AI and Cancer Research ── 2026-10-27

6 papers in this issue. Lead: Deep learning mitigates batch effects in Raman spectroscopy

New papers on cancer and AI, collected from journal feeds, PubMed (searched across all journals) and OpenAlex (a public index used instead of Google Scholar), judged by Jev (an AI that makes language judgements): original research, AI central, which of 13 themes, treatment or trials, and then ranked by importance up to a daily limit. Journals are not filtered by impact factor; each paper shows its journal's IF-equivalent (OpenAlex two-year mean citedness) and the date of that value. Each entry shows the full original abstract.

Read by cancer type: Cancer biology（2） · Breast（2） · Lung（1） · Pancreatic（0） · Prostate（0） · ACC（0） · Brain（0） · Ovarian（0） · Endometrial（0） · Gastric（1） · Liver（0） · Kidney（0） · Bladder（0）

Cancer molecular biology and AI

Deep learning mitigates batch effects in Raman spectroscopy
Scientific Reports · 2026-10-26 · Evidence: Preclinical (method development using Raman spectra from glioma samples)
Abstract
Raman spectroscopy is widely used for its ability to provide rich molecular-level information from biological samples. However, the high sensitivity of Raman spectra can also unintentionally encode extraneous information, such as patient identity, instrument-specific signatures, environmental conditions, and sample handling protocols. This hidden structure, referred to as the batch effect, poses increasing challenges in machine learning applications, where it can lead to model overfitting, poor generalization, and even privacy risks when datasets are shared. In this work, we investigate the presence and impact of the batch effect in a Raman spectroscopy dataset derived from glioma tumor samples. We show that deep learning can accurately predict patient identity from individual spectra, revealing strong bias patterns in the data. To mitigate this issue, we explore several approaches and introduce an algorithmic framework based on adversarial deep learning. Our method effectively reduces the influence of confounding sample-specific signals while preserving information relevant to tumor classification. These findings highlight the need for careful bias control in Raman-based AI pipelines and provide tools to support more robust applications in biomedical spectroscopy.
Journal IF-equivalent: 5.2 (OpenAlex 2-year mean citedness, value as of 2026-10-04, retrieved 2026-10-05; not the official Clarivate IF)
Reference: Sjöberg J, Lita A, Larion M, Petre I. Deep learning mitigates batch effects in Raman spectroscopy. Sci Rep. 2026 Oct 26;16(1):34019. doi:10.1038/s41598-026-62086-1.
Checked: Abstract only
UpTCR: a unified progressive knowledge transfer foundation model for robust T-cell receptor-antigen binding recognition.
Nature communications · 2026-09-24 · Evidence: Preclinical (computational model development with prospective experimental validation)
Abstract
T-cell receptor (TCR) recognition of antigenic peptides presented by human leukocyte antigen (HLA) molecules underpins adaptive immunity and T cell-based immunotherapy. However, the scarcity of complete interaction data and TCR cross-reactivity challenge robust prediction. Here, we present UpTCR, a unified progressive knowledge-transfer foundation model that learns from incomplete data to predict TCR-antigen-HLA binding. UpTCR progressively transfers knowledge from dimeric and trimeric interactions to tetrameric complexes and uses soft contrastive learning to mitigate false negatives. It outperforms existing methods in predicting TCR binding specificity and antigen-HLA binding affinity, particularly for neoantigens, and reveals pairwise residue-level interactions across the tetramer. UpTCR also transfers effectively to breast cancer cohorts with limited data. Prospective validation against melanoma antigen variants identifies eight immunogenic peptides that elicit T cell responses and one variant associated with immune escape. These findings establish UpTCR as a generalizable and interpretable tool for studying antigen recognition and advancing TCR-based immunotherapies.
Journal IF-equivalent: 18.1 (OpenAlex 2-year mean citedness, value as of 2026-10-06, retrieved 2026-10-07; not the official Clarivate IF)
Reference: Lv T, Xiao Y, Chen L, He B, Zhong M, Feng Z, et al. UpTCR: a unified progressive knowledge transfer foundation model for robust T-cell receptor-antigen binding recognition. Nat Commun. 2026 Sep 24;17(1):11086. doi:10.1038/s41467-026-78075-x. PMID: 42928063.
Checked: Abstract only

