HN-PPISP: a hybrid network based on MLP-Mixer for protein-protein interaction site prediction.

MOTIVATION: Biological experimental approaches to protein-protein interaction (PPI) site prediction are critical for understanding the mechanisms of biochemical processes but are time-consuming and laborious. With the development of Deep Learning (DL) techniques, the most popular Convolutional Neural Networks (CNN)-based methods have been proposed to address these problems. Although significant progress has been made, these methods still have limitations in encoding the characteristics of each amino acid in protein sequences. Current methods cannot efficiently explore the nature of Position Specific Scoring Matrix (PSSM), secondary structure and raw protein sequences by processing them all together. For PPI site prediction, how to effectively model the PPI context with attention to prediction remains an open problem. In addition, the long-distance dependencies of PPI features are important, which is very challenging for many CNN-based methods because the innate ability of CNN is difficult to outperform auto-regressive models like Transformers. RESULTS: To effectively mine the properties of PPI features, a novel hybrid neural network named HN-PPISP is proposed, which integrates a Multi-layer Perceptron Mixer (MLP-Mixer) module for local feature extraction and a two-stage multi-branch module for global feature capture. The model merits Transformer, TextCNN and Bi-LSTM as a powerful alternative for PPI site prediction. On the one hand, this is the first application of an advanced Transformer (i.e. MLP-Mixer) with a hybrid network for sequence-based PPI prediction. On the other hand, unlike existing methods that treat global features altogether, the proposed two-stage multi-branch hybrid module firstly assigns different attention scores to the input features and then encodes the feature through different branch modules. In the first stage, different improved attention modules are hybridized to extract features from the raw protein sequences, secondary structure and PSSM, respectively. In the second stage, a multi-branch network is designed to aggregate information from both branches in parallel. The two branches encode the features and extract dependencies through several operations such as TextCNN, Bi-LSTM and different activation functions. Experimental results on real-world public datasets show that our model consistently achieves state-of-the-art performance over seven remarkable baselines. AVAILABILITY: The source code of HN-PPISP model is available at https://github.com/ylxu05/HN-PPISP.

The METS-IR is independently related to bone mineral density, FRAX score, and bone fracture among U.S. non-diabetic adults: a cross-sectional study based on NHANES.

AIM: The purpose of this study was to investigate the association between the metabolic score for insulin resistance (METS-IR) and bone mineral density (BMD) in American non-diabetic adults. METHODS: We conducted a cross-sectional study with 1114 non-diabetic adults from the National Health and Nutrition Examination Survey cycle (2013-2014). The associations between METS-IR and BMD of total femur and spine were assessed by the multiple linear regression and verified the non-linear relationship with a smooth curve fit and threshold effect model. Furthermore, we evaluated the relationship between METS-IR, FRAX score, and history of bone fractures. RESULTS: We found that BMD of the total femur and spine increased by 0.005 g/cm3 and 0.005 g/cm3, respectively, for a one-unit increase of METS-IR in all participants. This positive association was more pronounced among higher METS-IR participants, and there was a non-linear relationship, which was more significant when the MTTS-IRfemur was < 41.62 or the METS-IRspine was < 41.39 (ßfemur = 0.008, ßspine = 0.011, all P < 0.05). We also found that METS-IR was positively correlated with both FRAX scores in all female participants. However, METS-IR was positively correlated only with the 10-year hip fracture risk score in male participants with fractures. No significant association between METS-IR and a history of bone fractures. CONCLUSIONS: In American non-diabetic adults, there is a correlation between elevated levels of METS-IR within the lower range and increased BMD as well as decreased risk of fractures, suggesting that METS-IR holds promise as a novel biomarker for guiding osteoporosis (OP) prevention. However, it is important to carefully balance the potential benefits and risks of METS-IR in OP.

Random RotBoost: An Ensemble Classification Method Based on Rotation Forest and AdaBoost in Random Subsets and Its Application to Clinical Decision Support.

