| 1. |
- Romagnoni, A, et al.
(författare)
-
Comparative performances of machine learning methods for classifying Crohn Disease patients using genome-wide genotyping data
- 2019
-
Ingår i: Scientific reports. - : Springer Science and Business Media LLC. - 2045-2322. ; 9:1, s. 10351-
-
Tidskriftsartikel (refereegranskat)abstract
- Crohn Disease (CD) is a complex genetic disorder for which more than 140 genes have been identified using genome wide association studies (GWAS). However, the genetic architecture of the trait remains largely unknown. The recent development of machine learning (ML) approaches incited us to apply them to classify healthy and diseased people according to their genomic information. The Immunochip dataset containing 18,227 CD patients and 34,050 healthy controls enrolled and genotyped by the international Inflammatory Bowel Disease genetic consortium (IIBDGC) has been re-analyzed using a set of ML methods: penalized logistic regression (LR), gradient boosted trees (GBT) and artificial neural networks (NN). The main score used to compare the methods was the Area Under the ROC Curve (AUC) statistics. The impact of quality control (QC), imputing and coding methods on LR results showed that QC methods and imputation of missing genotypes may artificially increase the scores. At the opposite, neither the patient/control ratio nor marker preselection or coding strategies significantly affected the results. LR methods, including Lasso, Ridge and ElasticNet provided similar results with a maximum AUC of 0.80. GBT methods like XGBoost, LightGBM and CatBoost, together with dense NN with one or more hidden layers, provided similar AUC values, suggesting limited epistatic effects in the genetic architecture of the trait. ML methods detected near all the genetic variants previously identified by GWAS among the best predictors plus additional predictors with lower effects. The robustness and complementarity of the different methods are also studied. Compared to LR, non-linear models such as GBT or NN may provide robust complementary approaches to identify and classify genetic markers.
|
|
| 2. |
- Momozawa, Y, et al.
(författare)
-
IBD risk loci are enriched in multigenic regulatory modules encompassing putative causative genes
- 2018
-
Ingår i: Nature communications. - : Springer Science and Business Media LLC. - 2041-1723. ; 9:1, s. 2427-
-
Tidskriftsartikel (refereegranskat)abstract
- GWAS have identified >200 risk loci for Inflammatory Bowel Disease (IBD). The majority of disease associations are known to be driven by regulatory variants. To identify the putative causative genes that are perturbed by these variants, we generate a large transcriptome data set (nine disease-relevant cell types) and identify 23,650 cis-eQTL. We show that these are determined by ∼9720 regulatory modules, of which ∼3000 operate in multiple tissues and ∼970 on multiple genes. We identify regulatory modules that drive the disease association for 63 of the 200 risk loci, and show that these are enriched in multigenic modules. Based on these analyses, we resequence 45 of the corresponding 100 candidate genes in 6600 Crohn disease (CD) cases and 5500 controls, and show with burden tests that they include likely causative genes. Our analyses indicate that ≥10-fold larger sample sizes will be required to demonstrate the causality of individual genes using this approach.
|
|
| 3. |
|
|
| 4. |
|
|
| 5. |
- Zhang, Xueli, et al.
(författare)
-
CBD2 : A functional biomarker database for colorectal cancer
- 2024
-
Ingår i: iMeta. - : John Wiley & Sons. - 2770-5986 .- 2770-596X. ; 3:1
-
Tidskriftsartikel (refereegranskat)abstract
- The rapidly evolving landscape of biomarkers for colorectal cancer (CRC) necessitates an integrative, updated repository. In response, we constructed the Colorectal Cancer Biomarker Database (CBD), which collected and displayed the curated biomedicine information for 870 CRC biomarkers in the previous study. Building on CBD, we have now developed CBD2, which includes information on 1569 newly reported biomarkers derived from different biological sources (DNA, RNA, protein, and others) and clinical applications (diagnosis, treatment, and prognosis). CBD2 also incorporates information on nonbiomarkers that have been identified as unsuitable for use as biomarkers in CRC. A key new feature of CBD2 is its network analysis function, by which users can investigate the visible and topological network between biomarkers and identify their relevant pathways. CBD2 also allows users to query a series of chemicals, drug combinations, or multiple targets, to enable multidrug, multitarget, multipathway analyses, toward facilitating the design of polypharmacological treatments for CRC. CBD2 is freely available at http://www.eyeseeworld.com/cbd.
|
|
| 6. |
- Zabarovsky, Eugene R, et al.
(författare)
-
Restriction site tagged (RST) microarrays : a novel technique to study the species composition of complex microbial systems
- 2003
-
Ingår i: Nucleic Acids Research. - Oxford, United Kingdom : Oxford University Press. - 0305-1048 .- 1362-4962. ; 31:16, s. e95-
-
Tidskriftsartikel (refereegranskat)abstract
- We have developed a new type of microarray, restriction site tagged (RST), for example NotI, microarrays. In this approach only sequences surrounding specific restriction sites (i.e. NotI linking clones) were used for generating microarrays. DNA was labeled using a new procedure, NotI representation, where only sequences surrounding NotI sites were labeled. Due to these modifications, the sensitivity of RST microarrays increases several hundred-fold compared to that of ordinary genomic microarrays. In a pilot experiment we have produced NotI microarrays from Gram-positive and Gram-negative bacteria and have shown that even closely related Escherichia coli strains can be easily discriminated using this technique. For example, two E.coli strains, K12 and R2, differ by less than 0.1% in their 16S rRNA sequences and thus the 16S rRNA sequence would not easily discriminate between these strains. However, these strains showed distinctly different hybridization patterns with NotI microarrays. The same technique can be adapted to other restriction enzymes as well. This type of microarray opens the possibility not only for studies of the normal flora of the gut but also for any problem where quantitative and qualitative analysis of microbial (or large viral) genomes is needed.
|
|
