GenoBERT is a transformer-based, reference‑free model that tokenizes phased genotypes and uses self‑attention to capture short‑ and long‑range linkage disequilibrium. Benchmarking on the Louisiana Osteoporosis Study and the 1000 Genomes Project shows GenoBERT outperforms four baseline methods, achieving an overall imputation accuracy of about 0.98 at up to 25% missing data and maintaining r² > 0.90 even at 50% missingness across multiple ancestries. The model’s 128‑SNP context window is sufficient to capture local correlation structures, and it remains robust to small sample sizes and weak LD, offering a scalable solution for genotype imputation without relying on reference panels.
arXiv:2509.20702v3 Announce Type: replace-cross Abstract: Recent advances in large language model (LLM) embeddings have enabled powerful representations for biological data, but most applications to...
arXiv:2606. 00483v1 Announce Type: cross Abstract: Genotype-based cis-expression prediction depends on accurately modeling local regulatory architecture.
arXiv:2607. 07725v1 Announce Type: cross Abstract: Genomic prediction models often fail to transfer across institutions because sequencing panels differ across sites, creating structural feature missingness at deployment.
The study evaluates 16 imputation methods for single‑cell RNA sequencing across 10 protocols, 6 downstream tasks, and 30 datasets. It finds that traditional methods generally perform better across many tasks, while deep learning approaches show more variability. No single method consistently outperforms others, and strong numerical recovery does not always improve biological interpretation.
RAGenome is a retrieval‑based genomic language model that extends pretraining to contexts 100 times longer than existing MSA‑based models, enabling it to capture both cross‑species evolutionary relationships and within‑species long‑range interactions. Trained on whole‑genome alignments from 100 vertebrates, it improves gene‑finding performance from 0.45 to 0.60 while staying competitive on evolutionary tasks such as prioritizing pathogenic variants. The model offers competitive performance at a fraction of the training cost, unifying evolutionary modeling and long‑range capabilities in a single scalable framework.
The paper introduces a pre‑training pipeline that creates transformer‑based imputation specialists for tabular data with specific missingness patterns. By featurizing entries, generating synthetic data with configurable missingness modules, and fitting on millions of synthetic tables, the pipeline produces pattern‑specific models that outperform dedicated methods for each missingness pattern. A default model trained only on MCAR data, TabImpute, remains robust across all tested patterns, and the authors release the pipeline, models, and a new benchmark of 42 datasets and 11 missingness patterns.
The paper introduces SCR-MF, a two‑stage workflow for single‑cell RNA sequencing imputation that first detects dropout events with scRecover and then imputes missing values using the non‑parametric missForest algorithm. Benchmarking on public and simulated datasets shows that SCR‑MF delivers robust, interpretable results that match or surpass existing methods while maintaining biological fidelity. Runtime analysis indicates that SCR‑MF balances accuracy with computational efficiency, making it well suited for mid‑scale single‑cell studies.
arXiv:2607. 11656v1 Announce Type: cross Abstract: Accurate diagnostic classification and disease-severity prediction for Alzheimer's disease are hampered by the incompleteness and heterogeneity of real-world clinical data.
arXiv:2609.16271v1 Announce Type: cross Abstract: Attribution methods for genomic sequence models are commonly evaluated by how much of a known motif they recover, or by how a prediction degrades as...
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:2511. 09026v2 Announce Type: replace-cross Abstract: Whole-genome sequencing (WGS) has revealed numerous non-coding short variants whose functional impacts remain poorly understood.
arXiv:2607. 05613v1 Announce Type: new Abstract: Clinical care often relies on key laboratory indicators, yet real-world patient visits are sparse and tests are ordered irregularly, leading to pervasive missingness.