Endowing Protein Language Models with Structural Knowledge

Understanding the relationships between protein sequence, structure and function is a long-standing biological challenge with manifold implications from drug design to our understanding of evolution. Recently, protein language models have emerged as the preferred method for this challenge, thanks to their ability to harness large sequence databases. Yet, their reliance on expansive sequence data and parameter sets limits their flexibility and practicality in real-world scenarios. Concurrently, the recent surge in computationally predicted protein structures unlocks new opportunities in protein representation learning. While promising, the computational burden carried by such complex data still hinders widely-adopted practical applications. To address these limitations, we introduce a novel framework that enhances protein language models by integrating protein structural data. Drawing from recent advances in graph transformers, our approach refines the self-attention mechanisms of pretrained language transformers by integrating structural information with structure extractor modules. This refined model, termed Protein Structure Transformer (PST), is further pretrained on a small protein structure database, using the same masked language modeling objective as traditional protein language models. Empirical evaluations of PST demonstrate its superior parameter efficiency relative to protein language models, despite being pretrained on a dataset comprising only 542K structures. Notably, PST consistently outperforms the state-of-the-art foundation model for protein sequences, ESM-2, setting a new benchmark in protein function prediction. Our findings underscore the potential of integrating structural information into protein language models, paving the way for more effective and efficient protein modeling Code and pretrained models are available at https://github.com/BorgwardtLab/PST.

Fisher Information Embedding for Node and Graph Learning

Attention-based graph neural networks (GNNs), such as graph attention networks (GATs), have become popular neural architectures for processing graph-structured data and learning node embeddings. Despite their empirical success, these models rely on labeled data and the theoretical properties of these models have yet to be fully understood. In this work, we propose a novel attention-based node embedding framework for graphs. Our framework builds upon a hierarchical kernel for multisets of subgraphs around nodes (e.g. neighborhoods) and each kernel leverages the geometry of a smooth statistical manifold to compare pairs of multisets, by "projecting" the multisets onto the manifold. By explicitly computing node embeddings with a manifold of Gaussian mixtures, our method leads to a new attention mechanism for neighborhood aggregation. We provide theoretical insights into genralizability and expressivity of our embeddings, contributing to a deeper understanding of attention-based GNNs. We propose efficient unsupervised and supervised methods for learning the embeddings, with the unsupervised method not requiring any labeled data. Through experiments on several node classification benchmarks, we demonstrate that our proposed method outperforms existing attention-based graph models like GATs. Our code is available at https://github.com/BorgwardtLab/fisher_information_embedding.

Unsupervised Manifold Alignment with Joint Multidimensional Scaling

We introduce Joint Multidimensional Scaling, a novel approach for unsupervised manifold alignment, which maps datasets from two different domains, without any known correspondences between data instances across the datasets, to a common low-dimensional Euclidean space. Our approach integrates Multidimensional Scaling (MDS) and Wasserstein Procrustes analysis into a joint optimization problem to simultaneously generate isometric embeddings of data and learn correspondences between instances from two different datasets, while only requiring intra-dataset pairwise dissimilarities as input. This unique characteristic makes our approach applicable to datasets without access to the input features, such as solving the inexact graph matching problem. We propose an alternating optimization scheme to solve the problem that can fully benefit from the optimization techniques for MDS and Wasserstein Procrustes. We demonstrate the effectiveness of our approach in several applications, including joint visualization of two datasets, unsupervised heterogeneous domain adaptation, graph matching, and protein structure alignment.

Approximate Network Motif Mining Via Graph Learning

Frequent and structurally related subgraphs, also known as network motifs, are valuable features of many graph datasets. However, the high computational complexity of identifying motif sets in arbitrary datasets (motif mining) has limited their use in many real-world datasets. By automatically leveraging statistical properties of datasets, machine learning approaches have shown promise in several tasks with combinatorial complexity and are therefore a promising candidate for network motif mining. In this work we seek to facilitate the development of machine learning approaches aimed at motif mining. We propose a formulation of the motif mining problem as a node labelling task. In addition, we build benchmark datasets and evaluation metrics which test the ability of models to capture different aspects of motif discovery such as motif number, size, topology, and scarcity. Next, we propose MotiFiesta, a first attempt at solving this problem in a fully differentiable manner with promising results on challenging baselines. Finally, we demonstrate through MotiFiesta that this learning setting can be applied simultaneously to general-purpose data mining and interpretable feature extraction for graph classification tasks.

