Biology subjects

Kalinina, O. V.

Publications and source records attributed to Kalinina, O. V..

At least 19 recordsLinked to original sources

bioRxiv2026

TopFor: Automated Preparation of AMBER-Compatible Parameters for Noncanonical Amino Acids in Peptides

Peptides containing noncanonical amino acids (ncAAs) are becoming increasingly important in drug discovery, but their molecular dynamics (MD) simulation remains limited by labor-intensive residue parameterization and topology preparation. Here, we present TopFor (Topology and Residue Force-Field Parameter Preparation), an open-source, peptide-oriented workflow that automates the generation of ncAA residue templates and force-field parameter files for MD simulations with AMBER using established charge-derivation methods. TopFor supports single-residue, whole-peptide, and batch parameterization workflows. The workflow was validated using the MDM2-p53 complex by comparing native AMBER residue definitions with residues processed by TopFor using three charge-derivation methods, each evaluated in three independent 100 ns MD simulations. TopFor-generated residue definitions showed structural and conformational behavior comparable to the native AMBER representation. Applicability to more complex peptide architectures was demonstrated using the head-to-tail cyclic peptide cyclosporin A and the cyclic depsipeptide cyclohexylgriselimycin. At library scale, 1,138 of 1,214 cyclohexylgriselimycin derivatives (93.7%) successfully completed TopFor parameterization and the subsequent initial AMBER-based computational workflow across two derivatization campaigns. TopFor was further integrated into a structure-based peptide discovery workflow based on the DnaN-griselimycin complex. Six GM-derived peptides were computationally prioritized and experimentally evaluated, of which four produced SPR responses against Mycobacterium smegmatis (M. smegmatis) DnaN and three showed concentration-dependent responses. TopFor reduces the manual effort required to prepare ncAA-containing peptides for MD simulations and enables their integration into both library-scale computational screening and structure-based peptide discovery workflows. Keywords: noncanonical amino acids; peptide parameterization; molecular dynamics; AMBER; AmberTools; peptide design; high-throughput virtual screening

bioinformatics↗

bioRxiv2026

A data-driven rediscovery of the specificity-conferring code of adenylation domains in nonribosomal peptide synthetases

Nonribosomal peptide synthetases (NRPSs) are large modular enzymes that assemble structurally diverse peptides, many of pharmacological importance, including antibiotics and immunosuppressants. Within each NRPS module, the adenylation (A) domain selects the substrate to be incorporated, a choice governed by a small set of residues lining the binding pocket. For two decades, computational prediction of A-domain substrate specificity has relied on residue sets--most prominently the Stachelhaus code and the 34-residue "8 [A] code"--that were defined by spatial proximity to the substrate rather than by demonstrated predictive value. Here we revisit which residues govern substrate specificity from a purely data-driven perspective. We assembled a non-redundant dataset of 5,366 A-domain sequences (4,693 bacterial and 673 fungal) and used information-theoretic measures to rank alignment positions by their statistical association with substrate identity, without restricting candidate positions to any predefined structural shell. This procedure yielded two compact, kingdom-specific codes: IG15B (15 positions) for bacterial and IG13F (13 positions) for fungal A-domains. Both match or exceed the predictive accuracy of the 34-residue 8 [A] code while using fewer than half its positions, and both independently recover the majority of the classical Stachelhaus positions. Notably, our analysis identifies four positions (242, 280, 281, and 284) that lie outside all conventional codes yet carry non-redundant specificity information and co-localize with classical determinants on two helices flanking the binding pocket. These positions provide new candidate sites for the rational engineering of A-domain specificity. Author summaryMany clinically important drugs--including antibiotics such as vancomycin and immunosuppressants such as cyclosporin--are nonribosomal peptides, assembled by large enzymes known as nonribosomal peptide synthetases. These enzymes contain adenylation domains that act as molecular gatekeepers, each selecting one chemical building block to add to a growing peptide. Identifying which amino acids within a domain determine this choice is central both to predicting what an enzyme produces and to re-engineering it to make new compounds. For over twenty years, researchers have approached this question by selecting the amino acids that sit physically closest to the substrate. However, being close to the substrate does not guarantee that a residue actually influences substrate selection. In this work, we instead let the data decide: using thousands of adenylation domain sequences, we measured which positions are statistically most informative about the substrate, using information gain, mutual information and{chi} 2 statistic. We found that far fewer positions than conventionally used are sufficient to predict specificity, and--importantly--we identified several influential positions that earlier approaches had overlooked because they lie just beyond the conventional distance cutoff. These positions offer promising new targets for engineering these enzymes to produce novel peptide-based drugs.

