Selective Genotyping and Phenotyping for Optimization of Genomic Prediction Models for Populations with Different Diversity

To overcome the different challenges to food security caused by a growing population and climate change, soybean (Glycine max (L.) Merr.) breeders are creating novel cultivars that have the potential to improve productivity while maintaining environmental sustainability. Genomic selection (GS) is an advanced approach that may accelerate the rate of genetic gain in breeding using genome-wide molecular markers. The accuracy of genomic selection can be affected by trait architecture and heritability, marker density, linkage disequilibrium, statistical models, and training set. The selection of a minimal and optimal marker set with high prediction accuracy can lower genotyping costs, computational time, and multicollinearity. Selective phenotyping could reduce the number of genotypes tested in the field while preserving the genetic diversity of the initial population. This study aimed to evaluate different methods of selective genotyping and phenotyping on the accuracy of genomic prediction for soybean yield. The evaluation was performed on three populations: recombinant inbred lines, multifamily diverse lines, and germplasm collection. Strategies adopted for marker selection were as follows: SNP (single nucleotide polymorphism) pruning, estimation of marker effects, randomly selected markers, and genome-wide association study. Reduction of the number of genotypes was performed by selecting a core set from the initial population based on marker data, yet maintaining the original population's genetic diversity. Prediction ability using all markers and genotypes was different among examined populations. The subsets obtained by the model-based strategy can be considered the most suitable for marker selection for all populations. The selective phenotyping based on makers in all cases had higher values of prediction ability compared to minimal values of prediction ability of multiple cycles of random selection, with the highest values of prediction obtained using AN approach and 75% population size. The obtained results indicate that selective genotyping and phenotyping hold great potential and can be integrated as tools for improving or retaining selection accuracy by reducing genotyping or phenotyping costs for genomic selection.

Development and validation of a predictive model for fetal cerebral maturation using ultrasound for fetuses with normal growth and fetal growth restriction

Background

Investigation of fetal cerebral maturation (FCM) is necessary and important to provide crucial prognostic information for normal and high-risk fetuses. The study aimed to develop a valid and quantitative predictive model for assessing FCM using ultrasound and validate the model for fetuses with normal and restricted growth.

Methods

This was a multicenter prospective observational study. Fetuses with normal growth recruited from a university teaching hospital (Center 1) and a municipal maternal unit (Center 2) were included in the training set and external validation set 1, respectively. The 124 growth-restricted fetuses enrolled in Center 1 were included in validation set 2. FCM was used to describe the gestational age (GA) in this study. The model was developed based on the sum of fetal cranial parameters (total fetal cranial parameters), including head circumference (HC) and depths of the insula (INS) and sylvian fissure (SF), parieto-occipital fissure (POF), and calcarine fissure (CF). A regression model, constructed based on total fetal cranial parameters and predicted GA, was established using the training set and validated using external validation set 1 and validation set 2.

Results

The intra- and interobserver intraclass correlation coefficients for HC, and depths of the INS and SF, POF, and CF were >0.90. An exponential regression equation was used to predict FCM: predicted GA of FCM (weeks) =11.16 × exp (0.003 × total fetal cranial parameters) (P<0.001; adjusted R2=0.973), standard error of estimate, 0.67 weeks. The standard error of the predicted GA of FCM from the model was ±4.7 days. In the validation set 1, the mean standard error of the developed prediction model for FCM was 0.97 weeks. The predictive model showed that FCM was significantly delayed in validation set 2 (2.10±1.31 weeks, P<0.001), considering the GA per the last menstrual period.

Conclusions

The predictive performance of the FCM model developed in this study was excellent, and the novel model may be a valuable investigative tool during clinical implementation.

Comparative Study of Augmented Classical Least Squares Models for UV Assay of Co-Formulated Antiemetics Together with Related Impurities

The classical least squares (CLS) model and three augmented CLS models are adopted and validated for the analysis of pyridoxine HCl (PYR), cyclizine HCl (CYC), and meclizine HCl (MEC) in a quinary mixture with two related impurities: the CYC main impurity, Benzhydrol (BEH), which has carcinogenic and hepatotoxic effects, and the MEC official impurity, 4-Chlorobenzophenone (BEP). The proposed augmented CLS models are orthogonal signal correction CLS (OSC-CLS), direct orthogonal signal correction CLS (DOSC-CLS), and net analyte processing CLS (NAP-CLS). These models were applied to quantify the three active constituents in their raw materials and their corresponding dosage forms using their UV spectra. To evaluate the CLS-based models sensibly, we design a comparative study involving two sets: the training set to construct models and the validation set to assess the prediction abilities of these models. A five-level, five-factor calibration design was established to produce 25 mixtures for the calibration set. In addition, 16 experiments were performed for a test set distributed equally between the in-space and out-space samples. The primary criterion for comparing the models' performance was the validation set's root mean square error of prediction (RMSEP) value. Finally, augmented CLS models showed acceptable results for assaying the three analytes. The results were compared statistically with the reported HPLC methods; however, the DOSC-CLS model proved the best for assaying the dosage forms.

