Ethanol (EtOH) alters many cellular processes in yeast. An integrated view of different EtOH-tolerant phenotypes and their long noncoding RNAs (lncRNAs) is not yet available. Here, large-scale data integration showed the core EtOH-responsive pathways, lncRNAs, and triggers of higher (HT) and lower (LT) EtOH-tolerant phenotypes. LncRNAs act in a strain-specific manner in the EtOH stress response. Network and omics analyses revealed that cells prepare for stress relief by favoring activation of life-essential systems. Therefore, longevity, peroxisomal, energy, lipid, and RNA/protein metabolisms are the core processes that drive EtOH tolerance. By integrating omics, network analysis, and several other experiments, we showed how the HT and LT phenotypes may arise: (1) the divergence occurs after cell signaling reaches the longevity and peroxisomal pathways, with CTA1 and ROS playing key roles; (2) signals reaching essential ribosomal and RNA pathways via SUI2 enhance the divergence; (3) specific lipid metabolism pathways also act on phenotype-specific profiles; (4) HTs take greater advantage of degradation and membraneless structures to cope with EtOH stress; and (5) our EtOH stress-buffering model suggests that diauxic shift drives EtOH buffering through an energy burst, mainly in HTs. Finally, critical genes, pathways, and the first models including lncRNAs to describe nuances of EtOH tolerance are reported here.

The correct capture of forest operations information carried out in forest plantations can help in the management of mechanized harvesting timber. Proper management must be able to dimension resources and tools necessary for the fulfillment of operations and helping in strategic, tactical, and operational planning. In order to facilitate the decision making of forest managers, this work aimed to analyze the performance of machine learning algorithms in estimating the productivity of timber harvesters. As predictors of productivity, we used the availability of hours of machine use, individual mean volumes of trees, and terrain slopes. The dataset was composed of 144,973 records, carried out over a period of 28 months. We tested the predictive performance of 24 machine learning algorithms in default mode. In addition, we tested the performance of blending and stacking joint learning methods. We evaluated the model’s fit using the root mean squared error, mean absolute error, mean absolute percentage error, and determination coefficient. After cleaning the initial database, we used only 1.12% to build the model. Learning by blending ensemble stood out with a determination coefficient of 0.71 and a mean absolute percentage error of 15%. From the use of data from machine learning algorithms, it became possible to predict the productivity of timber harvesters. Testing a variety of machine learning algorithms with different dynamics contributed to the machine learning technique that helped us reach our goal: maximizing the model’s performance by conducting experimentation.

Among the activities that burden capital in the supply chain of forest-based industries, the activity of road transport of wood deserves to be highlighted. Machine learning techniques are applied the knowledge extracted from real data, and support strategies that aim to maximize the resources destined for it. Based on variables inherent to the wood transport activity, we verified whether machine learning models can act as predictors of the volume of wood to be transported and support strategic decision-making. The database came from companies in the pulp and paper segments, which totaled 26,761 data instances. After the data wrangling process, machine learning algorithms were used to build models, which were optimized from the hyperparameter adjustment and selected to compose the blended learning hierarchy. In addition to belonging to different methodological basis, a CatBoost Regressor, Decision Tree Regressor, and K Neighbors Regressor were selected mainly for providing minimal values to errors metrics and maximal values to determination coefficient. The learning by stack stands out, with a coefficient of determination of 0.70 and an average absolute percentage error of 6% in the estimation of the volume of wood to be transported. Based on variables inherent to the wood transport process, we verified that machine learning models can act in the prediction of the volume of wood to be transported and support strategic decision-making.

Most of the bioinformatics tools for enzyme annotation focus on enzymatic function assignments. Sequence similarity to well‐characterized enzymes is often used for functional annotation and to assign metabolic pathways. However, these approaches are not feasible for all sequences leading to inaccurate annotations or lack of metabolic pathway information. Here we present the mApLe (metabolic pathway predictor of plant enzymes), a high‐performance machine learning‐based tool with models to label the metabolic pathway of enzymes rather than specifying enzymes’ reactions. The mApLe uses molecular descriptors of the enzyme sequences to perform predictions without considering sequence similarities with reference sequences. Hence, mApLe can classify a diversity of enzymes, even the ones without any homolog or with incomplete EC numbers. This tool can be used to improve the quality of genomic annotation of plants or to narrow down the number of candidate genes for metabolic engineering researches. The mApLe tool is available online, and the GUI can be locally installed.