An integrated systems biology and machine learning framework for identifying potential biomarkers and pathways in autism spectrum disorder
Sara Hosseinpoor, Hakimeh Zali, Hassan Zohrevand, Seyed Amir Mirmotalebisohi, Fariba Khodagholi, Maryam Bazrgar, Sareh Asadi, Abolhassan Ahmadiani · 2026
Read An integrated systems biology and machine learning framework for identifying potential biomarkers and pathways in autism spectrum disorder by Sara Hosseinpoor, Hakimeh Zali, Hassan Zohrevand, Seyed Amir Mirmotalebisohi, Fariba Khodagholi, Maryam Bazrgar, Sareh Asadi, Abolhassan Ahmadiani (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/plos-pone-0355984.txt.
Description
Sara Hosseinpoor and colleagues layered systems biology and machine learning over blood gene data to nominate molecular leads for autism spectrum disorder. Their 2026 study combined differential expression and gene co-expression networks. It added protein interaction maps and two feature selection algorithms. The winners were then checked in a rat model of autism induced by a prenatal drug exposure.
Two genes survived every filter: TLR8, an immune sensor, and CASP4, an inflammation-linked executioner protein. Both ran higher in the model animals. TLR8 rose in blood and brain, and CASP4 in brain alone. Network analysis attached a few small regulatory RNAs to each. The authors frame the pair as candidate biomarkers. Their immune flavor reinforces the view of autism as partly an immune story.
Catalog record
| CREATOR | Sara Hosseinpoor, Hakimeh Zali, Hassan Zohrevand, Seyed Amir Mirmotalebisohi, Fariba Khodagholi, Maryam Bazrgar, Sareh Asadi, Abolhassan Ahmadiani |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 49458 |
| LICENSE | CC_BY |
| RIGHTS | CC BY |
| SOURCE | PLOS |