Past events

Sven Furberg Seminar in Bioinformatics and Statistical Genomics

Thursday, October 19, 2017 - 14:30

Speaker: Dr. Eivind Valen, Group Leader at the Computational Biology Unit of the University of Bergen

Title: Searching for function in the dark matter of the genome

If you want to meet Dr. Eivind Valen, please book a time slot at https://doodle.com/poll/xnsb4gpse2kskcbn and send an email toanthony.mathelier@ncmm.uio.no. More information below and at http://www.mn.uio.no/ifi/english/research/networks/clsi/seminars/dr.-eivind-valen-lecture.html

Abstract: While most of the genome is transcribed, only a fraction codes for proteins. The remaining non-coding transcripts are largely uncharacterized and have been poetically referred to as “the dark matter of the genome”. We have found that many of these are highly regulated, but the lack of obvious conservation raises the question whether mere regulation is indeed indicative of function. Probing active translation we discovered that several of these actually harbor short "micropeptides" and that translation is considerably more pervasive than previously thought. Gene annotation has been biased against short peptides and an unbiased view could expand the catalog of genes. However, existence does not equal function and this “dark matter of the proteome” has yet to prove its significance.

Organizer: Oslo Centre for Biostatistics and Epidemiology (OCBE), Research group in Statistics and Biostatistics, Dept. of Mathematics, UiO, Big Insight and the Sven Furberg Seminars in Bioinformatics and Statistical Genomics

Location: 
Kristen Nygaards hus: Lille auditorium, Oslo

Wednesday Lunch: Robert Jensen, University of Tromsø

Wednesday, October 18, 2017 - 12:00

Speaker: Robert Jensen, head of the UiT Machine Learning Group

Title: Deep Learning Research at the UiT Machine Learning Group

Abstract: This talk will present recent deep learning research at the UiT Machine Learning Group: http://site.uit.no/ml. The talk will focus on applied and industrial areas of work, as well as our flagship strategic project on deep learning for health. Finally, some directions of foundational basic research will be briefly discussed.

The lunch starts at 12:00, and the talk will start around 12:20.

NB: Wednesday BigInsight Lunches are open to staff and students from any of the BigInsight partners, including UiO, but not to others.

Location: 
Ullevål Stadion, Sognsveien 77B

THURSDAY Biostatistical Seminar: The Tien Mai

Thursday, October 5, 2017 - 14:30

Speaker: The Tien Mai, Postdoc, Oslo Center for Biostatistics and Epidemiology, Department of Biostatistics, University of Oslo

Title: Bayesian Low-rank Matrix Completion

Abstract: Matrix completion has gained a significant interest over the past 10 years (starting by the Netflix challenge 2006). It aims at reconstructing an unknown matrix from a small subset of its (noisy) entries.  In this talk, we review some state-of-the-art approaches for matrix completion, especially on Bayesian methods. Statistical warranty for Bayesian methods is discussed together with some toy numerical experiments. We further discuss the Bi-Linear matrix completion with some open windows.

Organizer: Oslo Centre for Biostatistics and Epidemiology (OCBE), Research group in Statistics and Biostatistics, Dept. of Mathematics, UiO and Big Insight

Location: 
Domus Medica, room 2180 (outside the Department of Nutrition, second floor of DM)

THURSDAY Biostatistical Seminar: Dr. Christopher Yau

Thursday, September 21, 2017 - 14:30

Dr. Christopher Yau, Reader in Computational Biology based in the Centre for Computational Biology at the University of Birmingham will present the lecture "Probabilistic modelling approach for pseudotime estimation in single cells and populations."

Note: This biostatistics seminar is jointly organised with the Sven Furberg Seminars in Bioinformatics and Statistical Genomics.

Meeting Dr. Yau
If you want to meet Dr. Christopher Yau, please book a time slot at https://doodle.com/poll/wkxkwqb6gzqvde5v and send an email to anthony.mathelier@ncmm.uio.no.

More information below and at http://www.mn.uio.no/ifi/english/research/networks/clsi/seminars/dr.-christopher-yau-lecture%281%29.html.

