Publications
9 publications · 4 journal articles, 3 reviews, 1 thesis, 1 conference paper
No publications match these filters.
2026
Bioprinting-Enabled Customization of Biohybrid Actuators: Scaling Dimensions and Functional Complexity
Gels, 12(10), 923 · · Review · doi:10.3390/gels12100923
Abstract
Biohybrid actuators integrate living contractile cells with engineered materials, combining biological force generation with the structural and functional control offered by synthetic components. However, translating engineered muscle tissue into reproducible, high-performance biohybrid robots remains limited by tissue organization, matrix degradation, force transmission, and long-term functional stability. This review analyzes how biofabrication parameters and material properties influence tissue maturation and actuator-level performance, with particular emphasis on bioprinting. We compare muscle cell sources; extrusion-based, embedded, and light-assisted fabrication strategies; and scaffold biomaterials using reported structural and functional outcomes. We also evaluate electrical and optical activation and mechanical conditioning, distinguishing their roles in controlling contraction and promoting maturation. The comparison highlights a gap between architectural control during fabrication and reproducible robotic performance: methods that produce complex muscle constructs do not necessarily yield integrated devices with validated force transmission or locomotion. Tissue maturation, tissue–material interfaces, and nutrient transport emerge as closely coupled priorities for scaling functional constructs. We conclude with a framework for standardized benchmarking and discuss multimaterial printing, data-driven design, and feedback control as complementary routes toward more reproducible and capable biohybrid actuators.BibTeX
@article{pajouhande2026bioprinting, title = {{Bioprinting-Enabled Customization of Biohybrid Actuators: Scaling Dimensions and Functional Complexity}}, author = {Pajouhande, Maede and Celikkin, Nehar and Rafieyan, Saeed and Tirelli, Maria Celeste and Maiullari, Fabio and Piletskaya, Maryia and Costantini, Marco}, journal = {Gels}, year = {2026}, volume = {12}, number = {10}, pages = {923}, doi = {10.3390/gels12100923} }MLATE V3: An Open-Source Multi-Tissue AI Framework for Data-Driven Optimization of 3D-Printed and Bioprinted Scaffolds
Biofabrication · · doi:10.1088/1758-5090/aeb162 In press
CodeAppAbstract
3D (bio)printing is increasingly used for scaffold fabrication in tissue engineering; however, identifying suitable biomaterial compositions, cell types, cell densities, and printing conditions remains largely empirical, time-consuming, and costly. Practical application of machine learning in this field is further limited by the scarcity of comprehensive datasets based on pre-fabrication variables, the lack of integrated frameworks for prioritizing candidate scaffold formulations, and the limited availability of accessible tools for non-technical users. To address these challenges, we developed MLATE V3 (Machine Learning Applications in Tissue Engineering V3), an open-source, data-driven, multi-tissue framework for scaffold prediction, prioritization, and experimental planning. An open-source dataset comprising 2,646 samples, 130 biomaterials, and 186 cell lines, including co-culture systems, across 18 tissue engineering contexts was compiled and used to benchmark machine learning, deep learning, tabular transformer-based, and tabular foundation models for predicting cell response and printability from pre-fabrication variables. The best-performing models achieved weighted F1-scores of 0.773 for cell response and 0.806 for printability. These predictive outputs were subsequently integrated through the Weighted Synergistic Scaffold Quality (WSSQ) metric, which combines cell response and printability using adjustable weights to provide a unified criterion for candidate ranking. WSSQ was then incorporated into a Bayesian optimization framework to search user-defined biomaterial compositions and printing-parameter ranges and prioritize candidate scaffold formulations for experimental evaluation. To make the complete workflow accessible to researchers, MLATE V3 was implemented as an open-source web platform that enables users to select predictive models, define design spaces, perform WSSQ-based optimization, and generate step-by-step fabrication protocols through an LLM-assisted procedure-generation module. Overall, MLATE V3 provides an extensible decision-support framework that connects literature-derived data, predictive modeling, multi-objective scaffold ranking, optimization, and experimental planning. The platform is intended to narrow the experimental search space and generate candidate formulations for subsequent experimental validation rather than to serve as experimentally validated optimizer.BibTeX
