Opportunities in deep learning methods development for computational biology

Advances in molecular technologies underlie an enormous growth in the size of data sets pertaining to biology and biomedicine. These advances parallel those in the deep learning subfield of machine learning. Components in the differentiable programming toolbox that makes deep learning possible are allowing computer scientists to address an increasingly large array of problems with flexible and effective tools. However many of these tools have not fully proliferated into the computational biology and bioinformatics fields. In this perspective we survey some of these advances and highlight exemplary examples of their utilization in the biosciences, with the goal of increasing awareness among practitioners of emerging opportunities to blend expert knowledge with newly emerging deep learning architectural tools.

7T MRI Synthesization from 3T Acquisitions

Supervised deep learning techniques can be used to generate synthetic 7T MRIs from 3T MRI inputs. This image enhancement process leverages the advantages of ultra-high-field MRI to improve the signal-to-noise and contrast-to-noise ratios of 3T acquisitions. In this paper, we introduce multiple novel 7T synthesization algorithms based on custom-designed variants of the V-Net convolutional neural network. We demonstrate that the V-Net based model has superior performance in enhancing both single-site and multi-site MRI datasets compared to the existing benchmark model. When trained on 3T-7T MRI pairs from 8 subjects with mild Traumatic Brain Injury (TBI), our model achieves state-of-the-art 7T synthesization performance. Compared to previous works, synthetic 7T images generated from our pipeline also display superior enhancement of pathological tissue. Additionally, we implement and test a data augmentation scheme for training models that are robust to variations in the input distribution. This allows synthetic 7T models to accommodate intra-scanner and inter-scanner variability in multisite datasets. On a harmonized dataset consisting of 18 3T-7T MRI pairs from two institutions, including both healthy subjects and those with mild TBI, our model maintains its performance and can generalize to 3T MRI inputs with lower resolution. Our findings demonstrate the promise of V-Net based models for MRI enhancement and offer a preliminary probe into improving the generalizability of synthetic 7T models with data augmentation.

Zero-shot sampling of adversarial entities in biomedical question answering

The increasing depth of parametric domain knowledge in large language models (LLMs) is fueling their rapid deployment in real-world applications. In high-stakes and knowledge-intensive tasks, understanding model vulnerabilities is essential for quantifying the trustworthiness of model predictions and regulating their use. The recent discovery of named entities as adversarial examples in natural language processing tasks raises questions about their potential guises in other settings. Here, we propose a powerscaled distance-weighted sampling scheme in embedding space to discover diverse adversarial entities as distractors. We demonstrate its advantage over random sampling in adversarial question answering on biomedical topics. Our approach enables the exploration of different regions on the attack surface, which reveals two regimes of adversarial entities that markedly differ in their characteristics. Moreover, we show that the attacks successfully manipulate token-wise Shapley value explanations, which become deceptive in the adversarial setting. Our investigations illustrate the brittleness of domain knowledge in LLMs and reveal a shortcoming of standard evaluations for high-capacity models.

Machine Learning for Uncovering Biological Insights in Spatial Transcriptomics Data

Development and homeostasis in multicellular systems both require exquisite control over spatial molecular pattern formation and maintenance. Advances in spatially-resolved and high-throughput molecular imaging methods such as multiplexed immunofluorescence and spatial transcriptomics (ST) provide exciting new opportunities to augment our fundamental understanding of these processes in health and disease. The large and complex datasets resulting from these techniques, particularly ST, have led to rapid development of innovative machine learning (ML) tools primarily based on deep learning techniques. These ML tools are now increasingly featured in integrated experimental and computational workflows to disentangle signals from noise in complex biological systems. However, it can be difficult to understand and balance the different implicit assumptions and methodologies of a rapidly expanding toolbox of analytical tools in ST. To address this, we summarize major ST analysis goals that ML can help address and current analysis trends. We also describe four major data science concepts and related heuristics that can help guide practitioners in their choices of the right tools for the right biological questions.

Multi-Modal Prototype Learning for Interpretable Multivariable Time Series Classification

Multivariable time series classification problems are increasing in prevalence and complexity in a variety of domains, such as biology and finance. While deep learning methods are an effective tool for these problems, they often lack interpretability. In this work, we propose a novel modular prototype learning framework for multivariable time series classification. In the first stage of our framework, encoders extract features from each variable independently. Prototype layers identify single-variable prototypes in the resulting feature spaces. The next stage of our framework represents the multivariable time series sample points in terms of their similarity to these single-variable prototypes. This results in an inherently interpretable representation of multivariable patterns, on which prototype learning is applied to extract representative examples i.e. multivariable prototypes. Our framework is thus able to explicitly identify both informative patterns in the individual variables, as well as the relationships between the variables. We validate our framework on a simulated dataset with embedded patterns, as well as a real human activity recognition problem. Our framework attains comparable or superior classification performance to existing time series classification methods on these tasks. On the simulated dataset, we find that our model returns interpretations consistent with the embedded patterns. Moreover, the interpretations learned on the activity recognition dataset align with domain knowledge.

