Saeed Rafieyan
Portrait of Saeed Rafieyan

PhD researcher · IChF PAN · Warsaw

Saeed Rafieyan

I build machine-learning models and datasets that predict how tissue-engineering scaffolds will print and how cells will respond to them, before anything is fabricated.

Digital Manufacturing of Biomimetic Systems group · Institute of Physical Chemistry, Polish Academy of Sciences

Now (Oct 2026): MLATE V3 is out in Biofabrication. Open to collaborations on machine learning for biofabrication.

Curriculum vitaeEmail

Research

I am a biomedical engineer and machine-learning researcher, doing my PhD in the Digital Manufacturing of Biomimetic Systems group at the Institute of Physical Chemistry, Polish Academy of Sciences, in Warsaw. My MSc in Chemical Engineering – Biomedical Engineering at Tarbiat Modares University (2022) used machine learning to predict how cells behave on cardiac tissue-engineering scaffolds, and that question has shaped my research since.

My main focus is open-source AI for tissue engineering. I develop MLATE, a framework of predictive models that helps researchers judge scaffold quality, cell response and printability before they fabricate anything; its third version is built on 2,646 literature-derived scaffold samples across 18 tissue-engineering contexts. The long-term aim is an AI-assisted virtual laboratory that cuts experimental cost and speeds up biomaterial design.

Machine learning for scaffold design
Predicting printability, cell response and overall scaffold quality from biomaterials, cell lines and printing parameters, and optimising formulations before fabrication. 4 papers →
Biofabrication and biomimetic systems
Bioprinted tissues, natural-polymer scaffolds and biohybrid actuators, with computational design in the loop. 2 papers →
Language models for biomedical literature
Domain-specific models such as TissueGPT, trained on tissue-engineering papers to support literature mining and scientific writing.
Chemical and bioprocess engineering
Machine learning and Bayesian optimisation for biorefinery processes, with collaborators at Jiangnan University, building on earlier work in process simulation and biofuel separation. 3 papers →

Also exploring: protein design with AI · AI-driven drug discovery · medical image analysis · extracellular-matrix omics.

Featured work

The MLATE V3 pipeline. Phase A is built once from the literature corpus, including data gathering, data imputation, clustering, classification, and WSSQ definition. Phase B runs for each user query, including web app development, bioink optimization, and protocol generation.
Fig. 1. From literature to dataset to models (MLATE V3).

MLATE

Machine Learning Applications in Tissue Engineering: publicly available models and data that predict how a scaffold will print and how cells will respond to it, rank candidate formulations, and suggest what to fabricate next.

Python · 2,646 scaffold samples · 130 biomaterials · 186 cell lines · 18 tissue contexts

  1. V1 2023 · Computers in Biology and Medicine
  2. V2 2024 · Biofabrication
  3. V3 2026 · Biofabrication

TissueGPTmaintained

A BioGPT language model fine-tuned on tissue-engineering literature, for summarising papers, generating domain text and supporting scientific writing.

BioGPT fine-tune · Hugging Face · CC BY 4.0

Selected publications

All 9 publications →

Recent news

All news →

Contact

Open to collaborations on machine learning for biomaterials and tissue engineering.

Raf.Biomed@gmail.com