Search

We present RBPNet, a novel deep learning method, which predicts CLIP-seq crosslink count distribution from RNA sequence at single-nucleotide resolution. By training on up to a million regions, RBPNet achieves high generalization on eCLIP, iCLIP and miCLIP assays, outperforming state-of-the-art classifiers. RBPNet performs bias correction by modeling the raw signal as a mixture of the protein-specific and background signal. Through model interrogation via Integrated Gradients, RBPNet identifies predictive sub-sequences that correspond to known and novel binding motifs and enables variant-impact scoring via in silico mutagenesis. Together, RBPNet improves imputation of protein-RNA interactions, as well as mechanistic interpretation of predictions., We present RBPNet, a novel deep learning method, which predicts CLIP-seq crosslink count distribution from RNA sequence at single-nucleotide resolution. By training on up to a million regions, RBPNet achieves high generalization on eCLIP, iCLIP and miCLIP assays, outperforming state-of-the-art classifiers. RBPNet performs bias correction by modeling the raw signal as a mixture of the protein-specific and background signal. Through model interrogation via Integrated Gradients, RBPNet identifies predictive sub-sequences that correspond to known and novel binding motifs and enables variant-impact scoring via in silico mutagenesis. Together, RBPNet improves imputation of protein-RNA interactions, as well as mechanistic interpretation of predictions.

Dysfunction of regulatory elements through genetic variants is a central mechanism in the pathogenesis of disease. To better understand disease etiology, there is consequently a need to understand how DNA encodes regulatory activity. Deep learning methods show great promise for modeling of biomolecular data from DNA sequence but are limited to large input data for training. Here, we develop ChromTransfer, a transfer learning method that uses a pre-trained, cell-type agnostic model of open chromatin regions as a basis for fine-tuning on regulatory sequences. We demonstrate superior performances with ChromTransfer for learning cell-type specific chromatin accessibility from sequence compared to models not informed by a pre-trained model. Importantly, ChromTransfer enables fine-tuning on small input data with minimal decrease in accuracy. We show that ChromTransfer uses sequence features matching binding site sequences of key transcription factors for prediction. Together, these results demonstrate ChromTransfer as a promising tool for learning the regulatory code.

Background: Asthma exacerbations are a serious public health concern due to high healthcare resource utilization, work/school productivity loss, impact on quality of life, and risk of mortality. The genetic basis of asthma exacerbations has been studied in several populations, but no prior study has performed a multi-ancestry meta-analysis of genome-wide association studies (meta-GWAS) for this trait. We aimed to identify common genetic loci associated with asthma exacerbations across diverse populations and to assess their functional role in regulating DNA methylation and gene expression. Methods: A meta-GWAS of asthma exacerbations in 4989 Europeans, 2181 Hispanics/Latinos, 1250 Singaporean Chinese, and 972 African Americans analyzed 9.6 million genetic variants. Suggestively associated variants (p <= 5 x 10(-5)) were assessed for replication in 36,477 European and 1078 non-European asthma patients. Functional effects on DNA methylation were assessed in 595 Hispanic/Latino and African American asthma patients and in publicly available databases. The effect on gene expression was evaluated in silico. Results: One hundred and twenty-six independent variants were suggestively associated with asthma exacerbations in the discovery phase. Two variants independently replicated: rs12091010 located at vascular cell adhesion molecule-1/exostosin like glycosyltransferase-2 (VCAM1/EXTL2) (discovery: odds ratio (ORT allele) = 0.82, p = 9.05 x 10(-6) and replication: ORT allele = 0.89, p = 5.35 x 10(-3)) and rs943126 from pantothenate kinase 1 (PANK1) (discovery: ORC allele = 0.85, p = 3.10 x 10(-5) and replication: ORC allele = 0.89, p = 1.30 x 10(-2)). Both variants regulate gene expression of genes where they locate and DNA methylation levels of nearby genes in whole blood. Conclusions: This multi-ancestry study revealed novel suggestive regulatory loci for asthma exacerbations located in genomic regions participating in inflammation and host defense.

