Raghu Machiraju

Raghu Machiraju
The Ohio State University | OSU · Department of Computer Science and Engineering & Biomedical Informatics

About

250
Publications
26,920
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
3,609
Citations
Citations since 2016
42 Research Items
1402 Citations
2016201720182019202020212022050100150200250
2016201720182019202020212022050100150200250
2016201720182019202020212022050100150200250
2016201720182019202020212022050100150200250

Publications

Publications (250)
Article
Adult-type diffuse gliomas have been classified according to histopathological characteristics only. Based on molecular profiles, the World Health Organization (WHO) classification defines three distinct biologic and prognostic types of diffuse gliomas: (i) IDH wild type (IDHwt), (ii) IDH mutant, 1p19q intact (IDHmut-non-codel), and (iii) IDH mutan...
Chapter
Advances in digital pathology and deep learning have enabled robust disease classification, better diagnosis, and prognosis. In real-world settings, readily available and inexpensive image-level labels from pathology reports are weak, which seriously degrades the performance of deep learning models. Weak image-level labels do not represent the comp...
Chapter
Artificial intelligence is poised to transform the practice of pathology. Convolutional neural networks are powerful deep learning tools that can be applied to whole slide images to highlight regions of interest, identify artifacts, make diagnoses, and extract hidden features that may relate to prognosis and therapy. Here, we discuss the challenges...
Article
Full-text available
Background Assigning chromatin states genome-wide (e.g. promoters, enhancers, etc.) is commonly performed to improve functional interpretation of these states. However, computational methods to assign chromatin state suffer from the following drawbacks: they typically require data from multiple assays, which may not be practically feasible to obtai...
Article
Full-text available
Single-cell RNA sequencing (scRNA-seq) resolves heterogenous cell populations in tissues and helps to reveal single-cell level function and dynamics. In neuroscience, the rarity of brain tissue is the bottleneck for such study. Evidence shows that, mouse and human share similar cell type gene markers. We hypothesized that the scRNA-seq data of mous...
Article
Integration of transcriptomic and proteomic data should reveal multi-layered regulatory processes governing cancer cell behaviors. Traditional correlation-based analyses have demonstrated limited ability to identify the post-transcriptional regulatory (PTR) processes that drive the non-linear relationship between transcript and protein abundances....
Article
Relating genotypes with phenotypes is important to understand diseases like cancer, but extremely challenging, given the underlying biological variability and levels of phenotypes. 3D quantitative tools are increasingly used to provide robust inferences pertaining to variations across collections of cells. We especially focus on the changes wrought...
Article
Full-text available
Neural embeddings are widely used in language modeling and feature generation with superior computational power. Particularly, neural document embedding - converting texts of variable-length to semantic vector representations - has shown to benefit widespread downstream applications, e.g., information retrieval (IR). However, the black-box nature m...
Preprint
Full-text available
Technical advances have enabled the identification of high-resolution cell types within tissues based on single-cell transcriptomics. However, such analyses are restricted in human brain tissue due to the limited number of brain donors. In this study, we integrate mouse and human data to predict cell-type proportions in human brain tissue, and spat...
Article
Benchmark challenges, such as the Critical Assessment of Structure Prediction (CASP) and Dialogue for Reverse Engineering Assessments and Methods (DREAM) have been instrumental in driving the development of bioinformatics methods. Typically, challenges are posted, and then competitors perform a prediction based upon blinded test data. Challengers t...
Article
Full-text available
Convolutional neural networks (CNNs) have gained steady popularity as a tool to perform automatic classification of whole slide histology images. While CNNs have proven to be powerful classifiers in this context, they fail to explain this classification, as the network engineered features used for modeling and classification are ONLY interpretable...
Article
Motivation: Technologies that generate high-throughput 'omics data are flourishing, creating enormous, publicly available repositories of multi-omics data. As many data repositories continue to grow, there is an urgent need for computational methods that can leverage these data to create comprehensive clusters of patients with a given disease. Re...
