Original Sequence Research Articles

Face forgery video detection based on expression key sequences

In order to minimize additional computational costs in detecting forged videos, and enhance detection accuracy, this paper employs dynamic facial expression sequences as key sequences, replacing original video sequences as inputs for the detection model. A spatio-temporal dual-branch detection network is designed based on the visual Transformer architecture. Specifically, this process involves three steps. Firstly, dynamic facial expression sequences are localized as key sequences using optical flow difference algorithms. Subsequently, the spatial branch network employs the focal self-attention mechanism to focus on dynamic features of expression-relevant regions and uses Factorization Machines to facilitate feature interaction among multiple key sequences. Meanwhile, the temporal branch network concentrates on learning the temporal inconsistency of optical flow differences between adjacent frames. Finally, a binary classification linear SVM combines the Softmax values from the two branch networks to provide the ultimate detection outcome. Experimental results on the Faceforensics++ dataset demonstrate: (a) replacing whole video sequences with facial expression key sequences effectively reduces training and detection time by nearly 80% and 90%, respectively; (b) compared to state-of-the-art methods involving random sequence/frame extraction and key frame extraction based on video compression techniques, the proposed approach in this paper presents a more competitive detection accuracy.

IgRNA Prediction and Selection AI Models (igRNA-PS) for Bystander-less ABE Base Editing

CRISPR derived base editing techniques tend to edit multiple bases in the targeted region, which impedes precise reversion of disease-associated single nucleotide variations (SNVs). We designed an imperfect gRNA (igRNA) editing strategy to achieve bystander-less single-base editing. To predict the performance and provide ready-to-use igRNAs, we employed a high-throughput method to edit 5000 loci, each with approximate 19 systematically designed ABE igRNAs. Through deep learning of the relationship of editing efficiency, original gRNA sequence and igRNA sequence, AI models were constructed and tested, designated igRNA Prediction and Selection AI models (igRNA-PS). The models have three functions, First, they can identify the major editing site from the bystanders on a gRNA protospacer with a near 90% accuracy. second, a modified single-base editing efficiency (SBE), considering both single-base editing efficiency and product purity, can be predicted for any given igRNAs. Third, for an editing locus, a set of 64 igRNAs derived from a gRNA can be generated, evaluated through igRNA-PS to select for the best performer, and provided to the user. In this work, we overcome one of the most significant obstacles of base editors, and provide a convenient and efficient approach for single-base bystander-less ABE base editing.

Spatial-temporal Variations and Driving Factors of Surface Ozone over the Qinghai-Xizang Plateau from 2015 to 2021

The spatial-temporal distribution pattern of surface O3 over the Qinghai-Xizang Plateau （QXP） was analyzed based on air quality monitoring data and meteorological data from 12 cities on the QXP from 2015 to 2021. Kolmogorov-Zurbenko （KZ） filtering was employed to separate the original O3-8h series into components at different time scales. Then, multiple linear regression of meteorological variables was used to quantitatively isolate the effects of meteorology and emissions. The results revealed that the annual mass concentrations of surface O3-8h from 2015 to 2021 in 12 cities over the QXP ranged from 78.7 to 156.7 μg·m-3, and the exceedance rates of O3 mass concentrations （National Air Quality Standard of grade II） ranged from 0.7%-1.5%. The monthly O3-8h mass concentration displayed a single-peak inverted "V"-shape and a multi-peak "M"-shape. The maximum monthly concentration of O3 occurred in April to July, and valleys occurred in July, September, and December. The short-term, seasonal, and long-term components of O3-8hdecomposed by KZ filtering contributed 29.6%, 51.4%, and 9.1% to the total variance in the original O3 sequence in 12 cities, respectively. From the whole region, the meteorological conditions were unfavorable for O3 reduction on the QXP from 2015 to 2017, which made the long-term component of O3 increase by 0.2-2.1 μg·m-3. The meteorological conditions were favorable for O3-8h reduction from 2018 to 2021, which led to the long-term component of O3-8h decrease by 0.4-1.1 μg·m-3. The meteorological conditions increased the long-term component of O3-8h in Ngari, Lhasa, Naqu, Nyingchi, Qamdo, Haixi, and Xining, with an average contribution of 30.1%. The meteorological conditions decreased the long-term component of O3-8h in Shigatse and Golog, with contributions of 359.0% and 56.5%, respectively. The increase in the long-term component of O3-8h in Ngari, Shigatse, Nagqu, Haixi, and Xining could be due to the rapid decrease in the long-term component of PM2.5 （4.04 μg·（m3·a）-1）.

