Publications | Krauthammer Lab

, , , vol. pp. [DOI] [PubMed] [PubMed Central]

@inproceedings{kuhn2012smbm,
  author = {Kuhn, Tobias and Krauthammer, Michael.},
  title = {Image Mining from Gel Diagrams in Biomedical Publications},
  booktitle = {Proceedings of the 5th International Symposium on Semantic Mining in Biomedicine (SMBM)},
  year = {2012},
}

@inproceedings{kuhn2012amia,
  author = {Kuhn, Tobias and Luong, ThaiBinh and Krauthammer, Michael.},
  title = {Finding and Accessing Diagrams in Biomedical Publications},
  booktitle = {Proceedings of the American Medical Informatics Association (AMIA) 2012 Annual Symposium},
  year = {2012},
}

@article{Krauthammer2012,
annote = {10.1038/ng.2359},
author = {Krauthammer, Michael and Kong, Yong and Ha, Byung Hak and Evans, Perry and Bacchiocchi, Antonella and McCusker, James P and Cheng, Elaine and Davis, Matthew J and Goh, Gerald and Choi, Murim and Ariyan, Stephan and Narayan, Deepak and Dutton-Regester, Ken and Capatana, Ana and Holman, Edna C and Bosenberg, Marcus and Sznol, Mario and Kluger, Harriet M and Brash, Douglas E and Stern, David F and Materin, Miguel A and Lo, Roger S and Mane, Shrikant and Ma, Shuangge and Kidd, Kenneth K and Hayward, Nicholas K and Lifton, Richard P and Schlessinger, Joseph and Boggon, Titus J and Halaban, Ruth},
pages = {1546-1718},
journal = {Nature Genetics},
month = Jul,
publisher = {Nature Publishing Group},
title = {{Exome sequencing identifies recurrent somatic RAC1 mutations in melanoma}},
url = {http://www.nature.com/ng/journal/vaop/ncurrent/abs/ng.2359.html\#supplementary-information},
doi = {http://dx.doi.org/10.1038/ng.2359},
volume = {advance online publication},
year = {2012}
}

@conference{evans2012burden,
  title={{Estimating a gene's mutation burden by the number of synonymous base substitutions}},
  author={Evans, P. and Krauthammer, M.},
  booktitle={Proceedings of the 2012 IEEE International 
             Conference on Bioinformatics and Biomedicine},
  year={2012},
  organization={IEEE Computer Society}
}

% 22373303 
@Article{pmid22373303,
   Author="Holford, M. E.  and McCusker, J. P.  and Cheung, K. H.  and Krauthammer, M. ",
   Title={{A} semantic web framework to integrate cancer omics data with biological knowledge},
   Journal="BMC Bioinformatics",
   Year="2012",
   Volume="13 Suppl 1",
   Pages="S10",
   Month="Jan",
   Abstract={BACKGROUND: The RDF triple provides a simple linguistic means of describing limitless types of information. Triples can be flexibly combined into a unified data source we call a semantic model. Semantic models open new possibilities for the integration of variegated biological data. We use Semantic Web technology to explicate high throughput clinical data in the context of fundamental biological knowledge. We have extended Corvus, a data warehouse which provides a uniform interface to various forms of Omics data, by providing a SPARQL endpoint. With the querying and reasoning tools made possible by the Semantic Web, we were able to explore quantitative semantic models retrieved from Corvus in the light of systematic biological knowledge. RESULTS: For this paper, we merged semantic models containing genomic, transcriptomic and epigenomic data from melanoma samples with two semantic models of functional data - one containing Gene Ontology (GO) data, the other, regulatory networks constructed from transcription factor binding information. These two semantic models were created in an ad hoc manner but support a common interface for integration with the quantitative semantic models. Such combined semantic models allow us to pose significant translational medicine questions. Here, we study the interplay between a cell's molecular state and its response to anti-cancer therapy by exploring the resistance of cancer cells to Decitabine, a demethylating agent. CONCLUSIONS: We were able to generate a testable hypothesis to explain how Decitabine fights cancer - namely, that it targets apoptosis-related gene promoters predominantly in Decitabine-sensitive cell lines, thus conveying its cytotoxic effect by activating the apoptosis pathway. Our research provides a framework whereby similar hypotheses can be developed easily.},
   DOI={http://dx.doi.org/10.1186/1471-2105-13-S1-S10},
   PubMed={http://www.ncbi.nlm.nih.gov/pubmed/22373303},
}

% 22195090 
@Article{pmid22195090,
   Author="Evans, P.  and Krauthammer, M. ",
   Title={{E}xploring the use of social media to measure journal article impact},
   Journal="AMIA Annu Symp Proc",
   Year="2011",
   Volume="2011",
   Pages="374--381",
   Abstract={Science blogs, Twitter commentary, and comments on journal websites represent an immediate response to journal articles, and may help in identifying relevant publications. However, the use of these media for establishing paper impact is not well studied. Using Wikipedia as a proxy for other social media, we explore the correlation between inclusion of a journal article in Wikipedia, and article impact as measured by citation count. We start by cataloging features of PubMed articles cited in Wikipedia. We find that Wikipedia pages referencing the most journal articles are about disorders and diseases, while the most referenced articles in Wikipedia are about genomics. We note that journal articles in Wikipedia have significantly higher citation counts than an equivalent random article subset. We also observe that articles are included in Wikipedia soon after publication. Our data suggest that social media may represent a largely untapped post-publication review resource for assessing paper impact.},
   PubMedCentral={http://www.ncbi.nlm.nih.gov/pmc/articles/PMC3243242} ,
   PubMed={http://www.ncbi.nlm.nih.gov/pubmed/22195090}
}

% 22000016 
@Article{pmid22000016,
   Author="Karreth, F. A.  and Tay, Y.  and Perna, D.  and Ala, U.  and Tan, S. M.  and Rust, A. G.  and DeNicola, G.  and Webster, K. A.  and Weiss, D.  and Perez-Mancera, P. A.  and Krauthammer, M.  and Halaban, R.  and Provero, P.  and Adams, D. J.  and Tuveson, D. A.  and Pandolfi, P. P. ",
   Title={{I}n vivo identification of tumor- suppressive {P}{T}{E}{N} ce{R}{N}{A}s in an oncogenic {B}{R}{A}{F}-induced mouse model of melanoma},
   Journal="Cell",
   Year="2011",
   Volume="147",
   Number="2",
   Pages="382--395",
   Month="Oct",
   Abstract={We recently proposed that competitive endogenous RNAs (ceRNAs) sequester microRNAs to regulate mRNA transcripts containing common microRNA recognition elements (MREs). However, the functional role of ceRNAs in cancer remains unknown. Loss of PTEN, a tumor suppressor regulated by ceRNA activity, frequently occurs in melanoma. Here, we report the discovery of significant enrichment of putative PTEN ceRNAs among genes whose loss accelerates tumorigenesis following Sleeping Beauty insertional mutagenesis in a mouse model of melanoma. We validated several putative PTEN ceRNAs and further characterized one, the ZEB2 transcript. We show that ZEB2 modulates PTEN protein levels in a microRNA-dependent, protein coding-independent manner. Attenuation of ZEB2 expression activates the PI3K/AKT pathway, enhances cell transformation, and commonly occurs in human melanomas and other cancers expressing low PTEN levels. Our study genetically identifies multiple putative microRNA decoys for PTEN, validates ZEB2 mRNA as a bona fide PTEN ceRNA, and demonstrates that abrogated ZEB2 expression cooperates with BRAF(V600E) to promote melanomagenesis.},
   PubMedCentral={http://www.ncbi.nlm.nih.gov/pmc/articles/PMC3236086},
   DOI={http://dx.doi.org/10.1016/j.cell.2011.09.032},
   PubMed={http://www.ncbi.nlm.nih.gov/pubmed/22000016}
}

