Enhanced focal cortical dysplasia detection in pediatric frontal lobe epilepsy with asymmetric radiomic and morphological features.

Objective: Focal cortical dysplasia (FCD) is the most common pathological cause for pediatric epilepsy, with frontal lobe epilepsy (FLE) being the most prevalent in the pediatric population. We attempted to utilize radiomic and morphological methods on MRI and PET to detect FCD in children with FLE. Methods: Thirty-seven children with FLE and 20 controls were included in the primary cohort, and a five-fold cross-validation was performed. In addition, we validated the performance in an independent site of 12 FLE children. A two-stage experiments including frontal lobe and subregions were employed to detect the lesion area of FCD, incorporating the asymmetric feature between the left and right hemispheres. Specifically, for the radiomics approach, we used gray matter (GM), white matter (WM), GM and WM, and the gray-white matter boundary regions of interest to extract features. Then, we employed a Multi-Layer Perceptron classifier to achieve FCD lesion localization based on both radiomic and morphological methods. Results: The Multi-Layer Perceptron model based on the asymmetric feature exhibited excellent performance both in the frontal lobe and subregions. In the primary cohort and independent site, the radiomics analysis with GM and WM asymmetric features had the highest sensitivity (89.2 and 91.7%) and AUC (98.9 and 99.3%) in frontal lobe. While in the subregions, the GM asymmetric features had the highest sensitivity (85.6 and 79.7%). Furthermore, relying on the highest sensitivity of GM and WM asymmetric features in frontal lobe, when integrated with the subregions results, our approach exhibited overlaps with GM asymmetric features (55.4 and 52.4%), as well as morphological asymmetric features (54.4 and 53.8%), both in the primary cohort and at the independent site. Significance: This study demonstrates that a two-stage design based on the asymmetry of radiomic and morphological features can improve FCD detection. Specifically, incorporating regions of interest for GM, WM, GM, and WM, and the gray-white matter boundary significantly enhances the localization capabilities for lesion detection within the radiomics approach.

Interpreting SNP heritability in admixed populations.

SNP heritability (hsnp2) is defined as the proportion of phenotypic variance explained by genotyped SNPs and is believed to be a lower bound of heritability (h2), being equal to it if all causal variants are known. Despite the simple intuition behind hsnp2, its interpretation and equivalence to h2 is unclear, particularly in the presence of population structure and assortative mating. It is well known that population structure can lead to inflation in h/np2 estimates. Here we use analytical theory and simulations to demonstrate that hsnp2 estimated with genome-wide restricted maximum likelihood (GREML) can be biased in admixed populations, even in the absence of confounding and even if all causal variants are known. This is because admixture generates linkage disequilibrium (LD), which contributes to the genetic variance, and therefore to heritability. GREML implicitly assumes this component is zero, which may not be true, particularly for traits under divergent or stabilizing selection in the source populations, leading under- or over-estimates of hsnp2 relative to h2. For the same reason, GREML estimates of local ancestry heritability (hγ2) will also be biased. We describe the bias in h/np2 and h^γ2 as a function of admixture history and the genetic architecture of the trait and discuss its implications for genome-wide association and polygenic prediction.

End-to-end automatic pathology localization for Alzheimer's disease diagnosis using structural MRI.

Structural magnetic resonance imaging (sMRI) is an essential part of the clinical assessment of patients at risk of Alzheimer dementia. One key challenge in sMRI-based computer-aided dementia diagnosis is to localize local pathological regions for discriminative feature learning. Existing solutions predominantly depend on generating saliency maps for pathology localization and handle the localization task independently of the dementia diagnosis task, leading to a complex multi-stage training pipeline that is hard to optimize with weakly-supervised sMRI-level annotations. In this work, we aim to simplify the pathology localization task and construct an end-to-end automatic localization framework (AutoLoc) for Alzheimer's disease diagnosis. To this end, we first present an efficient pathology localization paradigm that directly predicts the coordinate of the most disease-related region in each sMRI slice. Then, we approximate the non-differentiable patch-cropping operation with the bilinear interpolation technique, which eliminates the barrier to gradient backpropagation and thus enables the joint optimization of localization and diagnosis tasks. Extensive experiments on commonly used ADNI and AIBL datasets demonstrate the superiority of our method. Especially, we achieve 93.38% and 81.12% accuracy on Alzheimer's disease classification and mild cognitive impairment conversion prediction tasks, respectively. Several important brain regions, such as rostral hippocampus and globus pallidus, are identified to be highly associated with Alzheimer's disease.

Improved motor imagery classification using adaptive spatial filters based on particle swarm optimization algorithm.

