Multi-omic machine learning predictor of breast cancer therapy response

A review on trends in development and translation of omics signatures in cancer

The field of cancer genomics and transcriptomics has evolved from targeted profiling to swift sequencing of individual tumor genome and transcriptome. The steady growth in genome, epigenome, and transcriptome datasets on a genome-wide scale has significantly increased our capability in capturing signatures that represent both the intrinsic and extrinsic biological features of tumors. These biological differences can help in precise molecular subtyping of cancer, predicting tumor progression, metastatic potential, and resistance to therapeutic agents. In this review, we summarized the current development of genomic, methylomic, transcriptomic, proteomic and metabolic signatures in the field of cancer research and highlighted their potentials in clinical applications to improve diagnosis, prognosis, and treatment decision in cancer patients.

A Machine Learning Algorithm Improves the Diagnostic Accuracy of the Histologic Component of Antibody Mediated Rejection (AMR-H) in Cardiac Transplant Endomyocardial Biopsies

BACKGROUND

Pathologic antibody mediated rejection (pAMR) remains a major driver of graft failure in cardiac transplant patients. The endomyocardial biopsy remains the primary diagnostic tool but presents with challenges, particularly in distinguishing the histologic component (pAMR-H) defined by 1) intravascular macrophage accumulation in capillaries and 2) activated endothelial cells that expand the cytoplasm to narrow or occlude the vascular lumen. Frequently, pAMR-H is difficult to distinguish from acute cellular rejection (ACR) and healing injury. With the advent of digital slide scanning and advances in machine deep learning, artificial intelligence technology is widely under investigation in the areas of oncologic pathology, but in its infancy in transplant pathology. For the first time, we determined if a machine learning algorithm could distinguish pAMR-H from normal myocardium, healing injury and ACR.

MATERIALS AND METHODS

A total of 4,212 annotations (1,053 regions of normal, 1,053 pAMR-H, 1,053 healing injury and 1,053 ACR) were completed from 300 hematoxylin and eosin slides scanned using a Leica Aperio GT450 digital whole slide scanner at 40X magnification. All regions of pAMR-H were annotated from patients confirmed with a previous diagnosis of pAMR2 (>50% positive C4d immunofluorescence and/or >10% CD68 positive intravascular macrophages). Annotations were imported into a Python 3.7 development environment using the OpenSlide™ package and a convolutional neural network approach utilizing transfer learning was performed.

RESULTS

The machine learning algorithm showed 98% overall validation accuracy and pAMR-H was correctly distinguished from specific categories with the following accuracies: normal myocardium (99.2%), healing injury (99.5%) and ACR (99.5%).

CONCLUSION

Our novel deep learning algorithm can reach acceptable, and possibly surpass, performance of current diagnostic standards of identifying pAMR-H. Such a tool may serve as an adjunct diagnostic aid for improving the pathologist's accuracy and reproducibility, especially in difficult cases with high inter-observer variability. This is one of the first studies that provides evidence that an artificial intelligence machine learning algorithm can be trained and validated to diagnose pAMR-H in cardiac transplant patients. Ongoing studies include multi-institutional verification testing to ensure generalizability.

Integration of 3D bioprinting and multi-algorithm machine learning identified glioma susceptibilities and microenvironment characteristics

Glioma, with its heterogeneous microenvironments and genetic subtypes, presents substantial challenges for treatment prediction and development. We integrated 3D bioprinting and multi-algorithm machine learning as a novel approach to enhance the assessment and understanding of glioma treatment responses and microenvironment characteristics. The bioprinted patient-derived glioma tissues successfully recapitulated molecular properties and drug responses of native tumors. We then developed GlioML, a machine learning workflow incorporating nine distinct algorithms and a weighted ensemble model that generated robust gene expression-based predictors, each reflecting the diverse action mechanisms of various compounds and drugs. The ensemble model superseded the performance of all individual algorithms across diverse in vitro systems, including sphere cultures, complex 3D bioprinted multicellular models, and 3D patient-derived tissues. By integrating bioprinting, the evaluative scope of the treatment expanded to T cell-related therapy and anti-angiogenesis targeted therapy. We identified promising compounds and drugs for glioma treatment and revealed distinct immunosuppressive or angiogenic myeloid-infiltrated tumor microenvironments. These insights pave the way for enhanced therapeutic development for glioma and potentially for other cancers, highlighting the broad application potential of this integrative and translational approach.

MOINER: A Novel Multiomics Early Integration Framework for Biomedical Classification and Biomarker Discovery

In the context of precision medicine, multiomics data integration provides a comprehensive understanding of underlying biological processes and is critical for disease diagnosis and biomarker discovery. One commonly used integration method is early integration through concatenation of multiple dimensionally reduced omics matrices due to its simplicity and ease of implementation. However, this approach is seriously limited by information loss and lack of latent feature interaction. Herein, a novel multiomics early integration framework (MOINER) based on information enhancement and image representation learning is thus presented to address the challenges. MOINER employs the self-attention mechanism to capture the intrinsic correlations of omics-features, which make it significantly outperform the existing state-of-the-art methods for multiomics data integration. Moreover, visualizing the attention embedding and identifying potential biomarkers offer interpretable insights into the prediction results. All source codes and model for MOINER are freely available https://github.com/idrblab/MOINER.

Pharmacogenomic profiling of intra-tumor heterogeneity using a large organoid biobank of liver cancer

Inter- and intra-tumor heterogeneity is a major hurdle in primary liver cancer (PLC) precision therapy. Here, we establish a PLC biobank, consisting of 399 tumor organoids derived from 144 patients, which recapitulates histopathology and genomic landscape of parental tumors, and is reliable for drug sensitivity screening, as evidenced by both in vivo models and patient response. Integrative analysis dissects PLC heterogeneity, regarding genomic/transcriptomic characteristics and sensitivity to seven clinically relevant drugs, as well as clinical associations. Pharmacogenomic analysis identifies and validates multi-gene expression signatures predicting drug response for better patient stratification. Furthermore, we reveal c-Jun as a major mediator of lenvatinib resistance through JNK and β-catenin signaling. A compound (PKUF-01) comprising moieties of lenvatinib and veratramine (c-Jun inhibitor) is synthesized and screened, exhibiting a marked synergistic effect. Together, our study characterizes the landscape of PLC heterogeneity, develops predictive biomarker panels, and identifies a lenvatinib-resistant mechanism for combination therapy.

Advances in the study of tertiary lymphoid structures in the immunotherapy of breast cancer

Breast cancer, as one of the most common malignancies in women, exhibits complex and heterogeneous pathological characteristics across different subtypes. Triple-negative breast cancer (TNBC) and HER2-positive breast cancer are two common and highly invasive subtypes within breast cancer. The stability of the breast microbiota is closely intertwined with the immune environment, and immunotherapy is a common approach for treating breast cancer.Tertiary lymphoid structures (TLSs), recently discovered immune cell aggregates surrounding breast cancer, resemble secondary lymphoid organs (SLOs) and are associated with the prognosis and survival of some breast cancer patients, offering new avenues for immunotherapy. Machine learning, as a form of artificial intelligence, has increasingly been used for detecting biomarkers and constructing tumor prognosis models. This article systematically reviews the latest research progress on TLSs in breast cancer and the application of machine learning in the detection of TLSs and the study of breast cancer prognosis. The insights provided contribute valuable perspectives for further exploring the biological differences among different subtypes of breast cancer and formulating personalized treatment strategies.

Single-cell characterization of infiltrating T cells identifies novel targets for gallbladder cancer immunotherapy

Gallbladder cancer (GBC) is among the most common malignancies of biliary tract system due to its limited treatments. The immunotherapeutic targets for T cells are appealing, however, heterogeneity of T cells hinds its further development. We systematically construct T cell atlas by single-cell RNA sequencing; and utilized the identified gene signatures of high_CNV_T cells to predict molecular subtyping towards personalized therapeutic treatments for GBC. We identified 12 T cell subtypes, where exhausted CD8+ T cells, activated/exhausted CD8+ T cells, and regulatory T cells were predominant in tumors. There appeared to be an inverse relationship between Th17 and Treg populations with Th17 levels significantly reduced, whereas Tregs were concomitantly increased. Furthermore, we first established subtyping criterion to identify three subtypes of GBC based on their pro-tumorigenic microenvironments, e.g., the type 1 group shows more M2 macrophages infiltration, while the type 2 group is infiltrated by highly exhausted CD8+ T cells, B cells and Tregs with suppressive activities. Our study provides valuable insights into T cell heterogeneity and suggests that molecular subtyping based on T cells might provide a potential immunotherapeutic strategy to improve GBC treatment.

