Machine learning classification of surgical pathology reports and chunk recognition for information extraction noise reduction.

Artif Intell Med. 2016 Jun;70:77-83

Authors: Napolitano G, Marshall A, Hamilton P, Gavin AT

Abstract
BACKGROUND AND AIMS: Machine learning techniques for the text mining of cancer-related clinical documents have not been sufficiently explored. Here some techniques are presented for the pre-processing of free-text breast cancer pathology reports, with the aim of facilitating the extraction of information relevant to cancer staging.
MATERIALS AND METHODS: The first technique was implemented using the freely available software RapidMiner to classify the reports according to their general layout: 'semi-structured' and 'unstructured'. The second technique was developed using the open source language engineering framework GATE and aimed at the prediction of chunks of the report text containing information pertaining to the cancer morphology, the tumour size, its hormone receptor status and the number of positive nodes. The classifiers were trained and tested respectively on sets of 635 and 163 manually classified or annotated reports, from the Northern Ireland Cancer Registry.
RESULTS: The best result of 99.4% accuracy - which included only one semi-structured report predicted as unstructured - was produced by the layout classifier with the k nearest algorithm, using the binary term occurrence word vector type with stopword filter and pruning. For chunk recognition, the best results were found using the PAUM algorithm with the same parameters for all cases, except for the prediction of chunks containing cancer morphology. For semi-structured reports the performance ranged from 0.97 to 0.94 and from 0.92 to 0.83 in precision and recall, while for unstructured reports performance ranged from 0.91 to 0.64 and from 0.68 to 0.41 in precision and recall. Poor results were found when the classifier was trained on semi-structured reports but tested on unstructured.
CONCLUSIONS: These results show that it is possible and beneficial to predict the layout of reports and that the accuracy of prediction of which segments of a report may contain certain information is sensitive to the report layout and the type of information sought.

PMID: 27431038 [PubMed - in process]

13 new pubmed citations were retrieved for your search. Click on the search hyperlink below to display the complete search results:

("orphan disease" OR "rare disease" OR "orphan diseases" OR "rare diseases")

These pubmed results were generated on 2016/07/19

PubMed comprises more than 24 million citations for biomedical literature from MEDLINE, life science journals, and online books. Citations may include links to full-text content from PubMed Central and publisher web sites.

9 new pubmed citations were retrieved for your search. Click on the search hyperlink below to display the complete search results:

"Cystic Fibrosis"

These pubmed results were generated on 2016/07/19

PubMed comprises more than 24 million citations for biomedical literature from MEDLINE, life science journals, and online books. Citations may include links to full-text content from PubMed Central and publisher web sites.

A Second WNT for Old Drugs: Drug Repositioning against WNT-Dependent Cancers.

Cancers (Basel). 2016;8(7)

Authors: Ahmed K, Shaw HV, Koval A, Katanaev VL

Abstract
Aberrant WNT signaling underlies cancerous transformation and growth in many tissues, such as the colon, breast, liver, and others. Downregulation of the WNT pathway is a desired mode of development of targeted therapies against these cancers. Despite the urgent need, no WNT signaling-directed drugs currently exist, and only very few candidates have reached early phase clinical trials. Among different strategies to develop WNT-targeting anti-cancer therapies, repositioning of existing drugs previously approved for other diseases is a promising approach. Nonsteroidal anti-inflammatory drugs like aspirin, the anti-leprotic clofazimine, and the anti-trypanosomal suramin are among examples of drugs having recently revealed WNT-targeting activities. In total, 16 human-use drug compounds have been found to be working through the WNT pathway and show promise for their prospective repositioning against various cancers. Advances, hurdles, and prospects of developing these molecules as potential drugs against WNT-dependent cancers, as well as approaches for discovering new ones for repositioning, are the foci of the current review.

PMID: 27429001 [PubMed - as supplied by publisher]

mTOR disruption causes intestinal epithelial cell defects and intestinal atrophy postinjury in mice.