Background: As a typical self-paced brain-computer interface (BCI) system, the motor imagery (MI) BCI has been widely applied in fields such as robot control, stroke rehabilitation, and assistance for patients with stroke or spinal cord injury. Many studies have focused on the traditional spatial filters obtained through the common spatial pattern (CSP) method. However, the CSP method can only obtain fixed spatial filters for specific input signals. In addition, the CSP method only focuses on the variance difference of two types of electroencephalogram (EEG) signals, so the decoding ability of EEG signals is limited. Methods: To make up for these deficiencies, this study introduces a novel spatial filter-solving paradigm named adaptive spatial pattern (ASP), which aims to minimize the energy intra-class matrix and maximize the inter-class matrix of MI-EEG after spatial filtering. The filter bank adaptive and common spatial pattern (FBACSP), our proposed method for MI-EEG decoding, amalgamates ASP spatial filters with CSP features across multiple frequency bands. Through a dual-stage feature selection strategy, it employs the Particle Swarm Optimization algorithm for spatial filter optimization, surpassing traditional CSP approaches in MI classification. To streamline feature sets and enhance recognition efficiency, it first prunes CSP features in each frequency band using mutual information, followed by merging these with ASP features. Results: Comparative experiments are conducted on two public datasets (2a and 2b) from BCI competition IV, which show the outstanding average recognition accuracy of FBACSP. The classification accuracy of the proposed method has reached 74.61 and 81.19% on datasets 2a and 2b, respectively. Compared with the baseline algorithm, filter bank common spatial pattern (FBCSP), the proposed algorithm improves by 11.44 and 7.11% on two datasets, respectively (p < 0.05). Conclusion: It is demonstrated that FBACSP has a strong ability to decode MI-EEG. In addition, the analysis based on mutual information, t-SNE, and Shapley values further proves that ASP features have excellent decoding ability for MI-EEG signals and explains the improvement of classification performance by the introduction of ASP features. These findings may provide useful information to optimize EEG-based BCI systems and further improve the performance of non-invasive BCI.

Automatic Localization of Seizure Onset Zone Based on Multi-Epileptogenic Biomarkers Analysis of Single-Contact from Interictal SEEG.

Successful surgery on drug-resistant epilepsy patients (DRE) needs precise localization of the seizure onset zone (SOZ). Previous studies analyzing this issue still face limitations, such as inadequate analysis of features, low sensitivity and limited generality. Our study proposed an innovative and effective SOZ localization method based on multiple epileptogenic biomarkers (spike and HFOs), and analysis of single-contact (MEBM-SC) to address the above problems. We extracted contacts epileptic features from signal distributions and signal energy based on machine learning and end-to-end deep learning. Among them, a normalized pathological ripple rate was designed to reduce the disturbance of physiological ripple and enhance the performance of SOZ localization. Then, a feature selection algorithm based on Shapley value and hypothetical testing (ShapHT+) was used to limit interference from irrelevant features. Moreover, an attention mechanism and a focal loss algorithm were used on the classifier to learn significant features and overcome the unbalance of SOZ/nSOZ contacts. Finally, we provided an SOZ prediction and visualization on magnetic resonance imaging (MRI). Ten patients with DRE were selected to verify our method. The experiment performed cross-validation and revealed that MEBM-SC obtains higher sensitivity. Additionally, the spike has better sensitivity while HFOs have better specificity, and the combination of these biomarkers can achieve the best performance. The study confirmed that MEBM-SC can increase the sensitivity and accuracy of SOZ localization and help clinicians to perform a precise and reliable preoperative evaluation based on interictal SEEG.

SEEG-Net: An explainable and deep learning-based cross-subject pathological activity detection method for drug-resistant epilepsy.

OBJECTIVE: Precise preoperative evaluation of drug-resistant epilepsy (DRE) requires accurate analysis of invasive stereoelectroencephalography (SEEG). With the tremendous breakthrough of Artificial intelligence (AI), previous studies can help clinical experts to identify pathological activities automatically. However, they still face limitations when applied in real-world clinical DRE scenarios, such as sample imbalance, cross-subject domain shift, and poor interpretability. Our objective is to propose a model that can address the above problems and realizes high-sensitivity SEEG pathological activity detection based on two real clinical datasets. METHODS: Our proposed innovative and effective SEEG-Net introduces a multiscale convolutional neural network (MSCNN) to increase the receptive field of the model, and to learn SEEG multiple frequency domain features, local and global features. Moreover, we designed a novel focal domain generalization loss (FDG-loss) function to enhance the target sample weight and to learn domain consistency features. Furthermore, to enhance the interpretability and flexibility of SEEG-Net, we explain SEEG-Net from multiple perspectives, such as significantly different features, interpretable models, and model learning process interpretation by Grad-CAM++. RESULTS: The performance of our proposed method is verified on a public benchmark multicenter SEEG dataset and a private clinical SEEG dataset for a robust comparison. The experimental results demonstrate that the SEEG-Net model achieves the highest sensitivity and is state-of-the-art on cross-subject (for different patients) evaluation, and well deal with the known problems. Besides, we provide an SEEG processing and database construction flow, by maintaining consistency with the real-world clinical scenarios. SIGNIFICANCE: According to the results, SEEG-Net is constructed to increase the sensitivity of SEEG pathological activity detection. Simultaneously, we settled certain problems about AI assistance in clinical DRE, built a bridge between AI algorithm application and clinical practice.