Structure-Aware Transformer for Graph Representation Learning

The Transformer architecture has gained growing attention in graph representation learning recently, as it naturally overcomes several limitations of graph neural networks (GNNs) by avoiding their strict structural inductive biases and instead only encoding the graph structure via positional encoding. Here, we show that the node representations generated by the Transformer with positional encoding do not necessarily capture structural similarity between them. To address this issue, we propose the Structure-Aware Transformer, a class of simple and flexible graph transformers built upon a new self-attention mechanism. This new self-attention incorporates structural information into the original self-attention by extracting a subgraph representation rooted at each node before computing the attention. We propose several methods for automatically generating the subgraph representation and show theoretically that the resulting representations are at least as expressive as the subgraph representations. Empirically, our method achieves state-of-the-art performance on five graph prediction benchmarks. Our structure-aware framework can leverage any existing GNN to extract the subgraph representation, and we show that it systematically improves performance relative to the base GNN model, successfully combining the advantages of GNNs and transformers.

Weisfeiler and Leman go Machine Learning: The Story so far

In recent years, algorithms and neural architectures based on the Weisfeiler-Leman algorithm, a well-known heuristic for the graph isomorphism problem, emerged as a powerful tool for machine learning with graphs and relational data. Here, we give a comprehensive overview of the algorithm's use in a machine learning setting, focusing on the supervised regime. We discuss the theoretical background, show how to use it for supervised graph- and node representation learning, discuss recent extensions, and outline the algorithm's connection to (permutation-)equivariant neural architectures. Moreover, we give an overview of current applications and future directions to stimulate further research.

The magnitude vector of images

The magnitude of a finite metric space is a recently-introduced invariant quantity. Despite beneficial theoretical and practical properties, such as a general utility for outlier detection, and a close connection to Laplace radial basis kernels, magnitude has received little attention by the machine learning community so far. In this work, we investigate the properties of magnitude on individual images, with each image forming its own metric space. We show that the known properties of outlier detection translate to edge detection in images and we give supporting theoretical justifications. In addition, we provide a proof of concept of its utility by using a novel magnitude layer to defend against adversarial attacks. Since naive magnitude calculations may be computationally prohibitive, we introduce an algorithm that leverages the regular structure of images to dramatically reduce the computational cost.

Predicting sepsis in multi-site, multi-national intensive care cohorts using deep learning

Despite decades of clinical research, sepsis remains a global public health crisis with high mortality, and morbidity. Currently, when sepsis is detected and the underlying pathogen is identified, organ damage may have already progressed to irreversible stages. Effective sepsis management is therefore highly time-sensitive. By systematically analysing trends in the plethora of clinical data available in the intensive care unit (ICU), an early prediction of sepsis could lead to earlier pathogen identification, resistance testing, and effective antibiotic and supportive treatment, and thereby become a life-saving measure. Here, we developed and validated a machine learning (ML) system for the prediction of sepsis in the ICU. Our analysis represents the largest multi-national, multi-centre in-ICU study for sepsis prediction using ML to date. Our dataset contains $156,309$ unique ICU admissions, which represent a refined and harmonised subset of five large ICU databases originating from three countries. Using the international consensus definition Sepsis-3, we derived hourly-resolved sepsis label annotations, amounting to $26,734$ ($17.1\%$) septic stays. We compared our approach, a deep self-attention model, to several clinical baselines as well as ML baselines and performed an extensive internal and external validation within and across databases. On average, our model was able to predict sepsis with an AUROC of $0.847 \pm 0.050$ (internal out-of sample validation) and $0.761 \pm 0.052$ (external validation). For a harmonised prevalence of $17\%$, at $80\%$ recall our model detects septic patients with $39\%$ precision 3.7 hours in advance.

Evaluation Metrics for Graph Generative Models: Problems, Pitfalls, and Practical Solutions

Graph generative models are a highly active branch of machine learning. Given the steady development of new models of ever-increasing complexity, it is necessary to provide a principled way to evaluate and compare them. In this paper, we enumerate the desirable criteria for comparison metrics, discuss the development of such metrics, and provide a comparison of their respective expressive power. We perform a systematic evaluation of the main metrics in use today, highlighting some of the challenges and pitfalls researchers inadvertently can run into. We then describe a collection of suitable metrics, give recommendations as to their practical suitability, and analyse their behaviour on synthetically generated perturbed graphs as well as on recently proposed graph generative models.

Topological Graph Neural Networks

Graph neural networks (GNNs) are a powerful architecture for tackling graph learning tasks, yet have been shown to be oblivious to eminent substructures, such as cycles. We present TOGL, a novel layer that incorporates global topological information of a graph using persistent homology. TOGL can be easily integrated into any type of GNN and is strictly more expressive in terms of the Weisfeiler--Lehman test of isomorphism. Augmenting GNNs with our layer leads to beneficial predictive performance, both on synthetic data sets, which can be trivially classified by humans but not by ordinary GNNs, and on real-world data.