@article{rafieyan2026mlate, title = {{MLATE V3: An Open-Source Multi-Tissue AI Framework for Data-Driven Optimization of 3D-Printed and Bioprinted Scaffolds}}, author = {Rafieyan, Saeed and Partovi Nasr, Minoo and Ansari, Elham and Kheradvar Kolour, Alireza and Banimohamad-Shotorbani, Behnaz and Vasheghani-Farahani, Ebrahim}, journal = {Biofabrication}, year = {2026}, month = oct, doi = {10.1088/1758-5090/aeb162}, note = {In press} }
2025
Data-driven insights for enhanced cellulose conversion to 5-hydroxymethylfurfural using machine learning
Bioresource Technology, 430, 132582 · · doi:10.1016/j.biortech.2025.132582
Abstract
Converting cellulose into 5-Hydroxymethylfurfural (HMF) provides a promising strategy for creating bio-based chemicals, offering sustainable alternatives to petroleum-based materials in polymers, biofuels, and pharmaceuticals. However, the efficient production of HMF from cellulose is challenged by the complex interplay of numerous operational variables. This study develops a machine learning (ML) model to optimize HMF production and conducts a feature importance analysis to identify the key factors affecting HMF yield. Additionally, a Bayesian optimization is employed for multi-objective optimization aimed at maximizing HMF yield. A comprehensive dataset, sourced from existing literature, was subjected to statistical analysis to elucidate the influence of each factor on HMF production. Among the eight models evaluated, the CatBoost Regressor emerged as the most effective, delivering robust predictive performance with R2 of 0.76 during testing and exhibiting low RMSE (4.72) and MAE (5.2) values. Feature importance analysis revealed that operational conditions, particularly time and temperature, were the most significant, accounting for 41.0% of the variability, followed by catalyst properties at 33.0% and solvent properties at 26.0%. The ML-based optimization achieved an HMF yield of 48.1%, with relative errors of −1% and 2.5% in the first (47.6%) and second (49.3%) runs of experimental validation, respectively. This research showcases ML’s ability to address challenges in cellulose-to-HMF conversion, offering insights for optimizing production and advancing sustainable manufacturing.BibTeX
@article{qiao2025data, title = {{Data-driven insights for enhanced cellulose conversion to 5-hydroxymethylfurfural using machine learning}}, author = {Qiao, Yanming and Kargaran, Ehsan and Ji, Hao and Madadi, Meysam and Rafieyan, Saeed and Liu, Dan}, journal = {Bioresource Technology}, year = {2025}, volume = {430}, pages = {132582}, doi = {10.1016/j.biortech.2025.132582} }
2024
A practical machine learning approach for predicting the quality of 3D (bio)printed scaffolds
Biofabrication, 16(4), 045014 · · doi:10.1088/1758-5090/ad6374
CodeAbstract
3D (Bio)printing is a highly effective method for fabricating tissue engineering scaffolds, renowned for their exceptional precision and control. Artificial intelligence (AI) has become a crucial technology in this field, capable of learning and replicating complex patterns that surpass human capabilities. However, the integration of AI in tissue engineering is often hampered by the lack of comprehensive and reliable data. This study addresses these challenges by providing one of the most extensive datasets on 3D-printed scaffolds. It provides the most comprehensive open-source dataset and employs various AI techniques, from unsupervised to supervised learning. This dataset includes detailed information on 1,171 scaffolds, featuring a variety of biomaterials and concentrations—including 60 biomaterials such as natural and synthesized biomaterials, crosslinkers, enzymes, etc.—along with 49 cell lines, cell densities, and different printing conditions. We used over 40 machine learning and deep learning algorithms, tuning their hyperparameters to reveal hidden patterns and predict cell response, printability, and scaffold quality. The clustering analysis using KMeans identified five distinct ones. In classification tasks, algorithms such as XGBoost, Gradient Boosting, Extra Trees Classifier, Random Forest Classifier, and LightGBM demonstrated superior performance, achieving higher accuracy and F1 scores. A fully connected neural network with six hidden layers from scratch was developed, precisely tuning its hyperparameters for accurate predictions. To promote future research, the developed dataset and the associated code are publicly available on www.github.com/saeedrafieyan/MLATE.BibTeX
