Interpretation of allele-specific chromatin accessibility using cell state-aware deep learning.

Genomic sequence variation within enhancers and promoters can have a significant impact on the cellular state and phenotype. However, sifting through the millions of candidate variants in a personal genome or a cancer genome, to identify those that impact cis-regulatory function, remains a major challenge. Interpretation of noncoding genome variation benefits from explainable artificial intelligence to predict and interpret the impact of a mutation on gene regulation. Here we generate phased whole genomes with matched chromatin accessibility, histone modifications, and gene expression for 10 melanoma cell lines. We find that training a specialized deep learning model, called DeepMEL2, on melanoma chromatin accessibility data can capture the various regulatory programs of the melanocytic and mesenchymal-like melanoma cell states. This model outperforms motif-based variant scoring, as well as more generic deep learning models. We detect hundreds to thousands of allele-specific chromatin accessibility variants (ASCAVs) in each melanoma genome, of which 15%-20% can be explained by gains or losses of transcription factor binding sites. A considerable fraction of ASCAVs are caused by changes in AP-1 binding, as confirmed by matched ChIP-seq data to identify allele-specific binding of JUN and FOSL1. Finally, by augmenting the DeepMEL2 model with ChIP-seq data for GABPA, the TERT promoter mutation, as well as additional ETS motif gains, can be identified with high confidence. In conclusion, we present a new integrative genomics approach and a deep learning model to identify and interpret functional enhancer mutations with allelic imbalance of chromatin accessibility and gene expression.

Cross-species analysis of enhancer logic using deep learning.

Deciphering the genomic regulatory code of enhancers is a key challenge in biology because this code underlies cellular identity. A better understanding of how enhancers work will improve the interpretation of noncoding genome variation and empower the generation of cell type-specific drivers for gene therapy. Here, we explore the combination of deep learning and cross-species chromatin accessibility profiling to build explainable enhancer models. We apply this strategy to decipher the enhancer code in melanoma, a relevant case study owing to the presence of distinct melanoma cell states. We trained and validated a deep learning model, called DeepMEL, using chromatin accessibility data of 26 melanoma samples across six different species. We show the accuracy of DeepMEL predictions on the CAGI5 challenge, where it significantly outperforms existing models on the melanoma enhancer of IRF4 Next, we exploit DeepMEL to analyze enhancer architectures and identify accurate transcription factor binding sites for the core regulatory complexes in the two different melanoma states, with distinct roles for each transcription factor, in terms of nucleosome displacement or enhancer activation. Finally, DeepMEL identifies orthologous enhancers across distantly related species, where sequence alignment fails, and the model highlights specific nucleotide substitutions that underlie enhancer turnover. DeepMEL can be used from the Kipoi database to predict and optimize candidate enhancers and to prioritize enhancer mutations. In addition, our computational strategy can be applied to other cancer or normal cell types.

The impact of adjuvant chemotherapy in older breast cancer patients on clinical and biological aging parameters.

PURPOSE: This prospective observational study aimed to evaluate the impact of adjuvant chemotherapy on biological and clinical markers of aging and frailty. METHODS: Women ≥ 70 years old with early breast cancer were enrolled after surgery and assigned to a chemotherapy (Docetaxel and Cyclophosphamide) group (CTG, n=57) or control group (CG, n=52) depending on their planned adjuvant treatment. Full geriatric assessment (GA) and Quality of Life (QoL) were evaluated at inclusion (T0), after 3 months (T1) and at 1 year (T2). Blood samples were collected to measure leukocyte telomere length (LTL), levels of interleukin-6 (IL-6) and other circulating markers potentially informative for aging and frailty: Interleukin-10 (IL-10), Tumor Necrosis Factor Alpha (TNF-α), Insulin-like Growth Factor 1 (IGF-1), Monocyte Chemotactic Protein 1 (MCP-1) and Regulated on Activation, Normal T cell Expressed and Secreted (RANTES). RESULTS: LTL decreased significantly but comparably in both groups, whereas IL-6 was unchanged at T2. However, IL-10, TNF-α, IGF-1 and MCP-1 suggested a minor biological aging effect of chemotherapy. Clinical frailty and QoL decreased at T1 in the CTG, but recovered at T2, while remaining stable in the CG. CONCLUSIONS: Chemotherapy (TC) is unlikely to amplify clinical aging or induce frailty at 1 year. Accordingly, there is no impact on the most established aging biomarkers (LTL, IL-6).

Decoding the regulatory landscape of melanoma reveals TEADS as regulators of the invasive cell state.

Transcriptional reprogramming of proliferative melanoma cells into a phenotypically distinct invasive cell subpopulation is a critical event at the origin of metastatic spreading. Here we generate transcriptome, open chromatin and histone modification maps of melanoma cultures; and integrate this data with existing transcriptome and DNA methylation profiles from tumour biopsies to gain insight into the mechanisms underlying this key reprogramming event. This shows thousands of genomic regulatory regions underlying the proliferative and invasive states, identifying SOX10/MITF and AP-1/TEAD as regulators, respectively. Knockdown of TEADs shows a previously unrecognized role in the invasive gene network and establishes a causative link between these transcription factors, cell invasion and sensitivity to MAPK inhibitors. Using regulatory landscapes and in silico analysis, we show that transcriptional reprogramming underlies the distinct cellular states present in melanoma. Furthermore, it reveals an essential role for the TEADs, linking it to clinically relevant mechanisms such as invasion and resistance.