In Silico: Predicting Intrinsic Features of HLA Class-I Restricted Neoantigens.

Mutation-containing immunogenic peptides from tumor cells, also named as neoantigens, have various amino acid descriptors and physical-chemical properties characterized intrinsic features, which are useful in prioritizing the immunogenicity potentials of neoantigens and predicting patients' survival. Here, we describe a glioma neoantigen intrinsic feature database, GNIFdb, that hosts computationally predicted HLA-I restricted neoantigens of gliomas, their intrinsic features, and the tools for calculating intrinsic features and predicting overall survival of gliomas. We illustrate the application of GNIFdb in searching for possible neoantigen candidates from ATF6 that plays important roles in tumor growth and resistance to radiotherapy in glioblastoma. We also demonstrate the application of intrinsic feature associated tools in GNIFdb to predict the overall survival of primary IDH wild-type glioblastoma.

NIN-LIKE PROTEIN3.2 inhibits repressor Aux/IAA14 expression and enhances root biomass in maize seedlings under low nitrogen.

Plants generally enhance their root growth in the form of greater biomass and/or root length to boost nutrient uptake in response to short-term low nitrogen (LN). However, the underlying mechanisms of short-term LN-mediated root growth remain largely elusive. Our genome-wide association study, haplotype analysis, and phenotyping of transgenic plants showed that the crucial nitrate signaling component NIN-LIKE PROTEIN3.2 (ZmNLP3.2), a positive regulator of root biomass, is associated with natural variations in root biomass of maize (Zea mays L.) seedlings under LN. The monocot-specific gene AUXIN/INDOLE-3-ACETIC ACID14 (ZmAux/IAA14) exhibited opposite expression patterns to ZmNLP3.2 in ZmNLP3.2 knockout and overexpression lines, suggesting that ZmNLP3.2 hampers ZmAux/IAA14 transcription. Importantly, ZmAux/IAA14 knockout seedlings showed a greater root dry weight (RDW), whereas ZmAux/IAA14 overexpression reduced RDW under LN compared with wild-type plants, indicating that ZmAux/IAA14 negatively regulates the RDW of LN-grown seedlings. Moreover, in vitro and vivo assays indicated that AUXIN RESPONSE FACTOR19 (ZmARF19) binds to and transcriptionally activates ZmAux/IAA14, which was weakened by the ZmNLP3.2-ZmARF19 interaction. The zmnlp3.2 ZmAux/IAA14-OE seedlings exhibited further reduced RDW compared to ZmAux/IAA14 overexpression lines when subjected to LN treatment, corroborating the ZmNLP3.2-ZmAux/IAA14 interaction. Thus, our study reveals a ZmNLP3.2-ZmARF19-ZmAux/IAA14 module regulating root biomass in response to nitrogen limitation in maize.

Genomic variation in weedy and cultivated broomcorn millet accessions uncovers the genetic architecture of agronomic traits.

Large-scale genomic variations are fundamental resources for crop genetics and breeding. Here we sequenced 1,904 genomes of broomcorn millet to an average of 40× sequencing depth and constructed a comprehensive variation map of weedy and cultivated accessions. Being one of the oldest cultivated crops, broomcorn millet has extremely low nucleotide diversity and remarkably rapid decay of linkage disequilibrium. Genome-wide association studies identified 186 loci for 12 agronomic traits. Many causative candidate genes, such as PmGW8 for grain size and PmLG1 for panicle shape, showed strong selection signatures during domestication. Weedy accessions contained many beneficial variations for the grain traits that are largely lost in cultivated accessions. Weedy and cultivated broomcorn millet have adopted different loci controlling flowering time for regional adaptation in parallel. Our study uncovers the unique population genomic features of broomcorn millet and provides an agronomically important resource for cereal crops.

Tissue-Matched IgH Gene Rearrangement of Circulating Tumor DNA Shows Significant Value in Predicting the Progression of Diffuse Large B Cell Lymphoma.

