Breeze: an integrated quality control and data analysis application for high-throughput drug screening.

SUMMARY: High-throughput screening (HTS) enables systematic testing of thousands of chemical compounds for potential use as investigational and therapeutic agents. HTS experiments are often conducted in multi-well plates that inherently bear technical and experimental sources of error. Thus, HTS data processing requires the use of robust quality control procedures before analysis and interpretation. Here, we have implemented an open-source analysis application, Breeze, an integrated quality control and data analysis application for HTS data. Furthermore, Breeze enables a reliable way to identify individual drug sensitivity and resistance patterns in cell lines or patient-derived samples for functional precision medicine applications. The Breeze application provides a complete solution for data quality assessment, dose-response curve fitting and quantification of the drug responses along with interactive visualization of the results. AVAILABILITY AND IMPLEMENTATION: The Breeze application with video tutorial and technical documentation is accessible at https://breeze.fimm.fi; the R source code is publicly available at https://github.com/potdarswapnil/Breeze under GNU General Public License v3.0. CONTACT: swapnil.potdar@helsinki.fi. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

JAK1/2 and BCL2 inhibitors synergize to counteract bone marrow stromal cell-induced protection of AML.

The bone marrow (BM) provides a protective microenvironment to support the survival of leukemic cells and influence their response to therapeutic agents. In acute myeloid leukemia (AML), the high rate of relapse may in part be a result of the inability of current treatment to effectively overcome the protective influence of the BM niche. To better understand the effect of the BM microenvironment on drug responses in AML, we conducted a comprehensive evaluation of 304 inhibitors, including approved and investigational agents, comparing ex vivo responses of primary AML cells in BM stroma-derived and standard culture conditions. In the stroma-based conditions, the AML patient cells exhibited significantly reduced sensitivity to 12% of the tested compounds, including topoisomerase II, B-cell chronic lymphocytic leukemia/lymphoma 2 (BCL2), and many tyrosine kinase inhibitors (TKIs). The loss of TKI sensitivity was most pronounced in patient samples harboring FLT3 or PDGFRB alterations. In contrast, the stroma-derived conditions enhanced sensitivity to Janus kinase (JAK) inhibitors. Increased cell viability and resistance to specific drug classes in the BM stroma-derived conditions was a result of activation of alternative signaling pathways mediated by factors secreted by BM stromal cells and involved a switch from BCL2 to BCLXL-dependent cell survival. Moreover, the JAK1/2 inhibitor ruxolitinib restored sensitivity to the BCL2 inhibitor venetoclax in AML patient cells ex vivo in different model systems and in vivo in an AML xenograft mouse model. These findings highlight the potential of JAK inhibitors to counteract stroma-induced resistance to BCL2 inhibitors in AML.

Serum Biomarkers of Allergic Contact Dermatitis: A Pilot Study.

BACKGROUND: Allergic contact dermatitis (ACD) is an inflammatory skin disease caused by repeated skin exposure to contact allergens. The goal of this pilot study was to identify inflammatory proteins which can serve as biomarkers for ACD. METHODS: We measured levels of 102 cytokines, chemokines, and growth factors in the sera of 16 ACD patients during acute and remission phases, and 16 healthy volunteers. RESULTS: Serum levels of adiponectin, chemokine (C-C motif) ligand 5 (CCL5), C-reactive protein (CRP), chitinase 3-like 1 (CHI3L1), complement factor D (CFD), endoglin, lipocalin-2, osteopontin, retinol-binding protein 4 (RBP4), and platelet factor 4 (PF4) were significantly higher, whereas levels of trefoil factor 3 (TFF3) were significantly lower, in ACD patients than in healthy controls. In ACD patients, serum levels of CCL5 were elevated, whereas levels of TFF3, soluble intercellular adhesion molecule-1 (sICAM-1), and platelet-derived growth factor (PDGF)-AB/BB were found to be lower during the remission phase of the disease. CONCLUSIONS: Serum levels of adiponectin, CCL5, CRP, CHI3L1, CFD, endoglin, lipocalin-2, osteopontin, RBP4, PF4, and TFF3 might be exploited as biomarkers for ACD, whereas levels of CCL5, TFF3, sICAM-1, and PDGF-AB/BB might be exploited for evaluation of disease progression and efficacy of ACD treatment.

Akt inhibitor MK2206 prevents influenza pH1N1 virus infection in vitro.