FASEB J. 2016 Mar;30(3):1263-75

Authors: Sampson LL, Davis AK, Grogg MW, Zheng Y

Abstract
Intestinal stem cells (ISCs) drive small intestinal epithelial homeostasis and regeneration. Mechanistic target of rapamycin (mTOR) regulates stem and progenitor cell metabolism and is frequently dysregulated in human disease, but its physiologic functions in the mammalian small intestinal epithelium remain poorly defined. We disrupted the genes mTOR, Rptor, Rictor, or both Rptor and Rictor in mouse ISCs, progenitors, and differentiated intestinal epithelial cells (IECs) using Villin-Cre. Mutant tissues and wild-type or heterozygous littermate controls were analyzed by histologic immunostaining, immunoblots, and proliferation assays. A total of 10 Gy irradiation was used to injure the intestinal epithelium and induce subsequent crypt regeneration. We report that mTOR supports absorptive enterocytes and secretory Paneth and goblet cell function while negatively regulating chromogranin A-positive enteroendocrine cell number. Through additional Rptor, Rictor, and Rptor/Rictor mutant mouse models, we identify mechanistic target of rapamycin complex 1 as the major IEC regulatory pathway, but mechanistic target of rapamycin complex 2 also contributes to ileal villus maintenance and goblet cell size. Homeostatic adult small intestinal crypt cell proliferation, survival, and canonical wingless-int (WNT) activity are not mTOR dependent, but Olfm4(+) ISC/progenitor population maintenance and crypt regeneration postinjury require mTOR. Overall, we conclude that mTOR regulates multiple IEC lineages and promotes stem and progenitor cell activity during intestinal epithelium repair postinjury.

PMID: 26631481 [PubMed - indexed for MEDLINE]

Genomics era and complex disorders: Implications of GWAS with special reference to coronary artery disease, type 2 diabetes mellitus, and cancers.

J Postgrad Med. 2016 Jul-Sep;62(3):188-98

Authors: Pranavchand R, Reddy MM

Abstract
The Human Genome Project (HGP) has identified millions of single nucleotide polymorphisms (SNPs) and their association with several diseases, apart from successfully characterizing the Mendelian/monogenic diseases. However, the dissection of precise etiology of complex genetic disorders still poses a challenge for human geneticists. This review outlines the landmark results of genome-wide association studies (GWAS) with respect to major complex diseases - Coronary artery disease (CAD), type 2 diabetes mellitus (T2DM), and predominant cancers. A brief account on the current Indian scenario is also given. All the relevant publications till mid-2015 were accessed through web databases such as PubMed and Google. Several databases providing genetic information related to these diseases were tabulated and in particular, the list of the most significant SNPs identified through GWAS was made, which may be useful for designing studies in functional validation. Post-GWAS implications and emerging concepts such as epigenomics and pharmacogenomics were also discussed.

PMID: 27424552 [PubMed - in process]

The Outlier in All of Us: Why Implementing Pharmacogenomics Could Matter for Everyone.

Clin Pharmacol Ther. 2016 Apr;99(4):401-4

Authors: O'Donnell PH, Danahey K, Ratain MJ

Abstract
The field of pharmacogenomics originally emerged in the 1950s from observations that a few rare individuals had unexpected, severe reactions to drugs. As recently as just 6 years ago, prominent views on the subject had largely remained unchanged, with authors from the US Food and Drug Administration (FDA) citing the purpose of pharmacogenetics as "tailoring treatment for the outliers." It should not be surprising if this is the prevailing view--the best-studied pharmacogenomic drug examples are indeed just that, genetic explanations of extreme responses or susceptibilities among usually a very small fraction of the human population. Thiopurine methyltransferase (TPMT) deficiency as a cause of severe myelosuppression upon treatment with azathioprine or mercaptopurine is found as a heterozygous trait in only ∼ 10% of patients, and homozygous (deficiency) carriers are even more rare--occurring in fewer than 1 in 300 patients. Malignant hyperthermia resulting from inhaled anesthetics and succinylcholine is believed to have a genetic incidence of only about 1 in 2000 people.

