Call for abstracts: StanConnect 2021 - Biomedical Statistics

Following the earlier inquiry, I am now putting out this call, blatantly copying from @bnicenboim’s proposal for Cognitive Science.

I think we should aim for a date in late October/November, but I’m open to suggestions.

So the tentative instructions are :

  • Reply to this post with a title and an abstract of no more than 250 words describing the research you’d like to present;
  • Please include your time zone in your reply;
  • Being selected for giving a talk implies the commitment of: (i) giving a 15-20 minute talk and (ii) preparing a notebook (Knitr/Jupyter) with your research come meeting time.

The catch is that we’re very short on time, seeing as proposal needs to be submitted to the SGB by Monday, 26th.

So I’ll re-tag everybody on the previous thread in an attempt to speed things along. Apologies in advance for the rush.

@harrelfe, @lcomm, @stemangiola, @wds15 @martinmodrak, @charlesm93, @sambrilleman, @mitzimorris, @ermeel, @arya @avehtari @tarheel @Max_Mantei @OriolAbril @Simon @andrjohns @rtrangucci @jsocolar




title: Coding the BYM2 model for disconnected graphs in Stan or how I stopped worrying and learned to love PC priors

In A note on intrinsic Conditional Autoregressive models for disconnected graphs, Freni-Sterrantino show how to implement the BYM2 model for use with areal data where the graph structure of the map is not fully connected. In this talk, we present an implementation of this proposal in Stan which illustrates use of the Penalized Complexity framework. Finally, we discuss the challenges of extending this to more complicated spatio-temporal data.

time zone: -5 GMT. (currently US Eastern Daylight Time)


Hi @maxbiostat. Thanks for the offer, but I’m actually now working outside of academia and health research, and so wouldn’t have the time to focus on / contribute to this. Best of luck with pulling it together though!

Normalized power prior models in Stan

The power prior (Chen and Ibrahim, 2000) enables practitioners to utilize historical data to obtain a flexible informative prior. However, the prior may be sensitive to hyperparameter specification. Typically, such sensitivity is eliminated by treating the hyperparameter as random, that is, utilizing a hierarchical model. Unfortunately, for the vast majority of models, the normalizing constant of the power prior is unavailable.

In this talk, we present computational techniques to estimate normalized power prior (NPP) models using Stan. Specifically, we utilize a two-stage process that first estimates the normalizing constant for a wide range of values, and then utilizes a second round of sampling to obtain samples from the posterior density using the normalized power prior. The methodology and software will be invaluable to practitioners and regulators who wish to incorporate prior knowledge on the basis of historical data, but are skeptical of tuning parameters.

Time Zone:
Eastern (US)


I’m bumping this because we have not received many abstracts so far. Bear in mind this does not need to be conference-grade work: submissions of partial work or promising ideas is more than welcome too.

1 Like

I am currently thinking about two possible submissions, happy to get feedback what people find most interesting:

  1. Using Hidden Markov Models as a complement/alternative to survival models (as discussed at Fitting HMMs with time-varying transition matrices using brms: A prototype)
  2. Bayesian modelling of organoid growth: In cystic fibrosis research (and presumably elsewhere) a common way to asses organoid growth is to compute area under the growth curve and compre this value between groups. It however turns out that using a simple hierarchical linear model on the logarithm of the size of the organoids adjusting for baseline size fits the data much better and provides more interpretable results.

Title: Summarising enzyme information from online databases using Stan and Arviz

Authors: Teddy Groves and Areti Tsigkinopoulou

Time Zone: Copenhagen (currently GMT+2)

Many systems biology applications require information about the kinetic behaviour of metabolic enzymes, which can be found in databases like BRENDA, which records measurements of kinetic parameters for a wide range of organisms, enzymes and experimental conditions. However, it is not straightforward to use this information in kinetic models as the raw measurements are often scarce, inconsistent and difficult to aggregate. For example, if a certain enzyme/substrate combination’s Michaelis constant has only been measured once, but additional measurements are available for the same substrate and a similar enzyme (say with the same first three digits of the EC number), it is not straightforward to say what is the best guess as to the true value of the
original measured quantity.

