| 1. |
- Baltzer, Nicholas, et al.
(författare)
-
Risk stratification in cervical cancer screening by complete screening history : Applying bioinformatics to a general screening population
- 2017
-
Ingår i: International Journal of Cancer. - : Wiley. - 0020-7136 .- 1097-0215. ; 141:1, s. 200-209
-
Tidskriftsartikel (refereegranskat)abstract
- Women screened for cervical cancer in Sweden are currently treated under a one-size-fits-all programme, which has been successful in reducing the incidence of cervical cancer but does not use all of the participants' available medical information. This study aimed to use women's complete cervical screening histories to identify diagnostic patterns that may indicate an increased risk of developing cervical cancer. A nationwide case-control study was performed where cervical cancer screening data from 125,476 women with a maximum follow-up of 10 years were evaluated for patterns of SNOMED diagnoses. The cancer development risk was estimated for a number of different screening history patterns and expressed as Odds Ratios (OR), with a history of 4 benign cervical tests as reference, using logistic regression. The overall performance of the model was moderate (64% accuracy, 71% area under curve) with 61-62% of the study population showing no specific patterns associated with risk. However, predictions for high-risk groups as defined by screening history patterns were highly discriminatory with ORs ranging from 8 to 36. The model for computing risk performed consistently across different screening history lengths, and several patterns predicted cancer outcomes. The results show the presence of risk-increasing and risk-decreasing factors in the screening history. Thus it is feasible to identify subgroups based on their complete screening histories. Several high-risk subgroups identified might benefit from an increased screening density. Some low-risk subgroups identified could likely have a moderately reduced screening density without additional risk.
|
|
| 2. |
|
|
| 3. |
- Baltzer, Nicholas, et al.
(författare)
-
Stratifying Cervical Cancer Risk With Registry Data
- 2018
-
Ingår i: 2018 IEEE 14th International Conference on e-Science (e-Science 2018). - : IEEE. - 9781538691564 ; , s. 288-289
-
Konferensbidrag (refereegranskat)abstract
- The cervical cancer screening programmes in Sweden and Norway have successfully reduced the frequency of cervical cancer incidence but have not implemented any form of evaluation for screening needs. This means that the screening frequency for individuals can he suboptimal, increasing either the cost of the programme or the risk of missing an early stage cancer development. We developed a framework for assessing an individual's risk of cervical cancer based on their available screening history and computing a primary risk factor called CRS from a data-driven separation model together with multiple derived attributes. The results show that this approach is highly practical, validates against multiple established trends, and can he effective in personalizing the screening needs for individuals.
|
|
| 4. |
- Cavalli, Marco, et al.
(författare)
-
Allele specific chromatin signals, 3D interactions, and motif predictions for immune and B cell related diseases
- 2019
-
Ingår i: Scientific Reports. - : NATURE PUBLISHING GROUP. - 2045-2322. ; 9
-
Tidskriftsartikel (refereegranskat)abstract
- Several Genome Wide Association Studies (GWAS) have reported variants associated to immune diseases. However, the identified variants are rarely the drivers of the associations and the molecular mechanisms behind the genetic contributions remain poorly understood. ChIP-seq data for TFs and histone modifications provide snapshots of protein-DNA interactions allowing the identification of heterozygous SNPs showing significant allele specific signals (AS-SNPs). AS-SNPs can change a TF binding site resulting in altered gene regulation and are primary candidates to explain associations observed in GWAS and expression studies. We identified 17,293 unique AS-SNPs across 7 lymphoblastoid cell lines. In this set of cell lines we interrogated 85% of common genetic variants in the population for potential regulatory effect and we identified 237 AS-SNPs associated to immune GWAS traits and 714 to gene expression in B cells. To elucidate possible regulatory mechanisms we integrated long-range 3D interactions data to identify putative target genes and motif predictions to identify TFs whose binding may be affected by AS-SNPs yielding a collection of 173 AS-SNPs associated to gene expression and 60 to B cell related traits. We present a systems strategy to find functional gene regulatory variants, the TFs that bind differentially between alleles and novel strategies to detect the regulated genes.
|
|
| 5. |
- Baltzer, Nicholas
(författare)
-
Predictive Healthcare : Cervical Cancer Screening Risk Stratification and Genetic Disease Markers
- 2019
-
Doktorsavhandling (övrigt vetenskapligt/konstnärligt)abstract
- The use of Machine Learning is rapidly expanding into previously uncharted waters. In the medicine fields there are vast troves of data available from hospitals, biobanks and registries that now are being explored due to the tremendous advancement in computer science and its related hardware. The progress in genomic extraction and analysis has made it possible for any individual to know their own genetic code. Genetic testing has become affordable and can be used as a tool in treatment, discovery, and prognosis of individuals in a wide variety of healthcare settings. This thesis addresses three different approaches to-wards predictive healthcare and disease exploration; first, the exploita-tion of diagnostic data in Nordic screening programmes for the purpose of identifying individuals at high risk of developing cervical cancer so that their screening schedules can be intensified in search of new dis-ease developments. Second, the search for genomic markers that can be used either as additions to diagnostic data for risk predictions or as can-didates for further functional analysis. Third, the development of a Ma-chine Learning pipeline called ||-ROSETTA that can effectively process large datasets in the search for common patterns. Together, this provides a functional approach to predictive healthcare that allows intervention at early stages of disease development resulting in treatments with reduced health consequences at a lower financial burden
|
|
| 6. |
- Baltzer, Nicholas, 1983-, et al.