Abstract
Single cell pseudotime algorithms attempt to extract temporal information from cross-sectional molecular profiles of single cells. Whilst there are a plethora of algorithmic methods for single cell pseudotime estimation, our focus has been on the development of model-based probabilistic approaches using Bayesian  inference. I shall talk about a suite of pseudotime methods that have been developed in my group and their application to single cell genomics and beyond.

Organizer: Oslo Centre for Biostatistics and Epidemiology (OCBE), Research group in Statistics and Biostatistics, Dept. of Mathematics, UiO, Big Insight and the Sven Furberg Seminars in Bioinformatics and Statistical Genomics

Location: 
Runde Auditorium, Domus Medica, Oslo

Wednesday Lunch: Epigram / Gjensidige

Wednesday, September 20, 2017 - 12:00

Speaker: Esten Leonardsen, Epigram

Title: Solving real life problems using AI: Price estimation of car damages

Abstract: Assessment of car damages has traditionally been a manual process. We will talk about how Gjensidige and Epigram is using image recognition to automate parts of the process, some of the problems we have faced and the techniques we have used to solve them.

The lunch starts at 12:00, and the talk will start around 12:20.

NB: Wednesday BigInsight Lunches are open to staff and students from any of the BigInsight partners, including UiO, but not to others.

Location: 
Spiseriet, Norwegian Computing Center

Wednesday Lunch: Election forecasts: why they are difficult and maybe useful

Wednesday, September 6, 2017 - 12:00

Speaker: Anders Løland, Assistant Research Director, Norwegian Computing Center.

Abstract: After Nate Silver's initial success in the presidential elections in 2008 and 2012, many forecasters failed completely in 2016. Why did this happen? We at 169.no are trying to forecast this year's Norwegian parliamentary election, and will describe and discuss in somewhat broad terms how and possibly why our model works. 

The lunch starts at 12:00, and the talk will start around 12:20.

NB: Wednesday BigInsight Lunches are open to staff and students from any of the BigInsight partners, including UiO, but not to others.

Location: 
Ullevål Stadion, Sognsveien 77B

The Hon. Doc. Sylvia Richardson Workshop 2017 on Statistics for the Life Sciences

Thursday, August 31, 2017 - 11:00

In the occasion of Professor Sylvia Richardson, University of Cambridge, receiving a Honorary Doctorate from the University of Oslo, we arrange a workshop in her honour. Please join us in the celebration of Sylvia and the statistics community at the University of Oslo, with presentations of some of the on going statistical research in the life sciences at our university:

The Hon. Doc. Sylvia Richardson Workshop 2017 on Statistics for the Life Sciences 

When: Thursday August 31st 2017, from 11.00-15.45
Where: Runde Auditorium, Domus Medica, UiO

The full program is now available here:
http://www.mn.uio.no/math/english/research/groups/statistics-biostatistics/events/hon-doc-richardson/index.html

Program:

11.00-11.10 Welcome
11.10-11.50 Manuela Zucknick 
11.50-12.30 Geir Storvik 
12.30-13.10 Lunch
13.10-13.50 Riccardo De Bin
13.50-14.30 Nils Lid Hjort
14.30-14.45 Coffee Break
14.45-15.45 Seven young statisticians 

No registration necessary. Please also attend the Honorary Doctorate talks on Friday September 1st, see separate event.

Welcome from org. comm. Riccardo De Bin, Arnoldo Frigessi and Ingrid Glad

Location: 
Runde Auditorium, Domus Medica, UiO

THURSDAY Biostatistical Seminar: Roderic Guigò

Thursday, June 22, 2017 - 14:30

Speaker: Roderic Guigò, Professor, Centre de Regualció Genòmica, Barcelona, Spain

Title: The molecular anatomy of the human body

Note: This biostatistics seminar is jointly organised with the Sven Furberg Seminars in Bioinformatics and Statistical Genomics. At the end of the seminar simple food and refreshments will be served.