bioinformatics↗

bioRxiv2026

Generative AI designs functional thiolation domains for reprogramming non-ribosomal peptide synthetases

Large language models and generative protein design promise to accelerate biotechnology, but it remains unclear whether they can engineer dynamic megasynth(et)ases whose activity depends on transient, context-specific domain interfaces. Non-ribosomal peptide synthetases (NRPSs) are an especially demanding target, yet a high-value one because they produce many clinically important natural products and offer a route to analogs that are often difficult or impractical to access by chemical synthesis. Here we integrate pretrained generative models (ESM3, ProteinMPNN and EvoDiff) with design-build-test-learn cycles and data-guided prioritization to generate 76 de novo thiolation (T) domains. We built and tested 578 recombinant NRPS variants in vivo spanning minimal, full-length and hybrid assembly lines. AI-designed T-domains supported product formation across architectures, enabled catalytically active hybrids at recombined junctions and increased yields by up to [~]3-fold relative to NRPSs carrying the native T-domain. A representative design showed improved soluble expression, refolding, and a 12 {degrees}C higher melting temperature, while molecular dynamics simulations indicated preserved global stability but reshaped, state-dependent interdomain contact networks. Together, these results establish generative design as an effective route to context-conditioned optimization and reprogramming of biosynthetic assembly lines.

synthetic biology↗

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↗

bioRxiv2026

Beyond additivity: zero-shot methods cannot predict impact of epistasis on protein properties and function

Accurate prediction of properties and function of mutated proteins is crucial for both research and industrial applications. Experimental assessment of mutations relies on biochemical techniques, which, while accurate, are costly and labour-intensive. As an alternative, computational methods have emerged as a scalable and cost-effective solution. A key challenge for predicting functional consequences of mutations is epistasis, a phenomenon where the effect of one mutation is influenced by others. We evaluated the ability of 95 zero-shot models to predict the impact of epistasis on proteins using datasets from ProteinGym. Our results demonstrate that while the current models perform well for single mutations and non-epistatic combinations of mutations, they fail to predict the effect of strongly epistatic combinations of mutations. This exposes deficiencies of the state-of-the-art models and the need for focusing on capturing complex mutational interactions, which is essential for advancing both evolutionary studies and protein design.

bioinformatics↗

bioRxiv2026

Unveiling the taxonomic diversity and unprecedented biosynthetic treasure of the phylum Myxococcota

Natural products remain vital sources of therapeutics, particularly anti-infectives, and members of the phylum Myxococcota constitute an especially rich reservoir for their discovery. Based on decades of microbiological efforts, we present 154 new Myxococcota genomes and propose a revised taxonomy expanding the number of described families from 11 to 28 and genera from 32 to 90. Comparison with an equivalent set from the prime source Actinomycetota shows that Myxococcota possess a comparable biosynthetic diversity, underscoring their promise for large-scale isolation and sequencing efforts. The vast untapped potential reflected in 2,387 uncharacterized gene cluster families is highlighted by genome mining efforts, yielding four validated compounds exhibiting novel chemistry, including myxolutamids and myxopentacins. We show that many Myxococcota-derived natural products, such as myxolutamid A and two new sorangicin derivatives, are conserved within taxonomic lineages. New described families thus bear high biosynthetic potential underpinning the importance of precise taxonomic classification guiding targeted drug discovery.

