GBDTLRL2D Predicts LncRNA–Disease Associations Using MetaGraph2Vec and K-Means Based on Heterogeneous Network

In recent years, the long noncoding RNA (lncRNA) has been shown to be involved in many disease processes. The prediction of the lncRNA–disease association is helpful to clarify the mechanism of disease occurrence and bring some new methods of disease prevention and treatment. The current methods for predicting the potential lncRNA–disease association seldom consider the heterogeneous networks with complex node paths, and these methods have the problem of unbalanced positive and negative samples. To solve this problem, a method based on the Gradient Boosting Decision Tree (GBDT) and logistic regression (LR) to predict the lncRNA–disease association (GBDTLRL2D) is proposed in this paper. MetaGraph2Vec is used for feature learning, and negative sample sets are selected by using K-means clustering. The innovation of the GBDTLRL2D is that the clustering algorithm is used to select a representative negative sample set, and the use of MetaGraph2Vec can better retain the semantic and structural features in heterogeneous networks. The average area under the receiver operating characteristic curve (AUC) values of GBDTLRL2D obtained on the three datasets are 0.98, 0.98, and 0.96 in 10-fold cross-validation.

FA-YOLO: An Improved YOLO Model for Infrared Occlusion Object Detection under Confusing Background

Infrared target detection is a popular applied field in object detection as well as a challenge. This paper proposes the focus and attention mechanism-based YOLO (FA-YOLO), which is an improved method to detect the infrared occluded vehicles in the complex background of remote sensing images. Firstly, we use GAN to create infrared images from the visible datasets to make sufficient datasets for training as well as using transfer learning. Then, to mitigate the impact of the useless and complex background information, we propose the negative sample focusing mechanism to focus on the confusing negative sample training to depress the false positives and increase the detection precision. Finally, to enhance the features of the infrared small targets, we add the dilated convolutional block attention module (dilated CBAM) to the CSPdarknet53 in the YOLOv4 backbone. To verify the superiority of our model, we carefully select 318 infrared occluded vehicle images from the VIVID-infrared dataset for testing. The detection accuracy-mAP improves from 79.24% to 92.95%, and the F1 score improves from 77.92% to 88.13%, which demonstrates a significant improvement in infrared small occluded vehicle detection.

Assessment of Minimal/Measurable Residual Disease Testing in Acute Myeloid Leukaemia By Molecular Methods in an Interlaboratory Study