If you want to meet Dr. Roderic Guigó, please book a time slot at https://doodle.com/poll/wattnfraexmrbexy and send an email to anthony.mathelier@ncmm.uio.no with your contact information. More information below and at http://www.mn.uio.no/ifi/english/research/networks/clsi/seminars/dr.-roderic-guig%C3%B3-lecture.html

Abstract: The pilot phase of the Genotype-Tissue Expression (GTEx) project has produced RNASeq from 1,641 samples originated from up to 43 tissues from 175 post-mortem donors, and constitutes a unique resource to investigate the human transcriptome across tissues and individuals. Clustering of samples based on gene expression recapitulates tissue types, separating solid from not solid tissues, while clustering based on splicing separates neural from non-neural tissues, suggesting that post-transcriptional regulation plays a comparatively important role in the definition of neural tissues .About 47 % of the variation in gene expression can be explained by variation of across tissues, while only 4% by variation across individuals. We find that the relative contribution of individual variation is similar for lncRNAs and for protein coding genes. However, we find that genes that vary with ethnicity are enriched in lncRNAs, whereas genes that vary with age are mostly protein coding. Among genes that vary with gender, we find novel candidates both to participate and to escape X-inactivation. In addition, by merging information on GWAS we are able to identify specific candidate genes that may explain differences in susceptibility to cardiovascular diseases between males and females and different ethnic groups. We find that genes that decrease with age are involved in neurodegenerative diseases such as Parkinson and Alzheimer and identify novel candidates that could be involved in these diseases. In contrast to gene expression, splicing varies similarly among tissues and individuals, and exhibits a larger proportion of residual unexplained variance. This may reflect that that stochastic, non-functional fluctuations of the relative abundances of splice isoforms may be more common than random fluctuations of gene expression. By comparing the variation of the abundance of individual isoforms across all GTEx samples, we find that a large fraction of this variation between tissues (84%) can be simply explained by variation in bulk gene expression, with splicing variation contributing comparatively little. This strongly suggests that regulation at the primary transcription level is the main driver of tissue specificity. Although blood is the most transcriptionally distinct of the surveyed tissues, RNA levels monitored in blood may retain clinically relevant information that can be used to help assess medical or biological conditions.

Organizer: Oslo Centre for Biostatistics and Epidemiology (OCBE), Research group in Statistics and Biostatistics, Dept. of Mathematics, UiO, Big Insight and the Sven Furberg Seminars in Bioinformatics and Statistical Genomics

Location: 
Hagen 3, Forskningsparken, Oslo

Data Science: Presentasjoner av studentprosjekter og lansering av UiO: Data Science

Friday, June 16, 2017 - 18:00

Velkommen til lansering av UiO: Data Science, et forskningssamarbeid mellom institutter, sentre og forskningsgrupper på UiO.

Under lanseringen vil studenter fra STK-INF4000 gi korte presentasjoner av sine prosjekter i Data Science. I tillegg kommer Christoph Best fra Google for å snakke om Big Data Analysis.

Vi serverer gratis mat og brus, og det blir mulig å kjøpe øl og vin.

Arrangementets aldersgrense: 18 år.

Program

  • 18:00 Dørene og servering åpner. Mingling med Data Science-studenter fra UiO
  • 19:00 Foredrag og presentasjoner på scenen
  • 21:00 (ca) Opplegg på scenen ferdig, servering og mingling til lokalet stenger klokken 22

Data Science website: http://www.ub.uio.no/kurs-arrangement/arrangementer/ureal/2017/170616DataScience.html

Location: 
Realfagsbiblioteket, Vilhelm Bjerknes' hus

TUESDAY Statistics Seminar: Double seminar - Ruth Keogh and Maximilian Coblenz

Tuesday, May 30, 2017 - 14:15

We will have two talks, separated by a pause with light refreshments.