In the era of bathing in big data, it is common to see enormous amounts of data generated daily. As for the medical industry, not only could we collect a large amount of data, but also see each data set with a great number of features. When the number of features is ramping up, a common dilemma is adding computational cost during inferring. To address this concern, the data rotational method by PCA in tree-based methods shows a path. This work tries to enhance this path by proposing an ensemble classification method with an AdaBoost mechanism in random, automatically generating rotation subsets termed Random RotBoost. The random rotation process has replaced the manual pre-defined number of subset features (free pre-defined process). Therefore, with the ensemble of the multiple AdaBoost-based classifier, overfitting problems can be avoided, thus reinforcing the robustness. In our experiments with real-world medical data sets, Random RotBoost reaches better classification performance when compared with existing methods. Thus, with the help from our proposed method, the quality of clinical decisions can potentially be enhanced and supported in medical tasks.

[Ginkgo leaves tablet improved the memory quotient of patients with mild cognitive impairment: a clinical observation].

OBJECTIVE: To observe the effect of Ginkgo Leaves Tablet (GLT) on memory quotient (MQ) of mild cognitive impairment (MCI) patients. METHODS: One hundred and thirteen patients were randomly assigned to the control group (55 cases) and the treatment group (58 cases). Patients in the control group received dietetic therapy and physical exercises, while those in the treatment group additionally took GLT, 19.2 mg each time, three times daily. The treatment course was 12 months for all. The MQ of all the patients was assessed by WMS-RC before treatment,at 6-month of treatment, and 12-month of treatment. RESULTS: Compared with the control group, the improvement of MQ increased in the treatment group 0.5 and 1 year after treatment (P < 0.05). The clinical efficiency of MQ obviously increased in the treatment group (48.28% and 50.00%), showing statistical difference when compared with the control group (30.91% and 27.27%, P < 0.05, P < 0.01). There was statistical difference in added scores of recognition, regeneration, understanding, and recitation test at 6-month of treatment and 12-month of treatment between the treatment group and the control group (P < 0.05, P < 0.01). CONCLUSION: GLT was effective in improving MQ of MCI patients, especially in improving recognition, regeneration, understanding, and recitation test.

Impact of SGLT2 inhibitors on lower limb complications: a mendelian randomization perspective.

Background: While Sodium-glucose cotransporter 2 (SGLT2) inhibitors are effective in managing diabetes and reducing cardiovascular risk, concerns about their association with lower limb complications, including, osteomyelitis, ulcers, and peripheral artery disease (PAD), persist. This study employs Mendelian Randomization (MR) to assess the causal relationship between SGLT2 inhibitors and these lower limb safety outcomes. Methods: A two-sample drug-target MR approach was used, complemented by a one-sample MR and genetic association analysis. Six SNPs were selected as instrumental variables to proxy the effect of SGLT2 inhibition. Primary outcomes were major limb safety outcomes, including osteomyelitis, lower limb ulcers, PAD, and cellulitis. The primary analytical method was the generalized inverse variance-weighted (IVW) approach, along with several sensitivity analyses. Results: The MR analysis indicated no significant causal association between genetically proxied SGLT2 inhibition and most of the studied lower limb safety outcomes. However, a significant association with PAD was observed, necessitating careful interpretation due to discrepancies between IVW and MR-Egger results. Sensitivity analyses supported these findings, showing little evidence of heterogeneity or directional pleiotropy. Conclusion: This study suggests that SGLT2 inhibitors may not be significantly associated with an increased risk of most lower limb safety outcomes, including osteomyelitis, lower limb ulcers, and cellulitis, in patients with type 2 diabetes. However, the complex relationship with PAD highlights the need for further research. These findings contribute to the understanding of the safety profile of SGLT2 inhibitors, supporting their continued use in diabetes management while underlining the importance of continuous safety monitoring.

HFSCCD: A Hybrid Neural Network for Fetal Standard Cardiac Cycle Detection in Ultrasound Videos.