Our analysis addresses the problem of summarising the information in BRENDA about kinetic parameters using a nested multilevel statistical model implemented in Stan. We demonstrate how representing structural information like the enzyme classification number and substrate improves the model’s predictive accuracy. We present our model’s results in a web application which we hope will allow systems biologists to more easily use the BRENDA data.


Title: Automated kinetic modelling in Stan and its application to the methionine cycle

Authors: Nicholas Cowie and Teddy Groves

Time Zone: Copenhagen (GMT +2/1 depending on daylight savings)

The methionine cycle is a fundamental pathway in human metabolism. Its intermediates participate in a variety of mechanisms competing for the same resources. These functions all occur simultaneously resulting in a highly regulated pathway with approximately 6 allosteric effectors. In order to understand the operation of the methionine cycle we constructed a kinetic model as a system of ODEs, where the state variables are the metabolite concentrations and the fluxes are constrained by mechanistic rate laws. However, these systems are described as ‘sloppy parameter’ systems, where the marginal parameter distributions can be large, yet still display tight posterior predictions. Furthermore, measuring these parameters independently is obscured by measuring the system in in vitro conditions, as opposed to those experienced in vivo. This prevents the standard practice of placing tight priors on the parameter values.

Our software automates network construction, and conducts parameter sampling in Stan conditioned on in vivo measurements of metabolite concentrations, fluxes, and protein concentrations. The resultant posterior draws take advantage of the HMC algorithm to efficiently sample the highly correlated parameter space and generate sets that describe the kinetic model equally well, despite their broad marginal distributions. This approach is applied to the methionine cycle as an ideal case of a highly regulated and non-linear pathway.


I’m happy to announce that the @SGB have approved our proposal for the tentative date of October 19th, 2021 10 AM EST.

I’m also very happy to announce the stellar biostatistician @harrelfe has agreed to be a discussant at our event.

I’m still ironing out some kinks and will post here with more details. Thanks everyone!




Hi, everyone,

Here’s an update:

Dear all,

The tentatitive talk for the Biomedical chapter of the StanConnect 2021 are:

  • “Coding the BYM2 model for disconnected graphs in Stan or how I stopped worrying and learned to love PC priors” by @mitzimorris

  • “Normalized power prior models in Stan” by Ethan Alt (PhD student), North Carolina University (Chapel Hill).

  • “Summarising enzyme information from online databases using Stan and Arviz” by @Teddy_Groves1
    (Postdoctoral researcher), Technical University of Denmark.

  • “Automated kinetic modelling in Stan and its application to the methionine cycle” by @ncowie (PhD student), Technical University of Denmark.

  • “Using Hidden Markov Models as a complement/alternative to survival models” by @martinmodrak (Researcher), Czech Academy of Sciences.

  • “A Bayesian Approach to Representing Variability in Space in Cardiac Action Potential Properties” by
    Alejandro Nieto Ramos (PhD student), Rochester Institute of Technology.

and @harrelfe will be a discussant!

I have put together a Github repository with talk abstracts.

The event is scheduled to take place virtually via Zoom on 19 October 2021, 10 AM-1PM EST.
Register here.

It’ll be great to see many of you there.

There’s also a Datamethods announcement.


Above you say 10am - 1pm EST but on the eventbrite page it says 11 - 1. Just curious which it is?

1 Like

It has to be 10AM, otherwise we won’t have time for everyone to speak and also discuss stuff. I’ll edit the eventbrite thing. Thank you very much for spotting that.

1 Like

My calendar has 11 - 1 since eventbrite emailed me a meeting so I wouldn’t have joined until 11!

1 Like

I’ll send an update email warning users! Thanks!

Just want to make totally sure, since we have such a crazy time system in the US:
10am EST is 11am EDT, so in strict terms there was never any conflict in the above.

@maxbiostat, I assume that in fact the start is at 10am EDT (GMT -4). If, on the other hand, you really did mean 10am EST above (GMT -5), then that’s 11am Eastern Time (which until 7 November means EDT = GMT - 4).

1 Like

I meant 10 AM EST (GMT -5). Thanks for the clarification. I’ll send an email via enventbrite.

@maxbiostat, how do I get on? I didn’t see a link to the actual event on EventBrite.


For anyone interested: there’s a zoom link that’s buried in one of the emails.

DM me if you can’t find it and I’ll send it to you.