Multishot laser damage of multilayer dielectric mirrors in the near-infrared subpicosecond regime

The laser damage resistance of dielectric components of high-power laser facilities to laser irradiation depends significantly on the irradiation sequence. In the short pulse (fs) regime, it is known that continuous irradiation of these components leads to a reduction in the damage threshold, reflecting a laser fatigue effect. Conversely, in the long pulse (ns) regime, progressive irradiation of these components leads to an increase in the damage threshold, reflecting a laser conditioning effect. In this article, we experimentally evaluate the competition between the effects of laser fatigue and laser conditioning for multilayer dielectric components irradiated in the subpicosecond pulse regime in the infrared (∼1µm) through different test sequences. For this purpose, we implemented an original test sequence derived from an S-on-1 type protocol, which consists of irradiating the component until damage. By repeating this sequence at different set points, it was possible to estimate the progressive reduction in damage threshold with the number of laser irradiations and to compare it with that observed during the fluence ramps. Particular attention was also paid to the precise knowledge of the test beam irradiating the component, as a dependence of the beam surface on the test set point was highlighted.

A novel optimization rainfall coupling model based on stepwise decomposition technique

Traditional decomposition integration models decompose the original sequence into subsequences, which are then proportionally divided into training and testing periods for modeling. Decomposition may cause data aliasing, then the decomposed training period may contain part of the test period data. A more effective method of sample construction is sought in order to accurately validate the model prediction accuracy. Semi-stepwise decomposition (SSD), full stepwise decomposition (FSD), single model semi-stepwise decomposition (SMSSD), and single model full stepwise decomposition (SMFSD) techniques were used to create the samples. This study integrates Variational Mode Decomposition (VMD), African Vulture Optimization Algorithm (AVOA), and Least Squares Support Vector Machine (LSSVM) to construct a coupled rainfall prediction model. The influence of different VMD parameters α is examined, and the most suitable stepwise decomposition machine learning coupled model algorithm for various stations in the North China Plain is selected. The results reveal that SMFSD is relatively the most suitable tool for monthly precipitation forecasting in the North China Plain. Among the predictions for the five stations, the best overall performance is observed at Huairou Station (RMSE of 18.37 mm, NSE of 0.86, MRE of 107.2%) and Jingxian Station (RMSE of 24.74 mm, NSE of 0.86, MRE of 51.71%), while Hekou Station exhibits the poorest performance (RMSE of 25.11 mm, NSE of 0.75, MRE of 173.75%).

Part of whose world? How The Little Mermaid (2023) attempts to revise the racist tropes of the 1989 animated film musical

The Little Mermaid (1989) has been the subject of much critical discussion but there has been little attention paid to its representation of race. Utilising textual analysis and drawing upon relevant critical paradigms from Disney studies and scholarship of film musicals, this article argues that The Little Mermaid was an implicitly racist narrative. Through analysis of the musical sequences this article shows how The Little Mermaid created a dichotomy between an exclusively white land life that is coded as superior to multiethnic Mer life. While white society on land is represented as postindustrial, well ordered and crime free, the multiethnic culture under the sea is coded not only as sexually unbridled, where promiscuous fish all “get the urge and start to play” with each other’s bodies, but as a thoroughly corrupt society racked with Welfare Queen coded villainesses dealing in black magic. The article contends that the 2023 remake attempts to revise many of the racist tropes of the original song sequences but, in its depiction of a society in which racial difference is devoid of socio-political significance, The Little Mermaid (2023)—especially in its Berkeley inspired dance sequences—reduces racial difference to a mere aesthetic of colour.