In the fetal cardiac ultrasound examination, standard cardiac cycle (SCC) recognition is the essential foundation for diagnosing congenital heart disease. Previous studies have mostly focused on the detection of adult CCs, which may not be applicable to the fetus. In clinical practice, localization of SCCs needs to recognize end-systole (ES) and end-diastole (ED) frames accurately, ensuring that every frame in the cycle is a standard view. Most existing methods are not based on the detection of key anatomical structures, which may not recognize irrelevant views and background frames, results containing non-standard frames, or even it does not work in clinical practice. We propose an end-to-end hybrid neural network based on an object detector to detect SCCs from fetal ultrasound videos efficiently, which consists of 3 modules, namely Anatomical Structure Detection (ASD), Cardiac Cycle Localization (CCL), and Standard Plane Recognition (SPR). Specifically, ASD uses an object detector to identify 9 key anatomical structures, 3 cardiac motion phases, and the corresponding confidence scores from fetal ultrasound videos. On this basis, we propose a joint probability method in the CCL to learn the cardiac motion cycle based on the 3 cardiac motion phases. In SPR, to reduce the impact of structure detection errors on the accuracy of the standard plane recognition, we use XGBoost algorithm to learn the relation knowledge of the detected anatomical structures. We evaluate our method on the test fetal ultrasound video datasets and clinical examination cases and achieve remarkable results. This study may pave the way for clinical practices.

Real-Time Automatic M-Mode Echocardiography Measurement With Panel Attention.

Motion mode (M-mode) echocardiography is essential for measuring cardiac dimension and ejection fraction. However, the current diagnosis is time-consuming and suffers from diagnosis accuracy variance. This work resorts to building an automatic scheme through well-designed and well-trained deep learning to conquer the situation. That is, we proposed RAMEM, an automatic scheme of real-time M-mode echocardiography, which contributes three aspects to address the challenges: 1) provide MEIS, the first dataset of M-mode echocardiograms, to enable consistent results and support developing an automatic scheme; For detecting objects accurately in echocardiograms, it requires big receptive field for covering long-range diastole to systole cycle. However, the limited receptive field in the typical backbone of convolutional neural networks (CNN) and the losing information risk in non-local block (NL) equipped CNN risk the accuracy requirement. Therefore, we 2) propose panel attention embedding with updated UPANets V2, a convolutional backbone network, in a real-time instance segmentation (RIS) scheme for boosting big object detection performance; 3) introduce AMEM, an efficient algorithm of automatic M-mode echocardiography measurement, for automatic diagnosis; The experimental results show that RAMEM surpasses existing RIS schemes (CNNs with NL & Transformers as the backbone) in PASCAL 2012 SBD and human performances in MEIS.

Bidirectional two-sample Mendelian randomization analysis identifies causal associations between cardiovascular diseases and frozen shoulder.

BACKGROUND: Although prior observational studies indicate an association between cardiovascular diseases (CVDs) and frozen shoulder (FS), the potential causal relationship between them remains uncertain. This study aims to explore the genetic causal relationship between CVDs and FS using Mendelian randomization (MR). METHODS: Genetic variations closely associated with FS were obtained from the FinnGen Consortium. Summary data for CVD, including atrial fibrillation (AF), coronary artery disease (CAD), heart failure (HF), myocardial infarction (MI), stroke, and ischemic stroke (IS), were sourced from several large-scale genome-wide association studies (GWAS). MR analysis was performed using inverse variance weighting (IVW), MR Egger, and weighted median methods. IVW, as the primary MR analysis method, complemented by other sensitivity analyses, was utilized to validate the robustness of the results. Further reverse MR analysis was conducted to explore the presence of reverse causal relationships. RESULTS: In the forward MR analysis, genetically determined risk of stroke and IS was positively associated with FS (OR [95% CI] = 1.58 (1.23-2.03), P < 0.01; OR [95% CI] = 1.46 (1.16-1.85), P < 0.01, respectively). There was no strong evidence of an effect of genetically predicted other CVDs on FS risk. Sensitivity analyses confirmed the robustness of the results. In the reverse MR analysis, no causal relationships were observed between FS and various CVDs. CONCLUSION: The study suggests that stroke increases the risk of developing FS. However, further basic and clinical research is needed to substantiate our findings.

MLMSeg: A multi-view learning model for ultrasound thyroid nodule segmentation.

