The repertoire of copy number alteration signatures in human cancer.

Copy number alterations (CNAs) are a predominant source of genetic alterations in human cancer and play an important role in cancer progression. However comprehensive understanding of the mutational processes and signatures of CNA is still lacking. Here we developed a mechanism-agnostic method to categorize CNA based on various fragment properties, which reflect the consequences of mutagenic processes and can be extracted from different types of data, including whole genome sequencing (WGS) and single nucleotide polymorphism (SNP) array. The 14 signatures of CNA have been extracted from 2778 pan-cancer analysis of whole genomes WGS samples, and further validated with 10 851 the cancer genome atlas SNP array dataset. Novel patterns of CNA have been revealed through this study. The activities of some CNA signatures consistently predict cancer patients' prognosis. This study provides a repertoire for understanding the signatures of CNA in cancer, with potential implications for cancer prognosis, evolution and etiology.

TLimmuno2: predicting MHC class II antigen immunogenicity through transfer learning.

Major histocompatibility complex (MHC) class II molecules play a pivotal role in antigen presentation and CD4+ T cell response. Accurate prediction of the immunogenicity of MHC class II-associated antigens is critical for vaccine design and cancer immunotherapies. However, current computational methods are limited by insufficient training data and algorithmic constraints, and the rules that govern which peptides are truly recognized by existing T cell receptors remain poorly understood. Here, we build a transfer learning-based, long short-term memory model named 'TLimmuno2' to predict whether epitope-MHC class II complex can elicit T cell response. Through leveraging binding affinity data, TLimmuno2 shows superior performance compared with existing models on independent validation datasets. TLimmuno2 can find real immunogenic neoantigen in real-world cancer immunotherapy data. The identification of significant MHC class II neoantigen-mediated immunoediting signal in the cancer genome atlas pan-cancer dataset further suggests the robustness of TLimmuno2 in identifying really immunogenic neoantigens that are undergoing negative selection during cancer evolution. Overall, TLimmuno2 is a powerful tool for the immunogenicity prediction of MHC class II presented epitopes and could promote the development of personalized immunotherapies.

Long-term saline water irrigation has the potential to balance greenhouse gas emissions and cotton yield in North China plain.

Saline water has proven to be one of the alternative sources of freshwater for agricultural irrigation in water-scarce areas. However, the changes in farmland ecology caused by saline water irrigation remain unclear. In this study, six irrigation water salinities (CK: 1.3 dS m-1, S1: 3.4 dS m-1, S2: 7.1 dS m-1, S3: 10.6 dS m-1, S4: 14.1 dS m-1, S5: 17.7 dS m-1) were set in a three-year (2019, 2021-2022) experiment to investigate their effects on soil environment and greenhouse gas emissions in cotton fields under long-term saline water irrigation. Results show that soil salinity in the same layer increased as increasing water salinity. Soil moisture of S3-S5 increased significantly by 4.99-12.94%. There was no significant difference in soil organic matter content between CK and S1. Saline water irrigation increased soil ammonium nitrogen content by 0.57-49.26%, while decreasing nitrate nitrogen content by 1.43-32.03%. Soil CO2 and N2O emissions and CH4 uptake were lower in S1-S5 than in CK at different cotton growth stages. In addition, saline water irrigation reduced the global warming potential by 6.93-53.86%. A structural equation model was developed to show that soil salinity, moisture, and ammonium nitrogen content were negatively correlated with global warming potential, while organic matter and nitrate nitrogen had positive effects on global warming potential. Considering the comprehensive perspectives of gas emissions and cotton yield, irrigation water with salinity less than 10.6 dS m-1 could effectively reduce greenhouse gas emissions from cotton fields while maintaining stable cotton yields in the experimental area and similar region.

Effect of phosphorus-loaded biochar and nitrogen-fertilization on release kinetic of toxic heavy metals and tomato growth.

