongolia, Heilongjiang, Jilin, Liaoning, Ningxia, Shanxi, and Gansu), and the "low-low" clusters of HB are located in southern China (Yunnan, Jiangxi, Shanghai, Guangxi, Guangdong, Zhejiang, Guizhou, and Hunan). In recent years, the incidence of HB in China has been controlled to some extent, but the incidence of HB has increased in southern China, and the disease has spread geographically in China from north to south. Further research is needed to address this change and to continue to explore the relationship between the incidence of HB and relevant factors.

Epidemiological Characteristics and Spatiotemporal Trend Analysis of Human Brucellosis in China, 1950-2018.

Human Leukocyte Antigen (HLA) is a type of molecule residing on the surfaces of most human cells and exerts an essential role in the immune system responding to the invasive items. The T cell antigen receptors may recognize the HLA-peptide complexes on the surfaces of cancer cells and destroy these cancer cells through toxic T lymphocytes. The computational determination of HLA-binding peptides will facilitate the rapid development of cancer immunotherapies. This study hypothesized that the natural language processing-encoded peptide features may be further enriched by another deep neural network. The hypothesis was tested with the Bi-directional Long Short-Term Memory-extracted features from the pretrained Protein Bidirectional Encoder Representations from Transformers-encoded features of the class I HLA (HLA-I)-binding peptides. The experimental data showed that our proposed HLAB feature engineering algorithm outperformed the existing ones in detecting the HLA-I-binding peptides. The extensive evaluation data show that the proposed HLAB algorithm outperforms all the seven existing studies on predicting the peptides binding to the HLA-A*01:01 allele in AUC and achieves the best average AUC values on the six out of the seven k-mers (k=8,9,...,14, respectively represent the prediction task of a polypeptide consisting of k amino acids) except for the 9-mer prediction tasks. The source code and the fine-tuned feature extraction models are available at http://www.healthinformaticslab.org/supp/resources.php.

HLAB: learning the BiLSTM features from the ProtBert-encoded proteins for the class I HLA-peptide binding prediction.

Nontyphoidal  (NTS) in children remains a growing burden on public health and often causes children to be hospitalized with diarrheic symptoms. In this work, 260 strains of human  isolated from Jilin, China were characterized by serotypes and antimicrobial resistance using whole genome sequencing (WGS). The most prevalent serotype was  (47.3%), followed by . I 4,[5],12:i:- (33.1%), and  (7.3%). Furthermore, the consistency between resistance phenotype and genotype was confirmed. Similarly, strains harbored   and  genes were detected, which verified the level of resistant phenotype in β-lactams and tetracyclines. The presence of a single mutation in , and  genes corresponding to quinolones was also observed. In our work, multilocus sequence typing (MLST) and core genome multilocus sequence typing (cgMLST) were found to have a high resolution to molecular traceability, and the combination of both was conducive to practical application in an actual situation. Taking all of this into account, we suggested that the comprehensive surveillance of  infection in children should be carried out to monitor antimicrobial-resistant trends from various sources and to alert on outbreaks of foodborne diseases to protect public health.

Whole Genome Sequencing, Antibiotic Resistance, and Epidemiology Features of Nontyphoidal  Isolated From Diarrheic Children: Evidence From North China.

Transmission and outbreaks of Staphylococcus aureus among retail food highlights the need to comprehensive analysis the molecular characteristic of Staphylococcus aureus in foods. However, the information about Staphylococcus aureus in north China is limited. In this study, 97 and 28 S. aureus strains were isolated for analysis from 4262 samples of retail food and 61 samples food outbreaks with prevalence rate 2.28 % and 45.9 %, respectively in Jilin, China from 2014 to 2018. This study aimed to investigate the prevalence of S. aureus isolates and characterize by antimicrobial resistance testing, virulence profiles, spa typing, and multilocus sequence typing (MLST) analysis. 60 % (75/125) of the isolates contained at least enterotoxin genes including classic and new SEs genes as following: sea (40/125,32 %), see (36/125,28.8 %), sec (29/125,23.2 %), sell (29/125,23.2 %), seb (25/125,20 %), seh (22/125,17.6 %), sed (6/125,4.8 %), selq (6/125,4.8 %), and selk (6/125,4.8 %). In antimicrobial susceptibility tests, 59.2 % of the isolates (74/125) were considered as multi-drug-resistant isolates and four MRSA strains were all found with high multi-drug-resistance. Phenotype resistance to penicillin (94.4 %), erythromycin (84.2 %), clindamycin (63.9 %), and tetracycline (47.2 %) was observed which was corresponding with genotype resistance. The strains were classified to twenty-two sequence types (STs), fourteen clonal complexes (CCs), and forty-seven spa types. The predominant ST and spa types were ST1(22/125,17.6 %), ST25(20/125,16.00 %), ST398 (14/125,11.2 %) and t127 (20/125,16 %), t078 (14/125,11.2 %), t803 (7/125,5.6 %). The wgSNP analysis of these isolates in food represents showed close relatedness with food outbreaks which pose a potential health risk for consumers and warrants further attention.

