The human microbiome is emerging as a key regulator of cancer biology, modulating tumor development, immune dynamics, and therapeutic responses across diverse malignancies. In this review, recent insights are synthesized regarding how microbial communities (bacterial, fungal, and viral) shape oncogenic signaling, immune checkpoint blockade (ICB) efficacy, and metabolic reprogramming in lung, pancreatic, colorectal, breast, cervical, melanoma, and gastric cancers. Mechanistic links between microbial metabolites, intratumoral colonization, and host immune phenotypes are highlighted proposing that the microbiome constitutes a programmable axis within the tumor immune-metabolic ecosystem. Drawing on multi-omics integration and translational studies, a shift from associative profiling toward causal, spatially resolved, and intervention-ready frameworks is proposed. This perspective positions the microbiome not as a passive bystander, but as a co-evolving participant in tumor progression and treatment response, with the potential to reshape diagnostics, prognostics, and therapeutic strategies in precision oncology.
Immune checkpoint blockade (ICB) has improved outcomes for patients with head and neck squamous cell carcinoma (HNSCC), but predictive biomarkers remain limited. Here, we use a time-resolved, multi-omic approach in a murine HNSCC model to characterize peripheral immune responses to ICB. Single-cell transcriptomics and T/B cell receptor analyses reveal early on-treatment expansion of effector memory T and B cell repertoires in responders, preceding tumor regression. These dynamic immune features inform a composite transcriptional signature that accurately predicts ICB response in independent human HNSCC cohorts. LiBIO outperforms existing biomarkers and generalizes to melanoma, non-small cell lung cancer, and breast cancer without retraining. These findings suggest that early treatment-induced changes in circulating immune repertoires reflect the host's capacity to mount an effective antitumor response. This work provides a framework for leveraging transient peripheral immune dynamics to develop non-invasive, high-fidelity biomarkers for response to immunotherapy across cancer types.
AI is steadily changing the way banks work. The technology can sift through massive amounts of data, calculate risks, and handle routine tasks at speeds people can’t match. Now, Malaysia has entered that space with the launch of Ryt Bank, billed as the first AI-powered bank created in the country.
The new venture, led by YTL Group in partnership with Sea Limited, arrives just ahead of Merdeka. “Ryt Bank demonstrates that groundbreaking innovation can be imagined, built, and led right here in Malaysia,” said Dato’ Seri Yeoh Seok Hong, Managing Director of YTL Power International. “By combining homegrown AI with the values and diversity of our people, we’ve created a bank that Malaysians can proudly call their own – one that speaks our languages, understands our culture, and sets a new standard for how banking should feel.”
Banking for Malaysians
Ryt Bank has been designed to work in the languages most Malaysians use every day. Its app is already available in Bahasa Malaysia and English, with Mandarin support scheduled to arrive by next month (September 2025). By offering multilingual access, the bank aims to make financial services more inclusive and easy to use for people in many different communities.
The centrepiece of the AI-powered bank is Ryt AI, a digital assistant powered by ILMU, Malaysia’s first locally-developed large language model. Ryt AI can understand natural conversation – in Bahasa Malaysia, English, or a mixture of both – and act on requests instantly.
The AI assistant can read and pay bills, track spending, and explain financial basics in plain terms. The idea is to blend convenience with cultural familiarity, while maintaining enterprise-grade security.
Everyday AI banking in one app
Ryt Bank is designed to pull together multiple financial needs into one platform. Customers can use the AI bank app to save, spend, borrow, and pay bills, with Ryt AI making the process more conversational and personal.
Personal banking with Ryt AI
Send money or pay bills through text chat, with support for DuitNow and JomPAY.
Snap and upload bills or receipts for instant payment.
Access guides and simple financial explanations as you bank.
All actions are encrypted and verified for security.
New users can claim a small launch reward of up to RM5 when they try Ryt AI.
Growing money
Customers earn up to 4% interest per year, credited daily.
Withdraw funds anytime, with no lock-in requirements.
