Sign in

David Selby

@davidselby.bsky.social
118 followers 318 following 60 posts

Data science researcher working on applications of machine learning in health at DFKI, getting the most out of small data. Reproducible #Rstats evangelist and unofficial British cultural ambassador to Rhineland-Palatinate 🇩🇪 selbydavid.com

PostsRepliesMedia
David Selby @davidselby.bsky.social · 28/08/2026
We are recruiting! Researchers, PhD students and postdocs in biologically informed AI and machine learning jobs.dfki.de/en/vacancy/p...
jobs.dfki.de
PhD/Postdoc Researcher in Biologically Informed Machine Learning and AI | DFKI
Interessieren Sie sich für maschinelles Lernen jenseits der „Black Box“? Hier am Deutschen Forschungszentrum für Künstliche Intelligenz mit Sitz in Kaiserslautern suchen wir begeisterte Forscher*innen...
010
Reposted by David Selby
Clarence Eckerson Jr./Streetfilms @streetfilms.bsky.social · 09/08/2026
What's the Paris Trombone? I have spoken to some of the biggest bike experts in the world. Asked them. And like 98.3% have never heard of it. We made this fun quick short in the midst of making another film 3 years ago in Paris.
1349
David Selby @davidselby.bsky.social · 16/07/2026
Similarly, being able to bunny hop a bike up a kerb is a useful skill, but all kerbs at crossings and entrances should be dropped and flush so this is never normally necessary.
000
David Selby @davidselby.bsky.social · 16/06/2026
New blog post: The Great Bordstein Conspiracy. 🧑‍🦽🚴🚗 Exploring how and why badly designed crossings make life harder for all German road users. Malice or incompetence? With reference to @rantyhighwayman.bsky.social selbydavid.com/2026/06/16/b...
selbydavid.com
The Great Bordstein Conspiracy
Germany’s “dropped” kerbs are not flush, making life worse for everybody. But is it the result of car-centric civil engineering and flawed DIN standards, or a conspiracy to get cyclists buying bikes w...
020
David Selby @davidselby.bsky.social · 09/06/2026
Britisches Rezept auf Deutsch: Kedgeree 🐟🍚 Curryreis-Pfanne mit geräuchertem Fisch britishfoodgermany.substack.com/p/kedgeree
britishfoodgermany.substack.com
Kedgeree
Britisches Curry-Reisgericht mit geräuchertem Fisch
010
David Selby @davidselby.bsky.social · 19/05/2026
My bilingual blog as City Cycling Star for Kaiserslautern. From tomorrow, 3 weeks without a car, clocking up as many kilometres by bike as I can. 🚲 login.stadtradeln.de/specials/blo...
login.stadtradeln.de
STADTRADELN - Radeln für ein gutes Klima
Beim Wettbewerb STADTRADELN trittst du 21 Tage in die Pedale für mehr Radförderung, Klimaschutz und Lebensqualität in deiner Kommune.
010
David Selby @davidselby.bsky.social · 20/04/2026
Introducing the Full Palatine Breakfast - an adaptation of the English breakfast to my adopted hometown in Germany. Saumagen, kassler and sauerkraut with bratwurst, eggs and beans open.substack.com/pub/britishf...
open.substack.com
The Full Palatine Breakfast (De Vollpälzer!)
Rhineland-Palatinate's answer to the English fry-up: a cooked breakfast featuring Saumagen, Kassler and Kartoffelpuffer... with eggs and beans.
000
David Selby @davidselby.bsky.social · 16/04/2026
The missing role of pastry in German Wurstkultur britishfoodgermany.substack.com/p/meat-pies-...
britishfoodgermany.substack.com
Where is the meat pie in the Metzgerei?
The missing role of pastry in German sausage culture
000
David Selby @davidselby.bsky.social · 14/04/2026
New post: Which component of a full breakfast is surprisingly tricky to track down in Germany? britishfoodgermany.substack.com/p/english-br...
britishfoodgermany.substack.com
English breakfast on the continent
Bringing home the bacon in Germany - how to distinguish back bacon from Rückenspeck and Frühstücksspeck for your next fry-up.
000
David Selby @davidselby.bsky.social · 07/03/2026
Stocking up for the weekend open.substack.com/pub/britishf...
open.substack.com
Scones and clotted cream in Germany
Finding ingredients for a proper cream tea
000
David Selby @davidselby.bsky.social · 03/03/2026
It's British week at Aldi Germany, and they are doing scones! But what are scones and how easy is it to find, make and eat an authentic cream tea in Germany? open.substack.com/pub/britishf...
open.substack.com
Scones and clotted cream in Germany
Finding ingredients for a proper cream tea
000
David Selby @davidselby.bsky.social · 20/02/2026
Interested in ML beyond the black box? The DFKI is looking for enthusiastic researchers to join the growing department Data Science and its Applications. If you want to work on ML for drug discovery, knowledge graphs and agentic AI, we have the project for you! jobs.dfki.de/intern/aussc...