% 21683344 
@Article{pmid21683344,
   Author="Xie, P.  and Kranzler, H. R.  and Krauthammer, M.  and Cosgrove, K. P.  and Oslin, D.  and Anton, R. F.  and Farrer, L. A.  and Picciotto, M. R.  and Krystal, J. H.  and Zhao, H.  and Gelernter, J. ",
   Title={{R}are nonsynonymous variants in alpha-4 nicotinic acetylcholine receptor gene protect against nicotine dependence},
   Journal="Biol. Psychiatry",
   Year="2011",
   Volume="70",
   Number="6",
   Pages="528--536",
   Month="Sep",
   Abstract={Several studies report association of alpha-4 nicotinic acetylcholine receptors (encoded by CHRNA4) with nicotine dependence (ND). A meta-analysis of genomewide linkage studies for ND implicated a single chromosomal region, which includes CHRNA4, as genome-wide significant.\\ After establishing that common variants are unlikely to completely account for this linkage, we investigated the distribution of CHRNA4 rare variants by sequencing the coding exons and flanking intronic regions of CHRNA4 in 209 European American (EA) ND cases and 183 EA control subjects. Because most of the rare variants that we detected (and all nonsynonymous changes) were in Exon 5, we sequenced Exon 5 in an additional 1000 ND cases and 1000 non-ND comparison subjects, both of which included equal numbers of EAs and African Americans.\\ Comparison subjects had a higher frequency of rare nonsynonymous variants in the Exon 5 region (encoding the large intercellular loop of the Î±4 subunit; Fisher's Exact Test p = .009; association test p = .009, odds ratio = .43; weighted-sum method p = .014), indicating a protective effect against ND. Considering data from the two stages combined and only nonsynonymous variants predicted to alter protein function, the association was stronger (Fisher's Exact Test p = .005; association test p = .008, odds ratio = .29; weighted-sum method p = .005). Single-photon emission computed tomography imaging results were consistent with functionality.\\ CHRNA4 functional rare variants may reduce ND risk. This is the first demonstration that rare functional variants at a candidate locus protect against substance dependence to our knowledge, suggesting a novel mechanism of substance dependence heritability that is potentially of general importance.},
   PubMedCentral={http://www.ncbi.nlm.nih.gov/pmc/articles/PMC3199609},
   DOI={http://dx.doi.org/10.1016/j.biopsych.2011.04.017},
   PubMed={http://www.ncbi.nlm.nih.gov/pubmed/21683344}
}

% 21543894 
@Article{pmid21543894,
   Author="Chan, E.  and Patel, R.  and Nallur, S.  and Ratner, E.  and Bacchiocchi, A.  and Hoyt, K.  and Szpakowski, S.  and Godshalk, S.  and Ariyan, S.  and Sznol, M.  and Halaban, R.  and Krauthammer, M.  and Tuck, D.  and Slack, F. J.  and Weidhaas, J. B. ",
   Title={{M}icro{R}{N}{A} signatures differentiate melanoma subtypes},
   Journal="Cell Cycle",
   Year="2011",
   Volume="10",
   Number="11",
   Pages="1845--1852",
   Month="Jun",
   Abstract={Melanoma is an aggressive cancer that is highly resistance to therapies once metastasized. We studied microRNA (miRNA) expression in clinical melanoma subtypes and evaluated different miRNA signatures in the background of gain of function somatic and inherited mutations associated with melanoma. Total RNA from 42 patient derived primary melanoma cell lines and three independent normal primary melanocyte cell cultures was evaluated by miRNA array. MiRNA expression was then analyzed comparing subtypes and additional clinicopathologic criteria including somatic mutations. The prevalence and association of an inherited variant in a miRNA binding site in the 3'UTR of the KRAS oncogene, referred to as the KRAS-variant, was also evaluated. We show that seven miRNAs, miR-142-3p, miR-486, miR-214, miR-218, miR-362, miR-650 and miR-31, were significantly correlated with acral as compared to non-acral melanomas (p < 0.04). In addition, we discovered that the KRAS-variant was enriched in non-acral melanoma (25%), and that miR-137 under expression was significantly associated with melanomas with the KRAS-variant. Our findings indicate that miRNAs are differentially expressed in melanoma subtypes and that their misregulation can be impacted by inherited gene variants, supporting the hypothesis that miRNA misregulation reflects biological differences in melanoma.},
   PubMedCentral={http://www.ncbi.nlm.nih.gov/pmc/articles/PMC3233487},
   PubMed={http://www.ncbi.nlm.nih.gov/pubmed/21543894}
}

% 21521745 
@Article{pmid21521745,
   Author="Tworkoski, K.  and Singhal, G.  and Szpakowski, S.  and Zito, C. I.  and Bacchiocchi, A.  and Muthusamy, V.  and Bosenberg, M.  and Krauthammer, M.  and Halaban, R.  and Stern, D. F. ",
   Title={{P}hosphoproteomic screen identifies potential therapeutic targets in melanoma},
   Journal="Mol. Cancer Res.",
   Year="2011",
   Volume="9",
   Number="6",
   Pages="801--812",
   Month="Jun",
   Abstract={Therapies directed against receptor tyrosine kinases are effective in many cancer subtypes, including lung and breast cancer. We used a phosphoproteomic platform to identify active receptor tyrosine kinases that might represent therapeutic targets in a panel of 25 melanoma cell strains. We detected activated receptors including TYRO3, AXL, MERTK, EPHB2, MET, IGF1R, EGFR, KIT, HER3, and HER4. Statistical analysis of receptor tyrosine kinase activation as well as ligand and receptor expression indicates that some receptors, such as FGFR3, may be activated via autocrine circuits. Short hairpin RNA knockdown targeting three of the active kinases identified in the screen, AXL, HER3, and IGF1R, inhibited the proliferation of melanoma cells and knockdown of active AXL also reduced melanoma cell migration. The changes in cellular phenotype observed on AXL knockdown seem to be modulated via the STAT3 signaling pathway, whereas the IGF1R-dependent alterations seem to be regulated by the AKT signaling pathway. Ultimately, this study identifies several novel targets for therapeutic intervention in melanoma.},
   PubMedCentral={http://www.ncbi.nlm.nih.gov/pmc/articles/PMC3117976},
   DOI={http://dx.doi.org/10.1158/1541-7786.MCR-10-0512},
   PubMed={http://www.ncbi.nlm.nih.gov/pubmed/21521745}
}