Pathological and pharmacological functions of the metabolites of polyunsaturated fatty acids mediated by cyclooxygenases, lipoxygenases, and cytochrome P450s in cancers

Oxylipins have garnered increasing attention because they were consistently shown to play pathological and/or pharmacological roles in the development of multiple cancers. Oxylipins are the metabolites of polyunsaturated fatty acids via both enzymatic and nonenzymatic pathways. The enzymes mediating the metabolism of PUFAs include but not limited to lipoxygenases (LOXs), cyclooxygenases (COXs), and cytochrome P450s (CYPs) pathways, as well as the down-stream enzymes. Here, we systematically summarized the pleiotropic effects of oxylipins in different cancers through pathological and pharmacological aspects, with specific reference to the enzyme-mediated oxylipins. We discussed the specific roles of oxylipins on cancer onset, growth, invasion, and metastasis, as well as the expression changes in the associated metabolic enzymes and the associated underlying mechanisms. In addition, we also discussed the clinical application and potential of oxylipins and related metabolic enzymes as the targets for cancer prevention and treatment. We found the specific function of most oxylipins in cancers, especially the underlying mechanisms and clinic applications, deserves and needs further investigation. We believe that research on oxylipins will provide not only more therapeutic targets for various cancers but also dietary guidance for both cancer patients and healthy humans.

Integrative spatial omics reveals distinct tumor-promoting multicellular niches and immunosuppressive mechanisms in African American and European American patients with TNBC

Racial disparities in triple-negative breast cancer (TNBC) outcomes have been reported. However, the biological mechanisms underlying these disparities remain unclear. We integrated imaging mass cytometry and spatial transcriptomics, to characterize the tumor microenvironment (TME) of African American (AA) and European American (EA) patients with TNBC. The TME in AA patients was characterized by interactions between endothelial cells, macrophages, and mesenchymal-like cells, which were associated with poor patient survival. In contrast, the EA TNBC-associated niche is enriched in T-cells and neutrophils suggestive of an exhaustion and suppression of otherwise active T cell responses. Ligand-receptor and pathway analyses of race-associated niches found AA TNBC to be immune cold and hence immunotherapy resistant tumors, and EA TNBC as inflamed tumors that evolved a distinctive immunosuppressive mechanism. Our study revealed the presence of racially distinct tumor-promoting and immunosuppressive microenvironments in AA and EA patients with TNBC, which may explain the poor clinical outcomes.

Embracing cancer complexity: Hallmarks of systemic disease

The last 50 years have witnessed extraordinary developments in understanding mechanisms of carcinogenesis, synthesized as the hallmarks of cancer. Despite this logical framework, our understanding of the molecular basis of systemic manifestations and the underlying causes of cancer-related death remains incomplete. Looking forward, elucidating how tumors interact with distant organs and how multifaceted environmental and physiological parameters impinge on tumors and their hosts will be crucial for advances in preventing and more effectively treating human cancers. In this perspective, we discuss complexities of cancer as a systemic disease, including tumor initiation and promotion, tumor micro- and immune macro-environments, aging, metabolism and obesity, cancer cachexia, circadian rhythms, nervous system interactions, tumor-related thrombosis, and the microbiome. Model systems incorporating human genetic variation will be essential to decipher the mechanistic basis of these phenomena and unravel gene-environment interactions, providing a modern synthesis of molecular oncology that is primed to prevent cancers and improve patient quality of life and cancer outcomes.

Advances in Machine Learning Processing of Big Data from Disease Diagnosis Sensors

Exploring accurate, noninvasive, and inexpensive disease diagnostic sensors is a critical task in the fields of chemistry, biology, and medicine. The complexity of biological systems and the explosive growth of biomarker data have driven machine learning to become a powerful tool for mining and processing big data from disease diagnosis sensors. With the development of bioinformatics and artificial intelligence (AI), machine learning models formed by data mining have been able to guide more sensitive and accurate molecular computing. This review presents an overview of big data collection approaches and fundamental machine learning algorithms and discusses recent advances in machine learning and molecular computational disease diagnostic sensors. More specifically, we highlight existing modular workflows and key opportunities and challenges for machine learning to achieve disease diagnosis through big data mining.

An advanced comprehensive muti-cell-type-specific model for predicting anti-PD-1 therapeutic effect in melanoma

Rationale: Immune checkpoint inhibitors targeting the programmed cell death (PD)-1/PD-L1 pathway have promise in patients with advanced melanoma. However, drug resistance usually results in limited patient benefits. Recent single-cell RNA sequencing studies have elucidated that MM patients display distinctive transcriptional features of tumor cells, immune cells and interstitial cells, including loss of antigen presentation function of tumor cells, exhaustion of CD8+T and extracellular matrix secreted by fibroblasts to prevents immune infiltration, which leads to a poor response to immune checkpoint inhibitors (ICIs). However, cell subgroups beneficial to anti-tumor immunity and the model developed by them remain to be further identified. Methods: In this clinical study of neoadjuvant therapy with anti-PD-1 in advanced melanoma, tumor tissues were collected before and after treatment for single-nucleus sequencing, and the results were verified using multicolor immunofluorescence staining and public datasets. Results: This study describes four cell subgroups which are closely associated with the effectiveness of anti-PD-1 treatment. It also describes a cell-cell communication network, in which the interaction of the four cell subgroups contributes to anti-tumor immunity. Furthermore, we discuss a newly developed predictive model based on these four subgroups that holds significant potential for assessing the efficacy of anti-PD-1 treatment. Conclusions: These findings elucidate the primary mechanism of anti-PD-1 resistance and offer guidance for clinical drug administration for melanoma.

A visual-language foundation model for computational pathology

The accelerated adoption of digital pathology and advances in deep learning have enabled the development of robust models for various pathology tasks across a diverse array of diseases and patient cohorts. However, model training is often difficult due to label scarcity in the medical domain, and a model's usage is limited by the specific task and disease for which it is trained. Additionally, most models in histopathology leverage only image data, a stark contrast to how humans teach each other and reason about histopathologic entities. We introduce CONtrastive learning from Captions for Histopathology (CONCH), a visual-language foundation model developed using diverse sources of histopathology images, biomedical text and, notably, over 1.17 million image-caption pairs through task-agnostic pretraining. Evaluated on a suite of 14 diverse benchmarks, CONCH can be transferred to a wide range of downstream tasks involving histopathology images and/or text, achieving state-of-the-art performance on histology image classification, segmentation, captioning, and text-to-image and image-to-text retrieval. CONCH represents a substantial leap over concurrent visual-language pretrained systems for histopathology, with the potential to directly facilitate a wide array of machine learning-based workflows requiring minimal or no further supervised fine-tuning.

Automated and reusable deep learning (AutoRDL) framework for predicting response to neoadjuvant chemotherapy and axillary lymph node metastasis in breast cancer using ultrasound images: a retrospective, multicentre study

Background

Previous deep learning models have been proposed to predict the pathological complete response (pCR) and axillary lymph node metastasis (ALNM) in breast cancer. Yet, the models often leveraged multiple frameworks, required manual annotation, and discarded low-quality images. We aimed to develop an automated and reusable deep learning (AutoRDL) framework for tumor detection and prediction of pCR and ALNM using ultrasound images with diverse qualities.

Methods

The AutoRDL framework includes a You Only Look Once version 5 (YOLOv5) network for tumor detection and a progressive multi-granularity (PMG) network for pCR and ALNM prediction. The training cohort and the internal validation cohort were recruited from Guangdong Provincial People's Hospital (GPPH) between November 2012 and May 2021. The two external validation cohorts were recruited from the First Affiliated Hospital of Kunming Medical University (KMUH), between January 2016 and December 2019, and Shunde Hospital of Southern Medical University (SHSMU) between January 2014 and July 2015. Prior to model training, super-resolution via iterative refinement (SR3) was employed to improve the spatial resolution of low-quality images from the KMUH. We developed three models for predicting pCR and ALNM: a clinical model using multivariable logistic regression analysis, an image model utilizing the PMG network, and a combined model that integrates both clinical and image data using the PMG network.

Findings

The YOLOv5 network demonstrated excellent accuracy in tumor detection, achieving average precisions of 0.880-0.921 during validation. In terms of pCR prediction, the combined modelpost-SR3 outperformed the combined modelpre-SR3, image modelpost-SR3, image modelpre-SR3, and clinical model (AUC: 0.833 vs 0.822 vs 0.806 vs 0.790 vs 0.712, all p < 0.05) in the external validation cohort (KMUH). Consistently, the combined modelpost-SR3 exhibited the highest accuracy in ALNM prediction, surpassing the combined modelpre-SR3, image modelpost-SR3, image modelpre-SR3, and clinical model (AUC: 0.825 vs 0.806 vs 0.802 vs 0.787 vs 0.703, all p < 0.05) in the external validation cohort 1 (KMUH). In the external validation cohort 2 (SHSMU), the combined model also showed superiority over the clinical and image models (0.819 vs 0.712 vs 0.806, both p < 0.05).

Interpretation

Our proposed AutoRDL framework is feasible in automatically predicting pCR and ALNM in real-world settings, which has the potential to assist clinicians in optimizing individualized treatment options for patients.

