AI for biomaterials and tissue engineering
I develop machine learning models, datasets, and computational tools to guide biomaterial and scaffold design. My research combines biological data, predictive modelling, and inverse design to help researchers decide what to fabricate and test.
I am a biomedical engineer and machine learning researcher at IChF PAN in Warsaw. My research connects biological data, predictive modelling, and computational design to support biomaterial development and tissue engineering.
I develop MLATE, an open-source framework for predicting scaffold printability and cell response and prioritising formulations for experimental testing. My PhD focuses on computational inverse design for biodegradable wound dressings. Alongside this, I investigate how extracellular-matrix information and structured biological knowledge can inform biomaterial and scaffold design.
Using machine learning to predict scaffold printability and cell response and support experimental prioritisation.
Related: MLATE3 articles + MSc thesis
Connecting design requirements with candidate scaffold structures for tissue engineering and regenerative applications.
Related: Computational inverse scaffold designAI-assisted geometry design
Exploring how tissue biology, extracellular-matrix information, and structured research knowledge can inform biomaterial development.
An open-source framework that uses literature-derived data and machine learning to predict scaffold printability and cell response, helping researchers prioritise candidate formulations for experimental testing.
Ongoing PhD research
Developing computational approaches that connect design requirements with candidate scaffold structures, with applications in regenerative medicine and wound healing.
Ongoing research
Investigating how information about the extracellular matrix can inform biomaterial and scaffold design, connecting tissue biology with computational approaches to regenerative medicine.
Biofabrication · Online ahead of print
Computers in Biology and Medicine ·
· 10 min read
Computers already help design scaffolds and bioreactors, yet tissue engineering still depends on making things and testing them. Why simulation has not replaced the experiment here, and what would have to change.
· 5 min read
Why I started turning the scaffold literature into data for machine learning, how the question changed over three versions, and what a tool like this can and cannot do.
New review in Gels with colleagues at IChF PAN: how bioprinting can scale biohybrid actuators in size and functional complexity. Read more: New review in Gels with colleagues at IChF PAN: how…
MLATE V3 is published online ahead of print in Biofabrication: an open-source, multi-tissue framework that predicts printability and cell response and helps prioritise scaffold formulations for experimental testing. Read more: MLATE V3 is published online ahead of print in Biofabrication:…
Released the MLATE V3 code, dataset and analysis pipeline on GitHub, with the updated web app at mlate.ir. Read more: Released the MLATE V3 code, dataset and analysis pipeline on…
I welcome research collaborations in machine learning for biofabrication, computational scaffold design, and biologically informed biomaterial development.
