Search

Motivation High-resolution Hi-C contact matrices reveal the detailed three-dimensional architecture of the genome, but high-coverage experimental Hi-C data are expensive to generate. Simultaneously, chromatin structure analyses struggle with extremely sparse contact matrices. To address this problem, computational methods to enhance low-coverage contact matrices have been developed, but existing methods are largely based on resolution enhancement methods for natural images and hence often employ models that do not distinguish between biologically meaningful contacts, such as loops and other stochastic contacts. Results We present Capricorn, a machine learning model for Hi-C resolution enhancement that incorporates small-scale chromatin features as additional views of the input Hi-C contact matrix and leverages a diffusion probability model backbone to generate a high-coverage matrix. We show that Capricorn outperforms the state of the art in a cross-cell-line setting, improving on existing methods by 17% in mean squared error and 26% in F 1 score for chromatin loop identification from the generated high-coverage data. We also demonstrate that Capricorn performs well in the cross-chromosome setting and cross-chromosome, cross-cell-line setting, improving the downstream loop F 1 score by 14% relative to existing methods. We further show that our multiview idea can also be used to improve several existing methods, HiCARN and HiCNN, indicating the wide applicability of this approach. Finally, we use DNA sequence to validate discovered loops and find that the fraction of CTCF-supported loops from Capricorn is similar to those identified from the high-coverage data. Capricorn is a powerful Hi-C resolution enhancement method that enables scientists to find chromatin features that cannot be identified in the low-coverage contact matrix. Availability and implementation Implementation of Capricorn and source code for reproducing all figures in this paper are available at https://github.com/CHNFTQ/Capricorn. [ABSTRACT FROM AUTHOR]

Transcription factors (TFs) are proteins specifically involved in gene expression regulation. It is generally accepted in epigenetics that methylated nucleotides could prevent the TFs from binding to DNA fragments. However, recent studies have confirmed that some TFs have capability to interact with methylated DNA fragments to further regulate gene expression. Although biochemical experiments could recognize TFs binding to methylated DNA sequences, these wet experimental methods are time-consuming and expensive. Machine learning methods provide a good choice for quickly identifying these TFs without experimental materials. Thus, this study aims to design a robust predictor to detect methylated DNA-bound TFs. We firstly proposed using tripeptide word vector feature to formulate protein samples. Subsequently, based on recurrent neural network with long short-term memory, a two-step computational model was designed. The first step predictor was utilized to discriminate transcription factors from non-transcription factors. Once proteins were predicted as TFs, the second step predictor was employed to judge whether the TFs can bind to methylated DNA. Through the independent dataset test, the accuracies of the first step and the second step are 86.63% and 73.59%, respectively. In addition, the statistical analysis of the distribution of tripeptides in training samples showed that the position and number of some tripeptides in the sequence could affect the binding of TFs to methylated DNA. Finally, on the basis of our model, a free web server was established based on the proposed model, which can be available at https://bioinfor.nefu.edu.cn/TFPM/. [ABSTRACT FROM AUTHOR]

Background Train travel is a common mode of public transport across the globe; however, the risk of coronavirus disease 2019 (COVID-19) transmission among individual train passengers remains unclear. Methods We quantified the transmission risk of COVID-19 on high-speed train passengers using data from 2334 index patients and 72 093 close contacts who had co-travel times of 0–8 hours from 19 December 2019 through 6 March 2020 in China. We analyzed the spatial and temporal distribution of COVID-19 transmission among train passengers to elucidate the associations between infection, spatial distance, and co-travel time. Results The attack rate in train passengers on seats within a distance of 3 rows and 5 columns of the index patient varied from 0 to 10.3% (95% confidence interval [CI], 5.3%–19.0%), with a mean of 0.32% (95% CI,.29%–.37%). Passengers in seats on the same row (including the adjacent passengers to the index patient) as the index patient had an average attack rate of 1.5% (95% CI, 1.3%–1.8%), higher than that in other rows (0.14% [95% CI,.11%–.17%]), with a relative risk (RR) of 11.2 (95% CI, 8.6–14.6). Travelers adjacent to the index patient had the highest attack rate (3.5% [95% CI, 2.9%–4.3%]) of COVID-19 infection (RR, 18.0 [95% CI, 13.9–23.4]) among all seats. The attack rate decreased with increasing distance, but increased with increasing co-travel time. The attack rate increased on average by 0.15% (P =.005) per hour of co-travel; for passengers in adjacent seats, this increase was 1.3% (P =.008), the highest among all seats considered. Conclusions COVID-19 has a high transmission risk among train passengers, but this risk shows significant differences with co-travel time and seat location. During disease outbreaks, when traveling on public transportation in confined spaces such as trains, measures should be taken to reduce the risk of transmission, including increasing seat distance, reducing passenger density, and use of personal hygiene protection. [ABSTRACT FROM AUTHOR]

We prove a geometric version of a classical result on the characterization of an irreducible cuspidal automorphic representation of being the base change of a stable cuspidal representation of the quasi-split unitary group associated to the quadratic extension E/F, via the nonvanishing of certain period integrals, called being distinguished. We show that certain cohomology of an automorphic sheaf of GLn,X′ is nonvanishing if and only if the corresponding local system E on X′ is conjugate self-dual with respect to an étale double cover X′/X of curves, which directly relates to the base change from the associated unitary group. In particular, the geometric setting makes sense over any base field. [ABSTRACT FROM AUTHOR]