CUP-AI-Dx: A tool for inferring cancer tissue of origin and molecular subtype using RNA gene-expression data and artificial intelligence

Image-based deep learning model using DNA methylation data predicts the origin of cancer of unknown primary

Cancer of unknown primary (CUP) is a rare type of metastatic cancer in which the origin of the tumor is unknown. Since the treatment strategy for patients with metastatic tumors depends on knowing the primary site, accurate identification of the origin site is important. Here, we developed an image-based deep-learning model that utilizes a vision transformer algorithm for predicting the origin of CUP. Using DNA methylation dataset of 8,233 primary tumors from The Cancer Genome Atlas (TCGA), we categorized 29 cancer types into 18 organ classes and extracted 2,312 differentially methylated CpG sites (DMCs) from non-squamous cancer group and 420 DMCs from squamous cell cancer group. Using these DMCs, we created organ-specific DNA methylation images and used them for model training and testing. Model performance was evaluated using 394 metastatic cancer samples from TCGA (TCGA-meta) and 995 samples (693 primary and 302 metastatic cancers) obtained from 20 independent external studies. We identified that the DNA methylation image reveals a distinct pattern based on the origin of cancer. Our model achieved an overall accuracy of 96.95 % in the TCGA-meta dataset. In the external validation datasets, our classifier achieved overall accuracies of 96.39 % and 94.37 % in primary and metastatic tumors, respectively. Especially, the overall accuracies for both primary and metastatic samples of non-squamous cell cancer were exceptionally high, with 96.79 % and 96.85 %, respectively.

The evolution of molecular management of carcinoma of unknown primary

PURPOSE OF REVIEW

There is significant need to improve diagnostic and therapeutic options for patients with cancer of unknown primary (CUP). In this review, we discuss the evolving landscape of molecular profiling in CUP.

RECENT FINDINGS

Molecular profiling is becoming accepted into the diagnostic work-up of CUP patients with tumour mutation profiling now described in international CUP guidelines. Although tissue-of-origin (ToO) molecular tests utilising gene-expression and DNA methylation have existed some time, their clinical benefit remains unclear. Novel technologies utilising whole genome sequencing and machine learning algorithms are showing promise in determining ToO, however further research is required prior to clinical application. A recent international clinical trial found patients treated with molecularly-guided therapy based on comprehensive-panel DNA sequencing had improved progression-free survival compared to chemotherapy alone, confirming utility of performing genomic profiling early in the patient journey. Small phase 2 trials have demonstrated that some CUP patients are responsive to immunotherapy, but the best way to select patients for treatment is not clear.

SUMMARY

Management of CUP requires a multifaceted approach incorporating clinical, histopathological, radiological and molecular sequencing results to assist with identifying the likely ToO and clinically actionable genomic alternations. Rapidly identifying a subset of CUP patients who are likely to benefit from site specific therapy, targeted therapy and/or immunotherapy will improve patient outcomes.

XENTURION is a population-level multidimensional resource of xenografts and tumoroids from metastatic colorectal cancer patients

The breadth and depth at which cancer models are interrogated contribute to the successful clinical translation of drug discovery efforts. In colorectal cancer (CRC), model availability is limited by a dearth of large-scale collections of patient-derived xenografts (PDXs) and paired tumoroids from metastatic disease, where experimental therapies are typically tested. Here we introduce XENTURION, an open-science resource offering a platform of 128 PDX models from patients with metastatic CRC, along with matched PDX-derived tumoroids. Multidimensional omics analyses indicate that tumoroids retain extensive molecular fidelity with parental PDXs. A tumoroid-based trial with the anti-EGFR antibody cetuximab reveals variable sensitivities that are consistent with clinical response biomarkers, mirror tumor growth changes in matched PDXs, and recapitulate EGFR genetic deletion outcomes. Inhibition of adaptive signals upregulated by EGFR blockade increases the magnitude of cetuximab response. These findings illustrate the potential of large living biobanks, providing avenues for molecularly informed preclinical research in oncology.

Seeing the primary tumor because of all the trees: Cancer type prediction on low-dimensional data

The Cancer of Unknown Primary (CUP) syndrome is characterized by identifiable metastases while the primary tumor remains hidden. In recent years, various data-driven approaches have been suggested to predict the location of the primary tumor (LOP) in CUP patients promising improved diagnosis and outcome. These LOP prediction approaches use high-dimensional input data like images or genetic data. However, leveraging such data is challenging, resource-intensive and therefore a potential translational barrier. Instead of using high-dimensional data, we analyzed the LOP prediction performance of low-dimensional data from routine medical care. With our findings, we show that such low-dimensional routine clinical information suffices as input data for tree-based LOP prediction models. The best model reached a mean Accuracy of 94% and a mean Matthews correlation coefficient (MCC) score of 0.92 in 10-fold nested cross-validation (NCV) when distinguishing four types of cancer. When considering eight types of cancer, this model achieved a mean Accuracy of 85% and a mean MCC score of 0.81. This is comparable to the performance achieved by approaches using high-dimensional input data. Additionally, the distribution pattern of metastases appears to be important information in predicting the LOP.

Occlusion enhanced pan-cancer classification via deep learning

Quantitative measurement of RNA expression levels through RNA-Seq is an ideal replacement for conventional cancer diagnosis via microscope examination. Currently, cancer-related RNA-Seq studies focus on two aspects: classifying the status and tissue of origin of a sample and discovering marker genes. Existing studies typically identify marker genes by statistically comparing healthy and cancer samples. However, this approach overlooks marker genes with low expression level differences and may be influenced by experimental results. This paper introduces "GENESO," a novel framework for pan-cancer classification and marker gene discovery using the occlusion method in conjunction with deep learning. we first trained a baseline deep LSTM neural network capable of distinguishing the origins and statuses of samples utilizing RNA-Seq data. Then, we propose a novel marker gene discovery method called "Symmetrical Occlusion (SO)". It collaborates with the baseline LSTM network, mimicking the "gain of function" and "loss of function" of genes to evaluate their importance in pan-cancer classification quantitatively. By identifying the genes of utmost importance, we then isolate them to train new neural networks, resulting in higher-performance LSTM models that utilize only a reduced set of highly relevant genes. The baseline neural network achieves an impressive validation accuracy of 96.59% in pan-cancer classification. With the help of SO, the accuracy of the second network reaches 98.30%, while using 67% fewer genes. Notably, our method excels in identifying marker genes that are not differentially expressed. Moreover, we assessed the feasibility of our method using single-cell RNA-Seq data, employing known marker genes as a validation test.

Deep Learning-Based Identification of Tissue of Origin for Carcinomas of Unknown Primary Using MicroRNA Expression: Algorithm Development and Validation

BACKGROUND

Carcinoma of unknown primary (CUP) is a subset of metastatic cancers in which the primary tissue source of the cancer cells remains unidentified. CUP is the eighth most common malignancy worldwide, accounting for up to 5% of all malignancies. Representing an exceptionally aggressive metastatic cancer, the median survival is approximately 3 to 6 months. The tissue in which cancer arises plays a key role in our understanding of sensitivities to various forms of cell death. Thus, the lack of knowledge on the tissue of origin (TOO) makes it difficult to devise tailored and effective treatments for patients with CUP. Developing quick and clinically implementable methods to identify the TOO of the primary site is crucial in treating patients with CUP. Noncoding RNAs may hold potential for origin identification and provide a robust route to clinical implementation due to their resistance against chemical degradation.

OBJECTIVE

This study aims to investigate the potential of microRNAs, a subset of noncoding RNAs, as highly accurate biomarkers for detecting the TOO through data-driven, machine learning approaches for metastatic cancers.

METHODS

We used microRNA expression data from The Cancer Genome Atlas data set and assessed various machine learning approaches, from simple classifiers to deep learning approaches. As a test of our classifiers, we evaluated the accuracy on a separate set of 194 primary tumor samples from the Sequence Read Archive. We used permutation feature importance to determine the potential microRNA biomarkers and assessed them with principal component analysis and t-distributed stochastic neighbor embedding visualizations.