In this study, we investigate the effect of nitrogen fertilizer application rates with and without phosphorus-loaded biochar (BCP) on the productivity of tomato (Solanum lycopersicum cv GS) planted on a contaminated soil based on pot and incubation experiments. The release kinetic of toxic metals as affected by BCP was also investigated. BCP at rate of 2% (w/w) and nitrogen levels (250 and 500 mg N kg-1) were added to sandy loam soil polluted with Cd, Pb, Zn, and Cu. The experiment consisted of five treatments including: Control (C), nitrogen a rate of 250 (N250), or 500 mg kg (N500), BCP + N250, and BCP + N500. Maximum tomato growth was achieved in the soil that was treated with BCP + N500, followed by BCP + N250, while lowest one was observed in the control. Tomato yield as affected by the BCP and N-fertilization was in the descending order: BCP + N500 > BCP + N250 > N500 = N250 > C. The addition of N250, N500, BCP + N250, and BCP + N500 increased the fruit yield by 24, 31, 35, 58% in comparison with the control. Levels of Zn, Cu, and Pb in tomato fruit was in the descending order: N500> N250 > C > BCP + N500 > BCP + N250. The combined application of BCP and N-fertilization augmented the availability and uptake of essential nutrients and effectively reduced those of toxic ones. The addition of BCP + N250 decreased Zn, Cu, Cd, and Pb content in fruit of tomato by 16, 10, 54, 54, and 58%, respectively, compared to the control soil, while these decreases were 13, 16, 60, 60, and 72% in the case of BCP + N500. BCP succeeded significantly in reducing the release of toxic chemicals, which ultimately may restrict the transfer of toxic chemical to the food chain solution. Novelty statement Tomato grown on metal-contaminated soils contains high levels of toxic metals. Phosphorus-loaded biochar (BCP) reduced the negative effects of high inorganic-N rates by reducing the release of toxic metals to the soil solution. BCP enhanced the soil quality indicators and increased the soil microbe's activity.

Seq2Neo: A Comprehensive Pipeline for Cancer Neoantigen Immunogenicity Prediction.

Neoantigens derived from somatic DNA alterations are ideal cancer-specific targets. In recent years, the combination therapy of PD-1/PD-L1 blockers and neoantigen vaccines has shown clinical efficacy in original PD-1/PD-L1 blocker non-responders. However, not all somatic DNA mutations result in immunogenicity among cancer cells and efficient tools to predict the immunogenicity of neoepitopes are still urgently needed. Here, we present the Seq2Neo pipeline, which provides a one-stop solution for neoepitope feature prediction using raw sequencing data. Neoantigens derived from different types of genome DNA alterations, including point mutations, insertion deletions and gene fusions, are all supported. Importantly, a convolutional neural network (CNN)-based model was trained to predict the immunogenicity of neoepitopes and this model showed an improved performance compared to the currently available tools in immunogenicity prediction using independent datasets. We anticipate that the Seq2Neo pipeline could become a useful tool in the prediction of neoantigen immunogenicity and cancer immunotherapy. Seq2Neo is open-source software under an academic free license (AFL) v3.0 and is freely available at Github.

Linking exogenous foliar application of glycine betaine and stomatal characteristics with salinity stress tolerance in cotton (Gossypium hirsutum L.) seedlings.

BACKGROUND: Glycine betaine (GB) plays a crucial role in plants responding to abiotic stresses. Studying the physiological response of cotton seedlings to exogenous GB under salt stress provides a reference for the application of GB to improve the resistance of cotton seedlings under salt stress. The purpose of this research is to examine the impacts of foliar-applied GB on leaf stomatal structure and characteristics, gas exchange and chlorophyll fluorescence characteristics and plant growth indicators of Gossypium hirsutum L. under NaCl stress conditions. RESULTS: Under the salinity of 150 mM, the four concentrations of GB are 0, 2.5, 5, and 7.5 mM, and the control (CK) was GB-untreated non-saline. Salt stress negatively affected leaf stomata as well as gas exchange and chlorophyll fluorescence and decreased plant growth parameters of cotton seedlings. The treatment with 5 mM GB significantly increased the evolution of photosynthetic rate (Pn), transpiration rate (Tr), intracellular CO2 concentration (Ci) and stomatal conductance (gs) compared to the GB-untreated saline treatment. The Exogenous foliar-applied GB has sustainably decreased the carboxylation efficiency (Pn/Ci) and water use efficiency (WUE). The concentration of 5 mM GB leads to a significant improvement of leaf stomatal characteristics. The leaf gas exchange attributes correlated positively with stomatal density (SD), stomatal length (SL) and stomatal with (SW). CONCLUSION: The overall results suggested that exogenous foliar supplementation with GB can effectively alleviate the damage of salt stress to cotton seedlings. The effect of applying 5 mM GB could be an optional choice for protecting cotton seedlings from NaCl stress through promoting the stomatal functions, photosynthetic activities and growth characteristics.

