SCOPE-OPSD: Fisher-Conditioned Privileged Subspaces for On-Policy Self-Distillation

arXiv:2609.12579v1 Announce Type: cross Abstract: On-policy self-distillation (OPSD) scores student-generated prefixes with a solution-conditioned self-teacher, yet transfers supervision only through next-token probabilities. We ask whether the aligned final-layer discrepancy offers a useful second channel, and how to test that channel without confusing its geometry with auxiliary strength. SCOPE-OPSD projects the privileged teacher-student residual onto a frozen rank-64 factor estimated from residual covariance and language-model-head Fisher sensitivity. It reuses the forwards already required by OPSD and adds neither rollouts nor inference-time modules. A matched Random control preserves the structured factor's rank and nonzero spectrum and uses per-arm gradient-RMS calibration, isolating the effect of the data-dependent orientation. Across the complete 25/50/75/100-step trajectories for Qwen3-1.7B, 4B, and 8B, Structured is never below Pure OPSD, with strict gains in 11 of the 12 model-checkpoint combinations and an exact tie at 4B step 25. Structured also exceeds matched Random in 10 of the 12 combinations. At step 75 on Qwen3-1.7B, Structured exceeds matched Random by 1.39 Macro Avg@12 points in each of two independent training reruns. A cross-fitted diagnostic also shows 4.40 times greater held-out privileged-gap capture than the matched random orientation. The results support a compact, Fisher-conditioned privileged subspace for short-budget OPSD.

Unveiling the Diagnostic Value and Potential Therapeutic Targets of Phenylalanine Metabolism in Pancreatic Cancer via Integrated Multi-Omics and Machine Learning

(Multiomics OR Omics) AND (Pancreatic)

By: Xing Liu · Yibin Li · Fangfang Qin · Jianghong Ou

12 September 2026 at 18:00

FASEB J. 2026 Sep 30;40(18):e72296. doi: 10.1096/fj.202603069R.

ABSTRACT

Pancreatic cancer (PC) presents a significant global health challenge because of its high mortality rate, highlighting the urgent requirement for effective early diagnostic and therapeutic strategies. This study examined the function of phenylalanine metabolism in PC and developed a high-accuracy diagnostic model by integrating metabolomics, Mendelian randomization (MR), and machine learning (ML) algorithms. Initially, MR analysis was conducted on 55 plasma metabolites, revealing a significant causal link between phenylalanine and PC. Utilizing GeneCards and public transcriptomic databases, we determined eight differentially expressed genes (DEGs) in PC associated with phenylalanine. Based on these genes, we utilized 12 ML algorithms, totaling 113 combinations, to select the optimal diagnostic model. We applied Shapley Additive exPlanations (SHAP) for feature interpretation and constructed a prognostic nomogram with strong predictive performance by incorporating clinical variables. Furthermore, immune infiltration analysis demonstrated strong connections between these key genes and specific immune cell populations. Based on the SHAP value, we conducted single-cell RNA sequencing (scRNA-seq) data and simulated gene knockout analyses using SLC6A14 as the key gene. Drug target prediction-guided molecular docking and molecular dynamics simulations, focusing on the core gene SLC6A14, confirmed the high binding stability of candidate compounds. Finally, in vitro cell experiments quantitative real-time PCR (RT-qPCR) verified the expression trends of the key genes in PC cell lines. In conclusion, this study successfully developed an ML diagnostic model with high biological interpretability. This analysis aims to identify biomarkers related to phenylalanine metabolism and potential therapeutic drugs for PC, offering new strategies for personalized targeted therapy of PC.

PMID:42730913 | PMC:PMC13570651 | DOI:10.1096/fj.202603069R

Artificial intelligence-assisted early screening of lung cancer and accurate diagnosis of pulmonary nodules: research progress and clinical prospects from radiomics to multi-omics integration: a narrative review

Pulmonary nodule

By: Junwei Wang · Guixue Yang · Zhuoxin Dai · Miao Yang · Peng Dai · Mengyang Chang · Quan-Xing Liu · Ji-Gang Dai

17 June 2026 at 18:00

J Thorac Dis. 2026 May 31;18(5):537. doi: 10.21037/jtd-2026-1-0315. Epub 2026 Apr 30.