% 21149339 
@Article{pmid21149339,
   Author="Garla, V.  and Kong, Y.  and Szpakowski, S.  and Krauthammer, M. ",
   Title={{M}{U}2{A}--reconciling the genome and transcriptome to determine the effects of base substitutions},
   Journal="Bioinformatics",
   Year="2011",
   Volume="27",
   Number="3",
   Pages="416--418",
   Month="Feb",
   Abstract={MOTIVATION: Next-generation sequencing technologies enable the identification of sequence variation in the genome and transcriptome. Differences between the reference genome and transcript libraries complicate the determination of the effect of genomic sequence variants on protein products; similarly, these differences complicate the mapping of sequence variants found in transcripts to their respective genomic position. We have developed MU2A, a publicly available web service for variant annotation that reconciles differences between the genome and transcriptome, enabling the rapid and accurate determination of the effects of genomic variants on protein products, and the mapping of variants detected in transcripts to genomic coordinates. The MU2A web service is available at http://krauthammerlab.med.yale.edu/mu2a. We have released MU2A as open source, available at http://code.google.com/p/mu2a/.},
   PubMedCentral={http://www.ncbi.nlm.nih.gov/pmc/articles/PMC3031033},
   DOI={http://dx.doi.org/10.1093/bioinformatics/btq658},
   PubMed={http://www.ncbi.nlm.nih.gov/pubmed/21149339}
}

% 20887803 
@Article{pmid20887803,
   Author="Xu, S.  and Krauthammer, M. ",
   Title={{A} new pivoting and iterative text detection algorithm for biomedical images},
   Journal="J Biomed Inform",
   Year="2010",
   Volume="43",
   Number="6",
   Pages="924--931",
   Month="Dec",
   Abstract={There is interest to expand the reach of literature mining to include the analysis of biomedical images, which often contain a paper's key findings. Examples include recent studies that use Optical Character Recognition (OCR) to extract image text, which is used to boost biomedical image retrieval and classification. Such studies rely on the robust identification of text elements in biomedical images, which is a non-trivial task. In this work, we introduce a new text detection algorithm for biomedical images based on iterative projection histograms. We study the effectiveness of our algorithm by evaluating the performance on a set of manually labeled random biomedical images, and compare the performance against other state-of-the-art text detection algorithms. We demonstrate that our projection histogram-based text detection approach is well suited for text detection in biomedical images, and that the iterative application of the algorithm boosts performance to an F score of .60. We provide a C++ implementation of our algorithm freely available for academic use.},
   PubMedCentral={http://www.ncbi.nlm.nih.gov/pmc/articles/PMC3265968},
   DOI={http://dx.doi.org/10.1016/j.jbi.2010.09.006},
   PubMed={http://www.ncbi.nlm.nih.gov/pubmed/20887803}
}

% 20149136 
@Article{pmid20149136,
   Author="Halaban, R.  and Zhang, W.  and Bacchiocchi, A.  and Cheng, E.  and Parisi, F.  and Ariyan, S.  and Krauthammer, M.  and McCusker, J. P.  and Kluger, Y.  and Sznol, M. ",
   Title={{P}{L}{X}4032, a selective {B}{R}{A}{F}({V}600{E}) kinase inhibitor, activates the {E}{R}{K} pathway and enhances cell migration and proliferation of {B}{R}{A}{F} melanoma cells},
   Journal="Pigment Cell Melanoma Res",
   Year="2010",
   Volume="23",
   Number="2",
   Pages="190--200",
   Month="Apr",
   Abstract={BRAF(V600E/K) is a frequent mutationally active tumor-specific kinase in melanomas that is currently targeted for therapy by the specific inhibitor PLX4032. Our studies with melanoma tumor cells that are BRAF(V600E/K) and BRAF(WT) showed that, paradoxically, while PLX4032 inhibited ERK1/2 in the highly sensitive BRAF(V600E/K), it activated the pathway in the resistant BRAF(WT) cells, via RAF1 activation, regardless of the status of mutations in NRAS or PTEN. The persistently active ERK1/2 triggered downstream effectors in BRAF(WT) melanoma cells and induced changes in the expression of a wide-spectrum of genes associated with cell cycle control. Furthermore, PLX4032 increased the rate of proliferation of growth factor-dependent NRAS Q61L mutant primary melanoma cells, reduced cell adherence and increased mobility of cells from advanced lesions. The results suggest that the drug can confer an advantage to BRAF(WT) primary and metastatic tumor cells in vivo and provide markers for monitoring clinical responses.},
   PubMedCentral={http://www.ncbi.nlm.nih.gov/pmc/articles/PMC2848976},
   DOI={http://dx.doi.org/10.1111/j.1755-148X.2010.00685.x},
   PubMed={http://www.ncbi.nlm.nih.gov/pubmed/20149136}
}

% 20144234 
@Article{pmid20144234,
   Author="Rubinstein, J. C.  and Tran, N.  and Ma, S.  and Halaban, R.  and Krauthammer, M. ",
   Title={{G}enome-wide methylation and expression profiling identifies promoter characteristics affecting demethylation-induced gene up-regulation in melanoma},
   Journal="BMC Med Genomics",
   Year="2010",
   Volume="3",
   Pages="4",
   Abstract={Abberant DNA methylation at CpG dinucleotides represents a common mechanism of transcriptional silencing in cancer. Since CpG methylation is a reversible event, tumor supressor genes that have undergone silencing through this mechanism represent promising targets for epigenetically active anti-cancer therapy. The cytosine analog 5-aza-2'-deoxycytidine (decitabine) induces genomic hypomethylation by inhibiting DNA methyltransferase, and is an example of an epigenetic agent that is thought to act by up-regulating silenced genes.\\ It is unclear why decitabine causes some silenced loci to re-express, while others remain inactive. By applying data-mining techniques to large-scale datasets, we attempted to elucidate the qualities of promoter regions that define susceptibility to the drug's action. Our experimental data, derived from melanoma cell strains, consist of genome-wide gene expression data before and after treatment with decitabine, as well as genome-wide data on un-treated promoter methylation status, and validation of specific genes by bisulfite sequencing.\\ We show that the combination of promoter CpG content and methylation level informs the ability of decitabine treatment to up-regulate gene expression. Promoters with high methylation levels and intermediate CpG content appear most susceptible to up-regulation by decitabine, whereas few of those highly methylated promoters with high CpG content are up-regulated. For promoters with low methylation levels, those with high CpG content are more likely to be up-regulated, whereas those with low CpG content are underrepresented among up-regulated genes.\\ Clinically, elucidating the patterns of action of decitabine could aid in predicting the likelihood of up-regulating epigenetically silenced tumor suppressor genes and others from pathways involved with tumor biology. As a first step toward an eventual translational application, we build a classifier to predict gene up-regulation based on promoter methylation and CpG content, which achieves a performance of 0.77 AUC.},
   PubMedCentral={http://www.ncbi.nlm.nih.gov/pmc/articles/PMC2843643},
   DOI={http://dx.doi.org/10.1186/1755-8794-3-4},
   PubMed={http://www.ncbi.nlm.nih.gov/pubmed/20144234}
}

