Brief report · 29 Dec 2025
Conference abstractPublished 11 Oct 2018
Deciphering the mechanisms of complex diseases using network and machine learning approaches
Shanghai Institutes for Biological Sciences, China
Abstract
Select any words in the title or abstract, or press this and choose a sentence.
The complex diseases, such as cancer, involves dysfunctions on multiple levels. There have been several methods to identify the dysfunctions on each level. On genomics level, GWAS (Genome-wide association study) can detect the disease phenotype associated SNPs (single nucleotide polymorphisms). But many GWAS identified SNPs locate in intergenic region and can't be annotated to specific genes. With the help of eQTL (expression quantitative trait loci) method, the downstream genes of the GWAS SNPs can be found. And based on the co-expression network, regulatory network, protein-protein interaction network, or even protein-chemical interaction network of these genes, the possible cascade of the signal transduction from the genetic perturbations can be discovered. By integrating all these omics data, we can establish a systems biology model of how the GWAS SNPs affect the expression of their direct target genes, how these direct targets affect secondary target genes, or proteins, or metabolites, and eventually cause the catastrophic pathological changes on network or pathway. With the comprehensive network, we can not only study the mechanism of one disease, but also the relationship of several traits. For example, schizophrenia and anti-tuberculosis drug-induced hepatotoxicity co-occurred frequently but they do not share common genes. We mapped their genes onto the network, the common drivers of these two diseases were revealed through two-way RWR analysis. Another example is that the lung cancer dysfunctions on several levels but how the different level dysfunctions connect are still unknown. We investigated the mutation, methylation, mRNA and microRNA expression difference between cancer and normal tissues using machine learning methods, then mapped the dysfunction of each level onto the comprehensive network. By connecting each other with shortest paths, the highly frequent shortest path genes that can cause the tumorigenesis on multiple levels were discovered. Overall, the network and machine learning approaches are effective to dissect the complex system and reveal the mechanisms of diseases. 1. Cai Y D, Zhang Q, Zhang Y H, Chen L and Huang T (2017) Identification of genes associated with breast cancer metastasis to bone on a protein-protein interaction network with a shortest path algorithm. Journal of Proteome Research. 16(2):1027- 1038. 2. Zhang N, Wang M, Zhang P and Huang T (2016) Classification of cancers based on copy number variation landscapes. Biochimica et Biophysica Acta. 860(11, Part B):2750-2755. 3. Huang T et al. (2016) SNHG8 is identified as a key regulator of epstein-barr virus (EBV)-associated gastric cancer by an integrative analysis of lncRNA and mRNA expression. Oncotarget. 7(49):80990-81002. 4. Huang T et al. (2016) A new method for identifying causal genes of schizophrenia and anti-tuberculosis drug-induced hepatotoxicity. Scientific Reports. 6:32571. 5. Chen L et al. (2016) Identification of novel candidate drivers connecting different dysfunctional levels for lung adenocarcinoma using protein-protein interactions and a shortest path approach. Scientific Reports. 6:29849.
Subjects
Biochemistry & BiotechnologyAsk about this article
Answers come only from this article's title, abstract and keywords, each sentence pointing to where it comes from. Your question is sent to OpenAI to write the answer. Scholars Central does not store it.
More from this journal
The newest in Metabolomics:Open Access.
Perspective · 29 Dec 2025
Metabolomics: Assessing Environmental Health and Risk
Brief report · 29 Dec 2025
Metabolite Quantification: Accuracy, Standards, Applications
Conferences in this field
Upcoming conferences in this field.
Follow
New articles from what you follow go into your email digest, once you agree to alert emails.
- JournalMetabolomics:Open Access
- SubjectBiochemistry & Biotechnology
- BylineArticles whose byline prints “Tao Huang”