HyperGen: Compact and Efficient Genome Sketching using Hyperdimensional Vectors.

Genomic distance estimation is a critical workload since exact computation for whole-genome similarity metrics such as Average Nucleotide Identity (ANI) incurs prohibitive runtime overhead. Genome sketching is a fast and memory-efficient solution to estimate ANI similarity by distilling representative k-mers from the original sequences. In this work, we present HyperGen that improves accuracy, runtime performance, and memory efficiency for large-scale ANI estimation. Unlike existing genome sketching algorithms that convert large genome files into discrete k-mer hashes, HyperGen leverages the emerging hyperdimensional computing (HDC) to encode genomes into quasi-orthogonal vectors (Hypervector, HV) in high-dimensional space. HV is compact and can preserve more information, allowing for accurate ANI estimation while reducing required sketch sizes. In particular, the HV sketch representation in HyperGen allows efficient ANI estimation using vector multiplication, which naturally benefits from highly optimized general matrix multiply (GEMM) routines. As a result, HyperGen enables the efficient sketching and ANI estimation for massive genome collections. We evaluate HyperGen 's sketching and database search performance using several genome datasets at various scales. HyperGen is able to achieve comparable or superior ANI estimation error and linearity compared to other sketch-based counterparts. The measurement results show that HyperGen is one of the fastest tools for both genome sketching and database search. Meanwhile, HyperGen produces memory-efficient sketch files while ensuring high ANI estimation accuracy. A Rust implementation of HyperGen is freely available under the MIT license as an open-source software project at https://github.com/wh-xu/Hyper-Gen. The scripts to reproduce the experimental results can be accessed at https://github.com/wh-xu/experiment-hyper-gen.

Systematization of Sharh al-Hikam by Sheykh Nawawi al-Bantani in Kitab Misbah al-Dzulam

This study examines the systematization of Al-Hikam aphorisms as presented in the Misbah Al-Dzulam, and explores Sheykh Nawawi Al-Bantani’s methodology for interpreting Al-Hikam. Utilizing a descriptive analysis method, the research focuses on the aphorisms of Al-Hikam. The sequence of Al-Hikam is a subject of two contrasting views. The first perspective suggests that despite an apparent randomness, the original sequence of Al-Hikam serves a specific purpose, with a spiritual secret underlying its arrangement. The second view argues that there is no lo­gical connection (irtibath mantiqi) between the initial and subsequent aphorisms. The systematic organization of these aphorisms facilitates to be studied. These divergent viewpoints have led to the creation of two models for studying Al-Hikam’s aphorisms: the tahlili model and the thematic model. The findings of this study reveal that the Misbah Al-Dzulam offers a systematic and categorized approach to Al-Hikam. This approach transforms the perceived randomness of Al-Hikam into a coherent and comprehensive structure, particularly when studied the­matically. The tahlili method further enhances the study by integrating language analysis with Sufistic interpretive approaches. This study sug­gests to include this book in the advanced learning curricula for santri or Ma’had Aly.

