 |
 |
 |
 |
 |
 |
Sains
Malaysiana 54(8)(2025): 1913-1925
http://doi.org/10.17576/jsm-2025-5408-04
MOHD HAFIS YUSWAN1,*, NORAZLINA ALI2,
SYAIFUL IZWAN ISMAIL2, BASYIRAH MUDA2, MOHAMAD HABEEB
HELMY IDRIS2, MAZIDAH MD NOR2, NUR SUHADAH NAWI2,
MUHAMAD SHIRWAN ABDULLAH SANI3 & LAI KOK SONG4
1Halal Products Research Institute, Universiti
Putra Malaysia, 43400 UPM Serdang, Selangor, Malaysia
2Malaysia Halal Analysis Centre (MyHAC),
Department of Islamic Development Malaysia, No. 1 Persiaran Teknologi 1, Lebuh
Enstek, 71760 Bandar Baru Enstek, Negeri Sembilan, Malaysia
3International Institute for Halal Research
and Training, International Islamic University Malaysia, Jalan Gombak, 53100
Kuala Lumpur, Malaysia
4Health Sciences Division, Abu Dhabi Women’s
College, Higher Colleges of Technology, 41012 Abu Dhabi, United Arab Emirates
Received: 17 February 2025/Acccepted: 23 June 2025
Abstract
Gelatin is derived from
animal collagen, sourced primarily from bovine or porcine, and finds widespread
application within the food industry. These issues raise concern over its halal
status, particularly among Muslims and Jews, as they adhere to dietary laws
prohibiting the consumption of pork and its derivatives. Conventional methods
like quantitative Polymerase Chain Reaction (qPCR) and liquid
chromatography–mass spectrometry (LC–MS) have limitations due to the
deoxyribonucleic acid (DNA)’s reliability and the gelatin's complex
composition, respectively. Therefore, this study aimed to explore the
application of artificial intelligence (AI)–based
machine learning, focusing on amino acid composition for non-halal gelatin
prediction. A set of 3,780 data points enabled the analysis of the
chromatographic peak areas of 18 amino acids in 210 gelatin samples. Orthogonal
partial least squares discriminant analysis (OPLS–DA) and artificial neural
network (ANN) compared their performance in machine learning models. The ANN
employed resilient backpropagation algorithms that demonstrated high accuracy
(98.5%) and regression (R2) of 0.913, with a slightly higher Root
Mean Square Error (RMSE) of 0.244. However, OPLSDA demonstrated the best
accuracy (100%), R2 of 0.997, and lower RMSE (0.130) compared to the
ANN model. The ANN's robustness against outliers and direct output results
provided practical advantages, while OPLS–DA offered comprehensive insights and
robust discrimination. This study demonstrates the potential of AI-based
machine learning in non-halal gelatin prediction, with both models showing the
same capability. These findings can be integrated with existing analytical
methods to complement the halal analysis, thus ensuring product integrity and
upholding halal sanctity.
Keywords: Artificial neural network; gelatin; halal; machine
learning; OPLS–DA
Abstrak
Gelatin
diperoleh daripada kolagen haiwan dan biasanya diperoleh daripada lembu atau
khinzir. Gelatin ini digunakan secara meluas dalam industri makanan. Hal ini
menimbulkan kebimbangan mengenai status halal, terutamanya dalam kalangan umat
Islam dan Yahudi, kerana mereka terikat kepada undang-undang pemakanan yang
melarang pengambilan daging babi dan sumbernya. Kaedah analisis seperti tindak
balas rantaian polimerase kuantitatif (qPCR) dan kromatografi
cecair–spektrometri jisim (LC–MS) mempunyai had kerana kebolehpercayaan asid
deoksiribonukleik (DNA) dan komposisi gelatin yang kompleks. Oleh itu, kajian
ini bertujuan untuk meneroka penggunaan pembelajaran mesin berasaskan
kecerdasan buatan (AI), dengan memberi tumpuan kepada komposisi asid amino
untuk ramalan gelatin tidak halal. Set data yang terdiri daripada 3,780 data
membolehkan analisis kawasan kromatografi bagi 18 asid amino dalam 210 sampel
gelatin. Analisis diskriminan–kuasa dua separa ortogonal (OPLS–DA) dan
rangkaian saraf tiruan (ANN) membandingkan prestasi masing-masing dalam model
pembelajaran mesin. ANN menggunakan algoritma perambatanbalik yang menunjukkan
ketepatan tinggi (98.5%) dan regresi (R2) 0.913 dengan Ralat Purata Punca
Kuasa Dua (RMSE) yang sedikit lebih tinggi iaitu 0.244. Walau bagaimanapun,
OPLS–DA menunjukkan ketepatan terbaik (100%), R2 (0.997) dan RMSE yang lebih rendah (0.130) berbanding model ANN. Ketahanan ANN
terhadap pencilan dan hasil langsung memberikan kelebihan praktikal, manakala
OPLS–DA memberikan pandangan yang komprehensif dan diskriminasi yang kukuh.
