Aug 2026· International Journal of Molecular Sciences· Vol 27, pp. 7511· 0 citations· 61 references
TL;DR
A reproducible artificial intelligence framework that integrates multi-omics benchmarking, sample-level drug prioritization, E3 ubiquitin ligase selection, and shape-anchored Proteolysis Targeting Chimera (PROTAC) design for KRASG12D in colon adenocarcinoma is presented.
Abstract
Colorectal cancer is a leading cause of cancer death, yet its molecular heterogeneity remains poorly translated into individualized treatment. We present a reproducible artificial intelligence (AI) framework that integrates multi-omics benchmarking, sample-level drug prioritization, E3 ubiquitin ligase selection, and shape-anchored Proteolysis Targeting Chimera (PROTAC) design for KRASG12D in colon adenocarcinoma (COAD). A controlled synthetic benchmark comprising 425 tumor and 41 simulated normal profiles, parameterized to match The Cancer Genome Atlas (TCGA) distributions, was used for pipeline verification. Among sixteen methods, the Balanced Latent Integration with Stability Selection (BLISS) model achieved the highest silhouette width (0.86) and competitive agreement (Adjusted Rand Index, ARI, 0.90). The pipeline was validated on real data: a TCGA COAD cohort (186 tumors) with independent Consensus Molecular Subtype (CMS) labels and a CPTAC cohort (104 tumors). Integration modestly recovered CMS (ARI 0.28), and stage, not molecular cluster, drove survival (log-rank p = 0.005 versus 0.81). Sample-level prioritization differed from cluster-level ranking in 82.6% of profiles, below chance (p < 0.0001), without indicating efficacy. Candidate NOVEL00489 showed a good MM-GBSA estimate, matching the reference ASP3082. Compounds are computational candidates requiring experimental validation. This establishes a transparent benchmark for in silico degrader generation in precision oncology.
This systematic review comprehensively evaluates computational advancements in oncology drug discovery published between 1997 and 2026 and concludes that AI has transitioned into an indispensable, data-driven framework for modern oncology chemistry and structural toxicology.
anyogita Shahi, Shirish Kumar Singh, Vinod Kumar Choudhary· Asian Journal of Medical Res...· 0 citations
Targeted therapies have transformed the management of lung adenocarcinoma (LUAD), yet further clinical progress is hindered by its molecular complexity. Previous efforts to characterize this heterogeneity have been constrained by small cohorts, limiting the discovery of therapeutic targets. We leveraged a large-scale real-world dataset (RWD) to define a LUAD subpopulation with high unmet clinical need. We integrated gene network modeling and spatial transcriptomics to identify key molecular drivers and functionally validated candidate gene targets using CRISPR screening in subtype-matched patient-derived organoids (PDOs).
De-identified clinico-genomic records from LUAD patients profiled with Tempus xT (DNA) and xR (RNA)-seq assays were analyzed (n=7956). Non-negative matrix factorization applied to gene expression data was used to identify molecular subtypes. Progression free survival (PFS), defined as the time from the start of first metastatic therapy to the date of first progression or death from any cause, was assessed in a subset of patients with available data (17.6% of total samples). A classifier trained on tumor-intrinsic features was used to assign subtypes to 36 LUAD PDOs and 19 LUAD tissue samples profiled with the Visium HD spatial transcriptomics platform. A gene regulatory network was modeled using the Priori algorithm by weighting known TF-target associations from the DoRothEA database with xR data. CRISPR/Cas9 screening was performed in PDOs, followed by CellTiter-Glo viability and xR assays to evaluate the functional and transcriptomic impact of gene knockouts.