BACKGROUND: Evidence has demonstrated that monitoring of the variable, diversity, and joining gene segments (VDJ) rearrangement of the immunoglobulin (Ig) genes in the circulating tumor DNA (ctDNA) is of value in predicting the outcomes of diffuse large B cell lymphoma (DLBCL). In this study, we investigated the role of VDJ rearrangement proportion in ctDNA for predicting DLBCL progression. METHODS: Patients diagnosed with newly diagnosed DLBCL were included in this study. The VDJ sequences of IgH were detected using next-generation sequencing (NGS) in formalin-fixed paraffin-embedded tissue and/or peripheral blood. The clonotype of the highest proportion in the peripheral blood was defined as the "dominant circulating clonotype," whilst the clonotype of the highest proportion in matched tissue that is detected in peripheral blood was defined as the "dominant tissue-matched clonotype." The decision tree, a machine learning-based methodology, was used to establish a progression-predicting model through a combination of "dominant tissue-matched clonotype" proportion or "dominant circulating clonotype" proportion, and the clinicopathological information, including age, sex, cell of origin, stage, international prognostic index, lactate dehydrogenase, number of extranodal involvements and ß2-microglobulin. RESULTS: A total of 55 patients with eligible sequencing data were used for prognosis analysis, among which 36 patients had matched tissue samples. The concordance rate of "dominant circulating clonotype" and "dominant tissue-matched clonotype" was 19.44% (7/36). The decision tree model showed that the combination of extranodal involvement event and "dominant circulating clonotype" proportion (≥37%) had a clinical value in predicting the prognosis of DLBCL following combined chemotherapy (sensitivity, 0.63; specificity, 0.81; positive prediction value (PPV), 0.59; negative prediction value, 0.83; kappa value, 0.42). Noticeably, the combination of the "dominant tissue-matched clonotype" and extranodal involvement event showed a higher value in predicting the progression (sensitivity, 0.85; specificity, 0.78; PPV, 0.69; kappa value, 0.64). CONCLUSION: IgH proportion detected in the ctDNA samples traced from tissue samples has a high clinical value in predicting the progression of DLBCL.

Detection of the DNA methylation of seven genes contribute to the early diagnosis of lung cancer.

BACKGROUND: Low-dose Computed Tomography (CT) is used for the detection of pulmonary nodules, but the ambiguous risk evaluation causes overdiagnosis. Here, we explored the significance of the DNA methylation of 7 genes including TAC1, CDO1, HOXA9, ZFP42, SOX17, RASSF1A and SHOX2 in the blood cfDNA samples in distinguishing lung cancer from benign nodules and healthy individuals. METHOD: A total of 149 lung cancer patients [72 mass and 77 ground-glass nodules (GGNs)], 5 benign and 48 healthy individuals were tested and analyzed in this study. The lasso-logistic regression model was built for distinguishing cancer and control/healthy individuals or IA lung cancer and non-IA lung cancer cases. RESULTS: The positive rates of methylation of 7 genes were higher in the cancer group as compared with the healthy group. We constructed a model using age, sex and the ΔCt value of 7 gene methylation to distinguish lung cancer from benign and healthy individuals. The sensitivity, specificity and AUC (area under the curve) were 86.7%, 81.4% and 0.891, respectively. Also, we assessed the significance of 7 gene methylation together with patients' age and sex in distinguishing of GGNs type from the mass type. The sensitivity, specificity and AUC were 77.1%, 65.8% and 0.753, respectively. Furthermore, the methylation positive rates of CDO1 and SHOX2 were different between I-IV stages of lung cancer. Specifically, the positive rate of CDO1 methylation was higher in the non-IA group as compared with the IA group. CONCLUSION: Collectively, this study reveals that the methylation of 7 genes has a big significance in the diagnosis of lung cancer with high sensitivity and specificity. Also, the 7 genes present with certain significance in distinguishing the GGN type lung cancer, as well as different stages.

