Search

Potential clinical biomarkers are often assessed with Cox regressions or their ability to differentiate two groups of patients based on a single cutoff. However, both of these approaches assume a monotonic relationship between the potential biomarker and survival. Tumor mutational burden (TMB) is currently being studied as a predictive biomarker for immunotherapy, and a single cutoff is often used to divide patients. In this study, we introduce a two-cutoff approach that allows splitting of patients when a non-monotonic relationship is present and explore the use of neural networks to model more complex relationships of TMB to outcome data. Using real-world data, we find that while in most cases the true relationship between TMB and survival appears monotonic, that is not always the case and researchers should be made aware of this possibility., Significance: When a non-monotonic relationship to survival is present it is not possible to divide patients by a single value of a predictor. Neural networks allow for complex transformations and can be used to correctly split patients when a non-monotonic relationship is present., (©2024 The Authors; Published by the American Association for Cancer Research.)

Polyploidy or whole-genome duplication (WGD) is a major event that drastically reshapes genome architecture and is often assumed to be causally associated with organismal innovations and radiations. The 2R hypothesis suggests that two WGD events (1R and 2R) occurred during early vertebrate evolution. However, the timing of the 2R event relative to the divergence of gnathostomes (jawed vertebrates) and cyclostomes (jawless hagfishes and lampreys) is unresolved and whether these WGD events underlie vertebrate phenotypic diversification remains elusive. Here we present the genome of the inshore hagfish, Eptatretus burgeri. Through comparative analysis with lamprey and gnathostome genomes, we reconstruct the early events in cyclostome genome evolution, leveraging insights into the ancestral vertebrate genome. Genome-wide synteny and phylogenetic analyses support a scenario in which 1R occurred in the vertebrate stem-lineage during the early Cambrian, and 2R occurred in the gnathostome stem-lineage, maximally in the late Cambrian-earliest Ordovician, after its divergence from cyclostomes. We find that the genome of stem-cyclostomes experienced an additional independent genome triplication. Functional genomic and morphospace analyses demonstrate that WGD events generally contribute to developmental evolution with similar changes in the regulatory genome of both vertebrate groups. However, appreciable morphological diversification occurred only in the gnathostome but not in the cyclostome lineage, calling into question the general expectation that WGDs lead to leaps of bodyplan complexity., (© 2024. The Author(s).)

Pediatric melanomas are rare and some of them may arise on giant congenital melanocytic nevi. The risk of developing melanoma on a medium-sized nevus is not clear but is thought to be very rare. Proliferative cellular nodules which mimic malignant melanoma may pose significant diagnostic challenges. We report the case of a 9-year-old patient who developed a melanoma on a medium-sized congenital melanocytic nevus on the tip of the nose, requiring a complex surgery with excellent aesthetic results.

The relationship between bullous pemphigoid (BP) and neoplasms has been debated in the medical literature. Although numerous case reports have described the coexistence of BP with various neoplasms, case-control studies have yielded conflicting results. We present the case of a male patient who developed BP shortly after being diagnosed with mycosis fungoides (MF). He was a 77-year-old man with a history of type 2 diabetes mellitus and hypertension who was diagnosed with MF. Subsequently, he developed blisters after sun exposure, and was diagnosed with BP through histopathology and direct immunofluorescence. The patient was treated with prednisone and methotrexate, with favorable evolution without recurrence of MF or appearance of new blisters. The association between cutaneous T-cell lymphoma and autoimmune blistering disease is rare, although similar cases have been reported, some associated with phototherapy. In this case, the onset of BP after sun exposure suggests a potential connection. The coexistence of BP and MF remains controversial, and this case highlights the importance of considering autoimmune blistering diseases in patients with oncohematological neoplasms.

Large-scale genomic data are well suited to analysis by deep learning algorithms. However, for many genomic datasets, labels are at the level of the sample rather than for individual genomic measures. Machine learning models leveraging these datasets generate predictions by using statically encoded measures that are then aggregated at the sample level. Here we show that a single weakly supervised end-to-end multiple-instance-learning model with multi-headed attention can be trained to encode and aggregate the local sequence context or genomic position of somatic mutations, hence allowing for the modelling of the importance of individual measures for sample-level classification and thus providing enhanced explainability. The model solves synthetic tasks that conventional models fail at, and achieves best-in-class performance for the classification of tumour type and for predicting microsatellite status. By improving the performance of tasks that require aggregate information from genomic datasets, multiple-instance deep learning may generate biological insight., (© 2023. The Author(s).)