RESULTS

Our results show that it is possible to design robust classifiers to detect the TOO for metastatic samples on The Cancer Genome Atlas data set, with an accuracy of up to 97% (351/362), which may be used in situations of CUP. Our findings show that deep learning techniques enhance prediction accuracy. We progressed from an initial accuracy prediction of 62.5% (226/362) with decision trees to 93.2% (337/362) with logistic regression, finally achieving 97% (351/362) accuracy using deep learning on metastatic samples. On the Sequence Read Archive validation set, a lower accuracy of 41.2% (77/188) was achieved by the decision tree, while deep learning achieved a higher accuracy of 80.4% (151/188). Notably, our feature importance analysis showed the top 3 most important features for predicting TOO to be microRNA-10b, microRNA-205, and microRNA-196b, which aligns with previous work.

CONCLUSIONS

Our findings highlight the potential of using machine learning techniques to devise accurate tests for detecting TOO for CUP. Since microRNAs are carried throughout the body via extracellular vesicles secreted from cells, they may serve as key biomarkers for liquid biopsy due to their presence in blood plasma. Our work serves as a foundation toward developing blood-based cancer detection tests based on the presence of microRNA.

Application of Transcriptome-Based Gene Set Featurization for Machine Learning Model to Predict the Origin of Metastatic Cancer

Identifying the primary site of origin of metastatic cancer is vital for guiding treatment decisions, especially for patients with cancer of unknown primary (CUP). Despite advanced diagnostic techniques, CUP remains difficult to pinpoint and is responsible for a considerable number of cancer-related fatalities. Understanding its origin is crucial for effective management and potentially improving patient outcomes. This study introduces a machine learning framework, ONCOfind-AI, that leverages transcriptome-based gene set features to enhance the accuracy of predicting the origin of metastatic cancers. We demonstrate its potential to facilitate the integration of RNA sequencing and microarray data by using gene set scores for characterization of transcriptome profiles generated from different platforms. Integrating data from different platforms resulted in improved accuracy of machine learning models for predicting cancer origins. We validated our method using external data from clinical samples collected through the Kangbuk Samsung Medical Center and Gene Expression Omnibus. The external validation results demonstrate a top-1 accuracy ranging from 0.80 to 0.86, with a top-2 accuracy of 0.90. This study highlights that incorporating biological knowledge through curated gene sets can help to merge gene expression data from different platforms, thereby enhancing the compatibility needed to develop more effective machine learning prediction models.

Tracing unknown tumor origins with a biological-pathway-based transformer model

Cancer of unknown primary (CUP) represents metastatic cancer where the primary site remains unidentified despite standard diagnostic procedures. To determine the tumor origin in such cases, we developed BPformer, a deep learning method integrating the transformer model with prior knowledge of biological pathways. Trained on transcriptomes from 10,410 primary tumors across 32 cancer types, BPformer achieved remarkable accuracy rates of 94%, 92%, and 89% in primary tumors and primary and metastatic sites of metastatic tumors, respectively, surpassing existing methods. Additionally, BPformer was validated in a retrospective study, demonstrating consistency with tumor sites diagnosed through immunohistochemistry and histopathology. Furthermore, BPformer was able to rank pathways based on their contribution to tumor origin identification, which helped to classify oncogenic signaling pathways into those that are highly conservative among different cancers versus those that are highly variable depending on their origins.

Deep-Learning Model for Tumor-Type Prediction Using Targeted Clinical Genomic Sequencing Data

Tumor type guides clinical treatment decisions in cancer, but histology-based diagnosis remains challenging. Genomic alterations are highly diagnostic of tumor type, and tumor-type classifiers trained on genomic features have been explored, but the most accurate methods are not clinically feasible, relying on features derived from whole-genome sequencing (WGS), or predicting across limited cancer types. We use genomic features from a data set of 39,787 solid tumors sequenced using a clinically targeted cancer gene panel to develop Genome-Derived-Diagnosis Ensemble (GDD-ENS): a hyperparameter ensemble for classifying tumor type using deep neural networks. GDD-ENS achieves 93% accuracy for high-confidence predictions across 38 cancer types, rivaling the performance of WGS-based methods. GDD-ENS can also guide diagnoses of rare type and cancers of unknown primary and incorporate patient-specific clinical information for improved predictions. Overall, integrating GDD-ENS into prospective clinical sequencing workflows could provide clinically relevant tumor-type predictions to guide treatment decisions in real time.

SIGNIFICANCE

We describe a highly accurate tumor-type prediction model, designed specifically for clinical implementation. Our model relies only on widely used cancer gene panel sequencing data, predicts across 38 distinct cancer types, and supports integration of patient-specific nongenomic information for enhanced decision support in challenging diagnostic situations. See related commentary by Garg, p. 906. This article is featured in Selected Articles from This Issue, p. 897.

Big data and deep learning for RNA biology

The exponential growth of big data in RNA biology (RB) has led to the development of deep learning (DL) models that have driven crucial discoveries. As constantly evidenced by DL studies in other fields, the successful implementation of DL in RB depends heavily on the effective utilization of large-scale datasets from public databases. In achieving this goal, data encoding methods, learning algorithms, and techniques that align well with biological domain knowledge have played pivotal roles. In this review, we provide guiding principles for applying these DL concepts to various problems in RB by demonstrating successful examples and associated methodologies. We also discuss the remaining challenges in developing DL models for RB and suggest strategies to overcome these challenges. Overall, this review aims to illuminate the compelling potential of DL for RB and ways to apply this powerful technology to investigate the intriguing biology of RNA more effectively.

Cancer of unknown primary and the «seed and soil» hypothesis

The worldwide incidence rate of cancer of unknown primary (CUP) reaches 5% (Kang et al, 2021; Lee, Sanoff, 2020; Yang et al, 2022). CUP has an alarmingly high mortality rate, with 84% of patients succumbing within the first year following diagnosis (Registration and Service, 2018). Under normal circumstances, tumor cell metastasis follows the «seed and soil» hypothesis, displaying a tissue-specific pattern of cancer cell homing behavior based on the microenvironment composition of secondary organs. In this study, we questioned whether seed and soil concept applies to CUP, and whether the pattern of tumor and metastasis manifestations for cancer of known primary (CKP) can be used to inform diagnostic strategies for CUP. We compared data from metastatic and primary CUP foci to the metastasis patterns observed in CKP. Furthermore, we evaluated several techniques for identifying the tissue-of-origin (TOO) in CUP profiling, including DNA, RNA, and epigenetic TOO techniques.

Deep learning in cancer genomics and histopathology

Histopathology and genomic profiling are cornerstones of precision oncology and are routinely obtained for patients with cancer. Traditionally, histopathology slides are manually reviewed by highly trained pathologists. Genomic data, on the other hand, is evaluated by engineered computational pipelines. In both applications, the advent of modern artificial intelligence methods, specifically machine learning (ML) and deep learning (DL), have opened up a fundamentally new way of extracting actionable insights from raw data, which could augment and potentially replace some aspects of traditional evaluation workflows. In this review, we summarize current and emerging applications of DL in histopathology and genomics, including basic diagnostic as well as advanced prognostic tasks. Based on a growing body of evidence, we suggest that DL could be the groundwork for a new kind of workflow in oncology and cancer research. However, we also point out that DL models can have biases and other flaws that users in healthcare and research need to know about, and we propose ways to address them.

