Application of deep learning techniques for de novo generation of molecules, termed as inverse molecular design, has been gaining enormous traction in drug design. The representation of molecules in SMILES notation as a string of characters enables the usage of state of the art models in natural language processing, such as Transformers, for molecular design in general. Inspired by generative pre-training (GPT) models that have been shown to be successful in generating meaningful text, we train a transformer-decoder on the next token prediction task using masked self-attention for the generation of druglike molecules in this study. We show that our model, MolGPT, performs on par with other previously proposed modern machine learning frameworks for molecular generation in terms of generating valid, unique, and novel molecules. Furthermore, we demonstrate that the model can be trained conditionally to control multiple properties of the generated molecules. We also show that the model can be used to generate molecules with desired scaffolds as well as desired molecular properties by conditioning the generation on scaffold SMILES strings of desired scaffolds and property values. Using saliency maps, we highlight the interpretability of the generative process of the model.

Whereas proliferating cells enter M phase shortly after DNA replication, the first M phase of meiosis is preceded by an extended prophase in which homologous chromosomes undergo recombination. Exit from prophase I is controlled by the recombination checkpoint (RC), which, in yeast, represses the meiosis-specific transcription factor Ndt80 required for the expression of B-type cyclins and other M phase regulators. We show that an extended prophase I additionally requires the suppression of latent, mitotic cell-cycle controls by the anaphase-promoting complex (APC/C) and its meiosis-specific activator Ama1, which trigger the degradation of M phase regulators and Ndd1, a subunit of a mitotic transcription factor. ama1Δ mutants exit from prophase I prematurely and independently of the RC, which results in recombination defects and chromosome missegregation. Thus, control of prophase I by meiotic mechanisms depends on the suppression of the alternative, mitotic mechanisms by a meiosis-specific form of the APC/C.

Histopathological images contain morphological markers of disease progression that have diagnostic and predictive values. In this study, we demonstrate how deep learning framework can be used for an automatic classification of Renal Cell Carcinoma (RCC) subtypes, and for identification of features that predict survival outcome from digital histopathological images. Convolutional neural networks (CNN’s) trained on whole-slide images distinguish clear cell and chromophobe RCC from normal tissue with a classification accuracy of 93.39% and 87.34%, respectively. Further, a CNN trained to distinguish clear cell, chromophobe and papillary RCC achieves a classification accuracy of 94.07%. Here, we introduced a novel support vector machine-based method that helped to break the multi-class classification task into multiple binary classification tasks which not only improved the performance of the model but also helped to deal with data imbalance. Finally, we extracted the morphological features from high probability tumor regions identified by the CNN to predict patient survival outcome of most common clear cell RCC. The generated risk index based on both tumor shape and nuclei features are significantly associated with patient survival outcome. These results highlight that deep learning can play a role in both cancer diagnosis and prognosis.

Resting-state functional connectivity (FC) analyses have shown atypical connectivity in autism spectrum disorder (ASD) as compared to typically developing (TD). However, this view emerges from investigating static FC overlooking the whole brain transient connectivity patterns. In our study, we investigated how age and disease influence the dynamic changes in functional connectivity of TD and ASD. We used resting-state functional magnetic resonance imaging (rs-fMRI) data stratified into three cohorts: children (7–11 years), adolescents (12–17 years), and adults (18+ years) for the analysis. The dynamic variability in the connection strength and the modular organization in terms of measures such as flexiblity, cohesion strength, and disjointness were explored for each subject to characterize the differences between ASD and TD. In ASD, we observed significantly higher inter-subject dynamic variability in connection strength as compared to TD. This hyper-variability relates to the symptom severity in ASD. We also found that whole-brain flexibility correlates with static modularity only in TD. Further, we observed a core-periphery organization in the resting-state, with Sensorimotor and Visual regions in the rigid core; and DMN and attention areas in the flexible periphery. TD also develops a more cohesive organization of sensorimotor areas. However, in ASD we found a strong positive correlation of symptom severity with flexibility of rigid areas and with disjointness of sensorimotor areas. The regions of the brain showing high predictive power of symptom severity were distributed across the cortex, with stronger bearings in the frontal, motor, and occipital cortices. Our study demonstrates that the dynamic framework best characterizes the variability in ASD.

Entry into mitosis is triggered by activation of Cdk1 and inactivation of its counteracting phosphatase PP2A/B55. Greatwall kinase inactivates PP2A/B55 via its substrates Ensa and ARPP19. Both Greatwall and Ensa/ARPP19 are regulated by phosphorylation, but the dynamic regulation of Greatwall activity and the phosphatases that control Greatwall kinase and its substrates are poorly understood. To address these questions we applied a combination of mathematical modelling and experiments using phospho-specific antibodies to monitor Greatwall, Ensa/ARPP19 and Cdk substrate phosphorylation during mitotic entry and exit. We demonstrate that PP2A/B55 is required for Gwl dephosphorylation at the essential Cdk site Thr194. Ensa/ARPP19 dephosphorylation is mediated by the RNA Polymerase II carboxy terminal domain phosphatase Fcp1. Surprisingly, inhibition or depletion of neither Fcp1 nor PP2A appears to block dephosphorylation of the bulk of mitotic Cdk1 substrates during mitotic exit. Taken together our results suggest a hierarchy of phosphatases coordinating Greatwall, Ensa/ARPP19 and Cdk substrate dephosphorylation during mitotic exit.