Abstract Pulmonary lobe segmentation is an important prerequisite for accurately quantifying pulmonary damage in many pulmonary diseases and planning treatment. However, due to the incomplete lobar structures and morphological changes caused by diseases, the lobe segmentation still encounters great challenges. In this study, a Learnable Interpolation and Extrapolation Network (LIE‐Net) is proposed to form complete and consecutive fissure surfaces by learning to extract information of the fissures from existing fissure points and absent points (unsegmented points belonging to fissures) to predict the z coordinate of the absent fissure points. The completed pulmonary fissures are further used for accurate pulmonary lobe segmentation. Specifically, LIE‐Net takes the coordinate information of existing fissure points (their ( x , y , z ) coordinates) and absent fissure points (their ( x , y ) coordinates) as two independent inputs, and predicts the z coordinates of absent points. The proposed LIE‐Net makes voxel‐wise predictions based on the spatial structure characteristics of the lung fissure, and is able to provide a consecutive fissure surface in space. According to the evaluation of radiologists, the lobe segmentation performance was remarkably enhanced in approximately 76% of patients in our additional dataset after the application of LIE‐Net, especially for those cases with large‐scale missing fissures.

Image denoising is a classic low level vision problem that attempts to recover a noise-free image from a noisy observation. Recent advances in deep neural networks have outperformed traditional prior based methods for image denoising. However, the existing methods either require paired noisy and clean images for training or impose certain assumptions on the noise distribution and data types. In this paper, we present an end-to-end unpaired image denoising framework (UIDNet) that denoises images with only unpaired clean and noisy training images. The critical component of our model is a noise learning module based on a conditional Generative Adversarial Network (cGAN). The model learns the noise distribution from the input noisy images and uses it to transform the input clean images to noisy ones without any assumption on the noise distribution and data types. This process results in pairs of clean and pseudo-noisy images. Such pairs are then used to train another denoising network similar to the existing denoising methods based on paired images. The noise learning and denoising components are integrated together so that they can be trained end-to-end. Extensive experimental evaluation has been performed on both synthetic and real data including real photographs and computer tomography (CT) images. The results demonstrate that our model outperforms the previous models trained on unpaired images as well as the state-of-the-art methods based on paired training data when proper training pairs are unavailable.

MOTIVATION: Advances in high-throughput genotyping and sequencing technologies during recent years have revealed essential roles of non-coding regions in gene regulation. Genome-wide association studies (GWAS) suggested that a large proportion of risk variants are located in non-coding regions and remain unexplained by current expression quantitative trait loci catalogs. Interpreting the causal effects of these genetic modifications is crucial but difficult owing to our limited knowledge of how regulatory elements function. Although several computational methods have been designed to prioritize regulatory variants that substantially impact human phenotypes, few of them achieve consistently high performance even when large-scale multi-omic data are integrated. RESULTS: We propose a novel multi-task framework based on Bayesian deep neural networks, MtBNN, to quantify the deleterious impact of single nucleotide polymorphisms in non-coding genomic regions. With the high-efficiency provided by the multi-task Bayesian framework to integrate information from different sources, MtBNN is capable of extracting features from genomic sequences of large-scale chromatin-profiling data, such as chromatin accessibility and transcript factor binding affinities, and calculating the distribution of the probability that a non-coding variant disrupts regulatory activities. A series of comprehensive experiments show that MtBNN quantifies the functional impact of cis-regulatory variations with high accuracy, including expression quantitative trait locus, DNase I sensitivity quantitative trait locus and functional genetic variants located within ATAC-peaks that affect the accessibility of the corresponding peak and achieves significantly better performance than the existing methods. Moreover, MtBNN has applications in the discovery of potentially causal disease-associated single-nucleotide polymorphisms (SNPs), thus helping fine-map the GWAS SNPs. AVAILABILITY AND IMPLEMENTATION: Code can be downloaded from https://github.com/Zoesgithub/MtBNN. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Understanding the cell-specific binding patterns of transcription factors (TFs) is fundamental to studying gene regulatory networks in biological systems, for which ChIP-seq not only provides valuable data but is also considered as the gold standard. Despite tremendous efforts from the scientific community to conduct TF ChIP-seq experiments, the available data represent only a limited percentage of ChIP-seq experiments, considering all possible combinations of TFs and cell lines. In this study, we demonstrate a method for accurately predicting cell-specific TF binding for TF-cell line combinations based on only a small fraction (4%) of the combinations using available ChIP-seq data. The proposed model, termed TFImpute, is based on a deep neural network with a multi-task learning setting to borrow information across transcription factors and cell lines. Compared with existing methods, TFImpute achieves comparable accuracy on TF-cell line combinations with ChIP-seq data; moreover, TFImpute achieves better accuracy on TF-cell line combinations without ChIP-seq data. This approach can predict cell line specific enhancer activities in K562 and HepG2 cell lines, as measured by massively parallel reporter assays, and predicts the impact of SNPs on TF binding.

