Avlant Nilsson

Biologically informed neural network models are robust to spurious interactions via self-pruning

This paper introduces a method to evaluate the robustness of biology-informed neural networks by measuring their ability to prune spurious interactions during training.

scLEMBAS: Context-Aware Modeling of Signaling Pathway Activity at Single-Cell Resolution

scLEMBAS models signaling pathway activity at single-cell resolution using a context-aware neural network to predict perturbation responses and capture cell-type-specific interactions.

Library-based single-cell analysis of CAR signaling reveals drivers of in vivo persistence

The paper uses single-cell sequencing to analyze CAR signaling and identifies ICD architectures that promote durable in vivo persistence in liquid tumors.

Inference of drug off-target effects on cellular signaling using Interactome-Based Deep Learning

The paper develops a deep learning model to infer drug-target interactions and their downstream effects on cellular signaling, outperforming basic machine learning approaches and validating predictions with an independent dataset.

Autoencoder Model for Translating Omics Signatures

The paper develops AutoTransOP, an autoencoder framework to translate omics signatures across species and contexts, outperforming existing methods in identifying predictive molecular features.

Artificial neural networks enable genome-scale simulations of intracellular signaling

The paper develops a recurrent neural network to simulate intracellular signaling by predicting transcription factor activity from ligand concentrations, validated with synthetic and experimental data.