Ryt PayLater
Access instant credit of up to RM1,499.
0% interest if paid back in a month.
No late fees and no paperwork.
Earn cashback on DuitNow QR payments and extra rewards with select partners.
Ryt Card
Switch between debit and credit card models in the app.
Accepted worldwide through Visa.
No foreign transaction or ATM fees in Malaysia.
Cashback on spending, plus partner offers like Shopee vouchers and dining discounts at YTL Hotels.
The AI bank is licensed by Bank Negara Malaysia and covered by PIDM, which protects deposits up to RM250,000 per customer. Security features include biometric login, layered encryption, and real-time fraud alerts.
A step forward for Malaysia’s banking sector
Ryt Bank’s launch shows how AI is being used to rethink traditional banking. It aims to make financial services more accessible and satisfy regulatory and security standards by supporting local languages and developing its own AI assistant.
Background: Chatbots have demonstrated promising capabilities in Medicine, scoring passing grades for board examinations across various specialties. However, their tendency to express high levels of confidence in their responses, even when incorrect, poses a limitation to their utility in clinical settings. Objective: To examine whether token probabilities outperform chatbots' Expressed Confidence levels in predict-ing the accuracy of their responses to medical questions. Methods: Seven large languages models (LLMs), comprising both commercial (GPT-3.5, GPT-4 and GPT-4o) and open-source (Llama 3-8b, Llama 3-70b, Phi-3-Mini, and Phi-3-Medium), were prompted to respond to a set of 2,522 questions from the US Medical Licensing Examination (MedQA database). Addition-ally, the models rated their confidence from 0 to 100 and the token probability of each response was extracted. The models’ success rates were measured, and the predictive performances of both Ex-pressed Confidence and Response Token Probability in predicting response accuracy were evaluated using Area Under the Receiver Operating Characteristic Curve (AUROC), Adapted Calibration Error (ACE) and Brier score. Sensitivity analyses were conducted using additional questions sourced from other databases in English (MedMCQA, n=2,797), Chinese (MedQA Main-land China, n=3,413 and Taiwan, n=2,808), and French (FrMedMCQA, n=1,079). Results: Overall, mean accuracy ranged from 52.7%[50.8-54.7] for Phi-3-Mini to 87.6%[86.2-88.9] for GPT-4o. Across the US Medical Licensing Examination questions, all chatbots consistently expressed high levels of confidence in their responses (ranging from 90[90-90] for Llama 3-70B to 100[100–100] for GPT-3.5). However, Expressed Confidence failed to predict response accuracy (AUROC ranging from 0.52[0.50-0.53] for Phi 3 Mini to 0.68[0.65-0.71] for GPT-4o). In contrast, the Response Token Probability consistently outperformed Expressed Confidence for predicting response accuracy (AU-ROC ranging from 0.67[0.65-0.69] for Phi-3-Mini to 0.83[0.81-0.85] for Llama 3-70B, all p-values
Electronic health records are often extracted and combined with environmental data to conduct research or public health surveillance. However, to date, electronic health record systems do not integrate environmental data to aid real-time decisions that could mitigate the health impacts of environmental hazards, including the impacts of climate change. Pursuing this goal requires the enhancement of health record systems and the modification of financial incentives driving healthcare innovation and delivery.
Trained and validated on multimodal data from 14.5 million images from multicountry datasets, a foundation model is shown to increase diagnostic and referral accuracy of clinicians when used as an assistant in a trial involving 16 ophthalmologists and 668 patients.
