Sphingolipid paracrine signaling impairs keratinocyte adhesion to promote melanoma invasion.

Melanoma is the deadliest form of skin cancer due to its propensity to metastasize. It arises from melanocytes, which are attached to keratinocytes within the basal epidermis. Here, we hypothesize that, in addition to melanocyte-intrinsic modifications, dysregulation of keratinocyte functions could initiate early-stage melanoma cell invasion. We identified the lysolipid sphingosine 1-phosphate (S1P) as a tumor paracrine signal from melanoma cells that modifies the keratinocyte transcriptome and reduces their adhesive properties, leading to tumor invasion. Mechanistically, tumor cell-derived S1P reduced E-cadherin expression in keratinocytes via S1P receptor dependent Snail and Slug activation. All of these effects were blocked by S1P2/3 antagonists. Importantly, we showed that epidermal E-cadherin expression was inversely correlated with the expression of the S1P-producing enzyme in neighboring tumors and the Breslow thickness in patients with early-stage melanoma. These findings support the notion that E-cadherin loss in the epidermis initiates the metastatic cascade in melanoma.

DeepG4: A deep learning approach to predict cell-type specific active G-quadruplex regions.

DNA is a complex molecule carrying the instructions an organism needs to develop, live and reproduce. In 1953, Watson and Crick discovered that DNA is composed of two chains forming a double-helix. Later on, other structures of DNA were discovered and shown to play important roles in the cell, in particular G-quadruplex (G4). Following genome sequencing, several bioinformatic algorithms were developed to map G4s in vitro based on a canonical sequence motif, G-richness and G-skewness or alternatively sequence features including k-mers, and more recently machine/deep learning. Recently, new sequencing techniques were developed to map G4s in vitro (G4-seq) and G4s in vivo (G4 ChIP-seq) at few hundred base resolution. Here, we propose a novel convolutional neural network (DeepG4) to map cell-type specific active G4 regions (e.g. regions within which G4s form both in vitro and in vivo). DeepG4 is very accurate to predict active G4 regions in different cell types. Moreover, DeepG4 identifies key DNA motifs that are predictive of G4 region activity. We found that such motifs do not follow a very flexible sequence pattern as current algorithms seek for. Instead, active G4 regions are determined by numerous specific motifs. Moreover, among those motifs, we identified known transcription factors (TFs) which could play important roles in G4 activity by contributing either directly to G4 structures themselves or indirectly by participating in G4 formation in the vicinity. In addition, we used DeepG4 to predict active G4 regions in a large number of tissues and cancers, thereby providing a comprehensive resource for researchers. Availability: https://github.com/morphos30/DeepG4.