Secondary Mutation-Induced Alternative Splicing Suppresses RNA Splicing Defect of the jhs1 Mutant.

jing he sheng1 (jhs1) is a mutant of the DNA2 homolog in Arabidopsis (Arabidopsis thaliana), which was previously identified as being involved in DNA damage repair, cell cycle regulation, and meristem maintenance. A mutation at the 3' intron splice site of the 11th intron causes alternative splicing of this intron at two other sites, which results in frame shifts and premature stop codons. Here, we screened suppressors of jhs1 to further study the function and regulatory networks of JHS1 Three suppressors with wild-type-like phenotypes were obtained. Sequencing analysis results showed that each of the suppressors has a second mutation in jhs1 that causes further alternative splicing of the intron and corrects the shifted reading frame with small insertions. Precursor mRNA sequence analysis and intron splice site evaluation results suggested that intron splicing was disturbed in the suppressors, and this switched the splice site, resulting in small insertions in the coding regions of JHS1. Structural analysis of JHS1 suggested that the insertions are in a disordered loop region of the DNA2 domain and do not seem to have much deleterious effect on the function of the protein. This work not only has implications for the evolution of protein sequences at exon junctions but also provides a strategy to study the mechanism of precursor mRNA splicing.

The effects of nitrogen application rate on the grain physicochemical properties of japonica rice under controlled and flooding irrigation.

BACKGROUND: In this study, we investigated the effects of water-nitrogen interaction on the grain quality of two varieties of japonica rice grown on the North China Plain, based on evaluations of grain biochemical components, starch X-ray diffraction properties, thermal and pasting characteristics, and particle size distribution. RESULTS: We found that, under controlled irrigation, increasing levels of nitrogen resulted in a reduction in grain starch content and an increase in protein content. Nitrogen fertilization, irrigation, and their interaction had significant effects on the particle size and size distribution of rice flour. Under both controlled and flooding irrigation, the lowest values of pasting parameters for cultivars Xindao22 and Xindao10 were observed in response to moderate and high nitrogen application, respectively. Under flooding irrigation, Xindao22 exhibited lower mean value of gelatinization onset, peak, and conclusion temperatures and enthalpy in response to control irrigation, whereas in Xindao10 these parameters were relatively stable with respect to nitrogen and irrigation treatments. However, we observed no significant effects of either nitrogen or irrigation on amylopectin chain length distribution or starch relative crystallinity. CONCLUSION: Nitrogen application rate and irrigation methods had distinct effects on the physicochemical properties of flour derived from treated rice plants. The findings will provide support for scientific irrigation and fertilization in order to improve rice grain quality. © 2020 Society of Chemical Industry.

Responses of leaf gas exchange attributes, photosynthetic pigments and antioxidant enzymes in NaCl-stressed cotton (Gossypium hirsutum L.) seedlings to exogenous glycine betaine and salicylic acid.