Kajian ini menunjukkan potensi pembelajaran mesin berasaskan AI dalam ramalan
gelatin tidak halal dengan kedua-dua model menunjukkan keupayaan yang sama.
Penemuan ini boleh digabungkan dengan kaedah analisis sedia ada untuk
melengkapkan analisis halal, justeru memastikan integriti produk dan memelihara
kesucian halal.
Kata kunci: Gelatin; halal; pembelajaran mesin;
pengesahan daging; rantaian saraf tiruan; OPLS–DA
REFERENCES
Abdullah
Sani Ahmad, M.I., Li, Y., Pan, J., Liu, F., Dai, H., Fu, Y., Huang, T., Farooq,
S. & Zhang, H. 2024. Collagen and gelatin: structure, properties, and
applications in food industry. International Journal of Biological
Macromolecules 254(3): 128037.
https://doi.org/10.1016/j.ijbiomac.2023.128037
Ali, E.,
Sultana, S., Abd Hamid, S.B., Hossain, M., Yehya, W.A., Kader, A. &
Bhargava, S.K. 2018. Gelatin controversies in food, pharmaceuticals, and
personal care products: Authentication methods, current status, and future
challenges. Critical Reviews in Food Science and Nutrition 58(9): 1495-1511.
Amira
Aqilah, S., Nur Azira, T., Haizatul Hadirah, G., Nurul Azarima, M.A. & Siti
Nur Syahirah, Z. 2019. Analytical methods for gelatin differentiation. Journal
of Halal Industry & Services 2(1): a0000048.
http://www.journals.hh-publisher.com/index.php/JHIS/article/view/57
Bhagya
Raj, G.V.S. & Dash, K.K. 2022. Comprehensive study on applications of
artificial neural network in food process modeling. Critical Reviews in Food
Science and Nutrition 62(10): 2756-2783.
https://doi.org/10.1080/10408398.2020.1858398
Boccard, J. & Rutledge, D.N. 2013. A consensus
orthogonal partial least squares discriminant analysis (OPLS-DA) strategy for
multiblock omics data fusion. Analytica Chimica Acta 769: 30-39.
https://doi.org/10.1016/j.aca.2013.01.022
Chang,
L., Mu, G., Wang, M., Zhao, T., Tuo, Y., Zhu, X. & Qian, F. 2022. Microbial
diversity and quality-related physicochemical properties of spicy cabbage in
Northeastern China and their correlation analysis. Foods 11(10): 1511.
https://doi.org/10.3390/foods11101511
Gbashi,
S., Maselesele, T.L., Njobeh, P.B., Molelekoa, T.B.J., Oyeyinka, S.A.,
Makhuvele, R. & Adebo, O.A. 2023. Application of a generative adversarial
network for multi-featured fermentation data synthesis and artificial neural
network (ANN) modeling of bitter gourd–grape beverage production. Scientific
Reports 13(1): 11755. https://doi.org/10.1038/s41598-023-38322-3
Gonçalves Neto, J., Ozorio, L.V., Campos de Abreu, T.V.,
dos Santos, B.F. & Pradelle, F. 2021. Modeling of biogas production from
food, fruits and vegetables wastes using artificial neural network (ANN). Fuel 285: 119081. https://doi.org/10.1016/j.fuel.2020.119081
Guiné,
R.P.F. 2019. The use of artificial neural networks (ANN) in food process
engineering. International Journal of Food Engineering 5(1): 15-21.
https://doi.org/10.18178/ijfe.5.1.15-21
Hang,
J., Shi, D., Neufeld, J., Bett, K.E. & House, J.D. 2022. Prediction of
protein and amino acid contents in whole and ground lentils using near-infrared
reflectance spectroscopy. LWT 165: 113669.
https://doi.org/10.1016/j.lwt.2022.113669
Jadhav,
S.R., Shah, R.M., Karpe, A.V., Barlow, R.S., McMillan, K.E., Colgrave, M.L.
& Beale, D.J. 2021. Utilizing the food-pathogen metabolome to putatively
identify biomarkers for the detection of shiga toxin-producing E. coli (stec) from spinach. Metabolites 11(2): 67.
https://doi.org/10.3390/metabo11020067
Jameel,
A.M. & Al-Salami, Q.H. 2023. Principal component analysis technique for
finding the best applicant for a job. Cihan University-Erbil Journal of
Humanities and Social Sciences 7(1): 121-125.
https://doi.org/10.24086/cuejhss.v7n1y2023.pp121-125
Jannat,
B., Ghorbani, K., Shafieyan, H., Kouchaki, S., Behfar, A., Sadeghi, N.,
Beyramysoltan, S., Rabbani, F., Dashtifard, S. & Sadeghi, M. 2018. Gelatin
speciation using real-time PCR and analysis of mass spectrometry-based
proteomics datasets. Food Control 87: 79-87.
