Deep learning-based risk stratification of preoperative breast biopsies using digital whole slide images.

BACKGROUND: Nottingham histological grade (NHG) is a well established prognostic factor in breast cancer histopathology but has a high inter-assessor variability with many tumours being classified as intermediate grade, NHG2. Here, we evaluate if DeepGrade, a previously developed model for risk stratification of resected tumour specimens, could be applied to risk-stratify tumour biopsy specimens. METHODS: A total of 11,955,755 tiles from 1169 whole slide images of preoperative biopsies from 896 patients diagnosed with breast cancer in Stockholm, Sweden, were included. DeepGrade, a deep convolutional neural network model, was applied for the prediction of low- and high-risk tumours. It was evaluated against clinically assigned grades NHG1 and NHG3 on the biopsy specimen but also against the grades assigned to the corresponding resection specimen using area under the operating curve (AUC). The prognostic value of the DeepGrade model in the biopsy setting was evaluated using time-to-event analysis. RESULTS: Based on preoperative biopsy images, the DeepGrade model predicted resected tumour cases of clinical grades NHG1 and NHG3 with an AUC of 0.908 (95% CI: 0.88; 0.93). Furthermore, out of the 432 resected clinically-assigned NHG2 tumours, 281 (65%) were classified as DeepGrade-low and 151 (35%) as DeepGrade-high. Using a multivariable Cox proportional hazards model the hazard ratio between DeepGrade low- and high-risk groups was estimated as 2.01 (95% CI: 1.06; 3.79). CONCLUSIONS: DeepGrade provided prediction of tumour grades NHG1 and NHG3 on the resection specimen using only the biopsy specimen. The results demonstrate that the DeepGrade model can provide decision support to identify high-risk tumours based on preoperative biopsies, thus improving early treatment decisions.

Clinical evaluation of deep learning-based risk profiling in breast cancer histopathology and comparison to an established multigene assay.

PURPOSE: To evaluate the Stratipath Breast tool for image-based risk profiling and compare it with an established prognostic multigene assay for risk profiling in a real-world case series of estrogen receptor (ER)-positive and human epidermal growth factor receptor 2 (HER2)-negative early breast cancer patients categorized as intermediate risk based on classic clinicopathological variables and eligible for chemotherapy. METHODS: In a case series comprising 234 invasive ER-positive/HER2-negative tumors, clinicopathological data including Prosigna results and corresponding HE-stained tissue slides were retrieved. The digitized HE slides were analysed by Stratipath Breast. RESULTS: Our findings showed that the Stratipath Breast analysis identified 49.6% of the clinically intermediate tumors as low risk and 50.4% as high risk. The Prosigna assay classified 32.5%, 47.0% and 20.5% tumors as low, intermediate and high risk, respectively. Among Prosigna intermediate-risk tumors, 47.3% were stratified as Stratipath low risk and 52.7% as high risk. In addition, 89.7% of Stratipath low-risk cases were classified as Prosigna low/intermediate risk. The overall agreement between the two tests for low-risk and high-risk groups (N = 124) was 71.0%, with a Cohen's kappa of 0.42. For both risk profiling tests, grade and Ki67 differed significantly between risk groups. CONCLUSION: The results from this clinical evaluation of image-based risk stratification shows a considerable agreement to an established gene expression assay in routine breast pathology.

Development and prognostic validation of a three-level NHG-like deep learning-based model for histological grading of breast cancer.