Dynamic transcriptome landscape of maize pericarp development.

As a maternal tissue, the pericarp supports and protects for other components of seed, such as embryo and endosperm. Despite the importance of maize pericarp in seed, the genome-wide transcriptome pattern throughout maize pericarp development has not been well characterized. Here, we developed RNA-seq transcriptome atlas of B73 maize pericarp development based on 21 samples from 5 days before fertilization (DBP5) to 32 days after fertilization (DAP32). A total of 25 346 genes were detected in programming pericarp development, including 1887 transcription factors (TFs). Together with pericarp morphological changes, the global clustering of gene expression revealed four developmental stages: undeveloped, thickening, expansion and strengthening. Coexpression analysis provided further insights on key regulators in functional transition of four developmental stages. Combined with non-seed, embryo, endosperm, and nucellus transcriptome data, we identified 598 pericarp-specific genes, including 75 TFs, which could elucidate key mechanisms and regulatory networks of pericarp development. Cell wall related genes were identified that reflected their crucial role in the maize pericarp structure building. In addition, key maternal proteases or TFs related with programmed cell death (PCD) were proposed, suggesting PCD in the maize pericarp was mediated by vacuolar processing enzymes (VPE), and jasmonic acid (JA) and ethylene-related pathways. The dynamic transcriptome atlas provides a valuable resource for unraveling the genetic control of maize pericarp development.

Targeted large fragment deletion in plants using paired crRNAs with type I CRISPR system.

The CRISPR-Cas systems have been widely used as genome editing tools, with type II and V systems typically introducing small indels, and type I system mediating long-range deletions. However, the precision of type I systems for large fragment deletion is still remained to be optimized. Here, we developed a compact Cascade-Cas3 Dvu I-C system with Cas11c for plant genome editing. The Dvu I-C system was efficient to introduce controllable large fragment deletion up to at least 20 kb using paired crRNAs. The paired-crRNAs design also improved the controllability of deletions for the type I-E system. Dvu I-C system was sensitive to spacer length and mismatch, which was benefit for target specificity. In addition, we showed that the Dvu I-C system was efficient for generating stable transgenic lines in maize and rice with the editing efficiency up to 86.67%. Overall, Dvu I-C system we developed here is powerful for achieving controllable large fragment deletions.

The latest edition of WHO and ELN guidance and a new risk model for Chinese acute myeloid leukemia patients.

Objective: Diagnosis classification and risk stratification are crucial in the prognosis prediction and treatment selection of acute myeloid leukemia (AML). Here, we used a database of 536 AML patients to compare the 4th and 5th WHO classifications and the 2017 and 2022 versions of ELN guidance. Methods: AML patients were classified according to the 4th and 5th WHO classifications, as well as the 2017 and 2022 versions of the European LeukemiaNet (ELN) guidance. Kaplan-Meier curves with log-rank tests were used for survival analysis. Results: The biggest change was that 25 (5.2%), 8 (1.6%), and 1 (0.2%) patients in the AML, not otherwise specified (NOS) group according to the 4th WHO classification, were re-classified into the AML-MR (myelodysplasia-related), KMT2A rearrangement, and NUP98 rearrangement subgroups based on the 5th WHO classification. Referring to the ELN guidance, 16 patients in the favorable group, six patients in the adverse group, and 13 patients in the intermediate group based on the 2017 ELN guidance were re-classified to the intermediate and adverse groups based on the 2022 ELN guidance. Regrettably, the Kaplan-Meier curves showed that the survival of intermediate and adverse groups could not be distinguished well according to either the 2017 or 2022 ELN guidance. To this end, we constructed a risk model for Chinese AML patients, in which the clinical information (age and gender), gene mutations (NPM1, RUNX1, SH2B3, and TP53), and fusions (CBFB::MYH11 and RUNX1::RUNX1T1) were included, and our model could help divide the patients into favorable, intermediate, and adverse groups. Conclusion: These results affirmed the clinical value of both WHO and ELN, but a more suitable prognosis model should be established in Chinese cohorts, such as the models we proposed.

