Neotropical Melyroidea group cockroaches reveal various degrees of (eu)sociality.

Eusociality in its various degrees represents an animal social system characterised by cooperative brood care, differentiation into castes and generational overlap. The fossil record indicates that eusociality is likely to have originated in hymenopterans and blattodeans during the Cretaceous. In this study, we present findings from surveys in Peruvian (Villa Carmen) and Ecuadorian (Rio Bigal, El Reventador) cloud forests revealing the first extant cockroach species living in complex, structured groups (n = 90-200 individuals, ˃ 20 adults). We observed and described behaviours that suggest the existence of cooperative care, nest guarding, nest chamber preparation within hardwood Casearia sp. (Salicaceae) and bamboo (Bambusoideae), multiple overlapping generations ('different stages of' instars), colony translocation, possibly a sole reproductive female (1.25 times larger white 'queen', but no potential 'king' observed), and morphologically diversified immature stages. In order to define the lineage where this type of sociality originated and occurs, the forms of Melyroidea magnifica Shelford, 1912, M. ecuadoriana sp. n., M. mimetica Shelford, 1912 and an undescribed species from Peru are also described in a separate section of this study. Blattoid morphological characteristics such as typical styli suggest categorisation within distinct Oulopterygidae (Rehn, 1951), outside Corydiidae Saussure 1864. Transitional advanced sociality or semisociality in related Aclavoidea socialis gen. et sp. n. is documented in a rotting stump (n = 80 individuals, few adults). Close phylogenetic relation between the genera, conserved morphology of numerous characters and their diverse feeding strategies generally lacking specialisation suggests a rather recent origin of a social way of life in this group. Eusociality in invertebrates and vertebrates can thus originate in various phylogenetical and ecological trajectories including predation, parasitism, care for herbs and the new one, documented through diet shift from detritivory to fungivory and algaevory. Interdisciplinary approaches reveal the low degree of knowledge of rainforest ecosystems, with fundamental groups remaining still systematically and also behaviourally undescribed.

Validation of MSIntuit as an AI-based pre-screening tool for MSI detection from colorectal cancer histology slides.

Mismatch Repair Deficiency (dMMR)/Microsatellite Instability (MSI) is a key biomarker in colorectal cancer (CRC). Universal screening of CRC patients for MSI status is now recommended, but contributes to increased workload for pathologists and delayed therapeutic decisions. Deep learning has the potential to ease dMMR/MSI testing and accelerate oncologist decision making in clinical practice, yet no comprehensive validation of a clinically approved tool has been conducted. We developed MSIntuit, a clinically approved artificial intelligence (AI) based pre-screening tool for MSI detection from haematoxylin-eosin (H&E) stained slides. After training on samples from The Cancer Genome Atlas (TCGA), a blind validation is performed on an independent dataset of 600 consecutive CRC patients. Inter-scanner reliability is studied by digitising each slide using two different scanners. MSIntuit yields a sensitivity of 0.96-0.98, a specificity of 0.47-0.46, and an excellent inter-scanner agreement (Cohen's κ: 0.82). By reaching high sensitivity comparable to gold standard methods while ruling out almost half of the non-MSI population, we show that MSIntuit can effectively serve as a pre-screening tool to alleviate MSI testing burden in clinical practice.