Interpretable machine learning: definitions, methods, and applications

Machine-learning models have demonstrated great success in learning complex patterns that enable them to make predictions about unobserved data. In addition to using models for prediction, the ability to interpret what a model has learned is receiving an increasing amount of attention. However, this increased focus has led to considerable confusion about the notion of interpretability. In particular, it is unclear how the wide array of proposed interpretation methods are related, and what common concepts can be used to evaluate them. We aim to address these concerns by defining interpretability in the context of machine learning and introducing the Predictive, Descriptive, Relevant (PDR) framework for discussing interpretations. The PDR framework provides three overarching desiderata for evaluation: predictive accuracy, descriptive accuracy and relevancy, with relevancy judged relative to a human audience. Moreover, to help manage the deluge of interpretation methods, we introduce a categorization of existing techniques into model-based and post-hoc categories, with sub-groups including sparsity, modularity and simulatability. To demonstrate how practitioners can use the PDR framework to evaluate and understand interpretations, we provide numerous real-world examples. These examples highlight the often under-appreciated role played by human audiences in discussions of interpretability. Finally, based on our framework, we discuss limitations of existing methods and directions for future work. We hope that this work will provide a common vocabulary that will make it easier for both practitioners and researchers to discuss and choose from the full range of interpretation methods.

Robust Image Registration via Empirical Mode Decomposition

Spatially varying intensity noise is a common source of distortion in images. Bias field noise is one example of such distortion that is often present in the magnetic resonance (MR) images. In this paper, we first show that empirical mode decomposition (EMD) can considerably reduce the bias field noise in the MR images. Then, we propose two hierarchical multi-resolution EMD-based algorithms for robust registration of images in the presence of spatially varying noise. One algorithm (LR-EMD) is based on registering EMD feature-maps of both floating and reference images in various resolution levels. In the second algorithm (AFR-EMD), we first extract an average feature-map based on EMD from both floating and reference images. Then, we use a simple hierarchical multi-resolution algorithm based on downsampling to register the average feature-maps. Both algorithms achieve lower error rate and higher convergence percentage compared to the intensity-based hierarchical registration. Specifically, using mutual information as the similarity measure, AFR-EMD achieves 42% lower error rate in intensity and 52% lower error rate in transformation compared to intensity-based hierarchical registration. For LR-EMD, the error rate is 32% lower for the intensity and 41% lower for the transformation.

Interpreting Convolutional Neural Networks Through Compression

Convolutional neural networks (CNNs) achieve state-of-the-art performance in a wide variety of tasks in computer vision. However, interpreting CNNs still remains a challenge. This is mainly due to the large number of parameters in these networks. Here, we investigate the role of compression and particularly pruning filters in the interpretation of CNNs. We exploit our recently-proposed greedy structural compression scheme that prunes filters in a trained CNN. In our compression, the filter importance index is defined as the classification accuracy reduction (CAR) of the network after pruning that filter. The filters are then iteratively pruned based on the CAR index. We demonstrate the interpretability of CAR-compressed CNNs by showing that our algorithm prunes filters with visually redundant pattern selectivity. Specifically, we show the importance of shape-selective filters for object recognition, as opposed to color-selective filters. Out of top 20 CAR-pruned filters in AlexNet, 17 of them in the first layer and 14 of them in the second layer are color-selective filters. Finally, we introduce a variant of our CAR importance index that quantifies the importance of each image class to each CNN filter. We show that the most and the least important class labels present a meaningful interpretation of each filter that is consistent with the visualized pattern selectivity of that filter.

Structural Compression of Convolutional Neural Networks Based on Greedy Filter Pruning

Convolutional neural networks (CNNs) have state-of-the-art performance on many problems in machine vision. However, networks with superior performance often have millions of weights so that it is difficult or impossible to use CNNs on computationally limited devices or to humanly interpret them. A myriad of CNN compression approaches have been proposed and they involve pruning and compressing the weights and filters. In this article, we introduce a greedy structural compression scheme that prunes filters in a trained CNN. We define a filter importance index equal to the classification accuracy reduction (CAR) of the network after pruning that filter (similarly defined as RAR for regression). We then iteratively prune filters based on the CAR index. This algorithm achieves substantially higher classification accuracy in AlexNet compared to other structural compression schemes that prune filters. Pruning half of the filters in the first or second layer of AlexNet, our CAR algorithm achieves 26% and 20% higher classification accuracies respectively, compared to the best benchmark filter pruning scheme. Our CAR algorithm, combined with further weight pruning and compressing, reduces the size of first or second convolutional layer in AlexNet by a factor of 42, while achieving close to original classification accuracy through retraining (or fine-tuning) network. Finally, we demonstrate the interpretability of CAR-compressed CNNs by showing that our algorithm prunes filters with visually redundant functionalities. In fact, out of top 20 CAR-pruned filters in AlexNet, 17 of them in the first layer and 14 of them in the second layer are color-selective filters as opposed to shape-selective filters. To our knowledge, this is the first reported result on the connection between compression and interpretability of CNNs.