BACKGROUND: Histological grade is a well-known prognostic factor that is routinely assessed in breast tumours. However, manual assessment of Nottingham Histological Grade (NHG) has high inter-assessor and inter-laboratory variability, causing uncertainty in grade assignments. To address this challenge, we developed and validated a three-level NHG-like deep learning-based histological grade model (predGrade). The primary performance evaluation focuses on prognostic performance. METHODS: This observational study is based on two patient cohorts (SöS-BC-4, N = 2421 (training and internal test); SCAN-B-Lund, N = 1262 (test)) that include routine histological whole-slide images (WSIs) together with patient outcomes. A deep convolutional neural network (CNN) model with an attention mechanism was optimised for the classification of the three-level histological grading (NHG) from haematoxylin and eosin-stained WSIs. The prognostic performance was evaluated by time-to-event analysis of recurrence-free survival and compared to clinical NHG grade assignments in the internal test set as well as in the fully independent external test cohort. RESULTS: We observed effect sizes (hazard ratio) for grade 3 versus 1, for the conventional NHG method (HR = 2.60 (1.18-5.70 95%CI, p-value = 0.017)) and the deep learning model (HR = 2.27, 95%CI 1.07-4.82, p-value = 0.033) on the internal test set after adjusting for established clinicopathological risk factors. In the external test set, the unadjusted HR for clinical NHG 2 versus 1 was estimated to be 2.59 (p-value = 0.004) and clinical NHG 3 versus 1 was estimated to be 3.58 (p-value < 0.001). For predGrade, the unadjusted HR for predGrade 2 versus 1 HR = 2.52 (p-value = 0.030), and 4.07 (p-value = 0.001) for preGrade 3 versus 1 was observed in the independent external test set. In multivariable analysis, HR estimates for neither clinical NHG nor predGrade were found to be significant (p-value > 0.05). We tested for differences in HR estimates between NHG and predGrade in the independent test set and found no significant difference between the two classification models (p-value > 0.05), confirming similar prognostic performance between conventional NHG and predGrade. CONCLUSION: Routine histopathology assessment of NHG has a high degree of inter-assessor variability, motivating the development of model-based decision support to improve reproducibility in histological grading. We found that the proposed model (predGrade) provides a similar prognostic performance as clinical NHG. The results indicate that deep CNN-based models can be applied for breast cancer histological grading.

A Multi-Stain Breast Cancer Histological Whole-Slide-Image Data Set from Routine Diagnostics.

The analysis of FFPE tissue sections stained with haematoxylin and eosin (H&E) or immunohistochemistry (IHC) is essential for the pathologic assessment of surgically resected breast cancer specimens. IHC staining has been broadly adopted into diagnostic guidelines and routine workflows to assess the status of several established biomarkers, including ER, PGR, HER2 and KI67. Biomarker assessment can also be facilitated by computational pathology image analysis methods, which have made numerous substantial advances recently, often based on publicly available whole slide image (WSI) data sets. However, the field is still considerably limited by the sparsity of public data sets. In particular, there are no large, high quality publicly available data sets with WSIs of matching IHC and H&E-stained tissue sections from the same tumour. Here, we publish the currently largest publicly available data set of WSIs of tissue sections from surgical resection specimens from female primary breast cancer patients with matched WSIs of corresponding H&E and IHC-stained tissue, consisting of 4,212 WSIs from 1,153 patients.

Transcriptional intra-tumour heterogeneity predicted by deep learning in routine breast histopathology slides provides independent prognostic information.

BACKGROUND: Intra-tumour heterogeneity (ITH) causes diagnostic challenges and increases the risk for disease recurrence. Quantification of ITH is challenging and has not been demonstrated in large studies. It has previously been shown that deep learning can enable spatially resolved prediction of molecular phenotypes from digital histopathology whole slide images (WSIs). Here we propose a novel method (Deep-ITH) to predict and measure ITH, and we evaluate its prognostic performance in breast cancer. METHODS: Deep convolutional neural networks were used to spatially predict gene-expression (PAM50 set) from WSIs. For each predicted transcript, 12 measures of heterogeneity were extracted in the training data set (N = 931). A prognostic score to dichotomise patients into Deep-ITH low- and high-risk groups was established using an elastic-net regularised Cox proportional hazards model (recurrence-free survival). Prognostic performance was evaluated in two independent data sets: SöS-BC-1 (N = 1358) and SCAN-B-Lund (N = 1262). RESULTS: We observed an increase in risk of recurrence in the high-risk group with hazard ratio (HR) 2.11 (95%CI:1.22-3.60; p = 0.007) using nested cross-validation. Subgroup analyses confirmed the prognostic performance in oestrogen receptor (ER)-positive, human epidermal growth factor receptor 2 (HER2)-negative, grade 3, and large tumour subgroups. The prognostic value was confirmed in the independent SöS-BC-1 cohort (HR=1.84; 95%CI:1.03-3.3; p = 3.99 ×10-2). In the other external cohort, significant HR was observed in the subgroup of histological grade 2 patients, as well as in the subgroup of patients with small tumours (<20 mm). CONCLUSION: We developed a novel method for an automated, scalable, and cost-efficient measure of ITH from WSIs that provides independent prognostic value for breast cancer. SIGNIFICANCE: Transcriptional ITH predicted by deep learning models enables prediction of patient survival from routine histopathology WSIs in breast cancer.