@article{rafieyan2024practical, title = {{A practical machine learning approach for predicting the quality of 3D (bio)printed scaffolds}}, author = {Rafieyan, Saeed and Ansari, Elham and Vasheghani-Farahani, Ebrahim}, journal = {Biofabrication}, year = {2024}, volume = {16}, number = {4}, pages = {045014}, doi = {10.1088/1758-5090/ad6374} }Acetone-butanol-ethanol fermentation products recovery: Challenges and opportunities
Chemical Engineering Research and Design, 205, 640–664 · · Review · doi:10.1016/j.cherd.2024.04.021
Abstract
Nowadays, global warming is one of the most significant concerns in modern societies, which entails considerable costs to the environment, health, economy, etc. Fossil fuels play an essential role in this phenomenon and finding an alternative for them has been the research topic for the past few decades. Among the array of options available, biofuel stands out as a highly effective and environmentally sustainable alternative. Biobutanol presents properties like high heating value, low volatility, high viscosity, and low corrosion. Additionally, it is a much safer option for use, and its ability to blend with gasoline and other fuels turns it into a suitable and promising renewable alternative. Biobutanol can be produced from the agricultural industry's residues by the acetone-butanol-ethanol (ABE) fermentation process. The separation and purification of biobutanol from the fermentation broth account for 40 % of the plant budget, which is notable. Various separation techniques like liquid-liquid extraction, membrane perstraction, gas stripping, vacuum flash, membrane pervaporation, thermopervaporation, reverse osmosis, adsorption, etc., are applied. A befitting separation method must produce sufficient butanol concentration in the output and reduce the final product's cost so biobutanol can compete economically with other fuels. This work reviewed the existing processes for the separation and purification of butanol from ABE fermentation, including advanced methods. All methods will be discussed in detail considering environmental and economic parameters and each technique's superiors and challenges.BibTeX
@article{rafieyan2024acetone, title = {{Acetone-butanol-ethanol fermentation products recovery: Challenges and opportunities}}, author = {Rafieyan, Saeed and Boojari, Mohammad Amin and Setayeshnia, Ali and Fakhroleslam, Mohammad and Sánchez-Ramírez, Eduardo and Bay, Mohammad Saber and Segovia-Hernández, Juan Gabriel}, journal = {Chemical Engineering Research and Design}, year = {2024}, volume = {205}, pages = {640--664}, doi = {10.1016/j.cherd.2024.04.021} }
2023
MLATE: Machine learning for predicting cell behavior on cardiac tissue engineering scaffolds
Computers in Biology and Medicine, 158, 106804 · · doi:10.1016/j.compbiomed.2023.106804
CodeAbstract
Cardiovascular disease is one of the leading causes of mortality worldwide and is responsible for millions of deaths annually. One of the most promising approaches to deal with this problem, which has spread recently, is cardiac tissue engineering (CTE). Many researchers have tried developing scaffolds with different materials, cell lines, and fabrication methods to help regenerate heart tissue. Machine learning (ML) is one of the hottest topics in science and technology, revolutionizing many fields and changing our perspective on solving problems. As a result of using ML, some scientific issues have been resolved, including protein-folding, a challenging problem in biology that remained unsolved for 50 years. However, it is not well addressed in tissue engineering. An AI-based software was developed by our group called MLATE (Machine Learning Applications in Tissue Engineering) to tackle tissue engineering challenges, which highly depend on conducting costly and time-consuming experiments. For the first time, to the best of our knowledge, a CTE scaffold dataset was created by collecting specifications from the literature, including different materials, cell lines, and fabrication methods commonly used in CTE scaffold development. These specifications were used as variables in the study. Then, the CTE scaffolds were rated based on cell behaviors such as cell viability, growth, proliferation, and differentiation on the scaffold on a scale of 0–3. These ratings were considered a function of the variables in the gathered dataset. It should be stated that this study was merely based on information available in the literature. Then, twenty-eight ML algorithms were applied to determine the most effective one for predicting cell behavior on CTE scaffolds fabricated by different materials, compositions, and methods. The results indicated the high performance of XGBoost with an accuracy of 87%. Also, by implementing ensemble learning algorithms and using five algorithms with the best performance, an accuracy of 93% with the AdaBoost Classifier and Voting Classifier was achieved. Finally, the open-source software developed in this study was made available for everyone by publishing the best model along with a step-by-step guide to using it online at: https://github.com/saeedrafieyan/MLATE.BibTeX
