Biology subjects

Bezshapkin, V.

Publications and source records attributed to Bezshapkin, V..

5 recordsLinked to original sources

bioRxiv2026

Scaling and democratising structure-based protein function prediction with metagenomic-deepFRI

High-quality protein structure models have become widely available, offering insights into protein function, yet they remain underutilized. Here, we introduce metagenomic-deepFRI, a framework incorporating structural templates into functional annotation pipelines at speeds comparable to sequence-alignment methods. Notably, structural features improved GO term prediction confidence and Information Content by up to 50%. Applied to metagenomic datasets, the framework achieves nearly 90% annotation coverage, enabling protein function inference without explicit orthology-based transfer.

bioinformatics↗

bioRxiv2026

TM-Vec 2: Accelerated Protein Homology Detection for Structural Similarity

Understanding protein function is an essential aspect of many biological applications. The exponential growth of protein sequence data has created a critical throughput bottleneck for structural homology detection: While billions of protein sequences have been identified from DNA sequencing data, the number of protein folds underlying biology is surprisingly limited, likely numbering tens of thousands. The "sequence-fold gap" limits the success of functional annotation methods that rely on sequence homology, especially for newly sequenced genomes. TM-Vec is a deep learning architecture that can predict TM-scores as a metric of structural similarity directly from sequence pairs, bypassing true structural alignment. However, the computational demands of its protein language model (PLM) embeddings create a significant bottleneck for large-scale database searches. In this work we present TM-Vec 2s, a highly efficient model created through distillation from a foundational teacher model. Benchmarks on the CATH and SCOPe domains for large-scale database queries showed that TM-Vec 2s is 185x faster than the original TM-Vec, while achieving higher TM-score prediction accuracy. It is even more efficient than the structure-informed search implemented in Foldseek, while showing strong competition in identifying remote homology between protein molecules. TM-Vec 2s significantly expands scalable, efficient exploration of protein structural homology space.

bioinformatics↗

bioRxiv2025

Uncovering Cas9 PAM diversity through metagenomic mining and machine learning

Recognition of protospacer adjacent motifs (PAMs) is crucial for target site recognition by CRISPR-Cas systems. In genome editing applications, the requirement for specific PAM sequences at the target locus imposes substantial constraints, driving efforts to search for novel Cas9 orthologs with extended or alternative PAM compatibilities. Here, we present CRISPR-PAMdb, a comprehensive and publicly accessible database compiling Cas9 protein sequences from 3.8 million bacterial and archaeal genomes and PAM profiles from 7.4 million phage and plasmid sequences. Through spacer-protospacer alignment, we inferred consensus PAM preferences for 8,003 unique Cas9 clusters. To extend PAM discovery beyond traditional alignment-based approaches, we developed CICERO, a machine learning model predicting PAM preferences directly from Cas9 protein sequences. Built on the ESM2 protein language model and trained on the CRISPR-PAMdb database, CICERO achieved an average accuracy of 0.68 on test data and 0.75 on experimentally validated Cas9 orthologs. For Cas9 clusters where alignment-based predictions were infeasible, CICERO generated PAM profiles for an additional 50,308 Cas9 proteins, including 17,453 high-confidence predictions with accuracies above 0.86. CRISPR-PAMdb, alongside CICERO models, enables large-scale exploration of PAM diversity across Cas9 proteins, accelerating design of next-generation CRISPR-Cas9 tools for precise genome engineering.

synthetic biology↗

bioRxiv2022

Spatial variability of the microbiome in chronic rhinosinusitis is associated with the patients' clinical characteristics but not with sinus ostia occlusion

BackgroundThe sinus microbiome in patients with chronic rhinosinusitis (CRS) is considered homogenous across the sinonasal cavity. The middle nasal meatus is the recommended sampling site for 16S rRNA sequencing. However, individuals with unusually high between-site variability between the middle meatus and the sinuses were identified in previous studies. This study aimed to identify which factors determine increased microbial heterogeneity between sampling sites in the sinuses. MethodologyIn this cross-sectional study samples for 16S rRNA sequencing were obtained from the middle meatus, the maxillary and the frontal sinus in 50 patients with CRS. The microbiome diversity between sampling sites was analysed in relation to the size of the sinus ostia and clinical metadata. ResultsIn approximately 15% of study participants, the differences between sampling sites within one patient were greater than between the patient and other individuals. Contrary to a popular hypothesis, obstruction of the sinus ostium resulted in decreased dissimilarity between the sinus and the middle meatus. The dissimilarity between the sampling sites was patient-specific: greater between-sinus differences were associated with greater meatus-sinus differences, regardless of the drainage pathway patency. Decreased spatial variability was observed in patients with nasal polyps and extensive mucosal changes in the sinuses. ConclusionsSampling from the middle meatus is not universally representative of the sinus microbiome. The differences between sites cannot be predicted from the patency of communication pathways between them.

microbiology↗

bioRxiv2022

Comprehensive function annotation of metagenomes and microbial genomes using a deep learning-based method

Comprehensive protein function annotation is essential for understanding microbiome-related disease mechanisms in the host organisms. Still, a large portion of human gut microbial proteins lack functional annotation. Here, we have developed a new metagenome analysis workflow integrating de novo genome reconstruction, taxonomic profiling and deep learning-based functional annotations from DeepFRI. We validate DeepFRI functional annotations by comparing them to orthology-based annotations from eggNOG on a set of 1,070 infant metagenome samples from the DIABIMMUNE cohort. Using the workflow, we have generated a sequence catalogue of 1.9 million non-redundant microbial genes. The functional annotations revealed 70% concordance between GO annotations predicted by DeepFRI and eggNOG. However, DeepFRI improved the annotation coverage, with 99% of the gene catalogue obtaining GO molecular function annotations, albeit less specific compared to eggNOG. Additionally, we construct pan-genomes in a reference-free manner using high-quality metagenome assembled genomes (MAGs) and analyse the associated annotations. eggNOG annotated more genes on well-studied organisms such as Escherichia coli while DeepFRI was less sensitive to taxa. This workflow will contribute to novel understanding of the functional signature of the human gut microbiome in health and disease as well as guide future metagenomics studies.

bioinformatics↗