000
David Selby @davidselby.bsky.social · 19/02/2026
What is the connection between Italian spaghetti Westerns and German baked beans? Where can you find Heinz Beans for a reasonable price? What separates cassoulet from Currywurst? All these important culinary questions answered in my latest newsletter britishfoodgermany.substack.com/p/baked-bean...
britishfoodgermany.substack.com
Baked beans in German supermarkets
How to improve your Bohnen-Saucen-Verhältnis
111
David Selby @davidselby.bsky.social · 14/02/2026
Having lived in Germany for 3 years, I'd like to share what I have learnt about adapting to and from 🇩🇪 and 🇬🇧 culture. Commonalities between haggis and Saumagen. Why Pudding is not pudding. Where to buy baked beans. Und was ist eigentlich ein Pie? britishfoodgermany.substack.com/p/welcome-to...
britishfoodgermany.substack.com
Welcome to British Food in Germany
When in Rome, never pay €2.50 for baked beans
000
David Selby @davidselby.bsky.social · 01/12/2025
Once again it's time for Secret Santa, powered by data science algorithms in #Rstats! selbydavid.com/2016/12/07/s...
selbydavid.com
Secret Santa in R
Our office just exchanged presents for Secret Santa, a tradition where each person is randomly assigned someone else to give an anonyous gift. One of the challenges of Secret Santa is keeping the pair...
020
David Selby @davidselby.bsky.social · 10/10/2025
Announcing a new special guest edition in Digital Health! Everything on patient-reported outcomes in mHealth, including algorithmic treatment and measurement allocation, N-of-1 trials, preference learning & handling subjective measurements. 📲 Take a look! journals.sagepub.com/topic/collec...
011
David Selby @davidselby.bsky.social · 05/09/2025
New preprint: how many patients could we save with LLM priors? Exploring the effect of eliciting informative priors for Bayesian clinical trials. arxiv.org/abs/2509.04250
arxiv.org
How many patients could we save with LLM priors?
Imagine a world where clinical trials need far fewer patients to achieve the same statistical power, thanks to the knowledge encoded in large language models (LLMs). We present a novel framework for h...
010
David Selby @davidselby.bsky.social · 19/08/2025
📊📉📈 Better data visualizations with AI: can LLMs provide constructive critiques on existing charts? We explore how generative AI can automate #MakeoverMonday -type exercises, suggesting improvements to existing charts. 📄 New preprint + benchmark dataset 💽 arxiv.org/abs/2508.05637
arxiv.org
Automated Visualization Makeovers with LLMs
Making a good graphic that accurately and efficiently conveys the desired message to the audience is both an art and a science, typically not taught in the data science curriculum. Visualisation makeo...
000
David Selby @davidselby.bsky.social · 05/08/2025
🧬BioDisco, an open-source biomedical hypothesis generator, uses agentic LLMs, knowledge graphs and literature search, with an iterative self-evaluation loop to discover novel relations, significantly outperforming other architectures. Preprint: arxiv.org/abs/2508.01285
arxiv.org
BioDisco: Multi-agent hypothesis generation with dual-mode evidence, iterative feedback and temporal evaluation
Identifying novel hypotheses is essential to scientific research, yet this process risks being overwhelmed by the sheer volume and complexity of available information. Existing automated methods often...
000
David Selby @davidselby.bsky.social · 29/07/2025
New: unofficial @quarto.org template for the upcoming @realaaai.bsky.social 2026 conference. Write your submission in Markdown with reproducible, inline computations! github.com/Selbosh/aaai...
github.com
GitHub - Selbosh/aaai2026-quarto: Unofficial Quarto template for the AAAI-2026 Conference
Unofficial Quarto template for the AAAI-2026 Conference - Selbosh/aaai2026-quarto
000
David Selby @davidselby.bsky.social · 21/07/2025
What is a "Visible Neural Network"? It's a new kind of deep learning model for multi-omics, where prior knowledge and interpretability are baked into the architecture. 📄 We reviewed dozens of models, datasets & applications, and call for better tools/benchmarks: www.frontiersin.org/journals/art...
frontiersin.org
Frontiers | Visible neural networks for multi-omics integration: a critical review
BackgroundBiomarker discovery and drug response prediction are central to personalized medicine, driving demand for predictive models that also offer biologi...