Glioma is an aggressive brain tumor that requires challenging treatments. Tumor Treating Fields (TTFields), an FDA-approved therapy for glioblastoma (GBM), pleural mesothelioma, and platinum-refractory metastatic nonsmall cell lung cancer (in combination with PD-1/PD-L1 inhibitors or docetaxel), employs specific frequency electric fields to disrupt cell division and enhance treatment efficacy. However, their molecular mechanisms remain unclear. This study aimed to elucidate these mechanisms and optimize the therapeutic potential of TTFields through quantitative proteomics, phosphoproteomics, and glycoproteomics. Pathway analysis of the proteomics revealed that TTFields impact the cell cycle, DNA repair, autophagy, and DNA replication. Phosphoproteomic studies further demonstrated a marked decline in the activity of key kinases ABL1 and PDK1, while glycoproteomics highlighted disruptions in cell adhesion and ECM-receptor interactions. Notably, proteomic analysis identified an upregulation of PARP1 and BRD4 protein levels, suggesting a previously unrecognized resistance mechanism. Consistently, combining TTFields with inhibitors targeting these proteins significantly enhanced the treatment efficacy in U87 cells. Thus, this study uncovers comprehensive molecular mechanisms underlying TTFields' effects on GBM cells and supports the development of concomitant therapies to enhance treatment efficacy.
Elias Nogueira shares a strategic approach to modern microservice testing, detailing solutions for three core challenges. He discusses parallel execution for multiple databases using Testcontainers, creating reliable, sharable mock environments with WireMock, and handling asynchronous event delays with Awaitility, offering a blueprint for senior engineers.
Cell. 2025 Aug 22:S0092-8674(25)00922-5. doi: 10.1016/j.cell.2025.08.008. Online ahead of print.
ABSTRACT
Performing total RNA profiling on formalin-fixed, paraffin-embedded (FFPE) samples, the predominant sample conservation method in clinical practice, remains challenging for current spatial transcriptomics techniques. Here, we introduce Stereo-seq V2, which employs random primers to capture and sequence RNAs in situ on FFPE sections and provides single-cell resolution. The random-priming-based strategy offers unbiased transcript capturing and uniform gene body coverage, which increase the sensitivity to marker genes, the efficiency of non-polyadenylation (poly(A)) RNA profiling, and immune repertoire coverage. We demonstrated the robust performance of Stereo-seq V2 on clinical FFPE samples using triple-negative breast cancer (TNBC) sections and identified tumor-specific alternative splicing events. In a Mycobacterium tuberculosis (Mtb)-infected mouse model, we monitored gene expression dynamics of host and pathogen transcriptomes simultaneously by utilizing Stereo-seq V2. We also assembled immune repertoires and identified Mtb-specific BCR clones, which could also be observed in human tuberculous lung samples. These results highlight Stereo-seq V2's potential in biomedical research and personalized medicine.
Early diagnosis of lung cancer is crucial for improving patient prognosis. In this study, we developed a diagnostic model for lung cancer based on serum proteomic data from the GSE168198 dataset using four machine learning algorithms (nnet, glmnet, svm, and XGBoost). The model's performance was validated on datasets that included normal controls, disease controls, and lung cancer data containing both. Furthermore, the model's diagnostic capability was further validated on an independent external dataset. Our analysis identified SLC16A4 as a key protein in the model, which was significantly downregulated in lung cancer serum samples compared to normal controls. The expression of SLC16A4 was closely associated with clinical pathological features such as gender, tumor stage, lymph node metastasis, and smoking history. Functional assays revealed that overexpression of SLC16A4 significantly inhibited lung cancer cell proliferation and induced cellular senescence, suggesting its potential role in lung cancer development. Additionally, correlation analyses showed that SLC16A4 expression was linked to immune cell infiltration and the expression of immune checkpoint genes, indicating its potential involvement in immune escape mechanisms. Based on multi-omics data from the TCGA database, we further discovered that the low expression of SLC16A4 in lung cancer may be regulated by DNA copy number variations and DNA methylation. In conclusion, this study not only established an efficient diagnostic model for lung cancer but also identified SLC16A4 as a promising biomarker with potential applications in early diagnosis and immunotherapy.
Over the past 20 years building advanced AI systems—from academic labs to enterprise deployments—I’ve witnessed AI’s waves of success rise and fall. My journey began during the “AI Winter,” when billions were invested in expert systems that ultimately underdelivered. Flash forward to today: large language models (LLMs) represent a quantum leap forward, but their prompt-based adoption is similarly overhyped, as it’s essentially a rule-based approach disguised in natural language.
