Dario Arcos-Díaz, PhD

Building a multi-agent system for drug target discovery

Thu, 19 Mar 2026 00:00:00 +0000

I built a multi-agent system in plain Python that takes a disease name and autonomously finds potential drug targets by querying public bioinformatics databases. It matched real-world pharma consensus on Alzheimer's, Parkinson's, and schizophrenia.

Classifying brain regions from gene expression RNA-seq data

Sun, 01 Mar 2026 00:00:00 +0000

I trained an XGBoost classifier on GTEx bulk RNA-seq to distinguish 13 brain regions. It got 95% accuracy, and the top identified genes are also known tissue markers in neuroscience.

COVID-19 Germany local incidence and ICU occupancy (in German)

Fri, 01 Jan 2021 00:00:00 +0000

Some time ago at the beginning of the COVID-19 pandemic, I decided to create a Twitter bot to automatically gather the latest data in Germany and share it to the Twittersphere. I also created and deployed a dashboard heroku app.

Graph Convolutional Networks for Fraud Detection of Bitcoin Transactions

Sun, 15 Dec 2019 00:00:00 +0000

Detecting fraudulent transactions is essential in keeping financial systems trustworthy. Here I illustrate an end-to-end approach of node classification by graph neural networks to identify suspicious transactions.

Fitbit activity and sleep data: a time-series analysis with Generalized Additive Models

Sun, 01 Apr 2018 00:00:00 +0000

This is a time-series analysis of activity and sleep data from a fitbit user throughout a year. I use this data to predict an additional year of the life of the user using Generalized Additive Models.

Personalized Medicine Kaggle Competition

Sat, 07 Oct 2017 00:00:00 +0000

This was my approach to the Personalized Healthcare Redefining Cancer Treatment Kaggle competition. The goal of the competition was to create a machine learning algorithm that can classify genetic variations that are present in cancer cells.

Exploratory analysis of Medicare drug cost data 2011-2015

Mon, 06 Feb 2017 00:00:00 +0000

Health care systems world-wide are under pressure due to the high costs associated with disease. In this post, I performed an analysis of Medicare data in the USA. Furthermore I used a drug-disease open database to cluster the costs by disease. I identified the most expensive diseases (mostly chronic diseases such as Diabetes) and the most expensive medicines.

Visualizing parallel event series in Python

Mon, 06 Feb 2017 00:00:00 +0000

In this post, I will use Python to visualize two different series of events, plotting them on top of each other to gain insights from time series data.

Simulating the revenue of a product with Monte-Carlo random walks

Sat, 15 Oct 2016 00:00:00 +0000

I take a look at how we can model the future revenue of a product by making certain assumptions and running a Monte Carlo simulation.

About Me

Mon, 01 Jan 0001 00:00:00 +0000

Hi! I’m Dario, a Senior Data Scientist at BASF with a PhD in Molecular Neuroscience (University of Heidelberg / Max Planck Institute). I work at the intersection of machine learning and the life sciences.

What I do: I build ML solutions for complex data, including graph-based simulations of production networks, knowledge graphs integrating multi-source data, and genomic foundation-model applications. Before BASF, I spent three years at IBM developing graph analytics, EHR-based predictive models, and anomaly-detection systems.