Biology subjects

Joeres, R.

Publications and source records attributed to Joeres, R..

9 recordsLinked to original sources

bioRxiv2026

Information Leakage in Enzyme Substrate Prediction

Enzymes are essential catalysts in many cellular processes. Understanding their interactions with small molecules, such as regulators, cofactors, and most importantly, substrates, is crucial for understanding the biochemical processes that occur in cells. Correctly interpreting the roles of small molecules that interact with enzymes is key to elucidating enzyme function. Recently, the field of enzyme-small molecule interaction prediction has gained more interest from computational and, especially, deep-learning methods, and numerous datasets and models with remarkable performances have been published. In this work, we critically examine one of the most popular datasets and three models trained on it, identifying leaked information that may overinflate reported model performance. We show that the inspected models are susceptible to information leakage, and their performance drops to near-random when the leakage is removed.

bioinformatics↗

bioRxiv2025

StructGuy: Data leakage free prediction of functional effects of genetic variants.

The extent to which variations in protein-coding genes affect protein function has drawn the biological machine learning communitys attention to computationally model variant effect prediction tools. Multiplexed assays of variant effects (MAVE) experiments serve as a rich data source, but cannot deliver enough data for training truly large neural-net models. Therefore, zero-shot methods, for example protein language models, have increasingly gained popularity. For these methods, MAVE results serve primarily for evaluation purposes, as exemplified by the ProteinGym benchmark. In this study, we argue that the rapidly increasing amounts of MAVE data can be used to train efficient supervised methods, presenting our new tool StructGuy, based on gradient boosting trees methodology. In contrast to other supervised methods in the field, StructGuy, thanks to its dedicated training dataset and data leakage-free training process, can predict variant effects for proteins not seen during training. To evaluate this generalization ability, we constructed a dedicated benchmark and compared StructGuy with zero-shot methods from the ProteinGym leaderboard achieving a competitive performance. Further, we demonstrate that thanks to its architecture and careful feature engineering, we are able to provide fully interpretable predictions and direct explanations of the influence of mutations on protein three-dimensional structure, which favourably differs StructGuy from zero-shot tools.

bioinformatics↗

bioRxiv2025

A General Transformer-Based Multi-Task Learning Framework for Predicting Interaction Types between Enzyme and Small Molecule

Predicting enzyme-small molecule interactions is critical for drug discovery and generally understanding the biochemical processes of life. While recent deep learning approaches have shown promising results, several challenges remain: the lack of a comprehensive training dataset, architectures lacking communication between representations of enzymes and small molecules, the tendency to simplify the problem as enzyme-substrate vs. enzyme--non-interacting, and thereby, misclassify enzyme-inhibitor pairs as substrates, and the negligence of the true impact of data leakage on the models performance. To address these issues, we present EMMA (Enzyme-small Molecule interaction Multi-head Attention), a transformer-based multi-task learning framework designed to learn pairwise interaction signals between enzymes and small molecules, that can well generalize to out-of-distribution data. EMMA operates directly on the SMILES string representation of small molecules and enzyme sequences, with two classification heads that distinguish enzyme--non-interacting, enzyme--substrate, and enzyme--inhibitor pairs. By evaluating EMMA under five distinct data-splitting regimes that control for different types of data leakage, we demonstrate that EMMA achieves a strong and robust performance, particularly for previously unseen combinations of enzymes and small molecules. Further, a deeper analysis highlights that the topological properties of the enzyme--small molecule interaction network are crucial for the model performance and its ability to generalize, yet again stressing the decisive role of well-designed training datasets for successful model training.

bioinformatics↗

bioRxiv2025

ALPAR: Automated Learning Pipeline for Antimicrobial Resistance

The field of machine learning in antimicrobial resistance (AMR) research has experienced rapid growth, fueled by advancements in high-throughput genome sequencing and growing capacity of computational resources. However, the complexity and lack of standardized data preparation and bioinformatic analyses present significant challenges, especially to newcomers to the domain. In response to these challenges, we introduce ALPAR (Automated Learning Pipeline for Antimicrobial Resistance), a comprehensive AMR data analysis tool covering the entire process from processing of raw genomic data to training machine learning models to interpretation of results. Our method relies on a reproducible pipeline that integrates widely used bioinformatics tools, presenting a simplified, automatic workflow specifically tailored for single-reference AMR analysis. Accepting genomic data in the form of FASTA files as input, ALPAR facilitates generation of machine learning-ready data tables and both training of machine learning and execution of genome-wide association studies (GWAS) experiments. Additionally, our tool offers supplementary functionalities such as phylogeny-based analysis of distribution of mutations, enhancing its utility for researchers. Our tool is accessible through the ALPAR GitHub page (https://github.com/kalininalab/ALPAR) and installable via conda (https://anaconda.org/kalininalab/ALPAR).

bioinformatics↗

bioRxiv2025

GlyContact reveals structure-function relationships in glycans

Glycans are branched, structurally diverse, and highly flexible biomolecules. These characteristics make glycoanalytics and glycan structural characterization challenging, resulting in often unclear structure-to-function relationships. The creation of GlycoShape, currently the largest open-access (OA) database of glycan 3D structures from molecular dynamics (MD) simulations, provides an opportunity to fill this information gap. Here, we present GlyContact, an open-source Python package designed and developed to retrieve, process, and analyze glycan 3D structures, from MD, NMR, or X-ray crystallography. We demonstrate that this platform can (i) unveil the impact of sequence context on glycan motif structure, (ii) yield a predictive understanding of motif flexibility and surface accessibility on lectin-glycan binding, which improves state-of-the-art AI models for this task, and (iii) accurately predict torsion angles of multiple conformers via new AI models. We envision that GlyContact will allow researchers to explore glycan structures within their 3D space, obtaining new insights into their biological functions. GlyContact is available OA at https://github.com/lthomes/glycontact.