microbiology↗

bioRxiv2026

LoReMINE: Long Read-based Microbial genome mining pipeline

Microbial natural products represent a chemically diverse repertoire of small molecules with major pharmaceutical potential. Despite the increasing availability of microbial genome sequences, large-scale natural product discovery remains challenging because the existing genome mining approaches lack integrated workflows for rapid dereplication of known compounds and prioritization of novel candidates, forcing researchers to rely on multiple tools that requires extensive manual curation and expert intervention at each step. To address these limitations, we introduce LoReMINE (Long Read-based Microbial genome mining pipeline), a fully automated end-to-end pipeline that generates high-quality assemblies, performs taxonomic classification, predicts biosynthetic gene clusters (BGCs) responsible for biosynthesis of natural products, and clusters them into gene cluster families (GCFs) directly from long-read sequencing data. By integrating state-of-the-art tools into a seamless pipeline, LoReMINE enables scalable, reproducible, and comprehensive genome mining across diverse microbial taxa. The pipeline is openly available at https://github.com/kalininalab/LoReMINE and can be installed via Conda (https://anaconda.org/kalininalab/loremine), facilitating broad adoption by the natural product research community. Author summaryFor decades, microbial natural products have been a major source of medicines, with most of the clinically used antibiotics being their derivatives. Recent advances in DNA sequencing technologies now allow the reconstruction of more complete and continuous microbial genomes, revealing a vast and largely untapped diversity of biosynthetic gene clusters responsible for natural product biosynthesis. Despite these advances, large-scale natural product discovery remains difficult because current genome mining approaches rely on many separate tools and lack an integrated workflow to dereplicate known compounds and prioritize novel biosynthetic pathways. To address these limitations, we introduce LoReMINE, an automated pipeline designed to simplify microbial genome mining directly from long-read sequencing data. LoReMINE integrates genome assembly, taxonomic classification, identification of biosynthetic gene clusters, and their clustering into gene cluster families within a single, reproducible workflow. This streamlined approach enables scalable analysis across diverse microbial taxa and facilitates comprehensive exploration of microbial biosynthetic potential. The pipeline is designed for both experimental and computational researchers, helping to advance natural product research and contribute towards the discovery of new therapeutic drugs.

bioinformatics↗

bioRxiv2026

Explainability methods from machine learning detect important drugs' atoms in drug-target interactions

Predicting drug-target interactions (DTI) with graph neural networks (GNNs) is hindered by their lack of interpretability. To address this, we benchmark four explainable artificial intelligence (XAI) attribution methods on GNN models trained for kinase and GPCR targets. We assess the methods consistency through atom-level intersection-over-union and validate their biological relevance by mapping attributed atoms to 3D protein-ligand structures. While consistency across methods was modest, consensus attributions were highly enriched for atoms directly contacting the binding pocket--up to 76% within 2 [A] in the kinase-inhibitor complexes. Notably, these attributed atoms were frequently found contacting experimentally important regulatory residues, such as those in the DFG motif. This indicates that XAI methods, despite their disagreements, can identify chemically meaningful ligand features, providing a foundation for developing more interpretable GNNs in drug discovery.

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↗

bioRxiv2024

EpiPAMPAS: Rapid detection of intra-protein epistasis via parsimonious ancestral state reconstruction and counting mutations

MotivationAn epistatic interaction is a non-linear combination of effects of individual mutations on fitness. This type of interaction is a known driver for evolution, as they alter the organisms fitness and adaptability. In this work we introduce EpiPAMPAS, a statistical method that is based on multiple sequence alignments (MSA) and detecting mutations in the same direction on a dendrogram instead of a phylogenetic tree using the Sankoff algorithm. ResultsWe tested EpiPAMPAS on both simulated and real sequencing data. On the simulated data, our method was able to detect the simulated epistatic pairs with very low p-value. In a real-world application, we tested the influenza proteins N1, N2, H1, H3 and HIV-1 envelope protein subtypes A, B and C. We observe that EpiPAMPAS detects fewer interacting pairs than comparable statistical approaches, although the overlap between detected positions is good. Moreover, some of the amino acids from the detected pairs are known to be deleterious for viral fitness. AvailabilityEpiPAMPAS is available under MIT license at https://github.com/kalininalab/EpiPAMPAS

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↗

bioRxiv2023

Machine learning and phylogenetic analysis allow for predicting antibiotic resistance in M. tuberculosis

Antimicrobial resistance (AMR) poses a significant global health threat, and an accurate prediction of bacterial resistance patterns is critical for effective treatment and control strategies. In recent years, machine learning (ML) approaches have emerged as powerful tools for analyzing large-scale bacterial AMR data. However, ML methods often ignore evolutionary relationships among bacterial strains, which can greatly impact performance of the ML methods, especially if resistance-associated features are attempted to be detected. Genomewide association studies (GWAS) methods like linear mixed models accounts for the evolutionary relationships in bacteria, but they uncover only highly significant variants which have already been reported in literature. In this work, we introduce a novel phylogeny-related parallelism score (PRPS), which measures whether a certain feature is correlated with the population structure of a set of samples. We demonstrate that PRPS can be used, in combination with SVM- and random forest-based models, to reduce the number of features in the analysis, while simultaneously increasing models performance. We applied our pipeline to publicly available AMR data from PATRIC database for Mycobacterium tuberculosis against six common antibiotics. Using our pipeline, we re-discovered known resistance-associated mutations as well as new candidate mutations which can be related to resistance and not previously reported in the literature.