A platform-independent AI tumor lineage and site (ATLAS) classifier

Histopathologic diagnosis and classification of cancer plays a critical role in guiding treatment. Advances in next-generation sequencing have ushered in new complementary molecular frameworks. However, existing approaches do not independently assess both site-of-origin (e.g. prostate) and lineage (e.g. adenocarcinoma) and have minimal validation in metastatic disease, where classification is more difficult. Utilizing gradient-boosted machine learning, we developed ATLAS, a pair of separate AI Tumor Lineage and Site-of-origin models from RNA expression data on 8249 tumor samples. We assessed performance independently in 10,376 total tumor samples, including 1490 metastatic samples, achieving an accuracy of 91.4% for cancer site-of-origin and 97.1% for cancer lineage. High confidence predictions (encompassing the majority of cases) were accurate 98-99% of the time in both localized and remarkably even in metastatic samples. We also identified emergent properties of our lineage scores for tumor types on which the model was never trained (zero-shot learning). Adenocarcinoma/sarcoma lineage scores differentiated epithelioid from biphasic/sarcomatoid mesothelioma. Also, predicted lineage de-differentiation identified neuroendocrine/small cell tumors and was associated with poor outcomes across tumor types. Our platform-independent single-sample approach can be easily translated to existing RNA-seq platforms. ATLAS can complement and guide traditional histopathologic assessment in challenging situations and tumors of unknown primary.

Automatic origin prediction of liver metastases via hierarchical artificial-intelligence system trained on multiphasic CT data: a retrospective, multicentre study

Background

Currently, the diagnostic testing for the primary origin of liver metastases (LMs) can be laborious, complicating clinical decision-making. Directly classifying the primary origin of LMs at computed tomography (CT) images has proven to be challenging, despite its potential to streamline the entire diagnostic workflow.

Methods

We developed ALMSS, an artificial intelligence (AI)-based LMs screening system, to provide automated liver contrast-enhanced CT analysis for distinguishing LMs from hepatocellular carcinoma (HCC) and intrahepatic cholangiocarcinoma (ICC), as well as subtyping primary origin of LMs as six organ systems. We processed a CECT dataset between January 1, 2013 and June 30, 2022 (n = 3105: 840 HCC, 354 ICC, and 1911 LMs) for training and internally testing ALMSS, and two additional cohorts (n = 622) for external validation of its diagnostic performance. The performance of radiologists with and without the assistance of ALMSS in diagnosing and subtyping LMs was assessed.

Findings

ALMSS achieved average area under the curve (AUC) of 0.917 (95% confidence interval [CI]: 0.899-0.931) and 0.923 (95% [CI]: 0.905-0.937) for differentiating LMs, HCC and ICC on both the internal testing set and external testing set, outperformed that of two radiologists. Moreover, ALMSS yielded average AUC of 0.815 (95% [CI]: 0.794-0.836) and 0.818 (95% [CI]: 0.790-0.842) for predicting six primary origins on both two testing sets. Interestingly, ALMSS assigned origin diagnoses for LMs with pathological phenotypes beyond the training categories with average AUC of 0.761 (95% [CI]: 0.657-0.842), which verify the model's diagnostic expandability.

Interpretation

Our study established an AI-based diagnostic system that effectively identifies and characterizes LMs directly from multiphasic CT images.

Funding

National Natural Science Foundation of China, Guangdong Provincial Key Laboratory of Medical Image Processing.

The practical utility of AI-assisted molecular profiling in the diagnosis and management of cancer of unknown primary: an updated review

Cancer of unknown primary (CUP) presents a complex diagnostic challenge, characterized by metastatic tumors of unknown tissue origin and a dismal prognosis. This review delves into the emerging significance of artificial intelligence (AI) and machine learning (ML) in transforming the landscape of CUP diagnosis, classification, and treatment. ML approaches, trained on extensive molecular profiling data, have shown promise in accurately predicting tissue of origin. Genomic profiling, encompassing driver mutations and copy number variations, plays a pivotal role in CUP diagnosis by providing insights into tumor type-specific oncogenic alterations. Mutational signatures (MS), reflecting somatic mutation patterns, offer further insights into CUP diagnosis. Known MS with established etiology, such as ultraviolet (UV) light-induced DNA damage and tobacco exposure, have been identified in cases of dedifferentiated/transdifferentiated melanoma and carcinoma. Deep learning models that integrate gene expression data and DNA methylation patterns offer insights into tissue lineage and tumor classification. In digital pathology, machine learning algorithms analyze whole-slide images to aid in CUP classification. Finally, precision oncology, guided by molecular profiling, offers targeted therapies independent of primary tissue identification. Clinical trials assigning CUP patients to molecularly guided therapies, including targetable alterations and tumor mutation burden as an immunotherapy biomarker, have resulted in improved overall survival in a subset of patients. In conclusion, AI- and ML-driven approaches are revolutionizing CUP management by enhancing diagnostic accuracy. Precision oncology utilizing enhanced molecular profiling facilitates the identification of targeted therapies that transcend the need to identify the tissue of origin, ultimately improving patient outcomes.

New techniques to identify the tissue of origin for cancer of unknown primary in the era of precision medicine: progress and challenges

Despite a standardized diagnostic examination, cancer of unknown primary (CUP) is a rare metastatic malignancy with an unidentified tissue of origin (TOO). Patients diagnosed with CUP are typically treated with empiric chemotherapy, although their prognosis is worse than those with metastatic cancer of a known origin. TOO identification of CUP has been employed in precision medicine, and subsequent site-specific therapy is clinically helpful. For example, molecular profiling, including genomic profiling, gene expression profiling, epigenetics and proteins, has facilitated TOO identification. Moreover, machine learning has improved identification accuracy, and non-invasive methods, such as liquid biopsy and image omics, are gaining momentum. However, the heterogeneity in prediction accuracy, sample requirements and technical fundamentals among the various techniques is noteworthy. Accordingly, we systematically reviewed the development and limitations of novel TOO identification methods, compared their pros and cons and assessed their potential clinical usefulness. Our study may help patients shift from empirical to customized care and improve their prognoses.

Identifying primary tumor site of origin for liver metastases via a combination of handcrafted and deep learning features

Liver is one of the most common sites for metastases, which can occur on account of primary tumors from multiple sites of origin. Identifying the primary site of origin (PSO) of a metastasis can help in guiding therapeutic options for liver metastases. In this pilot study, we hypothesized that computer extracted handcrafted (HC) histomorphometric features can be utilized to identify the PSO of liver metastases. Cellular features, including tumor nuclei morphological and graph features as well as cytoplasm texture features, were extracted by computer algorithms from 175 slides (114 patients). The study comprised three experiments: (1) comparing and (2) fusing a machine learning (ML) model trained with HC pathomic features and deep learning (DL)-based classifiers to predict site of origin; (3) identifying the section of the primary tumor from which metastases were derived. For experiment 1, we divided the cohort into training sets composed of primary and matched liver metastases [60 patients, 121 whole slide images (WSIs)], and a hold-out validation set (54 patients, 54 WSIs) composed solely of liver metastases of known site of origin. Using the extracted HC features of the training set, a combination of supervised machine classifiers and unsupervised clustering was applied to identify the PSO. A random forest classifier achieved areas under the curve (AUCs) of 0.83, 0.64, 0.82, and 0.64 in classifying the metastatic tumor from colon, esophagus, breast, and pancreas on the validation set. The top features related to nuclear and peri-nuclear shape and textural attributes. We also trained a DL network to serve as a direct comparison to our method. The DL model achieved AUCs for colon: 0.94, esophagus: 0.66, breast: 0.79, and pancreas: 0.67 in identifying PSO. A decision fusion-based strategy was deployed to fuse the trained ML and DL classifiers and achieved slightly better results than ML or DL classifier alone (colon: 0.93, esophagus: 0.68, breast: 0.81, and pancreas: 0.69). For the third experiment, WSI-level attention maps were also generated using a trained DL network to generate a composite feature similarity heat map between paired primaries and their associated metastases. Our experiments revealed that epithelium-rich and moderately differentiated tumor regions of primary tumors were quantitatively similar to paired metastatic tumors. Our findings suggest that a combination of HC and DL features could potentially help identify the PSO for liver metastases while at the same time also potentially identify the spatial sites of origin for the metastases within primary tumors.