N3 -Kethoxal-Based Bioorthogonal Intracellular RNA Labeling.

There is growing interest in developing intracellular RNA tools. Herein, we describe a strategy for N3 -kethoxal (N3 K)-based bioorthogonal intracellular RNA functionalization. With N3 K labeling followed by an in vivo click reaction with DBCO derivatives, RNA can be modified with fluorescent or phenol groups. This strategy provides a new way of labeling RNA inside cells.

Pt(IV) Prodrugs Designed to Embed in Nanotubes of a Polysaccharide for Drug Delivery.

Cisplatin exhibits a sufficient killing effect on cancer cells; however, it damages normal cells simultaneously. Herein, we developed a prodrug delivery system based on branched ß-(1→3)-d-glucan. This natural biomacromolecule-based polysaccharide nanotube was modified with cisplatin embedded in the hollow cavity (BFCP), showing high anticancer activity and low toxicity in vitro. It is a broad-prospect system, which is based on biocompatible nanomaterials loaded with Pt(IV) prodrugs for cancer cell absorption with subsequent release in tumors by utilizing the intracellular reducibility. BFCP chains adopted a nanotube conformation in water, observed by transmission electron microscopy. In comparison to cisplatin, the Pt(IV) prodrugs not only displayed better antitumor properties but also had significant tumor targeting. A potent natural complex conjugated with redox-responsive platinum prodrugs is a significantly efficient tumor drug demonstrated in vitro and in vivo.

4-Thiouridine-Enhanced Peroxidase-Generated Biotinylation of RNA.

Peroxidase-generated proximity labeling is in widespread use to study subcellular proteomes and the protein interaction networks in living cells, but the development of subcellular RNA labeling is limited. APEX-seq has emerged as a new method to study subcellular RNA in living cells, but the labeling of RNA still has room to improve. In this work, we describe 4-thiouridine (s4 U)-enhanced peroxidase-generated biotinylation of RNA with high efficiency. The incorporation of s4 U could introduce additional sites for RNA labeling, enhanced biotinylation was observed on monomer, model oligo RNA and total RNA. Through the s4 U metabolic approach, the in vivo RNA biotinylation efficiency by peroxidase catalysis was also dramatically increased, which will benefit RNA isolation and study for the spatial transcriptome.

Learning the properties of adaptive regions with functional data analysis.

Identifying regions of positive selection in genomic data remains a challenge in population genetics. Most current approaches rely on comparing values of summary statistics calculated in windows. We present an approach termed SURFDAWave, which translates measures of genetic diversity calculated in genomic windows to functional data. By transforming our discrete data points to be outputs of continuous functions defined over genomic space, we are able to learn the features of these functions that signify selection. This enables us to confidently identify complex modes of natural selection, including adaptive introgression. We are also able to predict important selection parameters that are responsible for shaping the inferred selection events. By applying our model to human population-genomic data, we recapitulate previously identified regions of selective sweeps, such as OCA2 in Europeans, and predict that its beneficial mutation reached a frequency of 0.02 before it swept 1,802 generations ago, a time when humans were relatively new to Europe. In addition, we identify BNC2 in Europeans as a target of adaptive introgression, and predict that it harbors a beneficial mutation that arose in an archaic human population that split from modern humans within the hypothesized modern human-Neanderthal divergence range.

Selective Chemical Labeling and Sequencing of 5-Carboxylcytosine in DNA at Single-Base Resolution.

5-Carboxylcytosine (5caC) plays a vital role in the dynamics of DNA demethylation, and sequencing of its sites will help us dig out more biological functions of 5caC. Herein, we present a novel chemical method to efficiently label 5caC distinguished from other bases in DNA. Combined with bisulfite sequencing, 5caC sites can be located at single-base resolution, and the efficiency of 5caC labeling is 92% based on the Sanger sequencing data. Furthermore, dot blot assays have confirmed that 5caC-containing DNA isolated from HeLa cells was successfully labeled using our method. We expect that our strategy can be further applied to selectively tagging other carboxyl-modified bases and mapping their sites in RNA.

A High-Speed Low-Cost VLSI System Capable of On-Chip Online Learning for Dynamic Vision Sensor Data Classification.

