Set Of Predictors Research Articles

Leveraging historical trials to predict Fusarium head blight resistance in spring wheat breeding programs.

Fusarium head blight (FHB) is a fungal disease posing a major threat to wheat production. Plant breeding that leverages genotyping is an effective method to improve the genetic resistance of cultivars. Started in 1995, the uniform regional scab nursery (URSN) consists of germplasm from several public breeding programs in the Northern US region. Its main objective is to showcase new sources of resistance and enable germplasm exchange among the cooperators; however, the data from the URSN have not been studied. Phenotypic and genotypic data from this nursery were gathered, as well as from two current breeding programs in the US Midwest. Genomic prediction on eight traits related to FHB and agronomic traits was applied, and the effects of statistical method, marker density, training set size, genetic structure, and genetic architecture of the trait were studied. Using the URSN population, reproducing kernel Hilbert space was the best method in various prediction settings, with an average accuracy of 0.63, marker density could be as low as 500 without decreasing the prediction accuracy, and training set optimization was useful for two traits. Furthermore, genotypic values were predicted in breeding programs using the URSN population as a training set with various prediction scenarios. Predicting unrelated populations led to a significant decrease in accuracy but with encouraging values for some traits and populations. Ultimately, when progressively decreasing the number of lines from breeding populations in the training set, the advantage of adding the URSN population was more pronounced, with an increase in accuracy up to 0.19.

Discriminating the adulteration of varieties and misrepresentation of vintages of Pu’er tea based on Fourier transform near infrared diffuse reflectance spectroscopy

In the Pu’er tea market, the ubiquity of blending different varieties and the fraudulent representation of vintage years present a persistent challenge. Traditional sensory evaluation and experience are often inadequate for discerning the true variety and vintage of tea, highlighting the need for more sophisticated analytical methods to ensure authenticity and quality. Fourier transform near infrared diffuse reflectance spectroscopy combined with radial basis function neural network (RBFNN) was applied for determination of the varieties and vintages of Pu’er tea. For vintage identification, the accuracy, precision, recall, and F1-score of the RBFNN model for the prediction set were 99.2%, 98.2%, 98.0%, and 98.0%, respectively. For identification of varieties adulteration, the corresponding parameters were 98.9%, 97.2%, 96.7%, and 96.6%, respectively. These results illustrated the feasibility to identify the adulteration of varieties and misrepresentation of vintages of Pu’er tea with near infrared spectra and RBFNN model, proving an efficient alternative for Pu’er tea quality inspection, and offering a robust method for combating the pervasive issues within the market.

False-Negative Review from the Mammography Audit: Refining Breast Imaging Practice.

Annual review of false-negative (FN) mammograms is a mandatory and critical component of the Mammography Quality Standards Act (MQSA) annual mammography audit. FN review can help hone reading skills and improve the ability to detect cancers at mammography. Subtle architectural distortion, asymmetries (seen only on one view), small lesions, lesions with probably benign appearance (circumscribed regular borders), isolated microcalcifications, and skin thickening are the most common mammographic findings when the malignancy is visible at retrospective review of FN mammograms. Most FN mammograms are not due to radiologist error. There are common and predictable settings in which FN mammograms occur. Patient factors associated with elevated FN mammograms include dense breasts, elevated lifetime risk of breast cancer, and personal history of breast cancer treated with lumpectomy and radiation therapy. About half of FN cancers are detected by supplemental screening examinations and half manifest clinically. The most common manifesting symptoms for interval cancers are a palpable abnormality, nipple discharge, and skin changes. Interval cancers can have more aggressive pathologic features and higher rates of node positivity. The FN review includes Breast Imaging Reporting and Data System (BI-RADS) 3 cases that develop a cancer diagnosis during surveillance. Nonbreast malignancies diagnosed as interval cancers (most commonly lymphoma and metastatic disease) do not need to be counted as FNs for audit purposes. The FN review and annual audit are confidential processes that protect patient and radiologist information while allowing meaningful quality control and improvement. Although FN mammograms are rare, review of these cases is a valuable educational tool. The slide presentation from the RSNA Annual Meeting is available for this article. ©RSNA, 2025.

Use of Fourier transform infrared spectroscopy and chemometric analysis to predict the bacilloscopic index in the saliva of leprosy patients.

