Machine learning-aided design of composite mycotoxin detoxifier material for animal feed

Abstract

The development of food and feed additives involves the design of materials with specific properties that enable the desired function while minimizing the adverse effects related with their interference with the concurrent complex biochemistry of the living organisms. Often, the development process is heavily dependent on costly and time-consuming in vitro and in vivo experiments. Herein, we present an approach to design clay-based composite materials for mycotoxin removal from animal feed. The approach can accommodate various material compositions and different toxin molecules. With application of machine learning trained on in vitro results of mycotoxin adsorption-desorption in the gastrointestinal tract, we have searched the space of possible composite material compositions to identify formulations with high removal capacity and gaining insights into their mode of action. An in vivo toxicokinetic study, based on the detection of biomarkers for mycotoxin-exposure in broilers, validated our findings by observing a significant reduction in systemic exposure to the challenging to be removed mycotoxin, i.e., deoxynivalenol (DON), when the optimal detoxifier is administrated to the animals. A mean reduction of 32% in the area under the plasma concentration-time curve of DON-sulphate was seen in the DON + detoxifier group compared to the DON group (P = 0.010).

Figure 1

Workflow representation starting from selection of feature vector space (a) which describes the in vitro adsorption and efficiency (model targets). Machine learning models (b) trained on in vitro dataset providing tools for material screening, wide in vitro detoxification assessment, and mode of action capturing (c). In vivo validation of the findings extracted by our approach (d).

Figure 2

Graphical assessment of RFads (a) and RFeff (b) of 6 mycotoxins by 15 MDTs under different experimental conditions. Validation of RFads (c) and RFeff (d) toward one yet-unregulated toxin (DAS).

Figure 3

Summed importance score of the groups of features outlined in Table 2, extracted by RFads and RFeff (a). Normalized individual contribution corresponding to in vitro experimental conditions (b) materials (c) and mycotoxin (d) group of features.

Figure 4

Synergy capturing by RF predicting efficiency for a series of hybrids of sepiolite-montmorillonite-charcoal in which the sepiolite-montmorillonite ratio was fixed to 1/4. The orange area is assigned to the positive synergistic effect. The experimental settings for the uptake of DON, OTA, T2, FB1 and ZEN were fixed to 2 kg/t of inclusion rate of MDT, 2 µg/ml of toxin concentration. The pH during the adsorption experiment was fixed to 3 while the desorption pH was 6.5.

Figure 5

Response of predicted in vitro efficiency of SEP/MONT/AC towards the removal of the explored mycotoxin groups (a). The predictions were obtained by RF fixing the experimental setting to 2 kg/t of inclusion rate of SEP/MONT/AC, 2 µg/ml of toxin concentration, adsorption and desorption pH to 3 and 6.5, respectively. Graphical representation of in vivo design of experiment validating the detoxification of DON by SEP/MONT/AC detoxifier (b). Mean plasma concentration and standard deviation of DON after single oral bolus administration of DON alone (0.5 mg/kg BW) and DON in combination with SEP/MONT/AC (0.4 g/kg BW) to 8 broiler chickens (c). Mean response and standard deviation of deoxynivalenol-sulphate (DON-S) in plasma after single oral bolus administration of DON alone (0.5 mg/kg BW) and DON in combination with SEP/MONT/AC (0.4 g/kg BW) to 8 broiler chickens (d).