@article{rafieyan2023mlate, title = {{MLATE: Machine learning for predicting cell behavior on cardiac tissue engineering scaffolds}}, author = {Rafieyan, Saeed and Vasheghani-Farahani, Ebrahim and Baheiraei, Nafiseh and Keshavarz, Hamidreza}, journal = {Computers in Biology and Medicine}, year = {2023}, volume = {158}, pages = {106804}, doi = {10.1016/j.compbiomed.2023.106804} }
2022
A Review of Recent Advances in Natural Polymer-Based Scaffolds for Musculoskeletal Tissue Engineering
Polymers, 14(10), 2097 · · Review · doi:10.3390/polym14102097
PDFAbstract
The musculoskeletal (MS) system consists of bone, cartilage, tendon, ligament, and skeletal muscle, which forms the basic framework of the human body. This system plays a vital role in appropriate body functions, including movement, the protection of internal organs, support, hematopoiesis, and postural stability. Therefore, it is understandable that the damage or loss of MS tissues significantly reduces the quality of life and limits mobility. Tissue engineering and its applications in the healthcare industry have been rapidly growing over the past few decades. Tissue engineering has made significant contributions toward developing new therapeutic strategies for the treatment of MS defects and relevant disease. Among various biomaterials used for tissue engineering, natural polymers offer superior properties that promote optimal cell interaction and desired biological function. Natural polymers have similarity with the native ECM, including enzymatic degradation, bio-resorb and non-toxic degradation products, ability to conjugate with various agents, and high chemical versatility, biocompatibility, and bioactivity that promote optimal cell interaction and desired biological functions. This review summarizes recent advances in applying natural-based scaffolds for musculoskeletal tissue engineering.BibTeX
@article{fan2022review, title = {{A Review of Recent Advances in Natural Polymer-Based Scaffolds for Musculoskeletal Tissue Engineering}}, author = {Fan, Jingzhi and Abedi-Dorcheh, Keyvan and Sadat Vaziri, Asma and Kazemi-Aghdam, Fereshteh and Rafieyan, Saeed and Sohrabinejad, Masoume and Ghorbani, Mina and Rastegar Adib, Fatemeh and Ghasemi, Zahra and Klavins, Kristaps and Jahed, Vahid}, journal = {Polymers}, year = {2022}, volume = {14}, number = {10}, pages = {2097}, doi = {10.3390/polym14102097} }Predicting cell behavior on cardiac tissue engineering scaffolds using machine learning algorithms
MSc thesis, Tarbiat Modares University, Tehran ·
BibTeX
@mastersthesis{rafieyan2022predicting, title = {{Predicting cell behavior on cardiac tissue engineering scaffolds using machine learning algorithms}}, author = {Rafieyan, Saeed}, school = {Tarbiat Modares University, Tehran}, year = {2022}, month = feb }
2020
Process Simulation of Biodiesel Production from Soybean Oil with Aspen HYSYS: A Comparative Study of two different processes
11th International Chemical Engineering Congress & Exhibition (IChEC 2020), Fouman, Iran · · Conference paper
PDFAbstract
Biodiesel is one of the most promising green fuels at present which can be easily obtained from various vegetable oils/animal fats and even waste cooking oils. In recent years, researchers have investigated a lot about biodiesel production processes. In order to produce biodiesel in an industrial scale and optimize the process, it's needed firstly to simulate the production process to obtain information consistent with real data. In this respect, the vegetable oil fatty acid components (as a feedstock) were defined in detail. Afterward, two different processes suggested in the literature for biodiesel production were compared in terms of resource consumption and biodiesel yield.BibTeX
@inproceedings{rafieyan2020process, title = {{Process Simulation of Biodiesel Production from Soybean Oil with Aspen HYSYS: A Comparative Study of two different processes}}, author = {Rafieyan, Saeed and Bayat, Ahmad}, booktitle = {11th International Chemical Engineering Congress \& Exhibition (IChEC 2020), Fouman, Iran}, year = {2020}, month = apr, url = {https://www.researchgate.net/publication/345254236_Process_Simulation_of_Biodiesel_Production_from_Soybean_Oil_with_Aspen_HYSYS_A_Comparative_Study_of_two_different_processes} }