Dissimilarity measures based on the application of Hamming distance to generate controlled probabilistic tests

Objectives. The problem of constructing dissimilarity measures based on the application of the Hamming distance to generate controlled random binary test sets is solved. The main goal of this article is to develop methods for determining the Hamming distance for the achievability of finding the difference between test sets when they coincide according to estimates of other difference measures.Methods. Based on the Hamming distance used in the theory and practice of generating controlled random tests, new dissimilarity measures are proposed for two binary test n-bit patterns. The basis of the proposed dissimilarity measures is the formation of sets of Hamming distances for initial sets, represented as sequences of characters from different alphabets.Results. The indistinguishability of pairs of binary test sets Ti and Tk is shown using a dissimilarity measure based on the application of the Hamming distance. In this case, different pairs of sets may have identical Hamming distance values. To construct new measures of difference, the original binary test sequences are represented as sequences consisting of characters belonging to different alphabets. Various strategies are proposed for applying new measures of difference based on the use of one of three rules in generating controlled probability tests. It is shown that in all three cases of dissimilarity measures, only the first few of their components areinformative, as a rule, no more than two or three. Accordingly, the computational complexity for all three options is comparable and does not exceed 3n comparison operations. The experimental studies carried out confirm the effectiveness of the proposed dissimilarity measures and their low computational complexity.Conclusion. The proposed dissimilarity measures expand the possibilities of generating test sets when forming controlled random tests. It is shown that test sets that are indistinguishable when using the Hamming distance as a dissimilarity measure have different values of the proposed dissimilarity measures, which makes it possible to more accurately classify randomly generated sets that are candidate test cases

Climate Classification for Major Cities in China Using Cluster Analysis

Climate classification plays a fundamental role in understanding climatic patterns, particularly in the context of a changing climate. This study utilized hourly meteorological data from 36 major cities in China from 2011 to 2021, including 2 m temperature (T2), relative humidity (RH), and precipitation (PRE). Both original hourly sequences and daily value sequences were used as inputs, applying two non-hierarchical clustering methods (k-means and k-medoids) and four hierarchical clustering methods (ward, complete, average, and single) for clustering. The classification results were compared using two clustering evaluation indices: the silhouette coefficient and the Calinski–Harabasz index. Additionally, the clustering was compared with the Köppen–Geiger climate classification based on the maximum difference in intra-cluster variables. The results showed that the clustering method outperformed the Köppen–Geiger climate classification, with the k-medoids method achieving the best results. Our research also compared the effectiveness of climate classification using two variables (T2 and PRE) versus three variables, including the addition of hourly RH. Cluster evaluation confirmed that incorporating the original sequence of hourly T2, PRE, and RH yielded the best performance in climate classification. This suggests that considering more meteorological variables and using hourly observation data can significantly improve the accuracy and reliability of climate classification. In addition, by setting the class numbers to two, the clustering methods effectively identified climate boundaries between northern and southern China, aligning with China’s traditional geographical division along the Qinling–Huaihe River line.

Peripheral Blood miRNA Expression in Patients with Essential Hypertension in the Han Chinese Population in Hefei, China.

Primary hypertension is a significant risk factor for cardiovascular diseases. However, the pathogenesis of primary hypertension involves multiple biological processes, including the nervous system, circulatory system, endocrine system, and more. Despite extensive research, there is no clear understanding of the regulatory mechanism underlying its pathogenesis. In recent years, miRNAs have gained attention as a regulatory factor capable of modulating the expression of related molecules through gene silencing. Therefore, exploring differentially expressed miRNAs in patients with essential hypertension (EH) may offer a novel approach for future diagnosis and treatment of EH. This study included a total of twenty Han Chinese population samples from Hefei, China. The samples consisted of 10 healthy individuals and 10 patients with EH. Statistical analysis was conducted to analyze the general information of the two-sample groups. High-throughput sequencing and base identification were performed to obtain the original sequencing sequences. These sequences were then annotated using various databases including Rfam, cDNA sequences, species repetitive sequences library, and miRBase database. The number of miRNA species contained in the samples was measured. Next, TPM values were calculated to determine the expression level of each miRNA. The bioinformatics of the differentiated miRNAs were analyzed using the OECloud tool, and RPM values were calculated. Furthermore, the reliability of the expression was analyzed by calculating the area under the Roc curve using the OECloud tools. Statistical analysis revealed no significant differences between the two samples in terms of age distribution, gender composition, smoking history, and alcohol consumption history (P > 0.05). However, there was a notable presence of family genetic history and high BMI in the EH population (P < 0.05). The sequencing results identified a total of 245 miRNAs, out of which 16 miRNAs exhibited differential expression. Among the highly expressed miRNAs were let-7d-5p, miR-101-3p, miR-122-5p, miR-122b-3p, miR-192-5p, and miR-6722-3p. On the other hand, the lowly expressed miRNAs included miR-103a-3p, miR-16-5p, miR-181a-2-3p, miR-200a-3p, miR-200b-3p, miR-200c-3p, miR-221-3p, miR-30d-5p, miR-342-5p, and miR-543. This study initially identified 16 miRNAs that are aberrantly expressed and function in various processes associated with the onset and progression of essential hypertension. These miRNAs have the potential to be targeted for future diagnosis and treatment of EH. However, further samples are required to provide additional support for this study.

