Real-World Molecular Out-Of-Distribution: Specification and Investigation.

This study presents a rigorous framework for investigating molecular out-of-distribution (MOOD) generalization in drug discovery. The concept of MOOD is first clarified through a problem specification that demonstrates how the covariate shifts encountered during real-world deployment can be characterized by the distribution of sample distances to the training set. We find that these shifts can cause performance to drop by up to 60% and uncertainty calibration by up to 40%. This leads us to propose a splitting protocol that aims to close the gap between the deployment and testing. Then, using this protocol, a thorough investigation is conducted to assess the impact of model design, model selection, and data set characteristics on MOOD performance and uncertainty calibration. We find that appropriate representations and algorithms with built-in uncertainty estimation are crucial to improving performance and uncertainty calibration. This study sets itself apart by its exhaustiveness and opens an exciting avenue to benchmark meaningful algorithmic progress in molecular scoring.

On the robustness of generalization of drug-drug interaction models.

BACKGROUND: Deep learning methods are a proven commodity in many fields and endeavors. One of these endeavors is predicting the presence of adverse drug-drug interactions (DDIs). The models generated can predict, with reasonable accuracy, the phenotypes arising from the drug interactions using their molecular structures. Nevertheless, this task requires improvement to be truly useful. Given the complexity of the predictive task, an extensive benchmarking on structure-based models for DDIs prediction was performed to evaluate their drawbacks and advantages. RESULTS: We rigorously tested various structure-based models that predict drug interactions using different splitting strategies to simulate different real-world scenarios. In addition to the effects of different training and testing setups on the robustness and generalizability of the models, we then explore the contribution of traditional approaches such as multitask learning and data augmentation. CONCLUSION: Structure-based models tend to generalize poorly to unseen drugs despite their ability to identify new DDIs among drugs seen during training accurately. Indeed, they efficiently propagate information between known drugs and could be valuable for discovering new DDIs in a database. However, these models will most probably fail when exposed to unknown drugs. While multitask learning does not help in our case to solve the problem, the use of data augmentation does at least mitigate it. Therefore, researchers must be cautious of the bias of the random evaluation scheme, especially if their goal is to discover new DDIs.

Convolutional Neural Networks for Spectroscopic Analysis in Retinal Oximetry.

Retinal oximetry is a non-invasive technique to investigate the hemodynamics, vasculature and health of the eye. Current techniques for retinal oximetry have been plagued by quantitatively inconsistent measurements and this has greatly limited their adoption in clinical environments. To become clinically relevant oximetry measurements must become reliable and reproducible across studies and locations. To this end, we have developed a convolutional neural network algorithm for multi-wavelength oximetry, showing a greatly improved calculation performance in comparison to previously reported techniques. The algorithm is calibration free, performs sensing of the four main hemoglobin conformations with no prior knowledge of their characteristic absorption spectra and, due to the convolution-based calculation, is invariable to spectral shifting. We show, herein, the dramatic performance improvements in using this algorithm to deduce effective oxygenation (SO2), as well as the added functionality to accurately measure fractional oxygenation ([Formula: see text]). Furthermore, this report compares, for the first time, the relative performance of several previously reported multi-wavelength oximetry algorithms in the face of controlled spectral variations. The improved ability of the algorithm to accurately and independently measure hemoglobin concentrations offers a high potential tool for disease diagnosis and monitoring when applied to retinal spectroscopy.

The gametic synapse: RNA transfer to the bovine oocyte.

Even after several decades of quiescent storage in the ovary, the female germ cell is capable of reinitiating transcription to build the reserves that are essential to support early embryonic development. In the current model of mammalian oogenesis, there exists bilateral communication between the gamete and the surrounding cells that is limited to paracrine signaling and direct transfer of small molecules via gap junctions existing at the end of the somatic cells' projections that are in contact with the oolemma. The purpose of this work was to explore the role of cumulus cell projections as a means of conductance of large molecules, including RNA, to the mammalian oocyte. By studying nascent RNA with confocal and transmission electron microscopy in combination with transcript detection, we show that the somatic cells surrounding the fully grown bovine oocyte contribute to the maternal reserves by actively transferring large cargo, including mRNA and long noncoding RNA. This occurrence was further demonstrated by the reconstruction of cumulus-oocyte complexes with transfected cumulus cells transferring a synthetic transcript. We propose selective transfer of transcripts occurs, the delivery of which is supported by a remarkable synapselike vesicular trafficking connection between the cumulus cells and the gamete. This unexpected exogenous contribution to the maternal stores offers a new perspective on the determinants of female fertility.