Funding

National Key Research and Development Program of China (2023YFF1204600); National Natural Science Foundation of China (82227802, 82302306); Clinical Frontier Technology Program of the First Affiliated Hospital of Jinan University, China (JNU1AF-CFTP-2022-a01201); Science and Technology Projects in Guangzhou (202201020022, 2023A03J1036, 2023A03J1038); Science and Technology Youth Talent Nurturing Program of Jinan University (21623209); and Postdoctoral Science Foundation of China (2022M721349).

A bibliometric insight into neoadjuvant chemotherapy in bladder cancer: trends, collaborations, and future avenues

Background

Neoadjuvant chemotherapy (NAC) followed by radical cystectomy (RC) remains the cornerstone of treatment for muscle-invasive bladder cancer (MIBC). While platinum-based regimens have demonstrated benefits in tumor downstaging and improved long-term survival for selected patients, they may pose risks for those who are ineligible or unresponsive to chemotherapy.

Objective

We undertook a bibliometric analysis to elucidate the breadth of literature on NAC in bladder cancer, discern research trajectories, and underscore emerging avenues of investigation.

Methods

A systematic search of the Web of Science Core Collection (WoSCC) was conducted to identify articles pertaining to NAC in bladder cancer from 1999 to 2022. Advanced bibliometric tools, such as VOSviewer, CiteSpace, and SCImago Graphica, facilitated the examination and depicted the publication trends, geographic contributions, institutional affiliations, journal prominence, author collaborations, and salient keywords, emphasizing the top 25 citation bursts.

Results

Our analysis included 1836 publications spanning 1999 to 2022, indicating a growing trend in both annual publications and citations related to NAC in bladder cancer. The United States emerged as the predominant contributor in terms of publications, citations, and international collaborations. The University of Texas was the leading institution in publication output. "Urologic Oncology Seminars and Original Investigations" was the primary publishing journal, while "European Urology" boasted the highest impact factor. Shariat, Shahrokh F., and Grossman, H.B., were identified as the most prolific and co-cited authors, respectively. Keyword analysis revealed both frequency of occurrence and citation bursts, highlighting areas of concentrated study. Notably, the integration of immunochemotherapy is projected to experience substantial growth in forthcoming research.

Conclusions

Our bibliometric assessment provides a panoramic view of the research milieu surrounding neoadjuvant chemotherapy for bladder cancer, encapsulating the present state, evolving trends, and potential future directions, with a particular emphasis on the promise of immunochemotherapy.

The Molecular Twin artificial-intelligence platform integrates multi-omic data to predict outcomes for pancreatic adenocarcinoma patients

Contemporary analyses focused on a limited number of clinical and molecular biomarkers have been unable to accurately predict clinical outcomes in pancreatic ductal adenocarcinoma. Here we describe a precision medicine platform known as the Molecular Twin consisting of advanced machine-learning models and use it to analyze a dataset of 6,363 clinical and multi-omic molecular features from patients with resected pancreatic ductal adenocarcinoma to accurately predict disease survival (DS). We show that a full multi-omic model predicts DS with the highest accuracy and that plasma protein is the top single-omic predictor of DS. A parsimonious model learning only 589 multi-omic features demonstrated similar predictive performance as the full multi-omic model. Our platform enables discovery of parsimonious biomarker panels and performance assessment of outcome prediction models learning from resource-intensive panels. This approach has considerable potential to impact clinical care and democratize precision cancer medicine worldwide.

Deep learning-based predictive model for pathological complete response to neoadjuvant chemotherapy in breast cancer from biopsy pathological images: a multicenter study

Introduction: Early predictive pathological complete response (pCR) is beneficial for optimizing neoadjuvant chemotherapy (NAC) strategies for breast cancer. The hematoxylin and eosin (HE)-stained slices of biopsy tissues contain a large amount of information on tumor epithelial cells and stromal. The fusion of pathological image features and clinicopathological features is expected to build a model to predict pCR of NAC in breast cancer. Methods: We retrospectively collected a total of 440 breast cancer patients from three hospitals who underwent NAC. HE-stained slices of biopsy tissues were scanned to form whole-slide images (WSIs), and pathological images of representative regions of interest (ROI) of each WSI were selected at different magnifications. Based on several different deep learning models, we propose a novel feature extraction method on pathological images with different magnifications. Further, fused with clinicopathological features, a multimodal breast cancer NAC pCR prediction model based on a support vector machine (SVM) classifier was developed and validated with two additional validation cohorts (VCs). Results: Through experimental validation of several different deep learning models, we found that the breast cancer pCR prediction model based on the SVM classifier, which uses the VGG16 model for feature extraction of pathological images at ×20 magnification, has the best prediction efficacy. The area under the curve (AUC) of deep learning pathological model (DPM) were 0.79, 0.73, and 0.71 for TC, VC1, and VC2, respectively, all of which exceeded 0.70. The AUCs of clinical model (CM), a clinical prediction model established by using clinicopathological features, were 0.79 for TC, 0.73 for VC1, and 0.71 for VC2, respectively. The multimodal deep learning clinicopathological model (DPCM) established by fusing pathological images and clinicopathological features improved the AUC of TC from 0.79 to 0.84. The AUC of VC2 improved from 0.71 to 0.78. Conclusion: Our study reveals that pathological images of HE-stained slices of pre-NAC biopsy tissues can be used to build a pCR prediction model. Combining pathological images and clinicopathological features can further enhance the predictive efficacy of the model.

Comprehensive assessment of immune context and immunotherapy response via noninvasive imaging in gastric cancer

BACKGROUNDThe tumor immune microenvironment can provide prognostic and therapeutic information. We aimed to develop noninvasive imaging biomarkers from computed tomography (CT) for comprehensive evaluation of immune context and investigate their associations with prognosis and immunotherapy response in gastric cancer (GC).METHODSThis study involved 2,600 patients with GC from 9 independent cohorts. We developed and validated 2 CT imaging biomarkers (lymphoid radiomics score [LRS] and myeloid radiomics score [MRS]) for evaluating the IHC-derived lymphoid and myeloid immune context respectively, and integrated them into a combined imaging biomarker [LRS/MRS: low(-) or high(+)] with 4 radiomics immune subtypes: 1 (-/-), 2 (+/-), 3 (-/+), and 4 (+/+). We further evaluated the imaging biomarkers' predictive values on prognosis and immunotherapy response.RESULTSThe developed imaging biomarkers (LRS and MRS) had a high accuracy in predicting lymphoid (AUC range: 0.765-0.773) and myeloid (AUC range: 0.736-0.750) immune context. Further, similar to the IHC-derived immune context, 2 imaging biomarkers (HR range: 0.240-0.761 for LRS; 1.301-4.012 for MRS) and the combined biomarker were independent predictors for disease-free and overall survival in the training and all validation cohorts (all P < 0.05). Additionally, patients with high LRS or low MRS may benefit more from immunotherapy (P < 0.001). Further, a highly heterogeneous outcome on objective response ​rate was observed in 4 imaging subtypes: 1 (-/-) with 27.3%, 2 (+/-) with 53.3%, 3 (-/+) with 10.2%, and 4 (+/+) with 30.0% (P < 0.0001).CONCLUSIONThe noninvasive imaging biomarkers could accurately evaluate the immune context and provide information regarding prognosis and immunotherapy for GC.

Toward Explainable Artificial Intelligence for Precision Pathology

The rapid development of precision medicine in recent years has started to challenge diagnostic pathology with respect to its ability to analyze histological images and increasingly large molecular profiling data in a quantitative, integrative, and standardized way. Artificial intelligence (AI) and, more precisely, deep learning technologies have recently demonstrated the potential to facilitate complex data analysis tasks, including clinical, histological, and molecular data for disease classification; tissue biomarker quantification; and clinical outcome prediction. This review provides a general introduction to AI and describes recent developments with a focus on applications in diagnostic pathology and beyond. We explain limitations including the black-box character of conventional AI and describe solutions to make machine learning decisions more transparent with so-called explainable AI. The purpose of the review is to foster a mutual understanding of both the biomedical and the AI side. To that end, in addition to providing an overview of the relevant foundations in pathology and machine learning, we present worked-through examples for a better practical understanding of what AI can achieve and how it should be done.

Genomic and transcriptomic analysis of breast cancer identifies novel signatures associated with response to neoadjuvant chemotherapy

BACKGROUND

Neoadjuvant chemotherapy (NAC) has become a standard treatment strategy for breast cancer (BC). However, owing to the high heterogeneity of these tumors, it is unclear which patient population most likely benefit from NAC. Multi-omics offer an improved approach to uncovering genomic and transcriptomic changes before and after NAC in BC and to identifying molecular features associated with NAC sensitivity.

METHODS

We performed whole-exome and RNA sequencing on 233 samples (including matched pre- and post-treatment tumors) from 50 BC patients with rigorously defined responses to NAC and analyzed changes in the multi-omics landscape. Molecular features associated with NAC response were identified and validated in a larger internal, and two external validation cohorts, as well as in vitro experiments.