Prediction model for drug response of acute myeloid leukemia patients.

Despite some encouraging successes, predicting the therapy response of acute myeloid leukemia (AML) patients remains highly challenging due to tumor heterogeneity. Here we aim to develop and validate MDREAM, a robust ensemble-based prediction model for drug response in AML based on an integration of omics data, including mutations and gene expression, and large-scale drug testing. Briefly, MDREAM is first trained in the BeatAML cohort (n = 278), and then validated in the BeatAML (n = 183) and two external cohorts, including a Swedish AML cohort (n = 45) and a relapsed/refractory acute leukemia cohort (n = 12). The final prediction is based on 122 ensemble models, each corresponding to a drug. A confidence score metric is used to convey the uncertainty of predictions; among predictions with a confidence score >0.75, the validated proportion of good responders is 77%. The Spearman correlations between the predicted and the observed drug response are 0.68 (95% CI: [0.64, 0.68]) in the BeatAML validation set, -0.49 (95% CI: [-0.53, -0.44]) in the Swedish cohort and 0.59 (95% CI: [0.51, 0.67]) in the relapsed/refractory cohort. A web-based implementation of MDREAM is publicly available at https://www.meb.ki.se/shiny/truvu/MDREAM/ .

Using deep learning to detect patients at risk for prostate cancer despite benign biopsies.

Routine transrectal ultrasound-guided systematic prostate biopsy only samples a small volume of the prostate and tumors between biopsy cores can be missed, leading to low sensitivity to detect clinically relevant prostate cancers (PCa). Deep learning may enable detection of PCa despite benign biopsies. We included 14,354 hematoxylin-eosin stained benign prostate biopsies from 1,508 men in two groups: men without established PCa diagnosis and men with at least one core biopsy diagnosed with PCa. A 10-Convolutional Neural Network ensemble was optimized to distinguish benign biopsies from benign men or patients with PCa. Area under the receiver operating characteristic curve was estimated at 0.739 (bootstrap 95% CI:0.682-0.796) on man level in the held-out test set. At the specificity of 0.90, the model sensitivity was 0.348. The proposed model can detect men with risk of missed PCa and has the potential to reduce false negatives and to indicate men who could benefit from rebiopsies.

Transcriptome-wide prediction of prostate cancer gene expression from histopathology images using co-expression-based convolutional neural networks.

MOTIVATION: Molecular phenotyping by gene expression profiling is central in contemporary cancer research and in molecular diagnostics but remains resource intense to implement. Changes in gene expression occurring in tumours cause morphological changes in tissue, which can be observed on the microscopic level. The relationship between morphological patterns and some of the molecular phenotypes can be exploited to predict molecular phenotypes from routine haematoxylin and eosin-stained whole slide images (WSIs) using convolutional neural networks (CNNs). In this study, we propose a new, computationally efficient approach to model relationships between morphology and gene expression. RESULTS: We conducted the first transcriptome-wide analysis in prostate cancer, using CNNs to predict bulk RNA-sequencing estimates from WSIs for 370 patients from the TCGA PRAD study. Out of 15 586 protein coding transcripts, 6618 had predicted expression significantly associated with RNA-seq estimates (FDR-adjusted P-value <1×10-4) in a cross-validation and 5419 (81.9%) of these associations were subsequently validated in a held-out test set. We furthermore predicted the prognostic cell-cycle progression score directly from WSIs. These findings suggest that contemporary computer vision models offer an inexpensive and scalable solution for prediction of gene expression phenotypes directly from WSIs, providing opportunity for cost-effective large-scale research studies and molecular diagnostics. AVAILABILITY AND IMPLEMENTATION: A self-contained example is available from http://github.com/phiwei/prostate_coexpression. Model predictions and metrics are available from doi.org/10.5281/zenodo.4739097. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Predicting Molecular Phenotypes from Histopathology Images: A Transcriptome-Wide Expression-Morphology Analysis in Breast Cancer.