PMID: 26756170 [PubMed - indexed for MEDLINE]

Top-down, Bottom-up and Middle-out Strategies for Drug Cardiac Safety Assessment via Modeling and Simulations.

Curr Pharmacol Rep. 2016;2:171-177

Authors: Tylutki Z, Polak S, Wiśniowska B

Abstract
Cardiac safety is an issue causing early terminations at various stages of drug development. Efforts are put into the elimination of false negatives as well as false positives resulting from the current testing paradigm. In silico approaches offer mathematical system and data description from the ion current, through cardiomyocytes level, up to incorporation of inter-individual variability at the population level. The article aims to review three main modelling and simulation approaches, i.e. "top-down" which refers to models built on the observed data, "bottom-up", which stands for a mechanistic description of human physiology, and "middle-out" which combines both strategies. Modelling and simulation is a well-established tool in the assessment of drug proarrhythmic potency with an impact on research and development as well as on regulatory decisions, and it is certainly here to stay. What is more, the shift to systems biology and physiology-based models makes the cardiac effect more predictable.

PMID: 27429898 [PubMed - as supplied by publisher]

2016 ISCB Overton Prize awarded to Debora Marks.

F1000Res. 2016;5

Authors: Fogg CN, Kovats DE

Abstract
The International Society for Computational Biology (ISCB) recognizes the achievements of an early- to mid-career scientist with the Overton Prize each year. The Overton Prize was established to honor the untimely loss of Dr. G. Christian Overton, a respected computational biologist and founding ISCB Board member. Winners of the Overton Prize are independent investigators in the early to middle phases of their careers who are selected because of their significant contributions to computational biology through research, teaching, and service. 2016 will mark the fifteenth bestowment of the ISCB Overton Prize.  ISCB is pleased to confer this award the to Debora Marks, Assistant Professor of Systems Biology and director of the Raymond and Beverly Sackler Laboratory for Computational Biology at Harvard Medical School.

PMID: 27429747 [PubMed - as supplied by publisher]

Guidelines for reproducibly building and simulating systems biology models.

IEEE Trans Biomed Eng. 2016 Jul 18;

Authors: Medley JK, Goldberg A, Karr JR

Abstract
Reproducibility is the cornerstone of the scientific method. However, currently, many systems biology models cannot easily be reproduced. This paper presents methods that address this problem.
METHODS: We analyzed the recent Mycoplasma genitalium whole-cell (WC) model to determine the requirements for reproducible modeling.
RESULTS: We determined that reproducible modeling requires both repeatable model building and repeatable simulation.
CONCLUSION: New standards and simulation software tools are needed to enhance and verify the reproducibility of modeling. New standards are needed to explicitly document every data source and assumption, and new deterministic parallel simulation tools are needed to quickly simulate large, complex models.
SIGNIFICANCE: We anticipate that these new standards and software will enable researchers to reproducibly build and simulate more complex models, including WC models.

PMID: 27429432 [PubMed - as supplied by publisher]

SIRT2- and NRF2-Targeting Thiazole-Containing Compound with Therapeutic Activity in Huntington's Disease Models.

Cell Chem Biol. 2016 Jul 9;

Authors: Quinti L, Casale M, Moniot S, Pais TF, Van Kanegan MJ, Kaltenbach LS, Pallos J, Lim RG, Naidu SD, Runne H, Meisel L, Rauf NA, Leyfer D, Maxwell MM, Saiah E, Landers JE, Luthi-Carter R, Abagyan R, Dinkova-Kostova AT, Steegborn C, Marsh JL, Lo DC, Thompson LM, Kazantsev AG