RESULTS

The most frequently altered genes were TP53, TTN, and MUC16 in both pre- and post-treatment tumors. In comparison with pre-treatment tumors, there was a significant decrease in C > A transversion mutations in post-treatment tumors (P = 0.020). NAC significantly decreased the mutation rate (P = 0.006) of the DNA repair pathway and gene expression levels (FDR = 0.007) in this pathway. NAC also significantly changed the expression level of immune checkpoint genes and the abundance of tumor-infiltrating immune and stroma cells, including B cells, activated dendritic cells, γδT cells, M2 macrophages and endothelial cells. Furthermore, there was a higher rate of C > T substitutions in NAC nonresponsive tumors than responsive ones, especially when the substitution site was flanked by C and G. Importantly, there was a unique amplified region at 8p11.23 (containing ADGRA2 and ADRB3) and a deleted region at 3p13 (harboring FOXP1) in NAC nonresponsive and responsive tumors, respectively. Particularly, the CDKAL1 missense variant P409L (p.Pro409Leu, c.1226C > T) decreased BC cell sensitivity to docetaxel, and ADGRA2 or ADRB3 gene amplifications were associated with worse NAC response and poor prognosis in BC patients.

CONCLUSIONS

Our study has revealed genomic and transcriptomic landscape changes following NAC in BC, and identified novel biomarkers (CDKAL1P409L, ADGRA2 and ADRB3) underlying chemotherapy resistance and poor prognosis, which could guide the development of personalized treatments for BC.

Integrating Multi-Omics Data With EHR for Precision Medicine Using Advanced Artificial Intelligence

With the recent advancement of novel biomedical technologies such as high-throughput sequencing and wearable devices, multi-modal biomedical data ranging from multi-omics molecular data to real-time continuous bio-signals are generated at an unprecedented speed and scale every day. For the first time, these multi-modal biomedical data are able to make precision medicine close to a reality. However, due to data volume and the complexity, making good use of these multi-modal biomedical data requires major effort. Researchers and clinicians are actively developing artificial intelligence (AI) approaches for data-driven knowledge discovery and causal inference using a variety of biomedical data modalities. These AI-based approaches have demonstrated promising results in various biomedical and healthcare applications. In this review paper, we summarize the state-of-the-art AI models for integrating multi-omics data and electronic health records (EHRs) for precision medicine. We discuss the challenges and opportunities in integrating multi-omics data with EHRs and future directions. We hope this review can inspire future research and developing in integrating multi-omics data with EHRs for precision medicine.

Preclinical Anticipation of On- and Off-Target Resistance Mechanisms to Anti-Cancer Drugs: A Systematic Review

The advent of targeted therapies has led to tremendous improvements in treatment options and their outcomes in the field of oncology. Yet, many cancers outsmart precision drugs by developing on-target or off-target resistance mechanisms. Gaining the ability to resist treatment is the rule rather than the exception in tumors, and it remains a major healthcare challenge to achieve long-lasting remission in most cancer patients. Here, we discuss emerging strategies that take advantage of innovative high-throughput screening technologies to anticipate on- and off-target resistance mechanisms before they occur in treated cancer patients. We divide the methods into non-systematic approaches, such as random mutagenesis or long-term drug treatment, and systematic approaches, relying on the clustered regularly interspaced short palindromic repeats (CRISPR) system, saturated mutagenesis, or computational methods. All these new developments, especially genome-wide CRISPR-based screening platforms, have significantly accelerated the processes for identification of the mechanisms responsible for cancer drug resistance and opened up new avenues for future treatments.

Spatial Distribution of Immune Cells Drives Resistance to Neoadjuvant Chemotherapy in Triple-Negative Breast Cancer

Neoadjuvant chemotherapy (NAC) alone or combined with target therapies represents the standard of care for localized triple-negative breast cancer (TNBC). However, only a fraction of patients have a response, necessitating better understanding of the complex elements in the TNBC ecosystem that establish continuous and multidimensional interactions. Resolving such complexity requires new spatially-defined approaches. Here, we used spatial transcriptomics to investigate the multidimensional organization of TNBC at diagnosis and explore the contribution of each cell component to response to NAC. Starting from a consecutive retrospective series of TNBC cases, we designed a case-control study including 24 patients with TNBC of which 12 experienced a pathologic complete response (pCR) and 12 no-response or progression (pNR) after NAC. Over 200 regions of interest (ROI) were profiled. Our computational approaches described a model that recapitulates clinical response to therapy. The data were validated in an independent cohort of patients. Differences in the transcriptional program were detected in the tumor, stroma, and immune infiltrate comparing patients with a pCR with those with pNR. In pCR, spatial contamination between the tumor mass and the infiltrating lymphocytes was observed, sustained by a massive activation of IFN-signaling. Conversely, pNR lesions displayed increased pro-angiogenetic signaling and oxygen-based metabolism. Only modest differences were observed in the stroma, revealing a topology-based functional heterogeneity of the immune infiltrate. Thus, spatial transcriptomics provides fundamental information on the multidimensionality of TNBC and allows an effective prediction of tumor behavior. These results open new perspectives for the improvement and personalization of therapeutic approaches to TNBCs.

Diagnosis of Esophageal Squamous Cell Carcinoma by High-Performance Serum Metabolic Fingerprints: A Retrospective Study

Esophageal squamous cell carcinoma (ESCC) is a highly prevalent and aggressive malignancy, and timely diagnosis of ESCC contributes to an increased cancer survival rate. However, current detection methods for ESCC mainly rely on endoscopic examination, limited by a relatively low participation rate. Herein, ferric-particle-enhanced laser desorption/ionization mass spectrometry (FPELDI MS) is utilized to record the serum metabolic fingerprints (SMFs) from a retrospective cohort (523 non-ESCC participants and 462 ESCC patients) to build diagnostic models toward ESCC. The PFELDI MS achieved high speed (≈30 s per sample), desirable reproducibility (coefficients of variation < 15%), and high throughput (985 samples with ≈124 200 data points for each spectrum). Desirable diagnostic performance with area-under-the-curves (AUCs) of 0.925-0.966 is obtained through machine learning of SMFs. Further, a metabolic biomarker panel is constructed, exhibiting superior diagnostic sensitivity (72.2-79.4%, p < 0.05) as compared with clinical protein biomarker tests (4.3-22.9%). Notably, the biomarker panel afforded an AUC of 0.844 (95% confidence interval [CI]: 0.806-0.880) toward early ESCC diagnosis. This work highlighted the potential of metabolic analysis for accurate screening and early detection of ESCC and offered insights into the metabolic characterization of diseases including but not limited to ESCC.

Risk stratification of papillary thyroid cancers using multidimensional machine learning

BACKGROUND

Papillary thyroid cancer (PTC) is one of the most common endocrine malignancies with different risk levels. However, preoperative risk assessment of PTC is still a challenge in the worldwide. Here, the authors first report a Preoperative Risk Assessment Classifier for PTC (PRAC-PTC) by multidimensional features including clinical indicators, immune indices, genetic feature, and proteomics.

MATERIALS AND METHODS

The 558 patients collected from June 2013 to November 2020 were allocated to three groups: the discovery set [274 patients, 274 formalin-fixed paraffin-embedded (FFPE)], the retrospective test set (166 patients, 166 FFPE), and the prospective test set (118 patients, 118 fine-needle aspiration). Proteomic profiling was conducted by FFPE and fine-needle aspiration tissues from the patients. Preoperative clinical information and blood immunological indices were collected. The BRAFV600E mutation were detected by the amplification refractory mutation system.

RESULTS

The authors developed a machine learning model of 17 variables based on the multidimensional features of 274 PTC patients from a retrospective cohort. The PRAC-PTC achieved areas under the curve (AUC) of 0.925 in the discovery set and was validated externally by blinded analyses in a retrospective cohort of 166 PTC patients (0.787 AUC) and a prospective cohort of 118 PTC patients (0.799 AUC) from two independent clinical centres. Meanwhile, the preoperative predictive risk effectiveness of clinicians was improved with the assistance of PRAC-PTC, and the accuracies reached at 84.4% (95% CI: 82.9-84.4) and 83.5% (95% CI: 82.2-84.2) in the retrospective and prospective test sets, respectively.

CONCLUSION

This study demonstrated that the PRAC-PTC that integrating clinical data, gene mutation information, immune indices, high-throughput proteomics and machine learning technology in multicentre retrospective and prospective clinical cohorts can effectively stratify the preoperative risk of PTC and may decrease unnecessary surgery or overtreatment.

