Search

Accurate estimates of total tree biomass are of critical importance to obtain reliable estimation of the carbon dioxide weight sequestered from the atmosphere by trees and forest stands. This information has the potential to guide appropriate forest management decisions which allow for both the improvement of forest sustainability and the implementation of multi-task reforestation designs aimed to mitigate the detrimental effects of climate change. The current laborious and tree-destructive procedures needed to attain such information has led to the development of machine learning (ML) models aimed at providing accurate estimations of the tree biomass sequestering the atmospheric carbon dioxide. We tested the Levenberg-Marquardt artificial neural network and the support vector machine for regression techniques as an alternative to non-linear allometric regression (NLR) modelling approaches commonly used for tree biomass estimation. We tested the developed ML models using primary ground-truth data from the Lebanon cedar forests in the Western Inner Anatolian regions of Turkey, and their predictions were compared to those of NLR models developed using the same dataset. The results showed that the ML approaches outperformed the NLR models in accurately estimating tree biomass and its components (above- and belowground dry biomass, dry branches biomass, etc.), and the support vector regression (SVR) models gave the highest accuracy of estimates. Therefore, the carbon dioxide weight sequestered in Lebanon cedar trees were reliably estimated, with the aim of supporting the best forest management practices to be applied in Lebanon cedar tree stands in Turkey.

Height-diameter relationships are of critical importance in tree and stand volume estimation. Stand description, site quality determination and appropriate forest management decisions originate from reliable stem height predictions. In this work, the predictive performances of height-diameter models developed for Taurus cedar (Cedrus libani A. Rich.) plantations in the Western Mediterranean Region of Turkey were investigated. Parametric modeling methods such as fixed-effects, calibrated fixed-effects, and calibrated mixed-effects were evaluated. Furthermore, in an effort to come up with more reliable stem-height prediction models, artificial neural networks were employed using two different modeling algorithms: the Levenberg-Marquardt and the resilient back-propagation. Considering the prediction behavior of each respective modeling strategy, while using a new validation data set, the mixed-effects model with calibration using 3 trees for each plot appeared to be a reliable alternative to other standard modeling approaches based on evaluation statistics regarding the predictions of tree heights. Regarding the results for the remaining models, the resilient propagation algorithm provided more accurate predictions of tree stem height and thus it is proposed as a reliable alternative to pre-existing modeling methodologies.

Linear and nonlinear crown variable functions for 173 Brutian pine (Pinus brutia Ten.) trees were incorporated into a well-known compatible volume and taper equation to evaluate their effect in model prediction accuracy. In addition, the same crown variables were also incorporated into three neural network (NN) types (Back-Propagation, Levenberg-Marquardt and Generalized Regression Neural Networks) to investigate their applicability in over-bark diameter and stem volume predictions. The inclusion of crown ratio and crown ratio with crown length variables resulted in a significant reduction of model sum of squared error, for all models. The incorporation of the crown variables to these models significantly improved model performance. According to results, non-linear regression models were less accurate than the three types of neural network models tested for both over-bark diameter and stem volume predictions in terms of standard error of the estimate and fit index. Specifically, the generated Levenberg-Marquardt Neural Network models outperformed the other models in terms of prediction accuracy. Therefore, this type of neural network model is worth consideration in over-bark diameter and volume prediction modeling, which are some of the most challenging tasks in forest resources management.

In this study defoliation damage in Taurus cedar (Cedrus libani A. Rich) stands in Turkey (Isparta region) caused by cedar shoot moth (Dichelia cedricola Diakonoff - Lep.: Tortricidae) was examined using multi-temporal Landsat data. Undamaged, low-damaged and heavily-damaged areas were located by assessing the variation of the Normalized Difference Vegetation Index derived from satellite imagery. Threshold boundaries for different damage levels were defined using mean NDVI values obtained from sub-areas spanning over the whole range of NDVI values. The reliability of the classification based on damages was statistically tested by comparing mean annual ring widths measured on increment cores extracted from sample trees exposed to different damage levels. Significant differences were found in mean annual ring widths among different areas previously classified based on NDVI data. Mean annual ring width in 2001 (an outbreak year) was 1.64 mm for undamaged area, 1.04 mm for low-damaged area, and 0.54 mm for heavily-damaged area. These findings indicate that damage mapping and monitoring mass damage caused by insect defoliation in Taurus cedar stands can be performed remotely by using NDVI values and Landsat TM data.