Abstract
There are currently no disease-modifying therapies for the neurodegenerative disorder Huntington's disease (HD). This study identified novel thiazole-containing inhibitors of the deacetylase sirtuin-2 (SIRT2) with neuroprotective activity in ex vivo brain slice and Drosophila models of HD. A systems biology approach revealed an additional SIRT2-independent property of the lead-compound, MIND4, as an inducer of cytoprotective NRF2 (nuclear factor-erythroid 2 p45-derived factor 2) activity. Structure-activity relationship studies further identified a potent NRF2 activator (MIND4-17) lacking SIRT2 inhibitory activity. MIND compounds induced NRF2 activation responses in neuronal and non-neuronal cells and reduced production of reactive oxygen species and nitrogen intermediates. These drug-like thiazole-containing compounds represent an exciting opportunity for development of multi-targeted agents with potentially synergistic therapeutic benefits in HD and related disorders.

PMID: 27427231 [PubMed - as supplied by publisher]

Causal Mechanistic Regulatory Network for Glioblastoma Deciphered Using Systems Genetics Network Analysis.

Cell Syst. 2016 Jul 14;

Authors: Plaisier CL, O'Brien S, Bernard B, Reynolds S, Simon Z, Toledo CM, Ding Y, Reiss DJ, Paddison PJ, Baliga NS

Abstract
We developed the transcription factor (TF)-target gene database and the Systems Genetics Network Analysis (SYGNAL) pipeline to decipher transcriptional regulatory networks from multi-omic and clinical patient data, and we applied these tools to 422 patients with glioblastoma multiforme (GBM). The resulting gbmSYGNAL network predicted 112 somatically mutated genes or pathways that act through 74 TFs and 37 microRNAs (miRNAs) (67 not previously associated with GBM) to dysregulate 237 distinct co-regulated gene modules associated with patient survival or oncogenic processes. The regulatory predictions were associated to cancer phenotypes using CRISPR-Cas9 and small RNA perturbation studies and also demonstrated GBM specificity. Two pairwise combinations (ETV6-NFKB1 and romidepsin-miR-486-3p) predicted by the gbmSYGNAL network had synergistic anti-proliferative effects. Finally, the network revealed that mutations in NF1 and PIK3CA modulate IRF1-mediated regulation of MHC class I antigen processing and presentation genes to increase tumor lymphocyte infiltration and worsen prognosis. Importantly, SYGNAL is widely applicable for integrating genomic and transcriptomic measurements from other human cohorts.

PMID: 27426982 [PubMed - as supplied by publisher]

Ebola virus disease and social media: A systematic review.

Am J Infect Control. 2016 Jul 14;

Authors: Fung IC, Duke CH, Finch KC, Snook KR, Tseng PL, Hernandez AC, Gambhir M, Fu KW, Tse ZT

Abstract
OBJECTIVES: We systematically reviewed existing research pertinent to Ebola virus disease and social media, especially to identify the research questions and the methods used to collect and analyze social media.
METHODS: We searched 6 databases for research articles pertinent to Ebola virus disease and social media. We extracted the data using a standardized form. We evaluated the quality of the included articles.
RESULTS: Twelve articles were included in the main analysis: 7 from Twitter with 1 also including Weibo, 1 from Facebook, 3 from YouTube, and 1 from Instagram and Flickr. All the studies were cross-sectional. Eleven of the 12 articles studied ≥ 1of these 3 elements of social media and their relationships: themes or topics of social media contents, meta-data of social media posts (such as frequency of original posts and reposts, and impressions) and characteristics of the social media accounts that made these posts (such as whether they are individuals or institutions). One article studied how news videos influenced Twitter traffic. Twitter content analysis methods included text mining (n = 3) and manual coding (n = 1). Two studies involved mathematical modeling. All 3 YouTube studies and the Instagram/Flickr study used manual coding of videos and images, respectively.
CONCLUSIONS: Published Ebola virus disease-related social media research focused on Twitter and YouTube. The utility of social media research to public health practitioners is warranted.

