AI-guided Immunoassay Measures Maternal Autoantibodies to Predict Likelihood of Autism Spectrum Disorder

In a recent paper they discussed the creation and validation of a serological assay to identify ASD-specific maternal autoantibody patterns of reactivity against eight previously identified proteins (CRMP1, CRMP2, GDA, NSE, LDHA, LDHB, STIP1, and YBOX) that are highly expressed in developing brain.

The investigators analyzed plasma from 450 mothers of children diagnosed with ASD and from 342 mothers of typically developing children to develop an ELISA test for each of the protein antigens. They then used a machine learning algorithm to determine patterns of highly significant association with ASD and discovered several patterns that were ASD-specific.

Results revealed that the three main patterns associated with MAR ASD were CRMP1 + GDA, CRMP1 + CRMP2, and NSE + STIP1. Additionally, they found that maternal autoantibody reactivity to CRMP1 significantly increased the odds of a child having a higher Autism Diagnostic Observation Schedule (ADOS) severity score.

"The implications from this study are tremendous," said senior author Dr. Judy Van de Water, professor of rheumatology, allergy, and clinical immunology at the University of California, Davis. "It is the first time that machine learning has been used to identify with 100% accuracy MAR ASD-specific patterns as potential biomarkers of ASD risk. We can envision that a woman could have a blood test for these antibodies prior to getting pregnant. If she had them, she would know she would be at very high risk of having a child with autism. If not, she has a 43% lower chance of having a child with autism, as MAR autism is ruled out."

The paper was published in the January 22, 2021, online edition of the journal Molecular Psychiatry.

Related Links:
University of California, Davis