Leprosy is an infectious disease caused by the Mycobacterium leprae complex. Although the diagnosis of this disease is clinical, additional tests are often needed. One of the most common tests is intradermal smear bacilloscopy, which detects the patient's bacillary load. However, bacilloscopy is an invasive test and its results are subjective. The aim of this study was to propose a methodology based on Fourier transform infrared (FTIR) spectroscopy to predict the bacilloscopic index in the saliva of leprosy patients. A total of 88 saliva samples were included, and the bacilloscopic index of the patients was previously defined by intradermal smear bacilloscopy. The saliva samples were analyzed by attenuated total reflection (ATR)-FTIR; a supervised analysis with partial least squares regression (PLS), after orthogonal signal correction (OSC), was used to predict the bacilloscopic index. The PLS model with three latent variables and one OSC component obtained a coefficient of determination greater than 0.9999 in both the calibration and prediction sets. The model was able to predict the bacilloscopic indexes with a minimum error, demonstrating its robustness. Thus, modeling with ATR/FTIR and multivariate calibration using one OSC component showed high accuracy and reproducibility, overcoming the limitations of intradermal smear bacilloscopy and proving to be a promising method in the clinical management of patients with leprosy.

Non-Destructive Detection of pH Value During Secondary Fermentation of Maize Silage Using Colorimetric Sensor Array Combined with Hyperspectral Imaging Technology

The pH value of maize silage can accurately reflect its quality. In this study, a colorimetric sensor array (CSA) combined with hyperspectral imaging (HSI) was used to predict the pH value of maize silage during secondary fermentation. Seventeen color-sensitive dyes were used to construct the CSA, which was subsequently applied to capture the volatile odor profiles of maize silage samples. Hyperspectral images of the color-sensitive dyes on the CSA were acquired using the HSI technique. Different algorithms were used to preprocess the raw spectral data of each dye, and a partial least squares regression (PLSR) model was built for each dye separately. Subsequently, the adaptive bacterial foraging optimization (ABFO) algorithm was employed to identify three color-sensitive dyes that demonstrated heightened sensitivity to pH variations in maize silage. This study further compared the capabilities of individual dyes, as well as their combinations, in predicting the pH value of maize silage. Additionally, a novel feature wavelength extraction method based on the ABFO algorithm was proposed, which was then compared with two traditional feature extraction algorithms. These methods were combined with PLSR and backpropagation neural network (BPNN) algorithms to construct a quantitative prediction model for the pH value of maize silage. The results show that the quantitative prediction model constructed based on three dyes was more accurate than that constructed based on an individual dye. Among them, the ABFO-BPNN model constructed on the basis of combined dyes had the best prediction performance, with prediction correlation coefficient (RP2), root mean square error of the prediction set (RMSEP), and ratio of performance deviation (RPD) values of 0.9348, 0.3976, and 3.9695, respectively. The aim of this study was to develop a reliable evaluation model to achieve fast and accurate predictions of silage pH.

Distribution-free uncertainty quantification for inverse problems: Application to weak lensing mass mapping

In inverse problems, the aim of distribution-free uncertainty quantification (UQ) is to obtain error bars in the reconstruction with coverage guarantees that are independent of any prior assumptions about the data distribution. This allows for a better understanding of how intermediate errors introduced during the process affect subsequent stages and ultimately influence the final reconstruction. In the context of mass mapping, uncertainties could lead to errors that affect how the underlying mass distribution is understood or that propagate to cosmological parameter estimation, thereby impacting the precision and reliability of cosmological models. Current surveys, such as Euclid or Rubin will provide new weak lensing datasets of very high quality. Accurately quantifying uncertainties in mass maps is therefore critical to fully exploit their scientific potential and to perform reliable cosmological parameter inference. In this paper, we extend the conformalized quantile regression (CQR) algorithm, initially proposed for scalar regression, to inverse problems. We compared our approach with another distribution-free approach based on risk-controlling prediction sets (RCPS). Both methods are based on a calibration dataset, and they offer finite-sample coverage guarantees that are independent of the data distribution. Furthermore, they are applicable to any mass mapping method, including black box predictors. In our experiments, we applied UQ to three mass-mapping methods: the Kaiser-Squires inversion, iterative Wiener filtering, and the MCALens algorithm. Our experiments reveal that RCPS tends to produce overconservative confidence bounds with small calibration sets, whereas CQR is designed to avoid this issue. Although the expected miscoverage rate is guaranteed to stay below a user-prescribed threshold regardless of the mass mapping method, selecting an appropriate reconstruction algorithm remains crucial for obtaining accurate estimates, especially around peak-like structures, which are particularly important for inferring cosmological parameters. Additionally, the choice of mass mapping method influences the size of the error bars.

