On Separate Normalization in Self-supervised Transformers

Self-supervised training methods for transformers have demonstrated remarkable performance across various domains. Previous transformer-based models, such as masked autoencoders (MAE), typically utilize a single normalization layer for both the [CLS] symbol and the tokens. We propose in this paper a simple modification that employs separate normalization layers for the tokens and the [CLS] symbol to better capture their distinct characteristics and enhance downstream task performance. Our method aims to alleviate the potential negative effects of using the same normalization statistics for both token types, which may not be optimally aligned with their individual roles. We empirically show that by utilizing a separate normalization layer, the [CLS] embeddings can better encode the global contextual information and are distributed more uniformly in its anisotropic space. When replacing the conventional normalization layer with the two separate layers, we observe an average 2.7% performance improvement over the image, natural language, and graph domains.

Ensemble Spectral Prediction (ESP) Model for Metabolite Annotation

A key challenge in metabolomics is annotating measured spectra from a biological sample with chemical identities. Currently, only a small fraction of measurements can be assigned identities. Two complementary computational approaches have emerged to address the annotation problem: mapping candidate molecules to spectra, and mapping query spectra to molecular candidates. In essence, the candidate molecule with the spectrum that best explains the query spectrum is recommended as the target molecule. Despite candidate ranking being fundamental in both approaches, no prior works utilized rank learning tasks in determining the target molecule. We propose a novel machine learning model, Ensemble Spectral Prediction (ESP), for metabolite annotation. ESP takes advantage of prior neural network-based annotation models that utilize multilayer perceptron (MLP) networks and Graph Neural Networks (GNNs). Based on the ranking results of the MLP and GNN-based models, ESP learns a weighting for the outputs of MLP and GNN spectral predictors to generate a spectral prediction for a query molecule. Importantly, training data is stratified by molecular formula to provide candidate sets during model training. Further, baseline MLP and GNN models are enhanced by considering peak dependencies through multi-head attention mechanism and multi-tasking on spectral topic distributions. ESP improves average rank by 41% and 30% over the MLP and GNN baselines, respectively, demonstrating remarkable performance gain over state-of-the-art neural network approaches. We show that annotation performance, for ESP and other models, is a strong function of the number of molecules in the candidate set and their similarity to the target molecule.

Contrastive Multiview Coding for Enzyme-Substrate Interaction Prediction

Characterizing Enzyme function is an important requirement for predicting Enzyme-Substrate interactions. In this paper, we present a novel approach of applying Contrastive Multiview Coding to this problem to improve the performance of prediction. We present a method to leverage auxiliary data from an Enzymatic database like KEGG to learn the mutual information present in multiple views of enzyme-substrate reactions. We show that congruency in the multiple views of the reaction data can be used to improve prediction performance.

Boost-RS: Boosted Embeddings for Recommender Systems and its Application to Enzyme-Substrate Interaction Prediction

Despite experimental and curation efforts, the extent of enzyme promiscuity on substrates continues to be largely unexplored and under documented. Recommender systems (RS), which are currently unexplored for the enzyme-substrate interaction prediction problem, can be utilized to provide enzyme recommendations for substrates, and vice versa. The performance of Collaborative-Filtering (CF) recommender systems however hinges on the quality of embedding vectors of users and items (enzymes and substrates in our case). Importantly, enhancing CF embeddings with heterogeneous auxiliary data, specially relational data (e.g., hierarchical, pairwise, or groupings), remains a challenge. We propose an innovative general RS framework, termed Boost-RS, that enhances RS performance by "boosting" embedding vectors through auxiliary data. Specifically, Boost-RS is trained and dynamically tuned on multiple relevant auxiliary learning tasks Boost-RS utilizes contrastive learning tasks to exploit relational data. To show the efficacy of Boost-RS for the enzyme-substrate prediction interaction problem, we apply the Boost-RS framework to several baseline CF models. We show that each of our auxiliary tasks boosts learning of the embedding vectors, and that contrastive learning using Boost-RS outperforms attribute concatenation and multi-label learning. We also show that Boost-RS outperforms similarity-based models. Ablation studies and visualization of learned representations highlight the importance of using contrastive learning on some of the auxiliary data in boosting the embedding vectors.