At Ensemble, the leading revenue cycle management (RCM) company for hospitals, we focus on overcoming model limitations by investing in what we believe is the next step in AI evolution: grounding LLMs in facts and logic through neuro-symbolic AI. Our in-house AI incubator pairs elite AI researchers with health-care experts to develop agentic systems powered by a neuro-symbolic AI framework. This bridges LLMs’ intuitive power with the precision of symbolic representation and reasoning.
Overcoming LLM limitations
LLMs excel at understanding nuanced context, performing instinctive reasoning, and generating human-like interactions, making them ideal for agentic tools to then interpret intricate data and communicate effectively. Yet in a domain like health care where compliance, accuracy, and adherence to regulatory standards are non-negotiable—and where a wealth of structured resources like taxonomies, rules, and clinical guidelines define the landscape—symbolic AI is indispensable.
By fusing LLMs and reinforcement learning with structured knowledge bases and clinical logic, our hybrid architecture delivers more than just intelligent automation—it minimizes hallucinations, expands reasoning capabilities, and ensures every decision is grounded in established guidelines and enforceable guardrails.
Creating a successful agentic AI strategy
Ensemble’s agentic AI approach includes three core pillars:
1. High-fidelity data sets: By managing revenue operations for hundreds of hospitals nationwide, Ensemble has unparallelled access to one of the most robust administrative datasets in health care. The team has decades of data aggregation, cleansing, and harmonization efforts, providing an exceptional environment to develop advanced applications.
To power our agentic systems, we’ve harmonized more than 2 petabytes of longitudinal claims data, 80,000 denial audit letters, and 80 million annual transactions mapped to industry-leading outcomes. This data fuels our end-to-end intelligence engine, EIQ, providing structured, context-rich data pipelines spanning across the 600-plus steps of revenue operations.
2. Collaborative domain expertise: Partnering with revenue cycle domain experts at each step of innovation, our AI scientists benefit from direct collaboration with in-house RCM experts, clinical ontologists, and clinical data labeling teams. Together, they architect nuanced use cases that account for regulatory constraints, evolving payer-specific logic and the complexity of revenue cycle processes. Embedded end users provide post-deployment feedback for continuous improvement cycles, flagging friction points early and enabling rapid iteration.
This trilateral collaboration—AI scientists, health-care experts, and end users—creates unmatched contextual awareness that escalates to human judgement appropriately, resulting in a system mirroring decision-making of experienced operators, and with the speed, scale, and consistency of AI, all with human oversight.
3. Elite AI scientists drive differentiation: Ensemble’s incubator model for research and development is comprised of AI talent typically only found in big tech. Our scientists hold PhD and MS degrees from top AI/NLP institutions like Columbia University and Carnegie Mellon University, and bring decades of experience from FAANG companies [Facebook/Meta, Amazon, Apple, Netflix, Google/Alphabet] and AI startups. At Ensemble, they’re able to pursue cutting-edge research in areas like LLMs, reinforcement learning, and neuro-symbolic AI within a mission-driven environment.
The also have unparalleled access to vast amounts of private and sensitive health-care data they wouldn’t see at tech giants paired with compute and infrastructure that startups simply can’t afford. This unique environment equips our scientists with everything they need to test novel ideas and push the frontiers of AI research—while driving meaningful, real-world impact in health care and improving lives.
Strategy in action: Health-care use cases in production and pilot
By pairing the brightest AI minds with the most powerful health-care resources, we’re successfully building, deploying, and scaling AI models that are delivering tangible results across hundreds of health systems. Here’s how we put it into action:
Supporting clinical reasoning: Ensemble deployed neuro-symbolic AI with fine-tuned LLMs to support clinical reasoning. Clinical guidelines are rewritten into proprietary symbolic language and reviewed by humans for accuracy. When a hospital is denied payment for appropriate clinical care, an LLM-based system parses the patient record to produce the same symbolic language describing the patient’s clinical journey, which is matched deterministically against the guidelines to find the right justification and the proper evidence from the patient’s record. An LLM then generates a denial appeal letter with clinical justification grounded in evidence. AI-enabled clinical appeal letters have already improved denial overturn rates by 15% or more across Ensemble’s clients.