Molecular profiling is central in cancer precision medicine but remains costly and is based on tumor average profiles. Morphologic patterns observable in histopathology sections from tumors are determined by the underlying molecular phenotype and therefore have the potential to be exploited for prediction of molecular phenotypes. We report here the first transcriptome-wide expression-morphology (EMO) analysis in breast cancer, where individual deep convolutional neural networks were optimized and validated for prediction of mRNA expression in 17,695 genes from hematoxylin and eosin-stained whole slide images. Predicted expressions in 9,334 (52.75%) genes were significantly associated with RNA sequencing estimates. We also demonstrated successful prediction of an mRNA-based proliferation score with established clinical value. The results were validated in independent internal and external test datasets. Predicted spatial intratumor variabilities in expression were validated through spatial transcriptomics profiling. These results suggest that EMO provides a cost-efficient and scalable approach to predict both tumor average and intratumor spatial expression from histopathology images. SIGNIFICANCE: Transcriptome-wide expression morphology deep learning analysis enables prediction of mRNA expression and proliferation markers from routine histopathology whole slide images in breast cancer.

Artificial Intelligence for Diagnosis and Gleason Grading of Prostate Cancer in Biopsies-Current Status and Next Steps.

Diagnosis and Gleason grading of prostate cancer in biopsies are critical for the clinical management of men with prostate cancer. Despite this, the high grading variability among pathologists leads to the potential for under- and overtreatment. Artificial intelligence (AI) systems have shown promise in assisting pathologists to perform Gleason grading, which could help address this problem. In this mini-review, we highlight studies reporting on the development of AI systems for cancer detection and Gleason grading, and discuss the progress needed for widespread clinical implementation, as well as anticipated future developments. PATIENT SUMMARY: This mini-review summarizes the evidence relating to the validation of artificial intelligence (AI)-assisted cancer detection and Gleason grading of prostate cancer in biopsies, and highlights the remaining steps required prior to its widespread clinical implementation. We found that, although there is strong evidence to show that AI is able to perform Gleason grading on par with experienced uropathologists, more work is needed to ensure the accuracy of results from AI systems in diverse settings across different patient populations, digitization platforms, and pathology laboratories.

Biological and therapeutic implications of a unique subtype of NPM1 mutated AML.

In acute myeloid leukemia (AML), molecular heterogeneity across patients constitutes a major challenge for prognosis and therapy. AML with NPM1 mutation is a distinct genetic entity in the revised World Health Organization classification. However, differing patterns of co-mutation and response to therapy within this group necessitate further stratification. Here we report two distinct subtypes within NPM1 mutated AML patients, which we label as primitive and committed based on the respective presence or absence of a stem cell signature. Using gene expression (RNA-seq), epigenomic (ATAC-seq) and immunophenotyping (CyToF) analysis, we associate each subtype with specific molecular characteristics, disease differentiation state and patient survival. Using ex vivo drug sensitivity profiling, we show a differential drug response of the subtypes to specific kinase inhibitors, irrespective of the FLT3-ITD status. Differential drug responses of the primitive and committed subtype are validated in an independent AML cohort. Our results highlight heterogeneity among NPM1 mutated AML patient samples based on stemness and suggest that the addition of kinase inhibitors to the treatment of cases with the primitive signature, lacking FLT3-ITD, could have therapeutic benefit.

Challenging conventional karyotyping by next-generation karyotyping in 281 intensively treated patients with AML.