Accurate segmentation of the thyroid gland in ultrasound images is an essential initial step in distinguishing between benign and malignant nodules, thus facilitating early diagnosis. Most existing deep learning-based methods to segment thyroid nodules are learned from only a single view or two views, which limits the performance of segmenting nodules at different scales in complex ultrasound scanning environments. To address this limitation, this study proposes a multi-view learning model, abbreviated as MLMSeg. First, a deep convolutional neural network is introduced to encode the features of the local view. Second, a multi-channel transformer module is designed to capture long-range dependency correlations of global view between different nodules. Third, there are semantic relationships of structural view between features of different layers. For example, low-level features and high-level features are endowed with hidden relationships in the feature space. To this end, a cross-layer graph convolutional module is proposed to adaptively learn the correlations of high-level and low-level features by constructing graphs across different layers. In addition, in the view fusion, a channel-aware graph attention block is devised to fuse the features from the aforementioned views for accurate segmentation of thyroid nodules. To demonstrate the effectiveness of the proposed method, extensive comparative experiments were conducted with 14 baseline methods. MLMSeg achieved higher Dice coefficients (92.10% and 83.84%) and Intersection over Union scores (86.60% and 73.52%) on two different thyroid datasets. The exceptional segmentation capability of MLMSeg for thyroid nodules can greatly assist in localizing thyroid nodules and facilitating more precise measurements of their transverse and longitudinal diameters, which is of significant clinical relevance for the diagnosis of thyroid nodules.

A knowledge-interpretable multi-task learning framework for automated thyroid nodule diagnosis in ultrasound videos.

Ultrasound has become the most widely used modality for thyroid nodule diagnosis, due to its portability, real-time feedback, lack of toxicity, and low cost. Recently, the computer-aided diagnosis (CAD) of thyroid nodules has attracted significant attention. However, most existing techniques can only be applied to either static images with prominent features (manually selected from scanning videos) or rely on 'black boxes' that cannot provide interpretable results. In this study, we develop a user-friendly framework for the automated diagnosis of thyroid nodules in ultrasound videos, by simulating the typical diagnostic workflow used by radiologists. This process consists of two orderly part-to-whole tasks. The first interprets the characteristics of each image using prior knowledge, to obtain corresponding frame-wise TI-RADS scores. Associated embedded representations not only provide diagnostic information for radiologists but also reduce computational costs. The second task models temporal contextual information in an embedding vector sequence and selectively enhances important information to distinguish benign and malignant thyroid nodules, thereby improving the efficiency and generalizability of the proposed framework. Experimental results demonstrated this approach outperformed other state-of-the-art video classification methods. In addition to assisting radiologists in understanding model predictions, these CAD results could further ease diagnostic workloads and improve patient care.

FARN: Fetal Anatomy Reasoning Network for Detection With Global Context Semantic and Local Topology Relationship.

Accurate recognition of fetal anatomical structure is a pivotal task in ultrasound (US) image analysis. Sonographers naturally apply anatomical knowledge and clinical expertise to recognizing key anatomical structures in complex US images. However, mainstream object detection approaches usually treat each structure recognition separately, overlooking anatomical correlations between different structures in fetal US planes. In this work, we propose a Fetal Anatomy Reasoning Network (FARN) that incorporates two kinds of relationship forms: a global context semantic block summarized with visual similarity and a local topology relationship block depicting structural pair constraints. Specifically, by designing the Adaptive Relation Graph Reasoning (ARGR) module, anatomical structures are treated as nodes, with two kinds of relationships between nodes modeled as edges. The flexibility of the model is enhanced by constructing the adaptive relationship graph in a data-driven way, enabling adaptation to various data samples without the need for predefined additional constraints. The feature representation is further refined by aggregating the outputs of the ARGR module. Comprehensive experimental results demonstrate that FARN achieves promising performance in detecting 37 anatomical structures across key US planes in tertiary obstetric screening. FARN effectively utilizes key relationships to improve detection performance, demonstrates robustness to small-scale, similar, and indistinct structures, and avoids some detection errors that deviate from anatomical norms. Overall, our study serves as a resource for developing efficient and concise approaches to model inter-anatomy relationships.

SKGC: A General Semantic-Level Knowledge Guided Classification Framework for Fetal Congenital Heart Disease.

