A Deep Learning Framework Identifies Pathogenic Noncoding Somatic Mutations from Personal Prostate Cancer Genomes

Integrative identification of non-coding regulatory regions driving metastatic prostate cancer

Large-scale sequencing efforts have been undertaken to understand the mutational landscape of the coding genome. However, the vast majority of variants occur within non-coding genomic regions. We designed an integrative computational and experimental framework to identify recurrently mutated non-coding regulatory regions that drive tumor progression. Applying this framework to sequencing data from a large prostate cancer patient cohort revealed a large set of candidate drivers. We used (1) in silico analyses, (2) massively parallel reporter assays, and (3) in vivo CRISPR interference screens to systematically validate metastatic castration-resistant prostate cancer (mCRPC) drivers. One identified enhancer region, GH22I030351, acts on a bidirectional promoter to simultaneously modulate expression of the U2-associated splicing factor SF3A1 and chromosomal protein CCDC157. SF3A1 and CCDC157 promote tumor growth in vivo. We nominated a number of transcription factors, notably SOX6, to regulate expression of SF3A1 and CCDC157. Our integrative approach enables the systematic detection of non-coding regulatory regions that drive human cancers.

Integrative analysis of noncoding mutations identifies the druggable genome in preterm birth

Preterm birth affects ~10% of pregnancies in the US. Despite familial associations, identifying at-risk genetic loci has been challenging. We built deep learning and graphical models to score mutational effects at base resolution via integrating the pregnant myometrial epigenome and large-scale patient genomes with spontaneous preterm birth (sPTB) from European and African American cohorts. We uncovered previously unidentified sPTB genes that are involved in myometrial muscle relaxation and inflammatory responses and that are regulated by the progesterone receptor near labor onset. We studied genomic variants in these genes in our recruited pregnant women administered progestin prophylaxis. We observed that mutation burden in these genes was predictive of responses to progestin treatment for preterm birth. To advance therapeutic development, we screened ~4000 compounds, identified candidate molecules that affect our identified genes, and experimentally validated their therapeutic effects on regulating labor. Together, our integrative approach revealed the druggable genome in preterm birth and provided a generalizable framework for studying complex diseases.

Assessment of Prostate and Bladder Cancer Genomic Biomarkers Using Artificial Intelligence: a Systematic Review

PURPOSE OF REVIEW

The aim of the systematic review is to assess AI's capabilities in the genetics of prostate cancer (PCa) and bladder cancer (BCa) to evaluate target groups for such analysis as well as to assess its prospects in daily practice.

RECENT FINDINGS

In total, our analysis included 27 articles: 10 articles have reported on PCa and 17 on BCa, respectively. The AI algorithms added clinical value and demonstrated promising results in several fields, including cancer detection, assessment of cancer development risk, risk stratification in terms of survival and relapse, and prediction of response to a specific therapy. Besides clinical applications, genetic analysis aided by the AI shed light on the basic urologic cancer biology. We believe, our results of the AI application to the analysis of PCa, BCa data sets will help to identify new targets for urological cancer therapy. The integration of AI in genomic research for screening and clinical applications will evolve with time to help personalizing chemotherapy, prediction of survival and relapse, aid treatment strategies such as reducing frequency of diagnostic cystoscopies, and clinical decision support, e.g., by predicting immunotherapy response. These factors will ultimately lead to personalized and precision medicine thereby improving patient outcomes.

The Diagnostic Landscape of Adult Neurogenetic Disorders

Neurogenetic diseases affect individuals across the lifespan, but accurate diagnosis remains elusive for many patients. Adults with neurogenetic disorders often undergo a long diagnostic odyssey, with multiple specialist evaluations and countless investigations without a satisfactory diagnostic outcome. Reasons for these diagnostic challenges include: (1) clinical features of neurogenetic syndromes are diverse and under-recognized, particularly those of adult-onset, (2) neurogenetic syndromes may manifest with symptoms that span multiple neurological and medical subspecialties, and (3) a positive family history may not be present or readily apparent. Furthermore, there is a large gap in the understanding of how to apply genetic diagnostic tools in adult patients, as most of the published literature focuses on the pediatric population. Despite these challenges, accurate genetic diagnosis is imperative to provide affected individuals and their families guidance on prognosis, recurrence risk, and, for an increasing number of disorders, offer targeted treatment. Here, we provide a framework for recognizing adult neurogenetic syndromes, describe the current diagnostic approach, and highlight studies using next-generation sequencing in different neurological disease cohorts. We also discuss diagnostic pitfalls, barriers to achieving a definitive diagnosis, and emerging technology that may increase the diagnostic yield of testing.

Attention-based generative adversarial networks improve prognostic outcome prediction of cancer from multimodal data

The prediction of prognostic outcome is critical for the development of efficient cancer therapeutics and potential personalized medicine. However, due to the heterogeneity and diversity of multimodal data of cancer, data integration and feature selection remain a challenge for prognostic outcome prediction. We proposed a deep learning method with generative adversarial network based on sequential channel-spatial attention modules (CSAM-GAN), a multimodal data integration and feature selection approach, for accomplishing prognostic stratification tasks in cancer. Sequential channel-spatial attention modules equipped with an encoder-decoder are applied for the input features of multimodal data to accurately refine selected features. A discriminator network was proposed to make the generator and discriminator learning in an adversarial way to accurately describe the complex heterogeneous information of multiple modal data. We conducted extensive experiments with various feature selection and classification methods and confirmed that the CSAM-GAN via the multilayer deep neural network (DNN) classifier outperformed these baseline methods on two different multimodal data sets with miRNA expression, mRNA expression and histopathological image data: lower-grade glioma and kidney renal clear cell carcinoma. The CSAM-GAN via the multilayer DNN classifier bridges the gap between heterogenous multimodal data and prognostic outcome prediction.

