Inhibition of MYC translation through targeting of the newly identified PHB-eIF4F complex as a therapeutic strategy in CLL.

Dysregulation of messenger RNA (mRNA) translation, including preferential translation of mRNA with complex 5' untranslated regions such as the MYC oncogene, is recognized as an important mechanism in cancer. Here, we show that both human and murine chronic lymphocytic leukemia (CLL) cells display a high translation rate, which is inhibited by the synthetic flavagline FL3, a prohibitin (PHB)-binding drug. A multiomics analysis performed in samples from patients with CLL and cell lines treated with FL3 revealed the decreased translation of the MYC oncogene and of proteins involved in cell cycle and metabolism. Furthermore, inhibiting translation induced a proliferation arrest and a rewiring of MYC-driven metabolism. Interestingly, contrary to other models, the RAS-RAF-(PHBs)-MAPK pathway is neither impaired by FL3 nor implicated in translation regulation in CLL cells. Here, we rather show that PHBs are directly associated with the eukaryotic initiation factor (eIF)4F translation complex and are targeted by FL3. Knockdown of PHBs resembled FL3 treatment. Importantly, inhibition of translation controlled CLL development in vivo, either alone or combined with immunotherapy. Finally, high expression of translation initiation-related genes and PHBs genes correlated with poor survival and unfavorable clinical parameters in patients with CLL. Overall, we demonstrated that translation inhibition is a valuable strategy to control CLL development by blocking the translation of several oncogenic pathways including MYC. We also unraveled a new and direct role of PHBs in translation initiation, thus creating new therapeutic opportunities for patients with CLL.

PARK7/DJ-1 deficiency impairs microglial activation in response to LPS-induced inflammation.

BACKGROUND: Specific microglia responses are thought to contribute to the development and progression of neurodegenerative diseases, including Parkinson's disease (PD). However, the phenotypic acquisition of microglial cells and their role during the underlying neuroinflammatory processes remain largely elusive. Here, according to the multiple-hit hypothesis, which stipulates that PD etiology is determined by a combination of genetics and various environmental risk factors, we investigate microglial transcriptional programs and morphological adaptations under PARK7/DJ-1 deficiency, a genetic cause of PD, during lipopolysaccharide (LPS)-induced inflammation. METHODS: Using a combination of single-cell RNA-sequencing, bulk RNA-sequencing, multicolor flow cytometry and immunofluorescence analyses, we comprehensively compared microglial cell phenotypic characteristics in PARK7/DJ-1 knock-out (KO) with wildtype littermate mice following 6- or 24-h intraperitoneal injection with LPS. For translational perspectives, we conducted corresponding analyses in human PARK7/DJ-1 mutant induced pluripotent stem cell (iPSC)-derived microglia and murine bone marrow-derived macrophages (BMDMs). RESULTS: By excluding the contribution of other immune brain resident and peripheral cells, we show that microglia acutely isolated from PARK7/DJ-1 KO mice display a distinct phenotype, specially related to type II interferon and DNA damage response signaling, when compared with wildtype microglia, in response to LPS. We also detected discrete signatures in human PARK7/DJ-1 mutant iPSC-derived microglia and BMDMs from PARK7/DJ-1 KO mice. These specific transcriptional signatures were reflected at the morphological level, with microglia in LPS-treated PARK7/DJ-1 KO mice showing a less amoeboid cell shape compared to wildtype mice, both at 6 and 24 h after acute inflammation, as also observed in BMDMs. CONCLUSIONS: Taken together, our results show that, under inflammatory conditions, PARK7/DJ-1 deficiency skews microglia towards a distinct phenotype characterized by downregulation of genes involved in type II interferon signaling and a less prominent amoeboid morphology compared to wildtype microglia. These findings suggest that the underlying oxidative stress associated with the lack of PARK7/DJ-1 affects microglia neuroinflammatory responses, which may play a causative role in PD onset and progression.

AllergoOncology: Biomarkers and refined classification for research in the allergy and glioma nexus-A joint EAACI-EANO position paper.

