Kerstin Kläser

Dominic Masters, Josef Dean, Kerstin Klaser et al.

This technical report presents GPS++, the first-place solution to the Open Graph Benchmark Large-Scale Challenge (OGB-LSC 2022) for the PCQM4Mv2 molecular property prediction task. Our approach implements several key principles from the prior literature. At its core our GPS++ method is a hybrid MPNN/Transformer model that incorporates 3D atom positions and an auxiliary denoising task. The effectiveness of GPS++ is demonstrated by achieving 0.0719 mean absolute error on the independent test-challenge PCQM4Mv2 split. Thanks to Graphcore IPU acceleration, GPS++ scales to deep architectures (16 layers), training at 3 minutes per epoch, and large ensemble (112 models), completing the final predictions in 1 hour 32 minutes, well under the 4 hour inference budget allocated. Our implementation is publicly available at: https://github.com/graphcore/ogb-lsc-pcqm4mv2.

Dominic Masters, Josef Dean, Kerstin Klaser et al.

We present GPS++, a hybrid Message Passing Neural Network / Graph Transformer model for molecular property prediction. Our model integrates a well-tuned local message passing component and biased global attention with other key ideas from prior literature to achieve state-of-the-art results on large-scale molecular dataset PCQM4Mv2. Through a thorough ablation study we highlight the impact of individual components and find that nearly all of the model's performance can be maintained without any use of global self-attention, showing that message passing is still a competitive approach for 3D molecular property prediction despite the recent dominance of graph transformers. We also find that our approach is significantly more accurate than prior art when 3D positional information is not available.

Alexander Mathiasen, Hatem Helal, Kerstin Klaser et al.

The emergence of foundation models in Computer Vision and Natural Language Processing have resulted in immense progress on downstream tasks. This progress was enabled by datasets with billions of training examples. Similar benefits are yet to be unlocked for quantum chemistry, where the potential of deep learning is constrained by comparatively small datasets with 100k to 20M training examples. These datasets are limited in size because the labels are computed using the accurate (but computationally demanding) predictions of Density Functional Theory (DFT). Notably, prior DFT datasets were created using CPU supercomputers without leveraging hardware acceleration. In this paper, we take a first step towards utilising hardware accelerators by introducing the data generator PySCF$_{\text{IPU}}$ using Intelligence Processing Units (IPUs). This allowed us to create the dataset QM1B with one billion training examples containing 9-11 heavy atoms. We demonstrate that a simple baseline neural network (SchNet 9M) improves its performance by simply increasing the amount of training data without additional inductive biases. To encourage future researchers to use QM1B responsibly, we highlight several limitations of QM1B and emphasise the low-resolution of our DFT options, which also serves as motivation for even larger, more accurate datasets. Code and dataset are available on Github: http://github.com/graphcore-research/pyscf-ipu

Dominique Beaini, Shenyang Huang, Joao Alex Cunha et al.

Recently, pre-trained foundation models have enabled significant advancements in multiple fields. In molecular machine learning, however, where datasets are often hand-curated, and hence typically small, the lack of datasets with labeled features, and codebases to manage those datasets, has hindered the development of foundation models. In this work, we present seven novel datasets categorized by size into three distinct categories: ToyMix, LargeMix and UltraLarge. These datasets push the boundaries in both the scale and the diversity of supervised labels for molecular learning. They cover nearly 100 million molecules and over 3000 sparsely defined tasks, totaling more than 13 billion individual labels of both quantum and biological nature. In comparison, our datasets contain 300 times more data points than the widely used OGB-LSC PCQM4Mv2 dataset, and 13 times more than the quantum-only QM1B dataset. In addition, to support the development of foundational models based on our proposed datasets, we present the Graphium graph machine learning library which simplifies the process of building and training molecular machine learning models for multi-task and multi-level molecular datasets. Finally, we present a range of baseline results as a starting point of multi-task and multi-level training on these datasets. Empirically, we observe that performance on low-resource biological datasets show improvement by also training on large amounts of quantum data. This indicates that there may be potential in multi-task and multi-level training of a foundation model and fine-tuning it to resource-constrained downstream tasks.

Kerstin Kläser, Błażej Banaszewski, Samuel Maddrell-Mander et al.

In biological tasks, data is rarely plentiful as it is generated from hard-to-gather measurements. Therefore, pre-training foundation models on large quantities of available data and then transfer to low-data downstream tasks is a promising direction. However, how to design effective foundation models for molecular learning remains an open question, with existing approaches typically focusing on models with large parameter capacities. In this work, we propose $\texttt{MiniMol}$, a foundational model for molecular learning with 10 million parameters. $\texttt{MiniMol}$ is pre-trained on a mix of roughly 3300 sparsely defined graph- and node-level tasks of both quantum and biological nature. The pre-training dataset includes approximately 6 million molecules and 500 million labels. To demonstrate the generalizability of $\texttt{MiniMol}$ across tasks, we evaluate it on downstream tasks from the Therapeutic Data Commons (TDC) ADMET group showing significant improvements over the prior state-of-the-art foundation model across 17 tasks. $\texttt{MiniMol}$ will be a public and open-sourced model for future research.

Benjamin Murray, Eric Kerfoot, Mark S. Graham et al.

