The promoter region is located near the transcription start sites and regulates transcription initiation of the gene by controlling the binding of RNA polymerase. Thus, promoter region recognition is an important area of interest in the field of bioinformatics. Numerous tools for promoter prediction were proposed. However, the reliability of these tools still needs to be improved. In this work, we propose a robust deep learning model, called DeePromoter, to analyze the characteristics of the short eukaryotic promoter sequences, and accurately recognize the human and mouse promoter sequences. DeePromoter combines a convolutional neural network (CNN) and a long short-term memory (LSTM). Additionally, instead of using non-promoter regions of the genome as a negative set, we derive a more challenging negative set from the promoter sequences. The proposed negative set reconstruction method improves the discrimination ability and significantly reduces the number of false positive predictions. Consequently, DeePromoter outperforms the previously proposed promoter prediction tools. In addition, a web-server for promoter prediction is developed based on the proposed methods and made available at https://home.jbnu.ac.kr/NSCL/deepromoter.htm.

Alternative splicing plays a major role in regulating the functional repertoire of the proteome. However, isoform-specific effects to protein-protein interactions (PPIs) are usually overlooked, making it impossible to judge the functional role of individual exons on a systems biology level. We overcome this barrier by integrating protein-protein interactions, domain-domain interactions and residue-level interactions information to lift exon expression analysis to a network level. Our user-friendly database DIGGER is available at https://exbio.wzw.tum.de/digger and allows users to seamlessly switch between isoform and exon-centric views of the interactome and to extract sub-networks of relevant isoforms, making it an essential resource for studying mechanistic consequences of alternative splicing.

Alternative splicing (AS) is the process of combining different parts of the pre-mRNA to produce diverse transcripts and eventually different protein products from a single gene. In computational biology field, researchers try to understand AS behavior and regulation using computational models known as “Splicing Codes”. The final goal of these algorithms is to make an in-silico prediction of AS outcome from genomic sequence. Here, we develop a deep learning approach, called Deep Splicing Code (DSC), for categorizing the well-studied classes of AS namely alternatively skipped exons, alternative 5’ss, alternative 3’ss, and constitutively spliced exons based only on the sequence of the exon junctions. The proposed approach significantly improves the prediction and the obtained results reveal that constitutive exons have distinguishable local characteristics from alternatively spliced exons. Using the motif visualization technique, we show that the trained models learned to search for competitive alternative splice sites as well as motifs of important splicing factors with high precision. Thus, the proposed approach greatly expands the opportunities to improve alternative splicing modeling. In addition, a web-server for AS events prediction has been developed based on the proposed method.

Gene regulation is frequently altered in diseases in unique and patient-specific ways. Hence, personalized strategies have been proposed to infer patient-specific gene-regulatory networks. However, existing methods do not scale well as they often require recomputing the entire network per sample. Moreover, they do not account for clinically important confounding factors such as age, sex, or treatment history. Finally, a user-friendly implementation for the analysis and interpretation of such net-works is missing. We present DysRegNet, a method for inferring patient-specific regulatory alterations (dysregulations) from bulk gene expression profiles. We compared DysRegNet to SSN, a well-known sample-specific network approach. We demonstrate that both SSN and DysRegNet produce interpretable and biologically meaningful networks across various cancer types. In contrast to SSN, DysRegNet can scale to arbitrary sample numbers and highlights the importance of confounders in network inference, revealing an age-specific bias in gene regulation in breast cancer. DysRegNet is available as a Python package ( https://github.com/biomedbigdata/DysRegNet_package ), and analysis results for eleven TCGA cancer types are available through an interactive web interface ( https://exbio.wzw.tum.de/dysregnet ).

Gene regulation is frequently altered in diseases in unique and often patient-specific ways. Hence, personalized strategies have been proposed to infer patient-specific gene-regulatory networks. However, existing methods do not focus on disease-specific dysregulation or lack assessment of statistical significance. Moreover, they do not account for clinically important confounding factors such as age, sex, or treatment history. To overcome these shortcomings, we present DysRegNet, a novel method for inferring patient-specific regulatory alterations (dysregulations) from gene expression profiles. We compared DysRegNet to SSN, the original sample-specific network approach, and demonstrated that DysRegNet produces more interpretable and biologically meaningful networks. We apply DysRegNet to eleven TCGA cancer types and illustrate how the inferred networks can be used for downstream analysis. We show that unique as well as cancer-type-specific dysregulation patterns exist and highlight immune-related mechanisms that are not obvious when focusing on individual genes rather than their interactions.

Background and Purpose: Gene regulation is frequently altered in diseases in unique and patient‐specific ways. Hence, personalised strategies have been proposed to infer patient‐specific gene‐regulatory networks. However, existing methods do not scale well because they often require recomputing the entire network per sample. Moreover, they do not account for clinically important confounding factors such as age, sex or treatment history. Finally, a user‐friendly implementation for the analysis and interpretation of such networks is missing. Experimental Approach: We present DysRegNet, a method for inferring patient‐specific regulatory alterations (dysregulations) from bulk gene expression profiles. We compared DysRegNet to the well‐known SSN method, considering patient clustering, promoter methylation, mutations and cancer‐stage data. Key Results: We demonstrate that both SSN and DysRegNet produce interpretable and biologically meaningful networks across various cancer types. In contrast to SSN, DysRegNet can scale to arbitrary sample numbers and highlights the importance of confounders in network inference, revealing an age‐specific bias in gene regulation in breast cancer. DysRegNet is available as a Python package ( https://github.com/biomedbigdata/DysRegNet_package ), and analysis results for 11 TCGA cancer types are available through an interactive web interface ( https://exbio.wzw.tum.de/dysregnet ). Conclusion and Implications: DysRegNet introduces a novel bioinformatics tool enabling confounder‐aware and patient‐specific network analysis to unravel regulatory alteration in complex diseases. LINKED ARTICLES: This article is part of a themed issue Network Medicine and Systems Pharmacology. To view the other articles in this section visit http://onlinelibrary.wiley.com/doi/10.1111/bph.v183.8/issuetoc