Genomics in Clinical trials for Breast Cancer

Breast cancer (B.C.) still has increasing incidences and mortality rates globally. It is known that B.C. and other cancers have a very high rate of genetic heterogeneity and genomic mutations. Traditional oncology approaches have not been able to provide a lasting solution. Targeted therapeutics have been instrumental in handling the complexity and resistance associated with B.C. However, the progress of genomic technology has transformed our understanding of the genetic landscape of breast cancer, opening new avenues for improved anti-cancer therapeutics. Genomics is critical in developing tailored therapeutics and identifying patients most benefit from these treatments. The next generation of breast cancer clinical trials has incorporated next-generation sequencing technologies into the process, and we have seen benefits. These innovations have led to the approval of better-targeted therapies for patients with breast cancer. Genomics has a role to play in clinical trials, including genomic tests that have been approved, patient selection and prediction of therapeutic response. Multiple clinical trials in breast cancer have been done and are still ongoing, which have applied genomics technology. Precision medicine can be achieved in breast cancer therapy with increased efforts and advanced genomic studies in this domain. Genomics studies assist with patient outcomes improvement and oncology advancement by providing a deeper understanding of the biology behind breast cancer. This article will examine the present state of genomics in breast cancer clinical trials.

Automated Prediction of Neoadjuvant Chemoradiotherapy Response in Locally Advanced Cervical Cancer Using Hybrid Model-Based MRI Radiomics

BACKGROUND

This study aimed to develop a model that automatically predicts the neoadjuvant chemoradiotherapy (nCRT) response for patients with locally advanced cervical cancer (LACC) based on T2-weighted MR images and clinical parameters.

METHODS

A total of 138 patients were enrolled, and T2-weighted MR images and clinical information of the patients before treatment were collected. Clinical information included age, stage, pathological type, squamous cell carcinoma (SCC) level, and lymph node status. A hybrid model extracted the domain-specific features from the computational radiomics system, the abstract features from the deep learning network, and the clinical parameters. Then, it employed an ensemble learning classifier weighted by logistic regression (LR) classifier, support vector machine (SVM) classifier, K-Nearest Neighbor (KNN) classifier, and Bayesian classifier to predict the pathologic complete response (pCR). The area under the receiver operating characteristics curve (AUC), accuracy (ACC), true positive rate (TPR), true negative rate (TNR), and precision were used as evaluation metrics.

RESULTS

Among the 138 LACC patients, 74 were in the pCR group, and 64 were in the non-pCR group. There was no significant difference between the two cohorts in terms of tumor diameter (p = 0.787), lymph node (p = 0.068), and stage before radiotherapy (p = 0.846), respectively. The 109-dimension domain features and 1472-dimension abstract features from MRI images were used to form a hybrid model. The average AUC, ACC, TPR, TNR, and precision of the proposed hybrid model were about 0.80, 0.71, 0.75, 0.66, and 0.71, while the AUC values of using clinical parameters, domain-specific features, and abstract features alone were 0.61, 0.67 and 0.76, respectively. The AUC value of the model without an ensemble learning classifier was 0.76.

CONCLUSIONS

The proposed hybrid model can predict the radiotherapy response of patients with LACC, which might help radiation oncologists create personalized treatment plans for patients.

Multiomics insights on the onset, progression, and metastatic evolution of breast cancer

Breast cancer is the most common malignant neoplasm in women. Despite progress to date, 700,000 women worldwide died of this disease in 2020. Apparently, the prognostic markers currently used in the clinic are not sufficient to determine the most appropriate treatment. For this reason, great efforts have been made in recent years to identify new molecular biomarkers that will allow more precise and personalized therapeutic decisions in both primary and recurrent breast cancers. These molecular biomarkers include genetic and post-transcriptional alterations, changes in protein expression, as well as metabolic, immunological or microbial changes identified by multiple omics technologies (e.g., genomics, epigenomics, transcriptomics, proteomics, glycomics, metabolomics, lipidomics, immunomics and microbiomics). This review summarizes studies based on omics analysis that have identified new biomarkers for diagnosis, patient stratification, differentiation between stages of tumor development (initiation, progression, and metastasis/recurrence), and their relevance for treatment selection. Furthermore, this review highlights the importance of clinical trials based on multiomics studies and the need to advance in this direction in order to establish personalized therapies and prolong disease-free survival of these patients in the future.

Gut microbiota landscape and potential biomarker identification in female patients with systemic lupus erythematosus using machine learning

Objectives

Systemic Lupus Erythematosus (SLE) is a complex autoimmune disease that disproportionately affects women. Early diagnosis and prevention are crucial for women's health, and the gut microbiota has been found to be strongly associated with SLE. This study aimed to identify potential biomarkers for SLE by characterizing the gut microbiota landscape using feature selection and exploring the use of machine learning (ML) algorithms with significantly dysregulated microbiotas (SDMs) for early identification of SLE patients. Additionally, we used the SHapley Additive exPlanations (SHAP) interpretability framework to visualize the impact of SDMs on the risk of developing SLE in females.

Methods

Stool samples were collected from 54 SLE patients and 55 Negative Controls (NC) for microbiota analysis using 16S rRNA sequencing. Feature selection was performed using Elastic Net and Boruta on species-level taxonomy. Subsequently, four ML algorithms, namely logistic regression (LR), Adaptive Boosting (AdaBoost), Random Forest (RF), and eXtreme gradient boosting (XGBoost), were used to achieve early identification of SLE with SDMs. Finally, the best-performing algorithm was combined with SHAP to explore how SDMs affect the risk of developing SLE in females.

Results

Both alpha and beta diversity were found to be different in SLE group. Following feature selection, 68 and 21 microbiota were retained in Elastic Net and Boruta, respectively, with 16 microbiota overlapping between the two, i.e., SDMs for SLE. The four ML algorithms with SDMs could effectively identify SLE patients, with XGBoost performing the best, achieving Accuracy, Sensitivity, Specificity, Positive Predictive Value, Negative Predictive Value, and AUC values of 0.844, 0.750, 0.938, 0.923, 0.790, and 0.930, respectively. The SHAP interpretability framework showed a complex non-linear relationship between the relative abundance of SDMs and the risk of SLE, with Escherichia_fergusonii having the largest SHAP value.

Conclusions

This study revealed dysbiosis in the gut microbiota of female SLE patients. ML classifiers combined with SDMs can facilitate early identification of female patients with SLE, particularly XGBoost. The SHAP interpretability framework provides insight into the impact of SDMs on the risk of SLE and may inform future scientific treatment for SLE.

Machine Learning Methods Based on CT Features Differentiate G1/G2 From G3 Pancreatic Neuroendocrine Tumors

RATIONALE AND OBJECTIVES

To identify CT features for distinguishing grade 1 (G1)/grade 2 (G2) from grade 3 (G3) pancreatic neuroendocrine tumors (PNETs) using different machine learning (ML) methods.

MATERIALS AND METHODS

A total of 147 patients with 155 lesions confirmed by pathology were retrospectively included. Clinical-demographic and radiological CT features was collected. The entire cohort was separated into training and validation groups at a 7:3 ratio. Least absolute shrinkage and selection operator (LASSO) algorithm and principal component analysis (PCA) were used to select features. Three ML methods, namely logistic regression (LR), support vector machine (SVM), and K-nearest neighbor (KNN) were used to build a differential model. Receiver operating characteristic (ROC) curves and precision-recall curves for each ML method were generated. The area under the curve (AUC), accuracy rate, sensitivity, and specificity were calculated.

RESULTS

G3 PNETs were more likely to present with invasive behaviors and lower enhancement than G1/G2 PNETs. The LR classifier yielded the highest AUC of 0.964 (95% confidence interval [CI]: 0.930, 0.972), with 95.4% accuracy rate, 95.7% sensitivity, and 92.9% specificity, followed by SVM (AUC: 0.957) and KNN (AUC: 0.893) in the training group. In the validation group, the SVM classier reached the highest AUC of 0.952 (95% CI: 0.860, 0.981), with 91.5% accuracy rate, 97.3% sensitivity, and 70% specificity, followed by LR (AUC: 0.949) and KNN (AUC: 0.923).

CONCLUSIONS

The LR and SVM classifiers had the best performance in the training group and validation group, respectively. ML method could be helpful in differentiating between G1/G2 and G3 PNETs.

iGenSig-Rx: an integral genomic signature based white-box tool for modeling cancer therapeutic responses using multi-omics data

Multi-omics sequencing is expected to become clinically routine within the next decade and transform clinical care. However, there is a paucity of viable and interpretable genome-wide modeling methods that can facilitate rational selection of patients for tailored intervention. Here we develop an integral genomic signature-based method called iGenSig-Rx as a white-box tool for modeling therapeutic response based on clinical trial datasets with improved cross-dataset applicability and tolerance to sequencing bias. This method leverages high-dimensional redundant genomic features to address the challenges of cross-dataset modeling, a concept similar to the use of redundant steel rods to reinforce the pillars of a building. Using genomic datasets for HER2 targeted therapies, the iGenSig-Rx model demonstrates stable predictive power across four independent clinical trials. More importantly, the iGenSig-Rx model offers the level of transparency much needed for clinical application, allowing for clear explanations as to how the predictions are produced, how the features contribute to the prediction, and what are the key underlying pathways. We expect that iGenSig-Rx as a class of biologically interpretable multi-omics modeling methods will have broad applications in big-data based precision oncology. The R package is available: https://github.com/wangxlab/iGenSig-Rx. NOTE: the Github website will be released upon publication and the R package is available for review through google drive: https://drive.google.com/drive/folders/1KgecmUoon9-h2Dg1rPCyEGFPOp28Ols3?usp=sharing.