Although copy number alterations (CNAs) and translocations constitute the backbone of the diagnosis and prognostication of acute myeloid leukemia (AML), techniques used for their assessment in routine diagnostics have not been reconsidered for decades. We used a combination of 2 next-generation sequencing-based techniques to challenge the currently recommended conventional cytogenetic analysis (CCA), comparing the approaches in a series of 281 intensively treated patients with AML. Shallow whole-genome sequencing (sWGS) outperformed CCA in detecting European Leukemia Net (ELN)-defining CNAs and showed that CCA overestimated monosomies and suboptimally reported karyotype complexity. Still, the concordance between CCA and sWGS for all ELN CNA-related criteria was 94%. Moreover, using in silico dilution, we showed that 1 million reads per patient would be enough to accurately assess ELN-defining CNAs. Total genomic loss, defined as a total loss ≥200 Mb by sWGS, was found to be a better marker for genetic complexity and poor prognosis compared with the CCA-based definition of complex karyotype. For fusion detection, the concordance between CCA and whole-transcriptome sequencing (WTS) was 99%. WTS had better sensitivity in identifying inv(16) and KMT2A rearrangements while showing limitations in detecting lowly expressed PML-RARA fusions. Ligation-dependent reverse transcription polymerase chain reaction was used for validation and was shown to be a fast and reliable method for fusion detection. We conclude that a next-generation sequencing-based approach can replace conventional CCA for karyotyping, provided that efforts are made to cover lowly expressed fusion transcripts.

Integrated transcriptomic and genomic analysis improves prediction of complete remission and survival in elderly patients with acute myeloid leukemia.

Relevant molecular tools for treatment stratification of patients ≥65 years with acute myeloid leukemia (AML) are lacking. We combined clinical data with targeted DNA- and full RNA-sequencing of 182 intensively and palliatively treated patients to predict complete remission (CR) and survival in AML patients ≥65 years. Intensively treated patients with NPM1 and IDH2R172 mutations had longer overall survival (OS), whereas mutated TP53 conferred lower CR rates and shorter OS. FLT3-ITD and TP53 mutations predicted worse OS in palliatively treated patients. Gene expression levels most predictive of CR were combined with somatic mutations for an integrated risk stratification that we externally validated using the beatAML cohort. We defined a high-risk group with a CR rate of 20% in patients with mutated TP53, compared to 97% CR in low-risk patients defined by high expression of ZBTB7A and EEPD1 without TP53 mutations. Patients without these criteria had a CR rate of 54% (intermediate risk). The difference in CR rates translated into significant OS differences that outperformed ELN stratification for OS prediction. The results suggest that an integrated molecular risk stratification can improve prediction of CR and OS and could be used to guide treatment in elderly AML patients.

Artificial intelligence for diagnosis and grading of prostate cancer in biopsies: a population-based, diagnostic study.

BACKGROUND: An increasing volume of prostate biopsies and a worldwide shortage of urological pathologists puts a strain on pathology departments. Additionally, the high intra-observer and inter-observer variability in grading can result in overtreatment and undertreatment of prostate cancer. To alleviate these problems, we aimed to develop an artificial intelligence (AI) system with clinically acceptable accuracy for prostate cancer detection, localisation, and Gleason grading. METHODS: We digitised 6682 slides from needle core biopsies from 976 randomly selected participants aged 50-69 in the Swedish prospective and population-based STHLM3 diagnostic study done between May 28, 2012, and Dec 30, 2014 (ISRCTN84445406), and another 271 from 93 men from outside the study. The resulting images were used to train deep neural networks for assessment of prostate biopsies. The networks were evaluated by predicting the presence, extent, and Gleason grade of malignant tissue for an independent test dataset comprising 1631 biopsies from 246 men from STHLM3 and an external validation dataset of 330 biopsies from 73 men. We also evaluated grading performance on 87 biopsies individually graded by 23 experienced urological pathologists from the International Society of Urological Pathology. We assessed discriminatory performance by receiver operating characteristics and tumour extent predictions by correlating predicted cancer length against measurements by the reporting pathologist. We quantified the concordance between grades assigned by the AI system and the expert urological pathologists using Cohen's kappa. FINDINGS: The AI achieved an area under the receiver operating characteristics curve of 0·997 (95% CI 0·994-0·999) for distinguishing between benign (n=910) and malignant (n=721) biopsy cores on the independent test dataset and 0·986 (0·972-0·996) on the external validation dataset (benign n=108, malignant n=222). The correlation between cancer length predicted by the AI and assigned by the reporting pathologist was 0·96 (95% CI 0·95-0·97) for the independent test dataset and 0·87 (0·84-0·90) for the external validation dataset. For assigning Gleason grades, the AI achieved a mean pairwise kappa of 0·62, which was within the range of the corresponding values for the expert pathologists (0·60-0·73). INTERPRETATION: An AI system can be trained to detect and grade cancer in prostate needle biopsy samples at a ranking comparable to that of international experts in prostate pathology. Clinical application could reduce pathology workload by reducing the assessment of benign biopsies and by automating the task of measuring cancer length in positive biopsy cores. An AI system with expert-level grading performance might contribute a second opinion, aid in standardising grading, and provide pathology expertise in parts of the world where it does not exist. FUNDING: Swedish Research Council, Swedish Cancer Society, Swedish eScience Research Center, EIT Health.

