Application of Meta-Analysis and Machine Learning Methods to the Prediction of Methane Production from In Vitro Mixed Ruminal Micro-Organism Fermentation

Machine learning methods for predicting the key metabolic parameters of Halomonas elongata DSM 2581 T

Ectoine is generally produced by the fermentation process of Halomonas elongata DSM 2581 ^T, which is one of the primary industrial ectoine production techniques. To effectively monitor and control the fermentation process, the important parameters require accurate real-time measurement. However, for ectoine fermentation, three critical parameters (cell optical density, glucose, and product concentration) cannot be measured conveniently in real-time due to time variation, strong coupling, and other constraints. As a result, our work effectively created a series of hybrid models to predict the values of these three parameters incorporating both fermentation kinetics and machine learning approaches. Compared with the traditional machine learning models, our models solve the problem of insufficient data which is common in fermentation. In addition, a simple kinetic modeling is only applicable to specific physical conditions, so different physical conditions require refitting the function, which is tedious to operate. However, our models also overcome this limitation. In this work, we compared different hybrid models based on 5 feature engineering methods, 11 machine-learning approaches, and 2 kinetic models. The best models for predicting three key parameters, respectively, are as follows: CORR-Ensemble (R²: 0.983 ± 0.0, RMSE: 0.086 ± 0.0, MAE: 0.07 ± 0.0), SBE-Ensemble (R²: 0.972 ± 0.0, RMSE: 0.127 ± 0.0, MAE: 0.078 ± 0.0), and SBE-Ensemble (R²:0.98 ± 0.0, RMSE: 0.023 ± 0.001, MAE: 0.018 ± 0.001). To verify the universality and stability of constructed models, we have done an experimental verification, and its results showed that our proposed models have excellent performance. KEY POINTS: • Using the kinetic models for producing simulated data • Through different feature engineering methods for dimension reduction • Creating a series of hybrid models to predict the values of three parameters in the fermentation process of Halomonas elongata DSM 2581 ^T.

Effect of waste mango silage on the in vitro gas production, in situ digestibility, intake, apparent digestibility, and ruminal characteristics in calf diets

Background and Aim: Mexico is the fifth largest producer of mangoes in the world. For the conservation of agro-industrial waste and crop residues, the ensiling technique has shown good results. This study aimed to evaluate the effect of increasing the level of mango silage (86% waste mango and 14% pangola grass hay) in calf diets on in vitro gas production, in situ digestibility, intake, apparent digestibility, and ruminal characteristics. Materials and Methods: The diets contained 0 (T0), 30 (T1), 45 (T2), and 60% (T3) mango silage. The partial (24, 48, and 72 h) and cumulative (72 h) biogas, CH4 production, and degradation were determined in the in vitro evaluation. In situ digestibility and estimators of fermentation kinetics of dry matter (DM) and organic matter (OM) were determined. Intake, apparent nutrient digestibility, and rumen parameters of calves (200 kg) were evaluated in a 4 × 4 Latin square design. Response to increased mango silage was calculated by linear and quadratic orthogonal contrasts. Results: In vitro partial and cumulative biogas production decreased linearly (p < 0.05), and the partial and cumulative CH4 production did not show linear or quadratic contrast (p > 0.05); in vitro DM degradation, in vitro neutral detergent fiber degradation, and in vitro acid detergent fiber degradation showed a linear increase (p < 0.05). In situ dry matter digestibility (DMDis), in situ organic matter digestibility (OMDis), b, a + b, c, and effective digestibility (ED) of DMDis, a, a + b, c, and ED of OMDis increased linearly (p < 0.05). Dry matter intake, OM intake, and crude protein intake showed a linear increase (p < 0.05); NDF intake and ADF intake presented a quadratic behavior (p < 0.05). Apparent digestibility of DM, OM, CP, and hemicellulose, pH, N-NH3, total bacterial count, acetate, propionate, butyrate, volatile fatty acids, acetate: propionate ratio, cellulolytic bacteria, and protozoa did not present a linear or quadratic orthogonal effect (p > 0.05). Conclusion: The in vitro, in situ, and in vivo variables demonstrated that up to 60% mango silage can be used for the intensive fattening of calves in confinement. Keywords: alternative feed, alternative feeding, cattle, silage, tropics.

