A Risk Assessment Tool for the Contamination of Aflatoxins on Dried Figs based on Machine Learning Algorithms

Authors: Kottaridi Klimentia, Demopoulos Vasilis, Sidiropoulos Anastasios, Ihara Diego, Nikolaidis Vasileios, Antonopoulos Dimitrios

Abstract:

Aflatoxins are highly poisonous and carcinogenic compounds produced by species of the genus Aspergillus spp. that can infect a variety of agricultural foods, including dried figs. Biological and environmental factors, such as population, pathogenicity and aflatoxinogenic capacity of the strains, topography, soil and climate parameters of the fig orchards are believed to have a strong effect on aflatoxin levels. Existing methods for aflatoxin detection and measurement, such as high-performance liquid chromatography (HPLC), and enzyme-linked immunosorbent assay (ELISA), can provide accurate results, but the procedures are usually time-consuming, sample-destructive and expensive. Predicting aflatoxin levels prior to crop harvest is useful for minimizing the health and financial impact of a contaminated crop. Consequently, there is interest in developing a tool that predicts aflatoxin levels based on topography and soil analysis data of fig orchards. This paper describes the development of a risk assessment tool for the contamination of aflatoxin on dried figs, based on the location and altitude of the fig orchards, the population of the fungus Aspergillus spp. in the soil, and soil parameters such as pH, saturation percentage (SP), electrical conductivity (EC), organic matter, particle size analysis (sand, silt, clay), concentration of the exchangeable cations (Ca, Mg, K, Na), extractable P and trace of elements (B, Fe, Mn, Zn and Cu), by employing machine learning methods. In particular, our proposed method integrates three machine learning techniques i.e., dimensionality reduction on the original dataset (Principal Component Analysis), metric learning (Mahalanobis Metric for Clustering) and K-nearest Neighbors learning algorithm (KNN), into an enhanced model, with mean performance equal to 85% by terms of the Pearson Correlation Coefficient (PCC) between observed and predicted values.

Keywords: aflatoxins, Aspergillus spp., dried figs, k-nearest neighbors, machine learning, prediction

References:

[1] M. Moss, “Mycotoxicology: Introduction to the mycology, plant pathology, chemistry, toxicology, and pathology of naturally occurring mycotoxicoses in animals and man,” in British Veterinary Journal, vol. 144, no. 104, 1988.
[2] P. J., Cotty, “Influence of field application of an atoxigenic strain of Aspergillus flavus on the populations of A. flavus infecting cotton bolls and on the aflatoxin content of cottonseed,” in Phytopathology, vol. 84, no. 11, 1994, pp. 1270-1277.
[3] P. J., Cotty, “Comparison of four media for the isolation of Aspergillus flavus group fungi,” in Mycopathologia, vol. 125, no. 3, 1994, pp. 157–162.
[4] J. E., Smith, Handbook of Plant and Fungal Toxicants, D'Mello,. J. P. F. (Ed.). CRC Press, Boca Raton, FL, 1997, pp. 269-285.
[5] J., Yu, D., Bhatnagar, and K. C., Ehrlich, “Aflatoxin biosynthesis,” in Revista iberoamericana de micologia, vol. 19, no.4, 2002, pp. 191–200.
[6] Μ., Iqbal, Μ., Abbas, Μ., Adil, Α., Nazir, and I., Ahmad, “Aflatoxins Biosynthesis, Toxicity and Intervention Strategies: A Review,” in Chemistry International, vol. 5, no. 3, 2019, pp. 168-191.
[Online]. Available: https://ssrn.com/abstract=3407341
[7] J. S., Angle, “Aflatoxin decomposition in various soils,” Journal of Environmental Science and Health, Part B, vol. 21, no. 4, pp. 277-288, 1986.
[8] A. M., Torres, G. G., Barros, S. A., Palacios, S. N., Chulze, P., Battilani, “Review on pre- and post-harvest management of peanuts to minimize aflatoxin contamination,” in Food Research International vol. 62, 2014, pp. 11-19.
[9] N. P., Keller, C., Nesbitt, B., Sarr, T. D., Phillips, and G. B., Burow, “pH regulation of sterigmatocystin and aflatoxin biosynthesis in A. Spp.” in Phytopathology, vol. 87, no. 6, 1997, pp. 643-648.
[10] A. G., Marroquín-Cardona, N. M., Johnson, T. D., Phillips, and A. W., Hayes, “Mycotoxins in a changing global environment–a review,” in Food and Chemical Toxicology, vol. 69, 2014, pp. 220-230.
[11] E. M., Embaby, L. F., Hagagg, and M. M., Abdel-Galil, “Decay of Some Fresh and Dry Fruit Quality Contaminated by Some Mold Fungi,” in Journal of Applied Sciences Research, vol. 8, no. 6, 2012, pp. 3083-3091.
[12] D., Heperkan, A., Moretti, C. D., Dikmen, and A. F., Logrieco, “Toxigenic Fungi and Mycotoxin Associated with Figs in the Mediterranean Area,” in Phytopathologia Mediterranea, vol. 51, no. 1, 2012, pp. 119-130.
[13] A. I., Galván, A., Rodríguez, A., Martín, M., Serradilla, A., Martínez-Dorado, M., Córdoba, “Effect of Temperature During Drying and Storage of Dried Figs on Growth, Gene Expression and Aflatoxin Production,” in Toxins, vol. 13, 2021.
[14] R. H., Luchese, and W. F., Harrigan, “Biosynthesis of aflatoxin—the role of nutritional factors,” Journal of Applied Bacteriology, vol. 74, no. 1, 1993, pp. 5-14.
[15] C., Henderson, W., Potter, R. W., McClendon, and G., Hoogenboom, “Aflatoxin Prediction Using a GA Trained Neural Network,” in FLAIRS Conference, 1998.
[16] H., Kalkan, A., Güneş, E., Durmuş, and A., Kuscu, “Non-invasive detection of aflatoxin-contaminated figs using fluorescence and multispectral imaging,” in Food additives and contaminants, Part A, Chemistry, analysis, control, exposure and risk assessment, vol. 31, no. 8, 2014, pp. 1414–1421,
[Online]. Available: https://doi.org/10.1080/19440049.2014.926398
[17] V. Z., Romina, and A., Mohamadi Sani, “Use of artificial intelligence Algorithms to predict reduction of Aflatoxin in Cotton seed meal treated with ozone,” in IJALS, vol. 9, no. 3, 2016, pp. 326-330.
[18] F. R., Bertani, L., Businaro, L., Gambacorta, A., Mencattin, D., Brenda, D., Giuseppe, A., De Ninno, M., Solfrizzo, E., Martinelli, and A., Gerardino, “Optical detection of Aflatoxins B in grained almonds using fluorescence spectroscopy and machine learning algorithms,” in arXiv, 2020.
[Online]. Available: https://arxiv.org/abs/2003.04096
[19] A., Godiya, and Dr. A., Kothari, “Study of Different Disease in Potato and their Detection Technique Using Leaf Image,” in International Journal of Innovative Research in Technology, vol. 6, no. 12, 2020, pp. 246 - 254.
[20] Α., Mohamed, “Comparative Study of Four Supervised Machine Learning Techniques for Classification,” in International Journal of Applied Science and Technology, vol. 7, no. 2, Jun 2017.
[21] H. J., Oh, F., Ozkaya, and R., LaRose, “How does online social networking enhance life satisfaction? The relationships among online supportive interaction, affect, perceived social support, sense of community, and life satisfaction,” in Computers in Human Behavior, vol. 30, 2014, pp. 69-78.
[22] K., Weinberger, J., Blitzer, and L., Saul, “Distance Metric Learning for Large Margin Nearest Neighbor Classification,” in Journal of Machine Learning Research, vol. 10, 2009, pp. 207-244.
[23] W., De Vazelhes, C. J., Carey, Y., Tang, N., Vauquier, and A., Bellet, “metric-learn:Metric Learning Algorithms in Python”, in Journal of Machine Learning Research, vol. 20, 2020, pp. 1-6.
[24] B., Shi, and J., Liu, “Nonlinear Metric Learning for kNN and SVMs through Geometric Transformations,” in Neurocomputing, vol. 318, 2018, pp. 18-29.
[25] Y., Qu, G., Ostrouchov, N., Samatova, and Al., Geist, “Principal Component Analysis for Dimension Reduction in Massive Distributed Data Sets,” in Proc. IEEE Int. Conf. Data Mining (ICDM), 2002.