Differential learning model for carbon emission allowance prices prediction based on adaptive decomposition and joint feature contribution

Currently, how to effectively control carbon emissions is a global concern. Accurate carbon price prediction can help us more effectively control carbon emissions and reduce environmental pollution. Due to the complexity of carbon valence, this study proposes an improved decomposition ensemble prediction model. Firstly, a novel signal decomposition algorithm is designed to adaptively determine the number of decomposition modes for carbon price sequences, obtaining a set of intrinsic mode functions (IMFs). Secondly, a creative method for assessing the contribution of feature components is developed. It utilizes a genetic algorithm-based mutual-information method to calculate the contribution of each IMFs to the original sequence, classifying all feature components into high and low contribution components. Then, this study developed a differential learning method that partitions the contribution of feature components and applies targeted learning and integration using temporal convolutional network with different structures. Compared to traditional forecasting frameworks, this framework improves prediction performance while reducing structural complexity and computational costs. Empirical results demonstrate the superiority and robustness of the proposed model with the outcomes of this study present the performances that the proposed model outperforms the others with Guangzhou's mean absolute percentage error of 3.30313%, which are beneficial for governments and enterprises to predict adverse signals in the carbon market in a more timely manner, and to take measures in advance to maintain the stability of carbon emissions.

Informer Short-Term PV Power Prediction Based on Sparrow Search Algorithm Optimised Variational Mode Decomposition

The output power of PV systems is influenced by various factors, resulting in strong volatility and randomness, which makes it difficult to forecast. Therefore, this paper proposes an Informer prediction model based on optimised VMD for predicting short-term PV power. Firstly, the temporal coding of the Informer model is improved and, secondly, the original sequence is decomposed into multiple modal components using VMD, and then optimisation of the results of VMD in conjunction with the optimisation strategy of SSA improves the characteristics of the time series data. Finally, the refined data are fed into the Informer framework for modelling and prediction, utilising the self-attention mechanism and multiscale feature fusion of Informer to precisely forecast PV power. The power of PV prediction data from the SSA-VMD-Informer model and four other commonly used models is compared. Experimental results indicate that the SSA-VMD-Informer model performs exceptionally well in short-term PV power prediction, achieving higher accuracy than traditional methods. As an example, the results of predicting the PV power on 24 April in a region of Xinjiang are 1.3882 for RMSE, 0.8310 for MSE, 1.14 for SDE, and 0.9944 for R2.