NGS-based IgH gene rearrangement monitoring predicts relapse and guides maintenance therapy in DLBCL: A case report from indolent lymphoma to aggressive lymphoma.

This report describes a case of extranodal marginal zone B-cell lymphoma (ENMZL) of the mucosa-associated lymphoid tissue (MALT) lymphoma that transformed to diffuse large B cell lymphoma (DLBCL) in a 39-year-old female patient with Hashimoto's thyroiditis (HT). The patient presented with MALT lymphoma in the thyroid tissue and DLBCL in the multiple site invasions, including the ovary, breast, and lymph nodes. We assessed the Ig gene rearrangement and mutation profile in lymphoma involved tissues and the collected stem cells. V(D)J sequence of the tumor clonotype detected in thyroid, ovary, and breast was identical, revealing a shared origin of the malignant lymphoma. Noticeably, a small percentage of tumor clonotype (the highest-ranking clonotype in tumor tissues) was detected in the stem cell sample, suggesting the malignant cells was residual in the stem cells, likely conferred disease relapse following ASCT. This patient recieved BTK inhibitor combined with radiotherapy to eradicate the residual tumor cells based on the V(D)J sequence monitoring after ASCT. Now the patient remains in complete remission following 12 months of ASCT.

A complete telomere-to-telomere assembly of the maize genome.

A complete telomere-to-telomere (T2T) finished genome has been the long pursuit of genomic research. Through generating deep coverage ultralong Oxford Nanopore Technology (ONT) and PacBio HiFi reads, we report here a complete genome assembly of maize with each chromosome entirely traversed in a single contig. The 2,178.6 Mb T2T Mo17 genome with a base accuracy of over 99.99% unveiled the structural features of all repetitive regions of the genome. There were several super-long simple-sequence-repeat arrays having consecutive thymine-adenine-guanine (TAG) tri-nucleotide repeats up to 235 kb. The assembly of the entire nucleolar organizer region of the 26.8 Mb array with 2,974 45S rDNA copies revealed the enormously complex patterns of rDNA duplications and transposon insertions. Additionally, complete assemblies of all ten centromeres enabled us to precisely dissect the repeat compositions of both CentC-rich and CentC-poor centromeres. The complete Mo17 genome represents a major step forward in understanding the complexity of the highly recalcitrant repetitive regions of higher plant genomes.

Detection of MET amplification by droplet digital PCR in peripheral blood samples of non-small cell lung cancer.

PURPOSE: Mesenchymal-epithelial transition (MET) amplification is one of the mechanisms accounting for the resistance of epidermal growth factor receptor (EGFR) tyrosine kinase inhibitors (TKIs) in lung cancer patients, as well as the poor prognosis. Fluorescence in situ hybridization (FISH) is the most widely used method for MET amplification detection. However, it is inapplicable when tissue samples were unavailable. Herein, we assessed the value of droplet digital PCR (ddPCR) in MET copy number gain (CNG) detection in non-small cell lung cancer (NSCLC) patients treated with EGFR-TKIs. MATERIALS AND METHODS: A total of 103 cancer tissues and the paired peripheral blood samples from NSCLC patients were collected for MET CNG detection using ddPCR. In parallel, MET amplification in tissue samples was verified by FISH. Also, the relationships between MET CNG and EGFR T790M, as well as the EGFR-TKI resistance were also evaluated using Chi-square or Fisher's exact tests. RESULT: The concordance rate of ddPCR and FISH in detecting MET CNG in tissue samples was 100% (102/102), and it was 94.17% (97/103) for ddPCR method in detecting the MET CNG among peripheral blood and tissue samples. No statistical difference was observed between MET amplification and EGFR T790M (p = 0.65), while MET amplification rate was significantly increased in patients with resistance to third generations of EGFR-TKIs as compared with patients with resistance to first/second EGFR-TKIs (p < 0.05). CONCLUSIONS: ddPCR is an alternative method to detect MET CNG in both tissues and peripheral blood samples, which is of worthy in clinical promotion.