041
Reposted by David Selby
cwcyau.bsky.social @cwcyau.bsky.social · 06/03/2025
Health Research From Home Hackathon 2025 | This hackathon is being held by Health Research From Home Partnership led by the @OfficialUoM. Register your interest now: health-research-from-home.github.io/DataAnalysis...
health-research-from-home.github.io
Health Research From Home Hackathon 2025
7-9 May 2025
001
David Selby @davidselby.bsky.social · 17/03/2025
Just published: 'Had enough of experts? Quantitative retrieval from large language models' Can LLMs, having read the scientific literature, offer us useful numerical info to help fill in missing data and fit statistical models, like a real human expert? We investigate: doi.org/10.1002/sta4...
doi.org
Had Enough of Experts? Quantitative Knowledge Retrieval From Large Language Models
Large language models (LLMs) have been extensively studied for their ability to generate convincing natural language sequences; however, their utility for quantitative information retrieval is less w...
010
David Selby @davidselby.bsky.social · 13/03/2025
New blog post: on all the English I have had to learn since moving to Germany 🇬🇧 🇩🇪 selbydavid.com/2025/03/13/d...
selbydavid.com
Learning to Denglisch
At the railway station, a lost-looking US soldier asked me if I spoke English. Do I? At times it feels like it, but the Germans keep me guessing. Since moving to Germany, I have been continually teste...
010
David Selby @davidselby.bsky.social · 06/03/2025
New blog post: Alternatives to @overleaf.com for #rstats, reproducible writing and collaboration selbydavid.com/2025/03/04/o...
selbydavid.com
041
Reposted by David Selby
Nature Reviews Genetics @natrevgenet.nature.com · 04/03/2025
New online! Beyond the black box with biologically informed neural networks
nature.com
Beyond the black box with biologically informed neural networks
Nature Reviews Genetics, Published online: 04 March 2025; doi:10.1038/s41576-025-00826-1Biologically informed neural networks promise to lead to more explainable, data-driven discoveries in genomics, drug development and precision medicine. Selby et al.…
081
David Selby @davidselby.bsky.social · 04/03/2025
Thrilled to share our latest publication in @natrevgenet.bsky.social. We explore how deep learning models infused with prior knowledge—biologically-informed neural networks or BINNs—offer better predictive accuracy and interpretability in multi-omics data analysis. www.nature.com/articles/s41...
nature.com
Beyond the black box with biologically informed neural networks - Nature Reviews Genetics
Biologically informed neural networks promise to lead to more explainable, data-driven discoveries in genomics, drug development and precision medicine. Selby et al. highlight emerging opportunities, ...
0125
David Selby @davidselby.bsky.social · 20/02/2025
Paper just accepted in Stat! Can LLMs replace experts as sources of numerical information, such as Bayesian prior distributions for statistical models, or filling in missing values in tabular datasets for ML tasks? We evaluate on applications across different fields. arxiv.org/abs/2402.07770
arxiv.org
Had enough of experts? Quantitative knowledge retrieval from large language models
Large language models (LLMs) have been extensively studied for their abilities to generate convincing natural language sequences, however their utility for quantitative information retrieval is less w...
000
David Selby @davidselby.bsky.social · 10/01/2025
How might one redesign this data visualization to avoid using much-maligned 'plunger plots'? #visualisation From www.nature.com/articles/s41...
Plot showing stacked bar plots with error bars to visualize normalized ROC AUC of different machine learning models, before and after fine-tuning for four hours. The main insight is that TabPFN, a tabular foundation model, outperforms tree-based methods such as random forests and XGBoost.
010
David Selby @davidselby.bsky.social · 20/12/2024
Pleased to present our poster at #NeurIPS2024 workshop on Bayesian Decisionmaking and Uncertainty! 🎉 Our work explores using large language models for eliciting expert-informed Bayesian priors. Elicited lots of discussion with the ML community too! Check it out: neurips.cc/virtual/2024...
Sebastian Vollmer, David Selby and Yuichiro Iwashita present their poster, "Had enough of experts? Bayesian prior elicitation from Large Language Models" at the NeurIPS Bayesian Decisionmaking and Uncertainty Workshop 2024 in Vancouver, Canada.Sebastian Vollmer, David Selby and Yuichiro Iwashita present their poster, "Had enough of experts? Bayesian prior elicitation from Large Language Models" at the NeurIPS Bayesian Decisionmaking and Uncertainty Workshop 2024 in Vancouver, Canada.
000
David Selby @davidselby.bsky.social · 20/12/2024
Excited to share our new preprint: Visible neural networks for multi-omics integration: a critical review! 🌟 We systematically analyse 86 studies on biologically informed neural networks (BINNs/VNNs), highlighting trends, challenges, interesting ideas & opportunities. www.biorxiv.org/content/10.1...
biorxiv.org
Visible neural networks for multi-omics integration: a critical review
Biomarker discovery and drug response prediction is central to personalized medicine, driving demand for predictive models that also offer biological insights. Biologically informed neural networks (B...
040