An AAM-Based Identification Method for Ear Acupoint Area

Ear image segmentation and identification is for the "observation" of TCM (traditional Chinese medicine), because disease diagnoses and treatment are achieved through the massaging of or pressing on some corresponding ear acupoints. With the image processing of ear image positioning and regional segmentation, the diagnosis and treatment of intelligent traditional Chinese medicine ear acupoints is improved. In order to popularize ear acupoint therapy, image processing technology has been adopted to detect the ear acupoint areas and help to gradually replace well-trained, experienced doctors. Due to the small area of the ear and the numerous ear acupoints, it is difficult to locate these acupoints based on traditional image recognition methods. An AAM (active appearance model)-based method for ear acupoint segmentation was proposed. The segmentation was illustrated as 91 feature points of a human ear image. In this process, the recognition effects of the ear acupoints, including the helix, antihelix, cymba conchae, cavum conchae, fossae helicis, fossae triangularis auriculae, tragus, antitragus, and earlobe, were divided precisely. Besides these, specially appointed acupoints or acupoint areas could be prominent in ear images. This method made it possible to partition and recognize the ear's acupoints through computer image processing, and maybe own the same abilities as experienced doctors for observation. The method was proved to be effective and accurate in experiments and can be used for the intelligent diagnosis of diseases.

Training set designs for prediction of yield and moisture of maize test cross hybrids with unreplicated trials

Unreplicated field trials and genomic prediction are both used to enhance the efficiency in early selection stages of a hybrid maize breeding program. No results are available on the optimal experimental design when combining both approaches. Our objectives were to investigate the effect of the training set design on the accuracy of genomic prediction in unreplicated maize test crosses. We carried out a cross validation study on basis of an experimental data set consisting of 1436 hybrids evaluated for yield and moisture for which genotyping information of 461 SNP markers were available. Training set designs of different size, implementing within environment prediction, within year prediction, across year prediction, and combinations of data sources across years and environments were compared with respect to their prediction accuracy. Across year prediction did not reach prediction accuracies that are useful for genomic selection. Within year prediction across environments provided useful correlations between observed and predicted breeding values. The prediction accuracies did not improve when adding to the training set data from previous years. We conclude that using all data available from unreplicated tests of the current breeding cycle provides a good accuracy of predicting test crosses, whereas adding data from previous breeding cycles, in which the genotypes are less related to the tested material, has only limited value for increasing the prediction accuracy.

Clinical Features and Computed Tomography Radiomics-Based Model for Predicting Pancreatic Ductal Adenocarcinoma and Focal Mass-Forming Pancreatitis

Objective: To establish a predictive model distinguishing focal mass-forming pancreatitis (FMFP) from pancreatic ductal adenocarcinoma (PDAC) based on computed tomography (CT) radiomics and clinical data. Methods: A total of 78 FMFP patients (FMFP group) and 120 PDAC patients (PDAC group) who were admitted to Xiangyang No.1 People's Hospital and Xiangyang Central Hospital from February 2012 to May 2021 and were pathologically diagnosed were included in this study, and were input to set up the training set and test set at a ratio of 7:3. The 3Dslicer software was used to extract the radiomic features and radiomic scores (Radscores) of the 2 groups, and the clinical data (age, gender, etc), CT imaging features (lesion location, size, enhancement degree, vascular wrapping, etc) and CT radiomic features of the 2 groups were compared. Logistic regression was used to screen the independent risk factors of the 2 groups, and multiple prediction models (clinical imaging model, radiomics model, and combined model) were established. Then the receiver operating characteristic (ROC) analysis and decision curve analysis (DCA) were conducted to compare the prediction performance and net benefit of the models. Results: The multivariate logistic regression results indicated that dilation of the main pancreatic duct, vascular wrapping, Radscore1 and Radscore2 were independent influencing factors for distinguishing FMFP from PDAC. In the training set, the combined model showed the best predictive performance (area under the ROC curve [AUC] 0.857, 95% CI [0.787-0.910]), significantly higher than the clinical imaging model (AUC 0.650, 95% CI [0.565-0.729]) and the radiomics model (AUC 0.812, 95% CI [0.759-0.890]). DCA confirmed that the combined model had the highest net benefit. These results were further validated by the test set. Conclusion: The combined model based on clinical-CT radiomics data can effectively identify FMFP and PDAC, providing a reference for clinical decision-making.