(författare)
-
||-ROSETTA
-
Annan publikation (övrigt vetenskapligt/konstnärligt)
|
|
| 7. |
- Cavalli, Marco, et al.
(författare)
-
Studies of liver tissue identify functional gene regulatory elements associated to gene expression, type 2 diabetes, and other metabolic diseases
- 2019
-
Ingår i: Human Genomics. - : Springer Science and Business Media LLC. - 1473-9542 .- 1479-7364. ; 13
-
Tidskriftsartikel (refereegranskat)abstract
- Background:Genome-wide association studies (GWAS) of diseases and traits have found associations to gene regions but not the functional SNP or the gene mediating the effect. Difference in gene regulatory signals can be detected using chromatin immunoprecipitation and next-gen sequencing (ChIP-seq) of transcription factors or histone modifications by aligning reads to known polymorphisms in individual genomes. The aim was to identify such regulatory elements in the human liver to understand the genetics behind type 2 diabetes and metabolic diseases.Methods: The genome of liver tissue was sequenced using 10X Genomics technology to call polymorphic positions. Using ChIP-seq for two histone modifications, H3K4me3 and H3K27ac, and the transcription factor CTCF, and our established bioinformatics pipeline, we detected sites with significant difference in signal between the alleles.Results:We detected 2329 allele-specific SNPs (AS-SNPs) including 25 associated to GWAS SNPs linked to liver biology, e.g., 4 AS-SNPs at two type 2 diabetes loci. Two hundred ninety-two AS-SNPs were associated to liver gene expression in GTEx, and 134 AS-SNPs were located on 166 candidate functional motifs and most of them in EGR1-binding sites.Conclusions:This study provides a valuable collection of candidate liver regulatory elements for further experimental validation.
|
|
| 8. |
- Garbulowski, Mateusz, et al.
(författare)
-
R.ROSETTA : an interpretable machine learning framework
- 2021
-
Ingår i: BMC Bioinformatics. - : BioMed Central (BMC). - 1471-2105. ; 22:1
-
Tidskriftsartikel (refereegranskat)abstract
- BackgroundMachine learning involves strategies and algorithms that may assist bioinformatics analyses in terms of data mining and knowledge discovery. In several applications, viz. in Life Sciences, it is often more important to understand how a prediction was obtained rather than knowing what prediction was made. To this end so-called interpretable machine learning has been recently advocated. In this study, we implemented an interpretable machine learning package based on the rough set theory. An important aim of our work was provision of statistical properties of the models and their components.ResultsWe present the R.ROSETTA package, which is an R wrapper of ROSETTA framework. The original ROSETTA functions have been improved and adapted to the R programming environment. The package allows for building and analyzing non-linear interpretable machine learning models. R.ROSETTA gathers combinatorial statistics via rule-based modelling for accessible and transparent results, well-suited for adoption within the greater scientific community. The package also provides statistics and visualization tools that facilitate minimization of analysis bias and noise. The R.ROSETTA package is freely available at https://github.com/komorowskilab/R.ROSETTA. To illustrate the usage of the package, we applied it to a transcriptome dataset from an autism case–control study. Our tool provided hypotheses for potential co-predictive mechanisms among features that discerned phenotype classes. These co-predictors represented neurodevelopmental and autism-related genes.ConclusionsR.ROSETTA provides new insights for interpretable machine learning analyses and knowledge-based systems. We demonstrated that our package facilitated detection of dependencies for autism-related genes. Although the sample application of R.ROSETTA illustrates transcriptome data analysis, the package can be used to analyze any data organized in decision tables.
|
|
| 9. |
- Kruczyk, Marcin, et al.
(författare)
-
Random Reducts : A Monte Carlo Rough Set-based Method for Feature Selection in Large Datasets
- 2013
-
Ingår i: Fundamenta Informaticae. - 0169-2968 .- 1875-8681. ; 127:1-4, s. 273-288
-
Tidskriftsartikel (refereegranskat)abstract
- An important step prior to constructing a classifier for a very large data set is feature selection. With many problems it is possible to find a subset of attributes that have the same discriminative power as the full data set. There are many feature selection methods but in none of them are Rough Set models tied up with statistical argumentation. Moreover, known methods of feature selection usually discard shadowed features, i.e. those carrying the same or partially the same information as the selected features. In this study we present Random Reducts (RR) - a feature selection method which precedes classification per se. The method is based on the Monte Carlo Feature Selection (MCFS) layout and uses Rough Set Theory in the feature selection process. On synthetic data, we demonstrate that the method is able to select otherwise shadowed features of which the user should be made aware, and to find interactions in the data set.
|
|
