Jarkko Salojärvi

Bio: Jarkko Salojärvi is an academic researcher from University of Helsinki. The author has contributed to research in topics: Arabidopsis & Arabidopsis thaliana. The author has an hindex of 43, co-authored 88 publications receiving 8687 citations. Previous affiliations of Jarkko Salojärvi include Helsinki Institute for Information Technology & Nanyang Technological University.

Self organization of a massive document collection

Abstract: Describes the implementation of a system that is able to organize vast document collections according to textual similarities. It is based on the self-organizing map (SOM) algorithm. As the feature vectors for the documents statistical representations of their vocabularies are used. The main goal in our work has been to scale up the SOM algorithm to be able to deal with large amounts of high-dimensional data. In a practical experiment we mapped 6840568 patent abstracts onto a 1002240-node SOM. As the feature vectors we used 500-dimensional vectors of stochastic figures obtained as random projections of weighted word histograms.

Impact of diet and individual variation on intestinal microbiota composition and fermentation products in obese men

Abstract: There is growing interest in understanding how diet affects the intestinal microbiota, including its possible associations with systemic diseases such as metabolic syndrome. Here we report a comprehensive and deep microbiota analysis of 14 obese males consuming fully controlled diets supplemented with resistant starch (RS) or non-starch polysaccharides (NSPs) and a weight-loss (WL) diet. We analyzed the composition, diversity and dynamics of the fecal microbiota on each dietary regime by phylogenetic microarray and quantitative PCR (qPCR) analysis. In addition, we analyzed fecal short chain fatty acids (SCFAs) as a proxy of colonic fermentation, and indices of insulin sensitivity from blood samples. The diet explained around 10% of the total variance in microbiota composition, which was substantially less than the inter-individual variance. Yet, each of the study diets induced clear and distinct changes in the microbiota. Multiple Ruminococcaceae phylotypes increased on the RS diet, whereas mostly Lachnospiraceae phylotypes increased on the NSP diet. Bifidobacteria decreased significantly on the WL diet. The RS diet decreased the diversity of the microbiota significantly. The total 16S ribosomal RNA gene signal estimated by qPCR correlated positively with the three major SCFAs, while the amount of propionate specifically correlated with the Bacteroidetes. The dietary responsiveness of the individual’s microbiota varied substantially and associated inversely with its diversity, suggesting that individuals can be stratified into responders and non-responders based on the features of their intestinal microbiota.

Durable coexistence of donor and recipient strains after fecal microbiota transplantation.

Abstract: Fecal microbiota transplantation (FMT) has shown efficacy in treating recurrent Clostridium difficile infection and is increasingly being applied to other gastrointestinal disorders, yet the fate of native and introduced microbial strains remains largely unknown. To quantify the extent of donor microbiota colonization, we monitored strain populations in fecal samples from a recent FMT study on metabolic syndrome patients using single-nucleotide variants in metagenomes. We found extensive coexistence of donor and recipient strains, persisting 3 months after treatment. Colonization success was greater for conspecific strains than for new species, the latter falling within fluctuation levels observed in healthy individuals over a similar time frame. Furthermore, same-donor recipients displayed varying degrees of microbiota transfer, indicating individual patterns of microbiome resistance and donor-recipient compatibilities.

Pattern Recognition and Machine Learning

Abstract: Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

SPAdes, a new genome assembly algorithm and its applications to single-cell sequencing ( 7th Annual SFAF Meeting, 2012)

Abstract: The lion's share of bacteria in various environments cannot be cloned in the laboratory and thus cannot be sequenced using existing technologies. A major goal of single-cell genomics is to complement gene-centric metagenomic data with whole-genome assemblies of uncultivated organisms. Assembly of single-cell data is challenging because of highly non-uniform read coverage as well as elevated levels of sequencing errors and chimeric reads. We describe SPAdes, a new assembler for both single-cell and standard (multicell) assembly, and demonstrate that it improves on the recently released E+V-SC assembler (specialized for single-cell data) and on popular assemblers Velvet and SoapDeNovo (for multicell data). SPAdes generates single-cell assemblies, providing information about genomes of uncultivatable bacteria that vastly exceeds what may be obtained via traditional metagenomics studies. SPAdes is available online ( http://bioinf.spbau.ru/spades ). It is distributed as open source software.

Machine Learning : A Probabilistic Perspective

Abstract: Today's Web-enabled deluge of electronic data calls for automated methods of data analysis. Machine learning provides these, developing methods that can automatically detect patterns in data and then use the uncovered patterns to predict future data. This textbook offers a comprehensive and self-contained introduction to the field of machine learning, based on a unified, probabilistic approach. The coverage combines breadth and depth, offering necessary background material on such topics as probability, optimization, and linear algebra as well as discussion of recent developments in the field, including conditional random fields, L1 regularization, and deep learning. The book is written in an informal, accessible style, complete with pseudo-code for the most important algorithms. All topics are copiously illustrated with color images and worked examples drawn from such application domains as biology, text processing, computer vision, and robotics. Rather than providing a cookbook of different heuristic methods, the book stresses a principled model-based approach, often using the language of graphical models to specify models in a concise and intuitive way. Almost all the models described have been implemented in a MATLAB software package--PMTK (probabilistic modeling toolkit)--that is freely available online. The book is suitable for upper-level undergraduates with an introductory-level college math background and beginning graduate students.