A Deep-Learning-Based Artificial Intelligence System for the Pathology Diagnosis of Uterine Smooth Muscle Tumor

We aimed to develop an artificial intelligence (AI) diagnosis system for uterine smooth muscle tumors (UMTs) by using deep learning. We analyzed the morphological features of UMTs on whole-slide images (233, 108, and 30 digital slides of leiomyosarcomas, leiomyomas, and smooth muscle tumors of uncertain malignant potential stained with hematoxylin and eosin, respectively). Aperio ImageScope software randomly selected ≥10 areas of the total field of view. Pathologists randomly selected a marked region in each section that was no smaller than the total area of 10 high-power fields in which necrotic, vascular, collagenous, and mitotic areas were labeled. We constructed an automatic identification algorithm for cytological atypia and necrosis by using ResNet and constructed an automatic detection algorithm for mitosis by using YOLOv5. A logical evaluation algorithm was then designed to obtain an automatic UMT diagnostic aid that can "study and synthesize" a pathologist's experience. The precision, recall, and F1 index reached more than 0.920. The detection network could accurately detect the mitoses (0.913 precision, 0.893 recall). For the prediction ability, the AI system had a precision of 0.90. An AI-assisted system for diagnosing UMTs in routine practice scenarios is feasible and can improve the accuracy and efficiency of diagnosis.

A Machine-Learning-Blockchain-Based Authentication Using Smart Contracts for an IoHT System

Nowadays, finding genetic components and determining the likelihood that treatment would be helpful for patients are the key issues in the medical field. Medical data storage in a centralized system is complex. Data storage, on the other hand, has recently been distributed electronically in a cloud-based system, allowing access to the data at any time through a cloud server or blockchain-based ledger system. The blockchain is essential to managing safe and decentralized transactions in cryptography systems such as bitcoin and Ethereum. The blockchain stores information in different blocks, each of which has a set capacity. Data processing and storage are more effective and better for data management when blockchain and machine learning are integrated. Therefore, we have proposed a machine-learning-blockchain-based smart-contract system that improves security, reduces consumption, and can be trusted for real-time medical applications. The accuracy and computation performance of the IoHT system are safely improved by our system.

One Step Is Not Enough: A Multi-Step Procedure for Building the Training Set of a Query by String Keyword Spotting System to Assist the Transcription of Historical Document

Digital libraries offer access to a large number of handwritten historical documents. These documents are available as raw images and therefore their content is not searchable. A fully manual transcription is time-consuming and expensive while a fully automatic transcription is cheaper but not comparable in terms of accuracy. The performance of automatic transcription systems is strictly related to the composition of the training set. We propose a multi-step procedure that exploits a Keyword Spotting system and human validation for building up a training set in a time shorter than the one required by a fully manual procedure. The multi-step procedure was tested on a data set made up of 50 pages extracted from the Bentham collection. The palaeographer that transcribed the data set with the multi-step procedure instead of the fully manual procedure had a time gain of 52.54%. Moreover, a small size training set that allowed the keyword spotting system to show a precision value greater than the recall value was built with the multi-step procedure in a time equal to 35.25% of the time required for annotating the whole data set.

An Integrated Three-Long Non-coding RNA Signature Predicts Prognosis in Colorectal Cancer Patients

Colorectal cancer (CRC) is one of the most common cancers worldwide, whose morbidity and mortality gradually increased. Here, we aimed to identify and access prognostic long non-coding RNAs (lncRNAs) associated with overall survival (OS) in CRC. Firstly, RNA expression profiles were obtained from The Cancer Genome Atlas (TCGA) database, and 439 CRC patients were enrolled as a training set. Univariate Cox analysis and the least absolute shrinkage and selection operator analysis (LASSO) were performed to identify the prognostic lncRNAs. Multivariable Cox regression analysis was used to establish a prognostic risk formula including three lncRNAs (AP003555.2, AP006284.1, and LINC01602). The low-risk group had a better OS than the high-risk group (P < 0.0001), and the areas under the receiver operating characteristic curve (AUCs) of 3- and 5-year OS were 0.712 and 0.674, respectively. Then, we evaluated the signature in a clinical validation set which were collected from the Affiliated Hospital of Jiangnan University. Compared with the low-risk group, patients' OS were found to be significantly worse in the high-risk group (P = 0.0057). The AUCs of 3- and 5-year OS were 0.701 and 0.694, respectively. Finally, we constructed an lncRNA–microRNA (miRNA)–messenger RNA (mRNA) competing endogenous RNA (ceRNA) network to explore the potential function of three differentially expressed lncRNAs (DElncRNAs). The Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway analysis indicated that these DElncRNAs were involved with several cancer-related pathways. In summary, our data provide evidence that the three-lncRNA signature could serve as an independent biomarker to predict prognosis in CRC. This study will also suggest that these three lncRNAs potentially participate in the progression of CRC.