Congenital heart disease (CHD) is the most common congenital disability affecting healthy development and growth, even resulting in pregnancy termination or fetal death. Recently, deep learning techniques have made remarkable progress to assist in diagnosing CHD. One very popular method is directly classifying fetal ultrasound images, recognized as abnormal and normal, which tends to focus more on global features and neglects semantic knowledge of anatomical structures. The other approach is segmentation-based diagnosis, which requires a large number of pixel-level annotation masks for training. However, the detailed pixel-level segmentation annotation is costly or even unavailable. Based on the above analysis, we propose SKGC, a universal framework to identify normal or abnormal four-chamber heart (4CH) images, guided by a few annotation masks, while improving accuracy remarkably. SKGC consists of a semantic-level knowledge extraction module (SKEM), a multi-knowledge fusion module (MFM), and a classification module (CM). SKEM is responsible for obtaining high-level semantic knowledge, serving as an abstract representation of the anatomical structures that obstetricians focus on. MFM is a lightweight but efficient module that fuses semantic-level knowledge with the original specific knowledge in ultrasound images. CM classifies the fused knowledge and can be replaced by any advanced classifier. Moreover, we design a new loss function that enhances the constraint between the foreground and background predictions, improving the quality of the semantic-level knowledge. Experimental results on the collected real-world NA-4CH and the publicly FEST datasets show that SKGC achieves impressive performance with the best accuracy of 99.68% and 95.40%, respectively. Notably, the accuracy improves from 74.68% to 88.14% using only 10 labeled masks.

TKR-FSOD: Fetal Anatomical Structure Few-Shot Detection Utilizing Topological Knowledge Reasoning.

Fetal multi-anatomical structure detection in Ultrasound (US) images can clearly present the relationship and influence between anatomical structures, providing more comprehensive information about fetal organ structures and assisting sonographers in making more accurate diagnoses, widely used in structure evaluation. Recently, deep learning methods have shown superior performance in detecting various anatomical structures in ultrasound images but still have the potential for performance improvement in categories where it is difficult to obtain samples, such as rare diseases. Few-shot learning has attracted a lot of attention in medical image analysis due to its ability to solve the problem of data scarcity. However, existing few-shot learning research in medical image analysis focuses on classification and segmentation, and the research on object detection has been neglected. In this paper, we propose a novel fetal anatomical structure fewshot detection method in ultrasound images, TKR-FSOD, which learns topological knowledge through a Topological Knowledge Reasoning Module to help the model reason about and detect anatomical structures. Furthermore, we propose a Discriminate Ability Enhanced Feature Learning Module that extracts abundant discriminative features to enhance the model's discriminative ability. Experimental results demonstrate that our method outperforms the state-of-the-art baseline methods, exceeding the second best method with a maximum margin of 4.8% on 5-shot of split 1 under 4CC. The code is publicly available at: https://github.com/lixi92/TKR-FSOD.

Deep endpoints focusing network under geometric constraints for end-to-end biometric measurement in fetal ultrasound images.

Biometric measurements in fetal ultrasound images are one of the most highly demanding medical image analysis tasks that can directly contribute to diagnosing fetal diseases. However, the natural high-speckle noise and shadows in ultrasound data present big challenges for automatic biometric measurement. Almost all the existing dominant automatic methods are two-stage models, where the key anatomical structures are segmented first and then measured, thus bringing segmentation and fitting errors. What is worse, the results of the second-stage fitting are completely dependent on the good performance of first-stage segmentation, i.e., the segmentation error will lead to a larger fitting error. To this end, we propose a novel end-to-end biometric measurement network, abbreviated as E2EBM-Net, that directly fits the measurement parameters. E2EBM-Net includes a cross-level feature fusion module to extract multi-scale texture information, a hard-soft attention module to improve position sensitivity, and center-focused detectors jointly to achieve accurate localizing and regressing of the measurement endpoints, as well as a loss function with geometric cues to enhance the correlations. To our knowledge, this is the first AI-based application to address the biometric measurement of irregular anatomical structures in fetal ultrasound images with an end-to-end approach. Experiment results showed that E2EBM-Net outperformed the existing methods and achieved the state-of-the-art performance.

Effects of vitamin D deficiency on blood lipids and bone metabolism: a large cross-sectional study.