bioinformatics↗

bioRxiv2023

PanPA: generation and alignment of panproteome graphs

MotivationCompared to eukaryotes, prokaryote genomes are more diverse through different mechanisms, including a higher mutation rate and horizontal gene transfer. Therefore, using a linear representative reference can cause a reference bias. Graph-based pangenome methods have been developed to tackle this problem. However, comparisons in DNA space is still challenging due to this high diversity. In contrast, amino acids have higher similarity due to evolutionary constraints, resulting in conserved amino acids that, however, may be encoded by several synonymous codons. Coding regions cover the majority of the genome in prokaryotes. Thus, building panproteomes leverages the high sequence similarity while not losing much of the genome in non-coding regions. ResultsWe present PanPA, a method that takes a set of multiple sequence alignments (MSAs) of proteins or protein clusters, indexes them, and builds a graph for each MSA. In the querying step, it can align DNA or amino acid sequences back to these graphs. We first showcase that PanPA generates correct alignments on a panproteome from 1,350 E. coli. To demonstrate that panproteomes allow longer phylogenetic distance comparison, we compare DNA and protein alignments from 1,073 S. enterica assemblies against E. coli reference genome, pangenome, and panproteome using BWA, GraphAligner, and PanPA respectively, where PanPA was able to produce around 22% more alignments. We also aligned DNA short-reads WGS sample from S. enterica against the E. coli reference with BWA and the panproteome with PanPA, where PanPA was able to find alignment for 69% of the reads compared to 5% with BWA AvailabilityPanPA is available at https://github.com/fawaz-dabbaghieh/PanPA Contactfawaz@hhu.de, olga.kalinina@helmholtz-hzi.de Supplementary informationSupplementary data are available at Bioinformatics online.

bioinformatics↗

bioRxiv2022

Simulated tempering-enhanced umbrella sampling improves convergence of free energy calculations of drug membrane permeation

Molecular dynamics simulations have been widely used to study solute permeation across biological membranes. The potential of mean force (PMF) for solute permeation is typically computed using enhanced sampling techniques such as umbrella sampling (US). For bulky drug-like permeants, however, obtaining converged PMFs remains challenging and often requires long simulation times, resulting in an unacceptable computational cost. Here, we augmented US with simulated tempering, introducing Simulated Tempering-enhanced US (STeUS), to improve the convergence of PMF calculations for the permeation of methanol and three common drug molecules. Simulate tempering helps to enhance sampling by varying the temperature of the system along a pre-defined temperature ladder. To obtain sufficient sampling of the umbrella histograms, which were computed only from the ground temperature, we modified the simulation time fraction spent at the ground temperature between 1/K and 50%, where K is the number of ST temperature states. We found that STeUS accelerates convergence compared to standard US, and the benefit of STeUS is system-dependent. For bulky molecules, for which standard US poorly converged, the application of ST was highly successful, leading to a more than five-fold accelerated convergence of the PMFs. For the small methanol solute, for which conventional US converges moderately, the application of ST is only beneficial if 50% of the STeUS simulation time is spent at the ground temperature. This study establishes STeUS as an efficient and simple method for PMF calculations, thereby strongly reducing the computational cost of routine high-throughput studies of drug permeability.

biophysics↗

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↗

bioRxiv2021

MetaProFi: A protein-based Bloom filter for storing and querying sequence data for accurate identification of functionally relevant genetic variants

Technological advances of next-generation sequencing present new computational challenges to develop methods to store and query these data in time- and memory-efficient ways. We present MetaProFi (https://github.com/kalininalab/metaprofi), a Bloom filter-based tool that, in addition to supporting nucleotide sequences, can for the first time directly store and query amino acid sequences and translated nucleotide sequences, thus bringing sequence comparison to a more biologically relevant protein level. Owing to the properties of Bloom filters, it has a zero false-negative rate, allows for exact and inexact searches, and leverages disk storage and Zstandard compression to achieve high time and space efficiency. We demonstrate the utility of MetaProFi by indexing UniProtKB datasets at organism- and at sequence-level in addition to the indexing of Tara Oceans dataset and the 2585 human RNA-seq experiments, showing that MetaProFi consumes far less disk space than state-of-the-art-tools while also improving performance.

bioinformatics↗