Background Minimal/measurable residual disease (MRD) testing is increasingly utilised and accepted as standard of care to manage a range of different haematological malignancies. It's use as a surrogate outcome in clinical trials of new therapies is being explored, where it has the potential to accelerate drug assessment and approval. The phenotypic and genetic heterogeneity of acute myeloid leukaemia (AML) has limited the use of MRD in this context; however, the European LeukaemiaNet (ELN) MRD working group have recently published consensus guidelines to standardise both flow cytometric and molecular genetic MRD testing. To assess the accuracy of testing and concordance between laboratories, crucial to patient safety, external quality assessment (EQA)/proficiency testing (PT) is required. Aims To determine the performance of molecular methods for measuring of MRD using the t(8;21)(q22:q22) RUNX1-RUNX1T1, inv(16)(p13q22) CBFB-MYH11, t(15;17)(q24.1;q21.2) PML-RARA and NPM1 Type A markers in an international interlaboratory study. Methods A total of 12 batches of lyophilised EQA material were manufactured. These consisted of three batches of samples for each marker all containing 9x10^6 cells: an MRD 'high' sample; an MRD 'low' sample; and an MRD 'negative' sample. The t(8;21)(q22:q22) RUNX1-RUNX1T1 positive samples were manufactured using the KASUMI-1 cell line, the inv(16)(p13q22) CBFB-MYH11 positive samples using the ME-1 cell line; t(15;17)(q24.1;q21.2 PML-RARA positive samples using the NB4 cell line and the NPM1 Type A (NM_002520.6:c.860_863dup) positive samples using the OCI-AML3 cell line. MRD positive samples were diluted with HL60 cells to achieve the desired MRD level. MRD negative samples were manufactured using the HL60 cell line. The samples were shipped at ambient temperature to the 29 laboratories in 12 countries. Participants were asked to test the blinded samples with their in-house assay and report % normalised ratio of the relevant marker alongside additional methodological and technical data. Results For t(8;21) RUNX1-RUNX1T1, all participants who returned results (n=23) classified the MRD 'high' and MRD 'low' samples as positive and the MRD 'negative' sample as negative. The robust mean log reduction between the MRD 'high' and MRD low sample was 2.7 (range 2.5-2.9). For inv(16) CBFB-MYH11, all participants who returned results (n=22) classified the MRD 'high' sample as positive, 21/22 (95.5%) classified the MRD 'low' sample as positive and 21/22 (95.5%) classified the MRD negative sample as negative. The robust mean log reduction between the MRD 'high' and MRD 'low' sample was 3.16 (range 2.8-4.2). For t(15;17) PML-RARA, all participants who returned results (n=22) classified the MRD 'high' sample as positive, 21/22 (95.5%) classified the MRD 'low' sample as positive and 21/22 (95.5%) classified the MRD negative sample as negative. The robust mean log reduction between the MRD 'high' and MRD 'low' sample was 2.1 (range 1.4-2.4). For NPM1, all participants who returned results (n=23) classified the MRD 'high' as positive, 21/23 (91.3%) classified the MRD 'low' sample as positive and, 17/23 (73.4%) classified the MRD negative sample as negative. The robust mean log reduction between the MRD 'high' and MRD 'low' sample was 3.8 (range 3.2-4.2). Summary/Conclusion The majority of participants in this study were able to detect and accurately quantify MRD when assessing the t(8;21)(q22:q22) RUNX1-RUNX1T1, inv(16)(p13q22) CBFB-MYH11, t(15;17)(q24.1;q21.2) PML-RARA and NPM1 markers, at levels that would be expected within a clinical trial or standard of care setting. A high proportion of participants reported false positive results in the NPM1 marker negative sample. This would have significant consequences clinically, with NPM1 marker false-positivity potentially committing patients to unneeded additional chemotherapy and/or transplant with the attendant risk of morbidity and mortality which highlights the need for ongoing EQA in this area. UK NEQAS LI will work with laboratories advocating they undertake a root cause analysis process to identify the source(s) of error contributing to false positive NPM1 marker results and support their subsequent corrective actions; sharing any educational findings with all participants. Figure 1 Figure 1. Disclosures Scott: Novartis: Research Funding; Biorad: Research Funding. Dillon: Abbvie: Consultancy, Membership on an entity's Board of Directors or advisory committees, Other: Research Support, Educational Events; Amgen: Other: Research support (paid to institution); Astellas: Consultancy, Other: Educational Events , Speakers Bureau; Menarini: Membership on an entity's Board of Directors or advisory committees; Novartis: Membership on an entity's Board of Directors or advisory committees, Other: Session chair (paid to institution), Speakers Bureau; Pfizer: Consultancy, Membership on an entity's Board of Directors or advisory committees, Other: educational events; Jazz: Other: Education events; Shattuck Labs: Membership on an entity's Board of Directors or advisory committees. Whitby: Roche: Membership on an entity's Board of Directors or advisory committees; Alexion: Honoraria, Other: Teaching.

Deep Spatial-Spectral Subspace Clustering for Hyperspectral Images Based on Contrastive Learning

Hyperspectral image (HSI) clustering is a major challenge due to the redundant spectral information in HSIs. In this paper, we propose a novel deep subspace clustering method that extracts spatial–spectral features via contrastive learning. First, we construct positive and negative sample pairs through data augmentation. Then, the data pairs are projected into feature space using a CNN model. Contrastive learning is conducted by minimizing the distances of positive pairs and maximizing those of negative pairs. Finally, based on their features, spectral clustering is employed to obtain the final result. Experimental results gained over three HSI datasets demonstrate that our proposed method is superior to other state-of-the-art methods.

Early-fusion based pulsar identification with smart under-sampling

The discovery of pulsars is of great significance in the field of physics and astronomy. As the astronomical equipment produces a large number of pulsar data, an algorithm for automatically identifying pulsars becomes urgent. We propose a deep learning framework for pulsar recognition. In response to the extreme imbalance between positive and negative examples and the hard negative sample issue presented in the High Time Resolution Universe Medlat Training Data, there are two coping strategies in our framework: the smart under-sampling and the improved loss function. We also apply the early-fusion strategy to integrate features obtained from different attributes before classification to improve the performance. To our best knowledge, this is the first study that integrates these strategies and techniques in pulsar recognition. The experiment results show that our framework outperforms previous works with respect to either the training time or F1 score. We can not only speed up the training time by 10 × compared with the state-of-the-art work, but also get a competitive result in terms of F1 score.