Generative deep learning is reshaping drug design. Chemical language models (CLMs) - which generate molecules in the form of molecular strings - bear particular promise for this endeavor. Here, we introduce a recent deep learning architecture, termed Structured State Space Sequence (S4) model, into de novo drug design. In addition to its unprecedented performance in various fields, S4 has shown remarkable capabilities to learn the global properties of sequences. This aspect is intriguing in chemical language modeling, where complex molecular properties like bioactivity can 'emerge' from separated portions in the molecular string. This observation gives rise to the following question: Can S4 advance chemical language modeling for de novo design? To provide an answer, we systematically benchmark S4 with state-of-the-art CLMs on an array of drug discovery tasks, such as the identification of bioactive compounds, and the design of drug-like molecules and natural products. S4 shows a superior capacity to learn complex molecular properties, while at the same time exploring diverse scaffolds. Finally, when applied prospectively to kinase inhibition, S4 designs eight of out ten molecules that are predicted as highly active by molecular dynamics simulations. Taken together, these findings advocate for the introduction of S4 into chemical language modeling - uncovering its untapped potential in the molecular sciences., (© 2024. The Author(s).)

Deep learning is becoming increasingly relevant in drug discovery, from de novo design to protein structure prediction and synthesis planning. However, it is often challenged by the small data regimes typical of certain drug discovery tasks. In such scenarios, deep learning approaches-which are notoriously 'data-hungry'-might fail to live up to their promise. Developing novel approaches to leverage the power of deep learning in low-data scenarios is sparking great attention, and future developments are expected to propel the field further. This mini-review provides an overview of recent low-data-learning approaches in drug discovery, analyzing their hurdles and advantages. Finally, we venture to provide a forecast of future research directions in low-data learning for drug discovery., Competing Interests: Declaration of competing interest There are no competing interests to disclose., (Copyright © 2024 The Author(s). Published by Elsevier Ltd.. All rights reserved.)

Machine learning models have found numerous successful applications in computational drug discovery. A large body of these models represents molecules as sequences since molecular sequences are easily available, simple, and informative. The sequence-based models often segment molecular sequences into pieces called chemical words, analogous to the words that make up sentences in human languages, and then apply advanced natural language processing techniques for tasks such as de novo drug design, property prediction, and binding affinity prediction. However, the chemical characteristics and significance of these building blocks, chemical words, remain unexplored. To address this gap, we employ data-driven SMILES tokenization techniques such as Byte Pair Encoding, WordPiece, and Unigram to identify chemical words and compare the resulting vocabularies. To understand the chemical significance of these words, we build a language-inspired pipeline that treats high affinity ligands of protein targets as documents and selects key chemical words making up those ligands based on tf-idf weighting. The experiments on multiple protein-ligand affinity datasets show that despite differences in words, lengths, and validity among the vocabularies generated by different subword tokenization algorithms, the identified key chemical words exhibit similarity. Further, we conduct case studies on a number of target to analyze the impact of key chemical words on binding. We find that these key chemical words are specific to protein targets and correspond to known pharmacophores and functional groups. Our approach elucidates chemical properties of the words identified by machine learning models and can be used in drug discovery studies to determine significant chemical moieties., (© 2024 The Authors. Molecular Informatics published by Wiley‐VCH GmbH.)

