Searching journal content for articles similar to Zeng et al. 34 (9): 1445.

Displaying results 1-10 of 5955
For checked items
  1. Method: Balancing gene ontology annotation specificity in protein function prediction based on the protein sequence large graph
    • Jiangyi Shao,
    • Shutao Chen,
    • Ziwen Wang,
    • Zixu Chen,
    • and Bin Liu
    Genome Res. April 15, 2026 gr.280816.125; Published in Advance April 15, 2026, doi:10.1101/gr.280816.125
    ...for predicting GO annotations at a fine granularity. TALE 74 (Cao and Shen 2021) on the other hand, uses a pre-trained language model to increase 75 the amount of useful information for GO annotations. Similarly, DeepFRI (Gligorijevic 76 et al. 2021) combines representations derived from pretrained sequence...
    ACCEPTED MANUSCRIPT
  2. Method: Automated interpretable artificial intelligence genomic prediction with AIGP
    • Lei Wei,
    • Ziqin Jiang,
    • Baoliang Fan,
    • Yidan Yan,
    • Zhenqiang Xu,
    • Xiaoxiang Hu,
    • and Yuzhe Wang
    Genome Res. April 2026 36: 814-826; Published in Advance March 5, 2026, doi:10.1101/gr.281006.125
    ...) increasing the marker density across Chr 28 and (2) focusing on the QTL within Chr 28. The prediction results of the four models (GBLUP, BayesR, LightGBM, and CatBoost) exhibited varying degrees of improvement. The second strategy achieved the optimal solution in all results. For TW, the accuracies...
  3. Method: Early feature extraction drives model performance in high-resolution chromatin accessibility prediction
    • Aayush Grover,
    • Till Muser,
    • Liine Kasak,
    • Lin Zhang,
    • Ekaterina Krymova,
    • and Valentina Boeva
    Genome Res. March 2026 36: 619-629; Published in Advance January 12, 2026, doi:10.1101/gr.281042.125
    ...for genomic data. Integrated into diverse architectures such as convoluted neural networks (CNNs), long short-term memory (LSTM), dilated CNNs, and transformers, ConvNeXt V2 blocks consistently improve performance, leading to similar prediction accuracy across these different model types. This reveals...
    OPEN ACCESS ARTICLE
  4. Method: Designing realistic regulatory DNA with autoregressive language models
    • Avantika Lal,
    • David Garfield,
    • Tommaso Biancalani,
    • and Gokcen Eraslan
    Genome Res. September 2024 34: 1411-1420; Published in Advance September 25, 2024, doi:10.1101/gr.279142.124
    ...train or fine-tune a HyenaDNA model to take the processed sequences and perform next token prediction beginning with the prompt tokens (Fig. 1C). This formulation allows us to use any prior knowledge on sequences in the model explicitly.View larger version: In this window In a new window Figure 1...
    OPEN ACCESS ARTICLE
  5. Method: CodonBERT large language model for mRNA vaccines
    • Sizhen Li,
    • Saeed Moayedpour,
    • Ruijiang Li,
    • Michael Bailey,
    • Saleh Riahi,
    • Lorenzo Kogler-Anele,
    • Milad Miladi,
    • Jacob Miner,
    • Fabien Pertuy,
    • Dinghai Zheng,
    • Jun Wang,
    • Akshay Balsubramani,
    • Khang Tran,
    • Minnie Zacharia,
    • Monica Wu,
    • Xiaobo Gu,
    • Ryan Clinton,
    • Carla Asquith,
    • Joseph Skaleski,
    • Lianne Boeglin,
    • Sudha Chivukula,
    • Anusha Dias,
    • Tod Strugnell,
    • Fernando Ulloa Montoya,
    • Vikram Agarwal,
    • Ziv Bar-Joseph,
    • and Sven Jager
    Genome Res. July 2024 34: 1027-1035; Published in Advance July 1, 2024, doi:10.1101/gr.278870.123
    ...RNA degradation prediction. As we show, both the pretrained and the fine-tuned version of the models can learn new biology and improve on current state-of-the-art methods for mRNA vaccine design.To assess generalization of our CodonBERT model, we collected a novel hemagglutinin flu vaccine data set. Different m...