Epidemiological studies have explored the relationship between allergic diseases and cancer risk or prognosis in AllergoOncology. Some studies suggest an inverse association, but uncertainties remain, including in IgE-mediated diseases and glioma. Allergic disease stems from a Th2-biased immune response to allergens in predisposed atopic individuals. Allergic disorders vary in phenotype, genotype and endotype, affecting their pathophysiology. Beyond clinical manifestation and commonly used clinical markers, there is ongoing research to identify novel biomarkers for allergy diagnosis, monitoring, severity assessment and treatment. Gliomas, the most common and diverse brain tumours, have in parallel undergone changes in classification over time, with specific molecular biomarkers defining glioma subtypes. Gliomas exhibit a complex tumour-immune interphase and distinct immune microenvironment features. Immunotherapy and targeted therapy hold promise for primary brain tumour treatment, but require more specific and effective approaches. Animal studies indicate allergic airway inflammation may delay glioma progression. This collaborative European Academy of Allergy and Clinical Immunology (EAACI) and European Association of Neuro-Oncology (EANO) Position Paper summarizes recent advances and emerging biomarkers for refined allergy and adult-type diffuse glioma classification to inform future epidemiological and clinical studies. Future research is needed to enhance our understanding of immune-glioma interactions to ultimately improve patient prognosis and survival.

BIODICA: a computational environment for Independent Component Analysis of omics data.

SUMMARY: We developed BIODICA, an integrated computational environment for application of independent component analysis (ICA) to bulk and single-cell molecular profiles, interpretation of the results in terms of biological functions and correlation with metadata. The computational core is the novel Python package stabilized-ica which provides interface to several ICA algorithms, a stabilization procedure, meta-analysis and component interpretation tools. BIODICA is equipped with a user-friendly graphical user interface, allowing non-experienced users to perform the ICA-based omics data analysis. The results are provided in interactive ways, thus facilitating communication with biology experts. AVAILABILITY AND IMPLEMENTATION: BIODICA is implemented in Java, Python and JavaScript. The source code is freely available on GitHub under the MIT and the GNU LGPL licenses. BIODICA is supported on all major operating systems. URL: https://sysbio-curie.github.io/biodica-environment/.

Allergic airway inflammation delays glioblastoma progression and reinvigorates systemic and local immunity in mice.

BACKGROUND: Numerous patient-based studies have highlighted the protective role of immunoglobulin E-mediated allergic diseases on glioblastoma (GBM) susceptibility and prognosis. However, the mechanisms behind this observation remain elusive. Our objective was to establish a preclinical model able to recapitulate this phenomenon and investigate the role of immunity underlying such protection. METHODS: An immunocompetent mouse model of allergic airway inflammation (AAI) was initiated before intracranial implantation of mouse GBM cells (GL261). RAG1-KO mice served to assess tumor growth in a model deficient for adaptive immunity. Tumor development was monitored by MRI. Microglia were isolated for functional analyses and RNA-sequencing. Peripheral as well as tumor-associated immune cells were characterized by flow cytometry. The impact of allergy-related microglial genes on patient survival was analyzed by Cox regression using publicly available datasets. RESULTS: We found that allergy establishment in mice delayed tumor engraftment in the brain and reduced tumor growth resulting in increased mouse survival. AAI induced a transcriptional reprogramming of microglia towards a pro-inflammatory-like state, uncovering a microglia gene signature, which correlated with limited local immunosuppression in glioma patients. AAI increased effector memory T-cells in the circulation as well as tumor-infiltrating CD4+ T-cells. The survival benefit conferred by AAI was lost in mice devoid of adaptive immunity. CONCLUSION: Our results demonstrate that AAI limits both tumor take and progression in mice, providing a preclinical model to study the impact of allergy on GBM susceptibility and prognosis, respectively. We identify a potentiation of local and adaptive systemic immunity, suggesting a reciprocal crosstalk that orchestrates allergy-induced immune protection against GBM.

XAB2 promotes Ku eviction from single-ended DNA double-strand breaks independently of the ATM kinase.

Replication-associated single-ended DNA double-strand breaks (seDSBs) are repaired predominantly through RAD51-mediated homologous recombination (HR). Removal of the non-homologous end-joining (NHEJ) factor Ku from resected seDSB ends is crucial for HR. The coordinated actions of MRE11-CtIP nuclease activities orchestrated by ATM define one pathway for Ku eviction. Here, we identify the pre-mRNA splicing protein XAB2 as a factor required for resistance to seDSBs induced by the chemotherapeutic alkylator temozolomide. Moreover, we show that XAB2 prevents Ku retention and abortive HR at seDSBs induced by temozolomide and camptothecin, via a pathway that operates in parallel to the ATM-CtIP-MRE11 axis. Although XAB2 depletion preserved RAD51 focus formation, the resulting RAD51-ssDNA associations were unproductive, leading to increased NHEJ engagement in S/G2 and genetic instability. Overexpression of RAD51 or RAD52 rescued the XAB2 defects and XAB2 loss was synthetically lethal with RAD52 inhibition, providing potential perspectives in cancer therapy.

