Short bio

Saeed Rafieyan develops machine learning models, datasets, and computational tools for biomaterial design, biofabrication, and tissue engineering.

Education

  1. PhD

    IChF PAN · Warsaw, Poland

    • Digital Manufacturing of Biomimetic Systems group.
    • Research topic: computational inverse design for biodegradable wound dressings.
  2. MSc in Chemical Engineering – Biomedical Engineering

    Tarbiat Modares University · Tehran, Iran

    Thesis: Predicting cell behavior on cardiac tissue engineering scaffolds using machine learning algorithms

    • GPA: 3.78 / 4
  3. BSc in Chemical Engineering

    Tafresh University · Tafresh, Iran

    Thesis: Simulation of the biodiesel production process with Aspen HYSYS

Research experience

  1. PhD researcher

    Digital Manufacturing of Biomimetic Systems group, IChF PAN · Warsaw, Poland

    • Developing computational approaches that connect design requirements with candidate scaffold structures, with applications in regenerative medicine and wound healing.
  2. Research assistant – data scientist

    Jiangnan University, Dr Madadi’s group · Wuxi, China

    • Machine-learning and deep-learning models for biofuel production and process optimisation, contributing to a peer-reviewed article in Bioresource Technology (2025).
  3. Research assistant – data scientist

    Tarbiat Modares University, Dr Fakhroleslam’s group · Tehran, Iran

    • Machine-learning and deep-learning models for distillation and separation processes; chemical-engineering text mining.
  4. Research assistant – data scientist

    Tarbiat Modares University, Prof Vasheghani-Farahani’s group · Tehran, Iran

    • Led the development of MLATE through three published versions as first author, including its literature-derived datasets and web app (mlate.ir).
    • Developed TissueGPT, a language model adapted to tissue-engineering literature, released on Hugging Face.
  5. Data scientist

    Men’s Health & Reproductive Health Research Centre, Shohadaye Tajrish Hospital · Tehran, Iran

    • Multimodal deep learning for semen analysis and drug-effectiveness prediction from clinical data and imaging.

Industry experience

  1. Data scientist

    HiWEB · Tehran, Iran

    • Churn, next-purchase and purchase-value models for marketing; ASR and LLM-based quality control for Persian call-centre audio; dashboards in Flask and Plotly Dash.
  2. Data scientist

    YecomSoft · Tehran, Iran

    • Persian NLP and text-to-speech for audiobook production.
  3. Django web developer (intern)

    MAPSA · Tehran, Iran

    • Backend and REST APIs for an online retail platform.

Publications

  1. MLATE V3: An Open-Source Multi-Tissue AI Framework for Data-Driven Optimization of 3D-Printed and Bioprinted Scaffolds

    Rafieyan S, Partovi Nasr M, Ansari E, Kheradvar Kolour A, Banimohamad-Shotorbani B, Vasheghani-Farahani E

    Biofabrication · · doi:10.1088/1758-5090/aeb162

  2. Acetone-butanol-ethanol fermentation products recovery: Challenges and opportunities

    Rafieyan S, Boojari MA, Setayeshnia A, et al.

    Chemical Engineering Research and Design · · Review · doi:10.1016/j.cherd.2024.04.021

  3. MLATE: Machine learning for predicting cell behavior on cardiac tissue engineering scaffolds

    Rafieyan S, Vasheghani-Farahani E, Baheiraei N, Keshavarz H

    Computers in Biology and Medicine · · doi:10.1016/j.compbiomed.2023.106804

  4. A Review of Recent Advances in Natural Polymer-Based Scaffolds for Musculoskeletal Tissue Engineering

    Fan J, Abedi-Dorcheh K, Sadat Vaziri A, Kazemi-Aghdam F, Rafieyan S, et al.

    Polymers · · Review · doi:10.3390/polym14102097

  5. Predicting cell behavior on cardiac tissue engineering scaffolds using machine learning algorithms

    Rafieyan S

    MSc thesis, Tarbiat Modares University, Tehran ·

  6. Process Simulation of Biodiesel Production from Soybean Oil with Aspen HYSYS: A Comparative Study of two different processes

    Rafieyan S, Bayat A

    11th International Chemical Engineering Congress & Exhibition (IChEC 2020), Fouman, Iran · · Conference paper

Software and data

  • MLATE (Machine Learning Applications in Tissue Engineering). 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.
  • TissueGPT (doi:10.57967/hf/8917). A language model adapted to tissue-engineering literature for exploring domain-specific text generation and research assistance.

Service

  • Peer reviewer for IOP Publishing journals (IOP Trusted Reviewer), including Physics in Medicine and Biology, Biomedical Materials, Biomedical Physics & Engineering Express, Engineering Research Express and Progress in Biomedical Engineering; also Results in Surfaces and Interfaces (Elsevier).

Skills

Machine learning
Regression, classification, clustering, feature engineering, model selection, Bayesian optimisation, gradient boosting (XGBoost, LightGBM, CatBoost), scikit-learn
Deep learning and NLP
PyTorch, TensorFlow, Hugging Face Transformers, CNNs, RNNs, multimodal learning, LLM fine-tuning, text mining, topic modelling
Programming and tools
Python, NumPy, pandas, Matplotlib, Plotly, Dash, Streamlit, Flask, FastAPI, Docker, GitHub Actions, PostgreSQL, MySQL, SQLite
Laboratory
Cell culture, MTT assay, decellularisation, hydrogel preparation, scaffold fabrication, 3D printing, freeze-drying

Languages

  • English · Proficient
  • Persian · Native

Additional training

Show 6 certificates

References

Available on request.