Saeed Rafieyan

Projects

Models, datasets and tools, mostly for tissue engineering and biofabrication.

MLATE active

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.

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.

Role
Lead developer
Years
2022–present
Methods
Gradient boosting, deep and tabular foundation models, Bayesian optimisation, LLM-assisted protocol generation
Data
Literature-derived scaffold dataset, published with the code

TissueGPT maintained

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

Role
Developer
Years
2024–present
Methods
Causal language-model fine-tuning (Hugging Face Transformers)
Licence
CC BY 4.0

ECM Program Atlas active

A reproducible, Matrisome-based framework for mapping extracellular-matrix gene programs across human tissues, validated on external transcriptomic and protein-level data, to support ECM-informed biomaterial design.

Years
2026–present
Methods
NMF program discovery, ECM-specificity controls, classical and deep classifiers
Data
GTEx, Tabula Sapiens, MatrisomeDB
Licence
MIT

Other and earlier work

  • PGG – Porous Geometry Generation · 2026 · Generates printable porous sphere lattices (STL and STEP) and gyroids (STL) from a plain-text spec, tuned to a target porosity. · Code
  • md2docx · 2026 · Converts Markdown into editable Word documents with native equations, for scientific writing. · Code