sequence-to-function modeling

A Taxonomy-Informed Sparse DNA Foundation Model for Microbial Genomics

A sparse mixture-of-experts DNA model conditioned on hyperbolic taxonomy embeddings learns better microbial representations than its taxonomy-free twin and comes close to Evo2-7B in probing and fine-tuning at lower compute.

Accessing Enzyme Kinetic Data and Prediction Methods at Scale

OpenKinetics Predictor unifies thirteen enzyme kinetic predictors behind one interface and API; on E. coli iML1515, eight kcat predictors correlate pairwise at r 0.08 to 0.67.

Analyzing Genomic Foundation Models for Viral Sequence Identification

This study evaluates genomic foundation models for viral sequence classification, finding that NTv3-650M achieves high accuracy comparable to BLAST on standard-length sequences.

Pruning the Search, Not the Signal: Adaptive-Banding Needleman-Wunsch Sequence Alignment via Protein Language Model Confidence

This paper introduces AB-NW, an adaptive-banding Needleman-Wunsch alignment method that improves speed while maintaining accuracy on challenging sequence alignment tasks.

De novo design of small cyclic peptide inhibitors from non-canonical amino acids by cofolding-guided search

This paper introduces nCycle-Forge, a computational method for designing cyclic peptides that outperforms existing approaches in hit rate and potency against two targets.

Coevolutionary mining of prokaryotic non-coding elements with a genome language model

Minerva extracts RNA base-pairing, protein-contact and repeat maps from a genome language model without alignments, flagging unannotated structured loci and a phage ncRNA array reverse-transcribed into short cDNAs.

Multi-attribute characterisation of mRNA via MazF endoribonuclease and LC-MS workflows

The paper presents two LC-MS workflows using MazF endoribonuclease to characterise mRNA sequence identity, 5' capping efficiency, and poly(A) tail length and heterogeneity.

Lossless compression of protein databases for efficient and accurate metagenomic sequence classification with Centrifuger

The paper introduces a lossless compression algorithm for protein databases, improving memory efficiency and classification accuracy in Centrifuger for metagenomic analysis.

BOTANIC-1: a series of long-context plant genomic foundation models in the agentic era

Bidirectional Mamba2 plant genomic language models (318M to 3.2B parameters) trained on 320 land-plant genomes top a 22-task frozen-model aggregate; a small variant reaches 131,072 bp context.

Optimized Multiple Circular Sequence Alignment for Cyclic Peptide Motif Discovery

The paper optimizes multiple circular sequence alignment for cyclic peptides, achieving faster performance while maintaining alignment quality.

Ancestral Sequences Cannot be Accurately Reconstructed via Interpolation in a Variational Autoencoder's Latent Space

This study tests using a variational autoencoder to reconstruct ancestral sequences by interpolating in its latent space, finding it less accurate than standard methods despite containing evolutionary signal.

A diffusion model of viral evolution predicts mutation fitness and evolutionary trajectories

VES predicts viral mutation fitness and evolutionary trajectories using a diffusion model trained on protein sequences, outperforming existing models in mutation fitting and forecasting future mutations.

Conditional Generation And Inpainting Of Non-coding RNA Sequences With Masked Discrete Diffusion

This paper introduces RNA-MDLM, a model for generating and inpainting non-coding RNA sequences, showing it produces sequences with natural composition and folding statistics.

A Unified 3D Generative Model for Synthesizable Structure-Based Drug Design

This paper introduces LDDM, a generative model for drug design that produces synthetically accessible compounds validated experimentally for five protein targets.

A foundation model learns the sequence and functional grammar of fully human heavy-chain-only antibodies

The paper develops a foundation model trained on fully human heavy-chain-only antibodies, showing it captures sequence and functional constraints distinct from conventional antibody models.

Sequence Generation and Phylogenetic Inference with Generative Flow Networks

This paper introduces AncestorGFN, a method using Generative Flow Networks for alignment-free sequence generation and phylogenetic inference, showing it can recover ancestral relationships and generate novel sequences.

OmniTCR: a foundation model unifying T cell receptor recognition prediction and conditional sequence generation

OmniTCR is a foundation model that predicts TCR recognition and generates TCR sequences, outperforming existing methods on multiple tasks.

Functional alignment of protein language models via reinforcement learning

This paper introduces RLXF, a framework that aligns protein language models with experimental functional goals, improving the generation of high-functioning protein variants.

Coverage Geometry and Heuristic Discovery Times in Protein Sequence Space

The paper introduces a geometric framework to analyze protein sequence space coverage and connects it to heuristic discovery times using a stochastic exploration model.

OligoSeq: Rapid nanopore-sequencing of single-stranded oligonucleotides

OligoSeq enables accurate sequencing of single-stranded oligonucleotides using nanopore technology, offering a cost-effective alternative for quality control in oligonucleotide synthesis.

Sequence-free landscape inference for directed evolution

This paper introduces SLIDE, a method to estimate landscape ruggedness in directed evolution using population-level phenotypic data and mutation rate, improving selection strategies for protein design.

Gradient-based Optimization for mRNA Sequence Design

The paper introduces ID3, a framework for optimizing mRNA sequences using gradient-based methods, balancing multiple properties while preserving amino acid sequences.

Dynamic Hierarchical Interleaved Bloom Filter: An Updatable Index for Large-Scale Fast Sequence Search

This paper introduces a dynamic and updatable sequence-search index called Dynamic HIBF, which efficiently handles large-scale data updates and outperforms existing methods in speed.

A multi-tissue epigenomic atlas links the sheep non-coding genome to domestication and complex traits

SheepEpimap combines 516 histone CUT&Tag, ATAC-seq and RNA-seq datasets from 43 sheep tissues to annotate 2.93 million cis-regulatory elements and 145,407 allele-specific variants for trait interpretation.

A membrane insertion code for intrinsically disordered proteins

The paper identifies sequence determinants for aromatic residue insertion into membranes and develops a predictor model with high accuracy.

Multiplexed sequence-resolved screening of transient DNA hybridization for programmable nanotechnology

The paper introduces SPARXS-Hyb, a method for multiplexed screening of DNA hybridization kinetics, identifying sequences with improved performance in DNA-PAINT.

Trust-Aware Sequence-to-Function Modelling in Regulatory Genomics

The paper introduces RegTrust-XAI, a trust-aware framework for sequence-to-function models in regulatory genomics, showing how reliability, explanation validity, and sequence novelty are distinct properties.

Improved inference of multiscale sequence statistics in generative protein models

This paper introduces a new regularization strategy for generative protein models that improves the inference of multiscale sequence statistics, enabling the generation of functional and diverse protein sequences.

CodonMamba: a foundation model for programmable mRNA coding sequence design

CodonMamba is a foundation model for mRNA coding sequence design that achieves state-of-the-art performance and enables programmable codon optimization through inference-time steering.

DualMyo: Multi-Channel Dual-Stream Transformer Architecture for EMG-to-Digit Classification

This paper introduces DualMyo, a Transformer-based model for EMG-to-digit classification, achieving 91% accuracy with lightweight fine-tuning for cross-session adaptation.