Validation of Commercial SARS-CoV-2 Immunoassays in a Nigerian Population

This study used positive and negative sample panels from Nigeria to test the performance of several commercially available SARS-CoV-2 serological assays. Using these prepandemic and SARS-CoV-2-positive samples, we found much lower levels of sensitivity in four commercially available assays than most assay manufacturer reports and independent evaluations.

On the Sample Autocorrelation Function’s Absolute Summability

The sample ACF is the most common basic tool in analyzing time-series data. This paper provides a theoretical proof that, under some regularity conditions, sample ACF of a given stationary time series is not absolutely summable. Furthermore, it shows that under some mild conditions, the number of positive and negative sample ACFs and their absolute summation tend to infinity as the length of time series increases. The theoretical results are supported by practical evidence from a simulation study.

COVID-19’s natural course among ambulatory monitored outpatients

Research objective was to detail COVID-19’s natural trajectory in relation to the Czech population’s viral load. Our prospective detailed daily questionnaire-based telemonitoring study evaluated COVID-19’s impact among 105 outpatients. In accordance with government quarantine requirements, outpatients were divided into a cohort with two negative tests at the end of the disease (40 patients) and a cohort with a new algorithm (65 patients) following a 14-day quarantine. Median follow-up differed significantly between the 2 groups (23 days vs. 16 days). Only 6% of patients were asymptomatic during the entire telemonitoring period. Another 13% of patients were diagnosed asymptomatic, as suspected contacts, yet later developed symptoms, while the remaining 81% were diagnosed as symptomatic on average 6 days following symptom onset. Telemonitoring enabled precise symptom status chronicling. The most frequently reported complaints were fevers, respiratory issues, and anosmia. Six patients were eventually hospitalized for complications detected early after routine telemonitoring. During the extended follow-up (median 181 days), anosmia persisted in 26% of patients. 79% of patients in the new quarantine algorithm cohort reported no symptoms on day 11 compared to just 56% of patients in the two negative test cohort upon first testing negative (median–19 days). The highest viral load occurred within 0–2 days of initial symptom onset. Both the PCR viral load and two consecutive PCR negative sample realizations indicated high interindividual variability with a surprisingly fluctuating pattern among 43% of patients. No definitive COVID-19 symptoms or set of symptoms excepting anosmia (59%) and/or ageusia (47%) were identified. No preexisting medical conditions specifically foreshadowed disease trajectory in a given patient. Without a PCR negativity requirement for quarantine cessation, patients could exhibit fewer symptoms. Our study therefore highlights the urgent need for routine ambulatory patient telemedicine monitoring, early complication detection, intensive mass education connecting disease demeanor with subsequent swift diagnostics, and, notably, the need to reevaluate and modify quarantine regulations for better control of SARS-CoV-2 proliferation.

Tailor-Made Immunochromatographic Test for the Detection of Multiple 17α-Methylated Anabolics in Dietary Supplements

In recent years, the undeclared presence of various anabolic androgenic steroids (AAS) in commercial supplements has been confirmed. This fact can be a potential threat to all athletes using these supplements, and therefore, there is of increased interest in the implementation of rapid methods for the detection of AAS. The presented study describes the development of an immunostrip test for the detection of multiple 17α-methylated AAS based on direct and indirect competitive principle using gold nanoparticles as a label. As a capture reagent on test lines conjugated stanazolol to rabbit serum albumin (RSA/ST-3) was used, the intensity of color formed in the test line of the AAS-positive sample was visually distinguishable from that of negative sample within 10 min. The optimized closed direct and indirect format of the test provided a similar visual detection limit (0.7 and 0.9 ng/mL, respectively). The most commonly orally abused AAS (17α-methyltestosterone, methandienone, methyldihydrotestosterone, oxandrolone and oxymetholone) showed a strong cross-reaction. Developed immunostrips were successfully applied to analysis of artificially contaminated dietary supplements with 17α-methylated AASs. The developed immunostrips offer potential as a useful user-friendly method for capturing suspicious dietary supplement samples with different contents of AAS at levels far below the usually used concentrations of AAS.