Background: Asthma exacerbations are a serious public health concern due to high healthcare resource utilization, work/school productivity loss, impact on quality of life, and risk of mortality. The genetic basis of asthma exacerbations has been studied in several populations, but no prior study has performed a multi-ancestry meta-analysis of genome-wide association studies (meta-GWAS) for this trait. We aimed to identify common genetic loci associated with asthma exacerbations across diverse populations and to assess their functional role in regulating DNA methylation and gene expression. Methods: A meta-GWAS of asthma exacerbations in 4989 Europeans, 2181 Hispanics/Latinos, 1250 Singaporean Chinese, and 972 African Americans analyzed 9.6 million genetic variants. Suggestively associated variants (p ≤ 5 × 10−5) were assessed for replication in 36,477 European and 1078 non-European asthma patients. Functional effects on DNA methylation were assessed in 595 Hispanic/Latino and African American asthma patients and in publicly available databases. The effect on gene expression was evaluated in silico. Results: One hundred and twenty-six independent variants were suggestively associated with asthma exacerbations in the discovery phase. Two variants independently replicated: rs12091010 located at vascular cell adhesion molecule-1/exostosin like glycosyltransferase-2 (VCAM1/EXTL2) (discovery: odds ratio (ORT allele) = 0.82, p = 9.05 × 10−6 and replication: ORT allele = 0.89, p = 5.35 × 10−3) and rs943126 from pantothenate kinase 1 (PANK1) (discovery: ORC allele = 0.85, p = 3.10 × 10−5 and replication: ORC allele = 0.89, p = 1.30 × 10−2). Both variants regulate gene expression of genes where they locate and DNA methylation levels of nearby genes in whole blood. Conclusions: This multi-ancestry study revealed novel suggestive regulatory loci for asthma exacerbations located

Background. Legionella pneumophila is a causative agent of severe pneumonia. Infection leads to a broad host cell response, as evident, for example, on the transcriptional level. Chromatin modifications, which control gene expression, play a central role in the transcriptional response to L. pneumophila. Methods. We infected human-blood-derived macrophages (BDMs) with L. pneumophila and used chromatin immunoprecipitation followed by sequencing to screen for gene promoters with the activating histone 4 acetylation mark. Results. We found the promoter of tumor necrosis factor alpha-induced protein 2 (TNFAIP2) to be acetylated at histone H4. This factor has not been characterized in the pathology of L. pneumophila. TNFAIP2 messenger RNA and protein were upregulated in response to L. pneumophila infection of human-BDMs and human alveolar epithelial (A549) cells. We showed that L. pneumophila-induced TNFAIP2 expression is dependent on the NF-kappa B transcription factor. Importantly, knock down of TNFAIP2 led to reduced intracellular replication of L. pneumophila Corby in A549 cells. Conclusions. Taken together, genome-wide chromatin analysis of L. pneumophila-infected macrophages demonstrated induction of TNFAIP2, a NF-kappa B-dependent factor relevant for bacterial replication.

KRAS is a gene that plays a very important role in the initiation and development of several types of cancer. In particular, 90% of human pancreatic cancers are due to KRAS mutations. KRAS is difficult to target directly and a promising therapeutic path is its indirect inactivation by targeting one of its Synthetic Lethal Partners (SLPs). A gene G is a Synthetic Lethal Partner of KRAS if the simultaneous perturbation of KRAS and G leads to cell death. In the past, efforts to identify KRAS SLPs with high-throughput RNAi screens have been performed. These studies have reported only few top-ranked SLPs. To our knowledge, these screens have never been considered in combination for further examination. This thesis employs integrative analysis of the published screens, utilizing additional, independent data aiming at the detection of more robust therapeutic targets. To this aim, RankSLP, a novel statistical analysis approach was implemented, which for the first time i) consistently integrates existing KRAS-specific RNAi screens, ii) consistently integrates and normalizes the results of various ranking methods, iii) evaluates its findings with the use of external data and iv) explores the effects of random data inclusion. This analysis was able to predict novel SLPs of KRAS and confirm some of the existing ones.