Novel research and future prospects of artificial intelligence in cancer diagnosis and treatment

Research into the potential benefits of artificial intelligence for comprehending the intricate biology of cancer has grown as a result of the widespread use of deep learning and machine learning in the healthcare sector and the availability of highly specialized cancer datasets. Here, we review new artificial intelligence approaches and how they are being used in oncology. We describe how artificial intelligence might be used in the detection, prognosis, and administration of cancer treatments and introduce the use of the latest large language models such as ChatGPT in oncology clinics. We highlight artificial intelligence applications for omics data types, and we offer perspectives on how the various data types might be combined to create decision-support tools. We also evaluate the present constraints and challenges to applying artificial intelligence in precision oncology. Finally, we discuss how current challenges may be surmounted to make artificial intelligence useful in clinical settings in the future.

Classification of tumor types using XGBoost machine learning model: a vector space transformation of genomic alterations

BACKGROUND

Machine learning (ML) represents a powerful tool to capture relationships between molecular alterations and cancer types and to extract biological information. Here, we developed a plain ML model aimed at distinguishing cancer types based on genetic lesions, providing an additional tool to improve cancer diagnosis, particularly for tumors of unknown origin.

METHODS

TCGA data from 9,927 samples spanning 32 different cancer types were downloaded from cBioportal. A vector space model type data transformation technique was designed to build consistently homogeneous new datasets containing, as predictive features, calls for somatic point mutations and copy number variations at chromosome arm-level, thus allowing the use of the XGBoost classifier models. Considering the imbalance in the dataset, due to large difference in the number of cases for each tumor, two preprocessing strategies were considered: i) setting a percentage cut-off threshold to remove less represented cancer types, ii) dividing cancer types into different groups based on biological criteria and training a specific XGBoost model for each of them. The performance of all trained models was mainly assessed by the out-of-sample balanced accuracy (BACC) and the AUC scores.

RESULTS

The XGBoost classifier achieved the best performance (BACC 77%; AUC 97%) on a dataset containing the 10 most represented tumor types. Moreover, dividing the 18 most represented cancers into three different groups (endocrine-related carcinomas, other carcinomas and other cancers),such analysis models achieved 78%, 71% and 86% BACC, respectively, with AUC scores greater than 96%. In addition, the model capable of linking each group to a specific cancer type reached 81% BACC and 94% AUC. Overall, the diagnostic potential of our model was comparable/higher with respect to others already described in literature and based on similar molecular data and ML approaches.

CONCLUSIONS

A boosted ML approach able to accurately discriminate different cancer types was developed. The methodology builds datasets simpler and more interpretable than the original data, while keeping enough information to accurately train standard ML models without resorting to sophisticated Deep Learning architectures. In combination with histopathological examinations, this approach could improve cancer diagnosis by using specific DNA alterations, processed by a replicable and easy-to-use automated technology. The study encourages new investigations which could further increase the classifier's performance, for example by considering more features and dividing tumors into their main molecular subtypes.

Cell-free multi-omics analysis reveals potential biomarkers in gastrointestinal cancer patients' blood

During cancer progression, tumorigenic and immune signals are spread through circulating molecules, such as cell-free DNA (cfDNA) and cell-free RNA (cfRNA) in the blood. So far, they have not been comprehensively investigated in gastrointestinal cancers. Here, we profile 4 categories of cell-free omics data from patients with colorectal cancer and patients with stomach adenocarcinoma and then assay 15 types of genomic, epigenomic, and transcriptomic variations. We find that multi-omics data are more appropriate for detection of cancer genes compared with single-omics data. In particular, cfRNAs are more sensitive and informative than cfDNAs in terms of detection rate, enriched functional pathways, etc. Moreover, we identify several peripheral immune signatures that are suppressed in patients with cancer. Specifically, we establish a γδ-T cell score and a cancer-associated-fibroblast (CAF) score, providing insights into clinical statuses like cancer stage and survival. Overall, we reveal a cell-free multi-molecular landscape that is useful for blood monitoring in personalized cancer treatment.

The Emerging Roles of Exosomal miRNAs in Breast Cancer Progression and Potential Clinical Applications

Breast cancer remains the leading malignancy in terms of morbidity and mortality today. The tumor microenvironment of breast cancer includes multiple cell types, secreted proteins, and signaling components such as exosomes. Among these, exosomes have a lipid bilayer structure. Exosomes can reflect the biological traits of the parent cell and carry a variety of biologically active components, including proteins, lipids, small molecules, and non-coding RNAs, which include miRNA, lncRNA, and circRNA. MiRNAs are a group of non-coding RNAs of approximately 20-23 nucleotides in length encoded by the genome, triggering silencing and functional repression of target genes. MiRNAs have been shown to play a significant role in the development of cancer owing to their role in the prognosis, pathogenesis, diagnosis, and treatment of cancer. MiRNAs in exosomes can serve as effective mediators of information transfer from parental cells to recipient cells and trigger changes in biological traits such as proliferation, invasion, migration, and drug resistance. These changes can profoundly alter the progression of breast cancer. Therefore, here, we systematically summarize the association of exosomal miRNAs on breast cancer progression, diagnosis, and treatment in the hope of providing novel strategies and directions for subsequent breast cancer treatment.

Advances in Early Breast Cancer Risk Profiling: From Histopathology to Molecular Technologies

Early breast cancer (BC) is the definition applied to breast-confined tumors with or without limited involvement of locoregional lymph nodes. While risk stratification is essential for guiding clinical decisions, it can be a complex endeavor in these patients due to the absence of comprehensive guidelines. Histopathological analysis and biomarker assessment play a pivotal role in defining patient outcomes. Traditional histological criteria such as tumor size, lymph node involvement, histological type and grade, lymphovascular invasion, and immune cell infiltration are significant prognostic indicators. In addition to the hormone receptor, HER2, and-in specific scenarios-BRCA1/2 testing, molecular subtyping through gene expression profiling provides valuable insights to tailor clinical decision-making. The emergence of "omics" technologies, applicable to both tissue and liquid biopsy samples, has broadened our arsenal for evaluating the risk of early BC. However, a pressing need remains for standardized methodologies and integrated pathological models that encompass multiple analytical dimensions. In this study, we provide a detailed examination of the existing strategies for early BC risk stratification, intending to serve as a practical guide for histopathologists and molecular pathologists.

Association of SLC12A1 and GLUR4 Ion Transporters with Neoadjuvant Chemoresistance in Luminal Locally Advanced Breast Cancer

Chemoresistance to standard neoadjuvant treatment commonly occurs in locally advanced breast cancer, particularly in the luminal subtype, which is hormone receptor-positive and represents the most common subtype of breast cancer associated with the worst outcomes. Identifying the genes associated with chemoresistance is crucial for understanding the underlying mechanisms and discovering effective treatments. In this study, we aimed to identify genes linked to neoadjuvant chemotherapy resistance in 62 retrospectively included patients with luminal breast cancer. Whole RNA sequencing of 12 patient biopsies revealed 269 differentially expressed genes in chemoresistant patients. We further validated eight highly correlated genes associated with resistance. Among these, solute carrier family 12 member 1 (SLC12A1) and glutamate ionotropic AMPA type subunit 4 (GRIA4), both implicated in ion transport, showed the strongest association with chemoresistance. Notably, SLC12A1 expression was downregulated, while protein levels of glutamate receptor 4 (GLUR4), encoded by GRIA4, were elevated in patients with a worse prognosis. Our results suggest a potential link between SLC12A1 gene expression and GLUR4 protein levels with chemoresistance in luminal breast cancer. In particular, GLUR4 protein could serve as a potential target for drug intervention to overcome chemoresistance.

Immunological and clinicopathological features predict HER2-positive breast cancer prognosis in the neoadjuvant NeoALTTO and CALGB 40601 randomized trials

The identification of prognostic markers in patients receiving neoadjuvant therapy is crucial for treatment optimization in HER2-positive breast cancer, with the immune microenvironment being a key factor. Here, we investigate the complexity of B and T cell receptor (BCR and TCR) repertoires in the context of two phase III trials, NeoALTTO and CALGB 40601, evaluating neoadjuvant paclitaxel with trastuzumab and/or lapatinib in women with HER2-positive breast cancer. BCR features, particularly the number of reads and clones, evenness and Gini index, are heterogeneous according to hormone receptor status and PAM50 subtypes. Moreover, BCR measures describing clonal expansion, namely evenness and Gini index, are independent prognostic factors. We present a model developed in NeoALTTO and validated in CALGB 40601 that can predict event-free survival (EFS) by integrating hormone receptor and clinical nodal status, breast pathological complete response (pCR), stromal tumor-infiltrating lymphocyte levels (%) and BCR repertoire evenness. A prognostic score derived from the model and including those variables, HER2-EveNT, allows the identification of patients with 5-year EFS > 90%, and, in those not achieving pCR, of a subgroup of immune-enriched tumors with an excellent outcome despite residual disease.

