arXiv subjects

Linus Bao

Publications and source records attributed to Linus Bao.

3 recordsLinked to original sources

arXiv2026

Causal multi-modal AI for personalized chemosensitivity prediction

Chemotherapy improves survival for some patients with breast cancer, but doctors cannot reliably predict who. Current guidelines rely on recurrence scores as a proxy for treatment benefit, which may contribute to the overprescription of chemotherapy. Here we present a causal multi-modal AI model that predicts personalized chemosensitivity using routinely collected pathology and clinical information. We developed our model on a multi-national dataset of 9,141 patients (twelve cohorts, nine countries) and evaluated it on another 1,994 patients (five cohorts, three countries). The model generated treatment-specific recurrence probabilities for each patient, with near-perfect calibration and strong prognostic discrimination across both 5- and 10-year follow-up horizons. Moreover, its chemotherapy benefit predictions demonstrated robust predictive performance, and out-performed existing recurrence-score-based tests. Compared to the standard of care, using the model to support personally tailored therapeutic decisions could reduce the number of patients receiving chemotherapy by 30% while achieving the same recurrence-free rate. Tumors predicted to be highly chemosensitive displayed concordant molecular and morphological programs of proliferation, cell cycle progression, and replication stress. The model's predictive capabilities transferred zero-shot to non-breast cancers, indicating our causal multi-modal AI approach may provide a universal strategy to predict treatment outcomes across cancer types.

cs.AI↗

arXiv2025

Homomorphism Counts as Structural Encodings for Graph Learning

Graph Transformers are popular neural networks that extend the well-known Transformer architecture to the graph domain. These architectures operate by applying self-attention on graph nodes and incorporating graph structure through the use of positional encodings (e.g., Laplacian positional encoding) or structural encodings (e.g., random-walk structural encoding). The quality of such encodings is critical, since they provide the necessary $\textit{graph inductive biases}$ to condition the model on graph structure. In this work, we propose $\textit{motif structural encoding}$ (MoSE) as a flexible and powerful structural encoding framework based on counting graph homomorphisms. Theoretically, we compare the expressive power of MoSE to random-walk structural encoding and relate both encodings to the expressive power of standard message passing neural networks. Empirically, we observe that MoSE outperforms other well-known positional and structural encodings across a range of architectures, and it achieves state-of-the-art performance on a widely studied molecular property prediction dataset.

cs.LG↗

arXiv2023

Transfer systems for rank two elementary Abelian groups: characteristic functions and matchstick games

We prove that Hill's characteristic function $χ$ for transfer systems on a lattice $P$ surjects onto interior operators for $P$. Moreover, the fibers of $χ$ have unique maxima which are exactly the saturated transfer systems. In order to apply this theorem in examples relevant to equivariant homotopy theory, we develop the theory of saturated transfer systems on modular lattices, ultimately producing a ``matchstick game'' that puts saturated transfer systems in bijection with certain structured subsets of covering relations. After an interlude developing a recursion for transfer systems on certain combinations of bounded posets, we apply these results to determine the full lattice of transfer systems for rank two elementary Abelian groups.

math.AT↗