PMID: 27425009 [PubMed - as supplied by publisher]

[Colonic gallstone ileus: A rare cause of intestinal obstruction].

Cir Cir. 2016 Jul 13;

Authors: Marenco-de la Cuadra B, López-Ruiz JA, Tallón-Aguilar L, López-Pérez J, Oliva-Mompeán F

Abstract
BACKGROUND: A gallstone colonic ileus is a very rare condition.
CLINICAL CASE: The case is reported of an 87 year-old patient who came to the Emergency Department due to an intestinal obstruction of several days onset, which was caused by a gallstone affected sigmoid colon.
CONCLUSION: Colonic gallstone ileus is a rare disease that usually occurs in older patients due to the passage of large gallstone directly from the gallbladder to colon, through a cholecystocolonic fistula. It has a high morbidity and mortality.

PMID: 27423884 [PubMed - as supplied by publisher]

Preface: Cystic Fibrosis in Children and Adults: Supplement to Paediatric Respiratory Reviews.

Paediatr Respir Rev. 2016 Jun 18;

Authors: David TJ

PMID: 27424228 [PubMed - as supplied by publisher]

Decreased TGF-β1 and VEGF Release in Cystic Fibrosis Platelets: Further Evidence for Platelet Defects in Cystic Fibrosis.

Lung. 2016 Jul 16;

Authors: Maloney JP, Narasimhan J, Biller J

Abstract
PURPOSE: Cystic fibrosis (CF) patients suffer from chronic lung inflammation. This inflammation may activate platelets. There are limited data on the role of platelet-secreted cytokines in CF. Platelet cytokines with inflammatory effects include vascular endothelial growth factor (VEGF) and transforming growth factor-β1 (TGF-β1). As levels of these cytokines are tenfold greater in serum than plasma due to platelet release, serum levels may be one index of platelet content, but a more specific index is release during the aggregation of isolated platelets. We postulated that altered release of these platelet cytokines occurs in CF.
METHODS: We obtained sera and plasma from CF outpatients (n = 21) and from healthy controls (n = 20), measured VEGF and TGF-β1, assessed for correlations with platelet number, analyzed cytokine release during platelet aggregation to collagen, and analyzed differences in maximal platelet aggregation.
RESULTS: Platelet number and maximal aggregation levels were higher in CF. Plasma and serum levels of TGF-β1 and VEGF were higher in CF, but these levels were similar after adjusting for platelet number (serum cytokines correlated with platelet count). The release of VEGF and TGF-β1 during aggregation was decreased in CF platelets (by 52 and 29 %, respectively).
CONCLUSION: Platelet release is not a source of the elevated blood proinflammatory cytokines TGF-β1 and VEGF in CF, as platelets from CF patients actually release less of these cytokines. These data provide further evidence for platelet defects in CF.

PMID: 27423781 [PubMed - as supplied by publisher]

Nasal potential difference outcomes support diagnostic decisions in cystic fibrosis.

J Cyst Fibros. 2016 Jul 13;

Authors: Tridello G, Menin L, Pintani E, Bergamini G, Assael BM, Melotti P

Abstract
BACKGROUND: When cystic fibrosis (CF) is suspected Nasal Potential Difference (NPD) measurements are proposed to support controversial diagnosis: we investigated appropriate outcomes at the CF Centre of Verona.
SUBJECTS/METHODS: NPD were measured in 196 subjects: 50 non-CF, 65 classical CF (the reference group) and 81 with uncertain CF (case group). Discriminating power was determined by comparison between several outcomes from the CF reference group versus non-CF: basal, amiloride, 0Cl, isoproterenol, ATP, Delta-amiloride, Delta-0Cl, Delta-isoproterenol, Delta-ATP, Delta-isoproterenol+Delta-0Cl, Wilschanski Index (WI) and Sermet score (SS). The most appropriate cut-off values for variables with the best discriminating power were then applied to the case group. Descriptive statistics, logistic regression models and ROC curve analysis were applied.
RESULTS: WI and SS were the most powerful in discriminating CF from non-CF subjects. In the reference group sensitivity of the 0.82 WI cut-off was 98%, specificity 96%; both sensitivity and specificity of the -0.44 SS cut-off value were 100%. For the case group, WI and SS were, respectively, consistent with CF diagnosis in 94% and 92% of the cases.
CONCLUSIONS: Formulae have the highest discriminating power and can support the diagnosis in uncertain cases; they should be utilized for standardized interpretation of NPD for diagnosis and possibly for clinical research.