  • Speaker: Ruth Keogh (Department of Medical Statistics,  London School of Hygiene and Tropical Medicine)
  • Title: Investigating time-varying effects in Cox regression in the presence of missing data: a strategy for imputation
  • Abstract: In Cox regression analyses it is often of interest to study whether there are time-varying effects of exposures, including as a way to test the proportional hazards assumption. I will discuss the use of multiple imputation (MI) to handle missing data on exposures in this context, to avoid the loss of efficiency and potential bias that result from the ‘complete-case’ approach of dropping individuals with missing data. White and Royston (Statistics in Medicine 2009) and Bartlett et al. (SMMR 2015) described two different MI methods suitable for use with Cox regression. However, no MI methods have been devised which handle time-varying effects of exposures. I will describe extensions of the two MI methods to this setting. I will focus on time-varying effects modelled using restricted cubic splines and will outline a model building strategy which incorporates both MI and selection of time-varying effects. I will present some results from simulation studies, showing that the proposed imputation methods perform well. Failure to account for time-varying effects results in the imputation results in biased estimates and in incorrect tests for proportional hazards, even when there are in truth no time varying effects. The methods will be illustrated using data from the Rotterdam Breast Cancer Study. 

 

  • Speaker: Maximilian Coblenz (Institute of Operations Research, Karlsruhe Institute of Technology)
  • Title: Nonparametric Estimation of Multivariate Quantiles
  • Abstract: In many applications of hydrology quantiles provide important insights in the statistical problems considered. In this paper, we focus on the estimation of multivariate quantiles based on copulas. We provide a nonparametric estimation procedure for a specific notion of multivariate quantiles. These quantiles are based on particular level sets of copulas and admit the usual probabilistic interpretation that a p-quantile comprises a probability mass p. We also explore the usefulness of a smoothed bootstrap in the estimation process. Our simulation results show that the nonparametric estimation procedure yields excellent results and that the smoothed bootstrap can be beneficially applied.
Location: 
Department of Mathematics, room Sverdrups plass (lunch area) on the 8th floor of Niels Henrik Abels hus

Wednesday Lunch: Awesome Possum

Wednesday, May 24, 2017 - 12:00

Speaker: Aleksander Bai, Senior Research Scientist at Norsk Regnesentral

Title: Awesome Possum

Abstract: We will present the Awesome Possum project where the goal is to get rid of passwords. This is an innovation project involving Telenor, Signicat, NR, NTNU, and UPM. We want to use sensors in your mobile phone to identify and authenticate you, so you never have to type another password again. We will talk about which sensors we use, how we are gathering data and what we are doing with it. We will also discuss some of the issues we have by trying to fit models into the phone itself.

The lunch starts at 12:00, and the talk will start around 12:20.

NB: Wednesday BigInsight Lunches are open to staff and students from any of the BigInsight partners, including UiO, but not to others

Location: 
Sverdrups plass (lunch area), 8th floor N. H. Abels hus, Department of Mathematics

TUESDAY Statistics Seminar: Willi Sauerbrei

Tuesday, May 9, 2017 - 14:15

Speaker: Willi Sauerbrei (Institute for Medical Biometry and Statistics, University of Freiburg)

Title: Regression model-building with continuous variables – multivariable fractional polynomials, with extensions for interactions

Abstract: In the analysis of studies in clinical epidemiology, the number of candidate variables for a regression model is often too large and a more parsimonious model is sought. Another key issue is the determination of appropriate dose-response functions for continuous covariates. Often, continuous predictors are either categorized or linearity is assumed. However, both approaches can have major disadvantages and models incorporating non-linear functions may markedly improve the fit. The method of multivariable fractional polynomials (MFP) simultaneously determines suitable functional forms for continuous covariates and eliminates uninfluential covariates (1,2,3). The method also allows categorical and binary covariates.

By analysing data in the framework of linear, logistic and Cox regression models, we discuss model-building issues with an emphasis on MFP. Extensions of MFP have been developed to investigate for interactions between continuous covariates and treatment (MFPI), between two continuous covariates (MFPIgen) and for interactions with time (non-proportional hazards, MFPT) in a Cox model (3,4,5). Using data from a large cohort study, we show that mis-modelling non-linear main effects can introduce spurious interactions between two continuous covariates. In RCTs, we illustrate that our approach has power to identify differential treatment effects, and demonstrate how to estimate and plot a continuous treatment-effect function. In a large simulation studies we could show that MFPI has advantages to several alternative approaches (5).

We conclude that MFP and its extensions for interactions are useful in multivariable model-building with continuous and categorical variables. MFP software for Stata, SAS and R is generally available (6).