Robust generalization of drug-target affinity (DTA) prediction models is a notoriously difficult problem in computational drug discovery. In this article, we present pydebiaseddta: a computational software for improving the generalizability of DTA prediction models to novel ligands and/or proteins. pydebiaseddta serves as the practical implementation of the DebiasedDTA training framework, which advocates modifying the training distribution to mitigate the effect of spurious correlations in the training data set that leads to substantially degraded performance for novel ligands and proteins. Written in Python programming language, pydebiaseddta combines a user-friendly streamlined interface with a feature-rich and highly modifiable architecture. With this article we introduce our software, showcase its main functionalities, and describe practical ways for new users to engage with it.

Statistical models that accurately predict the binding affinity of an input ligand-protein pair can greatly accelerate drug discovery. Such models are trained on available ligand-protein interaction data sets, which may contain biases that lead the predictor models to learn data set-specific, spurious patterns instead of generalizable relationships. This leads the prediction performances of these models to drop dramatically for previously unseen biomolecules. Various approaches that aim to improve model generalizability either have limited applicability or introduce the risk of degrading overall prediction performance. In this article, we present DebiasedDTA, a novel training framework for drug-target affinity (DTA) prediction models that addresses data set biases to improve the generalizability of such models. DebiasedDTA relies on reweighting the training samples to achieve robust generalization, and is thus applicable to most DTA prediction models. Extensive experiments with different biomolecule representations, model architectures, and data sets demonstrate that DebiasedDTA achieves improved generalizability in predicting drug-target affinities.

Animal owners' potential to observe and report clinical signs, as the persons with the closest contact to their animals, is an often neglected source of information in surveillance. Allowing community members other than health care professionals, such as animal owners, to report health events can contribute to close current surveillance gaps and enhance early detection. In the present study, we tested a community-based surveillance (CBS) approach in the equine community in Switzerland. We aimed at revealing the attitudes and intentions of equine owners toward reporting clinical signs by making use of an online questionnaire. We further set up and operated an online CBS tool, named Equi-Commun. Finally, we investigated potential reasons for the lack of its use by applying qualitative telephone interviews. The majority of the respondents of the online questionnaire (65.5%, 707/1,078) answered that they could see themselves reporting clinical observations of their equine. The multivariate logistic regression analysis indicated that French-speaking equine owners and those belonging to the positive attitude cluster are more likely to report to a CBS tool. Equi-Commun operated between October 2018 and December 2019 yet received only four reports. With the addition of qualitative interviews, we identified three critical, interlinked issues that may have led to the non-use of Equi-Commun within the Swiss equine community: (1) for successfully implementing CBS, the need for surveillance within the community of interest must be given; (2) the respective population under surveillance, here the equine, needs to show enough clinical cases for owners to be able to maintain the memory of an existing tool and its possible use; and (3) targeted and high effort communication of the system is key for its success. While CBS relying only on lay animal owners, complementary to existing surveillance systems, could potentially provide a good proxy of timely surveillance data, it is questionable whether the added value of generated surveillance knowledge is in balance with efforts necessary to implement a successful system. With this study, we showcased both the potential and challenges of CBS in animal health, as this may be of relevance and guidance for future initiatives., Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (Copyright © 2021 Özçelik, Remy-Wohlfender, Küker, Visschers, Hadorn and Dürr.)