ABSTRACT

BACKGROUND AND OBJECTIVE: Lung cancer remains one of the leading causes of cancer-related death worldwide. Although low-dose computed tomography (LDCT) has improved early detection, false-positive results, overdiagnosis, and interobserver variability continue to limit screening efficiency and downstream management of pulmonary nodules. This narrative review summarizes recent progress in artificial intelligence (AI)-assisted screening, radiomics-based nodule characterization, and multi-omics integration for the precision diagnosis of lung cancer.

METHODS: A narrative review with thematic analysis was conducted using representative literature on AI-assisted lung cancer screening, quantitative imaging analysis of pulmonary nodules, radiogenomic and multi-omics integration, and clinical translation challenges. Studies were synthesized to highlight technical advances, diagnostic performance, strengths, limitations, and barriers to implementation.

KEY CONTENT AND FINDINGS: AI improves nodule detection, second-reader support, workflow efficiency, and malignancy-risk estimation in LDCT screening. Radiomics converts CT images into quantitative features that can improve discrimination between benign and malignant nodules, especially when combined with clinical variables or deep-learning models. Beyond imaging alone, radiogenomic and other multi-omics approaches link imaging phenotypes with molecular alterations, treatment response, and prognosis, thereby supporting more individualized management. However, current evidence remains limited by dataset heterogeneity, retrospective design, limited interpretability, and insufficient multicenter prospective validation.

CONCLUSIONS: AI-based imaging and multi-omics integration offer a promising pathway toward earlier detection and more precise diagnosis of lung cancer. Broader clinical adoption will depend on standardized data acquisition, robust external validation, interpretable models, and careful governance of privacy, ethics, and workflow integration.

PMID:42306713 | PMC:PMC13266817 | DOI:10.21037/jtd-2026-1-0315

Non-enzymatic function of QSOX2 directly regulates the JUNB-ITGB4 axis and enhanced resistance to osimertinib in EGFR-mutation lung adenocarcinoma

Cell Death Discovery nature.com science feeds

By: Chaoxing Liu · Siya Wang · Rong Qi · Weiguo Gu · Chen Fang · Guohua Zhang · Jinyu Gan · Feng Yu · Ke Fang · Jianxiong Deng · Chao Shi · Feng Qiu

1 April 2026 at 08:00

Cell Death Discovery, Published online: 01 April 2026; doi:10.1038/s41420-026-02969-4

Non-enzymatic function of QSOX2 directly regulates the JUNB-ITGB4 axis and enhanced resistance to osimertinib in EGFR-mutation lung adenocarcinoma

WIST: Web-Grounded Iterative Self-Play Tree for Domain-Targeted Reasoning Improvement

cs.AI, q-bio.NC updates on arXiv.org

By: Fangyuan Li · Pengfei Li · Shijie Wang · Junqi Gao · Jianxing Liu · Biqing Qi · Yuqiang Li

25 March 2026 at 12:00

arXiv:2603.22352v1 Announce Type: cross Abstract: Recent progress in reinforcement learning with verifiable rewards (RLVR) offers a practical path to self-improvement of language models, but existing methods face a key trade-off: endogenous self-play can drift over iterations, while corpus-grounded approaches rely on curated data environments. We present \textbf{WIST}, a \textbf{W}eb-grounded \textbf{I}terative \textbf{S}elf-play \textbf{T}ree framework for domain-targeted reasoning improvement that learns directly from the open web without requiring any pre-arranged domain corpus. WIST incrementally expands a domain tree for exploration, and retrieves and cleans path-consistent web corpus to construct a controllable training environment. It then performs Challenger--Solver self-play with verifiable rewards, and feeds learnability signals back to update node posteriors and guide subsequent exploration through an adaptive curriculum. Across four backbones, WIST consistently improves over the base models and typically outperforms both purely endogenous self-evolution and corpus-grounded self-play baselines, with the Overall gains reaching \textbf{+9.8} (\textit{Qwen3-4B-Base}) and \textbf{+9.7} (\textit{OctoThinker-8B}). WIST is also domain-steerable, improving \textit{Qwen3-8B-Base} by \textbf{+14.79} in medicine and \textit{Qwen3-4B-Base} by \textbf{+5.28} on PhyBench. Ablations further confirm the importance of WIST's key components for stable open-web learning. Our Code is available at https://github.com/lfy-123/WIST.

Reading view