A Rare Presentation of Aggressive Renal Cell Carcinoma and the Utility of Early Molecular Testing in Rapidly Progressing Malignancies: A Case Report

In rapidly progressing cancers, appropriate selection of first-line therapy is essential in prolonging survival. Alongside immunohistochemistry (IHC), comprehensive genomics, including whole exome and transcriptome sequencing (WES/WTS), can improve diagnostic accuracy and guide therapeutic management. Here, we report a young patient with rapidly progressing malignancy and unexpected post-mortem results, a scenario that may have been altered by early, comprehensive genomic sequencing. A 43-year-old man with no relevant medical history presented to the emergency department with progressive cough and dyspnea despite treatment for pneumonia. Radiology revealed enlarged subcarinal, hilar, retroperitoneal, and mesenteric lymph nodes, suspicious for metastasis, and a right kidney mass. Pathologic analysis of a retroperitoneal lymph node was felt to be most consistent with metastatic epithelioid angiomyolipoma (mEAML). Three weeks later, he was urgently treated with an mTOR inhibitor for presumed mEAML due to rapid clinical decline, and a subsequent 4R lymph node biopsy was performed to confirm the diagnosis and identify genomic targets via IHC and WES/WTS. Unfortunately, he developed hypoxic respiratory failure, and only posthumously did WES/WTS reveal pathogenic variants in BAP1 and VHL, consistent with clear cell renal cell carcinoma (ccRCC). With an earlier ccRCC diagnosis, he would have received combination immunotherapy/tyrosine kinase inhibition, which has significantly greater activity than mTOR inhibition in ccRCC. He could have received systemic treatment earlier, with optimal therapy, while potentially carrying lower tumor burden and greater clinical stability. In cases of rapidly progressing malignancies with complex histopathological presentations, early comprehensive molecular-based testing can aid in diagnosis and critical therapeutic decision-making.

Machine learning for pan-cancer classification based on RNA sequencing data

Despite recent improvements in cancer diagnostics, 2%-5% of all malignancies are still cancers of unknown primary (CUP), for which the tissue-of-origin (TOO) cannot be determined at the time of presentation. Since the primary site of cancer leads to the choice of optimal treatment, CUP patients pose a significant clinical challenge with limited treatment options. Data produced by large-scale cancer genomics initiatives, which aim to determine the genomic, epigenomic, and transcriptomic characteristics of a large number of individual patients of multiple cancer types, have led to the introduction of various methods that use machine learning to predict the TOO of cancer patients. In this review, we assess the reproducibility, interpretability, and robustness of results obtained by 20 recent studies that utilize different machine learning methods for TOO prediction based on RNA sequencing data, including their reported performance on independent data sets and identification of important features. Our review investigates the strengths and weaknesses of different methods, checks the correspondence of their results, and identifies potential issues with datasets used for model training and testing, assessing their potential usefulness in a clinical setting and suggesting future improvements.

Artificial intelligence-based risk stratification, accurate diagnosis and treatment prediction in gynecologic oncology

As data-driven science, artificial intelligence (AI) has paved a promising path toward an evolving health system teeming with thrilling opportunities for precision oncology. Notwithstanding the tremendous success of oncological AI in such fields as lung carcinoma, breast tumor and brain malignancy, less attention has been devoted to investigating the influence of AI on gynecologic oncology. Hereby, this review sheds light on the ever-increasing contribution of state-of-the-art AI techniques to the refined risk stratification and whole-course management of patients with gynecologic tumors, in particular, cervical, ovarian and endometrial cancer, centering on information and features extracted from clinical data (electronic health records), cancer imaging including radiological imaging, colposcopic images, cytological and histopathological digital images, and molecular profiling (genomics, transcriptomics, metabolomics and so forth). However, there are still noteworthy challenges beyond performance validation. Thus, this work further describes the limitations and challenges faced in the real-word implementation of AI models, as well as potential solutions to address these issues.

Precision cancer medicine: Concepts, current practice, and future developments

Precision cancer medicine is a multidisciplinary team effort that requires involvement and commitment of many stakeholders including the society at large. Building on the success of significant advances in precision therapy for oncological patients over the last two decades, future developments will be significantly shaped by improvements in scalable molecular diagnostics in which increasingly complex multilayered datasets require transformation into clinically useful information guiding patient management at fast turnaround times. Adaptive profiling strategies involving tissue- and liquid-based testing that account for the immense plasticity of cancer during the patient's journey and also include early detection approaches are already finding their way into clinical routine and will become paramount. A second major driver is the development of smart clinical trials and trial concepts which, complemented by real-world evidence, rapidly broaden the spectrum of therapeutic options. Tight coordination with regulatory agencies and health technology assessment bodies is crucial in this context. Multicentric networks operating nationally and internationally are key in implementing precision oncology in clinical practice and support developing and improving the ecosystem and framework needed to turn invocation into benefits for patients. The review provides an overview of the diagnostic tools, innovative clinical studies, and collaborative efforts needed to realize precision cancer medicine.

A cross-cohort computational framework to trace tumor tissue-of-origin based on RNA sequencing

Carcinoma of unknown primary (CUP) is a type of metastatic cancer with tissue-of-origin (TOO) unidentifiable by traditional methods. CUP patients typically have poor prognosis but therapy targeting the original cancer tissue can significantly improve patients' prognosis. Thus, it's critical to develop accurate computational methods to infer cancer TOO. While qPCR or microarray-based methods are effective in inferring TOO for most cancer types, the overall prediction accuracy is yet to be improved. In this study, we propose a cross-cohort computational framework to trace TOO of 32 cancer types based on RNA sequencing (RNA-seq). Specifically, we employed logistic regression models to select 80 genes for each cancer type to create a combined 1356-gene set, based on transcriptomic data from 9911 tissue samples covering the 32 cancer types with known TOO from the Cancer Genome Atlas (TCGA). The selected genes are enriched in both tissue-specific and tissue-general functions. The cross-validation accuracy of our framework reaches 97.50% across all cancer types. Furthermore, we tested the performance of our model on the TCGA metastatic dataset and International Cancer Genome Consortium (ICGC) dataset, achieving an accuracy of 91.09% and 82.67%, respectively, despite the differences in experiment procedures and pipelines. In conclusion, we developed an accurate yet robust computational framework for identifying TOO, which holds promise for clinical applications. Our code is available at http://github.com/wangbo00129/classifybysklearn .

DNA methylation profiling to determine the primary sites of metastatic cancers using formalin-fixed paraffin-embedded tissues

Identifying the primary site of metastatic cancer is critical to guiding the subsequent treatment. Approximately 3-9% of metastatic patients are diagnosed with cancer of unknown primary sites (CUP) even after a comprehensive diagnostic workup. However, a widely accepted molecular test is still not available. Here, we report a method that applies formalin-fixed, paraffin-embedded tissues to construct reduced representation bisulfite sequencing libraries (FFPE-RRBS). We then generate and systematically evaluate 28 molecular classifiers, built on four DNA methylation scoring methods and seven machine learning approaches, using the RRBS library dataset of 498 fresh-frozen tumor tissues from primary cancer patients. Among these classifiers, the beta value-based linear support vector (BELIVE) performs the best, achieving overall accuracies of 81-93% for identifying the primary sites in 215 metastatic patients using top-k predictions (k = 1, 2, 3). Coincidentally, BELIVE also successfully predicts the tissue of origin in 81-93% of CUP patients (n = 68).

Deep Learning Model for Tumor Type Prediction using Targeted Clinical Genomic Sequencing Data

Tumor type guides clinical treatment decisions in cancer, but histology-based diagnosis remains challenging. Genomic alterations are highly diagnostic of tumor type, and tumor type classifiers trained on genomic features have been explored, but the most accurate methods are not clinically feasible, relying on features derived from whole genome sequencing (WGS), or predicting across limited cancer types. We use genomic features from a dataset of 39,787 solid tumors sequenced using a clinical targeted cancer gene panel to develop Genome-Derived-Diagnosis Ensemble (GDD-ENS): a hyperparameter ensemble for classifying tumor type using deep neural networks. GDD-ENS achieves 93% accuracy for high-confidence predictions across 38 cancer types, rivalling performance of WGS-based methods. GDD-ENS can also guide diagnoses on rare type and cancers of unknown primary, and incorporate patient-specific clinical information for improved predictions. Overall, integrating GDD-ENS into prospective clinical sequencing workflows has enabled clinically-relevant tumor type predictions to guide treatment decisions in real time.

