Simplified, interpretable graph convolutional neural networks for small molecule activity prediction

We here present a streamlined, explainable graph convolutional neural network (gCNN) architecture for small molecule activity prediction. We first conduct a hyperparameter optimization across nearly 800 protein targets that produces a simplified gCNN QSAR architecture, and we observe that such a model can yield performance improvements over both standard gCNN and RF methods on difficult-to-classify test sets. Additionally, we discuss how reductions in convolutional layer dimensions potentially speak to the “anatomical” needs of gCNNs with respect to radial coarse graining of molecular substructure. We augment this simplified architecture with saliency map technology that highlights molecular substructures relevant to activity, and we perform saliency analysis on nearly 100 data-rich protein targets. We show that resultant substructural clusters are useful visualization tools for understanding substructure-activity relationships. We go on to highlight connections between our models’ saliency predictions and observations made in the medicinal chemistry literature, focusing on four case studies of past lead finding and lead optimization campaigns.

The Demographics Behind the Courage to Tell for Survivors: Child Sexual Abuse Experiences in Kenya

Child Sexual Abuse (CSA) is both a global and national social issue, as well as an epidemic in various societies. Non-disclosure of CSA only worsens and extends survivors’ suffering, and CSA’s long-term effects can be devastating. Several studies have been done in the field of CSA and its health implications but rarely have previous studies addressed child sexual abuse disclosure (CSAD). The current study aimed at examining child factors of CSAD at Thika Level 5 Hospital (TL5H) in Kiambu County, Kenya. The study is a case study using a phenomenology approach where the primary data was collected from the sexual abuse survivors and caregivers using a mixed-method analysis. Interviews were conducted with 30 CSA survivors, 25 girls, and 5 boys: 5-17 years. The study utilised the convergent QUAL (investigative open-ended questions and storytelling) design with a Quan component (structured survey) to identify CSA survivors’ experiences while receiving medical treatment and therapeutic intervention at TL5H. Descriptive and thematic approaches were applied to analyse qualitative data that revealed survivors’ lived experiences with CSA. Informed by Bronfenbrenner’s Socio-Ecological Model (SEM), saliency analysis was applied to code the recurring and important themes from the data in order to identify which child factors. Survivors gave detailed accounts of types of threats and manipulation applied by perpetrators to stop them from disclosing abuse. Survivors said disclosing or not disclosing helped them cope with abuse trauma. Quantitative results revealed that 58% of the survivors who completed the disclosure process aged between 9-13 years, 83.3% were female, and 70% had achieved a lower level of education.

Designing Interpretable Convolution-Based Hybrid Networks for Genomics

Hybrid networks that build upon convolutional layers with attention mechanisms have demonstrated improved performance relative to pure convolutional networks across many regulatory genome analysis tasks. Their inductive bias to learn long-range interactions provides an avenue to identify learned motif-motif interactions. For attention maps to be interpretable, the convolutional layer(s) must learn identifiable motifs. Here we systematically investigate the extent that architectural choices in convolution-based hybrid networks influence learned motif representations in first layer filters, as well as the reliability of their attribution maps generated by saliency analysis. We find that design principles previously identified in standard convolutional networks also generalize to hybrid networks. This work provides an avenue to narrow the spectrum of architectural choices when designing hybrid networks such that they are amenable to commonly used interpretability methods in genomics.

Airport Detection-Based Cosaliency on Remote Sensing Images

This paper proposes a contour extraction model based on cosaliency detection for remote sensing image airport detection and improves the traditional line segmentation detection (LSD) algorithm to make it more suitable for the goal of this paper. Our model consists of two parts, a cosaliency detection module and a contour extraction module. In the first part, the cosaliency detection module mainly uses the network framework of Visual Geometry Group-19 (VGG-19) to obtain the result maps of the interimage comparison and the intraimage consistency, and then the two result maps are multiplied pixel by pixel to obtain the cosaliency mask. In the second part, the contour extraction module uses superpixel segmentation and parallel line segment detection (PLSD) to refine the airport contour and runway information to obtain the preprocessed result map, and then we merge the result of cosaliency detection with the preprocessed result to obtain the final airport contour. We compared the model proposed in this article with four commonly used methods. The experimental results show that the accuracy of the model is 15% higher than that of the target detection result based on the saliency model, and the accuracy of the active contour model based on the saliency analysis is improved by 1%. This shows that the model proposed in this paper can extract a contour that closely matches the actual target.

Modular machine learning for Alzheimer's disease classification from retinal vasculature

Alzheimer's disease is the leading cause of dementia. The long progression period in Alzheimer's disease provides a possibility for patients to get early treatment by having routine screenings. However, current clinical diagnostic imaging tools do not meet the specific requirements for screening procedures due to high cost and limited availability. In this work, we took the initiative to evaluate the retina, especially the retinal vasculature, as an alternative for conducting screenings for dementia patients caused by Alzheimer's disease. Highly modular machine learning techniques were employed throughout the whole pipeline. Utilizing data from the UK Biobank, the pipeline achieved an average classification accuracy of 82.44%. Besides the high classification accuracy, we also added a saliency analysis to strengthen this pipeline's interpretability. The saliency analysis indicated that within retinal images, small vessels carry more information for diagnosing Alzheimer's diseases, which aligns with related studies.