PMID: 27423539 [PubMed - as supplied by publisher]

Cystic Fibrosis Liver Disease and Ursodeoxycholic Acid: One Small Step Forward, Miles to Go.

J Pediatr. 2016 Jul 13;

Authors: Narkewicz MR

PMID: 27423176 [PubMed - as supplied by publisher]

Systems Glycobiology: Integrating glycogenomics, glycoproteomics, glycomics and other 'omics data sets to characterize cellular glycosylation processes.

J Mol Biol. 2016 Jul 13;

Authors: Bennun SV, Hizal DB, Heffner K, Can O, Zhang H, Betenbaugh MJ

Abstract
The number of proteins encoded in the human genome has been estimated at between 20,000 and 25,000 despite estimates that the entire proteome contains more than a million proteins. One reason for this difference is due to the many protein post-translational modifications that contribute to proteome complexity. Among them, glycosylation is of particular relevance because it serves to modify a large number of cellular proteins. Glycogenomics, glycoproteomics, glycomics and glycoinformatics are helping to accelerate our understanding of the cellular events involved in generating the glycoproteome, the variety of glycan structures possible, and the importance glycans play in therapeutics and disease. Indeed, interest in glycosylation has expanded rapidly over the past decade as large amounts of experimental 'omics data relevant to glycosylation processing has accumulated. Furthermore, new and more sophisticated glycoinformatics tools and databases are now available for glycan and glycosylation pathway analysis. Here, we summarize some of the recent advances in both experimental profiling and analytical methods involving N- and O-linked glycosylation processing for biotechnological and medically-relevant cells together with the unique opportunities and challenges associated with interrogating and assimilating multiple disparate high-throughput glycosylation data sets. This emerging era of advanced glycomics will lead to the discovery of key glycan biomarkers linked to diseases and help establish a better understanding of physiology and improved control of glycosylation processing in diverse cells and tissues important to disease and production of recombinant therapeutics. Furthermore, methodologies that facilitate the integration of glycomics measurements together with other 'omics data sets will lead to a deeper understanding and greater insights into the nature of glycosylation as a complex cellular process.

PMID: 27423401 [PubMed - as supplied by publisher]

Clinical guides for atypical hemolytic uremic syndrome in Japan.

Clin Exp Nephrol. 2016 Jul 15;

Authors: Kato H, Nangaku M, Hataya H, Sawai T, Ashida A, Fujimaru R, Hidaka Y, Kaname S, Maruyama S, Yasuda T, Yoshida Y, Ito S, Hattori M, Miyakawa Y, Fujimura Y, Okada H, Kagami S, Joint Committee for the Revision of Clinical Guides of Atypical Hemolytic Uremic Syndrome in Japan

Abstract
Atypical hemolytic uremic syndrome (aHUS) is a rare disease characterized by the triad of microangiopathic hemolytic anemia, thrombocytopenia, and acute kidney injury. In 2013, we developed diagnostic criteria to enable early diagnosis and timely initiation of appropriate treatment for aHUS. Recent clinical and molecular findings have resulted in several proposed classifications and definitions of thrombotic microangiopathy and aHUS. Based on recent advances in this field and the emerging international consensus to exclude secondary TMAs from the definition of aHUS, we have redefined aHUS and proposed diagnostic algorithms, differential diagnosis, and therapeutic strategies for aHUS.

PMID: 27422619 [PubMed - as supplied by publisher]