[Molecular tumor diagnostics as the driving force behind precision oncology]

Molecular pathological diagnostics plays a central role in personalized oncology and requires multidisciplinary teamwork. It is just as relevant for the individual patient who is being treated with an approved therapy method or an individual treatment attempt as it is for prospective clinical studies that require the identification of specific therapeutic target structures or complex biomarkers for study inclusion. It is also of crucial importance for the generation of real-world data, which is becoming increasingly important for drug development. Future developments will be significantly shaped by improvements in scalable molecular diagnostics, in which increasingly complex and multi-layered data sets must be quickly converted into clinically useful information. One focus will be on the development of adaptive diagnostic strategies in order to be able to depict the enormous plasticity of a cancer disease over time.

Machine learning for genetics-based classification and treatment response prediction in cancer of unknown primary

Cancer of unknown primary (CUP) is a type of cancer that cannot be traced back to its primary site and accounts for 3-5% of all cancers. Established targeted therapies are lacking for CUP, leading to generally poor outcomes. We developed OncoNPC, a machine-learning classifier trained on targeted next-generation sequencing (NGS) data from 36,445 tumors across 22 cancer types from three institutions. Oncology NGS-based primary cancer-type classifier (OncoNPC) achieved a weighted F1 score of 0.942 for high confidence predictions ([Formula: see text]) on held-out tumor samples, which made up 65.2% of all the held-out samples. When applied to 971 CUP tumors collected at the Dana-Farber Cancer Institute, OncoNPC predicted primary cancer types with high confidence in 41.2% of the tumors. OncoNPC also identified CUP subgroups with significantly higher polygenic germline risk for the predicted cancer types and with significantly different survival outcomes. Notably, patients with CUP who received first palliative intent treatments concordant with their OncoNPC-predicted cancers had significantly better outcomes (hazard ratio (HR) = 0.348; 95% confidence interval (CI) = 0.210-0.570; P = [Formula: see text]). Furthermore, OncoNPC enabled a 2.2-fold increase in patients with CUP who could have received genomically guided therapies. OncoNPC thus provides evidence of distinct CUP subgroups and offers the potential for clinical decision support for managing patients with CUP.

Validation of a Transcriptome-Based Assay for Classifying Cancers of Unknown Primary Origin

INTRODUCTION

Cancers assume a variety of distinct histologies, and may originate from a myriad of sites including solid organs, hematopoietic cells, and connective tissue. Clinical decision-making based on consensus guidelines such as the National Comprehensive Cancer Network (NCCN) is often predicated on a specific histologic and anatomic diagnosis, supported by clinical features and pathologist interpretation of morphology and immunohistochemical (IHC) staining patterns. However, in patients with nonspecific morphologic and IHC findings-in addition to ambiguous clinical presentations such as recurrence versus new primary-a definitive diagnosis may not be possible, resulting in the patient being categorized as having a cancer of unknown primary (CUP). Therapeutic options and clinical outcomes are poor for patients with CUP, with a median survival of 8-11 months.

METHODS

Here, we describe and validate the Tempus Tumor Origin (Tempus TO) assay, an RNA-sequencing-based machine learning classifier capable of discriminating between 68 clinically relevant cancer subtypes. Model accuracy was assessed using primary and/or metastatic samples with known subtype.

RESULTS

We show that the Tempus TO model is 91% accurate when assessed on both a retrospectively held out cohort and a set of samples sequenced after model freeze that collectively contained 9210 total samples with known diagnoses. When evaluated on a cohort of CUPs, the model recapitulated established associations between genomic alterations and cancer subtype.

DISCUSSION

Combining diagnostic prediction tests (e.g., Tempus TO) with sequencing-based variant reporting (e.g., Tempus xT) may expand therapeutic options for patients with cancers of unknown primary or uncertain histology.

Artificial Intelligence-Assisted Diagnostic Cytology and Genomic Testing for Hematologic Disorders

Artificial intelligence (AI) is a rapidly evolving field of computer science that involves the development of computational programs that can mimic human intelligence. In particular, machine learning and deep learning models have enabled the identification and grouping of patterns within data, leading to the development of AI systems that have been applied in various areas of hematology, including digital pathology, alpha thalassemia patient screening, cytogenetics, immunophenotyping, and sequencing. These AI-assisted methods have shown promise in improving diagnostic accuracy and efficiency, identifying novel biomarkers, and predicting treatment outcomes. However, limitations such as limited databases, lack of validation and standardization, systematic errors, and bias prevent AI from completely replacing manual diagnosis in hematology. In addition, the processing of large amounts of patient data and personal information by AI poses potential data privacy issues, necessitating the development of regulations to evaluate AI systems and address ethical concerns in clinical AI systems. Nonetheless, with continued research and development, AI has the potential to revolutionize the field of hematology and improve patient outcomes. To fully realize this potential, however, the challenges facing AI in hematology must be addressed and overcome.

AttOmics: attention-based architecture for diagnosis and prognosis from omics data

MOTIVATION

The increasing availability of high-throughput omics data allows for considering a new medicine centered on individual patients. Precision medicine relies on exploiting these high-throughput data with machine-learning models, especially the ones based on deep-learning approaches, to improve diagnosis. Due to the high-dimensional small-sample nature of omics data, current deep-learning models end up with many parameters and have to be fitted with a limited training set. Furthermore, interactions between molecular entities inside an omics profile are not patient specific but are the same for all patients.

RESULTS

In this article, we propose AttOmics, a new deep-learning architecture based on the self-attention mechanism. First, we decompose each omics profile into a set of groups, where each group contains related features. Then, by applying the self-attention mechanism to the set of groups, we can capture the different interactions specific to a patient. The results of different experiments carried out in this article show that our model can accurately predict the phenotype of a patient with fewer parameters than deep neural networks. Visualizing the attention maps can provide new insights into the essential groups for a particular phenotype.

AVAILABILITY AND IMPLEMENTATION

The code and data are available at https://forge.ibisc.univ-evry.fr/abeaude/AttOmics. TCGA data can be downloaded from the Genomic Data Commons Data Portal.

BrcaDx: precise identification of breast cancer from expression data using a minimal set of features

Background: Breast cancer is the foremost cancer in worldwide incidence, surpassing lung cancer notwithstanding the gender bias. One in four cancer cases among women are attributable to cancers of the breast, which are also the leading cause of death in women. Reliable options for early detection of breast cancer are needed. Methods: Using public-domain datasets, we screened transcriptomic profiles of breast cancer samples, and identified progression-significant linear and ordinal model genes using stage-informed models. We then applied a sequence of machine learning techniques, namely, feature selection, principal components analysis, and k-means clustering, to train a learner to discriminate "cancer" from "normal" based on expression levels of identified biomarkers. Results: Our computational pipeline yielded an optimal set of nine biomarker features for training the learner, namely, NEK2, PKMYT1, MMP11, CPA1, COL10A1, HSD17B13, CA4, MYOC, and LYVE1. Validation of the learned model on an independent test dataset yielded a performance of 99.5% accuracy. Blind validation on an out-of-domain external dataset yielded a balanced accuracy of 95.5%, demonstrating that the model has effectively reduced the dimensionality of the problem, and learnt the solution. The model was rebuilt using the full dataset, and then deployed as a web app for non-profit purposes at: https://apalania.shinyapps.io/brcadx/. To our knowledge, this is the best-performing freely available tool for the high-confidence diagnosis of breast cancer, and represents a promising aid to medical diagnosis.