The Covid Symptom Study, a smartphone-based surveillance study on COVID-19 symptoms in the population, is an exemplar of big data citizen science. Over 4.7 million participants and 189 million unique assessments have been logged since its introduction in March 2020. The success of the Covid Symptom Study creates technical challenges around effective data curation for two reasons. Firstly, the scale of the dataset means that it can no longer be easily processed using standard software on commodity hardware. Secondly, the size of the research group means that replicability and consistency of key analytics used across multiple publications becomes an issue. We present ExeTera, an open source data curation software designed to address scalability challenges and to enable reproducible research across an international research group for datasets such as the Covid Symptom Study dataset.

Pedro Borges, Richard Shaw, Thomas Varsavsky et al.

Combining multi-site data can strengthen and uncover trends, but is a task that is marred by the influence of site-specific covariates that can bias the data and therefore any downstream analyses. Post-hoc multi-site correction methods exist but have strong assumptions that often do not hold in real-world scenarios. Algorithms should be designed in a way that can account for site-specific effects, such as those that arise from sequence parameter choices, and in instances where generalisation fails, should be able to identify such a failure by means of explicit uncertainty modelling. This body of work showcases such an algorithm, that can become robust to the physics of acquisition in the context of segmentation tasks, while simultaneously modelling uncertainty. We demonstrate that our method not only generalises to complete holdout datasets, preserving segmentation quality, but does so while also accounting for site-specific sequence choices, which also allows it to perform as a harmonisation tool.

Pedro Borges, Richard Shaw, Thomas Varsavsky et al.

Being able to adequately process and combine data arising from different sites is crucial in neuroimaging, but is difficult, owing to site, sequence and acquisition-parameter dependent biases. It is important therefore to design algorithms that are not only robust to images of differing contrasts, but also be able to generalise well to unseen ones, with a quantifiable measure of uncertainty. In this paper we demonstrate the efficacy of a physics-informed, uncertainty-aware, segmentation network that employs augmentation-time MR simulations and homogeneous batch feature stratification to achieve acquisition invariance. We show that the proposed approach also accurately extrapolates to out-of-distribution sequence samples, providing well calibrated volumetric bounds on these. We demonstrate a significant improvement in terms of coefficients of variation, backed by uncertainty based volumetric validation.

Marta B. M. Ranzini, Irme Groothuis, Kerstin Kläser et al.

Metal artefact reduction (MAR) techniques aim at removing metal-induced noise from clinical images. In Computed Tomography (CT), supervised deep learning approaches have been shown effective but limited in generalisability, as they mostly rely on synthetic data. In Magnetic Resonance Imaging (MRI) instead, no method has yet been introduced to correct the susceptibility artefact, still present even in MAR-specific acquisitions. In this work, we hypothesise that a multimodal approach to MAR would improve both CT and MRI. Given their different artefact appearance, their complementary information can compensate for the corrupted signal in either modality. We thus propose an unsupervised deep learning method for multimodal MAR. We introduce the use of Locally Normalised Cross Correlation as a loss term to encourage the fusion of multimodal information. Experiments show that our approach favours a smoother correction in the CT, while promoting signal recovery in the MRI.

Kerstin Kläser, Thomas Varsavsky, Pawel Markiewicz et al.

The ability to synthesise Computed Tomography images - commonly known as pseudo CT, or pCT - from MRI input data is commonly assessed using an intensity-wise similarity, such as an L2-norm between the ground truth CT and the pCT. However, given that the ultimate purpose is often to use the pCT as an attenuation map ($μ$-map) in Positron Emission Tomography Magnetic Resonance Imaging (PET/MRI), minimising the error between pCT and CT is not necessarily optimal. The main objective should be to predict a pCT that, when used as $μ$-map, reconstructs a pseudo PET (pPET) which is as close as possible to the gold standard PET. To this end, we propose a novel multi-hypothesis deep learning framework that generates pCTs by minimising a combination of the pixel-wise error between pCT and CT and a proposed metric-loss that itself is represented by a convolutional neural network (CNN) and aims to minimise subsequent PET residuals. The model is trained on a database of 400 paired MR/CT/PET image slices. Quantitative results show that the network generates pCTs that seem less accurate when evaluating the Mean Absolute Error on the pCT (69.68HU) compared to a baseline CNN (66.25HU), but lead to significant improvement in the PET reconstruction - 115a.u. compared to baseline 140a.u.

Kerstin Kläser, Pawel Markiewicz, Marta Ranzini et al.

Attenuation correction is an essential requirement of positron emission tomography (PET) image reconstruction to allow for accurate quantification. However, attenuation correction is particularly challenging for PET-MRI as neither PET nor magnetic resonance imaging (MRI) can directly image tissue attenuation properties. MRI-based computed tomography (CT) synthesis has been proposed as an alternative to physics based and segmentation-based approaches that assign a population-based tissue density value in order to generate an attenuation map. We propose a novel deep fully convolutional neural network that generates synthetic CTs in a recursive manner by gradually reducing the residuals of the previous network, increasing the overall accuracy and generalisability, while keeping the number of trainable parameters within reasonable limits. The model is trained on a database of 20 pre-acquired MRI/CT pairs and a four-fold random bootstrapped validation with a 80:20 split is performed. Quantitative results show that the proposed framework outperforms a state-of-the-art atlas-based approach decreasing the Mean Absolute Error (MAE) from 131HU to 68HU for the synthetic CTs and reducing the PET reconstruction error from 14.3% to 7.2%.