https://doi.org/10.1016/j.foodcont.2017.12.006
Kleinnijenhuis, A.J., van
Holthoon, F.L. & Herregods, G. 2018. Validation and theoretical
justification of an LC-MS method for the animal species specific detection of
gelatin. Food Chemistry 243: 461-467.
https://doi.org/10.1016/j.foodchem.2017.09.104
Liu, K.,
Jin, Y., Gu, L., Li, M., Wang, P., Yin, G., Wang, S., Wang, T., Wang, L. &
Wang, B. 2023. Classification and authentication of Lonicerae japonicae flos
and Lonicerae flos by using 1H-NMR spectroscopy and chemical pattern
recognition analysis. Molecules 28(19): 6860.
https://doi.org/10.3390/molecules28196860
Liu, X.
& Locasale, J.W. 2017. Metabolomics reveals intratumor heterogeneity - Implications
for precision medicine. EBioMedicine 19: 4-5.
https://doi.org/10.1016/j.ebiom.2017.04.030
Mavani
Nidhi Rajesh, Jarinah Mohd Ali, Suhaili Othman, M.A. Hussain, Haslaniza Hashim
& Norliza Abd Rahman. 2022. Application of artificial intelligence in food
industry - A guideline. Food Engineering Reviews 14: 134-175.
https://doi.org/10.1007/s12393-021-09290-z
Milovanovic, I. & Hayes, M. 2018. Marine gelatine from
rest raw materials. Applied Sciences 8(12): 2407.
Muhamad
Shirwan Abdullah Sani, Azilawati Mohd Ismail, Azman Azid & Mohd Saiful
Samsudin. 2021. Establishing forensic food models for authentication and
quantification of porcine adulterant in gelatine and marshmallow. Food
Control 130: 108350. https://doi.org/10.1016/j.foodcont.2021.108350
Oliveri,
P., Malegori, C., Mustorgi, E. & Casale, M. 2021. Qualitative pattern
recognition in chemistry: Theoretical background and practical guidelines. Microchemical
Journal 162: 105725. https://doi.org/10.1016/j.microc.2020.105725
Sarker,
I.H. 2021. Machine learning: Algorithms, real-world applications and research
directions. SN Computer Science 2: 160.
https://doi.org/10.1007/s42979-021-00592-x
Stangierski,
J., Weiss, D. & Kaczmarek, A. 2019. Multiple regression models and
artificial neural network (ANN) as prediction tools of changes in overall
quality during the storage of spreadable processed gouda cheese. European
Food Research and Technology 245(11): 2539-2547.
https://doi.org/10.1007/s00217-019-03369-y
Uddin, S.M.K.,
Motalib Hossain, M.A., Sagadevan, S., Al Amin, Md. & Johan, M.R. 2021.
Halal and kosher gelatin: Applications as well as detection approaches with
challenges and prospects. Food Bioscience 44(PA): 101422.
https://doi.org/10.1016/j.fbio.2021.101422
Wang, Y.,
Wang, X., Huang, Y., Yue, T. & Cao, W. 2023. Analysis of volatile markers
and their biotransformation in raw chicken during Staphylococcus aureus early contamination. Foods 12(14): 2782.
https://doi.org/10.3390/foods12142782
Tsuchiya, Y. & Tomii, K. 2020. Neural networks for
protein structure and function prediction and dynamic analysis. Biophysical
Reviews 12(2): 569-573. https://doi.org/10.1007/s12551-020-00685-6
Yuswan,
M.H., A. Jalil, N.H., Mohamad, H., Keso, S., Mohamad, N.A., Tengku Md. Yusoff,
T.S., Ismail, N.F., Abdul Manaf, Y.N., Mohd Hashim, A., Mohd Desa, M.N., Yusof,
Y.A. & Mustafa, S. 2021. Hydroxyproline determination for initial detection
of halal-critical food ingredients (gelatin and collagen). Food Chemistry 337: 127762. https://doi.org/10.1016/j.foodchem.2020.127762
Zhang,
R-Z., Zhao, J.T., Wang, W.Q., Fan, R.H., Rong, R., Yu, Z.G. & Zhao, Y.L.
2022. Metabolomics-based comparative analysis of the effects of host and
environment on Viscum coloratum metabolites and antioxidative
activities. Journal of Pharmaceutical Analysis 12(2): 243-252.
https://doi.org/10.1016/j.jpha.2021.04.003
Zheng,
H., Jiang, L., Lou, H., Hu, Y., Kong, X. & Lu, H. 2011. Application of
artificial neural network (ANN) and partial least-squares regression (PLSR) to
predict the changes of anthocyanins, ascorbic acid, total phenols, flavonoids,
and antioxidant activity during storage of red bayberry juice based on fractal
analysis and red, green, and blue (RGB) intensity values. Journal of
Agricultural and Food Chemistry 59(2): 592-600.
https://doi.org/10.1021/jf1032476
*Corresponding author;
email: hafisyuswan@upm.edu.my
|
|||
|