Article
Introduction: Despite apparently complete surgical resection, approximately half of resected early stage lung cancer patients relapse and die of their disease. Adjuvant chemotherapy reduces this risk by only 5-8%. Thus, there is a need for better identifying who benefits from adjuvant therapy, the drivers of relapse and novel targets in this setti...
Preprint
We describe an effort to annotate a corpus of natural language instructions consisting of 622 wet lab protocols to facilitate automatic or semi-automatic conversion of protocols into a machine-readable format and benefit biological research. Experimental results demonstrate the utility of our corpus for developing machine learning approaches to sha...
Article
Utilization of single modality data to build predictive models in cancer results in a rather narrow view of most patient profiles. Some clinical facet s relate strongly to histology image features, e.g. tumor stages, whereas others are associated with genomic and proteomic variations (e.g. cancer subtypes and disease aggression biomarkers). We hypo...
Article
Full-text available
Background We develop predictive models enabling clinicians to better understand and explore patient clinical data along with risk factors for pressure ulcers in intensive care unit patients from electronic health record data. Identifying accurate risk factors of pressure ulcers is essential to determining appropriate prevention strategies; in this...
Article
Advances in optical microscopy, biosensors and cell culturing technologies have transformed live cell imaging. Thanks to these advances live cell imaging plays an increasingly important role in basic biology research as well as at all stages of drug development. Image analysis methods are needed to extract quantitative information from these vast a...
Article
Full-text available
Systematic Reviews (SRs) of biomedical literature summarize evidence from high-quality studies to inform clinical decisions, but are time and labor intensive due to the large number of article collections. Article similarities established from textual features have been shown to assist in the identification of relevant articles, thus facilitating t...
Article
Full-text available
Background Identification and analysis of recurrent combinatorial patterns of multiple chromatin modifications provide invaluable information for understanding epigenetic regulations. Furthermore, as more data becomes available, it is computationally expensive and unnecessary to study combinatorial patterns of all modifications. MethodsA novel fram...
Preprint
Full-text available
Cancer’s cellular behavior is driven by alterations in the processes that cells use to sense and respond to diverse stimuli. Underlying these processes are a series of chemical processes (enzyme-substrate, protein-protein, etc.). Here we introduce a set of mathematical techniques for describing and characterizing these processes.
Article
Full-text available
E2F-mediated transcriptional repression of cell cycle-dependent gene expression is critical for the control of cellular proliferation, survival, and development. E2F signaling also interacts with transcriptional programs that are downstream of genetic predictors for cancer development, including hepatocellular carcinoma (HCC). Here, we evaluated th...
Article
Full-text available
Co-expression analysis has been employed to predict gene function, identify functional modules, and determine tumor subtypes. Previous co-expression analysis was mainly conducted at bulk tissue level. It is unclear whether co-expression analysis at the single-cell level will provide novel insights into transcriptional regulation. Here we developed...
Data
Expression correlation of REST and ROCK2 at single-cell and bulk levels. Gene correlation at the single-cell level is separately showed for five glioblastomas. Pearson’s correlation coefficient (R) and corresponding P value are indicated in the panel. (TIF)
Data
Scatter plot of average and bulk-level expression in glioblastoma. Each point represents a gene. (TIF)
Data
The distribution of gene correlations at single-cell and bulk levels in prostate cancer. Green, orange, and cyan lines represent shared, single-cell specific, and bulk specific co-expressions, respectively. (TIF)
Data
Silhouette plot of the division of patients. The figure shows that the patients are similar to other patients within the group than patients in another group. Each line represents a patients. The color of the line indicate the group of patients. (TIFF)
Data
Expression correlation of ATP9B and MORC4 at single-cell and bulk levels. Gene correlation at the single-cell level is separately showed for five glioblastomas. Pearson’s correlation coefficient (R) and corresponding P value are indicated in the panel. (TIF)
Data
The division of correlation patterns at single-cell and bulk levels. The cutoffs of negative, no and positive correlations (vertical dashed lines) were set according to 1,000 times of the distributions of gene correlations of shuffled expression (only one example showed: R-S-MGH and R-B-GBM for single-cell and bulk levels, respectively). The shared...