TP53 Outperforms Other Androgen Receptor Biomarkers to Predict Abiraterone or Enzalutamide Outcome in Metastatic Castration-Resistant Prostate Cancer.

PURPOSE: To infer the prognostic value of simultaneous androgen receptor (AR) and TP53 profiling in liquid biopsies from patients with metastatic castration-resistant prostate cancer (mCRPC) starting a new line of AR signaling inhibitors (ARSi).Experimental Design: Between March 2014 and April 2017, we recruited patients with mCRPC (n = 168) prior to ARSi in a cohort study encompassing 10 European centers. Blood samples were collected for comprehensive profiling of CellSearch-enriched circulating tumor cells (CTC) and circulating tumor DNA (ctDNA). Targeted CTC RNA sequencing (RNA-seq) allowed the detection of eight AR splice variants (ARV). Low-pass whole-genome and targeted gene-body sequencing of AR and TP53 was applied to identify amplifications, loss of heterozygosity, mutations, and structural rearrangements in ctDNA. Clinical or radiologic progression-free survival (PFS) was estimated by Kaplan-Meier analysis, and independent associations were determined using multivariable Cox regression models. RESULTS: Overall, no single AR perturbation remained associated with adverse prognosis after multivariable analysis. Instead, tumor burden estimates (CTC counts, ctDNA fraction, and visceral metastases) were significantly associated with PFS. TP53 inactivation harbored independent prognostic value [HR 1.88; 95% confidence interval (CI), 1.18-3.00; P = 0.008], and outperformed ARV expression and detection of genomic AR alterations. Using Cox coefficient analysis of clinical parameters and TP53 status, we identified three prognostic groups with differing PFS estimates (median, 14.7 vs. 7.51 vs. 2.62 months; P < 0.0001), which was validated in an independent mCRPC cohort (n = 202) starting first-line ARSi (median, 14.3 vs. 6.39 vs. 2.23 months; P < 0.0001). CONCLUSIONS: In an all-comer cohort, tumor burden estimates and TP53 outperform any AR perturbation to infer prognosis.See related commentary by Rebello et al., p. 1699.

Cell-free DNA profiling of metastatic prostate cancer reveals microsatellite instability, structural rearrangements and clonal hematopoiesis.