P0918 Identification of a serum proteomics signature linked with anti-TNF therapy response outcomes in Inflammatory Bowel Disease

Abstract Background While treatment options for active disease in IBD become diverse, the choice of therapies is mostly based on patient characteristics, disease course and severity but restrained by economic rationales. To maximize treatment effectiveness, predictive biomarkers are needed to guide therapies either ex ante or at the earliest possible time point after therapy initiation. Previously, we identified dynamic blood-based RNA and DNA methylation signatures that are linked with therapy response to anti-TNF in IBD1. Here, we aim to identify serum proteome biomarkers associated with therapeutic outcomes in IBD patients receiving anti-TNF treatment. Methods 31 ulcerative colitis (UC) and 27 Crohn’s disease (CD) patients with active clinical and endoscopic disease were recruited and followed at baseline (W0) and at weeks 2 (W2), 6 (W6), and 14 (W14) after initiating infliximab therapy. The clinical endpoint of interest was defined as a combination of clinical remission (partial Mayo ≤ 2/CDAI < 150) and endoscopic response (reduction in endoscopic Mayo ≥ 1/SES-CD ≥ 50%) at W14. Serum was collected at each time point and subjected to proximity extension assays (Olink® Explore 3072 panel) to screen for 2,944 proteins. Linear mixed models (LMM) were applied to identify differentially expressed proteins (DEPs) between endpoint achievers/non-achievers over time. Additionally, post-analysis of DEPs was performed using cv.glmnet with least absolute shrinkage and selection operator (LASSO) regression to identify candidate predictive marker sets. Results A total of 229 DEPs were identified over time between UC responders and non-responders: 8 at W0, 22 at W2, 181 at W6, and 78 at W14. In CD patients, 23 DEPs were identified: 9 at W0, 7 at W2, 13 at W6, and 13 at W14. These DEPs were disease-specific and linked to Gene Ontology (GO) terms related to inflammatory response and cell differentiation. Using LMM and machine learning, we identified 5 baseline proteins in UC and 6 in CD patients that differentiated combined endpoint achievers from non-achievers (AUROC: UC: 0.958, CD: 0.800). Additionally, we identified dynamic changes from W0 to W2 in 7 proteins associated with immune regulation in UC patients (1 in CD), which were linked to therapeutic outcomes at W14. Conclusion Detecting specific ex ante biomarkers or early dynamic molecular signatures are critical for precision medicine in IBD. Our data suggest that serum proteomics profiling enables the differentiation of patients who will attain therapeutic success under anti-TNF therapy from those who will not. This study warrants further investigations in larger, independent datasets to confirm the potential clinical utility of the proteomics signature. References (1) Mishra N, et al. Longitudinal multi-omics analysis identifies early blood-based predictors of anti-TNF therapy response in inflammatory bowel disease. Genome Med. 2022 Sep 24;14(1):110. doi: 10.1186/s13073-022-01112-z. PMID: 36153599; PMCID: PMC9509553. This project has received funding from the DFG Cluster of Excellence 2167 "Precision medicine in chronic inflammation", the BMBF (e:Med Network iTREAT 01ZX2202A, and GUIDE-IBD 031L0188A), and the Innovative Medicines Initiative 2 Joint Undertaking (JU) under grant agreement No 831434 (3TR) and No 853995 (ImmUniverse).The JU receives support from the European Union’s Horizon 2020 research and innovation programme and EFPIA. The content provided in this publication reflects the author’s views only. Neither the Innovative Medicines Initiative (IMI JU) nor the European Commission are responsible for any use that may be made of the information it contains.

