Biology subjects

Belinkov, Y.

Publications and source records attributed to Belinkov, Y..

7 recordsLinked to original sources

bioRxiv2026

Phylogenetic tree inference using generative models

Accurate inference of phylogenetic trees is fundamental to evolutionary biology, yet existing methods rely on complex pipelines involving multiple sequence alignment, explicit evolutionary models, and computationally intensive tree search procedures. Here, we present BetaInfer, a generative framework that reformulates phylogenetic tree inference as a sequence transduction problem. BetaInfer leverages hybrid transformer-based architectures to directly map sets of unaligned sequences to phylogenetic trees represented in Newick format. Trained on large-scale simulated evolutionary data with known ground truth, BetaInfer learns to capture complex evolutionary signals directly from sequence data. Ensemble-based generation of multiple candidate trees further improves robustness, reducing reconstruction error by over 30% relative to single predictions. Across extensive evaluations on both simulated and empirical datasets, BetaInfer achieves competitive performance relative to state-of-the-art phylogenetic pipelines, matching, and in some cases exceeding, the accuracy of established likelihood-based and distance-based methods under a wide range of conditions. Interpretability analyses reveal that BetaInfer leverages internal pairwise-distance computations to synthesize evolutionary relationships into an integrated, global representation that supports direct tree generation. Together, these results demonstrate that generative models can serve as a viable and scalable alternative to standard phylogenetic pipelines.

bioinformatics↗

bioRxiv2026

Ancestral sequence reconstruction using generative models

Ancestral sequence reconstruction (ASR) is a foundational task in evolutionary biology, providing insights into the molecular past and guiding studies of protein function and adaptation. Conventional ASR methods rely on a multiple sequence alignment (MSA), a phylogenetic tree, and an evolutionary model. However, the underlying alignments and trees are often uncertain, and existing models typically focus on substitutions and do not explicitly account for insertion-deletion (indel) processes. Here, we introduce BetaReconstruct, a novel generative approach to ASR that harnesses recent advances in natural language processing (NLP) and hybrid transformer architectures. Our model was initially trained on large-scale simulated datasets with gold-standard ancestral sequences and subsequently on real-world protein sequences. The reconstruction requires neither MSAs nor phylogenetic trees. We demonstrate that BetaReconstruct generalizes robustly across diverse evolutionary scenarios and reconstructs ancestral sequences more accurately than maximum-likelihood-based pipelines. We additionally provide evidence that the generative-model ASR approach is also more accurate when analyzing empirical datasets. This work provides a scalable, alignment-free strategy for ASR and highlights the ability of data-driven models to capture evolutionary signals beyond the reach of traditional methods.

bioinformatics↗

bioRxiv2024

Protein2Text: Providing Rich Descriptions for Protein Sequences

Understanding the functionality of proteins has been a focal point of biological research due to their critical roles in various biological processes. Unraveling protein functions is essential for advancements in medicine, agriculture, and biotechnology, enabling the development of targeted therapies, engineered crops, and novel biomaterials. However, this endeavor is challenging due to the complex nature of proteins, requiring sophisticated experimental designs and extended timelines to uncover their specific functions. Public large language models (LLMs), though proficient in natural language processing, struggle with biological sequences due to the unique and intricate nature of biochemical data. These models often fail to accurately interpret and predict the functional and structural properties of proteins, limiting their utility in bioinformatics. To address this gap, we introduce BetaDescribe, a collection of models designed to generate detailed and rich textual descriptions of proteins, encompassing properties such as function, catalytic activity, involvement in specific metabolic pathways, subcellular localizations, and the presence of particular domains. The trained BetaDescribe model receives protein sequences as input and outputs a textual description of these properties. BetaDescribes starting point was the LLAMA2 model, which was trained on trillions of tokens. Next, we trained our model on datasets containing both biological and English text, allowing biological knowledge to be incorporated. We demonstrate the utility of BetaDescribe by providing descriptions for proteins that share little to no sequence similarity to proteins with functional descriptions in public datasets. We also show that BetaDescribe can be harnessed to conduct in-silico mutagenesis procedures to identify regions important for protein functionality without needing homologous sequences for the inference. Altogether, BetaDescribe offers a powerful tool to explore protein functionality, augmenting existing approaches such as annotation transfer based on sequence or structure similarity.

