AI 速览：作者提出基于大语言模型的智能体 ClinGeX，通过检索与依赖感知编排 105 个可执行技能来辅助临床基因组解读，并在基准与人类-AI 协作研究中报告了优于对照的表现。
Clinical genomic analysis requires experts to integrate evolving guidelines, databases, and computational evidence. As sequencing has become increasingly accessible, this complex and labor-intensive process has become a major bottleneck to the timely use of genomic information in clinical decision-making. To fill this gap, we developed ClinGeX, a large-language-model agent that composes 105 curated executable skills through task-specific retrieval and dependency-aware orchestration. On 223 temporally held-out benchmark cases, ClinGeX achieved 71.7\% macro-averaged task-level concordance with expert reference classifications, compared with 45.7\% for the strongest comparator. In a three-condition, counterbalanced human-AI collaboration study, 45 clinical genomic professionals assessed 135 clinically derived cases under routine (no AI assistance), DeepSeek-assisted and ClinGeX-assisted conditions. ClinGeX assistance increased raw case-level concordance across criterion-level variant analysis, genomic interpretation in rare disease and molecular oncology decision-making (51.1\%, 57.8\%, 64.4\% versus 15.6\%, 31.1\%, 20.0\% in comparator conditions) and reduced reported interpretation time in all scenarios. During an exploratory one-month real-world non-interventional assessment, 11 experienced professionals submitted feedback on 96 self-selected analysis episodes and reported frequent conclusion adoption and time savings. These findings support executable domain skills as a promising approach to augment specialist genomic interpretation.
Lei Huang, Chuan Qiu, Kuan-Jui Su, Anqi Liu, Yun Gong, Weiqiang Lin, Lindong Jiang, Chen Zhao 等 16 位作者
Genotype imputation enables dense variant coverage for genome-wide association and risk-prediction studies, yet conventional reference-panel methods remain limited by ancestry bias and reduced rare-variant accuracy. We present Genotype Bidirectional Encoder Representations from Transformers (GenoBERT), a transformer-based, reference-free framework that tokenizes phased genotypes and uses a self-attention mechanism to capture both short- and long-range linkage disequilibrium (LD) dependencies. Benchmarking on two independent datasets including the Louisiana Osteoporosis Study (LOS) and the 1000 Genomes Project (1KGP) across ancestry groups and multiple genotype missingness levels (5-50%) shows that GenoBERT achieves the highest overall accuracy compared to four baseline methods (Beagle5.4, SCDA, BiU-Net, and STICI). At practical sparsity levels (up to 25% missing), GenoBERT attains high overall imputation accuracy ($r^2 approx 0.98$) across datasets, and maintains robust performance ($r^2 > 0.90$) even at 50% missingness. Experimental results across different ancestries confirm consistent gains across datasets, with resilience to small sample sizes and weak LD. A 128-SNP (single-nucleotide polymorphism) context window (approximately 100 Kb) is validated through LD-decay analyses as sufficient to capture local correlation structures. By eliminating reference-panel dependence while preserving high accuracy, GenoBERT provides a scalable and robust solution for genotype imputation and a foundation for downstream genomic modeling.
Population-scale analysis of phased genetic variants requires both allele-carrier retrieval and ordered haplotype context. We examine H1, an adaptive allele-haplotype incidence-row index, and H2, a canonical edge-path representation derived from a fixed, nonoverlapping variant catalog. We prove conditional reconstruction of abstract H2 walks and distinguish this property from unrestricted equivalence to genomic variation graphs. A completed local notebook experiment used a chromosome 1 interval (20-22 Mb), 200 diploid individuals, 24,921 SNV/indel records, and 45 SVTYPE-annotated records. For 24,966 extracted nonreference rows across 400 haplotypes, the serialized H1 incidence-row files occupied 0.872 MiB with a simple adaptive layout and 1.126 MiB with a custom Roaring-like layout, versus 1.190 MiB for a bitmap-payload baseline; a whole-file Zstandard archive of the adaptive layout occupied 0.207 MiB. For a separately constructed nonoverlapping SNV projection containing 22,727 sites, indexed H2 edge sequences occupied 75,130,882 bytes in a raw format and 5,156,418 bytes with context-Huffman encoding (14.57-fold reduction). Carrier-equivalence and graph-adjacency assertions passed in the notebook, but full crosscallset phasing, nucleotide-level SV reconstruction, and comparison with production indexes remain unresolved. The measurements establish a restricted implementation feasibility result, not superior end-to-end pangenome compression.
Chi-Lam Poon, Michael Goneos, Zezheng Song, Xi Chen
Existing scientific-agent benchmarks rarely evaluate whether agents can reconstruct the exact molecular structures and generation workflows specified by sequencing protocols, a capability critical for analyzing customized sequencing assays. We introduce LibStructBench, a document-grounded benchmark for reconstructing sequencing-library structures and molecular workflows. Our experiments show that frontier agents often produce approximately correct reconstructions but remain unreliable at exact reconstruction, particularly in molecular-state representation and workflow connectivity. Switching the underlying language model produced larger average performance differences than switching agent harnesses, with a statistically significant difference only for molecular-state reconstruction. Additional knowledge improved oligo-family recovery in a small pilot without improving mean molecular-workflow scores. Autonomous accumulation of procedural rules and cross-protocol examples showed non-monotonic validation performance and no mean held-out molecular-workflow improvement in the tested trajectory. These findings highlight the need for more controlled and verifiable approaches to scientific reasoning about molecular processes in complex experimental protocols.