Threats to Terrestrial Plants from Emerging Nanoplastics

Nanoplastics are ubiquitous in ecosystems and impact planetary health. However, our current understanding on the impacts of nanoplastics upon terrestrial plants is fragmented. The lack of systematic approaches to evaluating these impacts limits our ability to generalize from existing studies and perpetuates regulatory barriers. Here, we undertook a meta-analysis to quantify the overall strength of nanoplastic impacts upon terrestrial plants and developed a machine learning approach to predict adverse impacts and identify contributing features. We show that adverse impacts are primarily associated with toxicity metrics, followed by plant species, nanoplastic mass concentration and size, and exposure time and medium. These results highlight that the threats of nanoplastics depend on a diversity of reactions across molecular to ecosystem scales. These reactions are rooted in both the spatial and functional complexities of nanoplastics and, as such, are specific to both the plastic characteristics and environmental conditions. These findings demonstrate the utility of interrogating the diversity of toxicity data in the literature to update both risk assessments and evidence-based policy actions.

Applications of Model-Based Meta-Analysis in Drug Development

Model-based meta-analysis (MBMA) is a quantitative approach that leverages published summary data along with internal data and can be applied to inform key drug development decisions, including the benefit-risk assessment of a treatment under investigation. These risk-benefit assessments may involve determining an optimal dose compared against historic external comparators of a particular disease indication. MBMA can provide a flexible framework for interpreting aggregated data from historic reference studies and therefore should be a standard tool for the model-informed drug development (MIDD) framework.In addition to pairwise and network meta-analyses, MBMA provides further contributions in the quantitative approaches with its ability to incorporate longitudinal data and the pharmacologic concept of dose-response relationship, as well as to combine individual- and summary-level data and routinely incorporate covariates in the analysis.A common application of MBMA is the selection of optimal dose and dosing regimen of the internal investigational molecule to evaluate external benchmarking and to support comparator selection. Two case studies provided examples in applications of MBMA in biologics (durvalumab + tremelimumab for safety) and small molecule (fenebrutinib for efficacy) to support drug development decision-making in two different but well-studied disease areas, i.e., oncology and rheumatoid arthritis, respectively.Important to the future directions of MBMA include additional recognition and engagement from drug development stakeholders for the MBMA approach, stronger collaboration between pharmacometrics and statistics, expanded data access, and the use of machine learning for database building. Timely, cost-effective, and successful application of MBMA should be part of providing an integrated view of MIDD.

Influence of combined yeast culture and enzymatically hydrolyzed yeast on in vitro ruminal fermentation in contrasting feed substrates

BACKGROUND

Feed additives such as live yeast cultures have increasingly been used in ruminant feeds to improve animal performance and feeding efficiency. However, it is not clear how inactive combined yeast cultures affect ruminal gas production, fermentation kinetics and efficiency. Therefore, this study was done to determine the influence of incubating different substrates with a combined yeast culture + enzymatically hydrolyzed yeast (YC + EHY) on in vitro ruminal gas production, fermentation kinetics and metabolizable energy. Six contrasting substrates (Trichantera gigantea and Glircidia sepium leaves, Brachiaria hybrid (cv. Mulato II) leaf + stem and leaf only, Cynodon nlemfuensis and a commercial concentrate dairy feed) were incubated with and without YC + EHY in buffered rumen fluid and gas production measured at 2, 4, 6, 8, 10, 12, 15, 19, 24, 30, 36, 48 and 72 h post incubation.

RESULTS

In vitro fermentation parameters (a, b, a + b and c) were unaffected by YC + EHY except for the lag phase in T. gigantea, which that reduced by 31.3% when it was incubated with YC + EHY. Supplementation with YC + EHY also did not affect metabolizable energy, 72 h organic matter digestibility, 24 h gas or CH₄ production within substrate. However, cumulative gas and methane production at peak fermentation in the commercial concentrate feed was reduced by 20% when incubated with YC + EHY.

CONCLUSION

It was concluded that YC + EHY has the potential to improve microbial colonization of T. gigantean substrates and reduce gas and methane production at peak fermentation in commercial concentrate feeds. © 2021 Society of Chemical Industry.