  6. Method: spRefine denoises and imputes spatial transcriptomic data with a reference-free framework powered by genomic language model
    • Tianyu Liu,
    • Tinglin Huang,
    • Wengong Jin,
    • Tinyi Chu,
    • Rex Ying,
    • and Hongyu Zhao
    Genome Res. April 2026 36: 754-768; Published in Advance February 3, 2026, doi:10.1101/gr.281001.125
    ...prediction task according to their ablation tests. PLMs are foundation models trained with large-scale amino-acid sequences to model protein data as a language (Ofer et al. 2021; Zhang et al. 2024), and the success of applying PLMs to this task suggests the utility of PLMs to build expression relationships...
    OPEN ACCESS ARTICLE
  7. Method: ERC2.0 evolutionary rate covariation update improves inference of functional interactions across large phylogenies
    • Jordan H. Little,
    • Guillermo Hoffmann Meyer,
    • Aakash Grover,
    • Alex Michael Francette,
    • Raghavendran Partha,
    • Karen M. Arndt,
    • Martin Smith,
    • Nathan Clark,
    • and Maria Chikina
    Genome Res. September 2025 35: 2041-2051; Published in Advance August 7, 2025, doi:10.1101/gr.280586.125
    ...would improve the biological relevance of ERC scores and, therefore, predictive power.To test this, we used logistic regression modeling to test how well ERC can be used to predict which genes belong to a given functional annotation (Methods). Logistic regression modeling allows us to test...
  8. Method: Leveraging protein language models for accurate multiple sequence alignments
    • Claire D. McWhite,
    • Isabel Armour-Garb,
    • and Mona Singh
    Genome Res. July 2023 33: 1145-1153; Published in Advance July 6, 2023, doi:10.1101/gr.277675.123
    ...of the RBHs between amino acid embeddings. To improve this network, we use MNCM to remove false-positive RBHs (Supplemental Fig. 2). However, it is likely that the RBH network could be improved in multiple ways, including through fine-tuning embeddings, use of other protein language models, and choice...
    OPEN ACCESS ARTICLE
  9. Method: Iterative improvement of deep learning models using synthetic regulatory genomics
    • André M. Ribeiro-dos-Santos and
    • Matthew T. Maurano
    Genome Res. November 2025 35: 2539-2549; Published in Advance October 22, 2025, doi:10.1101/gr.280540.125
    ...proportion of categories per bin. (C) Positive predictive value (PPV) per bin.Fine-tuning on synthetic regulatory genomic data sets improves predictive performanceWe then developed a fine-tuning strategy to improve model performance through incorporation of synthetic regulatory genomic data sets. We added...
  10. Method: Aggregation of recount3 RNA-seq data improves inference of consensus and tissue-specific gene coexpression networks
    • Prashanthi Ravichandran,
    • Princy Parsana,
    • Rebecca Keener,
    • Kasper D. Hansen,
    • and Alexis Battle
    Genome Res. September 2025 35: 2087-2103; Published in Advance July 17, 2025, doi:10.1101/gr.280808.125
    ...relationships that were curated by Liska et al. (2022) based on experimental evidence such as ChIP-seq. We observed a modest improvement in the precision of predicting direct gene-gene relationships at higher values of recall with sequential data aggregation. Although we do see improvement, the identification...
    OPEN ACCESS ARTICLE
For checked items

Search Results

Next 10 » New Search

Modify Results

Citation format:
Results / page:
Results order:

This search

  • Alert me when new articles matching this search are published
  • Download all citations on this page to my citation manager

Preprint Server



Current Issue

  1. April 2026, 36 (4)
  1. Current Issue
  1. Alert me to new issues of Genome Research