Rapid identification of high-temperature Daqu Baijiu with the same aroma type by UV-VIS sensor of HBT combined with Zn2+

Aim: Baijiu adulteration has always been a hot spot of social concern, especially high-temperature Daqu Baijiu, because of its better flavor quality and high value, it faces a challenge from illegal adulteration of high-grade Baijiu bottles with low-grade Baijiu. Methods: A new ultraviolet-visible spectroscopy (UV-VIS) sensor method based on 2-(2-hydroxyphenyl) benzothiazole (HBT) combined with Zn2+ was constructed. The specific mechanism of light signal change was mainly based on the competitive coordination effect of pyrazines and other nitrogen-containing compounds in high-temperature Daqu Baijiu and small molecular probe HBT on Zn2+ and the excited state intramolecular proton transfer (ESIPT) mechanism of HBT itself. Results: The random forest results showed that the prediction set classification accuracy was improved from 62.37% to 100%. The accuracy of the data driven-soft independent modelling of class analogies (DD-SIMCA) model was between 90% and 100%, indicating that the array sensor had a good recognition effect on the adulteration of the same aroma type of Baijiu. Twelve kinds of Maillard reaction products such as tetramethylpyrazine, 2,6-dimethylpyrazine, and furfural in Baijiu were predicted successfully, and the deviation between the real value and the predicted value was less than 1.8746% ± 1.4515%. Conclusions: This method not only improves the specificity of spectral detection, and the amount of information extracted from Baijiu samples, but also the detection time is shortened to less than 3 min, and the accurate identification of high-temperature Daqu Baijiu with the same aroma type was realized. This method can provide reliable help for the rapid identification of high-temperature Daqu and other precious Baijiu, even traditional fermented food.

Confidence-based Estimators for Predictive Performance in Model Monitoring

After a machine learning model has been deployed into production, its predictive performance needs to be monitored. Ideally, such monitoring can be carried out by comparing the model’s predictions against ground truth labels. For this to be possible, the ground truth labels must be available relatively soon after inference. However, there are many use cases where ground truth labels are available only after a significant delay, or in the worst case, not at all. In such cases, directly monitoring the model’s predictive performance is impossible. Recently, novel methods for estimating the predictive performance of a model when ground truth is unavailable have been developed. Many of these methods leverage model confidence or other uncertainty estimates and are experimentally compared against a naive baseline method, namely Average Confidence (AC), which estimates model accuracy as the average of confidence scores for a given set of predictions. However, until now the theoretical properties of the AC method have not been properly explored. In this paper, we bridge this gap by reviewing the AC method and show that under certain general assumptions, it is an unbiased and consistent estimator of model accuracy. We also augment the AC method by deriving valid confidence intervals for the estimates it produces. These contributions elevate AC from an ad-hoc estimator to a principled one, encouraging its use in practice. We complement our theoretical results with empirical experiments, comparing AC against more complex estimators in a monitoring setting under covariate shift. We conduct our experiments using synthetic datasets, which allow for full control over the nature of the shift. Our experiments with binary classifiers show that the AC method is able to beat other estimators in many cases. However, the comparative quality of the different estimators is found to be heavily case-dependent.

Prediction sets for high-dimensional mixture of experts models

Prediction sets for high-dimensional mixture of experts models

Rapid Determination of Crocin-I in Gardenia Fruits (Gardenia jasminoides Ellis) by Combining Spectral and Image Data Through Hyperspectral Imaging.

Crocin-I, a water-soluble carotenoid pigment, is an important coloring constituent in gardenia fruit. It has wide application in various industries such as food, medicine, chemical industry, and so on. So the content of crocin-I plays a key role in evaluating the quality of gardenia. We assessed crocin-I content in gardenia with a rapid, nondestructive, and convenient method. The data of gardenia samples were scanned under a portable visible-near-infrared (Vis-NIR) hyperspectral imaging (HSI) in the spectral range of 400-1000 nm. Afterward, the spectral data along with image-related information, encompassing color and texture, were extracted from the HSI. Based on a single information and its fusion at different fusion levels (low-level, traditional mid-level fusion, and an improved mid-level fusion), partial least squares regression (PLSR) prediction models were established and compared. The results demonstrated the superiority of data fusion, which ingeniously combined spectra and image data. Compared with individual information sources, the traditional mid-level fusion model showed a robust predictive ability. The correlation coefficient of the prediction set (Rp), the root mean square error of prediction (RMSEP), and the ratios of performance to deviation (RPDP) of the model were 0.901, 0.962, and 2.262, respectively. This study highlights the effectiveness of the data fusion method, showcasing its capacity to significantly enhance the prediction accuracy of crocin-I content in gardenia through the integration of hyperspectral mapping data. The findings of this research are anticipated to serve as a valuable reference for predicting the active ingredients of other Chinese herbal medicines.