MOTIVATION: RNA-seq has been widely used in transcriptome analysis to effectively measure gene expression levels. Although sequencing costs are rapidly decreasing, almost 70% of all the human RNA-seq samples in the gene expression omnibus do not have biological replicates and more unreplicated RNA-seq data were published than replicated RNA-seq data in 2011. Despite the large amount of single replicate studies, there is currently no satisfactory method for detecting differentially expressed genes when only a single biological replicate is available. RESULTS: We present the GFOLD (generalized fold change) algorithm to produce biologically meaningful rankings of differentially expressed genes from RNA-seq data. GFOLD assigns reliable statistics for expression changes based on the posterior distribution of log fold change. In this way, GFOLD overcomes the shortcomings of P-value and fold change calculated by existing RNA-seq analysis methods and gives more stable and biological meaningful gene rankings when only a single biological replicate is available. AVAILABILITY: The open source C/C++ program is available at http://www.tongji.edu.cn/∼zhanglab/GFOLD/index.html

MOTIVATION: With the rapid development of high-throughput sequencing technologies, the genome-wide profiling of nucleosome positioning has become increasingly affordable. Many future studies will investigate the dynamic behaviour of nucleosome positioning in cells that have different states or that are exposed to different conditions. However, a robust method to effectively identify the regions of differential nucleosome positioning (RDNPs) has not been previously available. RESULTS: We describe a novel computational approach, DiNuP, that compares nucleosome profiles generated by high-throughput sequencing under various conditions. DiNuP provides a statistical P-value for each identified RDNP based on the difference of read distributions. DiNuP also empirically estimates the false discovery rate as a cutoff when two samples have different sequencing depths and differentiate reliable RDNPs from the background noise. Evaluation of DiNuP showed it to be both sensitive and specific for the detection of changes in nucleosome location, occupancy and fuzziness. RDNPs that were identified using publicly available datasets revealed that nucleosome positioning dynamics are closely related to the epigenetic regulation of transcription. AVAILABILITY AND IMPLEMENTATION: DiNuP is implemented in Python and is freely available at http://www.tongji.edu.cn/~zhanglab/DiNuP. CONTACT: [email protected] SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

The emergence of high-throughput technologies leads to abundant protein-protein interaction (PPI) data and microarray gene expression profiles, and provides a great opportunity for the identification of novel protein complexes using computational methods. By combining these two types of data, we propose a novel Graph Fragmentation Algorithm (GFA) for protein complex identification. Adapted from a classical max-flow algorithm for finding the (weighted) densest subgraphs, GFA first finds large (weighted) dense subgraphs in a protein-protein interaction network, and then, breaks each such subgraph into fragments iteratively by weighting its nodes appropriately in terms of their corresponding log-fold changes in the microarray data, until the fragment subgraphs are sufficiently small. Our tests on three widely used protein-protein interaction data sets and comparisons with several latest methods for protein complex identification demonstrate the strong performance of our method in predicting novel protein complexes in terms of its specificity and efficiency. Given the high specificity (or precision) that our method has achieved, we conjecture that our prediction results imply more than 200 novel protein complexes.

In this article, we present a new data structure, called the permutation tree, to improve the running time of sorting permutation by transpositions and sorting permutation by block interchanges. The existing 1.5-approximation algorithm for sorting permutation by transpositions has time complexity O ( n 3/2 √ logn ). By means of the permutation tree, we can improve this algorithm to achieve time complexity O ( nlogn ). We can also improve the algorithm for sorting permutation by block interchanges to take its time complexity from O ( n 2 ) down to O ( nlogn ).