A distribution over instances of a sampling problem is said to exhibit transport disorder chaos if perturbing the instance by a small amount of random noise dramatically changes the stationary distribution (in Wasserstein distance). Seeking to provide evidence that some sampling tasks are hard on average, a recent line of work has demonstrated that disorder chaos is sufficient to rule out “stable” sampling algorithms, such as gradient methods and some diffusion processes. We demonstrate that disorder chaos does not preclude polynomial-time sampling by canonical algorithms in canonical models. We show that with high probability over a random graph $\mathbf{G} \sim G(n,1/2)$: (1) the hardcore model (at fugacity $\lambda = 1$) on $\mathbf{G}$ exhibits disorder chaos, and (2) Glauber dynamics run for $O(n)$ time can approximately sample from the hardcore model on $\mathbf{G}$ (in Wasserstein distance).

Hang Jiang, Xiajie Zhang, Robert Mahari, Daniel Kessler, Eric Ma, Tal August, Irene Li, Alex Pentland, Yoon Kim, Deb Roy, Jad Kabbara. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.

Geometric deep learning has broad applications in biology, a domain where relational structure in data is often intrinsic to modelling the underlying phenomena. Currently, efforts in both geometric deep learning and, more broadly, deep learning applied to biomolecular tasks have been hampered by a scarcity of appropriate datasets accessible to domain specialists and machine learning researchers alike. To address this, we introduce Graphein as a turn-key tool for transforming raw data from widely-used bioinformatics databases into machine learning-ready datasets in a high-throughput and flexible manner. Graphein is a Python library for constructing graph and surface-mesh representations of biomolecular structures, such as proteins, nucleic acids and small molecules, and biological interaction networks for computational analysis and machine learning. Graphein provides utilities for data retrieval from widely-used bioinformatics databases for structural data, including the Protein Data Bank, the AlphaFold Structure Database, chemical data from ZINC and ChEMBL, and for biomolecular interaction networks from STRINGdb, BioGrid, TRRUST and RegNetwork. The library interfaces with popular geometric deep learning libraries: DGL, Jraph, PyTorch Geometric and PyTorch3D though remains framework agnostic as it is built on top of the PyData ecosystem to enable inter-operability with scientific computing tools and libraries. Graphein is designed to be highly flexible, allowing the user to specify each step of the data preparation, scalable to facilitate working with large protein complexes and interaction graphs, and contains useful pre-processing tools for preparing experimental files. Graphein facilitates network-based, graph-theoretic and topological analyses of structural and interaction datasets in a high-throughput manner. We envision that Graphein will facilitate developments in computational biology, graph representation learning and drug discovery. Availability and implementation: Graphein is written in Python. Source code, example usage and tutorials, datasets, and documentation are made freely available under the MIT License at the following URL: https://anonymous.4open.science/r/graphein-3472/README.md

Chimeric antigen receptor (CAR) T-cell therapy is potentially an effective targeted immunotherapy for glioblastoma, yet there is presently little known about the efficacy of CAR T-cell treatment when combined with the widely used anti-inflammatory and immunosuppressant glucocorticoid, dexamethasone. Here we present a mathematical model-based analysis of three patient-derived glioblastoma cell lines treated in vitro with CAR T-cells and dexamethasone. Advanced in vitro experimental cell killing assay technologies allow for highly resolved temporal dynamics of tumor cells treated with CAR T-cells and dexamethasone, making this a valuable model system for studying the rich dynamics of nonlinear biological processes with translational applications. We model the system as a nonautonomous, two-species predator-prey interaction of tumor cells and CAR T-cells, with explicit time-dependence in the clearance rate of dexamethasone. Using time as a bifurcation parameter, we show that (1) dexamethasone destabilizes coexistence equilibria between CAR T-cells and tumor cells in a dose-dependent manner and (2) as dexamethasone is cleared from the system, a stable coexistence equilibrium returns in the form of a Hopf bifurcation. With the model fit to experimental data, we demonstrate that high concentrations of dexamethasone antagonizes CAR T-cell efficacy by exhausting, or reducing the activity of CAR T-cells, and by promoting tumor cell growth. Finally, we identify a critical threshold in the ratio of CAR T-cell death to CAR T-cell proliferation rates that predicts eventual treatment success or failure that may be used to guide the dose and timing of CAR T-cell therapy in the presence of dexamethasone in patients.

We present Peax, a novel feature-based technique for interactive visual pattern search in sequential data, like time series or data mapped to a genome sequence. Visually searching for patterns by similarity is often challenging because of the large search space, the visual complexity of patterns, and the user's perception of similarity. For example, in genomics, researchers try to link patterns in multivariate sequential data to cellular or pathogenic processes, but a lack of ground truth and high variance makes automatic pattern detection unreliable. We have developed a convolutional autoencoder for unsupervised representation learning of regions in sequential data that can capture more visual details of complex patterns compared to existing similarity measures. Using this learned representation as features of the sequential data, our accompanying visual query system enables interactive feedback-driven adjustments of the pattern search to adapt to the users' perceived similarity. Using an active learning sampling strategy, Peax collects user-generated binary relevance feedback. This feedback is used to train a model for binary classification, to ultimately find other regions that exhibit patterns similar to the search target. We demonstrate Peax's features through a case study in genomics and report on a user study with eight domain experts to assess the usability and usefulness of Peax. Moreover, we evaluate the effectiveness of the learned feature representation for visual similarity search in two additional user studies. We find that our models retrieve significantly more similar patterns than other commonly used techniques.