Six distinct molecular subtypes of LUAD were identified (C1-C6). The C5 subtype (23.15% of total samples) exhibited the worst prognosis (PFS 5.6 months, 95% CI 4.3-7.4) with high prevalence of STK11 (36.85%), KEAP1 (19.67%), and SMARCA4 (15.95%) mutations. Spatial transcriptomics analysis revealed that the C5 subtype was significantly enriched for three distinct niches (localized cellular micro-environments): tertiary lymphoid structure, macrophage-dominated myeloid, and mucinous malignant. Gene co-expression modules associated with the C5 subtype were enriched for NFE2L2 (NRF2) transcription factor pathways. The NFE2L2 gene regulatory network was most transcriptionally active in the C5 subtype. Spatially, NFE2L2 network activity was highest in the mucinous malignant niche and was driven primarily by club cells and malignant cells. Knockdown (KD) of key network nodes (NFE2L2, GPX2, NQO1) in C5 subtype-matched PDOs led to a reversal of the NFE2L2 signature. Additionally, GPX2 KD led to significantly higher viability loss in C5 versus C1 subtype-matched PDOs (p < 0.001).
The integrated multi-omic approach presented here identified GPX2 as a critical vulnerability in a well-defined LUAD subpopulation. These findings provide a rationale for targeting the NFE2L2/GPX2 axis, offering a strategic opportunity for therapeutic intervention.
Akul Singhania, Kayla R. Bastian, Yajas Shah, Swati Kaushik, Brandon L. Mapes, Lee F. Langer, Yaakov E. Stern, Prerna Jain, Ezgi Karaesmen Rizvi, Samantha Cowher, Chi-Sing Ho, Brian Roberts, Nick Callamaras, Richard A. Klinghoffer, Justin Guinney, Radia M. Johnson. Integrated multi-omic analysis and CRISPR screening identify GPX2 as a critical vulnerability in high-risk lung adenocarcinoma [abstract]. In: Proceedings of AACR Drug Discovery and Development (AACR D3) Conference; 2026 Jul 21-24; Boston, MA. Philadelphia (PA): AACR; Clin Cancer Res 2026;32(14_Suppl):Abstract nr A083.
A. Singhania, K. Bastian, Y. Shah et al.· Clinical Cancer Research· 0 citations
Abstract Brain metastases (BrMs) remain therapeutically challenging because metastatic adaptations within the CNS are heterogeneous and often poorly captured by primary-tumor biomarkers, limiting rational patient stratification and trial design. We constructed a pan-cancer multi-omic atlas of BrMs (n = 1,032) integrating genomic and transcriptomic profiling with quantitative proteomics and targeted metabolomics, supported by orthogonal single-cell and spatial measurements, to derive a metastatic state–based classification that generalizes across tumor origins and across analytic platforms. Consensus analysis revealed four reproducible BrM states: a neural-like program (BrMS1), an immune-infiltrated state coupled to EMT/stromal activation (BrMS2), a metabolically reprogrammed state enriched for mitochondrial oxidative phosphorylation (OXPHOS) (BrMS3), and a highly proliferative, immune-excluded state (BrMS4). These states captured convergent cross-cancer programs, providing a unifying framework to interpret BrM biology beyond tissue of origin. To connect states to tractable liabilities, we performed targeted drug screening in patient-derived organoids (PDOs) and identified state-linked vulnerabilities, nominating mTOR-pathway dependence in BrMS3 and CDK4/6-axis dependence in BrMS4, thereby prioritizing rational combination strategies. Focusing on lung cancer BrMs, we analyzed an integrated multi-omic cohort (n = 154) with matched clinical annotation and tissue immune phenotyping, confirming a “mitochondria-high/immune-low” axis characterized by elevated OXPHOS signatures, suppressed immune signaling, and an immunosuppressive microenvironment that associated with inferior survival, supporting its utility as a biomarker for risk stratification. This biomarker-defined axis motivated a mechanism-informed therapeutic hypothesis: mitochondrial inhibition reduced OXPHOS-associated programs and impaired viability in LC-BrM PDOs, and in an orthotopic LC-BrM mouse model, combining mitochondrial inhibition with anti–PD-1 therapy produced the most durable survival benefit compared with either monotherapy. Together, these results establish a pan-cancer metastatic state framework, link it to actionable biomarkers and validated therapeutic hypotheses, and provide an evidence base for biomarker-guided clinical trials that pair metabolism-targeting with immunotherapy for metabolically reprogrammed, immune-suppressed BrMs, and inform companion diagnostic development for CNS-active regimens.