See all 2 Cancer biology papers →

Breast cancer: treatment, trials and AI

Machine Learning Classification of Breast Cancer Molecular Subtypes and Clinical Phenotypes from GEO Expression Cohorts, with a Leakage-Controlled External Validation Protocol on GSE1456
International Journal of Oncology Research · 2026-10-25 · Evidence: Retrospective observational (computational analysis of public datasets with external validation)
Abstract
Background. Breast cancer comprises biologically distinct intrinsic subtypes with different outcomes. Public GEO cohorts allow reproducible computational classification, but small test sets, heterogeneous labels and information leakage often inflate reported performance. This study classified breast cancer subtypes and clinical phenotypes from expression data and tested whether subtype classification transfers to an independent cohort. Methods. Four Affymetrix cohorts (GSE20685, GSE45827, GSE2034, GSE7390) were processed through a common pipeline: probe-to-gene annotation, quality control, differential-expression (DEG) feature selection on the training split only, and Logistic Regression, SVM and Random Forest classification (80/20 stratified hold-out), each against its own available label. A model trained on GSE45827 with nested cross-validation (CV) was then tested once on GSE1456 as an independent external cohort. Results. Hold-out accuracy was 90.9–92.4% for six molecular clusters (GSE20685), 96.2–100% for four subtypes (GSE45827), 70.7–79.3% for bone relapse (GSE2034) and 80.0–90.0% for ER status (GSE7390); in GSE2034 no model clearly exceeded the 75.9% majority-class baseline. On GSE1456 (102 labelled tumours), the SVM selected by nested CV (97.4% internal accuracy) reached only 48.0% accuracy (bootstrap 95% CI 38–58; majority baseline 38.2%). Basal (recall 0.88) and HER2 (0.80) tumours partly transferred; luminal A (0.21) and luminal B (0.30) did not. Conclusion. Within a cohort, expression-based classification is accurate for subtype and ER labels but not for relapse. Subtype classification did not transfer reliably to an independent cohort: external accuracy (48.0%) was far below the internal estimate (97.4%). Keywords: breast cancer; Feature Selection; GEO; Differential expression; External validation; PAM50
Journal IF-equivalent: 0.0 (OpenAlex 2-year mean citedness, value as of 2026-10-26, retrieved 2026-10-27; not the official Clarivate IF)
Reference: ANUSHKA CHOUDAHA. Machine Learning Classification of Breast Cancer Molecular Subtypes and Clinical Phenotypes from GEO Expression Cohorts, with a Leakage-Controlled External Validation Protocol on GSE1456. Int J Oncol Res. 2026 Oct 25;1(1):73-83. doi:10.64823/ijor.2601005.
Checked: Abstract only
Development and External Validation of an M2 Macrophage-Related Prognostic Signature in Breast Cancer Using Multi-Omics Data and Machine Learning.
Breast cancer (Dove Medical Press) · 2026-10-21 · Evidence: Retrospective observational (development and external validation in public cohorts) with preclinical in vitro experiments
Abstract
PURPOSE: Tumor-associated macrophages (TAMs), particularly the M2-like phenotype, are central regulators of breast cancer progression; however, clinically applicable models capturing their functional heterogeneity and biological mechanisms remain limited. PATIENTS AND METHODS: We integrated single-cell RNA sequencing, spatial transcriptomics, and bulk RNA-seq data to construct an M2 macrophage-centered gene landscape. A machine learning framework based on 10-fold cross-validation was used to develop a prognostic signature in the TCGA-BRCA cohort (training set), with external validation in the independent GSE96058 cohort. Immune infiltration, genomic instability, pathway activity, and cell-cell communication were analyzed. KLF4 was examined in breast cancer cells and macrophages using qRT-PCR, Western blotting, siRNA-mediated knockdown, and a Transwell co-culture system. RESULTS: We identified a 16-gene M2 macrophage-related signature (M2MMS) that stratified patients into subgroups with distinct survival outcomes in both cohorts. High-risk tumors showed M2 macrophage enrichment, an immunosuppressive microenvironment, elevated genomic instability, and activation of E2F and MYC proliferative programs. Cell-cell communication analysis identified MDK-NCL as a dominant tumor-TME signaling axis. KLF4 was upregulated in breast cancer cells and in macrophages after co-culture, and silencing KLF4 attenuated CD206 induction, indicating that KLF4 is functionally involved in tumor cell-induced M2-like polarization in vitro. CONCLUSION: The M2MMS links M2 macrophage-driven immune remodeling to breast cancer prognosis and provides a basis for risk stratification and mechanistic investigation. KLF4 represents a regulatory node in tumor-macrophage interaction in vitro; its role in vivo and the clinical utility of the M2MMS require further validation.
Journal IF: unknown (could not be matched)
Reference: Liu Y, Liu Y, Wang H, Xiao Z, Chang X, Li Z, et al. Development and External Validation of an M2 Macrophage–Related Prognostic Signature in Breast Cancer Using Multi-Omics Data and Machine Learning. Breast Cancer (Dove Med Press). 2026 Oct;Volume 18:1-18. doi:10.2147/bctt.s636369. PMID: 42928788.
Checked: Abstract only

See all 2 Breast papers →