Circulating tumor DNA mutation profile is associated with the prognosis and treatment response of Chinese patients with newly diagnosed diffuse large B-cell lymphoma.

Background: Characterization of gene mutation profiles can provide new treatment options for patients with diffuse large B-cell lymphoma (DLBCL). However, this method is challenged by the limited source of tissue specimens, especially those of DLBCL patients at advanced stages. Therefore, in the current study, we aimed to describe the gene mutation landscape of DLBCL using circulating tumor DNA (ctDNA) samples obtained from patients' blood samples, as well as to explore the relationship between ctDNA mutations and the prognosis and treatment response of patients with newly diagnosed DLBCL. Methods: A total of 169 newly diagnosed Chinese DLBCL patients were included in this study, among which 85 patients were divided into a training set and 84 were assigned into a validation set. The mutation profile of a 59-gene panel was analyzed by targeted next generation sequencing (NGS) of the patients' ctDNA samples. Differences in clinical factors between patients with and without ctDNA mutations were analyzed. In addition, we also explored gene mutation frequencies between GCB and non-GCB subtypes, and the relationship between gene mutation status, clinical factors, mean VAF (variant allele frequencies) and the patients' overall survival (OS) and progression-free survival (PFS). Results: ctDNA mutations were detected in 64 (75.3%) patients of the training set and 67 (79.8%) patients of the validation set. The most commonly mutated genes in both sets were PCLO, PIM1, MYD88, TP53, KMT2D, CD79B, HIST1H1E and LRP1B, with mutation frequencies of >10%. Patients with detectable ctDNA mutations trended to present advanced Ann Arbor stages (III-IV), elevated LDH (lactate dehydrogenase) levels, shorter OS and PFS, and a lower complete response (CR) rate to the R-CHOP regimen compared with DLBCL patients without ctDNA mutations. In addition, mean VAF (≥4.94%) and PCLO mutations were associated with poor OS and PFS. Conclusion: We investigated the ctDNA mutation landscape in Chinese patients with newly diagnosed DLBCL and found that ctDNA could reflect tumor burden and patients with detectable ctDNA mutations trended to have shorter OS and PFS and a lower CR rate.

GNIFdb: a neoantigen intrinsic feature database for glioma.

ABSTRACT: Neoantigens are mutation-containing immunogenic peptides from tumor cells. Neoantigen intrinsic features are neoantigens' sequence-associated features characterized by different amino acid descriptors and physical-chemical properties, which have a crucial function in prioritization of neoantigens with immunogenic potentials and predicting patients with better survival. Different intrinsic features might have functions to varying degrees in evaluating neoantigens' potentials of immunogenicity. Identification and comparison of intrinsic features among neoantigens are particularly important for developing neoantigen-based personalized immunotherapy. However, there is still no public repository to host the intrinsic features of neoantigens. Therefore, we developed GNIFdb, a glioma neoantigen intrinsic feature database specifically designed for hosting, exploring and visualizing neoantigen and intrinsic features. The database provides a comprehensive repository of computationally predicted Human leukocyte antigen class I (HLA-I) restricted neoantigens and their intrinsic features; a systematic annotation of neoantigens including sequence, neoantigen-associated mutation, gene expression, glioma prognosis, HLA-I subtype and binding affinity between neoantigens and HLA-I; and a genome browser to visualize them in an interactive manner. It represents a valuable resource for the neoantigen research community and is publicly available at http://www.oncoimmunobank.cn/index.php. DATABASE URL: http://www.oncoimmunobank.cn/index.php.

HITAC-seq enables high-throughput cost-effective sequencing of plasmids and DNA fragments with identity.

