Nadine Fornelos

A foundational neuronal protein network model unifying multimodal genetic, transcriptional, and proteomic perturbations in schizophrenia.

The paper identifies three neuron-specific schizophrenia protein networks enriched for genetic and transcriptional perturbations and validates their disruption in 22q11.2 deletion carriers.

Interaction studies of risk proteins in human induced neurons reveal convergent biology and novel mechanisms underlying autism spectrum disorders

The paper identifies a protein-protein interaction network in human excitatory neurons for 13 ASD risk genes, revealing novel interactions and convergent mechanisms contributing to autism spectrum disorders.

Genoppi: an open-source software for robust and standardized integration of proteomic and genetic data

Genoppi integrates proteomic and genetic data to identify cell-type-specific interactions and their role in disease.

Systematic auditing is essential to debiasing machine learning in biology

This paper introduces a systematic auditing framework to identify biases in machine learning applications in biology, showing that biases can hinder model generalizability and lead to poor performance when training data lacks sufficient signal.