Joint work with Patrick Royston (MRC Clinical Trials Unit, London, UK). For more details see http://mfp.imbi.uni-freiburg.de/

References:

  1. Royston P and Altman DG (1994): Regression using fractional polynomials of continuous covariates: parsimonious parametric modelling (with disc.) Applied Statistics, 43: 429-467
  2. Sauerbrei W and Royston P (1999): Building multivariable prognostic and diagnostic models: transformation of the predictors using fractional polynomials. Journal of the Royal Statistical Society, Series A, 162: 71-94
  3. Royston P, Sauerbrei, W (2008): ‘Multivariable Model-Building – A pragmatic approach to regression analysis based on fractional polynomials for modelling continuous variables’. Wiley.
  4. Sauerbrei W, Royston P, Look M (2007): A new proposal for multivariable modelling of time-varying effects in survival data based on fractional polynomial time-transformation. Biometrical Journal, 49: 453-473
  5. Royston P., Sauerbrei W. (2014): Interaction of treatment with a continuous variable: simulation study of power for several methods of analysis. Statistics in Medicine, 33: 4695-4708
  6. Sauerbrei W, Meier-Hirmer C, Benner A, Royston P (2006): Multivariable regression model building by using fractional polynomials: description of SAS, STATA and R programs, Computational Statistics and Data Analysis, 50: 3464-3485
Location: 
Department of Mathematics, room Sverdrups plass (lunch area) on the 8th floor of Niels Henrik Abels hus

THURSDAY Biostatistical Seminar: Jukka Corander

Thursday, May 4, 2017 - 14:15

Speaker: Jukka Corander, Professor, Oslo Centre for Biostatistics and Epidemiology, Dept. of Biostatistics, University of Oslo

Title: Fast inference for intractable ultra high-dimensional Potts models for genome sequence data

Coffee/tea served from 14:15 and the talk will start around 14:30.

Abstract: The potential for genome-wide modeling of epistasis has recently surfaced given the possibility of sequencing densely sampled populations and the emerging families of statistical interaction models. Direct coupling analysis (DCA) has earlier been shown to yield valuable predictions for single protein structures, and has recently been extended to genome-wide analysis of bacteria, identifying novel interactions in the co-evolution between resistance, virulence and core genome elements. However, earlier computational DCA methods have not been scalable to enable model fitting simultaneously to 104-105 polymorphisms, representing the upper bound of variation observed in genomic analyses of many bacterial species. We will introduce a novel inference method (SuperDCA) which employs a new scoring principle, efficient parallelization, optimization and filtering on phylogenetic information to achieve scalability for up to 105 polymorphisms. Using large population samples of Streptococcus pneumoniae, we demonstrate the ability of SuperDCA to make significant biological findings about this major human pathogen. We also show that our method can uncover weak signals of selection that are not detectable by genome-wide association analysis, even though our analysis does not require phenotypic measurements. SuperDCA thus holds considerable potential in building understanding about numerous organisms at a systems biological level.

Organizer: Oslo Centre for Biostatistics and Epidemiology (OCBE), Research group in Statistics and Biostatistics, Dept. of Mathematics, UiO and Big Insight

Location: 
Domus Medica, room 2240 (Dep. of Biochemistry)

Wednesday Lunch:

Wednesday, May 3, 2017 - 12:00

Speakers: Qinghua Liu (Sylvia) (PhD candidate, Dept of Mathematics), Vinnie Ko (PhD candidate, Dept of Mathematics), Solveig Engebretsen (PhD candidate, Dept of Biostatistics), Vera Djordjilovic (Postdoc, Dept of Biostatistics), Andrew Henry Reiner (Researcher, Dept of Biostatistics) and Andrea Cremaschi (Postdoc, Centre for Molecular Medicine)

We will have a presentation of some of the PhD candiates and resesarchers that are connected to BigInsight. They will all give a short presentation of themeselves and the project they are working on.
 
 

The lunch starts at 12:00, and the talk will start around 12:20.

 

NB: Wednesday BigInsight Lunches are open to staff and students from any of the BigInsight partners, including UiO, but not to others

Location: 
Spiseriet, Norwegian Computing Center