Shared-Specific Feature Learning With Bottleneck Fusion Transformer for Multi-Modal Whole Slide Image Analysis

The fusion of multi-modal medical data is essential to assist medical experts to make treatment decisions for precision medicine. For example, combining the whole slide histopathological images (WSIs) and tabular clinical data can more accurately predict the lymph node metastasis (LNM) of papillary thyroid carcinoma before surgery to avoid unnecessary lymph node resection. However, the huge-sized WSI provides much more high-dimensional information than low-dimensional tabular clinical data, making the information alignment challenging in the multi-modal WSI analysis tasks. This paper presents a novel transformer-guided multi-modal multi-instance learning framework to predict lymph node metastasis from both WSIs and tabular clinical data. We first propose an effective multi-instance grouping scheme, named siamese attention-based feature grouping (SAG), to group high-dimensional WSIs into representative low-dimensional feature embeddings for fusion. We then design a novel bottleneck shared-specific feature transfer module (BSFT) to explore the shared and specific features between different modalities, where a few learnable bottleneck tokens are utilized for knowledge transfer between modalities. Moreover, a modal adaptation and orthogonal projection scheme were incorporated to further encourage BSFT to learn shared and specific features from multi-modal data. Finally, the shared and specific features are dynamically aggregated via an attention mechanism for slide-level prediction. Experimental results on our collected lymph node metastasis dataset demonstrate the efficiency of our proposed components and our framework achieves the best performance with AUC (area under the curve) of 97.34%, outperforming the state-of-the-art methods by over 1.27%.

Colorectal cancer tissue-originated spheroids reveal tumor intrinsic signaling pathways and mimic patient clinical chemotherapeutic response as a rapid and valid model

Locally advanced colorectal cancer requires preoperative chemotherapy to reduce local recurrence and metastasis rates, but it remains difficult to predict the tumor will be sensitive to which treatments. The patient-derived organoids (PDOs) are considered an effective platform for predicting tumor drug responses in precision oncology. However, it has the limitation of being time-consuming in practical applications, especially in neoadjuvant treatment. Here we used cancer tissue-originated spheroids (CTOS) method to establish organoids from a heterogeneous population of colorectal cancer specimens, and evaluated the capacity of CTOS to predict clinical drug responses. By analyzing the relationship of the activities of drug-treated CTOS, drug targets and target-related pathways, tumor intrinsic effective-target-related pathways can be identified. These pathways were highly matched to the abnormal pathways indicated by whole-exome sequencing. Based on this, we used half effective concentration gradients to classify CTOS as sensitive or resistant to chemotherapy regimens within a week, for predicting neoadjuvant treatment outcomes for colorectal cancer patients. The drug sensitivity test results are highly matched to the clinical responses to treatment in individual patients. Thus, our data suggested that CTOS models can be effectively screened ex vivo to identify pathways sensitive to chemotherapies. These data also supported organoid research for personalized clinical medication guidance immediately after diagnosis in patients with advanced colorectal cancer.

Deep radiomics-based fusion model for prediction of bevacizumab treatment response and outcome in patients with colorectal cancer liver metastases: a multicentre cohort study

Background

Accurate tumour response prediction to targeted therapy allows for personalised conversion therapy for patients with unresectable colorectal cancer liver metastases (CRLM). In this study, we aimed to develop and validate a multi-modal deep learning model to predict the efficacy of bevacizumab in patients with initially unresectable CRLM using baseline PET/CT, clinical data, and colonoscopy biopsy specimens.

Methods

In this multicentre cohort study, we retrospectively collected data of 307 patients with CRLM from the BECOME study (NCT01972490) (Zhongshan Hospital of Fudan University, Shanghai) and two independent Chinese cohorts (internal validation cohort from January 1, 2018 to December 31, 2018 at Zhongshan Hospital of Fudan University; external validation cohort from January 1, 2020 to December 31, 2020 at Zhongshan Hospital-Xiamen, Shanghai, and the First Hospital of Wenzhou Medical University, Wenzhou). The main inclusion criteria were that patients with CRLM had pre-treatment PET/CT images as well as colonoscopy specimens. After extracting PET/CT features with deep neural networks (DNN) and selecting related clinical factors using LASSO analysis, a random forest classifier was built as the Deep Radiomics Bevacizumab efficacy predicting model (DERBY). Furthermore, by combining histopathological biomarkers into DERBY, we established DERBY+. The performance of model was evaluated using area under the curve (AUC), sensitivity, specificity, positive predictive value, and negative predictive value.

Findings

DERBY achieved promising performance in predicting bevacizumab sensitivity with an AUC of 0.77 and 95% confidence interval (CI) [0.67-0.87]. After combining histopathological features, we developed DERBY+, which had more robust accuracy for predicting tumour response in external validation cohort (AUC 0.83 and 95% CI [0.75-0.92], sensitivity 80.4%, specificity 76.8%). DERBY+ also had prognostic value: the responders had longer progression-free survival (median progression-free survival: 9.6 vs 6.3 months, p = 0.002) and overall survival (median overall survival: 27.6 vs 18.5 months, p = 0.010) than non-responders.

Interpretation

This multi-modal deep radiomics model, using PET/CT, clinical data and histopathological data, was able to identify patients with bevacizumab-sensitive CRLM, providing a favourable approach for precise patient treatment. To further validate and explore the clinical impact of this work, future prospective studies with larger patient cohorts are warranted.

Funding

The National Natural Science Foundation of China; Fujian Provincial Health Commission Project; Xiamen Science and Technology Agency Program; Clinical Research Plan of SHDC; Shanghai Science and Technology Committee Project; Clinical Research Plan of SHDC; Zhejiang Provincial Natural Science Foundation of China; and National Science Foundation of Xiamen.

Artificial intelligence in breast cancer: application and future perspectives

Breast cancer is one of the most common cancers and is one of the leading causes of cancer-related deaths in women worldwide. Early diagnosis and treatment are the key for a favorable prognosis. The application of artificial intelligence technology in the medical field is increasingly extensive, including image analysis, automated diagnosis, intelligent pharmaceutical system, personalized treatment and so on. AI-based breast cancer imaging, pathology and adjuvant therapy technology cannot only reduce the workload of clinicians, but also continuously improve the accuracy and sensitivity of breast cancer diagnosis and treatment. This paper reviews the application of AI in breast cancer, as well as looks ahead and poses challenges to the future development of AI for breast cancer detection and therapeutic, so as to provide ideas for future research.

Predicting diagnosis and survival of bone metastasis in breast cancer using machine learning

This study aimed at establishing more accurate predictive models based on novel machine learning algorithms, with the overarching goal of providing clinicians with effective decision-making assistance. We retrospectively analyzed the breast cancer patients recorded in the Surveillance, Epidemiology, and End Results (SEER) database from 2010 to 2016. Multivariable logistic regression analyses were used to identify risk factors for bone metastases in breast cancer, whereas Cox proportional hazards regression analyses were used to identify prognostic factors for breast cancer with bone metastasis (BCBM). Based on the identified risk and prognostic factors, we developed diagnostic and prognostic models that incorporate six machine learning classifiers. We then used the area under the receiver operating characteristic (ROC) curve (AUC), learning curve, precision curve, calibration plot, and decision curve analysis to evaluate performance of the machine learning models. Univariable and multivariable logistic regression analyses showed that bone metastases were significantly associated with age, race, sex, grade, T stage, N stage, surgery, radiotherapy, chemotherapy, tumor size, brain metastasis, liver metastasis, lung metastasis, breast subtype, and PR. Univariate and multivariate Cox regression analyses revealed that age, race, marital status, grade, surgery, radiotherapy, chemotherapy, brain metastasis, liver metastasis, lung metastasis, breast subtype, ER, and PR were closely associated with the prognosis of BCBM. Among the six machine learning models, the XGBoost algorithm predicted the most accurate results (Diagnostic model AUC = 0.98; Prognostic model AUC = 0.88). According to the Shapley additive explanations (SHAP), the most critical feature of the diagnostic model was surgery, followed by N stage. Interestingly, surgery was also the most critical feature of prognostic model, followed by liver metastasis. Based on the XGBoost algorithm, we could effectively predict the diagnosis and survival of bone metastasis in breast cancer and provide targeted references for the treatment of BCBM patients.

