This is my 25th blog post, so this seems like a good time to provide an index to those first 25 posts for ease of reference. I’ve covered a range of topics over my first two years of blogging, and managed to average almost one post per month, as suggested in my first post. Due to the rather occasional nature of my posting, most regular readers subscribe to my RSS feed using some kind of RSS feed reader. I use Google Reader for following blogs and other RSS feeds, which I find very convenient as it is web based and therefore synced across all the machines and devices I use, but there are plenty of other options. Alternatively, you can follow me on twitter, where I am @darrenjw, or my Google+ feed, as I always announce new posts on those platforms.
1. About this blog…: quick introduction to the new blog and what to expect.
2. Hypercubes in R (getting started with programming in R): Constructing, rotating and plotting (2d projections of) hypercubes in order to illustrate some elementary R programming concepts.
3. Systems biology, mathematical modelling and mountains: My review of an excellent workshop I participated in at BIRS on Multi-scale Stochastic Modeling of Cell Dynamics.
4. (Yet another) introduction to R and Bioconductor: A very quick tutorial on basic R concepts and getting started with Bioconductor – very first steps.
5. MCMC programming in R, Python, Java and C: this post showed how to implement a very simple bivariate Gibbs sampler in four different programming languages, and compared the speeds. The post has now been superseded by post number 18.
6. The last Valencia meeting on Bayesian Statistics and the future of Bayesian computation: My impressions of Bayes 9, together with some thoughts on Bayesian computing in the context of multicore CPUs, GPUs, clusters and “Big Data”.
7. Metropolis-Hastings MCMC algorithms: A quick introduction to the Metropolis algorithm, with example code in R, discussing implementation issues.
8. The pseudo-marginal approach to “exact approximate” MCMC algorithms: a simple explanation of the “pseudo-marginal” idea, which has many potential applications in Bayesian inference.
9. Introduction to the processing of short read next generation sequencing data: a quick introduction to high-throughput sequencing data, the FASTQ file format, and the use of Unix and command-line tools for initial processing and analysis of FASTQ files.
10. A quick introduction to the Bioconductor ShortRead package for the analysis of NGS data: a follow-on from post 9. where I show how to get started with the analysis of FASTQ sequencing data using R and Bioconductor.
11. Getting started with parallel MCMC: an introduction to parallel Monte Carlo algorithms and their implementation using C, the GSL, and MPI.
12. Calling C code from R: how to call a Gibbs sampler written in C from R.
13. Calling Java code from R: how to call a Gibbs sampler written in Java from R.
14. Parallel Monte Carlo with an Intel i7 Quad Core: a quick look at the potential speed-ups possible exploiting parallelisation on a laptop with a nice Quad-core CPU.
15. MCMC, Monte Carlo likelihood estimation, and the bootstrap particle filter: how the pseudo-marginal idea discussed in post number 8. can be exploited for state-space models by using a simple particle filter to construct an unbiased estimate of marginal likelihood.
16. The particle marginal Metropolis-Hastings (PMMH) particle MCMC algorithm: following on from the previous post, an explanation of the full PMMH pMCMC algorithm for simultaneous estimation of parameters and state for state-space models.
17. Java math libraries and Monte Carlo simulation codes: a post bemoaning the lack of anything quite like the GSL C library in Java, but highlighting some reasonable alternatives (COLT, Parallel COLT and Apache Commons Math).
18. Gibbs sampler in various languages (revisited): an updated version of post number 5, including detailed timings. I also take the opportunity to include new languages PyPy, Groovy and Scala.
19. Faster Gibbs sampling MCMC from within R: How to call MCMC code written in C, C++ and Java from R, with timing details.
20. Stochastic Modelling for Systems Biology, second edition: A quick introduction to the 2nd edition of my book, together with a tutorial introduction to the associated CRAN R package, smfsb, for simulation and inference of stochastic kinetic network models and other Markov processes.
21. Particle filtering and pMCMC using R: code for particle filtering and particle MCMC for Markov processes, in R.
22. Review of “Parallel R” by McCallum and Weston: my somewhat critical review of this book.
23. Lexical scope and function closures in R: an introduction to notions of variable scope and closure in the context of R.
24. Parallel particle filtering and pMCMC using R and multicore: a discussion of the parallelisation of the particle filtering code from post 21. using R’s high-level parallelisation constructs.
25. Catalogue of my first 25 blog posts: this post!
Should I ever manage another 25 posts, I’ll do a similar review of the next 25 at post number 50…