Impact of IDH Mutations, the 1p/19q Co-Deletion and the G-CIMP Status on Alternative Splicing in Diffuse Gliomas.

By generating protein diversity, alternative splicing provides an important oncogenic pathway. Isocitrate dehydrogenase (IDH) 1 and 2 mutations and 1p/19q co-deletion have become crucial for the novel molecular classification of diffuse gliomas, which also incorporates DNA methylation profiling. In this study, we have carried out a bioinformatics analysis to examine the impact of the IDH mutation, as well as the 1p/19q co-deletion and the glioma CpG island methylator phenotype (G-CIMP) status on alternative splicing in a cohort of 662 diffuse gliomas from The Cancer Genome Atlas (TCGA). We identify the biological processes and molecular functions affected by alternative splicing in the various glioma subgroups and provide evidence supporting the important contribution of alternative splicing in modulating epigenetic regulation in diffuse gliomas. Targeting the genes and pathways affected by alternative splicing might provide novel therapeutic opportunities against gliomas.

Patient-derived organoids and orthotopic xenografts of primary and recurrent gliomas represent relevant patient avatars for precision oncology.

Patient-based cancer models are essential tools for studying tumor biology and for the assessment of drug responses in a translational context. We report the establishment a large cohort of unique organoids and patient-derived orthotopic xenografts (PDOX) of various glioma subtypes, including gliomas with mutations in IDH1, and paired longitudinal PDOX from primary and recurrent tumors of the same patient. We show that glioma PDOXs enable long-term propagation of patient tumors and represent clinically relevant patient avatars that retain histopathological, genetic, epigenetic, and transcriptomic features of parental tumors. We find no evidence of mouse-specific clonal evolution in glioma PDOXs. Our cohort captures individual molecular genotypes for precision medicine including mutations in IDH1, ATRX, TP53, MDM2/4, amplification of EGFR, PDGFRA, MET, CDK4/6, MDM2/4, and deletion of CDKN2A/B, PTCH, and PTEN. Matched longitudinal PDOX recapitulate the limited genetic evolution of gliomas observed in patients following treatment. At the histological level, we observe increased vascularization in the rat host as compared to mice. PDOX-derived standardized glioma organoids are amenable to high-throughput drug screens that can be validated in mice. We show clinically relevant responses to temozolomide (TMZ) and to targeted treatments, such as EGFR and CDK4/6 inhibitors in (epi)genetically defined subgroups, according to MGMT promoter and EGFR/CDK status, respectively. Dianhydrogalactitol (VAL-083), a promising bifunctional alkylating agent in the current clinical trial, displayed high therapeutic efficacy, and was able to overcome TMZ resistance in glioblastoma. Our work underscores the clinical relevance of glioma organoids and PDOX models for translational research and personalized treatment studies and represents a unique publicly available resource for precision oncology.

Independent Component Analysis for Unraveling the Complexity of Cancer Omics Datasets.

Independent component analysis (ICA) is a matrix factorization approach where the signals captured by each individual matrix factors are optimized to become as mutually independent as possible. Initially suggested for solving source blind separation problems in various fields, ICA was shown to be successful in analyzing functional magnetic resonance imaging (fMRI) and other types of biomedical data. In the last twenty years, ICA became a part of the standard machine learning toolbox, together with other matrix factorization methods such as principal component analysis (PCA) and non-negative matrix factorization (NMF). Here, we review a number of recent works where ICA was shown to be a useful tool for unraveling the complexity of cancer biology from the analysis of different types of omics data, mainly collected for tumoral samples. Such works highlight the use of ICA in dimensionality reduction, deconvolution, data pre-processing, meta-analysis, and others applied to different data types (transcriptome, methylome, proteome, single-cell data). We particularly focus on the technical aspects of ICA application in omics studies such as using different protocols, determining the optimal number of components, assessing and improving reproducibility of the ICA results, and comparison with other popular matrix factorization techniques. We discuss the emerging ICA applications to the integrative analysis of multi-level omics datasets and introduce a conceptual view on ICA as a tool for defining functional subsystems of a complex biological system and their interactions under various conditions. Our review is accompanied by a Jupyter notebook which illustrates the discussed concepts and provides a practical tool for applying ICA to the analysis of cancer omics datasets.

Crosstalk between different family members: IL27 recapitulates IFNγ responses in HCC cells, but is inhibited by IL6-type cytokines.