Improving (Q)SAR predictions by examining bias in the selection of compounds for experimental testing

Existing data on structures and biological activities are limited and distributed unevenly across distinct molecular targets and chemical compounds. The question arises if these data represent an unbiased sample of the general population of chemical-biological interactions. To answer this question, we analyzed ChEMBL data for 87,583 molecules tested against 919 protein targets using supervised and unsupervised approaches. Hierarchical clustering of the Murcko frameworks generated using Chemistry Development Toolkit showed that the available data form a big diffuse cloud without apparent structure. In contrast hereto, PASS-based classifiers allowed prediction whether the compound had been tested against the particular molecular target, despite whether it was active or not. Thus, one may conclude that the selection of chemical compounds for testing against specific targets is biased, probably due to the influence of prior knowledge. We assessed the possibility to improve (Q)SAR predictions using this fact: PASS prediction of the interaction with the particular target for compounds predicted as tested against the target has significantly higher accuracy than for those predicted as untested (average ROC AUC are about 0.87 and 0.75, respectively). Thus, considering the existing bias in the data of the training set may increase the performance of virtual screening.

Comparative Genomics Approaches Accurately Predict Deleterious Variants in Plants

Recent advances in genome resequencing have led to increased interest in prediction of the functional consequences of genetic variants. Variants at phylogenetically conserved sites are of particular interest, because they are more likely than variants at phylogenetically variable sites to have deleterious effects on fitness and contribute to phenotypic variation. Numerous comparative genomic approaches have been developed to predict deleterious variants, but the approaches are nearly always assessed based on their ability to identify known disease-causing mutations in humans. Determining the accuracy of deleterious variant predictions in nonhuman species is important to understanding evolution, domestication, and potentially to improving crop quality and yield. To examine our ability to predict deleterious variants in plants we generated a curated database of 2,910 Arabidopsis thaliana mutants with known phenotypes. We evaluated seven approaches and found that while all performed well, their relative ranking differed from prior benchmarks in humans. We conclude that deleterious mutations can be reliably predicted in A. thaliana and likely other plant species, but that the relative performance of various approaches does not necessarily translate from one species to another.

Non-Uniform Sample Assignment in Training Set Improving Recognition of Hand Gestures Dominated with Similar Muscle Activities

So far, little is known how the sample assignment of surface electromyogram (sEMG) features in training set influences the recognition efficiency of hand gesture, and the aim of this study is to explore the impact of different sample arrangements in training set on the classification of hand gestures dominated with similar muscle activation patterns. Seven right-handed healthy subjects (24.2 ± 1.2 years) were recruited to perform similar grasping tasks (fist, spherical, and cylindrical grasping) and similar pinch tasks (finger, key, and tape pinch). Each task was sustained for 4 s and followed by a 5-s rest interval to avoid fatigue, and the procedure was repeated 60 times for every task. sEMG were recorded from six forearm hand muscles during grasping or pinch tasks, and 4-s sEMG from each channel was segmented for empirical mode decomposition analysis trial by trial. The muscle activity was quantified with zero crossing (ZC) and Wilson amplitude (WAMP) of the first four resulting intrinsic mode function. Thereafter, a sEMG feature vector was constructed with the ZC and WAMP of each channel sEMG, and a classifier combined with support vector machine and genetic algorithm was used for hand gesture recognition. The sample number for each hand gesture was designed to be rearranged according to different sample proportion in training set, and corresponding recognition rate was calculated to evaluate the effect of sample assignment change on gesture classification. Either for similar grasping or pinch tasks, the sample assignment change in training set affected the overall recognition rate of candidate hand gesture. Compare to conventional results with uniformly assigned training samples, the recognition rate of similar pinch gestures was significantly improved when the sample of finger-, key-, and tape-pinch gesture were assigned as 60, 20, and 20%, respectively. Similarly, the recognition rate of similar grasping gestures also rose when the sample proportion of fist, spherical, and cylindrical grasping was 40, 30, and 30%, respectively. Our results suggested that the recognition rate of hand gestures can be regulated by change sample arrangement in training set, which can be potentially used to improve fine-gesture recognition for myoelectric robotic hand exoskeleton control.

