Biology subjects

Kardymon, O.

Publications and source records attributed to Kardymon, O..

6 recordsLinked to original sources

bioRxiv2026

GENATATORs: ab initio Gene Annotation With DNA Language Models

Inference of gene structure and location from genome sequences - known as de novo gene annotation - is a fundamental task in biological research. However, sequence grammar encoding gene structure is complex and poorly understood, often requiring costly transcriptomic data for accurate gene annotation. In this work, we benchmark current solutions and develop new methods of gene annotation. We show that pre-trained DNA language model (DNA LM) embeddings do not capture the features necessary for precise gene segmentation, and that task-specific fine-tuning remains essential. We comprehensively evaluate the impact of model architecture, training strategy, receptive field size, dataset composition, and data augmentations on gene segmentation performance. We revisit standard evaluation protocols, showing that commonly used per-token and per-sequence metrics fail to capture the challenges of real-world gene annotation. We introduce and theoretically justify new biologically grounded metrics, along with benchmarking datasets that better capture annotation quality. We show that fine-tuned DNA LMs outperform existing annotation tools, generalizing across species separated by hundreds of millions of years from those seen during training, and providing segmentation of previously intractable non-coding transcripts and untranslated regions of protein-coding genes. Our results thus provide a foundation for new biological applications centered on accurate gene annotation.

bioinformatics↗

bioRxiv2026

GeomMotif: A Benchmark for Arbitrary Geometric Preservation in Protein Generation

AO_SCPLOWBSTRACTC_SCPLOWMotif scaffolding in protein design involves generating complete protein structures while preserving the 3D geometry of designated structural fragments, analogous to image outpainting in computer vision. Current benchmarks focus on functional motifs, leaving general geometric preservation capabilities largely untested. We introduce GeomMotif, a systematic benchmark that evaluates arbitrary structural fragment preservation without requiring functional specificity. We construct 57 benchmark tasks, each containing one or two motifs with up to 7 continuous fragments, by sampling from the Protein Data Bank (PDB) to ensure a ground-truth, solvable conformation for every problem. The tasks are characterized by comprehensive structural and physicochemical properties: size, geometric context, secondary structure, hydrophobicity, charge, and degree of burial. These features enable detailed performance analysis beyond simple success rates, revealing model-specific strengths and limitations. We evaluate models using scRMSD and pLDDT for geometric fidelity and clustering for structural diversity and novelty. Our results show that sequence-based and structure-based approaches find different tasks challenging, and that geometric preservation varies significantly with structural and physicochemical context. GeomMotif provides insights complementary to function-focused benchmarks and establishes a foundation for improving protein generative models.

bioinformatics↗

bioRxiv2024

Towards Robust Evaluation of Protein Generative Models: A Systematic Analysis of Metrics

AO_SCPLOWBSTRACTC_SCPLOWThe rapid advancement of protein generative models necessitates robust and principled methods for their evaluation and comparison. As new models of increasing complexity continue to emerge, it is crucial to ensure that the metrics used for assessment are well-understood and reliable. In this work, we conduct a systematic investigation of commonly used metrics for evaluating protein generative models, focusing on quality, diversity, and distributional similarity. We examine the behavior of these metrics under various conditions, including synthetic perturbations and real-world generative models. Our analysis explores different design choices, parameters, and underlying representation models, revealing how these factors influence metric performance. We identify several challenges in applying these metrics, such as sample size dependencies, sensitivity to data distribution shifts, and computational efficiency trade-offs. By testing metrics on both synthetic datasets with controlled properties and outputs from state-of-the-art protein generators, we provide insights into each metrics strengths, limitations, and practical applicability. Based on our findings, we offer a set of practical recommendations for researchers to consider when evaluating protein generative models, aiming to contribute to the development of more robust and meaningful evaluation practices in the field of protein design.

bioinformatics↗

bioRxiv2024

GENA-Web - GENomic Annotations Web Inference using DNA language models

The advent of advanced sequencing technologies has significantly reduced the cost and increased the feasibility of assembling high-quality genomes. Yet, the annotation of genomic elements remains a complex challenge. Even for species with comprehensively annotated reference genomes, the functional assessment of individual genetic variants is not straightforward. In response to these challenges, recent breakthroughs in machine learning have led to the development of DNA language models. These transformer-based architectures are designed to tackle a wide array of genomic tasks with enhanced efficiency and accuracy. In this context, we introduce GENA-Web, a web-based platform that consolidates a suite of genome annotation tools powered by DNA language models. The version of GENA-Web presented here encompasses a diverse set of models trained on human data, including the prediction of promoter activity, annotation of splice sites, determination of various chromatin features, and a model for scoring of enhancer activity in Drosophila. GENA-Web is accessible online at https://dnalm.airi.net/

bioinformatics↗

bioRxiv2023

GENA-LM: A Family of Open-Source Foundational Models for Long DNA Sequences

Recent advancements in genomics, propelled by artificial intelligence, have unlocked unprecedented capabilities in interpreting genomic sequences, mitigating the need for exhaustive experimental analysis of complex, intertwined molecular processes inherent in DNA function. A significant challenge, however, resides in accurately decoding genomic sequences, which inherently involves comprehending rich contextual information dispersed across thousands of nucleotides. To address this need, we introduce GENA-LM, a suite of transformer-based foundational DNA language models capable of handling input lengths up to 36,000 base pairs. Notably, integrating the newly-developed Recurrent Memory mechanism allows these models to process even larger DNA segments. We provide pre-trained versions of GENA-LM, including multispecies and taxon-specific models, demonstrating their capability for fine-tuning and addressing a spectrum of complex biological tasks with modest computational demands. While language models have already achieved significant breakthroughs in protein biology, GENA-LM showcases a similarly promising potential for reshaping the landscape of genomics and multi-omics data analysis. All models are publicly available on GitHub https://github.com/AIRI-Institute/GENA_LM and HuggingFace https://huggingface.co/AIRI-Institute. In addition, we provide a web-service https://dnalm.airi.net/ allowing user-friendly DNA annotation with GENA-LM models.

bioinformatics↗

bioRxiv2022

Cell type-specific interpretation of noncoding variants using deep learning-based methods

Interpretation of non-coding genomic variants is one of the most important challenges in human genetics. Machine learning methods have emerged recently as a powerful tool to solve this problem. State-of-the-art approaches allow prediction of transcriptional and epigenetic effects caused by non-coding mutations. However, these approaches require specific experimental data for training and can not generalize across cell types where required features were not experimentally measured. We show here that available epigenetic characteristics of human cell types are extremely sparse, limiting those approaches that rely on specific epigenetic input. We propose a new neural network architecture, DeepCT, which can learn complex interconnections of epigenetic features and infer unmeasured data from any available input. Furthermore, we show that DeepCT can learn cell type-specific properties, build biologically meaningful vector representations of cell types and utilize these representations to generate cell type-specific predictions of the effects of non-coding variations in the human genome.

genetics↗