Building on this success, Ensemble is piloting similar clinical reasoning capabilities for utilization management and clinical documentation improvement, by analyzing real-time records, flagging documentation gaps, and suggesting compliance enhancements to reduce denial or downgrade risks.
Accelerating accurate reimbursement: Ensemble is piloting a multi-agent reasoning model to manage the complex process of collecting accurate reimbursement from health insurers. With this approach, a complex and coordinated system of autonomous agents work together to interpret account details, retrieve required data from various systems, decide account-specific next actions, automate resolution, and escalate complex cases to humans.
This will help reduce payment delays and minimize administrative burden for hospitals and ultimately improve the financial experience for patients.
Improving patient engagement: Ensemble’s conversational AI agents handle inbound patient calls naturally, routing to human operators as required. Operator assistant agents deliver call transcriptions, surface relevant data, suggest next-best actions, and streamline follow-up routines. According to Ensemble client performance metrics, the combination of these AI capabilities has reduced patient call duration by 35%, increasing one-call resolution rates and improving patient satisfaction by 15%.
The AI path forward in health care demands rigor, responsibility, and real-world impact. By grounding LLMs in symbolic logic and pairing AI scientists with domain experts, Ensemble is successfully deploying scalable AI to improve the experience for health-care providers and the people they serve.
This content was produced by Ensemble. It was not written by MIT Technology Review’s editorial staff.
Cancers (Basel). 2025 Aug 15;17(16):2668. doi: 10.3390/cancers17162668.
ABSTRACT
Background/Objectives: Esophageal and esophagogastric junction adenocarcinoma (EADC-EGJA), which mainly develops from Barrett's esophagus (BE), low-grade dysplasia (LGD), and high-grade dysplasia (HGD), has a poor prognosis and several unmet clinical needs, among which is the detection of minimal residual disease (MRD) after endoscopic/surgical resection. Long interspersed nuclear element-1 (LINE-1), a surrogate marker of global methylation, is considered an emerging biomarker for MRD monitoring. The aim of this study was to determine, by LINE-1 methylation analysis, at which carcinogenesis step global methylation is affected and whether this biomarker could be followed in longitudinal to monitor the disease behavior post-surgery. Methods: Cell-free DNA of 90 patients with non-dysplastic Barrett's esophagus (NDBE), HGD/early EADC-EGJA, or locally advanced/advanced EADC-EGJA were analyzed for LINE-1 methylation, by Methylation-Sensitive Restriction Enzyme droplet digital PCR (MSRE-ddPCR). Twenty-six patients were longitudinally studied by repetitive blood sampling. Results: Global hypomethylation increased during carcinogenesis, with significant difference between locally advanced/advanced EADC-EGJA and NDBE patients (p = 0.028). Longitudinal cases confirmed the rareness of hypomethylation in NDBE cases. The majority of HGD/early EADC-EGJA and locally advanced/advanced EADC-EGJA patients showed methylation changes after resection according to clinical status. Conclusions: This study suggests that global hypomethylation occurs just prior to cancer invasiveness and that it is a promising biomarker to monitor MRD.
J Transl Med. 2025 Aug 27;23(1):964. doi: 10.1186/s12967-025-06993-3.
ABSTRACT
BACKGROUND: Circulating tumour DNA (ctDNA) in liquid biopsies has emerged as a powerful biomarker in cancer patients. Its relative abundance in cell-free DNA serves as a proxy for the overall tumour burden. Here we present GeneBits, a method for cancer therapy monitoring and relapse detection. GeneBits employs tumour-informed enrichment panels targeting 20-100 somatic single-nucleotide variants (SNVs) in plasma-derived DNA, combined with ultra-deep sequencing and unique molecular barcoding. In conjunction with the newly developed computational method umiVar, GeneBits enables accurate detection of molecular residual disease and early relapse identification.
