DeepND: Deep multitask learning of gene risk for comorbid neurodevelopmental disorders

Proximity analysis of native proteomes reveals phenotypic modifiers in a mouse model of autism and related neurodevelopmental conditions

One of the main drivers of autism spectrum disorder is risk alleles within hundreds of genes, which may interact within shared but unknown protein complexes. Here we develop a scalable genome-editing-mediated approach to target 14 high-confidence autism risk genes within the mouse brain for proximity-based endogenous proteomics, achieving the identification of high-specificity spatial proteomes. The resulting native proximity proteomes are enriched for human genes dysregulated in the brain of autistic individuals, and reveal proximity interactions between proteins from high-confidence risk genes with those of lower-confidence that may provide new avenues to prioritize genetic risk. Importantly, the datasets are enriched for shared cellular functions and genetic interactions that may underlie the condition. We test this notion by spatial proteomics and CRISPR-based regulation of expression in two autism models, demonstrating functional interactions that modulate mechanisms of their dysregulation. Together, these results reveal native proteome networks in vivo relevant to autism, providing new inroads for understanding and manipulating the cellular drivers underpinning its etiology.

Graph Node Classification to Predict Autism Risk in Genes

This study explores the genetic risk associations with autism spectrum disorder (ASD) using graph neural networks (GNNs), leveraging the Sfari dataset and protein interaction network (PIN) data. We built a gene network with genes as nodes, chromosome band location as node features, and gene interactions as edges. Graph models were employed to classify the autism risk associated with newly introduced genes (test set). Three classification tasks were undertaken to test the ability of our models: binary risk association, multi-class risk association, and syndromic gene association. We tested graph convolutional networks, Graph Sage, graph transformer, and Multi-Layer Perceptron (Baseline) architectures on this problem. The Graph Sage model consistently outperformed the other models, showcasing its utility in classifying ASD-related genes. Our ablation studies show that the chromosome band location and protein interactions contain useful information for this problem. The models achieved 85.80% accuracy on the binary risk classification, 81.68% accuracy on the multi-class risk classification, and 90.22% on the syndromic classification.

Deep Learning for Genomics: From Early Neural Nets to Modern Large Language Models

The data explosion driven by advancements in genomic research, such as high-throughput sequencing techniques, is constantly challenging conventional methods used in genomics. In parallel with the urgent demand for robust algorithms, deep learning has succeeded in various fields such as vision, speech, and text processing. Yet genomics entails unique challenges to deep learning, since we expect a superhuman intelligence that explores beyond our knowledge to interpret the genome from deep learning. A powerful deep learning model should rely on the insightful utilization of task-specific knowledge. In this paper, we briefly discuss the strengths of different deep learning models from a genomic perspective so as to fit each particular task with proper deep learning-based architecture, and we remark on practical considerations of developing deep learning architectures for genomics. We also provide a concise review of deep learning applications in various aspects of genomic research and point out current challenges and potential research directions for future genomics applications. We believe the collaborative use of ever-growing diverse data and the fast iteration of deep learning models will continue to contribute to the future of genomics.