Tackling complex public health challenges requires integrated approaches to health, such as One Health (OH). A key element of these approaches is the integration of knowledge across sectors, disciplines and stakeholders. It is not yet clear which elements of knowledge integration need endorsement to achieve best outcomes. This paper assesses 15 OH initiatives in 16 African, Asian and European countries to identify opportunities to improve knowledge integration and to investigate geographic influences on knowledge integration capacities. Two related evaluation tools, both relying on semi-quantitative questionnaires, were applied to two sets of case studies. In one tool, the questions relate to operations and infrastructure, while the other assigns questions to the three phases of "design," "implementation," and "evaluation" of the project life cycle. In both, the question scores are aggregated using medians. For analysis, extreme values were identified to highlight strengths and weaknesses. Seven initiatives were assessed by a single evaluator external to the initiative, and the other eight initiatives were jointly assessed by several internal and external evaluators. The knowledge integration capacity was greatest during the project implementation stage, and lowest during the evaluation stage. The main weaknesses pointing towards concrete potential for improvement were identified to be a lack of consideration of systemic characteristics, missing engagement of external stakeholders and poor bridging of knowledge, amplified by the absence of opportunities to learn and evolve in a collective process. Most users were unfamiliar with the systems approach to evaluation and found the use of the tools challenging, but they appreciated the new perspective and saw benefits in the ensuing reflections. We conclude that systems thinking and associated practises for OH require not only specific education in OH core competencies, but also methodological and institutional measures to endorse broad participation. To facilitate meta-analyses and generic improvement of integrated approaches to health we suggest including knowledge integration processes as elements to report according to the COHERE guidelines., Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (Copyright © 2021 Hitziger, Berezowski, Dürr, Falzon, Léchenne, Lushasi, Markosyan, Mbilo, Momanyi, Özçelik, Prejit, Zinsstag and Rüegg.)

Identification of high affinity drug-target interactions is a major research question in drug discovery. Proteins are generally represented by their structures or sequences. However, structures are available only for a small subset of biomolecules and sequence similarity is not always correlated with functional similarity. We propose ChemBoost, a chemical language based approach for affinity prediction using SMILES syntax. We hypothesize that SMILES is a codified language and ligands are documents composed of chemical words. These documents can be used to learn chemical word vectors that represent words in similar contexts with similar vectors. In ChemBoost, the ligands are represented via chemical word embeddings, while the proteins are represented through sequence-based features and/or chemical words of their ligands. Our aim is to process the patterns in SMILES as a language to predict protein-ligand affinity, even when we cannot infer the function from the sequence. We used eXtreme Gradient Boosting to predict protein-ligand affinities in KIBA and BindingDB data sets. ChemBoost was able to predict drug-target binding affinity as well as or better than state-of-the-art machine learning systems. When powered with ligand-centric representations, ChemBoost was more robust to the changes in protein sequence similarity and successfully captured the interactions between a protein and a ligand, even if the protein has low sequence similarity to the known targets of the ligand., (© 2020 Wiley-VCH GmbH.)

The aim of this study is to examine the possible benefits of exercise and caloric restriction (CR) on cardiovascular hemodynamics, erectile function, and antioxidant system in metabolic syndrome (MS). Sixty male Spraque-Dawley rats were divided into five groups; control, MS, MS + CR, MS + exercise (EXC), and MS + CR + EXC. To induce MS, 10% fructose solution was applied for 3 months. Thereafter, in CR groups calorie was restricted 40% and in EXC groups swimming was performed for 6 weeks. Body weight, blood glucose, and blood pressure (BP) levels were measured before and after MS induction and at the end of the experiment. After decapitation, tumor necrosis factor (TNF)-α, adiponectin (ADP), and plasminogen activator inhibitor (PAI)-1 levels were investigated in blood, oxidative stress parameters were examined in heart, aorta, and corpus cavernosum (CC) tissues. Isometric contraction in isolated tissue bath was studied in aorta and CC tissues. Animals subjected to exercise and CR had decreased BP and blood glucose levels. Impaired contraction-relaxation responses in MS group were improved with exercise and CR. MS-induced increase in TNF-α, PAI-1, malondialdehyde (MDA), and decrease in ADP, glutathione (GSH), and superoxide dismutase (SOD) were normalized with exercise and CR. Exercise and CR may be beneficial against changes in cardiovascular hemodynamics caused by MS., (© 2020. The Author(s), under exclusive licence to Springer Nature Limited.)

