Biology subjects

Occhetta, M.

Publications and source records attributed to Occhetta, M..

3 recordsLinked to original sources

bioRxiv2026

Macrophage signature-based prediction of cancer treatment response using MIL-attention

Predicting immunotherapy response from single-cell data remains difficult due to patient-level labels, extreme class imbalance, and highly heterogeneous macrophage states. We present a Multiple Instance Learning (MIL) framework that treats each patient as a bag of macrophage embeddings derived from a single-cell RNA foundation model. The architecture incorporates an attention-based pooling mechanism with reduced model complexity, dropout-enhanced regularization and explicit attention penalties to improve stability in small-sample regimes. To address imbalanced clinical datasets, MIL outputs are optimized with a combined focal loss and supervised contrastive objective that simultaneously sharpens class boundaries and improves representation clustering. Across three cancer datasets, this approach outperforms pseudobulk aggregation, embedding baselines and standard MIL variants. Attention-weighted attribution and transcriptional regulatory analysis reveal distinct macrophage programs, interferon and antigen-presentation networks in responders versus hypoxia-linked regulatory modules in non-responders. This shows the potential of MIL to uncover predictive and mechanistically interpretable immune states.

bioinformatics↗

bioRxiv2025

MORGaN: self-supervised multi-relational graph learning for druggable gene discovery

Identifying therapeutically tractable targets remains difficult, partly because disease biology is distributed across multiple molecular layers and relation types, while labeled data are scarce. We present MORGaN, a self-supervised framework for node classification on multi-omic, multi-relation gene networks that learns structure-aware embeddings and outputs calibrated scores to prioritize therapeutic targets. On a pan-cancer graph integrating TCGA multi-omics and diverse biological relation types, MORGaN outperforms state-of-the-art biological node classification models across metrics (AUPR: 0.815 [->] 0.888; +9%). Ablation studies highlight that both relation diversity and the in-layer fusion architecture are necessary for these gains. Prioritized targets are biologically coherent: high-confidence hits are enriched for pharmaceutically tractable families and ligand-receptor signaling cascades. Post hoc explainability analyses recover compact, pathway-consistent motifs around both known and putative novel targets, and concordance with external resources further supports plausibility. MORGaN thus delivers label-efficient, interpretable node classification for target discovery and can be readily adapted to other diseases, other species, and other node classification tasks. Code and documentation are available at this link.

bioinformatics↗

bioRxiv2024

PertEval-scFM: Benchmarking Single-Cell Foundation Models for Perturbation Effect Prediction

In silico modeling of transcriptional responses to perturbations is crucial for advancing our understanding of cellular processes and disease mechanisms. We present PertEval-scFM, a standardized framework designed to evaluate models for perturbation effect prediction. We apply PertEval-scFM to benchmark zero-shot single-cell foundation model (scFM) embeddings against base-line models to assess whether these contextualized representations enhance perturbation effect prediction. Our results show that scFM embeddings do not provide consistent improvements over baseline models, especially under distribution shift. Overall, this study provides a systematic evaluation of zero-shot scFM embeddings for perturbation effect prediction, highlighting the challenges of this task and revealing the limitations of current-generation scFMs. Our findings underscore the need for specialized models and high-quality datasets that capture a broader range of cellular states. Source code and documentation can be found at: https://github.com/aaronwtr/PertEval.

bioinformatics↗