Updating predictions in a complex repertoire of actions and its neural representation

Even though actions we observe in everyday life seem to unfold in a continuous manner, they are automatically divided into meaningful chunks, that are single actions or segments, which provide information for the formation and updating of internal predictive models. Specifically, boundaries between actions constitute a hub for predictive processing since the prediction of the current action comes to an end and calls for updating of predictions for the next action. In the current study, we investigated neural processes which characterize such boundaries using a repertoire of complex action sequences with a predefined probabilistic structure. Action sequences consisted of actions that started with the hand touching an object (T) and ended with the hand releasing the object (U). These action boundaries were determined using an automatic computer vision algorithm. Participants trained all action sequences by imitating demo videos. Subsequently, they returned for an fMRI session during which the original action sequences were presented in addition to slightly modified versions thereof. Participants completed a post-fMRI memory test to assess the retention of original action sequences. The exchange of individual actions, and thus a violation of action prediction, resulted in increased activation of the action observation network and the anterior insula. At U events, marking the end of an action, increased brain activation in supplementary motor area, striatum, and lingual gyrus was indicative of the retrieval of the previously encoded action repertoire. As expected, brain activation at U events also reflected the predefined probabilistic branching structure of the action repertoire. At T events, marking the beginning of the next action, midline and hippocampal regions were recruited, reflecting the selected prediction of the unfolding action segment. In conclusion, our findings contribute to a better understanding of the various cerebral processes characterizing prediction during the observation of complex action repertoires.

Improving biomedical Named Entity Recognition with additional external contexts

Objective:Biomedical Named Entity Recognition (bio NER) is the task of recognizing named entities in biomedical texts. This paper introduces a new model that addresses bio NER by considering additional external contexts. Different from prior methods that mainly use original input sequences for sequence labeling, the model takes into account additional contexts to enhance the representation of entities in the original sequences, since additional contexts can provide enhanced information for the concept explanation of biomedical entities. Methods:To exploit an additional context, given an original input sequence, the model first retrieves the relevant sentences from PubMed and then ranks the retrieved sentences to form the contexts. It next combines the context with the original input sequence to form a new enhanced sequence. The original and new enhanced sequences are fed into PubMedBERT for learning feature representation. To obtain more fine-grained features, the model stacks a BiLSTM layer on top of PubMedBERT. The final named entity label prediction is done by using a CRF layer. The model is jointly trained in an end-to-end manner to take advantage of the additional context for NER of the original sequence. Results:Experimental results on six biomedical datasets show that the proposed model achieves promising performance compared to strong baselines and confirms the contribution of additional contexts for bio NER. Conclusion:The promising results confirm three important points. First, the additional context from PubMed helps to improve the quality of the recognition of biomedical entities. Second, PubMed is more appropriate than the Google search engine for providing relevant information of bio NER. Finally, more relevant sentences from the context are more beneficial than irrelevant ones to provide enhanced information for the original input sequences. The model is flexible to integrate any additional context types for the NER task.

Short-term wind power prediction based on improved variational modal decomposition, least absolute shrinkage and selection operator, and BiGRU networks

Wind energy is a clean resource widely utilized as a renewable energy source. However, due to its inherent strong volatility and the multitude of influencing factors, it is challenging to accurately predict wind power. To address these issues, an IVMD-LASSO-BiGRU model, comprising Improved Variational Mode Decomposition (IVMD), Least Absolute Shrinkage and Selection Operator (LASSO), and Bidirectional Gated Recurrent Unit (BiGRU), is proposed for forecasting. Firstly, based on the sparse prior knowledge of each component constructed in the variational model by VMD, the optimal decomposition mode number K is determined at the inflexion point where the sparsity index shifts from rising to falling. The original wind power sequence is then decomposed into a series of Intrinsic Mode Functions (IMFs) using VMD with the optimal K value, thereby reducing the volatility of the original sequence. Secondly, LASSO is employed to select key features from meteorological data, historical wind power, and IMFs, thereby reducing the data dimension. Subsequently, BiGRU is utilized to fully extract the temporal features of the input data, establishing the mapping between input and output. Experimental results demonstrate that on three different datasets, the R2 values of the proposed forecasting method reach 0.9872, 0.9917, and 0.9941, respectively. Compared to the traditional BiGRU model, the Mean Absolute Error (MAE) and Root Mean Square Error (RMSE) are reduced by an average of 57.56% and 58.88%, respectively. Thus, it is evident that the proposed method enhances the accuracy of short-term wind power forecasting, providing a basis for adjusting power generation plans.