BACKGROUND: Application of exogenous glycine betaine (GB) and exogenous salicylic acid (SA) mitigates the adverse effects of salinity. Foliar spraying with exogenous GB or SA alleviates salt stress in plants by increasing leaf gas exchange and stimulating antioxidant enzyme activity. The effects of foliar application of exogenous GB and SA on the physiology and biochemistry of cotton seedlings subjected to salt stress remain unclear. RESULTS: Results showed that salt stress of 150 mM NaCl significantly reduced leaf gas exchange and chlorophyll fluorescence and decreased photosynthetic pigment quantities and leaf relative water content. Foliar spray concentrations of 5.0 mM exogenous GB and 1.0 mM exogenous SA promoted gas exchange and fluorescence in cotton seedlings, increased quantities of chlorophyll pigments, and stimulated the antioxidant enzyme activity. The foliar spray also increased leaf relative water content and endogenous GB and SA content in comparison with the salt-stressed only control. Despite the salt-induced increase in antioxidant enzyme content, exogenous GB and SA in experimental concentrations significantly increased the activity of glutathione reductase, ascorbate peroxidase, superoxide dismutase, catalase and peroxidase, and decreased malondialdehyde content under salt stress. Across all experimental foliar spray GB and SA concentrations, the photochemical efficiency of photosystem II (FV/FM) reached a peak at a concentration of 5.0 mM GB. The net photosynthetic rate (Pn) and FV/FM were positively correlated with chlorophyll a and chlorophyll b content in response to foliar spraying of exogenous GB and SA under salt stress. CONCLUSIONS: We concluded, from our results, that concentrations of 5.0 mM GB or 1.0 mM SA are optimal choices for mitigating NaCl-induced damage in cotton seedlings because they promote leaf photosynthesis, increase quantities of photosynthetic pigments, and stimulate antioxidant enzyme activity. Among, 5.0 mM GB and 1.0 mM SA, the best performance in enhancing endogenous GB and SA concentrations was obtained with the foliar application of 1.0 mM SA under salt stress.

High adsorption performance of synthesized hexametaphosphate green rust towards Cr(VI) removal and its mechanism explorations.

Hexametaphosphate intercalated green rust (hexa-P GR) was fabricated by a coprecipitation process in an anaerobic environment to improve the adsorption of hexa-P GR for Cr(VI) and the total Cr under various aqueous conditions. Three kinetic models including the pseudo-first-order, intraparticle, and Elovich were appropriate in describing the adsorption of hexa-P GR towards Cr(VI) and the total Cr. The maximum mono-layer adsorption capacities (mg/g) of hexa-P GR for Cr(VI) at pH of 2 and 7 were 87.64 and 92.25, respectively, with the theoretical maximum capacity (mg/g) of 52.73 being obtained at pH of 7. Some competing cations existing in solutions such as Al3+, Ca2+, and Mg2+ would consume more hexa-P GR to remove Cr species. The neutral and weak alkaline environment was conducive to the hexa-P GR reuse, while the strong alkaline environment was beneficial to the removal of the total Cr. The orthogonal variables including the initial pH, the flow rate, and the Cr(VI) concentration all significantly influenced Cr removal. The sequences of reaction pathways referring to the adsorption of hexa-P GR differently occurred in various pH conditions.

Diet Affects the Temperature-Size Relationship in the Blowfly Aldrichina grahami.

In warmer environments, most ectotherms exhibit a plastic reduction in body size (the temperature-size rule, TSR). However, in such environments, growth is usually accelerated and would be expected to result in maturation at a larger body size, leading to increases in fecundity, survival, and mating success, compared to maturation at a smaller size (the 'life-history puzzle'). To explore these mechanisms, we reared Aldrichina grahami at 20 °C, 25 °C, and 30 °C, and added a nutritional challenge by using dilutions of pork liver paste to provide diets that ranged in quality from high (undiluted) to moderate (1/8), low (1/16), and poor (1/24). Larvae were randomly sampled for weighing from hatching. Growth curves were fitted to the relationships between growth rate and weight for the third instar larvae. Our results showed that body size was affected by an interaction between temperature and diet, and that following or not following the TSR can vary depending on underfeeding. Moreover, when the TSR was followed as temperature increased, there was a cross-over point that divided the two growth curves into early and later stages, which could be used to help understand the life-history puzzle in warmer temperatures, with the instantaneous growth rate being faster in the early stages of development and then slower in later stages. This study reminds us that animals have evolved to cope with multiple simultaneous environmental changes, and it has thus offered a better understanding of life-history puzzles.

Virtual Reality Utilized for Safety Skills Training for Autistic Individuals: A Review.

