Tessera
Folgen

David Selby

@davidselby.bsky.social

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 🇩🇪 https://selbydavid.com

60 Posts117 Follower318 Folgt
David Selby@davidselby.bsky.social · 3mo ago

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...

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...

selbydavid.com

David Selby@davidselby.bsky.social · last yr.

📊📉📈 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

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...

arxiv.org

David Selby@davidselby.bsky.social · last yr.

🧬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

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...

arxiv.org

David Selby@davidselby.bsky.social · last yr.

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...

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...

frontiersin.org

David Selby@davidselby.bsky.social · last yr.

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...

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...

doi.org

David Selby@davidselby.bsky.social · last yr.

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...

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, ...

nature.com

David Selby@davidselby.bsky.social · 2y ago

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

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...

arxiv.org