Generalising uncertainty improves accuracy and safety of deep learning analytics applied to oncology

Uncertainty estimation is crucial for understanding the reliability of deep learning (DL) predictions, and critical for deploying DL in the clinic. Differences between training and production datasets can lead to incorrect predictions with underestimated uncertainty. To investigate this pitfall, we benchmarked one pointwise and three approximate Bayesian DL models for predicting cancer of unknown primary, using three RNA-seq datasets with 10,968 samples across 57 cancer types. Our results highlight that simple and scalable Bayesian DL significantly improves the generalisation of uncertainty estimation. Moreover, we designed a prototypical metric-the area between development and production curve (ADP), which evaluates the accuracy loss when deploying models from development to production. Using ADP, we demonstrate that Bayesian DL improves accuracy under data distributional shifts when utilising 'uncertainty thresholding'. In summary, Bayesian DL is a promising approach for generalising uncertainty, improving performance, transparency, and safety of DL models for deployment in the real world.

Machine Learning Analysis of RNA-seq Data for Diagnostic and Prognostic Prediction of Colon Cancer

Data from omics studies have been used for prediction and classification of various diseases in biomedical and bioinformatics research. In recent years, Machine Learning (ML) algorithms have been used in many different fields related to healthcare systems, especially for disease prediction and classification tasks. Integration of molecular omics data with ML algorithms has offered a great opportunity to evaluate clinical data. RNA sequence (RNA-seq) analysis has been emerged as the gold standard for transcriptomics analysis. Currently, it is being used widely in clinical research. In our present work, RNA-seq data of extracellular vesicles (EV) from healthy and colon cancer patients are analyzed. Our aim is to develop models for prediction and classification of colon cancer stages. Five different canonical ML and Deep Learning (DL) classifiers are used to predict colon cancer of an individual with processed RNA-seq data. The classes of data are formed on the basis of both colon cancer stages and cancer presence (healthy or cancer). The canonical ML classifiers, which are k-Nearest Neighbor (kNN), Logistic Model Tree (LMT), Random Tree (RT), Random Committee (RC), and Random Forest (RF), are tested with both forms of the data. In addition, to compare the performance with canonical ML models, One-Dimensional Convolutional Neural Network (1-D CNN), Long Short-Term Memory (LSTM), and Bidirectional LSTM (BiLSTM) DL models are utilized. Hyper-parameter optimizations of DL models are constructed by using genetic meta-heuristic optimization algorithm (GA). The best accuracy in cancer prediction is obtained with RC, LMT, and RF canonical ML algorithms as 97.33%. However, RT and kNN show 95.33% performance. The best accuracy in cancer stage classification is achieved with RF as 97.33%. This result is followed by LMT, RC, kNN, and RT with 96.33%, 96%, 94.66%, and 94%, respectively. According to the results of the experiments with DL algorithms, the best accuracy in cancer prediction is obtained with 1-D CNN as 97.67%. BiLSTM and LSTM show 94.33% and 93.67% performance, respectively. In classification of the cancer stages, the best accuracy is achieved with BiLSTM as 98%. 1-D CNN and LSTM show 97% and 94.33% performance, respectively. The results reveal that both canonical ML and DL models may outperform each other for different numbers of features.

International consensus on the initial diagnostic workup of cancer of unknown primary

BACKGROUND

Although the incidence of Cancer of Unknown Primary (CUP) is estimated to be 1-2 % of all cancers worldwide, no international standards for diagnostic workup are yet established. Such an international guideline would facilitate international comparison, provide adequate incidence and survival rates, and ultimately improve care of patients with CUP.

METHODS

Participants for a four round modified Delphi study were selected via a CUP literature search in PubMed and an international network of cancer researchers. A total of 90 CUP experts were invited, and 34 experts from 15 countries over four continents completed all Delphi survey rounds.

FINDINGS

The Delphi procedure resulted in a multi-layer CUP classification for the diagnostic workup. Initial diagnostic workup should at least consist of history and physical examination, full blood count, analysis of serum markers, a biopsy of the most accessible lesion, a CT scan of chest/abdomen/pelvis, and immunohistochemical testing. Additionally, the expert panel agreed on the need of an ideal diagnostic lead time for CUP patients. There was no full consensus on the place in diagnostic workup of symptom-guided MRI or ultrasound, a PET/CT scan, targeted gene panels, immunohistochemical markers, and whole genome sequencing.

INTERPRETATION

Consensus was reached on the contents of the first diagnostic layer of a multi-layer CUP classification. This is a first step towards full consensus on CUP diagnostics, that should also include supplementary and advanced diagnostics.

A comparison of DNA sequencing and gene expression profiling to assist tissue of origin diagnosis in cancer of unknown primary

Cancer of unknown primary (CUP) is a syndrome defined by clinical absence of a primary cancer after standardised investigations. Gene expression profiling (GEP) and DNA sequencing have been used to predict primary tissue of origin (TOO) in CUP and find molecularly guided treatments; however, a detailed comparison of the diagnostic yield from these two tests has not been described. Here, we compared the diagnostic utility of RNA and DNA tests in 215 CUP patients (82% received both tests) in a prospective Australian study. Based on retrospective assessment of clinicopathological data, 77% (166/215) of CUPs had insufficient evidence to support TOO diagnosis (clinicopathology unresolved). The remainder had either a latent primary diagnosis (10%) or clinicopathological evidence to support a likely TOO diagnosis (13%) (clinicopathology resolved). We applied a microarray (CUPGuide) or custom NanoString 18-class GEP test to 191 CUPs with an accuracy of 91.5% in known metastatic cancers for high-medium confidence predictions. Classification performance was similar in clinicopathology-resolved CUPs - 80% had high-medium predictions and 94% were concordant with pathology. Notably, only 56% of the clinicopathology-unresolved CUPs had high-medium confidence GEP predictions. Diagnostic DNA features were interrogated in 201 CUP tumours guided by the cancer type specificity of mutations observed across 22 cancer types from the AACR Project GENIE database (77,058 tumours) as well as mutational signatures (e.g. smoking). Among the clinicopathology-unresolved CUPs, mutations and mutational signatures provided additional diagnostic evidence in 31% of cases. GEP classification was useful in only 13% of cases and oncoviral detection in 4%. Among CUPs where genomics informed TOO, lung and biliary cancers were the most frequently identified types, while kidney tumours were another identifiable subset. In conclusion, DNA and RNA profiling supported an unconfirmed TOO diagnosis in one-third of CUPs otherwise unresolved by clinicopathology assessment alone. DNA mutation profiling was the more diagnostically informative assay. © 2022 The Authors. The Journal of Pathology published by John Wiley & Sons Ltd on behalf of The Pathological Society of Great Britain and Ireland.

Value of genomics- and radiomics-based machine learning models in the identification of breast cancer molecular subtypes: a systematic review and meta-analysis

Background

In the era of precision therapy, early classification of breast cancer (BRCA) molecular subtypes has clinical significance for disease management and prognosis. We explored the accuracy of machine learning (ML) models for early classification of BRCA molecular subtypes through a systematic review of the literature currently available.

Methods

We retrieved relevant studies published in PubMed, EMBASE, Cochrane, and Web of Science until 15 April 2022. A prediction model risk of bias assessment tool (PROBAST) was applied for the assessment of risk of bias of a genomics-based ML model, and the Radiomics Quality Score (RQS) was simultaneously used to evaluate the quality of this radiomics-based ML model. A random effects model was adopted to analyze the predictive accuracy of genomics-based ML and radiomics-based ML for Luminal A, Luminal B, Basal-like or triple-negative breast cancer (TNBC), and human epidermal growth factor receptor 2 (HER2). The PROSPERO of our study was prospectively registered (CRD42022333611).