% 19884546 
@Article{pmid19884546,
   Author="Gould Rothberg, B. E.  and Berger, A. J.  and Molinaro, A. M.  and Subtil, A.  and Krauthammer, M. O.  and Camp, R. L.  and Bradley, W. R.  and Ariyan, S.  and Kluger, H. M.  and Rimm, D. L. ",
   Title={{M}elanoma prognostic model using tissue microarrays and genetic algorithms},
   Journal="J. Clin. Oncol.",
   Year="2009",
   Volume="27",
   Number="34",
   Pages="5772--5780",
   Month="Dec",
   Abstract={As a result of the questionable risk-to-benefit ratio of adjuvant therapies, stage II melanoma is currently managed by observation because available clinicopathologic parameters cannot identify the 20% to 60% of such patients likely to develop metastatic disease. Here, we propose a multimarker molecular prognostic assay that can help triage patients at increased risk of recurrence.\\ Protein expression for 38 candidates relevant to melanoma oncogenesis was evaluated using the automated quantitative analysis (AQUA) method for immunofluorescence-based immunohistochemistry in formalin-fixed, paraffin-embedded specimens from a cohort of 192 primary melanomas collected during 1959 to 1994. The prognostic assay was built using a genetic algorithm and validated on an independent cohort of 246 serial primary melanomas collected from 1997 to 2004.\\ Multiple iterations of the genetic algorithm yielded a consistent five-marker solution. A favorable prognosis was predicted by ATF2 ln(non-nuclear/nuclear AQUA score ratio) of more than -0.052, p21(WAF1) nuclear compartment AQUA score of more than 12.98, p16(INK4A) ln(non-nuclear/nuclear AQUA score ratio) of < or = -0.083, beta-catenin total AQUA score of more than 38.68, and fibronectin total AQUA score of < or = 57.93. Primary tumors that met at least four of these five conditions were considered a low-risk group, and those that met three or fewer conditions formed a high-risk group (log-rank P < .0001). Multivariable proportional hazards analysis adjusting for clinicopathologic parameters shows that the high-risk group has significantly reduced survival on both the discovery (hazard ratio = 2.84; 95% CI, 1.46 to 5.49; P = .002) and validation (hazard ratio = 2.72; 95% CI, 1.12 to 6.58; P = .027) cohorts.\\ This multimarker prognostic assay, an independent determinant of melanoma survival, might be beneficial in improving the selection of stage II patients for adjuvant therapy.},
   PubMedCentral={http://www.ncbi.nlm.nih.gov/pmc/articles/PMC2792999},
   DOI={http://dx.doi.org/10.1200/JCO.2009.22.8239},
   PubMed={http://www.ncbi.nlm.nih.gov/pubmed/19884546}
}

% 19796399 
@Article{pmid19796399,
   Author="McCusker, J. P.  and Phillips, J. A.  and Gonzalez Beltran, A.  and Finkelstein, A.  and Krauthammer, M. ",
   Title={{S}emantic web data warehousing for ca{G}rid},
   Journal="BMC Bioinformatics",
   Year="2009",
   Volume="10 Suppl 10",
   Pages="S2",
   Abstract={The National Cancer Institute (NCI) is developing caGrid as a means for sharing cancer-related data and services. As more data sets become available on caGrid, we need effective ways of accessing and integrating this information. Although the data models exposed on caGrid are semantically well annotated, it is currently up to the caGrid client to infer relationships between the different models and their classes. In this paper, we present a Semantic Web-based data warehouse (Corvus) for creating relationships among caGrid models. This is accomplished through the transformation of semantically-annotated caBIG Unified Modeling Language (UML) information models into Web Ontology Language (OWL) ontologies that preserve those semantics. We demonstrate the validity of the approach by Semantic Extraction, Transformation and Loading (SETL) of data from two caGrid data sources, caTissue and caArray, as well as alignment and query of those sources in Corvus. We argue that semantic integration is necessary for integration of data from distributed web services and that Corvus is a useful way of accomplishing this. Our approach is generalizable and of broad utility to researchers facing similar integration challenges.},
   PubMedCentral={http://www.ncbi.nlm.nih.gov/pmc/articles/PMC2755823},
   DOI={http://dx.doi.org/10.1186/1471-2105-10-S10-S2},
   PubMed={http://www.ncbi.nlm.nih.gov/pubmed/19796399}
}

% 19761571 
@Article{pmid19761571,
   Author="Shivakumar, P.  and Krauthammer, M. ",
   Title={{S}tructural similarity assessment for drug sensitivity prediction in cancer},
   Journal="BMC Bioinformatics",
   Year="2009",
   Volume="10 Suppl 9",
   Pages="S17",
   Abstract={The ability to predict drug sensitivity in cancer is one of the exciting promises of pharmacogenomic research. Several groups have demonstrated the ability to predict drug sensitivity by integrating chemo-sensitivity data and associated gene expression measurements from large anti-cancer drug screens such as NCI-60. The general approach is based on comparing gene expression measurements from sensitive and resistant cancer cell lines and deriving drug sensitivity profiles consisting of lists of genes whose expression is predictive of response to a drug. Importantly, it has been shown that such profiles are generic and can be applied to cancer cell lines that are not part of the anti-cancer screen. However, one limitation is that the profiles can not be generated for untested drugs (i.e., drugs that are not part of an anti-cancer drug screen). In this work, we propose using an existing drug sensitivity profile for drug A as a substitute for an untested drug B given high structural similarities between drugs A and B.\\ We first show that structural similarity between pairs of compounds in the NCI-60 dataset highly correlates with the similarity between their activities across the cancer cell lines. This result shows that structurally similar drugs can be expected to have a similar effect on cancer cell lines. We next set out to test our hypothesis that we can use existing drug sensitivity profiles as substitute profiles for untested drugs. In a cross-validation experiment, we found that the use of substitute profiles is possible without a significant loss of prediction accuracy if the substitute profile was generated from a compound with high structural similarity to the untested compound.\\ Anti-cancer drug screens are a valuable resource for generating omics-based drug sensitivity profiles. We show that it is possible to extend the usefulness of existing screens to untested drugs by deriving substitute sensitivity profiles from structurally similar drugs part of the screen.},
   PubMedCentral={http://www.ncbi.nlm.nih.gov/pmc/articles/PMC2745688},
   DOI={http://dx.doi.org/10.1186/1471-2105-10-S9-S17},
   PubMed={http://www.ncbi.nlm.nih.gov/pubmed/19761571}
}

% 19491193 
@Article{pmid19491193,
   Author="Koga, Y.  and Pelizzola, M.  and Cheng, E.  and Krauthammer, M.  and Sznol, M.  and Ariyan, S.  and Narayan, D.  and Molinaro, A. M.  and Halaban, R.  and Weissman, S. M. ",
   Title={{G}enome-wide screen of promoter methylation identifies novel markers in melanoma},
   Journal="Genome Res.",
   Year="2009",
   Volume="19",
   Number="8",
   Pages="1462--1470",
   Month="Aug",
   Abstract={DNA methylation is an important component of epigenetic modifications, which influences the transcriptional machinery aberrant in many human diseases. In this study we present the first genome-wide integrative analysis of promoter methylation and gene expression for the identification of methylation markers in melanoma. Genome-wide promoter methylation and gene expression of eight early-passage human melanoma cell strains were compared with newborn and adult melanocytes. We used linear mixed effect models (LME) in combination with a series of filters based on the localization of promoter methylation relative to the transcription start site, overall promoter CpG content, and differential gene expression to discover DNA methylation markers. This approach identified 76 markers, of which 68 were hyper- and eight hypomethylated (LME, P < 0.05). Promoter methylation and differential gene expression of five markers (COL1A2, NPM2, HSPB6, DDIT4L, MT1G) were validated by sequencing of bisulfite-modified DNA and real-time reverse transcriptase PCR, respectively. Importantly, the incidence of promoter methylation of the validated markers increased moderately in early and significantly in advanced-stage melanomas, using early-passage cell strains and snap-frozen tissues (n = 18 and n = 24, respectively) compared with normal melanocytes and nevi (n = 11 and n = 9, respectively). Our approach allows robust identification of methylation markers that can be applied to other studies involving genome-wide promoter methylation. In conclusion, this study represents the first unbiased systematic effort to determine methylation markers in melanoma and revealed several novel genes regulated by promoter methylation that were not described in cancer cells before.},
   PubMedCentral={http://www.ncbi.nlm.nih.gov/pmc/articles/PMC2720187},
   DOI={http://dx.doi.org/10.1101/gr.091447.109},
   PubMed={http://www.ncbi.nlm.nih.gov/pubmed/19491193}
}