Data
Enriched functions of three types of co-expressed genes. The significant value for term ‘Translation elongation’ is equal to 90 and truncated for view. The bar-plot is corresponding to Fig 3C. (TIF)
Data
Chromatin interaction of co-expressed genes in hESC. The dash horizontal line represents an average percentage of control gene pairs with chromatin interaction. The asterisk indicates the percentage is significantly higher than control in statistics. (TIF)
Data
Kaplan-Meier survival curves of 120 glioblastoma patients based on the best subnetwork from bulk co-expressed networks. The two-gene set was one of 13 subnetworks in bulk co-expressed network which divides 120 glioblastomas to two size-balanced groups. Log-rank test was performed to assess the significance of survival difference. (TIF)
Data
Expression correlation of RPL41 and RPS14 at single-cell and bulk levels. Gene correlation at the single-cell level is separately showed for five glioblastomas. Pearson’s correlation coefficient (R) and corresponding P value are indicated in the panel. (TIF)
Data
The distribution of top maximal information coefficients at single-cell and bulk levels of glioblastomas. Green, orange, and cyan lines represent shared, single-cell specific, and bulk specific correlations, respectively. (TIF)
Data
The number of gene pairs in each correlation pattern. The symbols ‘+’, ‘0’, and ‘-’ separately represent positive, no, and negative correlation. The three groups of gene pairs which are shared, single-cell specific, and bulk specific co-expressions are highlighted in green, orange, and cyan color, respectively. (TIF)
Data
Kaplan-Meier survival curves of 120 glioblastoma patients based on four TCGA subtypes. Log-rank test was performed to assess the significance of survival difference. (TIF)
Article
Full-text available
Systematic reviews (SRs) provide high quality evidence for clinical practice, but the article screening process is time and labor intensive. As SRs aim to identify relevant articles with a specific scope, we propose that a pre-defined article relationship, using similarity metrics, could accelerate this process. In this study, we established the ar...
Article
Histone modification is an important epigenetic event which plays essential roles in cell differentiation and tissue development. Recent studies show that a unique dimethylation of lysine 4 residue on histone 3 (H3K4me2) distribution pattern around transcription starting sites (TSS) of genes marks tissue specific genes in human CD4+ T cells and mou...
Article
Full-text available
Our goal in this study is to find risk factors associated with Pressure Ulcers (PUs) and to develop predictive models of PU incidence. We focus on Intensive Care Unit (ICU) patients since patients admitted to ICU have shown higher incidence of PUs. The most common PU incidence assessment tool is the Braden scale, which sums up six subscale features...
Article
Full-text available
Histology images comprise one of the important sources of knowledge for phenotyping studies in systems biology. However, the annotation and analyses of histological data have remained a manual, subjective and relatively low-throughput process. We introduce Graph based Histology Image Explorer (GRAPHIE)-a visual analytics tool to explore, annotate a...
Article
Robust mechanisms to control cell proliferation have evolved to maintain the integrity of organ architecture. Here, we investigated how two critical proliferative pathways, Myc and E2f, are integrated to control cell cycles in normal and Rb-deficient cells using a murine intestinal model. We show that Myc and E2f1-3 have little impact on normal G1-...
Conference Paper
Full-text available
Although vortex analysis and detection have been extensively in-vestigated in the past, none of the existing techniques are able to provide fully robust and reliable identification results. Local vortex detection methods are popular as they are efficient and easy to im-plement, and produce binary outputs based on a user-specified, hard threshold. H...
Article
Interaction of endothelial-lineage cells with three-dimensional substrates was much less studied than that with flat culture surfaces. We investigated the in vitro attachment of both mature endothelial cells (ECs) and of less differentiated EC colony-forming cells to poly-ε-capro-lactone (PCL) fibers with diameters in 5-20 μm range ('scaffold micro...
Article
Studies of the brain’s transcriptome have become prominent in recent years, resulting in an accumulation of datasets with somewhat distinct attributes. These datasets, which are often analyzed only in isolation, also are often collected with divergent goals, which are reflected in their sampling properties. While many researchers have been interest...