Relating pathogenic loss-of-function mutations in humans to their evolutionary fitness costs

Causal loss-of-function (LOF) variants for Mendelian and severe complex diseases are enriched in 'mutation intolerant' genes. We show how such observations can be interpreted in light of a model of mutation-selection balance and use the model to relate the pathogenic consequences of LOF mutations at present to their evolutionary fitness effects. To this end, we first infer posterior distributions for the fitness costs of LOF mutations in 17,318 autosomal and 679 X-linked genes from exome sequences in 56,855 individuals. Estimated fitness costs for the loss of a gene copy are typically above 1%; they tend to be largest for X-linked genes, whether or not they have a Y homolog, followed by autosomal genes and genes in the pseudoautosomal region. We compare inferred fitness effects for all possible de novo LOF mutations to those of de novo mutations identified in individuals diagnosed with one of six severe, complex diseases or developmental disorders. Probands carry an excess of mutations with estimated fitness effects above 10%; as we show by simulation, when sampled in the population, such highly deleterious mutations are typically only a couple of generations old. Moreover, the proportion of highly deleterious mutations carried by probands reflects the typical age of onset of the disease. The study design also has a discernible influence: a greater proportion of highly deleterious mutations is detected in pedigree than case-control studies, and for autism, in simplex than multiplex families and in female versus male probands. Thus, anchoring observations in human genetics to a population genetic model allows us to learn about the fitness effects of mutations identified by different mapping strategies and for different traits.

Role of IGF2 in the Study of Development and Evolution of Prostate Cancer

Prostate Cancer (PC) is commonly known as one of the most frequent tumors among males. A significant problem of this tumor is that in early stages most of the cases course as indolent forms, so an active surveillance will anticipate the appearance of aggressive stages. One of the main strategies in medical and biomedical research is to find non-invasive biomarkers for improving monitoring and performing a more precise follow-up of diseases like PC. Here we report the relevant role of IGF2 and miR-93-5p as non-invasive biomarker for PC. This event could improve current medical strategies in PC.

Computational modeling of chromatin accessibility identified important epigenomic regulators

Chromatin accessibility is essential for transcriptional activation of genomic regions. It is well established that transcription factors (TFs) and histone modifications (HMs) play critical roles in chromatin accessibility regulation. However, there is a lack of studies that quantify these relationships. Here we constructed a two-layer model to predict chromatin accessibility by integrating DNA sequence, TF binding, and HM signals. By applying the model to two human cell lines (GM12878 and HepG2), we found that DNA sequences had limited power for accessibility prediction, while both TF binding and HM signals predicted chromatin accessibility with high accuracy. According to the HM model, HM features determined chromatin accessibility in a cell line shared manner, with the prediction power attributing to five core HM types. Results from the TF model indicated that chromatin accessibility was determined by a subset of informative TFs including both cell line-specific and generic TFs. The combined model of both TF and HM signals did not further improve the prediction accuracy, indicating that they provide redundant information in terms of chromatin accessibility prediction. The TFs and HM models can also distinguish the chromatin accessibility of proximal versus distal transcription start sites with high accuracy.

Deep Learning for Human Disease Detection, Subtype Classification, and Treatment Response Prediction Using Epigenomic Data

Deep learning (DL) is a distinct class of machine learning that has achieved first-class performance in many fields of study. For epigenomics, the application of DL to assist physicians and scientists in human disease-relevant prediction tasks has been relatively unexplored until very recently. In this article, we critically review published studies that employed DL models to predict disease detection, subtype classification, and treatment responses, using epigenomic data. A comprehensive search on PubMed, Scopus, Web of Science, Google Scholar, and arXiv.org was performed following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines. Among 1140 initially identified publications, we included 22 articles in our review. DNA methylation and RNA-sequencing data are most frequently used to train the predictive models. The reviewed models achieved a high accuracy ranged from 88.3% to 100.0% for disease detection tasks, from 69.5% to 97.8% for subtype classification tasks, and from 80.0% to 93.0% for treatment response prediction tasks. We generated a workflow to develop a predictive model that encompasses all steps from first defining human disease-related tasks to finally evaluating model performance. DL holds promise for transforming epigenomic big data into valuable knowledge that will enhance the development of translational epigenomics.

A panoramic view of proteomics and multiomics in precision health

Health is often qualitatively defined as a status free from disease and its quantitative definition requires finding the boundary separating health from pathological conditions. Since many complex diseases have a strong genetic component, substantial efforts have been made to sequence large-scale personal genomes; however, we are not yet able to effectively quantify health status from personal genomes. Since mutational impacts are ultimately manifested at the protein level, we envision that introducing a panoramic proteomic view of complex diseases will allow us to mechanistically understand the molecular etiologies of human diseases. In this perspective article, we will highlight key proteomic approaches to identify pathogenic mutations and map their convergent pathways underlying disease pathogenesis and the integration of omics data at multiple levels to define the borderline between health and disease.