| 1. |
|
|
| 2. |
|
|
| 3. |
- Bäcklin, Christofer L., 1983-, et al.
(författare)
-
Developer-Friendly and Computationally Efficient Predictive Modeling without Information Leakage : The emil Package for R
- 2018
-
Ingår i: Journal of Statistical Software. - : JOURNAL STATISTICAL SOFTWARE. - 1548-7660. ; 85:13, s. 1-30
-
Tidskriftsartikel (refereegranskat)abstract
- Data driven machine learning for predictive modeling problems (classification, regression, or survival analysis) typically involves a number of steps beginning with data preprocessing and ending with performance evaluation. A large number of packages providing tools for the individual steps are available for R, but there is a lack of tools for facilitating rigorous performance evaluation of the complete procedures assembled from them by means of cross-validation, bootstrap, or similar methods. Such a tool should strictly prevent test set observations from influencing model training and meta- parameter tuning, so- called information leakage, in order to not produce overly optimistic performance estimates. Here we present a new package for R denoted emil (evaluation of modeling without information leakage) that offers this form of performance evaluation. It provides a transparent and highly customizable framework for facilitating the assembly, execution, performance evaluation, and interpretation of complete procedures for classification, regression, and survival analysis. The components of package emil have been designed to be as modular and general as possible to allow users to combine, replace, and extend them if needed. Package emil was also developed with scalability in mind and has a small computational overhead, which is a key requirement for analyzing the very big data sets now available in fields like medicine, physics, and finance. First package emil's functionality and usage is explained. Then three specific application examples are presented to show its potential in terms of parallelization, customization for survival analysis, and development of ensemble models. Finally a brief comparison to similar software is provided.
|
|
| 4. |
- Bäcklin, Christofer, 1983-
(författare)
-
Machine Learning Based Analysis of DNA Methylation Patterns in Pediatric Acute Leukemia
- 2015
-
Doktorsavhandling (övrigt vetenskapligt/konstnärligt)abstract
- Acute lymphoblastic leukemia (ALL) is the most common pediatric cancer in the Nordic countries. Recent evidence indicate that DNA methylation (DNAm) play a central role in the development and progression of the disease.DNAm profiles of a collection of ALL patient samples and a panel of non-leukemic reference samples were analyzed using the Infinium 450k methylation assay. State-of-the-art machine learning algorithms were used to search the large amounts of data produced for patterns predictive of future relapses, in vitro drug resistance, and cytogenetic subtypes, aiming at improving our understanding of the disease and ultimately improving treatment.In paper I, the predictive modeling framework developed to perform the analyses of DNAm dataset was presented. It focused on uncompromising statistical rigor and computational efficiency, while allowing a high level of modeling flexibility and usability. In paper II, the DNAm landscape of ALL was comprehensively characterized, discovering widespread aberrant methylation at diagnosis strongly influenced by cytogenetic subtype. The aberrantly methylated regions were enriched for genes repressed by polycomb group proteins, repressively marked histones in healthy cells, and genes associated with embryonic development. A consistent trend of hypermethylation at relapse was also discovered. In paper III, a tool for DNAm-based subtyping was presented, validated using blinded samples and used to re-classify samples with incomplete phenotypic information. Using RNA-sequencing, previously undetected non-canonical aberrations were found in many re-classified samples. In paper IV, the relationship between DNAm and in vitro drug resistance was investigated and predictive signatures were obtained for seven of the eight therapeutic drugs studied. Interpretation was challenging due to poor correlation between DNAm and gene expression, further complicated by the discovery that random subsets of the array can yield comparable classification accuracy. Paper V presents a novel Bayesian method for multivariate density estimation with variable bandwidths. Simulations showed comparable performance to the current state-of-the-art methods and an advantage on skewed distributions.In conclusion, the studies characterize the information contained in the aberrant DNAm patterns of ALL and assess its predictive capabilities for future relapses, in vitro drug sensitivity and subtyping. They also present three publicly available tools for the scientific community to use.
|
|
| 5. |
- Bäcklin, Christofer, 1983-, et al.
(författare)
-
Self-tuning density estimation based on Bayesian averaging of adaptive kernel density estimations yields state-of-the-art performance
- 2018
-
Ingår i: Pattern Recognition. - : ELSEVIER SCI LTD. - 0031-3203 .- 1873-5142. ; 78, s. 133-143
-
Tidskriftsartikel (refereegranskat)abstract
- Non-parametric probability density function (pdf) estimation is a general problem encountered in many fields. A promising alternative to the dominating solutions, kernel density estimation (KDE) and Gaussian mixture modeling, is adaptive KDE where kernels are given individual bandwidths adjusted to the local data density. Traditionally the bandwidths are selected by a non-linear transformation of a pilot pdf estimate, containing parameters controlling the scaling, but identifying parameters values yielding competitive performance has turned out to be non-trivial. We present a new self-tuning (parameter free) pdf estimation method called adaptive density estimation by Bayesian averaging (ADEBA) that approximates pdf estimates in the form of weighted model averages across all possible parameter values, weighted by their Bayesian posterior calculated from the data. ADEBA is shown to be simple, robust, competitive in comparison to the current practice, and easily generalize to multivariate distributions. An implementation of the method for R is publicly available.
|
|
| 6. |
- Carlsson Almlöf, Jonas, et al.