Machine learning links T cell function and spatial localization to neoadjuvant immunotherapy and clinical outcome in pancreatic cancer

Tumor molecular datasets are becoming increasingly complex, making it nearly impossible for humans alone to effectively analyze them. Here, we demonstrate the power of using machine learning to analyze a single-cell, spatial, and highly multiplexed proteomic dataset from human pancreatic cancer and reveal underlying biological mechanisms that may contribute to clinical outcome. A novel multiplex immunohistochemistry antibody panel was used to audit T cell functionality and spatial localization in resected tumors from treatment-naive patients with localized pancreatic ductal adenocarcinoma (PDAC) compared to a second cohort of patients treated with neoadjuvant agonistic CD40 (αCD40) monoclonal antibody therapy. In total, nearly 2.5 million cells from 306 tissue regions collected from 29 patients across both treatment cohorts were assayed, and more than 1,000 tumor microenvironment (TME) features were quantified. We then trained machine learning models to accurately predict αCD40 treatment status and disease-free survival (DFS) following αCD40 therapy based upon TME features. Through downstream interpretation of the machine learning models' predictions, we found αCD40 therapy to reduce canonical aspects of T cell exhaustion within the TME, as compared to treatment-naive TMEs. Using automated clustering approaches, we found improved DFS following αCD40 therapy to correlate with the increased presence of CD44+ CD4+ Th1 cells located specifically within cellular spatial neighborhoods characterized by increased T cell proliferation, antigen-experience, and cytotoxicity in immune aggregates. Overall, our results demonstrate the utility of machine learning in molecular cancer immunology applications, highlight the impact of αCD40 therapy on T cells within the TME, and identify potential candidate biomarkers of DFS for αCD40-treated patients with PDAC.

Multi-Omics Integration for the Design of Novel Therapies and the Identification of Novel Biomarkers

Multi-omics is a cutting-edge approach that combines data from different biomolecular levels, such as DNA, RNA, proteins, metabolites, and epigenetic marks, to obtain a holistic view of how living systems work and interact. Multi-omics has been used for various purposes in biomedical research, such as identifying new diseases, discovering new drugs, personalizing treatments, and optimizing therapies. This review summarizes the latest progress and challenges of multi-omics for designing new treatments for human diseases, focusing on how to integrate and analyze multiple proteome data and examples of how to use multi-proteomics data to identify new drug targets. We also discussed the future directions and opportunities of multi-omics for developing innovative and effective therapies by deciphering proteome complexity.

A simplified frailty index and nomogram to predict the postoperative complications and survival in older patients with upper urinary tract urothelial carcinoma

Purpose

This study was designed to investigate the clinical value of a simplified five-item frailty index (sFI) for predicting short- and long-term outcomes in older patients with upper urinary tract urothelial carcinoma (UTUC) patients after radical nephroureterectomy (RNU).

Method

This retrospective study included 333 patients (aged ≥65 years) with UTUC. Patients were classified into five groups: 0, 1, 2, 3, and 3+, according to sFI score. The variable importance and minimum depth methods were used to screen for significant variables, and univariable and multivariable logistic regression models applied to investigated the relationships between significant variables and postoperative complications. Survival differences between groups were analyzed using Kaplan-Meier plots and log-rank tests. Cox proportional hazards regression was used to evaluate risk factors associated with overall survival (OS) and cancer-specific survival (CSS). Further, we developed a nomogram based on clinicopathological features and the sFI. The area under the curve (AUC), Harrel's concordance index (C-index), calibration curve, and decision curve analysis (DCA) were used to evaluate the nomogram.

Result

Of 333 cases identified, 31.2% experienced a Clavien-Dindo grade of 2 or greater complication. Random forest-logistic regression modeling showed that sFI significantly influenced the incidence of postoperative complications in older patients (AUC= 0.756). Compared with patients with low sFI score, those with high sFI scores had significantly lower OS and CSS (p < 0.001). Across all patients, the random survival forest-Cox regression model revealed that sFI score was an independent prognostic factor for OS and CSS, with AUC values of 0.815 and 0.823 for predicting 3-year OS and CSS, respectively. The nomogram developed was clinically valuable and had good ability to discriminate abilities for high-risk patients. Further, we developed a survival risk classification system that divided all patients into high-, moderate-, and low-risk groups based on total nomogram points for each patient.

Conclusion

A simple five-item frailty index may be considered a prognostic factor for the prognosis and postoperative complications of UTUC following RNU. By using this predictive model, clinicians may increase their accuracy in predicting complications and prognosis and improve preoperative decision-making.

B-cells and regulatory T-cells in the microenvironment of HER2+ breast cancer are associated with decreased survival: a real-world analysis of women with HER2+ metastatic breast cancer

BACKGROUND

Despite major improvements in treatment of HER2-positive metastatic breast cancer (MBC), only few patients achieve complete remission and remain progression free for a prolonged time. The tumor immune microenvironment plays an important role in the response to treatment in HER2-positive breast cancer and could contain valuable prognostic information. Detailed information on the cancer-immune cell interactions in HER2-positive MBC is however still lacking. By characterizing the tumor immune microenvironment in patients with HER2-positive MBC, we aimed to get a better understanding why overall survival (OS) differs so widely and which alternative treatment approaches may improve outcome.

METHODS

We included all patients with HER2-positive MBC who were treated with trastuzumab-based palliative therapy in the Netherlands Cancer Institute between 2000 and 2014 and for whom pre-treatment tissue from the primary tumor or from metastases was available. Infiltrating immune cells and their spatial relationships to one another and to tumor cells were characterized by immunohistochemistry and multiplex immunofluorescence. We also evaluated immune signatures and other key pathways using next-generation RNA-sequencing data. With nine years median follow-up from initial diagnosis of MBC, we investigated the association between tumor and immune characteristics and outcome.

RESULTS

A total of 124 patients with 147 samples were included and evaluated. The different technologies showed high correlations between each other. T-cells were less prevalent in metastases compared to primary tumors, whereas B-cells and regulatory T-cells (Tregs) were comparable between primary tumors and metastases. Stromal tumor-infiltrating lymphocytes in general were not associated with OS. The infiltration of B-cells and Tregs in the primary tumor was associated with unfavorable OS. Four signatures classifying the extracellular matrix of primary tumors showed differential survival in the population as a whole.

CONCLUSIONS

In a real-world cohort of 124 patients with HER2-positive MBC, B-cells, and Tregs in primary tumors are associated with unfavorable survival. With this paper, we provide a comprehensive insight in the tumor immune microenvironment that could guide further research into development of novel immunomodulatory strategies.

Artificial Intelligence in Breast Cancer Diagnosis and Personalized Medicine

Breast cancer is a significant cause of cancer-related mortality in women worldwide. Early and precise diagnosis is crucial, and clinical outcomes can be markedly enhanced. The rise of artificial intelligence (AI) has ushered in a new era, notably in image analysis, paving the way for major advancements in breast cancer diagnosis and individualized treatment regimens. In the diagnostic workflow for patients with breast cancer, the role of AI encompasses screening, diagnosis, staging, biomarker evaluation, prognostication, and therapeutic response prediction. Although its potential is immense, its complete integration into clinical practice is challenging. Particularly, these challenges include the imperatives for extensive clinical validation, model generalizability, navigating the "black-box" conundrum, and pragmatic considerations of embedding AI into everyday clinical environments. In this review, we comprehensively explored the diverse applications of AI in breast cancer care, underlining its transformative promise and existing impediments. In radiology, we specifically address AI in mammography, tomosynthesis, risk prediction models, and supplementary imaging methods, including magnetic resonance imaging and ultrasound. In pathology, our focus is on AI applications for pathologic diagnosis, evaluation of biomarkers, and predictions related to genetic alterations, treatment response, and prognosis in the context of breast cancer diagnosis and treatment. Our discussion underscores the transformative potential of AI in breast cancer management and emphasizes the importance of focused research to realize the full spectrum of benefits of AI in patient care.

Artificial intelligence (AI) and machine learning (ML) in precision oncology: a review on enhancing discoverability through multiomics integration

Multiomics data including imaging radiomics and various types of molecular biomarkers have been increasingly investigated for better diagnosis and therapy in the era of precision oncology. Artificial intelligence (AI) including machine learning (ML) and deep learning (DL) techniques combined with the exponential growth of multiomics data may have great potential to revolutionize cancer subtyping, risk stratification, prognostication, prediction and clinical decision-making. In this article, we first present different categories of multiomics data and their roles in diagnosis and therapy. Second, AI-based data fusion methods and modeling methods as well as different validation schemes are illustrated. Third, the applications and examples of multiomics research in oncology are demonstrated. Finally, the challenges regarding the heterogeneity data set, availability of omics data, and validation of the research are discussed. The transition of multiomics research to real clinics still requires consistent efforts in standardizing omics data collection and analysis, building computational infrastructure for data sharing and storing, developing advanced methods to improve data fusion and interpretability, and ultimately, conducting large-scale prospective clinical trials to fill the gap between study findings and clinical benefits.