DNA sequencing is vital for many aspects of biological research and diagnostics. Despite the development of second and third generation sequencing technologies, Sanger sequencing has long been the only choice when required to precisely track each sequenced plasmids or DNA fragments. Here, we report a complete set of novel barcoding and assembling system, Highly-parallel Indexed Tagmentation-reads Assembled Consensus sequencing (HITAC-seq), that could massively sequence and track the identities of each individual sequencing sample. With the cost of much less than that of single read of Sanger sequencing, HITAC-seq can generate high-quality contiguous sequences of up to 10 kilobases or longer. The capability of HITAC-seq was confirmed through large-scale sequencing of thousands of plasmid clones and hundreds of amplicon fragments using approximately 100 pg of input DNAs. Due to its long synthetic length, HITAC-seq was effective in detecting relatively large structural variations, as demonstrated by the identification of a ∼1.3 kb Copia retrotransposon insertion in the upstream of a likely maize domestication gene. Besides being a practical alternative to traditional Sanger sequencing, HITAC-seq is suitable for many high-throughput sequencing and genotyping applications.

TFBSshape: an expanded motif database for DNA shape features of transcription factor binding sites.

TFBSshape (https://tfbsshape.usc.edu) is a motif database for analyzing structural profiles of transcription factor binding sites (TFBSs). The main rationale for this database is to be able to derive mechanistic insights in protein-DNA readout modes from sequencing data without available structures. We extended the quantity and dimensionality of TFBSshape, from mostly in vitro to in vivo binding and from unmethylated to methylated DNA. This new release of TFBSshape improves its functionality and launches a responsive and user-friendly web interface for easy access to the data. The current expansion includes new entries from the most recent collections of transcription factors (TFs) from the JASPAR and UniPROBE databases, methylated TFBSs derived from in vitro high-throughput EpiSELEX-seq binding assays and in vivo methylated TFBSs from the MeDReaders database. TFBSshape content has increased to 2428 structural profiles for 1900 TFs from 39 different species. The structural profiles for each TFBS entry now include 13 shape features and minor groove electrostatic potential for standard DNA and four shape features for methylated DNA. We improved the flexibility and accuracy for the shape-based alignment of TFBSs and designed new tools to compare methylated and unmethylated structural profiles of TFs and methods to derive DNA shape-preserving nucleotide mutations in TFBSs.

Author Correction: Epigenetic stress responses induce muscle stem-cell ageing by Hoxa9 developmental signals.

An Amendment to this paper has been published and can be accessed via a link at the top of the paper.

Rational selection of antibacterial drugs and postoperative nursing for gynecologic and obstetric surgery patients.

Infection after gynecologic surgery is very common and frequent. If the control is not good, it will lead to serious consequences. Therefore, it is necessary to use antibiotics in the period of obstetrics and gynecology. This study will explore the use of antimicrobial agents in gynecologic and obstetric surgery, thus standardizing the use of antibiotics in the process of obstetrics and gynecology. Through the analysis of the use of antibacterials, we can see that the highest utilization rate of 5 kinds of antibacterial drugs followed by Cefaclor Sustained Release Tablets (65.7%), metronidazole (32.5%), cefathiamidine (26.8%), enoxacin (22.5%) and cefoperazone tazobactam sodium (11.8%). At the same time, the hospital should improve the consciousness of rational drug use and strengthen the administration of antibacterials in the operative period of obstetrics and gynecology. The application of antibiotics in the operative period of the department of obstetrics and gynecology can improve the current situation of its irrational use. Nursing work must take strict aseptic operation to prevent cross infection. At the same time, we should strengthen the observation of the effect of medication, monitor the body temperature and blood pressure, and identify the side effects of drugs.

Artemin regulates CXCR4 expression to induce migration and invasion in pancreatic cancer cells through activation of NF-κB signaling.

