Home -> Work -> Bio-Prodict
2016 - 2025

Senior Data Scientist at Bio-Prodict

Led AI initiatives for protein analysis and bioinformatics. Built and deployed machine learning systems for mutation effect prediction, achieving production-grade accuracy on complex biological data. Direct client engagement and technical leadership.

Primary focus: Helix pathogenicity prediction platform
Protein Engineering & DNA Diagnostics
9 yrs
Tenure
8+
Publications
Visit Bio-Prodict
Overview

What we do

Bio-Prodict is focused on delivering solutions for guiding scientific research in the field of protein engineering, molecular design and DNA diagnostics. We apply novel approaches to data mining, storage and analysis of protein data and combine these with state-of-the-art analysis methods and visualization tools to create custom-built information systems for protein superfamilies.

I am primarily involved in the production of the Helix product, leading a team that builds on the results of previous research to predict pathogenicity for different protein variants.

Responsibilities

What I do

As Senior Data Scientist, I was responsible for both the technical direction and the client-facing work that turned AI capabilities into delivered value.

AI Solution Development

Developing AI-based solutions in Bioinformatics, including exploratory research, system design, and hardware provisioning

ML Model Building

Building and adapting state-of-the-art machine learning models for protein analysis

Deployment & Infrastructure

Deploying solutions to on-premise hardware or cloud environments. Managing Helix cloud capabilities

Team Leadership

Leading and mentoring students and junior team members

Client Relations

Conducting direct client communications, including sales talks and technical support

Conference Representation

Representing Bio-Prodict at international scientific conferences

Technical Skills

Technologies & expertise

Building production AI systems for bioinformatics requires a pragmatic technology stack—tools that work reliably at scale and can be maintained by research teams.

Core Languages
Python Rust SQL R Java
ML Frameworks
PyTorch Keras TensorFlow scikit-learn
Cloud & DevOps
GCP Kubernetes Cloud Run Git CI/CD
Databases
PostgreSQL MySQL MongoDB ElasticSearch
Publications

Research contributions

Academic publications and preprints from my work in computational biology and machine learning.

2025
Navigating the Sequence-Function Landscape: AI-Driven Discovery of Unseen and Synergistic Mutations in an Amine Transaminase
Weigmann KFG, Heijl S, Vroling B, Michels N, Menke MJ, Doerr M, et al.
ACS Catalysis, Volume 15 Issue 17
2023
Understanding structure-guided variant effect predictions using 3D convolutional neural networks
Ramakrishnan G, Baakman C, Heijl S, Vroling B, van Horck R, Hiraki J, et al.
Frontiers in Molecular Biosciences, 10, 1204157
Cited by: 7
2022
Helix engineering: Combining the power of 3DM with AI to disrupt protein engineering
Heijl S, Boot J, Bergh T, Vroling B, Joosten HJ, Brier B.
Conference Publication
2022
Functional Analysis Identifies Damaging CHEK2 Missense Variants Associated with Increased Cancer Risk
Boonen RACM, Wiegant WW, Celosse N, Vroling B, Heijl S, et al.
Cancer Research, 82(4), 615-631
Cited by: 40
2022
Breast cancer risks associated with missense variants in breast cancer susceptibility genes
Dorling L, Carvalho S, Allen J, Parsons MT, ..., Heijl S, et al.
Genome Medicine, 14(1), 51
Cited by: 25
2021
White paper: the helix pathogenicity prediction platform
Vroling B, Heijl S.
arXiv preprint arXiv:2104.01033
Cited by: 7
2020
Mind the gap: preventing circularity in missense variant prediction
Heijl S, Vroling B, van den Bergh T, Joosten HJ.
bioRxiv, 2020.05.06.080424
Cited by: 4
2016
Inherited arrhythmia syndromes, how to identify pathogenic mutations?
Vroling B, van den Bergh T, Alders M, Heijl S, Tanck M, Deprez RLD, et al.
Conference Publication
Back to Work