bioinformatics↗

bioRxiv2024

BetaAlign: a deep learning approach for multiple sequence alignment

The multiple sequence alignment (MSA) problem is a fundamental pillar in bioinformatics, comparative genomics, and phylogenetics. Here we characterize and improve BetaAlign, the first deep learning aligner, which substantially deviates from conventional algorithms of alignment computation. BetaAlign draws on natural language processing (NLP) techniques and trains transformers to map a set of unaligned biological sequences to an MSA. We show that our approach is highly accurate, comparable and sometimes better than state-of-the-art alignment tools. We characterize the performance of BetaAlign and the effect of various aspects on accuracy; for example, the size of the training data, the effect of different transformer architectures, and the effect of learning on a subspace of indel-model parameters (subspace learning). We also introduce a new technique that leads to improved performance compared to our previous approach. Our findings further uncover the potential of NLP-based approaches for sequence alignment, highlighting that AI-based methodologies can substantially challenge classic tasks in phylogenomics and bioinformatics.

bioinformatics↗

bioRxiv2023

OM2Seq: Learning retrieval embeddings for optical genome mapping

MotivationGenomics-based diagnostic methods that are quick, precise, and economical are essential for the advancement of precision medicine, with applications spanning the diagnosis of infectious diseases, cancer, and rare diseases. One technology that holds potential in this field is optical genome mapping (OGM), which is capable of detecting structural variations, epigenomic profiling, and microbial species identification. It is based on imaging of linearized DNA molecules that are stained with fluorescent labels, that are then aligned to a reference genome. However, the computational methods currently available for OGM fall short in terms of accuracy and computational speed. ResultsThis work introduces OM2Seq, a new approach for the rapid and accurate mapping of DNA fragment images to a reference genome. Based on a Transformer-encoder architecture, OM2Seq is trained on acquired OGM data to efficiently encode DNA fragment images and reference genome segments to a common embedding space, which can be indexed and efficiently queried using a vector database. We show that OM2Seq significantly outperforms the baseline methods in both computational speed (by two orders of magnitude) and accuracy. Availability and implementationhttps://github.com/yevgenin/om2seq Contactyoavsh@bm.technion.ac.il

bioinformatics↗

bioRxiv2023

Effect of Tokenization on Transformers for Biological Sequences

Deep learning models are transforming biological research. Many bioinformatics and comparative genomics algorithms analyze genomic data, either DNA or protein sequences. Examples include sequence alignments, phylogenetic tree inference and automatic classification of protein functions. Among these deep learning algorithms, models for processing natural languages, developed in the natural language processing (NLP) community, were recently applied to biological sequences. However, biological sequences are different than natural languages, such as English, and French, in which segmentation of the text to separate words is relatively straightforward. Moreover, biological sequences are characterized by extremely long sentences, which hamper their processing by current machine-learning models, notably the transformer architecture. In NLP, one of the first processing steps is to transform the raw text to a list of tokens. Deep-learning applications to biological sequence data mostly segment proteins and DNA to single characters. In this work, we study the effect of alternative tokenization algorithms on eight different tasks in biology, from predicting the function of proteins and their stability, through nucleotide sequence alignment, to classifying proteins to specific families. We demonstrate that applying alternative tokenization algorithms can increase accuracy and at the same time, substantially reduce the input length compared to the trivial tokenizer in which each character is a token. Furthermore, applying these tokenization algorithms allows interpreting trained models, taking into account dependencies among positions. Finally, we trained these tokenizers on a large dataset of protein sequences containing more than 400 billion amino acids, which resulted in over a three-fold decrease in the number of tokens. We then tested these tokenizers trained on large-scale data on the above specific tasks and showed that for some tasks it is highly beneficial to train database-specific tokenizers. Our study suggests that tokenizers are likely to be a critical component in future deep-network analysis of biological sequence data.

bioinformatics↗

bioRxiv2022

Harnessing machine translation methods for sequence alignment

The sequence alignment problem is one of the most fundamental problems in bioinformatics and a plethora of methods were devised to tackle it. Here we introduce BetaAlign, a novel methodology for aligning sequences using a natural language processing (NLP) approach. BetaAlign accounts for the possible variability of the evolutionary process among different datasets by using an ensemble of transformers, each trained on millions of samples generated from a different evolutionary model. Our approach leads to outstanding alignment accuracy, often outperforming commonly used methods, such as MAFFT, DIALIGN, ClustalW, T-Coffee, and MUSCLE. Notably, the utilization of deep-learning techniques for the sequence alignment problem brings additional advantages, such as automatic feature extraction that can be leveraged for a variety of downstream analysis tasks.

evolutionary biology↗