Pancreatic ductal adenocarcinoma (PDAC) is the most lethal human malignant tumor because of the early onset of local invasion and distant metastasis. Perineural invasion is a prominent characteristic of pancreatic adenocarcinoma, which is a multifactorial process that involves various signaling molecules from different signaling pathways. The glial cell line-derived neurotrophic factor family of ligands was reported to be involved in perineural invasion in pancreatic cancer. Artemin is one member of the glial cell line-derived neurotrophic factor family of ligands. Although Artemin has previously been demonstrated to promote invasiveness of pancreatic cancer, the mechanisms remain poorly understood. In this study, we performed an analysis to determine the effects of Artemin on modulating tumor cell metastatic potential and invasion activity and explored its mechanisms in pancreatic cancer. We indicated that Artemin and CXCR4 were overexpressed in cancer tissues and widely expressed in pancreatic cancer cell lines. We observed that activation of ERK1/2 and Akt in Artemin-treated cells led to enhanced nuclear accumulation of NF-κB, which then induced CXCR4 expression. Through regulation of the expression of CXCR4, Artemin functionally promoted the migration and invasion in pancreatic cancer cells. The present study indicated that Artemin induced CXCR4 expression by activating Akt and ERK 1/2/NF-κB signaling, thereby modulating tumor cell metastatic potential and invasion activity in pancreatic cancer by regulating SDF-1α/CXCR4 axis. Artemin might be an effective and potent therapeutic target for pancreatic cancer metastasis, especially in perineural invasion.

Relationship between histone modifications and transcription factor binding is protein family specific.

The very small fraction of putative binding sites (BSs) that are occupied by transcription factors (TFs) in vivo can be highly variable across different cell types. This observation has been partly attributed to changes in chromatin accessibility and histone modification (HM) patterns surrounding BSs. Previous studies focusing on BSs within DNA regulatory regions found correlations between HM patterns and TF binding specificities. However, a mechanistic understanding of TF-DNA binding specificity determinants is still not available. The ability to predict in vivo TF binding on a genome-wide scale requires the identification of features that determine TF binding based on evolutionary relationships of DNA binding proteins. To reveal protein family-dependent mechanisms of TF binding, we conducted comprehensive comparisons of HM patterns surrounding BSs and non-BSs with exactly matched core motifs for TFs in three cell lines: 33 TFs in GM12878, 37 TFs in K562, and 18 TFs in H1-hESC. These TFs displayed protein family-specific preferences for HM patterns surrounding BSs, with high agreement among cell lines. Moreover, compared to models based on DNA sequence and shape at flanking regions of BSs, HM-augmented quantitative machine-learning methods resulted in increased performance in a TF family-specific manner. Analysis of the relative importance of features in these models indicated that TFs, displaying larger HM pattern differences between BSs and non-BSs, bound DNA in an HM-specific manner on a protein family-specific basis. We propose that TF family-specific HM preferences reveal distinct mechanisms that assist in guiding TFs to their cognate BSs by altering chromatin structure and accessibility.

Deep Graph Embedding for Ranking Optimization in E-commerce.

Matching buyers with most suitable sellers providing relevant items (e.g., products) is essential for e-commerce platforms to guarantee customer experience. This matching process is usually achieved through modeling inter-group (buyer-seller) proximity by e-commerce ranking systems. However, current ranking systems often match buyers with sellers of various qualities, and the mismatch is detrimental to not only buyers' level of satisfaction but also the platforms' return on investment (ROI). In this paper, we address this problem by incorporating intra-group structural information (e.g., buyer-buyer proximity implied by buyer attributes) into the ranking systems. Specifically, we propose Deep Graph Embedding (DEGREE), a deep learning based method, to exploit both inter-group and intra-group proximities jointly for structural learning. With a sparse filtering technique, DEGREE can significantly improve the matching performance with computation resources less than that of alternative deep learning based methods. Experimental results demonstrate that DEGREE outperforms state-of-the-art graph embedding methods on real-world e-commence datasets. In particular, our solution boosts the average unit price in purchases during an online A/B test by up to 11.93%, leading to better operational efficiency and shopping experience.