The influenza pH1N1 virus caused a global flu pandemic in 2009 and continues manifestation as a seasonal virus. Better understanding of the virus-host cell interaction could result in development of better prevention and treatment options. Here we show that the Akt inhibitor MK2206 blocks influenza pH1N1 virus infection in vitro. In particular, at noncytotoxic concentrations, MK2206 alters Akt signaling and inhibits endocytic uptake of the virus. Interestingly, MK2206 is unable to inhibit H3N2, H7N9, and H5N1 viruses, indicating that pH1N1 evolved specific requirements for efficient infection. Thus, Akt signaling could be exploited further for development of better therapeutics against pH1N1 virus.

A deep convolutional neural network for efficient microglia detection.

Microglial cells are a type of glial cells that make up 10-15% of all brain cells, and they play a significant role in neurodegenerative disorders and cardiovascular diseases. Despite their vital role in these diseases, developing fully automated microglia counting methods from immunohistological images is challenging. Current image analysis methods are inefficient and lack accuracy in detecting microglia due to their morphological heterogeneity. This study presents development and validation of a fully automated and efficient microglia detection method using the YOLOv3 deep learning-based algorithm. We applied this method to analyse the number of microglia in different spinal cord and brain regions of rats exposed to opioid-induced hyperalgesia/tolerance. Our numerical tests showed that the proposed method outperforms existing computational and manual methods with high accuracy, achieving 94% precision, 91% recall, and 92% F1-score. Furthermore, our tool is freely available and adds value to exploring different disease models. Our findings demonstrate the effectiveness and efficiency of our new tool in automated microglia detection, providing a valuable asset for researchers in neuroscience.

Outcome and Biomarker Supervised Deep Learning for Survival Prediction in Two Multicenter Breast Cancer Series.

BACKGROUND: Prediction of clinical outcomes for individual cancer patients is an important step in the disease diagnosis and subsequently guides the treatment and patient counseling. In this work, we develop and evaluate a joint outcome and biomarker supervised (estrogen receptor expression and ERBB2 expression and gene amplification) multitask deep learning model for prediction of outcome in breast cancer patients in two nation-wide multicenter studies in Finland (the FinProg and FinHer studies). Our approach combines deep learning with expert knowledge to provide more accurate, robust, and integrated prediction of breast cancer outcomes. MATERIALS AND METHODS: Using deep learning, we trained convolutional neural networks (CNNs) with digitized tissue microarray (TMA) samples of primary hematoxylin-eosin-stained breast cancer specimens from 693 patients in the FinProg series as input and breast cancer-specific survival as the endpoint. The trained algorithms were tested on 354 TMA patient samples in the same series. An independent set of whole-slide (WS) tumor samples from 674 patients in another multicenter study (FinHer) was used to validate and verify the generalization of the outcome prediction based on CNN models by Cox survival regression and concordance index (c-index). Visual cancer tissue characterization, i.e., number of mitoses, tubules, nuclear pleomorphism, tumor-infiltrating lymphocytes, and necrosis was performed on TMA samples in the FinProg test set by a pathologist and combined with deep learning-based outcome prediction in a multitask algorithm. RESULTS: The multitask algorithm achieved a hazard ratio (HR) of 2.0 (95% confidence interval [CI] 1.30-3.00), P < 0.001, c-index of 0.59 on the 354 test set of FinProg patients, and an HR of 1.7 (95% CI 1.2-2.6), P = 0.003, c-index 0.57 on the WS tumor samples from 674 patients in the independent FinHer series. The multitask CNN remained a statistically independent predictor of survival in both test sets when adjusted for histological grade, tumor size, and axillary lymph node status in a multivariate Cox analyses. An improved accuracy (c-index 0.66) was achieved when deep learning was combined with the tissue characteristics assessed visually by a pathologist. CONCLUSIONS: A multitask deep learning algorithm supervised by both patient outcome and biomarker status learned features in basic tissue morphology predictive of survival in a nationwide, multicenter series of patients with breast cancer. The algorithms generalized to another independent multicenter patient series and whole-slide breast cancer samples and provide prognostic information complementary to that of a comprehensive series of established prognostic factors.

Antibody Supervised Training of a Deep Learning Based Algorithm for Leukocyte Segmentation in Papillary Thyroid Carcinoma.