(författare)
-
Novel risk genes for systemic lupus erythematosus predicted by random forest classification
- 2017
-
Ingår i: Scientific Reports. - : Springer Science and Business Media LLC. - 2045-2322. ; 7:1
-
Tidskriftsartikel (refereegranskat)abstract
- Genome-wide association studies have identified risk loci for SLE, but a large proportion of the genetic contribution to SLE still remains unexplained. To detect novel risk genes, and to predict an individual's SLE risk we designed a random forest classifier using SNP genotype data generated on the "Immunochip" from 1,160 patients with SLE and 2,711 controls. Using gene importance scores defined by the random forest classifier, we identified 15 potential novel risk genes for SLE. Of them 12 are associated with other autoimmune diseases than SLE, whereas three genes (ZNF804A, CDK1, and MANF) have not previously been associated with autoimmunity. Random forest classification also allowed prediction of patients at risk for lupus nephritis with an area under the curve of 0.94. By allele-specific gene expression analysis we detected cis-regulatory SNPs that affect the expression levels of six of the top 40 genes designed by the random forest analysis, indicating a regulatory role for the identified risk variants. The 40 top genes from the prediction were overrepresented for differential expression in B and T cells according to RNA-sequencing of samples from five healthy donors, with more frequent over-expression in B cells compared to T cells.
|
|
| 7. |
- Darmanis, Spyros, et al.
(författare)
-
ProteinSeq : high-performance proteomic analyses by proximity ligation and next generation sequencing
- 2011
-
Ingår i: PLOS ONE. - : Public Library of Science (PLoS). - 1932-6203. ; 6:9, s. e25583-
-
Tidskriftsartikel (refereegranskat)abstract
- Despite intense interest, methods that provide enhanced sensitivity and specificity in parallel measurements of candidate protein biomarkers in numerous samples have been lacking. We present herein a multiplex proximity ligation assay with readout via realtime PCR or DNA sequencing (ProteinSeq). We demonstrate improved sensitivity over conventional sandwich assays for simultaneous analysis of sets of 35 proteins in 5 μl of blood plasma. Importantly, we observe a minimal tendency to increased background with multiplexing, compared to a sandwich assay, suggesting that higher levels of multiplexing are possible. We used ProteinSeq to analyze proteins in plasma samples from cardiovascular disease (CVD) patient cohorts and matched controls. Three proteins, namely P-selectin, Cystatin-B and Kallikrein-6, were identified as putative diagnostic biomarkers for CVD. The latter two have not been previously reported in the literature and their potential roles must be validated in larger patient cohorts. We conclude that ProteinSeq is promising for screening large numbers of proteins and samples while the technology can provide a much-needed platform for validation of diagnostic markers in biobank samples and in clinical use.
|
|
| 8. |
- Edfeldt, Katarina, 1979-, et al.
(författare)
-
DcR3, TFF3 and Midkine are Novel Serum Biomarkers in Small Intestinal Neuroendocrine Tumors
- 2017
-
Ingår i: Neuroendocrinology. - : S. Karger AG. - 0028-3835 .- 1423-0194. ; 105:2, s. 170-181
-
Tidskriftsartikel (refereegranskat)abstract
- Small intestinal neuroendocrine tumors (SI-NETs) are amine- and peptide producing neoplasms. Most patients display metastases at the time of diagnosis, they have an unpredictable individual disease course and the tumors are often therapy resistant. Chromogranin A (CgA) and 5-hydroxyindoleacetic acid (5-HIAA) are the clinically most used biomarkers today, but there is a great need for novel diagnostic and prognostic biomarkers and new therapeutic targets. Sixty-nine biomarkers were screened in serum from 23 SI-NET patients and 23 healthy controls using multiplex PLA (proximity ligation assay). A refined method, PEA (proximity extension assay), was used to analyze 76 additional biomarkers. Statistical testing and multivariate classification were performed. Immunohistochemistry and ELISA assays were performed in an extended cohort. Using PLA, 19 biomarkers showed a significant difference in serum concentrations between patients and controls, and PEA revealed difference in concentrations in 13 proteins. Multivariate classification analysis revealed decoy receptor 3 (DcR3), trefoil factor 3 (TFF3) and Midkine to be good biomarkers for disease, which was confirmed by ELISA analysis. All three biomarkers were expressed in tumor tissue. DcR3 concentrations were elevated in patients with stage IV disease. High concentrations of DcR3 and TFF3 were correlated to poor survival. DcR3, TFF3 and Midkine exhibited elevated serum concentrations in SI-NET patients compared to healthy controls, and DcR3 and TFF3 were associated with poor survival. DcR3 seems to be a marker for liver metastases while TFF3 and Midkine may be new diagnostic biomarkers for SI-NETs.
|
|
| 9. |
|
|
| 10. |
|
|