Metastatic disease remains the leading cause of cancer-related death, yet most precision oncology strategies still emphasize profiling primary tumors and tracking cell-free tumor DNA (ctDNA). Although ctDNA has transformed genomic profiling, molecular residual disease monitoring, and early cancer detection, it cannot directly capture viable tumor cell states, phenotypic plasticity, or functional adaptations that drive metastatic spread. We propose that the next phase of precision oncology should integrate the cellular dimension of metastasis through systematic circulating tumor cell (CTC) profiling. The SCRUM-MONSTAR platform, one of the largest pan-cancer molecular profiling initiatives in Japan, offers an exceptional foundation for this transition through its nationwide infrastructure for multi-omics analysis, longitudinal biospecimen collection, and artificial intelligence-enabled clinical interpretation. By combining matched tissue profiling, serial ctDNA analysis, single-cell CTC transcriptomics, metabolomics, and organoid- and mouse-based functional modeling, SCRUM-MONSTAR-CTC could evolve into a translational ecosystem for anti-metastatic drug discovery. Within this framework, we highlight adherent-to-suspension transition (AST) as one representative, experimentally tractable plasticity program that enables tumor cells to survive in circulation and subsequently colonize distant organs. We envision that identifying and therapeutically targeting AST-related and other metastatic plasticity programs across tumor types will provide a path toward clinically actionable anti-metastatic therapies. More broadly, this framework could enable the identification of metastatic vulnerabilities, the development of biomarker-guided anti-metastatic trials, and the reverse translation of patient-derived discoveries into early-phase clinical testing. Precision oncology must move beyond cataloging tumor genomes and begin targeting metastasis as a dynamic biological process. UMIN000056873, approved by the Institutional Review Board of the National Cancer Center Hospital East.
T. Hashimoto, T. Shibuki, T. Fujisawa et al.· International Journal of Cli...· 0 citations
Pancreatic ductal adenocarcinoma (PDAC) is the most lethal common cancer (5-year survival ∼13%), emerging through years-to-decades progression involving chronic fibro-inflammatory injury and precursor transformation processes including ADM and PanIN. KRAS-driven acinar-to-ductal metaplasia (ADM) is among the earliest experimentally tractable and potentially interceptable events; KRAS (mutated in >90% of PDAC) has remained difficult to therapeutically target, particularly for prevention; emerging KRAS inhibitors are developed for treatment of established malignancy rather than early interception. We aimed to prioritize KRAS-axis interception candidates via AI-guided network analysis of TCGA-PAAD restricted to a curated KRAS-driven ADM/PanIN-initiation mechanism module.
The 38-gene module (n=183 TCGA-PAAD samples; 37 genes available, PRSS2 absent) spans KRAS-MAPK, RTKs, TGF-β/SMAD, ECM, inflammation, transcription, tumor suppressors, and ductal/acinar genes from canonical pancreatic-cancer-progression biology, linking established-tumor transcriptomes to early-interception biology. A stability-selected Spearman-correlation network served as the network backbone (PCMCI+/NOTEARS extensions ongoing), paired with patient-level bootstrap filtering (B=200 resamples; ≥70% retention). A composite Interception Score I(v) = α·CB + β·Σ|w| + γ·U + δ·R integrating betweenness centrality, summed edge-weight influence, druggability (literature-curated drug-target prior), and bootstrap robustness ranked candidate interception nodes (unoptimized weights; tuning ongoing).