Results

Of the 38 studies were selected for analysis, 14 ML models were based on gene-transcriptomic, with only 4 external validations; and 43 ML models were based on radiomics, with only 14 external validations. Meta-analysis results showed that c-statistic values of the ML based on radiomics for the identification of BRCA molecular subtypes Luminal A, Luminal B, Basal-like or TNBC, and HER2 were 0.76 [95% confidence interval (CI): 0.60-0.96], 0.78 (95% CI: 0.69-0.87), 0.89 (95% CI: 0.83-0.91), and 0.83 (95% CI: 0.81-0.86), respectively. The c-statistic values of ML based on the gene-transcriptomic analysis cohort for the identification of the previously described BRCA molecular subtypes were 0.96 (95% CI: 0.93-0.99), 0.96 (95% CI: 0.93-0.99), 0.98 (95% CI: 0.95-1.00), and 0.97 (95% CI: 0.96-0.98) respectively. Additionally, the sensitivity of the ML model based on radiomics for each molecular subtype ranged from 0.79 to 0.85, while the sensitivity of the ML model based on gene-transcriptomic was between 0.92 and 0.99.

Conclusions

Both radiomics and gene transcriptomics produced ideal effects on BRCA molecular subtype prediction. Compared with radiomics, gene transcriptomics yielded better prediction results, but radiomics was simpler and more convenient from a clinical point of view.

Developmental Deconvolution for Classification of Cancer Origin

Cancer is partly a developmental disease, with malignancies named based on cell or tissue of origin. However, a systematic atlas of tumor origins is lacking. Here we map the single-cell organogenesis of 56 developmental trajectories to the transcriptomes of over 10,000 tumors across 33 cancer types. We deconvolute tumor transcriptomes into signals for individual developmental trajectories. Using these signals as inputs, we construct a developmental multilayer perceptron (D-MLP) classifier that outputs cancer origin. D-MLP (ROC-AUC: 0.974 for top prediction) outperforms benchmark classifiers. We analyze tumors from patients with cancer of unknown primary (CUP), selecting the most difficult cases in which extensive multimodal workup yielded no definitive tumor type. Interestingly, CUPs form groups distinguished by developmental trajectories, and classification reveals diagnosis for patient tumors. Our results provide an atlas of tumor developmental origins, provide a tool for diagnostic pathology, and suggest developmental classification may be a useful approach for patient tumors.

SIGNIFICANCE

Here we map the developmental trajectories of tumors. We deconvolute tumor transcriptomes into signals for mammalian developmental programs and use this information to construct a deep learning classifier that outputs tumor type. We apply the classifier to CUP and reveal the developmental origins of patient tumors. See related commentary by Wang, p. 2498. This article is highlighted in the In This Issue feature, p. 2483.

Omics Data and Data Representations for Deep Learning-Based Predictive Modeling

Medical discoveries mainly depend on the capability to process and analyze biological datasets, which inundate the scientific community and are still expanding as the cost of next-generation sequencing technologies is decreasing. Deep learning (DL) is a viable method to exploit this massive data stream since it has advanced quickly with there being successive innovations. However, an obstacle to scientific progress emerges: the difficulty of applying DL to biology, and this because both fields are evolving at a breakneck pace, thus making it hard for an individual to occupy the front lines of both of them. This paper aims to bridge the gap and help computer scientists bring their valuable expertise into the life sciences. This work provides an overview of the most common types of biological data and data representations that are used to train DL models, with additional information on the models themselves and the various tasks that are being tackled. This is the essential information a DL expert with no background in biology needs in order to participate in DL-based research projects in biomedicine, biotechnology, and drug discovery. Alternatively, this study could be also useful to researchers in biology to understand and utilize the power of DL to gain better insights into and extract important information from the omics data.

Blood Test for Breast Cancer Screening through the Detection of Tumor-Associated Circulating Transcripts

Liquid biopsy has been emerging for early screening and treatment monitoring at each cancer stage. However, the current blood-based diagnostic tools in breast cancer have not been sufficient to understand patient-derived molecular features of aggressive tumors individually. Herein, we aimed to develop a blood test for the early detection of breast cancer with cost-effective and high-throughput considerations in order to combat the challenges associated with precision oncology using mRNA-based tests. We prospectively evaluated 719 blood samples from 404 breast cancer patients and 315 healthy controls, and identified 10 mRNA transcripts whose expression is increased in the blood of breast cancer patients relative to healthy controls. Modeling of the tumor-associated circulating transcripts (TACTs) is performed by means of four different machine learning techniques (artificial neural network (ANN), decision tree (DT), logistic regression (LR), and support vector machine (SVM)). The ANN model had superior sensitivity (90.2%), specificity (80.0%), and accuracy (85.7%) compared with the other three models. Relative to the value of 90.2% achieved using the TACT assay on our test set, the sensitivity values of other conventional assays (mammogram, CEA, and CA 15-3) were comparable or much lower, at 89%, 7%, and 5%, respectively. The sensitivity, specificity, and accuracy of TACTs were appreciably consistent across the different breast cancer stages, suggesting the potential of the TACTs assay as an early diagnosis and prediction of poor outcomes. Our study potentially paves the way for a simple and accurate diagnostic and prognostic tool for liquid biopsy.

Comprehensive genomic and epigenomic analysis in cancer of unknown primary guides molecularly-informed therapies despite heterogeneity

The benefit of molecularly-informed therapies in cancer of unknown primary (CUP) is unclear. Here, we use comprehensive molecular characterization by whole genome/exome, transcriptome and methylome analysis in 70 CUP patients to reveal substantial mutational heterogeneity with TP53, MUC16, KRAS, LRP1B and CSMD3 being the most frequently mutated known cancer-related genes. The most common fusion partner is FGFR2, the most common focal homozygous deletion affects CDKN2A. 56/70 (80%) patients receive genomics-based treatment recommendations which are applied in 20/56 (36%) cases. Transcriptome and methylome data provide evidence for the underlying entity in 62/70 (89%) cases. Germline analysis reveals five (likely) pathogenic mutations in five patients. Recommended off-label therapies translate into a mean PFS ratio of 3.6 with a median PFS1 of 2.9 months (17 patients) and a median PFS2 of 7.8 months (20 patients). Our data emphasize the clinical value of molecular analysis and underline the need for innovative, mechanism-based clinical trials.

The identification of molecular biomarkers in cancer of unknown primary site (CUP) cases may enable the improvement of prognosis in these patients. Here, the authors integrate whole genome/exome, transcriptome and methylome data in 70 CUP patients, recommend therapies based on their analysis and report clinical outcome data.

Visual Clustering of Transcriptomic Data from Primary and Metastatic Tumors-Dependencies and Novel Pitfalls

Personalized oncology is a rapidly evolving area and offers cancer patients therapy options that are more specific than ever. However, there is still a lack of understanding regarding transcriptomic similarities or differences of metastases and corresponding primary sites. Applying two unsupervised dimension reduction methods (t-Distributed Stochastic Neighbor Embedding (t-SNE) and Uniform Manifold Approximation and Projection (UMAP)) on three datasets of metastases (n = 682 samples) with three different data transformations (unprocessed, log10 as well as log10 + 1 transformed values), we visualized potential underlying clusters. Additionally, we analyzed two datasets (n = 616 samples) containing metastases and primary tumors of one entity, to point out potential familiarities. Using these methods, no tight link between the site of resection and cluster formation outcome could be demonstrated, or for datasets consisting of solely metastasis or mixed datasets. Instead, dimension reduction methods and data transformation significantly impacted visual clustering results. Our findings strongly suggest data transformation to be considered as another key element in the interpretation of visual clustering approaches along with initialization and different parameters. Furthermore, the results highlight the need for a more thorough examination of parameters used in the analysis of clusters.

Machine learning-based tissue of origin classification for cancer of unknown primary diagnostics using genome-wide mutation features

Cancers of unknown primary (CUP) origin account for ∼3% of all cancer diagnoses, whereby the tumor tissue of origin (TOO) cannot be determined. Using a uniformly processed dataset encompassing 6756 whole-genome sequenced primary and metastatic tumors, we develop Cancer of Unknown Primary Location Resolver (CUPLR), a random forest TOO classifier that employs 511 features based on simple and complex somatic driver and passenger mutations. CUPLR distinguishes 35 cancer (sub)types with ∼90% recall and ∼90% precision based on cross-validation and test set predictions. We find that structural variant derived features increase the performance and utility for classifying specific cancer types. With CUPLR, we could determine the TOO for 82/141 (58%) of CUP patients. Although CUPLR is based on machine learning, it provides a human interpretable graphical report with detailed feature explanations. The comprehensive output of CUPLR complements existing histopathological procedures and can enable improved diagnostics for CUP patients.

