Ask about this productRelated genes to: GPT2 Blocking Peptide
- Gene:
- GPT2 NIH gene
- Name:
- glutamic--pyruvic transaminase 2
- Previous symbol:
- -
- Synonyms:
- ALT2
- Chromosome:
- 16q11.2
- Locus Type:
- gene with protein product
- Date approved:
- 2002-03-05
- Date modifiied:
- 2016-10-05
Related products to: GPT2 Blocking Peptide
Related articles to: GPT2 Blocking Peptide
- The metabolite α-ketoglutarate (αKG) is required for chromatin demethylation, but mechanisms that control αKG abundance in the nucleus are poorly defined. We designed a biosensor to monitor this metabolite pool in human cells using an αKG-responsive cyanobacterial transcription factor, NtcA, and used it to identify genes that regulate αKG in the nucleus. We defined an interorganelle pathway in which sequential mitochondrial activities of glutamic-pyruvic transaminase 2 (GPT2) and the SLC25A11 transporter supply nuclear αKG. In a mouse model of GPT2 deficiency, an inborn error of metabolism, Gpt2 loss caused histone hypermethylation in the brain and dysregulated neurodevelopmental genes. Restoring αKG counteracted these changes and promoted mouse fitness. Our work provides a tool to directly monitor nuclear αKG and reveals nuclear αKG depletion as a key pathogenic mechanism underlying GPT2 deficiency. - Source: PubMed
Publication date: 2026/07/16
Sternisha Alex CLi HaochengGajendra KumarXiao YiZhao XinTraylor Jeffrey IGuo LeiJun Ji HyungFleishman MorganShipman TraceyPuliyappadamba Vinesh TKaphle PranitaOuyang QingSchmidt MichaelShi Diana DSavani Milan RTsai Alexander C-YLee Joyce HGordillo RuthGarcia-Bermudez JavierKim Yoon JungTso Shih-ChiaBrautigam Chad AZacharias Lauren GMathews Thomas PXu LinDoench John GKoduri VidyasagarAbdullah Kalil GAgathocleous MichalisBanaszynski Laura ADeBerardinis Ralph JMorrow Eric MMcBrayer Samuel K - Time series forecasting models often face challenges in cross-domain fine-tuning, such as high training costs and limited adaptability. To address these issues, we propose a Cue-driven Feature Fusion Network (CFF-Net), which combines semantic cues from textual prompts with numerical time series features for parameter-efficient adaptation. The main idea is to use the semantic representation ability of large language models to provide auxiliary guidance, while dynamically modulating numerical predictions through scale-and-shift operations. Specifically, CFF-Net includes three main components. First, the Semantic Prompt Encoding Module (SPM) transforms numerical sequences into temporally relevant natural language descriptions, which are processed by GPT-2 to extract semantic representations. Second, the Dynamic Semantic Modulation Module (DSM) maps these semantic representations into learnable scaling (γ) and shifting (β) factors through a multi-layer perceptron, enabling modulation of PatchTST predictions within the Scale-and-Shift Feature (SSF) mechanism. Finally, a warm-start strategy is used to stabilize semantic integration during training. Experimental results on three public datasets and the TCTS dataset show that CFF-Net achieves lower errors than PatchTST in many settings, although the improvements are not uniform across all datasets and metrics. For example, on the Weather dataset, CFF-Net reduces MSE by 12.50% and 11.88% under the 30% and 20% training-sample settings, respectively. On the TCTS dataset, the corresponding MSE reductions are 5.83% and 6.60%. These results suggest that semantic prompt guidance can improve forecasting performance in several limited-data scenarios while keeping most backbone parameters fixed. - Source: PubMed
Publication date: 2026/07/08
Wei KaibinJing JianqiangLiu JiaweiLiu QingXie Xiannian - Breast cancer is the most common malignancy in women. Ultrasound plays a critical role in dense breasts, and BI-RADS provides a standardized framework for lesion assessment. However, conventional reports may suffer from variability. Deep learning and large language models (LLMs) show promise in automated report generation. We propose a workflow integrating deep learning with GPT-4o for structured breast ultrasound reports. - Source: PubMed
Publication date: 2026/07/02
Feng GuotaoXie XinxinJiang JieLee Jeong MinCui Ligang - The lack of high-quality multimodal resources for low-resource languages such as Bangla poses significant challenges for vision-language research, image captioning, and accessibility technologies. To address this gap, this study introduces ShilpoBangla, a curated dataset comprising 1200 images representing Bengali cultural products across five categories including traditional clothing, food, musical instruments, folk arts and crafts, and jewelry. Each image is paired with human-authored alternative text in both Bangla and English. The study further demonstrates the feasibility of generating image alternative text using a ViT encoder and a GPT-2 decoder, and establishes a benchmark for future multimodal research and cross-linguistic applications. Additionally, the inclusion of alternative text in both Bangla and English enhances the dataset's accessibility, usability, and adoption among a broader global audience, thereby improving the generalizability and practical applicability of the ShilpoBangla dataset. - Source: PubMed
Publication date: 2026/06/06
Ahmed S M NafisKaiser Syed NafeesNur Fernaz NarinMajib Mohammad ShahjahanIslam Muhammad Nazrul - Transformer-based language models have demonstrated sensitivity to a range of linguistic dependencies, yet it remains unclear how they represent information-structural focus and integrate discourse and lexical focus cues during ellipsis resolution. We investigated GPT-style models' interpretation of elliptical remnant continuations in double-object constructions by manipulating contextual focus via preceding interrogatives (who vs. what) and lexical focus via the particle only, whose surface position was varied. Using word-by-word surprisal as an index of processing difficulty, we conducted three experiments with GPT-2 models (Small-XL) and GPT-Neo. In Experiment 1 (no only), models robustly tracked the wh-induced discourse focus, assigning higher surprisal to remnants that mismatched the contextually focused constituent. In Experiment 2 (only preceding the indirect object), contextual focus continued to dominate, indicating that discourse cues were maintained despite the presence of a competing lexical marker. In Experiment 3 (only preceding the direct object), lexical focus effects became stronger: models favored remnants aligned with the lexically biased direct object, consistent with locality-based cue weighting when only is adjacent to that object. Comparisons with human reaction-time data revealed broad convergence in contextual-focus sensitivity but divergence when the remnant was compatible with one cue but not the other, with GPT-style models exhibiting a stronger bias toward alignment with only than humans. Together, these findings suggest that the tested models maintain discourse-level focus representations while integrating multiple focus cues in a proximity-sensitive manner, revealing both overlap and limits in their alignment with human processing. - Source: PubMed
Publication date: 2026/06/18
Chung WonilKoo Keonwoo