Stochastic Iterative Graph Matching

Recent works leveraging Graph Neural Networks to approach graph matching tasks have shown promising results. Recent progress in learning discrete distributions poses new opportunities for learning graph matching models. In this work, we propose a new model, Stochastic Iterative Graph MAtching (SIGMA), to address the graph matching problem. Our model defines a distribution of matchings for a graph pair so the model can explore a wide range of possible matchings. We further introduce a novel multi-step matching procedure, which learns how to refine a graph pair's matching results incrementally. The model also includes dummy nodes so that the model does not have to find matchings for nodes without correspondence. We fit this model to data via scalable stochastic optimization. We conduct extensive experiments across synthetic graph datasets as well as biochemistry and computer vision applications. Across all tasks, our results show that SIGMA can produce significantly improved graph matching results compared to state-of-the-art models. Ablation studies verify that each of our components (stochastic training, iterative matching, and dummy nodes) offers noticeable improvement.

Using Graph Neural Networks for Mass Spectrometry Prediction

Detecting and quantifying products of cellular metabolism using Mass Spectrometry (MS) has already shown great promise in many biological and biomedical applications. The biggest challenge in metabolomics is annotation, where measured spectra are assigned chemical identities. Despite advances, current methods provide limited annotation for measured spectra. Here, we explore using graph neural networks (GNNs) to predict the spectra. The input to our model is a molecular graph. The model is trained and tested on the NIST 17 LC-MS dataset. We compare our results to NEIMS, a neural network model that utilizes molecular fingerprints as inputs. Our results show that GNN-based models offer higher performance than NEIMS. Importantly, we show that ranking results heavily depend on the candidate set size and on the similarity of the candidates to the target molecule, thus highlighting the need for consistent, well-characterized evaluation protocols for this domain.

Hierarchical Classification of Enzyme Promiscuity Using Positive, Unlabeled, and Hard Negative Examples

Despite significant progress in sequencing technology, there are many cellular enzymatic activities that remain unknown. We develop a new method, referred to as SUNDRY (Similarity-weighting for UNlabeled Data in a Residual HierarchY), for training enzyme-specific predictors that take as input a query substrate molecule and return whether the enzyme would act on that substrate or not. When addressing this enzyme promiscuity prediction problem, a major challenge is the lack of abundant labeled data, especially the shortage of labeled data for negative cases (enzyme-substrate pairs where the enzyme does not act to transform the substrate to a product molecule). To overcome this issue, our proposed method can learn to classify a target enzyme by sharing information from related enzymes via known tree hierarchies. Our method can also incorporate three types of data: those molecules known to be catalyzed by an enzyme (positive cases), those with unknown relationships (unlabeled cases), and molecules labeled as inhibitors for the enzyme. We refer to inhibitors as hard negative cases because they may be difficult to classify well: they bind to the enzyme, like positive cases, but are not transformed by the enzyme. Our method uses confidence scores derived from structural similarity to treat unlabeled examples as weighted negatives. We compare our proposed hierarchy-aware predictor against a baseline that cannot share information across related enzymes. Using data from the BRENDA database, we show that each of our contributions (hierarchical sharing, per-example confidence weighting of unlabeled data based on molecular similarity, and including inhibitors as hard-negative examples) contributes towards a better characterization of enzyme promiscuity.

Pathway Activity Analysis and Metabolite Annotation for Untargeted Metabolomics using Probabilistic Modeling

Motivation: Untargeted metabolomics comprehensively characterizes small molecules and elucidates activities of biochemical pathways within a biological sample. Despite computational advances, interpreting collected measurements and determining their biological role remains a challenge. Results: To interpret measurements, we present an inference-based approach, termed Probabilistic modeling for Untargeted Metabolomics Analysis (PUMA). Our approach captures measurements and known information about the sample under study in a generative model and uses stochastic sampling to compute posterior probability distributions. PUMA predicts the likelihood of pathways being active, and then derives a probabilistic annotation, which assigns chemical identities to the measurements. PUMA is validated on synthetic datasets. When applied to test cases, the resulting pathway activities are biologically meaningful and distinctly different from those obtained using statistical pathway enrichment techniques. Annotation results are in agreement to those obtained using other tools that utilize additional information in the form of spectral signatures. Importantly, PUMA annotates many additional measurements.