Multimodal data analysis reveals that pancreatobiliary-type ampullary adenocarcinoma resembles pancreatic adenocarcinoma and differs from cholangiocarcinoma

BACKGROUND

Ampullary adenocarcinoma (AAC) arises from the ampulla of Vater where the pancreatic duct and bile duct join and empty into the duodenum. It can be classified into intestinal and pancreatobiliary types based on histopathology or immunohistochemistry. However, there are no biomarkers for further classification of pancreatobiliary-type AAC which has important implications for its treatment. We aimed to identify the tumor origin of pancreatobiliary-type AAC by systematically analyzing whole-slide images (WSIs), survival data, and genome sequencing data collected from multiple centers.

METHODS

This study involved three experiments. First, we extracted quantitative and highly interpretable features from the tumor region in WSIs and constructed a histologic classifier to differentiate between pancreatic adenocarcinoma (PAC) and cholangiocarcinoma. The histologic classifier was then applied to patients with pancreatobiliary-type AAC to infer the tumor origin. Secondly, we compared the overall survival of patients with pancreatobiliary-type AAC stratified by the adjuvant chemotherapy regimens designed for PAC or cholangiocarcinoma. Finally, we compared the mutation landscape of pancreatobiliary-type AAC with those of PAC and cholangiocarcinoma.

RESULTS

The histologic classifier accurately classified PAC and cholangiocarcinoma in both the internal and external validation sets (AUC > 0.99). All pancreatobiliary-type AACs (n = 45) were classified as PAC. The patients with pancreatobiliary-type AAC receiving regimens designed for PAC showed more favorable overall survival than those receiving regimens designed for cholangiocarcinoma in a multivariable Cox regression (hazard ratio = 7.24, 95% confidence interval: 1.28-40.78, P = 0.025). The results of mutation analysis showed that the mutation landscape of AAC was very similar to that of PAC but distinct from that of cholangiocarcinoma.

CONCLUSIONS

This multi-center study provides compelling evidence that pancreatobiliary-type AAC resembles PAC instead of cholangiocarcinoma in different aspects, which can guide the treatment selection and clinical trials planning for pancreatobiliary-type AAC.

Therapeutic Strategies Focused on Cancer-Associated Hypercoagulation for Ovarian Clear Cell Carcinoma

Ovarian clear cell carcinoma (OCCC) is associated with chemotherapy resistance and poor prognosis, especially in advanced cases. Although comprehensive genomic analyses have clarified the significance of genomic alterations such as ARID1A and PIK3CA mutations in OCCC, therapeutic strategies based on genomic alterations have not been confirmed. On the other hand, OCCC is clinically characterized by a high incidence of thromboembolism. Moreover, OCCC specifically shows high expression of tissue factor and interleukin-6, which play a critical role in cancer-associated hypercoagulation and may be induced by OCCC-specific genetic alterations or the endometriosis-related tumor microenvironment. In this review, we focused on the association between cancer-associated hypercoagulation and molecular biology in OCCC. Moreover, we reviewed the effectiveness of candidate drugs targeting hypercoagulation, such as tissue factor- or interleukin-6-targeting drugs, anti-inflammatory drugs, anti-hypoxia signaling drugs, anticoagulants, and combined immunotherapy with these drugs for OCCC. This review is expected to contribute to novel basic research and clinical trials for the prevention, early detection, and treatment of OCCC focused on hypercoagulation.

SEOM-GETTHI clinical guideline for the practical management of molecular platforms (2021)

The improvement of molecular alterations in cancer as well as the development of technology has allowed us to bring closer to clinical practice the determination of molecular alterations in the diagnosis and treatment of cancer. The use of multidetermination platforms is spreading in most Spanish hospitals. The objective of these clinical practice guides is to review their usefulness, and establish usage guidelines that guide their incorporation into clinical practice.

Deep Learning-Based Pan-Cancer Classification Model Reveals Tissue-of-Origin Specific Gene Expression Signatures

Cancer tissue-of-origin specific biomarkers are needed for effective diagnosis, monitoring, and treatment of cancers. In this study, we analyzed transcriptomics data from 37 cancer types provided by The Cancer Genome Atlas (TCGA) to identify cancer tissue-of-origin specific gene expression signatures. We developed a deep neural network model to classify cancers based on gene expression data. The model achieved a predictive accuracy of >97% across cancer types indicating the presence of distinct cancer tissue-of-origin specific gene expression signatures. We interpreted the model using Shapley additive explanations to identify specific gene signatures that significantly contributed to cancer-type classification. We evaluated the model and the validity of gene signatures using an independent test data set from the International Cancer Genome Consortium. In conclusion, we present a robust neural network model for accurate classification of cancers based on gene expression data and also provide a list of gene signatures that are valuable for developing biomarker panels for determining cancer tissue-of-origin. These gene signatures serve as valuable biomarkers for determining tissue-of-origin for cancers of unknown primary.

Artificial intelligence and cholangiocarcinoma: Updates and prospects

Artificial intelligence (AI) is the timeliest field of computer science and attempts to mimic cognitive function of humans to solve problems. In the era of “Big data”, there is an ever-increasing need for AI in all aspects of medicine. Cholangiocarcinoma (CCA) is the second most common primary malignancy of liver that has shown an increase in incidence in the last years. CCA has high mortality as it is diagnosed in later stages that decreases effect of surgery, chemotherapy, and other modalities. With technological advancement there is an immense amount of clinicopathologic, genetic, serologic, histologic, and radiologic data that can be assimilated together by modern AI tools for diagnosis, treatment, and prognosis of CCA. The literature shows that in almost all cases AI models have the capacity to increase accuracy in diagnosis, treatment, and prognosis of CCA. Most studies however are retrospective, and one study failed to show AI benefit in practice. There is immense potential for AI in diagnosis, treatment, and prognosis of CCA however limitations such as relative lack of studies in use by human operators in improvement of survival remains to be seen.

Artificial image objects for classification of breast cancer biomarkers with transcriptome sequencing data and convolutional neural network algorithms

BACKGROUND

Transcriptome sequencing has been broadly available in clinical studies. However, it remains a challenge to utilize these data effectively for clinical applications due to the high dimension of the data and the highly correlated expression between individual genes.

METHODS

We proposed a method to transform RNA sequencing data into artificial image objects (AIOs) and applied convolutional neural network (CNN) algorithms to classify these AIOs. With the AIO technique, we considered each gene as a pixel in an image and its expression level as pixel intensity. Using the GSE96058 (n = 2976), GSE81538 (n = 405), and GSE163882 (n = 222) datasets, we created AIOs for the subjects and designed CNN models to classify biomarker Ki67 and Nottingham histologic grade (NHG).

RESULTS

With fivefold cross-validation, we accomplished a classification accuracy and AUC of 0.821 ± 0.023 and 0.891 ± 0.021 for Ki67 status. For NHG, the weighted average of categorical accuracy was 0.820 ± 0.012, and the weighted average of AUC was 0.931 ± 0.006. With GSE96058 as training data and GSE81538 as testing data, the accuracy and AUC for Ki67 were 0.826 ± 0.037 and 0.883 ± 0.016, and that for NHG were 0.764 ± 0.052 and 0.882 ± 0.012, respectively. These results were 10% better than the results reported in the original studies. For Ki67, the calls generated from our models had a better power for prediction of survival as compared to the calls from trained pathologists in survival analyses.

CONCLUSIONS

We demonstrated that RNA sequencing data could be transformed into AIOs and be used to classify Ki67 status and NHG with CNN algorithms. The AIO method could handle high-dimensional data with highly correlated variables, and there was no need for variable selection. With the AIO technique, a data-driven, consistent, and automation-ready model could be developed to classify biomarkers with RNA sequencing data and provide more efficient care for cancer patients.