arXiv:2608. 00697v1 Announce Type: cross Abstract: Variational autoencoders (VAEs) trained on multiple sequence alignments (MSAs) have emerged as powerful generative models for biological sequences, with applications ranging from disease variant prediction to functional RNA design.
arXiv:2603. 14717v2 Announce Type: replace Abstract: Generating novel protein sequences that respect a family's statistical constraints typically requires training deep generative models on thousands to millions of examples.
The paper introduces GenDA, a bidirectional discrete diffusion model designed for genomic sequence reconstruction, hypothesizing that entropy-guided span placement would improve variant-effect prediction and functional sequence generation. While the 202‑million‑parameter GenDA model achieves a higher ClinVar SNV AUROC (0.774) than a comparable autoregressive model, the improvement is not attributable to entropy guidance, and the model fails to outperform a shuffled‑gap baseline in zero‑shot functional inpainting across various genomic regions. The authors identify limitations such as tokenization granularity, span length caps, and the mismatch between local sequence complexity and functional importance, concluding that variant prediction, corruption priors, and functional generation are distinct tasks requiring separate validation.
arXiv:2606. 18703v1 Announce Type: new Abstract: Pretrained biological language models expose per-token probability distributions through masked-token prediction, providing the likelihood interface central to sequence design, variant scoring, and mechanistic interpretation.
arXiv:2609.07500v1 Announce Type: cross Abstract: The evolution of DNA sequences can be viewed as stochastic dynamics on a high-dimensional discrete space, but it is unclear when empirical transition...
arXiv:2609.39644v2 Announce Type: new Abstract: Ribosome profiling (Ribo-seq) measures ribosome distributions along mRNAs, but observed occupancy profiles also contain experiment-specific distortions...
arXiv:2606. 28659v1 Announce Type: cross Abstract: High-fidelity molecular docking simulations can produce biologically relevant estimates of epitope-receptor binding affinity but are computationally expensive and therefore limit the number of candidates that can be screened for vaccine design.
EvoLen is a tokenization method for DNA language models that incorporates evolutionary information to prioritize functional sequence patterns such as regulatory motifs. It groups DNA sequences by cross-species evolutionary signals, trains separate BPE tokenizers for each group, merges vocabularies with a rule that favors preserved patterns, and uses length-aware decoding with dynamic programming. Experiments show EvoLen better preserves functional motifs, differentiates genomic contexts, and aligns with evolutionary constraints while matching or surpassing standard BPE on various DNALM benchmarks.
The paper introduces Murmur2Vec, a lightweight, alignment‑free embedding that uses k‑mer counts hashed with MurmurHash to create a compact representation for biological sequences. It provides a full theoretical analysis, including bias/variance formulas, a Johnson–Lindenstrauss‑style concentration bound, and an excess‑risk bound that clarifies the trade‑off between hash‑table size and classifier performance. Empirically, Murmur2Vec matches or surpasses a fine‑tuned 650M‑parameter ESM‑2 protein language model across several classification tasks, including SARS‑CoV‑2 spike lineage and HIV‑1 Env subtype identification.
STAR-VAE is a Transformer-based variational autoencoder that uses SELFIES encoding and a bidirectional encoder with an autoregressive decoder pretrained on 79 million PubChem molecules. It incorporates a property signal to jointly condition the prior, posterior, and decoder, and employs LoRA adapters for fine‑tuning on small datasets without altering the backbone. The model achieves 100 % validity and near‑perfect novelty in MOSES sampling, low KL divergence on several GuacaMol descriptors, strong synthetic‑accessibility conditioning, and effective docking‑score control across multiple protein targets, while also enabling scaffold recovery and diverse label‑conditioned generation on ChEMBL targets.
arXiv:2608.22849v2 Announce Type: replace Abstract: Full-length RNAs, particularly messenger RNAs, often exceed the context lengths used to pretrain existing RNA foundation models, limiting complete-...
The study evaluates 4‑bit quantization and low‑rank adapter fine‑tuning (QLoRA) on several large protein language models, finding that many model‑task pairs retain over 90% of full fine‑tuning performance while achieving up to 90% GPU memory savings. QLoRA preserves early‑layer representations and induces task‑specific changes in later layers, closely resembling full fine‑tuning with smaller representational shifts. For generative models, 4‑bit quantization largely maintains structural and sequence‑level properties, though token‑level analysis reveals model‑dependent changes in autoregressive output distributions.
arXiv:2605. 00182v3 Announce Type: replace Abstract: Proteins are shaped by gradual evolution under biophysical and functional constraints.