RESULTS: To assess the performance of GeneBits and umiVar, we conducted benchmarking experiments using three different commercial cell-free DNA reference standards. These standards were tested with targeted next-generation sequencing (NGS) workflows from both IDT and Twist, allowing us to evaluate the consistency and accuracy of our approach across different oligo-enrichment strategies. GeneBits achieved comparable depth of coverage across all target sites, demonstrating robust performance independent of the enrichment kit used. For duplex reads with ≥ 4x UMI-family size, umiVar achieved exceptionally low error rates, ranging from 7.4×10-7 to 7.5×10-5. Even when including mixed consensus reads (duplex & simplex), error rates remained low, between 6.1×10-6 and 9×10-5. Furthermore, umiVar enabled variant detection at a limit of detection as low as 0.0017%, with no false positive calls in mutation-free reference samples. In a reanalysed melanoma cohort, variant allele frequency kinetics closely mirrored imaging results, confirming the clinical relevance of our method.
CONCLUSION: GeneBits and umiVar enable highly accurate therapy and relapse monitoring in plasma as well as identification of molecular residual disease within four weeks of tumour surgery or biopsy. By leveraging small, tumour-informed sequencing panels, GeneBits provides a targeted, cost-effective, and scalable approach for ctDNA-based cancer monitoring. The benchmarking experiments using multiple commercial cell-free DNA reference standards confirmed the high sensitivity and specificity of GeneBits and umiVar, making them valuable tools for precision oncology. UmiVar is available at https://github.com/imgag/umiVar .
Metabolites. 2025 Aug 1;15(8):514. doi: 10.3390/metabo15080514.
ABSTRACT
Cancer metabolic reprogramming plays a critical role in tumor progression and therapeutic resistance, underscoring the need for advanced analytical strategies. Metabolomics, leveraging mass spectrometry and nuclear magnetic resonance (NMR) spectroscopy, offers a comprehensive and functional readout of tumor biochemistry. By enabling both targeted metabolite quantification and untargeted profiling, metabolomics captures the dynamic metabolic alterations associated with cancer. The integration of metabolomics with machine learning (ML) approaches further enhances the interpretation of these complex, high-dimensional datasets, providing powerful insights into cancer biology from biomarker discovery to therapeutic targeting. This review systematically examines the transformative role of ML in cancer metabolomics. We discuss how various ML methodologies-including supervised algorithms (e.g., Support Vector Machine, Random Forest), unsupervised techniques (e.g., Principal Component Analysis, t-SNE), and deep learning frameworks-are advancing cancer research. Specifically, we highlight three major applications of ML-metabolomics integration: (1) cancer subtyping, exemplified by the use of Similarity Network Fusion (SNF) and LASSO regression to classify triple-negative breast cancer into subtypes with distinct survival outcomes; (2) biomarker discovery, where Random Forest and Partial Least Squares Discriminant Analysis (PLS-DA) models have achieved >90% accuracy in detecting breast and colorectal cancers through biofluid metabolomics; and (3) prognostic modeling, demonstrated by the identification of race-specific metabolic signatures in breast cancer and the prediction of clinical outcomes in lung and ovarian cancers. Beyond these areas, we explore applications across prostate, thyroid, and pancreatic cancers, where ML-driven metabolomics is contributing to earlier detection, improved risk stratification, and personalized treatment planning. We also address critical challenges, including issues of data quality (e.g., batch effects, missing values), model interpretability, and barriers to clinical translation. Emerging solutions, such as explainable artificial intelligence (XAI) approaches and standardized multi-omics integration pipelines, are discussed as pathways to overcome these hurdles. By synthesizing recent advances, this review illustrates how ML-enhanced metabolomics bridges the gap between fundamental cancer metabolism research and clinical application, offering new avenues for precision oncology through improved diagnosis, prognosis, and tailored therapeutic strategies.
Login