PPI-CoAttNet: A Web Server for Protein-Protein Interaction Tasks Using a Coattention Model.

Predicting protein-protein interactions (PPIs) is crucial for advancing drug discovery. Despite the proposal of numerous advanced computational methods, these approaches often suffer from poor usability for biologists and lack generalization. In this study, we designed a deep learning model based on a coattention mechanism that was capable of both PPI and site prediction and used this model as the foundation for PPI-CoAttNet, a user-friendly, multifunctional web server for PPI prediction. This platform provides comprehensive services for online PPI model training, PPI and site prediction, and prediction of interactions with proteins associated with highly prevalent cancers. In our Homo sapiens test set for PPI prediction, PPI-CoAttNet achieved an AUC of 0.9841 and an F1 score of 0.9440, outperforming most state-of-the-art models. Additionally, these results are generated in real time, delivering outcomes within minutes. We also evaluated PPI-CoAttNet for downstream tasks, including novel E3 ligase scoring, demonstrating outstanding accuracy. We believe that this tool will empower researchers, especially those without computational expertise, to leverage AI for accelerating drug development.

Nanogap-Assisted SERS/PCR Biosensor Coupled Machine Learning for the Direct Sensing of Staphylococcus aureus in Food.

Staphylococcus aureus (S. aureus) is the primary risk factor in food safety. Herein, a nanogap-assisted surface-enhanced Raman scattering/polymerase chain reaction (SERS/PCR) biosensor coupled with a machine-learning tool was developed for the direct and specific sensing of S. aureus in milk. The specific nuc gene (nuc T) from S. aureus was initially amplified through PCR and subsequently captured via the nanogap effect of I- and Mg2+-mediated bimetallic gold and silver nanoflowers (Au/Ag FL@I--Mg2+). These nanogaps generate hotspots for the direct signal amplification of enclosed nuc T. Subsequently, machine-learning tools were used to comparatively analyze the collected SERS signals. The bootstrapping soft shrinkage-partial least-squares method exhibited superior performance (root mean-square error of prediction: 0.437, prediction set correlation coefficient: 0.967). This study demonstrated a novel label-free strategy for specifically detecting S. aureus. The strategy could be advanced to serve as a platform for application to other types of foodborne pathogenic bacteria by engineering a suitable specific primer.

Fair prediction sets through multi-objective hyperparameter optimization

The widespread implementation of machine learning in safety-critical domains has raised ethical concerns regarding algorithmic discrimination. In such settings, the integration of fairness-aware algorithms with uncertainty quantification tools enables the development of reliable and safe decision-making. In this paper, we introduce a novel methodology that combines conformal prediction, offering rigorous prediction sets, with multi-objective optimization via evolutionary learning. The proposed meta-algorithm optimizes the hyperparameter configuration of classifiers to produce confidence predictors that balance efficiency and equalized coverage guarantees, addressing fairness concerns related to sensitive attributes. We empirically evaluate our methodology with four real-world problems and demonstrate its efficacy in exploring this trade-off and producing a repertoire of Pareto optimal conformal predictors. In this way, our contribution offers different modeling alternatives from which to choose depending on the policy adopted by stakeholders, thus illustrating its capability to enhance equitable decision-making.

Regularized Multi-Decoder Ensemble for an Error-Aware Scene Representation Network.