Interleukin-27 (IL27) is a type-I-cytokine of the IL6/IL12 family predominantly secreted by activated macrophages and dendritic cells. In the liver, IL27 expression was observed to be upregulated in patients with hepatitis B, and sera of hepatocellular carcinoma (HCC) patients contain significantly elevated levels of IL27 compared to healthy controls or patients with hepatitis and/or liver cirrhosis. In this study, we show that IL27 induces STAT1 and STAT3 phosphorylation in 5 HCC lines and 3 different types of non-transformed liver cells. We were especially interested in the relevance of the IL27-induced STAT3 activation in liver cells. Thus, we compared the IL27 responses with those induced by IFNγ (STAT1-dominated response) or IL6-type cytokines (IL6, hyper-IL6 (hy-IL6) or OSM) (STAT3-dominated response) by microarray analysis and find that in HCC cells, IL27 induces an IFNγ-like, STAT1-dependent transcriptional response, but we do not find an effective STAT3-dependent response. Validation experiments corroborate the finding from the microarray evaluation. Interestingly, the availability of STAT1 seems critical in the shaping of the IL27 response, as the siRNA knock-down of STAT1 revealed the ability of IL27 to induce the acute-phase protein γ-fibrinogen, a typical IL6 family characteristic. Moreover, we describe a crosstalk between the signaling of IL6-type cytokines and IL27: responses to the gp130-engaging cytokine IL27 (but not those to IFNs) can be inhibited by IL6-type cytokine pre-stimulation, likely by a SOCS3-mediated mechanism. Thus, IL27 recapitulates IFNγ responses in liver cells, but differs from IFNγ by its sensitivity to SOCS3 inhibition.

Transcriptional variations in the wider peritumoral tissue environment of pancreatic cancer.

Transcriptional profiling was performed on 452 RNA preparations isolated from various types of pancreatic tissue from tumour patients and healthy donors, with a particular focus on peritumoral samples. Pancreatic ductal adenocarcinomas (PDAC) and cystic tumours were most different in these non-tumorous tissues surrounding them, whereas the actual tumours exhibited rather similar transcript patterns. The environment of cystic tumours was transcriptionally nearly identical to normal pancreas tissue. In contrast, the tissue around PDAC behaved a lot like the tumour, indicating some kind of field defect, while showing far less molecular resemblance to both chronic pancreatitis and healthy tissue. This suggests that the major pathogenic difference between cystic and ductal tumours may be due to their cellular environment rather than the few variations between the tumours. Lack of correlation between DNA methylation and transcript levels makes it unlikely that the observed field defect in the peritumoral tissue of PDAC is controlled to a large extent by such epigenetic regulation. Functionally, a strikingly large number of autophagy-related transcripts was changed in both PDAC and its peritumoral tissue, but not in other pancreatic tumours. A transcription signature of 15 autophagy-related genes was established that permits a prognosis of survival with high accuracy and indicates the role of autophagy in tumour biology.

Identification of beta-arrestin-1 as a diagnostic biomarker in lung cancer.

BACKGROUND: Distinguishing lung adenocarcinoma (ADC) from squamous cell carcinoma (SCC) has a tremendous therapeutic implication. Sometimes, the commonly used immunohistochemistry (IHC) markers fail to discriminate between them, urging for the identification of new diagnostic biomarkers. METHODS: We performed IHC on tissue microarrays from two cohorts of lung cancer patients to analyse the expression of beta-arrestin-1, beta-arrestin-2 and clinically used diagnostic markers in ADC and SCC samples. Logistic regression models were applied for tumour subtype prediction. Parallel reaction monitoring (PRM)-based mass spectrometry was used to quantify beta-arrestin-1 in plasma from cancer patients and healthy donors. RESULTS: Beta-arrestin-1 expression was significantly higher in ADC versus SCC samples. Beta-arrestin-1 displayed high sensitivity, specificity and negative predictive value. Its usefulness in an IHC panel was also shown. Plasma beta-arrestin-1 levels were considerably higher in lung cancer patients than in healthy donors and were higher in patients who later experienced a progressive disease than in patients showing complete/partial response following EGFR inhibitor therapy. CONCLUSIONS: Our data identify beta-arrestin-1 as a diagnostic marker to differentiate ADC from SCC and indicate its potential as a plasma biomarker for non-invasive diagnosis of lung cancer. Its utility to predict response to EGFR inhibitors is yet to be confirmed.

RNA sequencing and transcriptome arrays analyses show opposing results for alternative splicing in patient derived samples.