To investigate the relationship between serum high-density lipoprotein (HDL-C) and spinal bone mineral density (BMD) under different serum 25-hydroxyvitamin D (25 (OH) D) levels in adults over 40 years old and to explore its mechanism. We include participants over the age of 40 with data on HDL-C, 25 (OH) D, spinal BMD, and other variables in the National Health and Nutrition Examination Survey 2007-2010 in the analysis. A weighted multiple linear regression model was used to evaluate the association between serum HDL-C and spinal BMD in different gender, ages, and serum 25 (OH) D levels. A total of 3599 subjects aged ≥ 40 years old were included in this study. Univariate analysis of the complete correction model showed a negative correlation between serum HDL-C and spinal BMD. In the two subgroups of serum 25 (OH) D, we found that the higher the serum HDL-C in the female with serum 25 (OH) D < 75 nmol/L aged 40-59 years old, the lower the total spinal BMD, and a similar relationship was found in the lumbar spine. However, no similar relationship was found in all populations with serum 25 (OH) D ≥ 75 nmol/L and males with serum 25 (OH) D < 75 nmol/L. These results suggest that among Americans over the age of 40, the increase in serum HDL-C is related to decreased BMD of spine only in women aged 40-59 years with vitamin D insufficiency or deficiency.

The role of NSAID in mediating the effect of genetically predicted major depressive disorder on osteomyelitis: A Mendelian randomization study.

BACKGROUND: Osteomyelitis and major depressive disorder (MDD) are significant health concerns with potential interconnections. However, the underlying mechanisms linking these conditions remain unknown. This study aimed to investigate the potential mediating role of non-steroidal anti-inflammatory drug (NSAID) medication in the association between MDD and the risk of osteomyelitis. METHODS: We utilized summary data from large-scale genome-wide association studies (GWAS) to perform Mendelian randomization (MR) mediation analysis. Instrumental variables were selected based on genome-wide significance, and instrumental strength was assessed using F-statistics. Univariable and multivariable MR analyses were conducted to estimate causal effects and proportions mediated by NSAID medication. RESULTS: The univariable MR analysis revealed significant associations between MDD and osteomyelitis (odds ratio [OR] = 1.44, 95 % confidence interval [CI]: 1.18-1.874) and between MDD and NSAID medication (OR = 1.36, 95 % CI 1.24-1.49). In the multivariable MR analysis, the direct effect of MDD on osteomyelitis was OR 1.35 (95 % CI: 1.09, 1.67) after adjusting for NSAID medication. The proportion of mediation by NSAID medication was 23 % (95 % CI: 0.05 %, 38.6 %). CONCLUSION: This MR study provides evidence for a genetically predicted causal association between MDD, NSAID medication, and osteomyelitis. The findings emphasize the need for a comprehensive approach in managing individuals with comorbid depression and osteomyelitis, considering the potential risks and benefits of NSAID medication. Future research should address limitations and explore additional mediators and confounding factors to enhance understanding of this complex relationship.

TransFSM: Fetal Anatomy Segmentation and Biometric Measurement in Ultrasound Images Using a Hybrid Transformer.

Biometric parameter measurements are powerful tools for evaluating a fetus's gestational age, growth pattern, and abnormalities in a 2D ultrasound. However, it is still challenging to measure fetal biometric parameters automatically due to the indiscriminate confusing factors, limited foreground-background contrast, variety of fetal anatomy shapes at different gestational ages, and blurry anatomical boundaries in ultrasound images. The performance of a standard CNN architecture is limited for these tasks due to the restricted receptive field. We propose a novel hybrid Transformer framework, TransFSM, to address fetal multi-anatomy segmentation and biometric measurement tasks. Unlike the vanilla Transformer based on a single-scale input, TransFSM has a deformable self-attention mechanism so it can effectively process multi-scale information to segment fetal anatomy with irregular shapes and different sizes. We devised a BAD to capture more intrinsic local details using boundary-wise prior knowledge, which compensates for the defects of the Transformer in extracting local features. In addition, a Transformer auxiliary segment head is designed to improve mask prediction by learning the semantic correspondence of the same pixel categories and feature discriminability among different pixel categories. Extensive experiments were conducted on clinical cases and benchmark datasets for anatomy segmentation and biometric measurement tasks. The experiment results indicate that our method achieves state-of-the-art performance in seven evaluation metrics compared with CNN-based, Transformer-based, and hybrid approaches. By Knowledge distillation, the proposed TransFSM can create a more compact and efficient model with high deploying potential in resource-constrained scenarios. Our study serves as a unified framework for biometric estimation across multiple anatomical regions to monitor fetal growth in clinical practice.