Feature grid Scene Representation Networks (SRNs) have been applied to scientific data as compact functional surrogates for analysis and visualization. As SRNs are black-box lossy data representations, assessing the prediction quality is critical for scientific visualization applications to ensure that scientists can trust the information being visualized. Currently, existing architectures do not support inference time reconstruction quality assessment, as coordinate-level errors cannot be evaluated in the absence of ground truth data. By employing the uncertain neural network architecture in feature grid SRNs, we obtain prediction variances during inference time to facilitate confidence-aware data reconstruction. Specifically, we propose a parameter-efficient multi-decoder SRN (MDSRN) architecture consisting of a shared feature grid with multiple lightweight multi-layer perceptron decoders. MDSRN can generate a set of plausible predictions for a given input coordinate to compute the mean as the prediction of the multi-decoder ensemble and the variance as a confidence score. The coordinate-level variance can be rendered along with the data to inform the reconstruction quality, or be integrated into uncertainty-aware volume visualization algorithms. To prevent the misalignment between the quantified variance and the prediction quality, we propose a novel variance regularization loss for ensemble learning that promotes the Regularized multi-decoder SRN (RMDSRN) to obtain a more reliable variance that correlates closely to the true model error. We comprehensively evaluate the quality of variance quantification and data reconstruction of Monte Carlo Dropout (MCD), Mean Field Variational Inference (MFVI), Deep Ensemble (DE), and Predicting Variance (PV) in comparison with our proposed MDSRN and RMDSRN applied to state-of-the-art feature grid SRNs across diverse scalar field datasets. We demonstrate that RMDSRN attains the most accurate data reconstruction and competitive variance-error correlation among uncertain SRNs under the same neural network parameter budgets. Furthermore, we present an adaptation of uncertainty-aware volume rendering and shed light on the potential of incorporating uncertain predictions in improving the quality of volume rendering for uncertain SRNs. Through ablation studies on the regularization strength and decoder count, we show that MDSRN and RMDSRN are expected to perform sufficiently well with a default configuration without requiring customized hyperparameter settings for different datasets.

Quality Assurance of Total Carotenoids and Quercetin in Marigold Flowers (Tagetes erecta L.) as Edible Flowers.

Marigold flowers, which are also known as Tagetes erecta L., are widely recognized for their bright colors and health benefits. Therefore, the purpose of this research was to investigate the quality of total carotenoid content (TCC) and quercetin in marigold flowers, specifically the edible ones, using visible near-infrared spectroscopy (Vis-NIRS) technology. Both bioactive compounds in these flowers were assessed using Vis-NIRS. The technology is considered to be a rapid and non-destructive method for evaluating the quality of agricultural products. To ensure accuracy in the evaluation, Vis-NIRS was validated against conventional methods such as spectrophotometry and chromatography. The results showed that the use of Vis-NIRS helped to accurately determine the levels of TCC and quercetin in marigold flowers. Based on the analysis results, the best accuracy values for TCC were as follows: the correlation coefficient of the calibration set (R cal) was 0.94, the root mean square error of the calibration set (RMSEC) was 125.57, the correlation coefficient of the prediction set (R pred) was 0.87, the root mean square error of the prediction set (RMSEP) was 129.35, and the ratio of prediction to deviation (RPD) was 2.77. For quercetin, the best accuracy values were: R cal was 0.96, RMSEC was 1.63, R pred was 0.88, RMSEP was 2.37, and RPD was 2.09. These results demonstrate that the method provides a reliable alternative to destructive method. The research showed that Vis-NIRS served as a reliable quality assurance tool for assessing bioactive compounds in marigold flowers.

Detection of heavy metals in soil using Au@SiO2 nanoparticles and surface microstructure combined with laser-induced breakdown spectroscopy.

The detection of heavy metals in soil is of great scientific significance for food security and human health. However, traditional detection methods are complicated, time-consuming, and labor-intensive. Herein, we developed a novel method using Au@SiO2 nanoparticles (NPs) and surface microstructure combined with laser-induced breakdown spectroscopy (Au@SiO2 NPs-SMS-LIBS) for the rapid detection of lead (Pb), chromium (Cr), and copper (Cu) in soil samples. The surface microstructures and Au@SiO2 NPs were prepared to improve detection sensitivity and stability. The limits of detection (LODs) for Pb, Cr, and Cu were 0.36 mg/kg, 0.32 mg/kg, and 0.28 mg/kg, respectively, with relative standard deviations (RSDs) of 5.47-6.72 %. The mechanisms of spectral performance enhancement of LIBS detection were thoroughly investigated. Furthermore, the stacking combination model was developed to improve quantitative accuracy, with the correlation of the prediction set (Rp2) for Pb, Cr, and Cu being 0.9285, 0.8625, and 0.9160, respectively. This work offers a very promising solution to improve the sensitivity, stability, and accuracy of heavy metal detection. The developed method holds great application potential for large-scale soil assessments and real-time heavy metal pollution monitoring.

Non-destructive detection of milk nutritional components based on hyperspectral imaging.