In recent years, virtual reality technology, which is able to simulate real-life environments, has been widely used in the field of intervention for individuals with autism and has demonstrated distinct advantages. This review aimed to evaluate the impact of virtual reality technology on safety skills intervention for individuals with autism. After searching and screening three databases, a total of 20 pertinent articles were included. There were six articles dedicated to the VR training of street-crossing skills for individuals with autism, nine articles focusing on the training of driving skills for individuals with ASD, and three studies examining the training of bus riding for individuals with ASD. Furthermore, there were two studies on the training of air travel skills for individuals with ASD. First, we found that training in some complex skills (e.g., driving skills) should be selected for older, high-functioning individuals with ASD, to determine their capacity to participate in the training using scales or questionnaires before the intervention; VR devices with higher levels of immersion are not suitable for younger individuals with ASD. Second, VR is effective in training safety skills for ASD, but there is not enough evidence to determine the relationship between the level of VR immersion and intervention effects. Although the degree of virtual reality involvement has an impact on the ability of ASD to be generalized to the real world, it is important to ensure that future virtual reality settings are realistic and lifelike. Again, adaptive models that provide personalized training to individuals with ASD in VR environments are very promising, and future research should continue in this direction. This paper also discusses the limitations of these studies, as well as potential future research directions.

Long-term saline water irrigation affected soil carbon and nitrogen cycling functional profiles in the cotton field.

Saline water irrigation (SWI) plays an important role in alleviating water resource shortages. At the same time, the salt input of irrigation water affects soil microorganisms which participate in various ecological processes of terrestrial ecosystems. However, the responses of soil microbial functional potential to long-term SWI remains unclear. Therefore, Metagenomics method was utilized in cotton fields under long-term SWI to reveal the microbial functional profiles associated with soil carbon and nitrogen cycles. Results indicated that SWI impacted the microbial functional profiles of soil carbon and nitrogen cycles in the cotton fields significantly. Especially, irrigation water salinity inhibited the relative abundances of sacC and vanB, which are soil carbon degradation genes. SWI also affected the functional gene abundance of nitrogen degradation, dissimilatory nitrate reduction, and nitrification. Moreover, SWI significantly increased the abundance of Candidatus_Cloacimonetes in both carbon and nitrogen cycles. In the discussion, we used person analysis found that soil salinity, pH, and ammonium nitrogen were important factors affecting the abundance of functional genes and microbial taxa. Overall, this study indicated that long-term SWI significantly influenced specific microbial functional genes and taxa abundance, which may lead to predictable outcomes for soil carbon and nitrogen cycling, and is of great importance in exploring the impact of SWI on soil environments.

Insufficient Sleep is Associated With Increasing Trends in Adolescent Suicidal Behaviors.

PURPOSE: Youth suicide has been increasing and became a public health concern worldwide. Identifying insufficient sleep as the potential risk factor is critical to reducing suicide risk and increasing trends. This study aimed to determine whether insufficient sleep is associated with increasing trends in suicidal behaviors and disparities by sex, age, and race/ethnicity among school adolescents. METHODS: The present study used biennial data from the US nationally representative Youth Risk Behavior Survey from 2007 to 2019. Joinpoint regression models were used to estimate biennial percent changes (BPCs) and average BPCs (ABPCs) of suicidal behaviors by sleep duration. Logistic regression models were used to examine the association between insufficient sleep and suicidal behaviors. RESULTS: Of 73,356 adolescent students included (mean [standard deviation] age, 16.11 [1.23] years), 50.03% were female. Suicidal ideation and suicide plan among insufficient sleep group increased from 2007 to 2019 (BPC = 2.88% [95% confidence interval {CI}: 1.65%, 4.13%]; BPC = 3.42% [95% CI: 2.09%, 4.77%]), but were nonsignificant among sufficient sleep group. Trends in suicidal ideation (ABPC = 3.03% [95% CI: 1.35%, 4.73%]) and suicide plan (ABPC = 4.03% [95% CI: 2.47%, 5.62%]) among female adolescents with insufficient sleep increased, but nonsignificant among male adolescents with insufficient sleep. Suicidal ideation (ABPC = 1.73% [95% CI: 0.51%, 2.97%]) and suicide plan (ABPC = 2.31% [95% CI: 0.70%, 3.95%]) increased among younger adolescents only with insufficient sleep, whereas suicide trends by sleep duration were similar among older adolescents. Suicide plan among insufficient sleep group increased across the four racial groups, with BPC highest for the White (BPC = 3.48% [95% CI: 1.31%, 5.69%]), and lowest for the Hispanic/Latino (BPC = 1.18% [95% CI: 0.15%, 2.23%]), but were nonsignificant among sufficient sleep group except for the White (BPC = 2.83% [95% CI: 0.62%, 5.09%]). DISCUSSION: Insufficient sleep was disproportionately associated with increasing trends in suicidal behaviors among female, younger, and non-White adolescent students. Ensuring sufficient sleep can potentially reduce suicide among school adolescents.