The importance of conceptual knowledge when becoming familiar with faces during naturalistic viewing

Although the ability to recognise familiar faces is a critical part of everyday life, the process by which a face becomes familiar in the real world is not fully understood. Previous research has focussed on the importance of perceptual experience. However, in natural viewing, perceptual experience with faces is accompanied by increased knowledge about the person and the context in which they are encountered. Although conceptual information is known to be crucial for the formation of new episodic memories, it requires a period of consolidation. It is unclear, however, whether a similar process occurs when we learn new faces. Using a natural viewing paradigm, we investigated how the context in which events are presented influences our understanding of those events and whether, after a period of consolidation, this has a subsequent effect on face recognition. The context was manipulated by presenting events in 1) the original sequence, or 2) a scrambled sequence. Although this manipulation was predicted to have a significant effect on conceptual understanding of events, it had no effect on overall visual experience with the faces. Our prediction was that this contextual manipulation would affect face recognition after the information has been consolidated into memory. We found that understanding of the narrative was greater for participants who viewed the movie in the original sequence compared to those that viewed the movie in a scrambled order. To determine if the context in which the movie was viewed had an effect on face recognition, we compared recognition in the original and scrambled condition. We found an overall effect of conceptual knowledge on face recognition. That is, participants who viewed the original sequence had higher face recognition compared to participants who viewed the scrambled sequence. However, our planned comparisons did not reveal a greater effect of conceptual knowledge on face recognition after consolidation. In an exploratory analysis, we found that overlap in conceptual knowledge between participants was significantly correlated with the overlap in face recognition. We also found that this relationship was greater after a period of consolidation. Together, these findings provide new insights into the role of non-visual, conceptual knowledge for face recognition during natural viewing.

GEMA: A Genome Exact Mapping Accelerator Based on Learned Indexes.

In this article, we introduce GEMA, a genome exact mapping accelerator based on learned indexes, specifically designed for FPGA implementation. GEMA utilizes a machine learning (ML) algorithm to precisely locate the exact position of read sequences within the original sequence. To enhance the accuracy of the trained ML model, we incorporate data augmentation and data-distribution-aware partitioning techniques. Additionally, we present an efficient yet low-overhead error recovery technique. To map long reads more efficiently, we propose a speculative prefetching approach, which reduces the required memory bandwidth. Furthermore, we suggest an FPGA-based architecture for implementing the proposed mapping accelerator, optimizing the accesses to off-chip memory. Our studies demonstrate that GEMA achieves up to 1.36 × higher speed for short reads compared to the corresponding results reported in recently published exact mapping accelerators. Moreover, GEMA achieves up to ∼22 × faster mapping of long reads compared to the available results for the longest mapped reads using these accelerators.

Outcomes of advanced/metastatic breast cancer (aMBC) treated with BRIA-IMT, an allogeneic whole cell immunotherapy.