As consumers increasingly prioritize food safety and nutritional value, the dairy industry faces a pressing need for rapid and accurate methods to detect essential nutritional components in milk, such as fat, protein, and lactose. Hyperspectral imaging (HSI) technology, known for its non-destructive, fast, and precise nature, shows great promise in food quality assessment. However, the high dimensionality of HSI data poses challenges for effective band selection and model optimization. Additionally, prior studies primarily focus on predicting single nutritional components without addressing simultaneous multi-component detection. To overcome these challenges, this study presents a comprehensive approach that integrates moving average smoothing and first derivative (MA-FD) preprocessing, the improved coati optimization algorithm (ICOA), and the CatBoost model for multi-target regression. ICOA incorporates the good point set strategy, dynamic opposition-based learning, and the golden sine algorithm, which significantly enhance its global search capability and convergence speed in band selection. Combined with CatBoost's multi-target prediction capability, this method enables accurate detection of fat, protein, and lactose levels in milk. Experimental results demonstrate high prediction accuracy, with the calibration set achieving an multi-target coefficient of determination (MultiR2) of 0.9992 and multi-target root mean square error (MultiRMSE) of 0.0240, while the prediction set yielded an MultiR2 of 0.9797 and MultiRMSE of 0.1181. Prediction set R2 values for fat, protein, and lactose were 0.9658, 0.9910, and 0.9825, respectively. The proposed method demonstrates robust predictive accuracy and reliability in milk quality assessment, and its potential for application in broader food quality assessments is substantial. PRACTICAL APPLICATION: This study provides a rapid, non-destructive method for assessing milk quality by detecting key nutritional components through hyperspectral imaging, combined with MA-FD preprocessing, ICOA for band selection, and CatBoost for multi-target regression. This approach offers the dairy industry a reliable, non-invasive solution that supports quality control and helps safeguard consumer health.

Cognate reflex prediction as hypothesis test for a genealogical relation between the Panoan and Takanan language families.

We present a novel approach for testing genealogical relations between language families. Our method, which has previously only been applied to closely related languages, makes predictions for cognate reflexes based on the regularity of proposed sound correspondences between language families that are hypothesized to be related. We test the hypothesis about a genealogical relation between Panoan and Takanan, two linguistic families of the Amazon. The workflow contributes to new ideas of hypothesis testing in historical linguistics and can likely be transferred to other language families. We predict 206 cognate reflexes from Shipibo-Konibo, a Panoan language, from independently proposed Proto-Takanan reconstructions and test our predictions in elicitation sessions with speakers of the language. We found 21 correct predictions from the core-set, as well as another 20 correct predictions from the extended set of predictions. In addition to confirming the previously established sound correspondence patterns, we find further evidence for additional patterns that suggest the reconstruction of three new phonemes for Proto-Pano-Takanan. PROTOCOL REGISTRATION: The stage 1 protocol for this Registered Report was accepted in principle on 06/05/24. The protocol, as accepted by the journal, can be found at: https://doi.org/10.17605/OSF.IO/FGBM7 .

Assessing the predicted impact of single amino acid substitutions in calmodulin for CAGI6 challenges.

Recent thermodynamic and functional studies have been conducted to evaluate the impact of amino acid substitutions on Calmodulin (CaM). The Critical Assessment of Genome Interpretation (CAGI) data provider at University of Verona (Italy) measured the melting temperature (Tm) and the percentage of unfolding (%unfold) of a set of CaM variants (CaM challenge dataset). Thermodynamic measurements for the equilibrium unfolding of CaM were obtained by monitoring far-UV Circular Dichroism as a function of temperature. These measurements were used to determine the Tm and the percentage of protein remaining unfolded at the highest temperature. The CaM challenge dataset, comprising a total of 15 single amino acid substitutions, was used to evaluate the effectiveness of computational methods in predicting the Tm and unfolding percentages associated with the variants, and categorizing them as destabilizing or not. For the sixth edition of CAGI, nine independent research groups from four continents (Asia, Australia, Europe, and North America) submitted over 52 sets of predictions, derived from various approaches. In this manuscript, we summarize the results of our assessment to highlight the potential limitations of current algorithms and provide insights into the future development of more accurate prediction tools. By evaluating the thermodynamic stability of CaM variants, this study aims to enhance our understanding of the relationship between amino acid substitutions and protein stability, ultimately contributing to more accurate predictions of the effects of genetic variants.