Genomic Algorithms for Identifying Autism
We explore several algorithmic approaches to determining causal variants for detecting autism. These include game theoretic approaches (Shapley values), novel applications of the maximum flow algorithm, family-based statistical studies, and machine learning approaches.
Systematic Sex-Biased Sequencing Errors
This is a large-scale genomics analysis of next-generation sequencing (NGS) datasets from autism case-control and family data. We explore systematic sex biasing errors in modern sequencing technologies for "reading" DNA base pairs from biological samples.
The Gut Microbiome in Autism
This study aims to improve our understanding of the link between gut microbiome functionality, genome variation, and ASD phenotype, and reveal the specific mechanisms by which the gut microbiome interacts with autism-related alleles to produce and modify ASD. We use the 16s sequence-based biomarkers to better capture phylogenetic relationships between microbiome taxa.
This game is a research study for parents of children between the ages of 3 and 12 years. Families who participate in this game are helping researchers in the Wall Lab use machine learning and artificial intelligence to analyze behaviors expressed by children while interacting with family members via home video.
Autism Therapy on Glass
The Wall Lab, the Winograd Lab, and Sension are building a new tool on Google Glass, an interdisciplinary effort bringing together some of the brightest minds in psychiatry, behavioral science, human-computer interaction and artificial intelligence to create an assistive tool for facial emotion recognition. The Autism Glass Project seeks to provide individuals with challenges navigating social cues with a clinically validated therapeutic device to aid in interpreting facial expressions.
Through a collaborative effort that includes researchers from Stanford, UCLA, the New York Genome Center, Cold Spring Harbor Laboratory, and the Simons Foundation, we have amassed a collection of whole genomes and phenotypic measurements on thousands of individuals from families with autism. This platform will help researchers explore connections across data and individuals to more precisely understand autism.
GapMap engages the community of families with autism to capture geographic, diagnostic, and resource usage information to yield a more complete and dynamically updated understanding of autism resource epidemiology.
Home Video Project
This proof of concept project evaluated the feasibility of applying our machine learning classifiers to home videos to evaluate accuracy for detection of autism spectrum disorder in a non-clinical setting.
Our Research Focus
Translating the thinking of systems biology to the field of autism genetics with the intent to develop effective early-stage diagnostics and targets for therapeutic intervention. The work involves the generation and analysis of genomic and phenotypic databases using computational tools of systems biology, machine learning and network inference.
Efforts to understand and characterize the clinical significance and utility of human genetic variation. This work involves clinical-grade annotation of human genetic variation, estimating the rates of both true and false positives in present day genetic testing and their likely impacts on the practice of personalized care, the construction of an authoritative knowledgebase for clinical decision support, and efforts in educating present and future doctors on the potentials of genomics in individualized healthcare.
Computational Disease Analyses
Redefining human diseases through computational and comparative network analysis. The work involves the integration and analysis of transcriptomic, genomic and bibliomic data to network all known human diseases. Deliverables include revealing disease connections, properly reshaping blurred boundaries of classification, and opportunities for drug treatment repositioning.
Our lab is interested in the design and application of translational bioinformatics tools to help bring whole-genomic data to the point of clinical care. Our research projects are designed to complement and potentially supplant standard molecular diagnostics currently being used to characterize a patient’s autoimmune deficiencies and/or complex behavioral disorders, with the intent to have a faster and more robust system in place for real-time genomic diagnostics. (Find out more)