sequence-to-function modeling

Generative design of antigen-specific T-cell receptor sequences with a conditional diffusion model

This paper introduces TCRDiff, a conditional diffusion model for generating antigen-specific TCR sequences, validated through in vitro assays.

Signed-XOR Error and Sparse Coding in a Dale-Complaint Substrate for Sequence Memorization

The paper demonstrates a biologically plausible model that memorizes and recalls sequences using a sparse coding scheme and Dale's law constraints, achieving perfect recall with a modest latent size.

FoldARE, an RNA secondary structure analysis and prediction tool via generative pseudo-SHAPE modeling

FoldARE improves RNA secondary structure prediction by using pseudo-SHAPE constraints from structural ensembles, achieving high accuracy across benchmark datasets.

Topological Entanglement in Intrinsically Disordered Proteins: Sequence, Structural, and Functional Determinants

The paper uses entanglement measures from knot theory to analyze sequence and structural features of intrinsically disordered proteins and identifies functionally enriched regions in entanglement space.

Sequence-to-function modeling uncovers the context-specific grammar of Drosophila chromatin insulation

The paper introduces Domino, a deep learning framework that models sequence-to-function relationships to uncover the context-specific grammar of Drosophila chromatin insulation.

RetroMol: Parsing a shared encoding from natural products and their biosynthetic gene clusters

RetroMol converts natural product structures and biosynthetic gene clusters into shared primary sequences to enable biosynthetic similarity comparisons.

MoE-Bind: Guiding De Novo Protein Binder Generation with Sparse Experts

MoE-Bind is a sparse Mixture-of-Experts model for protein binder generation that outperforms dense baselines while reducing compute requirements.

Reinforcement learning-driven unified generative framework for multi-objective RNA codon design

RNARL is a reinforcement learning framework for RNA codon design that generates high-performance sequences across multiple species and RNA types.

Sequence-Based Therapeutic Peptide Classification with Augmented Negative Sampling

This paper introduces a CNN classifier for therapeutic peptide classification using augmented negative sampling, achieving significantly lower false positive rates and competitive performance on external benchmarks.

GermRL: Alleviating The Germline Bias In Autoregressive Antibody Language Models Through Reinforcement Learning

This paper introduces GermRL, a reinforcement learning framework that reduces germline bias in antibody language models, improving mutation diversity while maintaining structural plausibility.

ProtGPT3: an Open-source family of Promptable and Aligned Protein Language Models

ProtGPT3 is an open-source family of protein language models that enables controlled protein generation through alignment and prompting, showing effectiveness in generating functional proteins.

pLM-Guided Inverse Folding for Antibody Sequence Design

The paper improves antibody sequence design by combining a general inverse folding model with an antibody-specific language model, achieving better amino acid recovery and sequence diversity.

Replaying germinal center evolution on a quantified affinity landscape

Across 119 monoclonal germinal centers, B cell affinity rises reliably despite divergent phylogenies. Selection is noisy but persistent; mutability limits exploration. A DMS-based landscape shows saturating fitness and survivorship biases.

Deep Proteoform Sequencing with Top-Down Direct Mass Technology

This paper introduces a top-down mass spectrometry workflow with DMTm technology and a new software platform to achieve deeper proteoform sequencing and improved sequence coverage.

DanioDecima: A DNA sequence-to-function model of zebrafish embryogenesis

DanioDecima improves gene expression prediction in zebrafish by transferring knowledge from human and mouse models, enhancing correlations and generating synthetic promoters with expected lineage-specific motifs.

Bayesian optimisation and graph-based rheology enable sequence-dependent modelling of DNA materials

This paper uses Bayesian optimisation and graph-based rheology to model DNA materials by linking sequence design to material properties.

SSPSPredictor: A Sequence and Structure based Deep Learning Model for Predicting Phase-Separating Proteins

SSPSPredictor predicts phase-separating proteins using sequence and structure data, showing higher LLPS propensity in intrinsically disordered proteins and pathogenic variants.

Fine-tuning sequence-to-expression models onpersonal genome and transcriptome data

This study fine-tunes sequence-to-expression models on personal genome and transcriptome data, showing improved performance on seen genes but not on unseen genes.

Carbon: Decoding the Language of Life

The paper introduces CO_SCPLOWARBONC_SCPLOW, a family of efficient DNA language models that address challenges in genomic sequence modeling by adapting LLM techniques to DNA's unique properties.

A generative-AI framework for target-Specific MicroRNAs towards RNAi-based drug design

This paper introduces a generative AI framework to design target-specific siRNAs for RNAi-based drug design, showing improved specificity and reduced off-target effects compared to existing methods.

PlasmidLM: A Promptable DNA Language Model via Verifiable-Reward Post-Training

PlasmidLM is a DNA language model that generates plasmid constructs from component specifications, achieving high fidelity and viability in generated sequences.

TreeGazer: Prospecting Protein Sequence-Function Landscapes via Phylogenetic Structure

TreeGazer selects informative protein sequences using phylogenetic structure and Bayesian optimization, outperforming alternative strategies in simulated campaigns and low-data settings.

Explicit representation of germline and non-germline residues improves antibody language modeling

PRISM improves antibody language modeling by distinguishing germline and non-germline residues, achieving better binding affinity correlation and controllable generation.

Simple baselines rival protein language models in dense combinatorial protein landscapes

This study compares protein language models (pLMs) with simple baselines in combinatorial protein design, finding no consistent advantage for pLMs in predicting or generating superior variants.

Functional Profiling of Thousands of Sequence-Diverse Protease Homologs with GROQ-seq

The paper uses GROQ-seq to profile function across a diverse protease library, showing robust activity across sequence divergence.

Fast and Ultra-Capable Protein Design: Advancing the Frontier Through Atomistic SE(3)-Equivariance with Genie 3

This paper introduces Genie 3, a diffusion model that improves protein design by combining SE(3)-equivariance with hallucination, achieving state-of-the-art results in binder design and motif scaffolding.

End-to-end single-stranded DNA sequence design with all-atom structure reconstruction

This paper introduces InvDNA, a deep learning method for designing single-stranded DNA sequences from backbone coordinates, achieving better sequence recovery and structural accuracy than existing methods.

Ankh-score produces better sequence alignments than AlphaFold3

Ankh-score improves sequence alignment over AlphaFold3 structural alignments and traditional BLOSUM methods on benchmark datasets.

linearPOA: A parallel, memory-efficient framework for Partial Order Alignment with linear space complexity

linearPOA introduces a memory-efficient framework for Partial Order Alignment with linear space complexity, significantly reducing memory usage for long-read sequencing.

On learning functions over biological sequence space: relating Gaussian process priors, regularization, and gauge fixing

The paper establishes the relationship between Gaussian process priors and regularized regression in sequence-to-function mapping, showing how to construct regularizers that correspond to explicit Gaussian process priors and characterize implicit function space priors.