Equine health is important in regard to trade, economy, society, and the veterinary, as well as public health. To reduce the burden of equine infectious diseases internationally, it is important to collect, review, and distribute equine health surveillance data as accurate and timely as possible. Within this study, we aimed at providing a comprehensive descriptive analysis of data submitted to Equinella, a voluntary veterinary-based surveillance system of non-notifiable equine infectious diseases and clinical signs, in Switzerland. This was achieved by reviewing the reports submitted since its relaunch in November 2013 and until April 2019, as well as assessing the data validity, activeness of participating veterinarians, coverage of the equine population, geographical representativeness, and timeliness of the system. In total, 630 reports have been submitted. Data validity ranged between 88.2 and 100%. The coverage of Equinella was assessed to be 50.8% of the Swiss equine population. Over the 5.5 years, of all 102 registered veterinarians, 67 (65.7%) submitted at least one report. On average, these veterinarians submitted 1.7 reports per year (median = 4 reports). More recently, in 2018, approximately only one-third [29 (28.4%)] of all registered veterinarians submitted at least one report. However, 59 (57.8%) have responded to the monthly reminder emails to confirm that they have not observed any relevant clinical case to be reported at least once (median number of confirmation per veterinarian = 9 of 12 reminder emails). The incidence of reports varied between cantons (member states of the Swiss confederation). The median timeliness of report submission was found to be 7 days. Overall, Equinella has been receiving reports since its initiation and contributed continuously to the surveillance of infectious diseases in the Swiss equine population and provided an output for the international equine community. Challenges encountered in achieving a higher number of submitted reports and increasing the coverage of the equine population, as well as the overall activeness of veterinarians, require further work. With our study, we provide a comprehensive overview of a veterinary-based voluntary surveillance system for equine health, assessed challenges of such, and suggest concrete improvements with transdisciplinary approaches for similar veterinary-based surveillance systems., (Copyright © 2020 Özçelik, Graubner, Remy-Wohlfender, Dürr and Faverjon.)

In ruminants, colostrum is the main source of immunoglobulins for the newborn animal, conferring immune protection until the immune system becomes active and able to synthesize its own immunoglobulins. Serotonin (5-HT), a biogenic amine derived from tryptophan, has stimulatory effects on many physiological processes, including components of the innate (mastocytes, eosinophils, and natural killer cells) and adaptive (T and B lymphocytes) immune systems. Based on the known effects of 5-HT on the immune system, we hypothesized that increased concentrations of 5-HT, through administration of its precursor 5-hydroxy-l-tryptophan (5-HTP), may positively affect development of the calf's immune system and therefore support health and growth performance during the first weeks of life. Eighteen calves were randomly assigned to 1 of 2 experimental groups (control and 5-HTP), resulting in n = 9 per treatment group. Both groups received 2 colostrum meals from a common pool of colostrum. Thereafter, calves were fed milk replacer twice daily for 30 d. In the 5-HTP group, colostrum and milk replacer were supplemented with 1.5 mg of 5-HTP/kg of birth weight during the first 15 d after birth. Body weight was recorded at birth and on d 5, 10, 15, and 30 after birth. Blood samples were collected every morning (0800 h) before feeding from birth until d 5 and then on d 7, 9, 11, 13, 15, and 30 after birth. Serum 5-HT concentrations were increased as a consequence of the 5-HTP supplementation. Plasma immunoglobulin G concentrations did not differ between groups throughout the experimental period. The blood mRNA abundance of several factors related to the innate and adaptive immune system [nuclear factor kappa-light-chain-enhancer of activated B cells (NF-κB), serum amyloid A-1 (SAA1), chemokine C-C motif ligand 5 (CCL5), cyclooxygenase 2 (PTGS2), haptoglobin (HP), and IL-1β] were increased in calves supplemented with 5-HTP. Supplementation of 5-HTP did not affect any of the measured metabolites (fatty acids and glucose) or minerals (calcium and magnesium) or milk feed intake, feed conversion ratio, and growth. In conclusion, 5-HTP supplementation induced an increase of 5-HT concentrations in blood and caused an increase in mRNA abundance of several factors related to the innate and adaptive immune systems, which might increase the protection of the calf against external agents., (Copyright © 2018 American Dairy Science Association. Published by Elsevier Inc. All rights reserved.)