1022 Background: The Bria-IMT regimen is a combination immunotherapy using an allogeneic whole cell cancer vaccine combined with checkpoint inhibitors (CPIs). Intradermally administered irradiated SV-BR-1-GM breast cancer cells secrete GM-CSF and present tumor associated antigens (TAAs) on HLA-I and –II molecules to directly stimulate anti-tumor immunity. Anti-PD1 CPI further stimulates T-cells and synergizes with SV-BR-1-GM. Here we report the results of the phase 1/2 trial (NCT03328026) of Bria-IMT in metastatic/advanced breast cancer evaluating sequencing of SV-BR-1-GM inoculation and CPI. Methods: Analysis of the phase 1 with expansion phase 2 cohort randomized by sequence using SV-BR-1-GM, checkpoint inhibitor (pembrolizumab or retifanlimab), low dose cyclophosphamide (Day –2) and post-dose local pegylated interferon α, with cycles every 3 weeks. In the 1:1 randomized cohort, CPI is either dosed at C1 prior to SV-BR-1-GM (original sequence) or delayed to C2 post-SV-BR-1-GM (alternative sequence). Cancer-associated macrophage-like cells (CAMLs) and circulating tumor cells (CTCs) were monitored as biomarkers. Results: A total of 54 patients were dosed: 11 with pembrolizumab, 44 with retifanlimab (1 patient received pembrolizumab and later retifanlimab). Median age=61 (38-81); Median prior regimen=6 (2-13); 72% ER+/PR+/HER2-; 6% HER2+ and 22% triple negative. Bria-IMT regimen was well tolerated with only 9% drop-out rate due to AE. AEs related to IPs were seen in 74% of patients; the majority (91%) being grade 1-2, and few (1.7%) grade 4 cases including pulmonary embolism, dehydration and increased lipase. Among 30 patients with post-dose CAML/CTC data and evaluable outcome, CAML count &lt;5 associates with disease control (p=0.06, Chi square test). Patients who developed DTH to SV-BR-1-GM had significantly better PFS and higher OS. Patients treated with phase III formulation had an increase in PFS. Quality of life improvement correlates with disease outcome and survival. Among the patients treated with the phase III formulation of SV-BR-1-GM (n=23 with evaluable outcomes), objective response rate (ORR) is 13% and disease control rate (DCR) is 61%, with median PFS and OS are 4.1 and 13.3 months, respectively. In the randomized portion, the original sequence cohort had higher DCR (43% vs 36%) and OS (P=0.08, HR 0.30, 95%CI 0.08-1.17) compared to the alternative sequence cohort. Conclusions: BRIA-IMT has shown a favorable safety profile while providing benefits to heavily treated aMBC patients. Superior outcomes and survival were seen in patients treated with the phase III formulation and regimen now being used in the ongoing Ph3 trial, confirming the improvement in efficacy of the novel regimen. The results from this randomized phase 2 study informed the study design of the ongoing Ph3 trial comparing BRIA-IMT to standard of care physician choice treatments (NCT06072612). Clinical trial information: NCT03328026 .

Automatic Recognition of Auditory Brainstem Response Waveforms Using a Deep Learning-Based Framework.

Recognition of auditory brainstem response (ABR) waveforms may be challenging, particularly for older individuals or those with hearing loss. This study aimed to investigate deep learning frameworks to improve the automatic recognition of ABR waveforms in participants with varying ages and hearing levels. The research used a descriptive study design to collect and analyze pure tone audiometry and ABR data from 100 participants. The research was conducted at a tertiary academic medical center, specifically at the Clinical Audiology Center of Tsinghua Chang Gung Hospital (Beijing, China). Data from 100 participants were collected and categorized into four groups based on age and hearing level. Features from both time-domain and frequency-domain ABR signals were extracted and combined with demographic factors, such as age, sex, pure-tone thresholds, stimulus intensity, and original signal sequences to generate feature vectors. An enhanced Wide&Deep model was utilized, incorporating the Light-multi-layer perceptron (MLP) model to train the recognition of ABR waveforms. The recognition accuracy (ACC) of each model was calculated for the overall data set and each group. The ACC rates of the Light-MLP model were 97.8%, 97.2%, 93.8%, and 92.0% for Groups 1 to 4, respectively, with a weighted average ACC rate of 95.4%. For the Wide&Deep model, the ACC rates were 93.4%, 90.8%, 92.0%, and 88.3% for Groups 1 to 4, respectively, with a weighted average ACC rate of 91.0%. Both the Light-MLP model and the Wide&Deep model demonstrated excellent ACC in automatic recognition of ABR waveforms across participants with diverse ages and hearing levels. While the Wide&Deep model's performance was slightly poorer than that of the Light-MLP model, particularly due to the limited sample size, it is anticipated that with an expanded data set, the performance of Wide&Deep model may be further improved.