The quantity of leukocytes in papillary thyroid carcinoma (PTC) potentially have prognostic and treatment predictive value. Here, we propose a novel method for training a convolutional neural network (CNN) algorithm for segmenting leukocytes in PTCs. Tissue samples from two retrospective PTC cohort were obtained and representative tissue slides from twelve patients were stained with hematoxylin and eosin (HE) and digitized. Then, the HE slides were destained and restained immunohistochemically (IHC) with antibodies to the pan-leukocyte anti CD45 antigen and scanned again. The two stain-pairs of all representative tissue slides were registered, and image tiles of regions of interests were exported. The image tiles were processed and the 3,3'-diaminobenzidine (DAB) stained areas representing anti CD45 expression were turned into binary masks. These binary masks were applied as annotations on the HE image tiles and used in the training of a CNN algorithm. Ten whole slide images (WSIs) were used for training using a five-fold cross-validation and the remaining two slides were used as an independent test set for the trained model. For visual evaluation, the algorithm was run on all twelve WSIs, and in total 238,144 tiles sized 500 × 500 pixels were analyzed. The trained CNN algorithm had an intersection over union of 0.82 for detection of leukocytes in the HE image tiles when comparing the prediction masks to the ground truth anti CD45 mask. We conclude that this method for generating antibody supervised annotations using the destain-restain IHC guided annotations resulted in high accuracy segmentations of leukocytes in HE tissue images.

Deep learning identifies morphological features in breast cancer predictive of cancer ERBB2 status and trastuzumab treatment efficacy.

The treatment of patients with ERBB2 (HER2)-positive breast cancer with anti-ERBB2 therapy is based on the detection of ERBB2 gene amplification or protein overexpression. Machine learning (ML) algorithms can predict the amplification of ERBB2 based on tumor morphological features, but it is not known whether ML-derived features can predict survival and efficacy of anti-ERBB2 treatment. In this study, we trained a deep learning model with digital images of hematoxylin-eosin (H&E)-stained formalin-fixed primary breast tumor tissue sections, weakly supervised by ERBB2 gene amplification status. The gene amplification was determined by chromogenic in situ hybridization (CISH). The training data comprised digitized tissue microarray (TMA) samples from 1,047 patients. The correlation between the deep learning-predicted ERBB2 status, which we call H&E-ERBB2 score, and distant disease-free survival (DDFS) was investigated on a fully independent test set, which included whole-slide tumor images from 712 patients with trastuzumab treatment status available. The area under the receiver operating characteristic curve (AUC) in predicting gene amplification in the test sets was 0.70 (95% CI, 0.63-0.77) on 354 TMA samples and 0.67 (95% CI, 0.62-0.71) on 712 whole-slide images. Among patients with ERBB2-positive cancer treated with trastuzumab, those with a higher than the median morphology-based H&E-ERBB2 score derived from machine learning had more favorable DDFS than those with a lower score (hazard ratio [HR] 0.37; 95% CI, 0.15-0.93; P = 0.034). A high H&E-ERBB2 score was associated with unfavorable survival in patients with ERBB2-negative cancer as determined by CISH. ERBB2-associated morphology correlated with the efficacy of adjuvant anti-ERBB2 treatment and can contribute to treatment-predictive information in breast cancer.

Deep learning based tissue analysis predicts outcome in colorectal cancer.

Image-based machine learning and deep learning in particular has recently shown expert-level accuracy in medical image classification. In this study, we combine convolutional and recurrent architectures to train a deep network to predict colorectal cancer outcome based on images of tumour tissue samples. The novelty of our approach is that we directly predict patient outcome, without any intermediate tissue classification. We evaluate a set of digitized haematoxylin-eosin-stained tumour tissue microarray (TMA) samples from 420 colorectal cancer patients with clinicopathological and outcome data available. The results show that deep learning-based outcome prediction with only small tissue areas as input outperforms (hazard ratio 2.3; CI 95% 1.79-3.03; AUC 0.69) visual histological assessment performed by human experts on both TMA spot (HR 1.67; CI 95% 1.28-2.19; AUC 0.58) and whole-slide level (HR 1.65; CI 95% 1.30-2.15; AUC 0.57) in the stratification into low- and high-risk patients. Our results suggest that state-of-the-art deep learning techniques can extract more prognostic information from the tissue morphology of colorectal cancer than an experienced human observer.

Systems pathology by multiplexed immunohistochemistry and whole-slide digital image analysis.