BACKGROUND: RNA sequencing (RNA-seq) and microarrays are two transcriptomics techniques aimed at the quantification of transcribed genes and their isoforms. Here we compare the latest Affymetrix HTA 2.0 microarray with Illumina 2000 RNA-seq for the analysis of patient samples - normal lung epithelium tissue and squamous cell carcinoma lung tumours. Protein coding mRNAs and long non-coding RNAs (lncRNAs) were included in the study. RESULTS: Both platforms performed equally well for protein-coding RNAs, however the stochastic variability was higher for the sequencing data than for microarrays. This reduced the number of differentially expressed genes and genes with predictive potential for RNA-seq compared to microarray data. Analysis of this variability revealed a lack of reads for short and low abundant genes; lncRNAs, being shorter and less abundant RNAs, were found especially susceptible to this issue. A major difference between the two platforms was uncovered by analysis of alternatively spliced genes. Investigation of differential exon abundance showed insufficient reads for many exons and exon junctions in RNA-seq while the detection on the array platform was more stable. Nevertheless, we identified 207 genes which undergo alternative splicing and were consistently detected by both techniques. CONCLUSIONS: Despite the fact that the results of gene expression analysis were highly consistent between Human Transcriptome Arrays and RNA-seq platforms, the analysis of alternative splicing produced discordant results. We concluded that modern microarrays can still outperform sequencing for standard analysis of gene expression in terms of reproducibility and cost.

Constitutive activation of oncogenic PDGFRα-mutant proteins occurring in GIST patients induces receptor mislocalisation and alters PDGFRα signalling characteristics.

BACKGROUND: Gastrointestinal stromal tumours (GIST) are mainly characterised by the presence of activating mutations in either of the two receptor tyrosine kinases c-KIT or platelet-derived growth factor receptor-α (PDGFRα). Most mechanistic studies dealing with GIST mutations have focused on c-KIT and far less is known about the signalling characteristics of the mutated PDGFRα proteins. Here, we study the signalling capacities and corresponding transcriptional responses of the different PDGFRα proteins under comparable genomic conditions. RESULTS: We demonstrate that the constitutive signalling via the oncogenic PDGFRα mutants favours a mislocalisation of the receptors and that this modifies the signalling characteristics of the mutated receptors. We show that signalling via the oncogenic PDGFRα mutants is not solely characterised by a constitutive activation of the conventional PDGFRα signalling pathways. In contrast to wild-type PDGFRα signal transduction, the activation of STAT factors (STAT1, STAT3 and STAT5) is an integral part of signalling mediated via mutated PDGF-receptors. Furthermore, this unconventional STAT activation by mutated PDGFRα is already initiated in the endoplasmic reticulum whereas the conventional signalling pathways rather require cell surface expression of the receptor. Finally, we demonstrate that the activation of STAT factors also translates into a biologic response as highlighted by the induction of STAT target genes. CONCLUSION: We show that the overall oncogenic response is the result of different signatures emanating from different cellular compartments. Furthermore, STAT mediated responses are an integral part of mutated PDGFRα signalling.

Interplay of microRNAs, transcription factors and target genes: linking dynamic expression changes to function.

MicroRNAs (miRNAs) are ubiquitously expressed small non-coding RNAs that, in most cases, negatively regulate gene expression at the post-transcriptional level. miRNAs are involved in fine-tuning fundamental cellular processes such as proliferation, cell death and cell cycle control and are believed to confer robustness to biological responses. Here, we investigated simultaneously the transcriptional changes of miRNA and mRNA expression levels over time after activation of the Janus kinase/Signal transducer and activator of transcription (Jak/STAT) pathway by interferon-γ stimulation of melanoma cells. To examine global miRNA and mRNA expression patterns, time-series microarray data were analysed. We observed delayed responses of miRNAs (after 24-48 h) with respect to mRNAs (12-24 h) and identified biological functions involved at each step of the cellular response. Inference of the upstream regulators allowed for identification of transcriptional regulators involved in cellular reactions to interferon-γ stimulation. Linking expression profiles of transcriptional regulators and miRNAs with their annotated functions, we demonstrate the dynamic interplay of miRNAs and upstream regulators with biological functions. Finally, our data revealed network motifs in the form of feed-forward loops involving transcriptional regulators, mRNAs and miRNAs. Additional information obtained from integrating time-series mRNA and miRNA data may represent an important step towards understanding the regulatory principles of gene expression.

Transcriptional response to cardiac injury in the zebrafish: systematic identification of genes with highly concordant activity across in vivo models.