This paper proposes a high-speed low-cost VLSI system capable of on-chip online learning for classifying address-event representation (AER) streams from dynamic vision sensor (DVS) retina chips. The proposed system executes a lightweight statistic algorithm based on simple binary features extracted from AER streams and a Random Ferns classifier to classify these features. The proposed system's characteristics of multi-level pipelines and parallel processing circuits achieves a high throughput up to 1 spike event per clock cycle for AER data processing. Thanks to the nature of the lightweight algorithm, our hardware system is realized in a low-cost memory-centric paradigm. In addition, the system is capable of on-chip online learning to flexibly adapt to different in-situ application scenarios. The extra overheads for on-chip learning in terms of time and resource consumption are quite low, as the training procedure of the Random Ferns is quite simple, requiring few auxiliary learning circuits. An FPGA prototype of the proposed VLSI system was implemented with 9.5~96.7% memory consumption and <11% computational and logic resources on a Xilinx Zynq-7045 chip platform. It was running at a clock frequency of 100 MHz and achieved a peak processing throughput up to 100 Meps (Mega events per second), with an estimated power consumption of 690 mW leading to a high energy efficiency of 145 Meps/W or 145 event/µJ. We tested the prototype system on MNIST-DVS, Poker-DVS, and Posture-DVS datasets, and obtained classification accuracies of 77.9%, 99.4% and 99.3%, respectively. Compared to prior works, our VLSI system achieves higher processing speeds, higher computing efficiency, comparable accuracy, and lower resource costs.

Cell Lysate Microarray for Mapping the Network of Genetic Regulators for Histone Marks.

Proteins, as the major executer for cell progresses and functions, its abundance and the level of post-translational modifications, are tightly monitored by regulators. Genetic perturbation could help us to understand the relationships between genes and protein functions. Herein, to explore the impact of the genome-wide interruption on certain protein, we developed a cell lysate microarray on kilo-conditions (CLICK) with 4837 knockout (YKO) and 322 temperature-sensitive (ts) mutant strains of yeast (Saccharomyces cerevisiae). Taking histone marks as examples, a general workflow was established for the global identification of upstream regulators. Through a single CLICK array test, we obtained a series of regulators for H3K4me3, which covers most of the known regulators in S. cerevisiae We also noted that several group of proteins are involved in negatively regulation of H3K4me3. Further, we discovered that Cab4p and Cab5p, two key enzymes of CoA biosynthesis, play central roles in histone acylation. Because of its general applicability, CLICK array could be easily adopted to rapid and global identification of upstream protein/enzyme(s) that regulate/modify the level of a protein or the posttranslational modification of a non-histone protein.

Fluorogenic labeling and single-base resolution analysis of 5-formylcytosine in DNA.

5-Formylcytosine (5fC), which plays an important role in epigenetic functions, has received widespread attention in many related fields. Here, we demonstrate a new design for both the fluorogenic switch-on detection and single-base resolution analysis of 5fC through selectively reacting a reagent with 5fC to yield an intramolecular cyclization nucleobase. The generated product, bearing a similar benzothiazole-iminocoumarin scaffold, is highly fluorescent and enables us to qualitatively and quantitatively detect 5fC moieties in γ-irradiated calf thymus DNA. Additionally, losing the exocyclic 4-amino group in 5fC causes the incorporation of dATP through base pairing with the generated nucleobase during polymerase extension, which helped us to analyze the 5fC sites in both single- and double-stranded oligonucleotides. Our Sanger and Illumina sequencing results show great potential in single-base resolution analysis of 5fC. It is hopeful that a similar design may be used for more detection targets.

Right-handed and left-handed G-quadruplexes have the same DNA sequence: distinct conformations induced by an organic small molecule and potassium.

Herein, we report two distinct G-quadruplex conformations of the same G-rich oligonucleotide, regulated by a small molecule. This is the first report in which both right- and left-handed G-quadruplex conformations have been obtained from the same sequence. We discriminated these two distinct conformations and investigated their kinetics and thermodynamics.

Label-free detection of pH based on the i-motif using an aggregation-caused quenching strategy.

A label-free and biocompatible pH sensor system based on the aggregation-caused quenching (ACQ) probe has been reported herein. The DNA i-motif, a kind of pH-triggered structure, affects the aggregation of PTCDI derivatives by structural switch that would provide significant fluorescence signals responding to the different pH values. Our method not only shows sensitive and reversible response to pH changes, but also could expand the detection range by allosteric control of the DNA i-motif.

Qualitative and quantitative detection of methylation at CpG sites using the fluorescein-dGTP incorporated asymmetric PCR assay strategy.

The methylation status of each CpG site can be monitored by Fl-dGTP incorporated asymmetric PCR assay. The ability of quantitative detection makes it a good choice for detecting partial methylation at CpG sites compared with others. And the monitoring is not limited to sites within PCR primers or restriction enzyme-recognition sites.