Predictive genomic and metabolomic analysis for the standardization of enzyme data

CSI: Contrastive data Stratification for Interaction prediction and its application to compound-protein interaction prediction

MOTIVATION

Accurately predicting the likelihood of interaction between two objects (compound-protein sequence, user-item, author-paper, etc.) is a fundamental problem in Computer Science. Current deep-learning models rely on learning accurate representations of the interacting objects. Importantly, relationships between the interacting objects, or features of the interaction, offer an opportunity to partition the data to create multi-views of the interacting objects. The resulting congruent and non-congruent views can then be exploited via contrastive learning techniques to learn enhanced representations of the objects.

RESULTS

We present a novel method, Contrastive Stratification for Interaction Prediction (CSI), to stratify (partition) a dataset in a manner that can be exploited via Contrastive Multiview Coding to learn embeddings that maximize the mutual information across congruent data views. CSI assigns a key and multiple views to each data point, where data partitions under a particular key form congruent views of the data. We showcase the effectiveness of CSI by applying it to the compound-protein sequence interaction prediction problem, a pressing problem whose solution promises to expedite drug delivery (drug-protein interaction prediction), metabolic engineering, and synthetic biology (compound-enzyme interaction prediction) applications. Comparing CSI with a baseline model that does not utilize data stratification and contrastive learning, and show gains in average precision ranging from 13.7% to 39% using compounds and sequences as keys across multiple drug-target and enzymatic datasets, and gains ranging from 16.9% to 63% using reaction features as keys across enzymatic datasets.

AVAILABILITY AND IMPLEMENTATION

Code and dataset available at https://github.com/HassounLab/CSI.

Learning graph representations of biochemical networks and its application to enzymatic link prediction

Motivation

The complete characterization of enzymatic activities between molecules remains incomplete, hindering biological engineering and limiting biological discovery. We develop in this work a technique, enzymatic link prediction (ELP), for predicting the likelihood of an enzymatic transformation between two molecules. ELP models enzymatic reactions cataloged in the KEGG database as a graph. ELP is innovative over prior works in using graph embedding to learn molecular representations that capture not only molecular and enzymatic attributes but also graph connectivity.

Results

We explore transductive (test nodes included in the training graph) and inductive (test nodes not part of the training graph) learning models. We show that ELP achieves high AUC when learning node embeddings using both graph connectivity and node attributes. Further, we show that graph embedding improves link prediction by 30% in area under curve over fingerprint-based similarity approaches and by 8% over support vector machines. We compare ELP against rule-based methods. We also evaluate ELP for predicting links in pathway maps and for reconstruction of edges in reaction networks of four common gut microbiota phyla: actinobacteria, bacteroidetes, firmicutes and proteobacteria. To emphasize the importance of graph embedding in the context of biochemical networks, we illustrate how graph embedding can guide visualization.

Availability and implementation

The code and datasets are available through https://github.com/HassounLab/ELP.

Metabolic pathway reconstruction strategies for central metabolism and natural product biosynthesis

Metabolic pathway reconstruction presents a challenge for understanding metabolic pathways in organisms of interest. Different strategies, i.e., reference-based vs. de novo, must be used for pathway reconstruction depending on the availability of well-characterized enzymatic reactions. If at least one enzyme is already known to catalyze a reaction, its amino acid sequence can be used as a reference for identifying homologous enzymes in the genome of an organism of interest. Where there is no known enzyme able to catalyze a corresponding reaction, however, the reaction and the corresponding enzyme must be predicted de novo from chemical transformations of the putative substrate-product pair. This review summarizes studies involving reference-based and de novo metabolic pathway reconstruction and discusses the importance of the classification and structure-function relationships of enzymes.

Characterising Complex Enzyme Reaction Data

The relationship between enzyme-catalysed reactions and the Enzyme Commission (EC) number, the widely accepted classification scheme used to characterise enzyme activity, is complex and with the rapid increase in our knowledge of the reactions catalysed by enzymes needs revisiting. We present a manual and computational analysis to investigate this complexity and found that almost one-third of all known EC numbers are linked to more than one reaction in the secondary reaction databases (e.g., KEGG). Although this complexity is often resolved by defining generic, alternative and partial reactions, we have also found individual EC numbers with more than one reaction catalysing different types of bond changes. This analysis adds a new dimension to our understanding of enzyme function and might be useful for the accurate annotation of the function of enzymes and to study the changes in enzyme function during evolution.

PIERO ontology for analysis of biochemical transformations: effective implementation of reaction information in the IUBMB enzyme list

Genomics is faced with the issue of many partially annotated putative enzyme-encoding genes for which activities have not yet been verified, while metabolomics is faced with the issue of many putative enzyme reactions for which full equations have not been verified. Knowledge of enzymes has been collected by IUBMB, and has been made public as the Enzyme List. To date, however, the terminology of the Enzyme List has not been assessed comprehensively by bioinformatics studies. Instead, most of the bioinformatics studies simply use the identifiers of the enzymes, i.e. the Enzyme Commission (EC) numbers. We investigated the actual usage of terminology throughout the Enzyme List, and demonstrated that the partial characteristics of reactions cannot be retrieved by simply using EC numbers. Thus, we developed a novel ontology, named PIERO, for annotating biochemical transformations as follows. First, the terminology describing enzymatic reactions was retrieved from the Enzyme List, and was grouped into those related to overall reactions and biochemical transformations. Consequently, these terms were mapped onto the actual transformations taken from enzymatic reaction equations. This ontology was linked to Gene Ontology (GO) and EC numbers, allowing the extraction of common partial reaction characteristics from given sets of orthologous genes and the elucidation of possible enzymes from the given transformations. Further future development of the PIERO ontology should enhance the Enzyme List to promote the integration of genomics and metabolomics.