% 19234609 
@Article{pmid19234609,
   Author="Halaban, R.  and Krauthammer, M.  and Pelizzola, M.  and Cheng, E.  and Kovacs, D.  and Sznol, M.  and Ariyan, S.  and Narayan, D.  and Bacchiocchi, A.  and Molinaro, A.  and Kluger, Y.  and Deng, M.  and Tran, N.  and Zhang, W.  and Picardo, M.  and Enghild, J. J. ",
   Title={{I}ntegrative analysis of epigenetic modulation in melanoma cell response to decitabine: clinical implications},
   Journal="PLoS ONE",
   Year="2009",
   Volume="4",
   Number="2",
   Pages="e4563",
   Abstract={Decitabine, an epigenetic modifier that reactivates genes otherwise suppressed by DNA promoter methylation, is effective for some, but not all cancer patients, especially those with solid tumors. It is commonly recognized that to overcome resistance and improve outcome, treatment should be guided by tumor biology, which includes genotype, epigenotype, and gene expression profile. We therefore took an integrative approach to better understand melanoma cell response to clinically relevant dose of decitabine and identify complementary targets for combined therapy. We employed eight different melanoma cell strains, determined their growth, apoptotic and DNA damage responses to increasing doses of decitabine, and chose a low, clinically relevant drug dose to perform whole-genome differential gene expression, bioinformatic analysis, and protein validation studies. The data ruled out the DNA damage response, demonstrated the involvement of p21(Cip1) in a p53-independent manner, identified the TGFbeta pathway genes CLU and TGFBI as markers of sensitivity to decitabine and revealed an effect on histone modification as part of decitabine-induced gene expression. Mutation analysis and knockdown by siRNA implicated activated beta-catenin/MITF, but not BRAF, NRAS or PTEN mutations as a source for resistance. The importance of protein stability predicted from the results was validated by the synergistic effect of Bortezomib, a proteasome inhibitor, in enhancing the growth arrest of decitabine in otherwise resistant melanoma cells. Our integrative analysis show that improved therapy can be achieved by comprehensive analysis of cancer cells, identified biomarkers for patient's selection and monitoring response, as well as targets for improved combination therapy.},
   PubMedCentral={http://www.ncbi.nlm.nih.gov/pmc/articles/PMC2642998},
   DOI={http://dx.doi.org/10.1371/journal.pone.0004563},
   PubMed={http://www.ncbi.nlm.nih.gov/pubmed/19234609}
}

% 19156209 
@Article{pmid19156209,
   Author="Nath, A. K.  and Krauthammer, M.  and Li, P.  and Davidov, E.  and Butler, L. C.  and Copel, J.  and Katajamaa, M.  and Oresic, M.  and Buhimschi, I.  and Buhimschi, C.  and Snyder, M.  and Madri, J. A. ",
   Title={{P}roteomic-based detection of a protein cluster dysregulated during cardiovascular development identifies biomarkers of congenital heart defects},
   Journal="PLoS ONE",
   Year="2009",
   Volume="4",
   Number="1",
   Pages="e4221",
   Abstract={Cardiovascular development is vital for embryonic survival and growth. Early gestation embryo loss or malformation has been linked to yolk sac vasculopathy and congenital heart defects (CHDs). However, the molecular pathways that underlie these structural defects in humans remain largely unknown hindering the development of molecular-based diagnostic tools and novel therapies.\\ Murine embryos were exposed to high glucose, a condition known to induce cardiovascular defects in both animal models and humans. We further employed a mass spectrometry-based proteomics approach to identify proteins differentially expressed in embryos with defects from those with normal cardiovascular development. The proteins detected by mass spectrometry (WNT16, ST14, Pcsk1, Jumonji, Morca2a, TRPC5, and others) were validated by Western blotting and immunoflorescent staining of the yolk sac and heart. The proteins within the proteomic dataset clustered to adhesion/migration, differentiation, transport, and insulin signaling pathways. A functional role for several proteins (WNT16, ADAM15 and NOGO-A/B) was demonstrated in an ex vivo model of heart development. Additionally, a successful application of a cluster of protein biomarkers (WNT16, ST14 and Pcsk1) as a prenatal screen for CHDs was confirmed in a study of human amniotic fluid (AF) samples from women carrying normal fetuses and those with CHDs.\\ The novel finding that WNT16, ST14 and Pcsk1 protein levels increase in fetuses with CHDs suggests that these proteins may play a role in the etiology of human CHDs. The information gained through this bed-side to bench translational approach contributes to a more complete understanding of the protein pathways dysregulated during cardiovascular development and provides novel avenues for diagnostic and therapeutic interventions, beneficial to fetuses at risk for CHDs.},
   PubMedCentral={http://www.ncbi.nlm.nih.gov/pmc/articles/PMC2626248},
   DOI={http://dx.doi.org/10.1371/journal.pone.0004221},
   PubMed={http://www.ncbi.nlm.nih.gov/pubmed/19156209}
}

% 20351935 
@Article{pmid20351935,
   Author="Tran, N.  and Alves, P.  and Ma, S.  and Krauthammer, M. ",
   Title={{E}nriching {P}ub{M}ed related article search with sentence level co-citations},
   Journal="AMIA Annu Symp Proc",
   Year="2009",
   Volume="2009",
   Pages="650--654",
   Abstract={PubMed related article links identify closely related articles and enhance our ability to navigate the biomedical literature. They are derived by calculating the word similarity between two articles, relating articles with overlapping word content. In this paper, we propose to enrich PubMed with a new type of related article link based on citations within a single sentence (i.e. sentence level co-citations or SLCs). Using different similarity metrics, we demonstrated that articles linked by SLCs are highly related. We also showed that only half of SLCs are found among PubMed related article links. Additionally, we discuss how the citing sentence of an SLC explains the connection between two articles.},
   PubMedCentral={http://www.ncbi.nlm.nih.gov/pmc/articles/PMC2815371},
   PubMed={http://www.ncbi.nlm.nih.gov/pubmed/20351935}
}