Genomic analysis, antibiotic resistance, and virulence of Staphylococcus aureus from food and food outbreaks: A potential public concern.

Melanoma is a lethal skin disease that develops from moles. This study aimed to integrate multimodal data to predict metastatic melanoma, which is highly aggressive and difficult to treat. The proposed EnsembleSKCM method evaluated the prediction performances of long noncoding RNAs (lncRNAs), protein-coding messenger genes (mRNAs) and pathology images (images) for metastatic melanoma. Feature selection was used to screen for metastatic biomarkers in the lncRNA and mRNA datasets. The integrated EnsembleSKCM model was built based on the weighted results of the lncRNA-, mRNA- and image-based models. EnsembleSKCM achieved 0.9444 in the prediction accuracy of metastatic melanoma and outperformed the single-modal prediction models based on the lncRNA, mRNA and image data. The experimental data suggest the importance of integrating the complementary information from the three data modalities. WGCNA was used to analyze the relationship of molecular-level features and image features, and the results show connections between them. Another cohort was used to validate our prediction.

Integration of lncRNAs, Protein-Coding Genes and Pathology Images for Detecting Metastatic Melanoma.

Human listeriosis outbreaks are often associated with consumption of contaminated food, especially meat products. To better understand meat contamination of L. monocytogenes, whole genome sequencing(WGS) was performed on all detected isolates to investigate genetic relationships between retail markets and slaughterhouses. 110 and 13 isolates were isolated from 1914 food samples and 67 food and environmental samples, respectively. IIa (51/123,41.5%) and IIc (7/123,5.7%) were detected as the dominant serogroups of 123 L. monocytogenes isolates.Most isolates were penicillin-resistant (22/123,17.9%) in the phenotypic test, and all isolates were also found to be susceptible to ampicillin, meropenem, and vancomycin. All of them harbored virulence-associated genes and premature stop codons (PMSCs) in inlA genes were occurred in 35 strains. 22 multilocus sequence types and 19 clonal complexes were identified with ST9 being most common. This study also showed the prevalence and uniqueness of strains from Jilin, China compared with worldwide epidemic international strains. The findings of this study will contribute to the epidemiological understanding of transmission of L. monocytogenes from production and circulation in the region of northern China.

Genetic diversity, antibiotic resistance, and virulence profiles of Listeria monocytogenes from retail meat and meat processing.

Methylation is a major DNA epigenetic modification for regulating the biological processes without altering the DNA sequence, and multiple types of DNA methylations have been discovered, including 6mA, 5hmC, and 4mC. Multiple computational approaches were developed to automatically identify the DNA methylation residues using machine learning or deep learning algorithms. The machine learning (ML) based methods are difficult to be transferred to the other predicting tasks of the DNA methylation sites using additional knowledge. Deep learning (DL) may facilitate the transfer learning of knowledge from similar tasks, but they are often ineffective on small datasets. This study proposes an integrated feature representation framework EpiTEAmDNA based on the strategies of transfer learning and ensemble learning, which is evaluated on multiple DNA methylation types across 15 species. EpiTEAmDNA integrates convolutional neural network (CNN) and conventional machine learning methods, and shows improved performances than the existing DL-based methods on small datasets when no additional knowledge is available. The experimental data suggests that the EpiTEAmDNA models may be further improved via transfer learning based on additional knowledge. The evaluation experiments on the independent test datasets also suggest that the proposed EpiTEAmDNA framework outperforms the existing models in most prediction tasks of the 3 DNA methylation types across 15 species. The source code, pre-trained global model, and the EpiTEAmDNA feature representation framework are freely available at http://www.healthinformaticslab.org/supp/.

EpiTEAmDNA: Sequence feature representation via transfer learning and ensemble learning for identifying multiple DNA epigenetic modification types across species.