Boyang Fu, Sameer Gabbita, George Dasoulas, Xiang Lin, Shanghua Gao, Xiaorui Su, Soumya Ghosh, Marinka Zitnik
Prediction of the transcriptional response of a cell to a genetic perturbation is a central problem in the computational modeling of gene regulation. Perturbations of the same gene can produce different transcriptional responses depending on the targeted locus, such as an alternative transcription start site or a distal regulatory element, and gene-level perturbation models represent these distinct interventions with a single gene identifier. We introduce STRAND, a generative model that encodes the regulatory DNA sequence at the perturbation locus and uses this encoding to parameterize a conditional transport process from control to perturbed single-cell states. Sequence conditioning enables zero-shot prediction for perturbation targets absent from training and supports locus-resolved inputs at 128 bp model resolution within a 524 kb sequence window. On CRISPRi screens in K562, Jurkat, and RPE1 cells, STRAND achieves the best average rank on few-shot and unseen-gene benchmarks, with gains of up to 33% in perturbation discrimination, and improves transfer to held-out cell lines by up to 0.12 in $Δ$Pearson. Ablation studies attribute these gains to sequence conditioning and to conditional transport. At the locus level, STRAND distinguishes alternative transcription start sites and validated regulatory elements that gene-identifier models represent as a single perturbation. STRAND is available at https://github.com/mims-harvard/STRAND.
DNA offers high-density, durable storage by encoding digital information into synthetic strands and retrieving it through sequencing. Sequence reconstruction combines noisy copies of each strand before downstream decoding. Conventional offline methods typically reconstruct completed read clusters, separating reconstruction from ongoing read collection. Streaming reconstruction offers a way to overlap evidence processing with sequencing and reduce the computation remaining before downstream decoding. We present ACOR, a streaming consensus reconstruction method that records $k$-mer transitions and boundary support in a persistent ledger, then decodes through length-constrained beam search and priority-based selection at cluster closure. Evaluation on real and simulated DNA-storage datasets showed competitive recovery. On our own short-read next-generation sequencing (NGS) wet-lab library, ACOR combined near-complete recovery with second-scale reconstruction of more than ten million reads. A smaller public benchmark was completed in a fraction of a second. Parallel ACOR achieved speedups of tens to over a thousand-fold relative to the tested serial baseline configurations. Sparse storage reduced high-context memory requirements, while parallel execution accelerated reconstruction computation. ACOR is designed for streaming readout pipelines that process assigned reads while sequencing continues.
Individual-level genotype data underpin genetic discovery, disease-risk modeling, and therapeutic development, yet many critical settings remain data-limited, including underrepresented ancestries, rare or imbalanced disease cohorts, and restricted-access biobanks. Conditional synthetic genome generation would support privacy-aware benchmarking, simulation, and data augmentation, but requires learning an ultra-high-dimensional discrete distribution over hundreds of thousands to tens of millions of correlated single-nucleotide polymorphisms (SNPs), or sites of DNA variation. We introduce HELICS: High-fidelity gEneration via Latent Interpolant Conditional Synthesis, a phasing-free latent flow matching framework for genome-wide SNP-level generation from biobank-scale genotype data. HELICS tokenizes chromosomes with convolutional autoencoders, reducing >600K SNPs to 4,096 continuous latent tokens, and trains a transformer parameterized conditional flow matching model over the concatenated multi-chromosome latent representation. Trained on over 417K genomes in the UK Biobank, HELICS generates genome-wide common-variant synthetic cohorts without haplotype phasing and achieves stronger fidelity to real genotypes than existing haplotype-based simulators, including high allele-frequency agreement in external evaluation and superior preservation of local and long-range SNP correlation structure. Conditioning on ancestry and genetic liability summaries enables targeted generation across genetic risk profiles; in perturbation analyses, by increasing the conditioned disease trait liability, HELICS induces SNP-level dosage changes in generated genomes that are highly correlated with published association weights. HELICS provides a scalable generative modeling framework for SNP-level genome data and a path toward conditional synthetic cohorts for data-limited genetic studies.
Md Zahangir Alom, Quynh T. Tran, Breuer Alexandar, Brent A. Orr
DNA methylation (DNAM) array-based tumor classification is a powerful clinical diagnostic tool, but models trained on fixed reference cohorts can produce faulty predictions for tumor types not represented in the training distribution. We propose an end-to-end deep representation learning-based out-of-distribution (OOD) detection framework for DNAm array data. Deep neural network (DNN) classifiers were trained on public sarcoma (SARC) (GSE140686) and brain tumor (BT) (GSE90496) cohorts, and feature vectors were extracted from bottleneck layers. Five OOD methods, including 1dimension (1D)-Subspace Analysis (1D-SSA), K-Nearest Neighbors (KNN), Ridge Regression, Mahalanobis Distance (MD), and Sum of Squared Distances (SSD), were explored with 200 and 500-dimensional embeddings. Spectral discrepancy was used to discriminate in-distribution (IND) from OOD samples. Performance was measured via cross-validation, holdout samples, and an independent clinical dataset. 1D-SSA was the most effective approach. In the sarcoma-IND/brain tumor-OOD setting, the framework achieved an AUROC of 0.975 and True Negative Rate (TNR)@95TPR of 0.930, and an AUROC of 0.9569 and TNR@95TPR of 0.8660 for the brain tumor-IND/sarcoma-OOD setting. On the independent clinical test set, the method yielded a mean AUROC of 0.976, a DE of 0.032, an FPR@95TPR of 0.065, and a TNR@95TPR of 0.935. These results show deep representation-based OOD detection as a practical quality-control layer for clinical-grade methylation-based tumor classification systems.