% 20351934 
@Article{pmid20351934,
   Author="Tran, N.  and Michel, G.  and Krauthammer, M.  and Shiffman, R. N. ",
   Title={{E}mbedding the guideline elements model in web ontology language},
   Journal="AMIA Annu Symp Proc",
   Year="2009",
   Volume="2009",
   Pages="645--649",
   Abstract={The Guideline Elements Model (GEM) uses XML to represent the heterogeneous knowledge contained in clinical practice guidelines. GEM has important applications in computer aided guideline authoring and clinical decision support systems. However, its XML representation format could limit its potential impact, as semantic web ontology languages, such as OWL, are becoming major knowledge representation frameworks in medical informatics. In this work, we present a faithful translation of GEM from XML into OWL. This translation is intended to keep the knowledge model of GEM intact, as this knowledge model has been carefully designed and has become a recognized standard. An OWL representation would make GEM more applicable in medical informatics systems that rely on semantic web. This work will also be the initial step in making GEM a guideline recommendation ontology.},
   PubMedCentral={http://www.ncbi.nlm.nih.gov/pmc/articles/PMC2815420},
   PubMed={http://www.ncbi.nlm.nih.gov/pubmed/20351934}
}

% 18999241 
@Article{pmid18999241,
   Author="Xu, S.  and McCusker, J.  and Krauthammer, M. ",
   Title={{E}xploring the use of image text for biomedical literature retrieval},
   Journal="AMIA Annu Symp Proc",
   Year="2008",
   Pages="1186",
   Abstract={In biomedical publications, figures and images concisely summarize a paper's experimental findings and results. Recent studies have therefore explored the use of images to assist in information retrieval (IR) in biomedicine, mostly based on mining the image caption content. We extend this approach by mining the image text, which refers to the text inside biomedical figures and images. In this work, we discuss the distinct advantages of using image text for biomedical IR and present a prototype search engine implementing the idea.},
   PubMed={http://www.ncbi.nlm.nih.gov/pubmed/18999241}
}

% 18834497 
@Article{pmid18834497,
   Author="Leitner, F.  and Krallinger, M.  and Rodriguez-Penagos, C.  and Hakenberg, J.  and Plake, C.  and Kuo, C. J.  and Hsu, C. N.  and Tsai, R. T.  and Hung, H. C.  and Lau, W. W.  and Johnson, C. A.  and Saetre, R.  and Yoshida, K.  and Chen, Y. H.  and Kim, S.  and Shin, S. Y.  and Zhang, B. T.  and Baumgartner, W. A.  and Hunter, L.  and Haddow, B.  and Matthews, M.  and Wang, X.  and Ruch, P.  and Ehrler, F.  and Ozgur, A.  and Erkan, G.  and Radev, D. R.  and Krauthammer, M.  and Luong, T.  and Hoffmann, R.  and Sander, C.  and Valencia, A. ",
   Title={{I}ntroducing meta-services for biomedical information extraction},
   Journal="Genome Biol.",
   Year="2008",
   Volume="9 Suppl 2",
   Pages="S6",
   Abstract={We introduce the first meta-service for information extraction in molecular biology, the BioCreative MetaServer (BCMS; http://bcms.bioinfo.cnio.es/). This prototype platform is a joint effort of 13 research groups and provides automatically generated annotations for PubMed/Medline abstracts. Annotation types cover gene names, gene IDs, species, and protein-protein interactions. The annotations are distributed by the meta-server in both human and machine readable formats (HTML/XML). This service is intended to be used by biomedical researchers and database annotators, and in biomedical language processing. The platform allows direct comparison, unified access, and result aggregation of the annotations.},
   PubMedCentral={http://www.ncbi.nlm.nih.gov/pmc/articles/PMC2559990},
   DOI={http://dx.doi.org/10.1186/gb-2008-9-s2-s6},
   PubMed={http://www.ncbi.nlm.nih.gov/pubmed/18834497}
}

% 18834494 
@Article{pmid18834494,
   Author="Morgan, A. A.  and Lu, Z.  and Wang, X.  and Cohen, A. M.  and Fluck, J.  and Ruch, P.  and Divoli, A.  and Fundel, K.  and Leaman, R.  and Hakenberg, J.  and Sun, C.  and Liu, H. H.  and Torres, R.  and Krauthammer, M.  and Lau, W. W.  and Liu, H.  and Hsu, C. N.  and Schuemie, M.  and Cohen, K. B.  and Hirschman, L. ",
   Title={{O}verview of {B}io{C}reative {I}{I} gene normalization},
   Journal="Genome Biol.",
   Year="2008",
   Volume="9 Suppl 2",
   Pages="S3",
   Abstract={The goal of the gene normalization task is to link genes or gene products mentioned in the literature to biological databases. This is a key step in an accurate search of the biological literature. It is a challenging task, even for the human expert; genes are often described rather than referred to by gene symbol and, confusingly, one gene name may refer to different genes (often from different organisms). For BioCreative II, the task was to list the Entrez Gene identifiers for human genes or gene products mentioned in PubMed/MEDLINE abstracts. We selected abstracts associated with articles previously curated for human genes. We provided 281 expert-annotated abstracts containing 684 gene identifiers for training, and a blind test set of 262 documents containing 785 identifiers, with a gold standard created by expert annotators. Inter-annotator agreement was measured at over 90%.\\ Twenty groups submitted one to three runs each, for a total of 54 runs. Three systems achieved F-measures (balanced precision and recall) between 0.80 and 0.81. Combining the system outputs using simple voting schemes and classifiers obtained improved results; the best composite system achieved an F-measure of 0.92 with 10-fold cross-validation. A 'maximum recall' system based on the pooled responses of all participants gave a recall of 0.97 (with precision 0.23), identifying 763 out of 785 identifiers.\\ Major advances for the BioCreative II gene normalization task include broader participation (20 versus 8 teams) and a pooled system performance comparable to human experts, at over 90% agreement. These results show promise as tools to link the literature with biological databases.},
   PubMedCentral={http://www.ncbi.nlm.nih.gov/pmc/articles/PMC2559987},
   DOI={http://dx.doi.org/10.1186/gb-2008-9-s2-s3},
   PubMed={http://www.ncbi.nlm.nih.gov/pubmed/18834494}
}

% 18765822 
@Article{pmid18765822,
   Author="Pelizzola, M.  and Koga, Y.  and Urban, A. E.  and Krauthammer, M.  and Weissman, S.  and Halaban, R.  and Molinaro, A. M. ",
   Title={{M}{E}{D}{M}{E}: an experimental and analytical methodology for the estimation of {D}{N}{A} methylation levels based on microarray derived {M}e{D}{I}{P}-enrichment},
   Journal="Genome Res.",
   Year="2008",
   Volume="18",
   Number="10",
   Pages="1652--1659",
   Month="Oct",
   Abstract={DNA methylation is an important component of epigenetic modifications that influences the transcriptional machinery and is aberrant in many human diseases. Several methods have been developed to map DNA methylation for either limited regions or genome-wide. In particular, antibodies specific for methylated CpG have been successfully applied in genome-wide studies. However, despite the relevance of the obtained results, the interpretation of antibody enrichment is not trivial. Of greatest importance, the coupling of antibody-enriched methylated fragments with microarrays generates DNA methylation estimates that are not linearly related to the true methylation level. Here, we present an experimental and analytical methodology, MEDME (modeling experimental data with MeDIP enrichment), to obtain enhanced estimates that better describe the true values of DNA methylation level throughout the genome. We propose an experimental scenario for evaluating the true relationship in a high-throughput setting and a model-based analysis to predict the absolute and relative DNA methylation levels. We successfully applied this model to evaluate DNA methylation status of normal human melanocytes compared to a melanoma cell strain. Despite the low resolution typical of methods based on immunoprecipitation, we show that model-derived estimates of DNA methylation provide relatively high correlation with measured absolute and relative levels, as validated by bisulfite genomic DNA sequencing. Importantly, the model-derived DNA methylation estimates simplify the interpretation of the results both at single-loci and at chromosome-wide levels.},
   PubMedCentral={http://www.ncbi.nlm.nih.gov/pmc/articles/PMC2556264},
   DOI={http://dx.doi.org/10.1101/gr.080721.108},
   PubMed={http://www.ncbi.nlm.nih.gov/pubmed/18765822}
}