bioinformatics↗

bioRxiv2025

Bridging Worlds: Connecting Glycan Representations with Glycoinformatics via Universal Input and a Canonicalized Nomenclature

As the field of glycobiology has developed, so too have different glycan nomenclature systems, reflecting diverse cognitive and practical needs of different scientific uses. While each system serves specific purposes, this multiplicity creates challenges for usability, data integration, and knowledge sharing. Here, we present a practical framework for automated nomenclature conversion, taking any nomenclature as input, without having to declare the specific language, and using a canonicalized IUPAC-condensed format as a standardized output representation. Our implementation handles (i) all common nomenclatures, including common typos, (ii) complex cases including structural ambiguities, modifications, and uncertainty in linkage information, and (iii) different compositional representations. This Universal Input framework can translate more than 10 nomenclatures in less than 1 ms, tested on over 50,000 sequences with 95-100% coverage, enabling seamless integration of existing glycan databases and tools while maintaining the specific advantages of each representation system.

bioinformatics↗

bioRxiv2024

Navigating the Maze of Mass Spectra: A Machine-Learning Guide to Identifying Diagnostic Ions in O-Glycan Analysis

Structural details of oligosaccharides, or glycans, often carry biological relevance, which is why they are typically elucidated using tandem mass spectrometry. Common approaches to distinguish isomers rely on diagnostic glycan fragments for annotating topologies or linkages. Diagnostic fragments are often only known informally among practitioners or stem from individual studies, with unclear validity or generalizability, causing annotation heterogeneity and hampering new analysts. Drawing on a curated set of 237,000 O-glycomics spectra, we here present a rule-based machine learning workflow to uncover quantifiably valid and generalizable diagnostic fragments. This results in fragmentation rules to robustly distinguish common O-glycan isomers. We envision this resource to improve glycan annotation accuracy and concomitantly make annotations more transparent and homogeneous across analysts.

bioinformatics↗

bioRxiv2023

DataSAIL: Data Splitting Against Information Leakage

Information Leakage is an increasing problem in machine learning research. It is a common practice to report models with benchmarks, comparing them to the state-of-the-art performance on the test splits of datasets. If two or more dataset splits contain identical or highly similar samples, a model risks simply memorizing them, and hence, the true performance is overestimated, which is one form of Information Leakage. Depending on the application of the model, the challenge is to find splits that minimize the similarity between data points in any two splits. Frequently, after reducing the similarity between training and test sets, one sees a considerable drop in performance, which is a signal of removed Information Leakage. Recent work has shown that Information Leakage is an emerging problem in model performance assessment. This work presents DataSAIL, a tool for splitting biological datasets while minimizing Information Leakage in different settings. This is done by splitting the dataset such that the total similarity of any two samples in different splits is minimized. To this end, we formulate data splitting as a Binary Linear Program (BLP) following the rules of Disciplined Quasi-Convex Programming (DQCP) and optimize a solution. DataSAIL can split one-dimensional data, e.g., for property prediction, and two-dimensional data, e.g., data organized as a matrix of binding affinities between two sets of molecules, accounting for similarities along each dimension and missing values. We compute splits of the MoleculeNet benchmarks using DeepChem, the LoHi splitter, GraphPart, and DataSAIL to compare their computational speed and quality. We show that DataSAIL can impose more complex learning tasks on machine learning models and allows for a better assessment of how well the model generalizes beyond the data presented during training.

bioinformatics↗

bioRxiv2022

GlyLES: Grammar-based Parsing of Glycans from IUPAC-condensed to SMILES

Glycans are important polysaccharides on cellular surfaces that are bound to glycoproteins and glycolipids. These are one of the most common post-translational modifications of proteins in eukaryotic cells. They play important roles in protein folding, cell-cell interactions, and other extracellular processes. Changes in glycan structures may influence the course of different diseases, such as infections or cancer. Glycans are commonly represented using the IUPAC-condensed notation. IUPAC-condensed is a textual representation of the Symbol Nomenclature for Glycans (SNFG) that assigns a colored, geometrical shape to the main monosaccharides. These symbols are then connected in tree-like structures, visualizing the glycan structure on a polymeric level. Yet for a representation on the atomic level, notations such as SMILES should be used. To our knowledge, there is no easy-to-use, general, open-source, and offline tool to convert the IUPAC-condensed notation to SMILES. Here, we present the open-access Python package GlyLES for the generalizable generation of SMILES representations out of IUPAC-condensed representations. GlyLES uses a grammar to read in the monomer tree from the IUPAC-condensed notation. From this tree, the tool can compute atomic structures of each monomer based on their IUPAC-condensed descriptions. In the last step, it merges all monomers into the atomic structure of a glycan in the SMILES notation. GlyLES is the first package that allows conversion between IUPAC-condensed notations of glycans and SMILES strings. This may have multiple applications, including straightforward visualization, substructure search, molecular modelling and docking, and a new featurization strategy for machine-learning algorithms. GlyLES is available at https://github.com/kalininalab/GlyLES.

bioinformatics↗