Spearman correlation yielded a 37-node, 248-edge network baseline; bootstrap resampling (B=200) evaluated 856 distinct candidate edges, of which 194 (22.7%) achieved ≥70% retention, defining the stable subgraph used for scoring. The Interception Score placed 7 KRAS-axis genes among the top-10 candidates: ERBB2 (0.953), KRAS (0.743), ERBB3 (0.742), MAPK1 (0.708), EGFR (0.675), MAP2K2 (0.605), and BRAF (0.589). Inflammation (IL6, 0.755), TGF-β/SMAD2 (0.726), and ECM/MMP2 (0.638) also ranked highly, recapitulating PDAC initiation mechanisms (stromal-epithelial crosstalk; inflammatory-fibrotic priming). ERBB2 (HER2), a clinically druggable RTK with approved inhibitors in other malignancies, emerged as the top-ranked candidate, supporting evaluation of HER2-axis signaling for interception in molecularly selected PDAC subsets. These findings align with canonical PDAC biology, supporting biological plausibility prior to formal weight optimization and external validation.
AI-guided network analysis of TCGA-PAAD prioritizes biologically coherent KRAS-axis and stromal-inflammatory candidates with clinically available HER2-, EGFR-, MEK-, BRAF-, and KRAS-pathway inhibitors, supporting hypothesis generation for future pancreatic cancer interception studies. Stage-resolved analysis, causal-inference extensions, and sex-/age-stratified validation are ongoing.
Jianfu Li, Yingyun Yang, Michael Wallace, Cui Tao, Yan Bi. AI-Driven Network-Based Discovery on TCGA-PAAD Identifies KRAS-Axis Drug-Repurposing Targets for Pancreatic Cancer Interception [abstract]. In: Proceedings of AACR Drug Discovery and Development (AACR D3) Conference; 2026 Jul 21-24; Boston, MA. Philadelphia (PA): AACR; Clin Cancer Res 2026;32(14_Suppl):Abstract nr A029.
Jianfu Li, Yingyun Yang, Michael B. Wallace et al.· Clinical Cancer Research· 0 citations
Objective: PIK3CA is one of the most frequently mutated oncogenes across multiple cancer types, playing a crucial role in tumorigenesis via the PI3K/AKT/mTOR signaling pathway. Understanding its genuine co-mutation landscape is essential for identifying oncogenic interactions and refining targeted therapeutic strategies. In this study, we analyzed the true functional co-mutation patterns of PIK3CA in colorectal adenocarcinoma (COAD), cervical squamous cell carcinoma and endocervical adenocarcinoma (CESC), stomach adenocarcinoma (STAD), and lung adenocarcinoma (LUAD).
Method: Somatic mutation data were obtained from The Cancer Genome Atlas (TCGA). Co-mutation and mutual exclusivity analyses were performed using R (maftools). To rigorously distinguish genuine biological cooperativity from confounding background mutation rates, multivariate logistic regression models were implemented, incorporating tumor mutational burden (TMB) continuous covariate.
Results: TMB-adjusted analyses revealed distinct, robust co-occurrence and mutual exclusivity relationships across cancer types, filtering out passenger mutations. In COAD, PIK3CA mutations significantly co-occur with KRAS, suggesting a cooperative role in tumorigenesis, while maintaining strict mutual exclusivity with TP53. In STAD, PIK3CA exhibits a strong, true functional co-occurrence with the chromatin remodeling gene ARID1A, while maintaining mutual exclusivity with TP53 and CSMD3. Interestingly, in both LUAD and CESC, PIK3CA demonstrates a highly significant mutual exclusivity with the mucin gene MUC17, pointing to context-specific evolutionary trajectories.
Conclusion: These findings highlight the complex, TMB-independent molecular landscape of PIK3CA-driven tumors, emphasizing the necessity of cancer-type-specific therapeutic approaches. By utilizing robust TMB-adjusted models, this study successfully isolates true genetic interactions, providing valuable insights into potential drug resistance mechanisms and novel combination therapy strategies for PIK3CA-mutant cancers.
Perçin Pazarcı· Scientific Reports in Medici...· 0 citations