BACKGROUND: There are multiple existing and emerging therapeutic avenues for metastatic prostate cancer, with a common denominator, which is the need for predictive biomarkers. Circulating tumor DNA (ctDNA) has the potential to cost-efficiently accelerate precision medicine trials to improve clinical efficacy and diminish costs and toxicity. However, comprehensive ctDNA profiling in metastatic prostate cancer to date has been limited. METHODS: A combination of targeted and low-pass whole genome sequencing was performed on plasma cell-free DNA and matched white blood cell germline DNA in 364 blood samples from 217 metastatic prostate cancer patients. RESULTS: ctDNA was detected in 85.9% of baseline samples, correlated to line of therapy and was mirrored by circulating tumor cell enumeration of synchronous blood samples. Comprehensive profiling of the androgen receptor (AR) revealed a continuous increase in the fraction of patients with intra-AR structural variation, from 15.4% during first-line metastatic castration-resistant prostate cancer therapy to 45.2% in fourth line, indicating a continuous evolution of AR during the course of the disease. Patients displayed frequent alterations in DNA repair deficiency genes (18.0%). Additionally, the microsatellite instability phenotype was identified in 3.81% of eligible samples (≥ 0.1 ctDNA fraction). Sequencing of non-repetitive intronic and exonic regions of PTEN, RB1, and TP53 detected biallelic inactivation in 47.5%, 20.3%, and 44.1% of samples with ≥ 0.2 ctDNA fraction, respectively. Only one patient carried a clonal high-impact variant without a detectable second hit. Intronic high-impact structural variation was twice as common as exonic mutations in PTEN and RB1. Finally, 14.6% of patients presented false positive variants due to clonal hematopoiesis, commonly ignored in commercially available assays. CONCLUSIONS: ctDNA profiles appear to mirror the genomic landscape of metastatic prostate cancer tissue and may cost-efficiently provide somatic information in clinical trials designed to identify predictive biomarkers. However, intronic sequencing of the interrogated tumor suppressors challenges the ubiquitous focus on coding regions and is vital, together with profiling of synchronous white blood cells, to minimize erroneous assignments which in turn may confound results and impede true associations in clinical trials.

Expression levels of long non-coding RNAs are prognostic for AML outcome.

BACKGROUND: Long non-coding RNA (lncRNA) expression has been implicated in a range of molecular mechanisms that are central in cancer. However, lncRNA expression has not yet been comprehensively characterized in acute myeloid leukemia (AML). Here, we assess to what extent lncRNA expression is prognostic of AML patient overall survival (OS) and determine if there are indications of lncRNA-based molecular subtypes of AML. METHODS: We performed RNA sequencing of 274 intensively treated AML patients in a Swedish cohort and quantified lncRNA expression. Univariate and multivariate time-to-event analysis was applied to determine association between individual lncRNAs with OS. Unsupervised statistical learning was applied to ascertain if lncRNA-based molecular subtypes exist and are prognostic. RESULTS: Thirty-three individual lncRNAs were found to be associated with OS (adjusted p value < 0.05). We established four distinct molecular subtypes based on lncRNA expression using a consensus clustering approach. LncRNA-based subtypes were found to stratify patients into groups with prognostic information (p value < 0.05). Subsequently, lncRNA expression-based subtypes were validated in an independent patient cohort (TCGA-AML). LncRNA subtypes could not be directly explained by any of the recurrent cytogenetic or mutational aberrations, although associations with some of the established genetic and clinical factors were found, including mutations in NPM1, TP53, and FLT3. CONCLUSION: LncRNA expression-based four subtypes, discovered in this study, are reproducible and can effectively stratify AML patients. LncRNA expression profiling can provide valuable information for improved risk stratification of AML patients.

Isoform-level gene expression patterns in single-cell RNA-sequencing data.

Motivation: RNA sequencing of single cells enables characterization of transcriptional heterogeneity in seemingly homogeneous cell populations. Single-cell sequencing has been applied in a wide range of researches fields. However, few studies have focus on characterization of isoform-level expression patterns at the single-cell level. In this study, we propose and apply a novel method, ISOform-Patterns (ISOP), based on mixture modeling, to characterize the expression patterns of isoform pairs from the same gene in single-cell isoform-level expression data. Results: We define six principal patterns of isoform expression relationships and describe a method for differential-pattern analysis. We demonstrate ISOP through analysis of single-cell RNA-sequencing data from a breast cancer cell line, with replication in three independent datasets. We assigned the pattern types to each of 16 562 isoform-pairs from 4929 genes. Among those, 26% of the discovered patterns were significant (P<0.05), while remaining patterns are possibly effects of transcriptional bursting, drop-out and stochastic biological heterogeneity. Furthermore, 32% of genes discovered through differential-pattern analysis were not detected by differential-expression analysis. Finally, the effects of drop-out events and expression levels of isoforms on ISOP's performances were investigated through simulated datasets. To conclude, ISOP provides a novel approach for characterization of isoform-level preference, commitment and heterogeneity in single-cell RNA-sequencing data. Availability and implementation: The ISOP method has been implemented as a R package and is available at https://github.com/nghiavtr/ISOP under a GPL-3 license. Supplementary information: Supplementary data are available at Bioinformatics online.