The paradigm of molecular histopathology is shifting from a single-marker immunohistochemistry towards multiplexed detection of markers to better understand the complex pathological processes. However, there are no systems allowing multiplexed IHC (mIHC) with high-resolution whole-slide tissue imaging and analysis, yet providing feasible throughput for routine use. We present an mIHC platform combining fluorescent and chromogenic staining with automated whole-slide imaging and integrated whole-slide image analysis, enabling simultaneous detection of six protein markers and nuclei, and automatic quantification and classification of hundreds of thousands of cells in situ in formalin-fixed paraffin-embedded tissues. In the first proof-of-concept, we detected immune cells at cell-level resolution (n = 128,894 cells) in human prostate cancer, and analysed T cell subpopulations in different tumour compartments (epithelium vs. stroma). In the second proof-of-concept, we demonstrated an automatic classification of epithelial cell populations (n = 83,558) and glands (benign vs. cancer) in prostate cancer with simultaneous analysis of androgen receptor (AR) and alpha-methylacyl-CoA (AMACR) expression at cell-level resolution. We conclude that the open-source combination of 8-plex mIHC detection, whole-slide image acquisition and analysis provides a robust tool allowing quantitative, spatially resolved whole-slide tissue cytometry directly in formalin-fixed human tumour tissues for improved characterization of histology and the tumour microenvironment.

Genome-Wide Analysis of Evolutionary Markers of Human Influenza A(H1N1)pdm09 and A(H3N2) Viruses May Guide Selection of Vaccine Strain Candidates.

Here we analyzed whole-genome sequences of 3,969 influenza A(H1N1)pdm09 and 4,774 A(H3N2) strains that circulated during 2009-2015 in the world. The analysis revealed changes at 481 and 533 amino acid sites in proteins of influenza A(H1N1)pdm09 and A(H3N2) strains, respectively. Many of these changes were introduced as a result of random drift. However, there were 61 and 68 changes that were present in relatively large number of A(H1N1)pdm09 and A(H3N2) strains, respectively, that circulated during relatively long time. We named these amino acid substitutions evolutionary markers, as they seemed to contain valuable information regarding the viral evolution. Interestingly, influenza A(H1N1)pdm09 and A(H3N2) viruses acquired non-overlapping sets of evolutionary markers. We next analyzed these characteristic markers in vaccine strains recommended by the World Health Organization for the past five years. Our analysis revealed that vaccine strains carried only few evolutionary markers at antigenic sites of viral hemagglutinin (HA) and neuraminidase (NA). The absence of these markers at antigenic sites could affect the recognition of HA and NA by human antibodies generated in response to vaccinations. This could, in part, explain moderate efficacy of influenza vaccines during 2009-2014. Finally, we identified influenza A(H1N1)pdm09 and A(H3N2) strains, which contain all the evolutionary markers of influenza A strains circulated in 2015, and which could be used as vaccine candidates for the 2015/2016 season. Thus, genome-wide analysis of evolutionary markers of influenza A(H1N1)pdm09 and A(H3N2) viruses may guide selection of vaccine strain candidates.

Comparative Analysis of Whole-Genome Sequences of Influenza A(H1N1)pdm09 Viruses Isolated from Hospitalized and Nonhospitalized Patients Identifies Missense Mutations That Might Be Associated with Patient Hospital Admissions in Finland during 2009 to 2014.

Here, we report 40 new whole-genome sequences of influenza A(H1N1)pdm09 viruses isolated from Finnish patients during 2009 to 2014. A preliminary analysis of these and 186 other whole genomes of influenza A(H1N1)pdm09 viruses isolated from hospitalized and nonhospitalized patients during 2009 to 2014 in Finland revealed several viral mutations that might be associated with patient hospitalizations.

Genetic Instability of Influenza pH1N1 Viruses.

Here, we report full-length genome sequences of influenza pH1N1 viruses obtained prior to and after propagation in MDCK cells. Paired comparisons of the genomes showed that each strain acquired 1.0 to 18.8 mutations per genome per replication cycle, which corresponds to 0.5 to 5.8 mutations per virus proteome per replication cycle. Our analysis indicates that pH1N1 viruses accumulated adaptive mutations among others in response to propagation in cell culture. These results could be important for vaccine and drug-sensitivity surveillance studies, as well as for vaccine and antiviral drug development programs where cell cultures are used for influenza propagation.

Influenza pH1N1 Virus Accumulated H275Y Mutation in Neuraminidase during Propagation in MDCK Cells.

Here, we sequenced the genome of the influenza A/Finland/741 M/2014(H1N1) virus and found that the virus accumulated oseltamivir resistance mutation H275Y in its neuraminidase during propagation in cell culture. This indicates that propagation in cell culture modifies virus genomes. The instability of influenza genomes should be taken into consideration during drug-sensitivity studies.