Can human-machine feedback in a smart learning environment enhance learners' learning performance? A meta-analysis.

Objective: The human-machine feedback in a smart learning environment can influences learners' learning styles, ability enhancement, and affective interactions. However, whether it has stability in improving learning performance and learning processes, the findings of many empirical studies are controversial. This study aimed to analyze the effect of human-machine feedback on learning performance and the potential boundary conditions that produce the effect in a smart learning environment. Methods: Web of Science, EBSCO, PsycINFO, and Science Direct were searched for publications from 2010 to 2022. We included randomized controlled trials with learning performance as outcome. The random effects model was used in the meta-analysis. The main effect tests and the heterogeneity tests were used to evaluate the effect of human-machine feedback mechanism on learning performance, and the boundary conditions of the effect were tested by moderating effects. Moreover, the validity of the meta-analysis was proved by publication bias test. Results: Out of 35 articles identified, 2,222 participants were included in this study. Human-machine interaction feedback had significant effects on learners' learning process (d = 0.594, k = 26) and learning outcomes (d = 0.407, k = 42). Also, the positive effects of human-machine interaction feedback were regulated by the direction of feedback, the form of feedback, and the type of feedback technique. Conclusion: To enhance learning performance through human-machine interactive feedback, we should focus on using two-way and multi-subject feedback. The technology that can provide emotional feedback and feedback loops should be used as a priority. Also, pay attention to the feedback process and mechanism, avoid increasing students' dependence on machines, and strengthen learners' subjectivity from feedback mechanism.

Early Onset of Impairments of Interpersonal Motor Synchrony in Preschool-Aged Children with Autism Spectrum Disorder.

Characteristics of interpersonal motor synchrony in individuals with autism spectrum disorder (ASD) have been investigated only in older children and adolescents, which calls for investigations in younger samples. The interpersonal motor synchrony was compared between preschool-aged children with (n = 23) and without ASD (n = 24) during free plays with familiar teachers. Children with ASD exhibited reduced synchrony of the upper body and trunk compared with typically developing (TD) children. Moreover, the degree of synchrony in ASD group was not above than chance. For autistic children, interpersonal motor synchrony was negatively correlated with aspects of autistic traits. The results suggest that the impairment of interpersonal motor synchrony has an onset earlier than school age and is a potential pathway for understanding autistic traits.

Neodb: a comprehensive neoantigen database and discovery platform for cancer immunotherapy.

Neoantigens derived from somatic deoxyribonucleic acid alterations are ideal cancer-specific targets. However, integrated platform for neoantigen discovery is urgently needed. Recently, many scattered experimental evidences suggest that some neoantigens are immunogenic, and comprehensive collection of these experimentally validated neoantigens is still lacking. Here, we have integrated the commonly used tools in the current neoantigen discovery process to form a comprehensive web-based analysis platform. To identify experimental evidences supporting the immunogenicity of neoantigens, we performed comprehensive literature search and constructed the database. The collection of public neoantigens was obtained by using comprehensive features to filter the potential neoantigens from recurrent driver mutations. Importantly, we constructed a graph neural network (GNN) model (Immuno-GNN) using an attention mechanism to consider the spatial interactions between human leukocyte antigen and antigenic peptides for neoantigen immunogenicity prediction. The new easy-to-use R/Shiny web-based neoantigen database and discovery platform, Neodb, contains currently the largest number of experimentally validated neoantigens. In addition to validated neoantigen, Neodb also includes three additional modules for facilitating neoantigen prediction and analysis, including 'Tools' module (comprehensive neoantigen prediction tools); 'Driver-Neo' module (collection of public neoantigens derived from recurrent mutations) and 'Immuno-GNN' module (a novel immunogenicity prediction tool based on a GNN). Immuno-GNN shows improved performance compared with known methods and also represents the first application of GNN model in neoantigen immunogenicity prediction. The construction of Neodb will facilitate the study of neoantigen immunogenicity and the clinical application of neoantigen-based cancer immunotherapy. Database URL https://liuxslab.com/Neodb/.