% 18694233 
@Article{pmid18694233,
   Author="Tran, N.  and Luong, T.  and Krauthammer, M. ",
   Title={{M}apping terms to {U}{M}{L}{S} concepts of the same semantic type},
   Journal="AMIA Annu Symp Proc",
   Year="2007",
   Pages="1136",
   Abstract={We are interested in mapping terms from the biomedical literature to controlled terminologies. For clinical and related terms, we rely on the MetaMap program for mapping terms to the UMLS Metathesaurus, accepting term assignments that have a reasonable match score. In a sizable number of cases, terms are ambiguous, and MetaMap proposes several mapping candidates. To address these cases prior studies investigated Word Sense Disambiguation (WSD) strategies for selecting between concepts of different semantic types. Here, we investigated the situation where MetaMap proposes concepts that share the same semantic type. We present an ontology-based strategy for selecting between these concepts.},
   PubMed={http://www.ncbi.nlm.nih.gov/pubmed/18694233}
}

% 18614584 
@Article{pmid18614584,
   Author="Xu, S.  and McCusker, J.  and Krauthammer, M. ",
   Title={{Y}ale {I}mage {F}inder ({Y}{I}{F}): a new search engine for retrieving biomedical images},
   Journal="Bioinformatics",
   Year="2008",
   Volume="24",
   Number="17",
   Pages="1968--1970",
   Month="Sep",
   Abstract={Yale Image Finder (YIF) is a publicly accessible search engine featuring a new way of retrieving biomedical images and associated papers based on the text carried inside the images. Image queries can also be issued against the image caption, as well as words in the associated paper abstract and title. A typical search scenario using YIF is as follows: a user provides few search keywords and the most relevant images are returned and presented in the form of thumbnails. Users can click on the image of interest to retrieve the high resolution image. In addition, the search engine will provide two types of related images: those that appear in the same paper, and those from other papers with similar image content. Retrieved images link back to their source papers, allowing users to find related papers starting with an image of interest. Currently, YIF has indexed over 140 000 images from over 34 000 open access biomedical journal papers. AVAILABILITY: http://krauthammerlab.med.yale.edu/imagefinder/},
   PubMedCentral={http://www.ncbi.nlm.nih.gov/pmc/articles/PMC2732221},
   DOI={http://dx.doi.org/10.1093/bioinformatics/btn340},
   PubMed={http://www.ncbi.nlm.nih.gov/pubmed/18614584}
}

% 17923450 
@Article{pmid17923450,
   Author="Smith, A.  and Cheung, K.  and Krauthammer, M.  and Schultz, M.  and Gerstein, M. ",
   Title={{L}everaging the structure of the {S}emantic {W}eb to enhance information retrieval for proteomics},
   Journal="Bioinformatics",
   Year="2007",
   Volume="23",
   Number="22",
   Pages="3073--3079",
   Month="Nov",
   Abstract={MOTIVATION: Proteomics researchers need to be able to quickly retrieve relevant information from the web and the biomedical literature. To improve information retrieval, we leverage the structure of the semantic web, developing an approach for joining it with the largely opposing paradigm of unsupervised web search. RESULTS: Our approach uses a Resource-Description-Framework (RDF) graph that inter-relates documents through their associated biological identifiers (e.g., protein ID). A search begins with a simple query term (UniProt identifier), which is expanded with terms extracted from documents in the RDF graph surrounding the query ("the subgraph"). We re-rank documents in the full corpus (e.g. all PubMed) by their cosine-similarity scores against a composite word-weight vector created from the subgraph. This vector is a weighted sum of individual word-weight vectors for documents at each node of the subgraph, taking into account the types of relationships between the central query identifier and the nodes connected to it. The computation also uses inverse document frequency (IDF) in a novel way to rescale the local word frequencies in the query's subgraph relative to that in other subgraphs. Applying our procedure to PubMed, we optimize weights for various relationships in the subgraph and benchmark overall performance in detail. Using a subgraph containing family relationships (from PFAM) results in a significant improvement in accuracy (as compared to not considering the subgraph in the search) when assessed against known relationships in the yeast literature. Moreover, we achieve this accuracy using only relatively simple and computationally efficient methods.},
   DOI={http://dx.doi.org/10.1093/bioinformatics/btm452},
   PubMed={http://www.ncbi.nlm.nih.gov/pubmed/17923450}
}

% 17286447 
@Article{pmid17286447,
   Author="Nielsen, D. A.  and Leidner, M.  and Haynes, C.  and Krauthammer, M.  and Kreek, M. J. ",
   Title={{T}he {B}iol{A}{D}-{D}{B} system : an informatics system for clinical and genetic data},
   Journal="Mol Diagn Ther",
   Year="2007",
   Volume="11",
   Number="1",
   Pages="15--19",
   Abstract={The Biology of Addictive Diseases-Database (BiolAD-DB) system is a research bioinformatics system for archiving, analyzing, and processing of complex clinical and genetic data. The database schema employs design principles for handling complex clinical information, such as response items in genetic questionnaires. Data access and validation is provided by the BiolAD-DB client application, which features a data validation engine tightly coupled to a graphical user interface. Data integrity is provided by the password-protected BiolAD-DB SQL compliant server and database. BiolAD-DB tools further provide functionalities for generating customized reports and views. The BiolAD-DB system schema, client, and installation instructions are freely available at http://www.rockefeller.edu/biolad-db/.},
   PubMed={http://www.ncbi.nlm.nih.gov/pubmed/17286447}
}

% 17238412 
@Article{pmid17238412,
   Author="Paek, H.  and Kogan, Y.  and Thomas, P.  and Codish, S.  and Krauthammer, M. ",
   Title={{S}hallow semantic parsing of randomized controlled trial reports},
   Journal="AMIA Annu Symp Proc",
   Year="2006",
   Pages="604--608",
   Abstract={In this work, we are measuring the performance of Propbank-based Machine Learning (ML) for automatically annotating abstracts of Randomized Controlled Trials (CTRs) with semantically meaningful tags. Propbank is a resource of annotated sentences from the Wall Street Journal (WSJ) corpus, and we were interested in assessing performance issues when porting this resource to the medical domain. We compare intra-domain (WSJ/WSJ) with cross-domain (WSJ/medical abstract) performance. Although the intra-domain performance is superior, we found a reasonable cross-domain performance.},
   PubMedCentral={http://www.ncbi.nlm.nih.gov/pmc/articles/PMC1839261},
   PubMed={http://www.ncbi.nlm.nih.gov/pubmed/17238412}
}