[26] J., Suárez, S., García, and F., Herrera, “A tutorial on distance metric learning: Mathematical foundations, algorithms, experimental analysis, prospects and challenges,” in Neurocomputing, vol. 425, 2021, pp. 300-322.
[27] L., Tang, H., Pan, and Y., Yao, “K-Nearest Neighbor Regression with Principal Component Analysis for Financial Time Series Prediction,” in Proc. Int. Conf. on Computing and Artificial Intelligence (ICCAI), 2018, pp. 127-131.
[Online]. Available: https://doi.org/10.1145/3194452.3194467
[28] S., Karamizadeh, S., Abdullah, A., Manaf, M., Zamani, and A., Hooman, “An Overview of Principal Component Analysis,” in Journal of Signal and Information Processing, vol. 4, 2013, pp. 173-175.
[29] S. Raschka, “Model Evaluation, Model Selection, and Algorithm Selection in Machine Learning,” arXiv, 2018.
[Online]. Available: https://arxiv.org/abs/1811.12808
[30] W. I., Baggerman, “A modified Rose Bengal medium for the enumeration of yeasts and moulds from foods,” in European Journal of Applied Microbiology and Biotechnology, vol. 12, 1981, pp. 242-247.
[31] D., Nilufer, and D., Boyacioglu, “Comparative Study of Three Different Methods for the Determination of Aflatoxins in Tahini,” in Journal of agricultural and food chemistry, vol. 50, 2002, pp. 3375-9.
[Online]. Available: https://doi.org/10.1021/jf020005a
[32] Ö. B., Özlüoymak, and E., Güzel, 2 “Prediction of aflatoxin contamination on dried fig (ficus carica) samples by spectral image analysis in comparison with laboratory results,” Fresenius Environmental Bulletin, vol. 27, no.2, 2018, pp. 681-689.
[33] M., Namjoo, F., Salamat, N., Rajabli, R., Haji-Hoseeini, F., Niknejad, F., Kohsar, and H., Joshaghani, “Quantitative Determination of Aflatoxin by High Performance Liquid Chromatography in Wheat Silos in Golestan Province, North of Iran,” Iranian journal of public health, vol. 45, 2016, pp. 905-910.
[34] K., Elk, and R. H., Gelderman, “Soil sample preparation,” in Recommended chemical soil test procedures for the North Central Region, no. 221, W.C. Dahnke, Ed. North Dakota: Agric. Exp. Stn. Bull., 1988, pp. 2-4.
[35] M. G., Klages, “Reproducibility of saturation percentage of soils” in Proc. of the Montana Academy of Sciences (USA), vol. 44, 1984, pp. 67-69.
[36] J. D., Rhoades, “Salinity: Electrical Conductivity and Total Dissolved Solids,” in Methods of Soil Analysis: Part 3 Chemical Methods, D.L.Sparks, Ed. USA Madison: SSSA Book Series, 1996.
[37] Y. P., Kalra, “Determination of pH of soils by different methods: collaborative study,” in Journal of the Association Off. Analytical Chemistry International, vol. 78, no. 2, 1995, pp. 310-321.
[38] H. H., Janzen, “Soluble salts,” in Soil Sampling and Methods of Analysis, M.R. Carter, Ed. Boca Raton, FL: Lewis Publishers, 1993, pp. 161–166.
[39] R. O., Miller, J., Kotuby-Amacher, J. B., Rodriguez, “Western States Laboratory Proficiency Testing Program-Soil Plant and Analytical Methods,” Ver. 4.10, 1998.
[40] A., Walkley, and I. A., Black, “An Examination of the Degtjareff Method for Determining Soil Organic Matter and a Proposed Modification of the Chromic Acid Titration Method,” in Soil Science, vol. 37, 1934, pp. 29-38.
[41] L., van Reeuwijk, “Procedures for Soil Analysis (6th Edition),” ISRIC, FAO, Wageningen, 2002.
[42] W. L., Lindsay, and W. A., Norvell, “Development of a DTPA soil test for zinc, iron, manganese and copper,” in Soil Science Society of America Journal, vol. 42, 1978, pp. 421-428.
[43] D., Warncke, and J. R., Brown, “Potassium and Other Basic Cations” in Recommended Chemical Soil Test Procedures for the North Central Region, J.R., Brown, Ed. Columbia: NCR Publication No. 221, Missouri Agricultural Experiment Station, 1998, pp. 31-33.
[44] S. R., Olsen, C. V., Cole, F. S., Watanabe, and L.A. Dean, “Estimation of available phosphorus in soils by extraction with sodium bicarbonate,” Circular, vol. 939, Ed. Washington, DC: US Department of Agriculture, pp.19, 1954.
[45] S. K., Gupta, J.W.B., Stewart, “The extraction and determination of plant available boron in soil” in Schweizerische landwirtschaftliche Forschung vol.14, pp. 153-169, 1975.
[46] B., Wolf, “Improvements in the azomethine‐H method for the determination of boron,” in Communications in Soil Science and Plant Analysis, vol. 5, 1974, pp. 39-44.
[47] A. G., Asuero, A., Sayago, and A., González, “The Correlation Coefficient: An Overview,” in Critical Reviews in Analytical Chemistry, vol. 36, 2006, pp.41 - 59.
[48] L., Yang, and A., Shami, “On Hyperparameter Optimization of Machine Learning Algorithms: Theory and Practice,” in arXiv, 2020.
[Online]. Available: https://arxiv.org/abs/2007.15745
[49] P., Schratz, J., Muenchow, E., Iturritxa, J., Richter, and A., Brenning, “Performance evaluation and hyperparameter tuning of statistical and machine-learning models using spatial data,” in arXiv, 2018.
[Online]. Available: https://arxiv.org/abs/1803.11266
[50] G., Piñeiro, S., Perelman, J., Guerschman, and J., Paruelo, “How to Evaluate Models: Observed vs. Predicted or Predicted vs. Observed?” in Ecological Modelling, vol. 216, issue 3, 2008, pp. 316-322.