Bidirectional two-sample mendelian randomization analysis identifies causal associations between age at menarche and sarcopenia-related traits.

BACKGROUND: Observational studies have shown that the age of menarche is associated with sarcopenia, but confounding factors make the causal relationship difficult to infer. OBJECTIVE: Therefore, we conducted a bidirectional two-sample Mendelian randomized (MR) analysis to evaluate the potential causal relationship between age at menarche and sarcopenia-related traits (hand grip strength, lean mass, walking pace). METHODS: We obtained the latest aggregate statistics from the Genome-wide association studies (GWAS) database on the age of menarche of 182,416 participants from ReproGen, the appendicular lean mass of 244,730 participants from EMBL's European Bioinformatics Institute, the left-hand grip strength of 401,026 participants, the right-hand grip strength of 461,089 participants and the usual walking pace of 459,915 participants from the UK Biobank. The inverse variance weighting (IVW) method and other MR methods were used to evaluate the bidirectional causal relationship between the age of menarche and sarcopenia. RESULTS: The forward MR results showed that the age of menarche predicted by the gene was positively correlated with left-hand grip strength (IVWß=0.041, P = 2.00 × 10-10), right-hand grip strength (IVWß=0.053, P = 1.97 × 10-18), appendicular lean mass (IVWß=0.012, P = 4.38 × 10-13) and usual walking pace (IVWß=0.033, P = 1.62 × 10-8).In the reverse MR analysis, we also found that the usual walking pace was positively correlated with the age of menarche predicted by genes (IVWß=0.532, P = 1.65 × 10-4). Still, there was no causal relationship between grip strength and appendicular lean mass and the age at menarche. CONCLUSION: Our results show that earlier menarche will increase the risk of sarcopenia. In addition, people with higher muscle function tend to have menarche later. These findings may provide a reference for prevention strategies and interventions for menarche in advance and sarcopenia.

Causal effects of tea intake on multiple types of fractures: A two-sample Mendelian randomization study.

Fracture is a global public health disease. Bone health and fracture risk have become the focus of public and scientific attention. Observational studies have reported that tea consumption is associated with fracture risk, but the results are inconsistent. The present study used 2-sample Mendelian randomization (MR) analysis. The inverse variance weighted method, employing genetic data from UK Biobank (447,485 cases) of tea intake and UK Biobank (Genome-wide association study Round 2) project (361,194 cases) of fractures, was performed to estimate the causal relationship between tea intake and multiple types of fractures. The inverse variance weighted indicated no causal effects of tea consumption on fractures of the skull and face, shoulder and upper arm, hand and wrist, femur, calf, and ankle (odds ratio = 1.000, 1.000, 1.002, 0.997, 0.998; P = .881, 0.857, 0.339, 0.054, 0.569, respectively). Consistent results were also found in MR-Egger, weighted median, and weighted mode. Our research provided evidence that tea consumption is unlikely to affect the incidence of fractures.

A Hybrid Two-Stage Teaching-Learning-Based Optimization Algorithm for Feature Selection in Bioinformatics.

The "curse of dimensionality" brings new challenges to the feature selection (FS) problem, especially in bioinformatics filed. In this paper, we propose a hybrid Two-Stage Teaching-Learning-Based Optimization (TS-TLBO) algorithm to improve the performance of bioinformatics data classification. In the selection reduction stage, potentially informative features, as well as noisy features, are selected to effectively reduce the search space. In the following comparative self-learning stage, the teacher and the worst student with self-learning evolve together based on the duality of the FS problems to enhance the exploitation capabilities. In addition, an opposition-based learning strategy is utilized to generate initial solutions to rapidly improve the quality of the solutions. We further develop a self-adaptive mutation mechanism to improve the search performance by dynamically adjusting the mutation rate according to the teacher's convergence ability. Moreover, we integrate a differential evolutionary method with TLBO to boost the exploration ability of our algorithm. We conduct comparative experiments on 31 public data sets with different data dimensions, including 7 bioinformatics datasets, and evaluate our TS-TLBO algorithm compared with 11 related methods. The experimental results show that the TS-TLBO algorithm obtains a good feature subset with better classification performance, and indicates its generality to the FS problems.