Development and Validation of a Novel RNA Sequencing-Based Prognostic Score for Acute Myeloid Leukemia.

Background: Recent progress in sequencing technologies allows us to explore comprehensive genomic and transcriptomic information to improve the current European LeukemiaNet (ELN) system of acute myeloid leukemia (AML). Methods: We compared the prognostic value of traditional demographic and cytogenetic risk factors, genomic data in the form of somatic aberrations of 25 AML-relevant genes, and whole-transcriptome expression profiling (RNA sequencing) in 267 intensively treated AML patients (Clinseq-AML). Multivariable penalized Cox models (overall survival [OS]) were developed for each data modality (clinical, genomic, transcriptomic), together with an associated prognostic risk score. Results: Of the three data modalities, transcriptomic data provided the best prognostic value, with an integrated area under the curve (iAUC) of a time-dependent receiver operating characteristic (ROC) curve of 0.73. We developed a prognostic risk score (Clinseq-G) from transcriptomic data, which was validated in the independent The Cancer Genome Atlas AML cohort (RNA sequencing, n = 142, iAUC = 0.73, comparing the high-risk group with the low-risk group, hazard ratio [HR]OS = 2.42, 95% confidence interval [CI] = 1.51 to 3.88). Comparison between Clinseq-G and ELN score iAUC estimates indicated strong evidence in favor of the Clinseq-G model (Bayes factor = 26.78). The proposed model remained statistically significant in multivariable analysis including the ELN and other well-known risk factors (HRos = 2.34, 95% CI = 1.30 to 4.22). We further validated the Clinseq-G model in a second independent data set (n = 458, iAUC = 0.66, adjusted HROS = 2.02, 95% CI = 1.33 to 3.08; adjusted HREFS = 2.10, 95% CI = 1.42 to 3.12). Conclusions: Our results indicate that the Clinseq-G prediction model, based on transcriptomic data from RNA sequencing, outperforms traditional clinical parameters and previously reported models based on genomic biomarkers.

Prognostic value of Ki67 analysed by cytology or histology in primary breast cancer.

AIMS: The accuracy of biomarker assessment in breast pathology is vital for therapy decisions. The therapy predictive and prognostic biomarkers oestrogen receptor (ER), progesterone receptor, HER2 and Ki67 may act as surrogates to gene expression profiling of breast cancer. The aims of this study were to investigate the concordance of consecutive biomarker assessment by immunocytochemistry on preoperative fine-needle aspiration cytology versus immunohistochemistry (IHC) on the corresponding resected breast tumours. Further, to investigate the concordance with molecular subtype and correlation to stage and outcome. METHODS: Two retrospective cohorts comprising 385 breast tumours with clinicopathological data including gene expression-based subtype and up to 10-year overall survival data were evaluated. RESULTS: In both cohorts, we identified a substantial variation in Ki67 index between cytology and histology and a switch between low and high proliferation within the same tumour in 121/360 cases. ER evaluations were discordant in only 1.5% of the tumours. From cohort 2, gene expression data with PAM50 subtype were used to correlate surrogate subtypes. IHC-based surrogate classification could identify the correct molecular subtype in 60% and 64% of patients by cytology (n=63) and surgical resections (n=73), respectively. Furthermore, high Ki67 in surgical resections but not in cytology was associated with poor overall survival and higher probability for axillary lymph node metastasis. CONCLUSIONS: This study shows considerable differences in the prognostic value of Ki67 but not ER in breast cancer depending on the diagnostic method. Furthermore, our findings show that both methods are insufficient in predicting true molecular subtypes.