Abstract Deciphering protein function is fundamental to advancements in medicine and biotechnology. However, conventional experimental characterization remains resource-intensive. Public large language models (LLMs), though proficient in natural language processing, 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, designed to generate detailed and rich textual descriptions of proteins, including their function, catalytic activity, involvement in specific metabolic pathways, subcellular localizations, and the presence of specific domains. The trained BetaDescribe model receives protein sequences as input and outputs a textual description of these properties. BetaDescribe starting point was the LLAMA2 model, which was trained on trillions of tokens. Our model was next trained on datasets containing both biological and English text, which allowed the incorporation of biological knowledge. In addition to the description generator, BetaDescribe comprises multiple validator models and a judge, which together enable accurate ranking of alternative generated descriptions. 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. Using in silico mutagenesis, we further show that BetaDescribe relies on functionally important regions, as part of its prediction, suggesting that the model identifies regions of importance for the protein functionality without needing homologous sequence. BetaDescribe offers a powerful tool to explore protein functionality, augmenting existing approaches such as annotation transfer based on sequence or structure similarity.

Abstract Sequence simulations along phylogenetic trees play an important role in numerous molecular evolution studies such as benchmarking algorithms for ancestral sequence reconstruction, multiple sequence alignment, and phylogeny inference. They are also used in phylogenetic model-selection tasks, including the inference of selective forces. Recently, Approximate Bayesian Computation (ABC)-based approaches have been developed for inferring parameters of complex evolutionary models, which rely on massive generation of simulated data. For all these applications, computationally efficient sequence simulators are essential.

Abstract Large-scale analyses of bacterial genomic datasets contribute to the comprehensive characterization of complex microbial dynamics among different strains and species. Such analyses often include open reading frame extraction, orthogroup inference, phylogeny reconstruction, and functional annotation of proteins. We have previously developed the M1CR0B1AL1Z3R web server, a “one-stop shop” for conducting comparative analyses of microbial genomes. Here, we present M1CR0B1AL1Z3R 2.0, an enhanced version that includes a new user-friendly web interface and an improved, optimized, and more versatile pipeline. The following features were added: (i) a computationally efficient inference of orthogroups, which allows the analysis of up to 2000 bacterial genomes; (ii) genome completeness analysis; (iii) lists of orphan genes per genome; (iv) genome numeric representation that allows detecting genomic rearrangement events; (v) codon bias analysis; (vi) annotation of orthogroups with KEGG Orthology numbers; and (vii) a map of pairwise average nucleotide identity values. M1CR0B1AL1Z3R 2.0 is freely available at https://microbializer.tau.ac.il/.

Abstract Multiple sequence alignments (MSAs) are extensively used in biology, from phylogenetic reconstruction to structure and function prediction. Here, we suggest an out-of-the-box approach for the inference of MSAs, which relies on algorithms developed for processing natural languages. We show that our artificial intelligence (AI)-based methodology can be trained to align sequences by processing alignments that are generated via simulations, and thus different aligners can be easily generated for datasets with specific evolutionary dynamics attributes. We expect that natural language processing (NLP) solutions will replace or augment classic solutions for computing alignments, and more generally, challenging inference tasks in phylogenomics.

Abstract The two apolipoprotein L1 (APOL1) variants, G1 and G2, are common in populations of sub-Saharan African ancestry. Individuals with two of these alleles (G1 or G2) have an increased risk for a spectrum of non-diabetic chronic kidney diseases. However, these variants are typically not observed outside of populations that self-identify as current continental Africans or having clear recent African ancestry such as, most notably, African Americans, and other large population groups in the Americas and several European countries. We hypothesized that the diverse ethnic groups within the Israeli population may exhibit varying levels of recent African ancestry. Therefore, it is plausible that APOL1 risk alleles might be present even in individuals who do not self-identify as being of sub-Saharan African descent.

Abstract Deep-learning models are transforming biological research, including many bioinformatics and comparative genomics algorithms, such as 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 from 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.

Abstract In the last decade, advances in sequencing technology have led to an exponential increase in genomic data. These new data have dramatically changed our understanding of the evolution and function of genes and genomes. Despite improvements in sequencing technologies, identifying contaminated reads remains a complex task for many research groups. Here, we introduce GenomeFLTR, a new web server to filter contaminated reads. Reads are compared against existing sequence databases from various representative organisms to detect potential contaminants. The main features implemented in GenomeFLTR are: (i) automated updating of the relevant databases; (ii) fast comparison of each read against the database; (iii) the ability to create user-specified databases; (iv) a user-friendly interactive dashboard to investigate the origin and frequency of the contaminations; (v) the generation of a contamination-free file. Availability: https://genomefltr.tau.ac.il/.

Abstract 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 methodology for aligning sequences using an 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 alignment accuracy that is similar and often better than commonly used methods, such as MAFFT, DIALIGN, ClustalW, T-Coffee, PRANK, and MUSCLE.

Abstract Type III effectors are proteins injected by Gram-negative bacteria into eukaryotic hosts. In many plant and animal pathogens, these effectors manipulate host cellular processes to the benefit of the bacteria. Type III effectors are secreted by a type III secretion system that must “classify” each bacterial protein into one of two categories, either the protein should be translocated or not. It was previously shown that type III effectors have a secretion signal within their N-terminus, however, despite numerous efforts, the exact biochemical identity of this secretion signal is generally unknown. Computational characterization of the secretion signal is important for the identification of novel effectors and for better understanding the molecular translocation mechanism. In this work we developed novel machine-learning algorithms for characterizing the secretion signal in both plant and animal pathogens. Specifically, we represented each protein as a vector in high-dimensional space using Facebook’s protein language model. Classification algorithms were next used to separate effectors from non-effector proteins. We subsequently curated a benchmark dataset of hundreds of effectors and thousands of non-effector proteins. We showed that on this curated dataset, our novel approach yielded substantially better classification accuracy compared to previously developed methodologies. We have also tested the hypothesis that plant and animal pathogen effectors are characterized by different secretion signals. Finally, we integrated the novel approach in Effectidor, a web-server for predicting type III effector proteins, leading to a more accurate classification of effectors from non-effectors.

Abstract 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.

Abstract 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.

Abstract The SARS-Coronavirus-2 (SARS-CoV-2) driven pandemic was first recognized in late 2019, and the first few months of its evolution were relatively clock-like, dominated mostly by neutral substitutions. In contrast, the second year of the pandemic was punctuated by the emergence of several variants that bore evidence of dramatic evolution. Here, we compare and contrast evolutionary patterns of various variants, with a focus on the recent Delta variant. Most variants are characterized by long branches leading to their emergence, with an excess of non-synonymous substitutions occurring particularly in the Spike and Nucleocapsid proteins. In contrast, the Delta variant that is now becoming globally dominant, lacks the signature long branch, and is characterized by a step-wise evolutionary process that is ongoing. Contrary to the “star-like” topologies of other variants, we note the formation of several distinct clades within Delta that we denote as clades A-E. We find that sequences from the Delta D clade are dramatically increasing in frequency across different regions of the globe. Delta D is characterized by an excess of non-synonymous mutations, mostly occurring in ORF1a/b, some of which occurred in parallel in other notable variants. We conclude that the Delta surge these days is composed almost exclusively of Delta D, and discuss whether selection or random genetic drift has driven the emergence of Delta D.