Detection of Outdated Structural Priors in the Discrete Cosine Transformation-based Electrical Impedance Tomography Algorithm

Morphological prior information incorporated with the discrete cosine transformation (DCT) based electrical impedance tomography (EIT) algorithm can improve the interpretability of EIT reconstructions in clinical applications. However, an outdated structural prior can yield a misleading reconstruction compromising the accuracy of the clinical diagnosis and the appropriate treatment decision. In this contribution, we propose a redistribution index scaled between 0 and 1 to quantify the possible error in a DCT-based EIT reconstruction influenced by structural prior information. Two simulation models of different tissue atelectasis and collapsed ratios were investigated. Outdated and updated structural prior information were applied to obtain different EIT reconstructions using this simulated data, with which the redistribution index was calculated and compared. When the difference between prior and reality (the redistribution index) became larger and exceeded a threshold, this was considered as an indicator of an outdated prior information. The evaluation result shows the potential of the redistribution index to detect outdated prior information in a DCT-based EIT algorithm.

A Deep Generative Model Enables Automated Structure Elucidation of Novel Psychoactive Substances

Over the past decade, the illicit drug market has been reshaped by the proliferation of clandestinely produced designer drugs. These agents, referred to as new psychoactive substances (NPSs), are designed to mimic the physiological actions of better-known drugs of abuse while skirting drug control laws. The public health burden of NPS abuse obliges toxicological, police, and customs laboratories to screen for them in law enforcement seizures and biological samples. However, the identification of emerging NPSs is challenging due to the chemical diversity of these substances and the fleeting nature of their appearance on the illicit market. Here, we present DarkNPS, a deep learning-enabled approach to automatically elucidate the structures of unidentified designer drugs using only mass spectrometric data. Our method employs a deep generative model to learn a statistical probability distribution over unobserved structures, which we term the structural prior. We show that the structural prior allows DarkNPS to elucidate the exact chemical structure of an unidentified NPS with an accuracy of 51%, and a top-10 accuracy of 78%. Our generative approach has the potential to enable de novo structure elucidation for other types of small molecules that are routinely analyzed by mass spectrometry.

A Deep Generative Model Enables Automated Structure Elucidation of Novel Psychoactive Substances

Over the past decade, the illicit drug market has been reshaped by the proliferation of clandestinely produced designer drugs. These agents, referred to as new psychoactive substances (NPSs), are designed to mimic the physiological actions of better-known drugs of abuse while skirting drug control laws. The public health burden of NPS abuse obliges toxicological, police, and customs laboratories to screen for them in law enforcement seizures and biological samples. However, the identification of emerging NPSs is challenging due to the chemical diversity of these substances and the fleeting nature of their appearance on the illicit market. Here, we present DarkNPS, a deep learning-enabled approach to automatically elucidate the structures of unidentified designer drugs using only mass spectrometric data. Our method employs a deep generative model to learn a statistical probability distribution over unobserved structures, which we term the structural prior. We show that the structural prior allows DarkNPS to elucidate the exact chemical structure of an unidentified NPS with an accuracy of 51%, and a top-10 accuracy of 78%. Our generative approach has the potential to enable de novo structure elucidation for other types of small molecules that are routinely analyzed by mass spectrometry.

Pre-training RNNs on ecologically relevant tasks explains sub-optimal behavioral reset

When faced with a new task, animals′ cognitive capabilities are determined both by individual experience and by structural priors evolved to leverage the statistics of natural environments. Rats can quickly learn to capitalize on the trial sequence correlations of two-alternative forced choice (2AFC) tasks after correct trials, but consistently deviate from optimal behavior after error trials, when they waive the accumulated evidence. To understand this outcome-dependent gating, we first show that Recurrent Neural Networks (RNNs) trained in the same 2AFC task outperform animals as they can readily learn to use previous trials′ information both after correct and error trials. We hypothesize that, while RNNs can optimize their behavior in the 2AFC task without a priori restrictions, rats′ strategy is constrained by a structural prior adapted to a natural environment in which rewarded and non-rewarded actions provide largely asymmetric information. When pre-training RNNs in a more ecological task with more than two possible choices, networks develop a strategy by which they gate off the across-trial evidence after errors, mimicking rats′ behavior. Our results suggest that the observed suboptimal behavior reflects the influence of a structural prior that, adaptive in a natural multi-choice environment, constrains performance in a 2AFC laboratory task.

Transferring structural knowledge across cognitive maps in humans and models

Relations between task elements often follow hidden underlying structural forms such as periodicities or hierarchies, whose inferences fosters performance. However, transferring structural knowledge to novel environments requires flexible representations that are generalizable over particularities of the current environment, such as its stimuli and size. We suggest that humans represent structural forms as abstract basis sets and that in novel tasks, the structural form is inferred and the relevant basis set is transferred. Using a computational model, we show that such representation allows inference of the underlying structural form, important task states, effective behavioural policies and the existence of unobserved state-trajectories. In two experiments, participants learned three abstract graphs during two successive days. We tested how structural knowledge acquired on Day-1 affected Day-2 performance. In line with our model, participants who had a correct structural prior were able to infer the existence of unobserved state-trajectories and appropriate behavioural policies.