Modeling and optimization of protein extraction from sunflower seed Cake: RSM and ANN-GA approaches

Sunflower seed cake (SSC) is an agricultural waste that is rich in proteins and numerous biologically active compounds. Moreover, SSC is devoid of any anti-nutritional compounds. Therefore, it can be leveraged for many food applications. In this work, SSC was explored for the extraction of proteins. Preliminary experiments on defatted and de-phenolized SSC were carried out using one-factor analysis. Protein extraction from sunflower seed cake was performed following isoelectric precipitation, and the amino acid profile was analyzed. Response surface methodology (RSM) and artificial neural networks (ANNs) were used to optimize the extraction conditions, i.e., pH (8.5-10.5), temperature (25-45°C), solvent-solid ratio (10-30 mL/g) and time (1-3 h). Under optimized conditions, the protein yield and protein content were 24.24% (RSM), 28.03% (ANN-GA), 87.17% (RSM), and 88.69% (ANN-GA). Compared to RSM, the ANN model demonstrated a notably more significant coefficient of determination in the overall output values (RSM (0.969 (protein yield), 0.989 (protein content) and ANN-GA (0.996 (protein yield), 0.996 (protein content)), showing superior performance during validation. The SSC protein isolates contained considerable quantities of all the essential amino acids except lysine. Its good nutritional index (61.87) and high crucial amino acid score (70.98) make it a high-quality protein. According to FAO standards, the amino acid score indicates the abundance of all essential amino acids, making it a helpful protein supplement for meeting dietary requirements. Furthermore, this research highlights the potential to utilize industrial byproducts as economical substrates for protein isolation efficiently. • Using ANNs, protein yield reached 28.03%, outperforming RSM in optimization. • SSC protein is high-quality, with a nutritional index of 61.87 and a good amino acid score. • ANN showed better accuracy than RSM for protein yield and content. • SSC offers a cost-effective, high-quality protein source from agricultural by-products.

Authors

Institutions

Publication Details

Journal
Journal of Agriculture and Food Research
Published
2025-06-13
DOI
https://doi.org/10.1016/j.jafr.2025.102088
Citations
1
Primary Topic
Proteins in Food Systems
Type
article
Field-Weighted Citation Impact
1.16
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Modeling and optimization of protein extraction from sunflower seed Cake: RSM and ANN-GA approaches

Piyush Kashyap, B. R. Ganesh Raj, Rahul Mehra, Syed Amir Ashraf et al.
1 citations
Journal of Agriculture and Food Research
Proteins in Food Systems
1.16
article

Modeling and optimization of protein extraction from sunflower seed Cake: RSM and ANN-GA approaches

Piyush Kashyap, B. R. Ganesh Raj, Rahul Mehra, Syed Amir Ashraf, Mohd Adnan, Maanas Sharma, Pooja Vartiya
article en
1 citations

Abstract

Sunflower seed cake (SSC) is an agricultural waste that is rich in proteins and numerous biologically active compounds. Moreover, SSC is devoid of any anti-nutritional compounds. Therefore, it can be leveraged for many food applications. In this work, SSC was explored for the extraction of proteins. Preliminary experiments on defatted and de-phenolized SSC were carried out using one-factor analysis. Protein extraction from sunflower seed cake was performed following isoelectric precipitation, and the amino acid profile was analyzed. Response surface methodology (RSM) and artificial neural networks (ANNs) were used to optimize the extraction conditions, i.e., pH (8.5-10.5), temperature (25-45°C), solvent-solid ratio (10-30 mL/g) and time (1-3 h). Under optimized conditions, the protein yield and protein content were 24.24% (RSM), 28.03% (ANN-GA), 87.17% (RSM), and 88.69% (ANN-GA). Compared to RSM, the ANN model demonstrated a notably more significant coefficient of determination in the overall output values (RSM (0.969 (protein yield), 0.989 (protein content) and ANN-GA (0.996 (protein yield), 0.996 (protein content)), showing superior performance during validation. The SSC protein isolates contained considerable quantities of all the essential amino acids except lysine. Its good nutritional index (61.87) and high crucial amino acid score (70.98) make it a high-quality protein. According to FAO standards, the amino acid score indicates the abundance of all essential amino acids, making it a helpful protein supplement for meeting dietary requirements. Furthermore, this research highlights the potential to utilize industrial byproducts as economical substrates for protein isolation efficiently. • Using ANNs, protein yield reached 28.03%, outperforming RSM in optimization. • SSC protein is high-quality, with a nutritional index of 61.87 and a good amino acid score. • ANN showed better accuracy than RSM for protein yield and content. • SSC offers a cost-effective, high-quality protein source from agricultural by-products.

Journal of Agriculture and Food ResearchVol. 22
Lovely Professional University (IN), Acharya N. G. Ranga Agricultural University (IN), Symbiosis International University (IN), University of Ha'il (SA), Swami Vivekanand College of Pharmacy (IN)
Zero hunger
Openalex Percentile: Top 21%
Proteins in Food Systems
1.16
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.