: Colon cancer (CC) is common, and the mortality rate greatly increases as the disease progresses to the metastatic stage. Early detection of metastatic colon cancer (mCC) is crucial for reducing the mortality rate. Most previous studies have focused on the top-ranked differentially expressed transcriptomic biomarkers between mCC and primary CC while ignoring non-differentially expressed genes.  This study proposed that the complicated inter-feature correlations could be quantitatively formulated as a complementary transcriptomic view. We used a regression model to formulate the correlation between the expression levels of a messenger RNA (mRNA) and its regulatory transcription factors (TFs). The change between the predicted and real expression levels of a query mRNA was defined as the mqTrans value in the given sample, reflecting transcription regulatory changes compared with the model-training samples. A dark biomarker in mCC is defined as an mRNA gene that is non-differentially expressed in mCC but demonstrates mqTrans values significantly associated with mCC. This study detected seven dark biomarkers using 805 samples from three independent datasets. Evidence from the literature supports the role of some of these dark biomarkers.  This study presented a complementary high-dimensional analysis procedure for transcriptome-based biomarker investigations with a case study on mCC.

Transcriptional Dysregulations of Seven Non-Differentially Expressed Genes as Biomarkers of Metastatic Colon Cancer.

Artificial intelligence (AI) has achieved significant progress in the field of drug discovery. AI-based tools have been used in all aspects of drug discovery, including chemical structure recognition. We propose a chemical structure recognition framework, Optical Chemical Molecular Recognition (OCMR), to improve the data extraction capability in practical scenarios compared with the rule-based and end-to-end deep learning models. The proposed OCMR framework enhances the recognition performances via the integration of local information in the topology of molecular graphs. OCMR handles complex tasks like non-canonical drawing and atomic group abbreviation and substantially improves the current state-of-the-art results on multiple public benchmark datasets and one internally curated dataset.

OCMR: A comprehensive framework for optical chemical molecular recognition.

This work hypothesizes that some genes undergo radically changed transcription regulations (TRs) in breast cancer (BC), but don't show differential expressions for unknown reasons. The TR of a gene is quantitatively formulated by a regression model between the expression of this gene and multiple transcription factors (TFs). The difference between the predicted and real expression levels of a gene in a query sample is defined as the mqTrans value of this gene, which quantitatively reflects its regulatory changes. This work systematically screens the undifferentially expressed genes with differentially expressed mqTrans values in 1036 samples across five datasets and three ethnic groups. This study calls the 25 genes satisfying the above hypothesis in at least four datasets as dark biomarkers, and the strong dark biomarker gene CXXC5 (CXXC Finger Protein 5) is even supported by all the five independent BC datasets. Although CXXC5 does not show differential expressions in BC, its transcription regulations show quantitative associations with BCs in diversified cohorts. The overlapping long noncoding RNAs (lncRNAs) may have contributed their transcripts to the expression miscalculations of dark biomarkers. The mqTrans analysis serves as a complementary view of the transcriptome-based detections of biomarkers that are ignored by many existing studies.

Undifferentially Expressed CXXC5 as a Transcriptionally Regulatory Biomarker of Breast Cancer.

Survival analysis is critical to cancer prognosis estimation. High-throughput technologies facilitate the increase in the dimension of genic features, but the number of clinical samples in cohorts is relatively small due to various reasons, including difficulties in participant recruitment and high data-generation costs. Transcriptome is one of the most abundantly available OMIC (referring to the high-throughput data, including genomic, transcriptomic, proteomic and epigenomic) data types. This study introduced a multitask graph attention network (GAT) framework DQSurv for the survival analysis task. We first used a large dataset of healthy tissue samples to pretrain the GAT-based HealthModel for the quantitative measurement of the gene regulatory relations. The multitask survival analysis framework DQSurv used the idea of transfer learning to initiate the GAT model with the pretrained HealthModel and further fine-tuned this model using two tasks i.e. the main task of survival analysis and the auxiliary task of gene expression prediction. This refined GAT was denoted as DiseaseModel. We fused the original transcriptomic features with the difference vector between the latent features encoded by the HealthModel and DiseaseModel for the final task of survival analysis. The proposed DQSurv model stably outperformed the existing models for the survival analysis of 10 benchmark cancer types and an independent dataset. The ablation study also supported the necessity of the main modules. We released the codes and the pretrained HealthModel to facilitate the feature encodings and survival analysis of transcriptome-based future studies, especially on small datasets. The model and the code are available at http://www.healthinformaticslab.org/supp/.

Orchestrating information across tissues via a novel multitask GAT framework to improve quantitative gene regulation relation modeling for survival analysis.

Coronavirus disease 2019 (COVID-19) is a rapidly developing and sometimes lethal pulmonary disease. Accurately predicting COVID-19 mortality will facilitate optimal patient treatment and medical resource deployment, but the clinical practice still needs to address it. Both complete blood counts and cytokine levels were observed to be modified by COVID-19 infection. This study aimed to use inexpensive and easily accessible complete blood counts to build an accurate COVID-19 mortality prediction model. The cytokine fluctuations reflect the inflammatory storm induced by COVID-19, but their levels are not as commonly accessible as complete blood counts. Therefore, this study explored the possibility of predicting cytokine levels based on complete blood counts.