Article
In this paper, we demonstrate the use of machine learning techniques to enhance the robustness of vortex visualization algorithms. We combine several local feature detection algorithms, which we term weak classifiers into a robust compound classifier using adaptive boosting or AdaBoost. This compound classifier combines the advantages of each indiv...
Article
The 2013 IEEE Scientific Visualization Contest focused on developmental neuroscience related to the mouse brain. In developmental neuroscience, researchers examine spatiotemporal patterns of gene expression to understand how brain structures evolve and vary over an organism's life. The Allen Developing Mouse Brain Atlas project generated expression...
Article
Full-text available
Introduction In 2011, the BioVis symposium of the IEEE VisWeek conferences inaugurated a new variety of data analysis contest. Aimed at fostering collaborations between computational scientists and biologists, the BioVis contest provided real data from biological domains with emerging visualization needs, in the hope that novel approaches would res...
Article
Full-text available
Background Cancers are highly heterogeneous with different subtypes. These subtypes often possess different genetic variants, present different pathological phenotypes, and most importantly, show various clinical outcomes such as varied prognosis and response to treatment and likelihood for recurrence and metastasis. Recently, integrative genomics...
Article
Breast cancers are highly heterogeneous with different subtypes that lead to different clinical outcomes including prognosis, response to treatment and chances of recurrence and metastasis. An important task in personalized medicine is to determine the subtype for a breast cancer patient in order to provide the most effective treatment. In order to...
Article
Scatterplot matrices or SPLOMs provide a feasible method of visualizing and representing multi-dimensional data especially for a small number of dimensions. For very high dimensional data, we introduce a novel technique to summarize a SPLOM, as a clustered matrix of glyphs, or a Glyph SPLOM. Each glyph visually encodes a general measure of dependen...
Article
Full-text available
Background Mapping medical terms to standardized UMLS concepts is a basic step for leveraging biomedical texts in data management and analysis. However, available methods and tools have major limitations in handling queries over the UMLS Metathesaurus that contain inaccurate query terms, which frequently appear in real world applications. Methods...
Patent
Full-text available
Systems and methods for segmenting images comprising cells, wherein the images comprise a plurality of pixels; one or more three dimensional (3D) clusters of cells are identified in the images; and the 3D clusters of cells are automatically segmented into individual cells using one or more models.
Article
Full-text available
The preeminence of a systems approach in the biological and other life sciences creates enormous challenges for computational visualization techniques to enable researchers to gain insight from their large, highly complex, and multiple datasets. This special issue presents articles describing applications of visual-analytics techniques to yield via...
Article
Robust automated vortex detection algorithms are needed to facilitate the exploration of large-scale turbulent fluid flow simulations. Unfortunately, robust non-local vortex detection algorithms are computationally intractable for large data sets and local algorithms, while computationally tractable, lack robustness. We argue that the deficiencies...
Article
Full-text available
The first installment of Computer's series highlighting the work published in IEEE Computer Society journals comes from IEEE Transactions on Visualization and Computer Graphics.
Conference Paper
This paper presents a novel algorithm to enhance the robustness of vortex core detection that automatically learns to build a strong compound classifier based on a locally weighted combination of weak detectors and the training samples. We use semi-supervised learning with domain expert input to develop strategies for guiding the selective refineme...
Conference Paper
Full-text available
Polymerized actin-based cytoskeletal structures provide the cells with shape, resilience and dynamics. A mechanistic understanding of actin-based structures is crucial for finding solutions to practical problems occurring in tissue engineering constructs that require the interaction of cells with materials. In this regard, the first step is to dete...
Article
Numerous studies have examined gene × environment interactions (G × E) in cognitive and behavioral domains. However, these studies have been limited in that they have not been able to directly assess differential patterns of gene expression in the human brain. Here, we assessed G × E interactions using two publically available datasets to assess if...
Article
Full-text available
Background and objective Biomarkers for subtyping triple negative breast cancer (TNBC) are needed given the absence of responsive therapy and relatively poor prediction of survival. Morphology of cancer tissues is widely used in clinical practice for stratifying cancer patients, while genomic data are highly effective to classify cancer patients in...
Data
Full-text available