Accurate prediction of pan-cancer types using machine learning with minimal number of DNA methylation sites.

DNA methylation analysis has been applied to determine the primary site of cancer; however, robust and accurate prediction of cancer types with a minimum number of sites is still a significant scientific challenge. To build an accurate and robust cancer type prediction tool with a minimum number of DNA methylation sites, we internally benchmarked different DNA methylation site selection and ranking procedures, as well as different classification models. We used The Cancer Genome Atlas dataset (26 cancer types with 8296 samples) to train and test models and used an independent dataset (17 cancer types with 2738 samples) for model validation. A deep neural network model using a combined feature selection procedure (named MethyDeep) can predict 26 cancer types using 30 methylation sites with superior performance compared with the known methods for both primary and metastatic cancers in independent validation datasets. In conclusion, MethyDeep is an accurate and robust cancer type predictor with the minimum number of DNA methylation sites; it could help the cost-effective clarification of cancer of unknown primary patients and the liquid biopsy-based early screening of cancers.

Copy number alteration features in pan-cancer homologous recombination deficiency prediction and biology.

Homologous recombination deficiency (HRD) renders cancer cells vulnerable to unrepaired double-strand breaks and is an important therapeutic target as exemplified by the clinical efficacy of poly ADP-ribose polymerase (PARP) inhibitors as well as the platinum chemotherapy drugs applied to HRD patients. However, it remains a challenge to predict HRD status precisely and economically. Copy number alteration (CNA), as a pervasive trait of human cancers, can be extracted from a variety of data sources, including whole genome sequencing (WGS), SNP array, and panel sequencing, and thus can be easily applied clinically. Here we systematically evaluate the predictive performance of various CNA features and signatures in HRD prediction and build a gradient boosting machine model (HRDCNA) for pan-cancer HRD prediction based on these CNA features. CNA features BP10MB[1] (The number of breakpoints per 10MB of DNA is 1) and SS[ > 7 & <=8] (The log10-based size of segments is greater than 7 and less than or equal to 8) are identified as the most important features in HRD prediction. HRDCNA suggests the biallelic inactivation of BRCA1, BRCA2, PALB2, RAD51C, RAD51D, and BARD1 as the major genetic basis for human HRD, and may also be applied to effectively validate the pathogenicity of BRCA1/2 variants of uncertain significance (VUS). Together, this study provides a robust tool for cost-effective HRD prediction and also demonstrates the applicability of CNA features and signatures in cancer precision medicine.

Application of Machine Learning Techniques to Detect the Children with Autism Spectrum Disorder.

Early detection of autism spectrum disorder (ASD) is highly beneficial to the health sustainability of children. Existing detection methods depend on the assessment of experts, which are subjective and costly. In this study, we proposed a machine learning approach that fuses physiological data (electroencephalography, EEG) and behavioral data (eye fixation and facial expression) to detect children with ASD. Its implementation can improve detection efficiency and reduce costs. First, we used an innovative approach to extract features of eye fixation, facial expression, and EEG data. Then, a hybrid fusion approach based on a weighted naive Bayes algorithm was presented for multimodal data fusion with a classification accuracy of 87.50%. Results suggest that the machine learning classification approach in this study is effective for the early detection of ASD. Confusion matrices and graphs demonstrate that eye fixation, facial expression, and EEG have different discriminative powers for the detection of ASD and typically developing children, and EEG may be the most discriminative information. The physiological and behavioral data have important complementary characteristics. Thus, the machine learning approach proposed in this study, which combines the complementary information, can significantly improve classification accuracy.