Reconstructing the cytokine view for the multi-view prediction of COVID-19 mortality.

Thyroid cancer is the most common type of endocrine system cancer. The pre-cancer and early stages are usually benign or slowly growing, and do not need invasive treatments. This study investigated the challenging classification task of four classes of samples, i.e., normal controls (N), thyroid adenomas (TA), papillary thyroid cancers (PTC) and metastasized papillary thyroid cancers (MPTC). We proposed a multi-view progression diagnosis framework ThyroidBloodTest to integrate the two views of RNAseq platelet transcriptomes (View-T) and blood routine (View-B) features. Platelet transcriptome represented the molecular-level information, while the blood routine features were easy to obtain in the clinical practice. Eleven feature selection algorithms and seven classifiers were evaluated for both views. The experimental data suggested the importance of choosing appropriate data analysis algorithms and feature engineering techniques like principal component analysis (PCA). The best ThyroidBloodTest model achieved Acc = 0.8750 for the four-class classification of the N/TA/PTC/MPTC samples based on the integrated feature space of View-T and View-B. The cellular localization cytosol and three post-translational modification types acetylation/phosphorylation/ubiquitination were observed to be enriched in the proteins encoded by the View-T biomarkers. The numbers of different immune cells also contributed positively to the progression diagnosis of thyroid cancer. The proposed multi-view prediction model demonstrated the necessity of integrating both platelet transcriptomes and blood routine tests for the progression diagnosis of thyroid cancer.

Multi-view progression diagnosis of thyroid cancer by integrating platelet transcriptomes and blood routine tests.

Predicting molecular properties is a pivotal task in various scientific domains, including drug discovery, material science, and computational chemistry. This problem is often hindered by the lack of annotated data and imbalanced class distributions, which pose significant challenges in developing accurate and robust predictive models.

Article	Year
Epidemiological Characteristics and Spatiotemporal Trend Analysis of Human Brucellosis in China, 1950-2018. International journal of environmental research and public health\| PubMed ID: 32244493	2020
HLAB: learning the BiLSTM features from the ProtBert-encoded proteins for the class I HLA-peptide binding prediction. Briefings in bioinformatics\| PubMed ID: 35514183	2022
Whole Genome Sequencing, Antibiotic Resistance, and Epidemiology Features of Nontyphoidal Isolated From Diarrheic Children: Evidence From North China. Frontiers in microbiology\| PubMed ID: 35651495	2022
Genomic analysis, antibiotic resistance, and virulence of Staphylococcus aureus from food and food outbreaks: A potential public concern. International journal of food microbiology\| PubMed ID: 35834921	2022
Integration of lncRNAs, Protein-Coding Genes and Pathology Images for Detecting Metastatic Melanoma. Genes\| PubMed ID: 36292801	2022
Genetic diversity, antibiotic resistance, and virulence profiles of Listeria monocytogenes from retail meat and meat processing. Food research international (Ottawa, Ont.)\| PubMed ID: 36461311	2022
EpiTEAmDNA: Sequence feature representation via transfer learning and ensemble learning for identifying multiple DNA epigenetic modification types across species. Computers in biology and medicine\| PubMed ID: 37196456	2023
Transcriptional Dysregulations of Seven Non-Differentially Expressed Genes as Biomarkers of Metastatic Colon Cancer. Genes\| PubMed ID: 37372321	2023
OCMR: A comprehensive framework for optical chemical molecular recognition. Computers in biology and medicine\| PubMed ID: 37393787	2023
Undifferentially Expressed CXXC5 as a Transcriptionally Regulatory Biomarker of Breast Cancer. Advanced biology\| PubMed ID: 37423953	2023
Orchestrating information across tissues via a novel multitask GAT framework to improve quantitative gene regulation relation modeling for survival analysis. Briefings in bioinformatics\| PubMed ID: 37427963	2023
Reconstructing the cytokine view for the multi-view prediction of COVID-19 mortality. BMC infectious diseases\| PubMed ID: 37735372	2023
Multi-view progression diagnosis of thyroid cancer by integrating platelet transcriptomes and blood routine tests. Computers in biology and medicine\| PubMed ID: 37918259	2023
MolFeSCue: Enhancing molecular property prediction in Data-Limited and imbalanced contexts using Few-Shot and contrastive learning. Bioinformatics (Oxford, England)\| PubMed ID: 38426310	2024

Kewei Li

Biography

JoVE Journal Publications

Other Publications