Conor Lawless

12 August 2019

Inference for dynamic simulation models

I recently bought a copy of the latest edition of Darren Wilkinson’s book: Stochastic Modelling for Systems Biology because I’m interested to see what he has to say about Approximate Bayesian Computation (ABC). Browsing through, I am reminded of the very useful example in Chapter 11: Inference for stochastic kinetic Models, which describes a likelihood-free method for Bayesian inference of dynamic simulation model parameters. This approach involves using a bootstrap particle filter for marginal likelihood estimation. ... Read more

21 November 2017

Visualising correlation in an AR(1) process

Autoregression models are a type of stochastic, dynamic process. They are a mathematical representation of some value that varies with time, where the variation includes a random, unpredictable component. Using a computer to generate (pseudo-)random numbers, we can generate a set of simulated values across time that are consistent with this kind of model. Stochastic simulations aim to capture the random component in the process and so are usually different every time they’re run. ... Read more

11 October 2017

Quantifying the strength & significance of genetic interactions

Recently, I have been analysing some functional genomics and drug screen datasets. The techniques I use are similar to those I developed while working on and using a method called Quantitative Fitness Analysis (QFA) (Addinall et al. (2011), Lawless et al. (2010)). QFA is a method for screening the health of up to tens of thousands of microbial cell populations (examples in picture above). It is typically used to search for genes interacting with a gene of particular interest. ... Read more

07 May 2017

Translating maths into code: writing the tattoo function in Python

In a previous post I discussed a mathematical function which represents a range of different list-comprehensions and how their output can be visualised. Here I’ll describe in detail how we can evaluate this function on a computer, using the Python programming language as an example. Here is the mathematical notation for the tattoo function $t$ again: $$t(\theta, p) = \left\{ \sum_{k=-1}^{n}e^{\frac{2 \pi i k^p}{\theta}} \mid n \in -1,\dots,\theta \right\}$$ What should we expect from mathematical expressions in code? ... Read more