BACKGROUND: Zebrafish is a clinically-relevant model of heart regeneration. Unlike mammals, it has a remarkable heart repair capacity after injury, and promises novel translational applications. Amputation and cryoinjury models are key research tools for understanding injury response and regeneration in vivo. An understanding of the transcriptional responses following injury is needed to identify key players of heart tissue repair, as well as potential targets for boosting this property in humans. RESULTS: We investigated amputation and cryoinjury in vivo models of heart damage in the zebrafish through unbiased, integrative analyses of independent molecular datasets. To detect genes with potential biological roles, we derived computational prediction models with microarray data from heart amputation experiments. We focused on a top-ranked set of genes highly activated in the early post-injury stage, whose activity was further verified in independent microarray datasets. Next, we performed independent validations of expression responses with qPCR in a cryoinjury model. Across in vivo models, the top candidates showed highly concordant responses at 1 and 3 days post-injury, which highlights the predictive power of our analysis strategies and the possible biological relevance of these genes. Top candidates are significantly involved in cell fate specification and differentiation, and include heart failure markers such as periostin, as well as potential new targets for heart regeneration. For example, ptgis and ca2 were overexpressed, while usp2a, a regulator of the p53 pathway, was down-regulated in our in vivo models. Interestingly, a high activity of ptgis and ca2 has been previously observed in failing hearts from rats and humans. CONCLUSIONS: We identified genes with potential critical roles in the response to cardiac damage in the zebrafish. Their transcriptional activities are reproducible in different in vivo models of cardiac injury.

MicroRNA as biomarkers and regulators in B-cell chronic lymphocytic leukemia.

Early cancer detection and disease stratification or classification are critical to successful treatment. Accessible, reliable, and informative cancer biomarkers can be medically valuable and can provide some relevant insights into cancer biology. Recent studies have suggested improvements in detecting malignancies by the use of specific extracellular microRNAs (miRNAs) in plasma. In chronic lymphocytic leukemia (CLL), an incurable hematologic disorder, sensitive, early, and noninvasive diagnosis and better disease classification would be very useful for more effective therapies. We show here that circulating miRNAs can be sensitive biomarkers for CLL, because certain extracellular miRNAs are present in CLL patient plasma at levels significantly different from healthy controls and from patients affected by other hematologic malignancies. The levels of several of these circulating miRNAs also displayed significant differences between zeta-associated protein 70 (ZAP-70)(+) and ZAP-70(-) CLL. We also determined that the level of circulating miR-20a correlates reliably with diagnosis-to-treatment time. Network analysis of our data, suggests a regulatory network associated with BCL2 and ZAP-70 expression in CLL. This hypothesis suggests the possibility of using the levels of specific miRNAs in plasma to detect CLL and to determine the ZAP-70 status.

From 'I' to 'L' and back again: the odyssey of membrane-bound M13 protein.

The major coat protein of the filamentous bacteriophage M13 is a surprising protein because it exists both as a membrane protein and as part of the M13 phage coat during its life cycle. Early studies showed that the phage-bound structure of the coat protein was a continuous I-shaped alpha-helix. However, throughout the years various structural models, both I-shaped and L-shaped, have been proposed for the membrane-bound state of the coat protein. Recently, site-directed labelling approaches have enabled the study of the coat protein under conditions that more closely mimic the in vivo membrane-bound state. Interestingly, the structure that has emerged from this work is I-shaped and similar to the structure in the phage-bound state.

Glioma subtype classification from histopathological images using in-domain and out-of-domain transfer learning: An experimental study.

We provide in this paper a comprehensive comparison of various transfer learning strategies and deep learning architectures for computer-aided classification of adult-type diffuse gliomas. We evaluate the generalizability of out-of-domain ImageNet representations for a target domain of histopathological images, and study the impact of in-domain adaptation using self-supervised and multi-task learning approaches for pretraining the models using the medium-to-large scale datasets of histopathological images. A semi-supervised learning approach is furthermore proposed, where the fine-tuned models are utilized to predict the labels of unannotated regions of the whole slide images (WSI). The models are subsequently retrained using the ground-truth labels and weak labels determined in the previous step, providing superior performance in comparison to standard in-domain transfer learning with balanced accuracy of 96.91% and F1-score 97.07%, and minimizing the pathologist's efforts for annotation. Finally, we provide a visualization tool working at WSI level which generates heatmaps that highlight tumor areas; thus, providing insights to pathologists concerning the most informative parts of the WSI.