Improvement of Predictive Ability by Uniform Coverage of the Target Genetic Space

Genome-enabled prediction provides breeders with the means to increase the number of genotypes that can be evaluated for selection. One of the major challenges in genome-enabled prediction is how to construct a training set of genotypes from a calibration set that represents the target population of genotypes, where the calibration set is composed of a training and validation set. A random sampling protocol of genotypes from the calibration set will lead to low quality coverage of the total genetic space by the training set when the calibration set contains population structure. As a consequence, predictive ability will be affected negatively, because some parts of the genotypic diversity in the target population will be under-represented in the training set, whereas other parts will be over-represented. Therefore, we propose a training set construction method that uniformly samples the genetic space spanned by the target population of genotypes, thereby increasing predictive ability. To evaluate our method, we constructed training sets alongside with the identification of corresponding genomic prediction models for four genotype panels that differed in the amount of population structure they contained (maize Flint, maize Dent, wheat, and rice). Training sets were constructed using uniform sampling, stratified-uniform sampling, stratified sampling and random sampling. We compared these methods with a method that maximizes the generalized coefficient of determination (CD). Several training set sizes were considered. We investigated four genomic prediction models: multi-locus QTL models, GBLUP models, combinations of QTL and GBLUPs, and Reproducing Kernel Hilbert Space (RKHS) models. For the maize and wheat panels, construction of the training set under uniform sampling led to a larger predictive ability than under stratified and random sampling. The results of our methods were similar to those of the CD method. For the rice panel, all training set construction methods led to similar predictive ability, a reflection of the very strong population structure in this panel.

Improvement of Predictive Ability by Uniform Coverage of the Target Genetic Space

Genome-enabled prediction provides breeders with the means to increase the number of genotypes that can be evaluated for selection. One of the major challenges in genome-enabled prediction is how to construct a training set of genotypes from a calibration set that represents the target population of genotypes, where the calibration set is composed of a training and validation set. A random sampling protocol of genotypes from the calibration set will lead to low quality coverage of the total genetic space by the training set when the calibration set contains population structure. As a consequence, predictive ability will be affected negatively, because some parts of the genotypic diversity in the target population will be under-represented in the training set, whereas other parts will be over-represented. Therefore, we propose a training set construction method that uniformly samples the genetic space spanned by the target population of genotypes, thereby increasing predictive ability. To evaluate our method, we constructed training sets alongside with the identification of corresponding genomic prediction models for four genotype panels that differed in the amount of population structure they contained (maize Flint, maize Dent, wheat, and rice). Training sets were constructed using uniform sampling, stratified-uniform sampling, stratified sampling and random sampling. We compared these methods with a method that maximizes the generalized coefficient of determination (CD). Several training set sizes were considered. We investigated four genomic prediction models: multi-locus QTL models, GBLUP models, combinations of QTL and GBLUPs, and Reproducing Kernel Hilbert Space (RKHS) models. For the maize and wheat panels, construction of the training set under uniform sampling led to a larger predictive ability than under stratified and random sampling. The results of our methods were similar to those of the CD method. For the rice panel, all training set construction methods led to similar predictive ability, a reflection of the very strong population structure in this panel.

Genomic Prediction in Pea: Effect of Marker Density and Training Population Size and Composition on Prediction Accuracy

Pea is an important food and feed crop and a valuable component of low-input farming systems. Improving resistance to biotic and abiotic stresses is a major breeding target to enhance yield potential and regularity. Genomic selection (GS) has lately emerged as a promising technique to increase the accuracy and gain of marker-based selection. It uses genome-wide molecular marker data to predict the breeding values of candidate lines to selection. A collection of 339 genetic resource accessions (CRB339) was subjected to high-density genotyping using the GenoPea 13.2K SNP Array. Genomic prediction accuracy was evaluated for thousand seed weight (TSW), the number of seeds per plant (NSeed), and the date of flowering (BegFlo). Mean cross-environment prediction accuracies reached 0.83 for TSW, 0.68 for NSeed, and 0.65 for BegFlo. For each trait, the statistical method, the marker density, and/or the training population size and composition used for prediction were varied to investigate their effects on prediction accuracy: the effect was large for the size and composition of the training population but limited for the statistical method and marker density. Maximizing the relatedness between individuals in the training and test sets, through the CDmean-based method, significantly improved prediction accuracies. A cross-population cross-validation experiment was further conducted using the CRB339 collection as a training population set and nine recombinant inbred lines populations as test set. Prediction quality was high with mean Q (2) of 0.44 for TSW and 0.59 for BegFlo. Results are discussed in the light of current efforts to develop GS strategies in pea.