Sexual selection and intelligence: Does sexual reproduction drive the evolution of intelligence?

The basal hypothesis discussed here is the idea that brain architecture could be plastic on a very basal, genetic level due to sexual recombination and reassortment of alleles of genes related to brain development, e.g., neuronal cell adhesion molecules (NCAMs) and others.The role of sexual reassortment leads the study of brain development, species behavior and intelligence to a new version of the so-called “Red Queen Hypothesis”: using the mechanism described here, a kind of runaway selection mechanism seems to arise. Even if NCAMs are almost constant within an individual, they seem to act very differently at the population level and so the role of reassorting polymorphic NCAM- (and other) genes gets particularly clear. If several NCAM-NCAM combinations cause extreme behavior and intelligence variability in a population, these combinations also represent a use of sexual selection. This mechanism of NCAM allele assortment seems to be important for the process of speciation by mutual selection of individuals. Therefore NCAM variants and their associated behaviors are thought to be important for the development of intelligence, in that they promote the attraction of individuals with already high intelligence, leading to the speciation of super-intelligent groups.     

Meniscal lesion detection and characterization in adult knee MRI: A deep learning model approach with external validation

PurposeEvaluation of a deep learning approach for the detection of meniscal tears and their characterization (presence/absence of migrated meniscal fragment).MethodsA large annotated adult knee MRI database was built combining medical expertise of radiologists and data scientists’ tools. Coronal and sagittal proton density fat suppressed-weighted images of 11,353 knee MRI examinations (10,401 individual patients) paired with their standardized structured reports were retrospectively collected. After database curation, deep learning models were trained and validated on a subset of 8058 examinations. Algorithm performance was evaluated on a test set of 299 examinations reviewed by 5 musculoskeletal specialists and compared to general radiologists’ reports. External validation was performed using the publicly available MRNet database. Receiver Operating Characteristic (ROC) curves results and Area Under the Curve (AUC) values were obtained on internal and external databases.ResultsA combined architecture of meniscal localization and lesion classification 3D convolutional neural networks reached AUC values of 0.93 (95% CI 0.82, 0.95) for medial and 0.84 (95% CI 0.78, 0.89) for lateral meniscal tear detection, and 0.91 (95% CI 0.87, 0.94) for medial and 0.95 (95% CI 0.92, 0.97) for lateral meniscal tear migration detection. External validation of the combined medial and lateral meniscal tear detection models resulted in an AUC of 0.83 (95% CI 0.75, 0.90) without further training and 0.89 (95% CI 0.82, 0.95) with fine tuning.ConclusionOur deep learning algorithm demonstrated high performance in knee menisci lesion detection and characterization, validated on an external database.     

Chemical language models for de novo drug design: Challenges and opportunities

Generative deep learning is accelerating de novo drug design, by allowing the generation of molecules with desired properties on demand. Chemical language models – which generate new molecules in the form of strings using deep learning – have been particularly successful in this endeavour. Thanks to advances in natural language processing methods and interdisciplinary collaborations, chemical language models are expected to become increasingly relevant in drug discovery. This minireview provides an overview of the current state-of-the-art of chemical language models for de novo design, and analyses current limitations, challenges, and advantages. Finally, a perspective on future opportunities is provided.