% 17081504 
@Article{pmid17081504,
   Author="Gelernter, J.  and Panhuysen, C.  and Weiss, R.  and Brady, K.  and Poling, J.  and Krauthammer, M.  and Farrer, L.  and Kranzler, H. R. ",
   Title={{G}enomewide linkage scan for nicotine dependence: identification of a chromosome 5 risk locus},
   Journal="Biol. Psychiatry",
   Year="2007",
   Volume="61",
   Number="1",
   Pages="119--126",
   Month="Jan",
   Abstract={Nicotine dependence (ND) is costly to societies worldwide, moderately heritable, and genetically complex. Risk loci can be identified with genetic linkage analysis independent of prior physiological hypotheses.\\ We completed a genomewide linkage scan to map loci increasing risk for DSM-IV ND and for a quantitative assessment of ND as measured by the Fagerstrom Test for Nicotine Dependence (FTND) in a set of 634 small nuclear families ascertained on the basis of multiple individuals affected with cocaine or opioid dependence. Of these, 507 had at least two subjects affected with ND. There are two distinct populations within this sample, European-Americans (EAs) and African-Americans (AAs).\\ A region on chromosome 5 was identified as containing a gene that affects risk for ND on the basis of FTND score in the AA part of our sample (logarithm of the odds [lod] score 3.04; empirically determined to be genomewide-significant, p = .0374; point p = .0001). The highest lod score observed in the EA part of the sample was on chromosome 7 (lod score 2.73). Several other "possible" risk loci were identified in either AA or EA subjects, with many of these in proximity to previously suggested risk loci from other clinical samples. Three nominally significant single-nucleotide polymorphism associations were found at the peptidylglycine alpha-amidating monooxygenase (PAM) locus under the chromosome 5 linkage peak, also in the AA part of the sample.\\ These data add to the growing evidence for locations for ND risk loci, add a novel statistically significant locus important in AAs, and suggest a gene that might be contributing to this linkage signal.},
   DOI={http://dx.doi.org/10.1016/j.biopsych.2006.08.023},
   PubMed={http://www.ncbi.nlm.nih.gov/pubmed/17081504}
}

% 16779072 
@Article{pmid16779072,
   Author="Kogan, Y.  and Collier, N.  and Pakhomov, S.  and Krauthammer, M. ",
   Title={{T}owards semantic role labeling & {I}{E} in the medical literature},
   Journal="AMIA Annu Symp Proc",
   Year="2005",
   Pages="410--414",
   Abstract={In this work, we introduce the concept of semantic role labeling to the medical domain. We report first results of porting and adapting an existing resource, Propbank, to the medical field. Propbank is an adjunct to Penn Treebank that provides semantic annotation of predicates and the roles played by their arguments. The main aim of this work is the applicability of the Propbank frame files to predicates typically encountered in the medical literature.\\ We analyzed a target corpus of 610,100 abstracts, which was selected by searching for publication type "case reports". From this target corpus, we randomly selected 10,000 sample abstracts to estimate the predicate distribution, and matched the predicates from this sample to the predicates in Propbank.\\ Of the 1998 unique verbs in our sample, 76% were represented in Propbank. This included the 40 most frequent verbs, which represented 49% of all predicate instances in our sample and which matched the Propbank usage in a study of representative sentences. We propose extensions to Propbank that handle medical predicates, which are not adequately covered by Propbank.\\ We believe that semantic role labeling using Propbank is a valid approach to capture predicate relations in the medical literature.},
   PubMedCentral={http://www.ncbi.nlm.nih.gov/pmc/articles/PMC1560806},
   PubMed={http://www.ncbi.nlm.nih.gov/pubmed/16779072}
}

% 15542023 
@Article{pmid15542023,
   Author="Krauthammer, M.  and Nenadic, G. ",
   Title={{T}erm identification in the biomedical literature},
   Journal="J Biomed Inform",
   Year="2004",
   Volume="37",
   Number="6",
   Pages="512--526",
   Month="Dec",
   Abstract={Sophisticated information technologies are needed for effective data acquisition and integration from a growing body of the biomedical literature. Successful term identification is key to getting access to the stored literature information, as it is the terms (and their relationships) that convey knowledge across scientific articles. Due to the complexities of a dynamically changing biomedical terminology, term identification has been recognized as the current bottleneck in text mining, and--as a consequence--has become an important research topic both in natural language processing and biomedical communities. This article overviews state-of-the-art approaches in term identification. The process of identifying terms is analysed through three steps: term recognition, term classification, and term mapping. For each step, main approaches and general trends, along with the major problems, are discussed. By assessing previous work in context of the overall term identification process, the review also tries to delineate needs for future work in the field.},
   DOI={http://dx.doi.org/10.1016/j.jbi.2004.08.004},
   PubMed={http://www.ncbi.nlm.nih.gov/pubmed/15542023}
}

% 15471992 
@Article{pmid15471992,
   Author="Krauthammer, M.  and Kaufmann, C. A.  and Gilliam, T. C.  and Rzhetsky, A. ",
   Title={{M}olecular triangulation: bridging linkage and molecular-network information for identifying candidate genes in {A}lzheimer's disease},
   Journal="Proc. Natl. Acad. Sci. U.S.A.",
   Year="2004",
   Volume="101",
   Number="42",
   Pages="15148--15153",
   Month="Oct",
   Abstract={A major challenge in human genetics is identifying the molecular basis of common heritable disorders. In contrast to rare single-gene diseases, multifactorial disorders are thought to arise from the combined effect of multiple gene variants, such that any single variant may have only a modest effect on disease susceptibility. We present a method to identify genes that may harbor a significant proportion of the genetic variation that predisposes individuals to a given multifactorial disorder. First, we perform an automated literature analysis that predicts physical interactions (edges) among candidate disease genes (seed nodes, selected on the basis of prior information) and other molecular entities. We derive models of molecular networks from this analysis and map the seed nodes to them. We then compute the graph-theoretic distance (the minimum number of edges that must be traversed) between the seed nodes and all other nodes in the network. We assume that nodes that are found in close proximity to multiple seed nodes are the best disease-related candidate genes. To evaluate this approach, we selected four seed genes, each with a proven role in Alzheimer's disease (AD). The method performed well in predicting additional network nodes that match AD gene candidates identified manually by an expert. We also show that the method prioritizes among the seed nodes themselves, rejecting false-positive seeds that are derived from (noisy) whole-genome genetic-linkage scans. We propose that this strategy will provide a valuable means to bridge genetic and genomic knowledge in the search for genetic determinants of multifactorial disorders.},
   PubMedCentral={http://www.ncbi.nlm.nih.gov/pmc/articles/PMC523448},
   DOI={http://dx.doi.org/10.1073/pnas.0404315101},
   PubMed={http://www.ncbi.nlm.nih.gov/pubmed/15471992}
}

% 15016385 
@Article{pmid15016385,
   Author="Rzhetsky, A.  and Iossifov, I.  and Koike, T.  and Krauthammer, M.  and Kra, P.  and Morris, M.  and Yu, H.  and Duboue, P. A.  and Weng, W.  and Wilbur, W. J.  and Hatzivassiloglou, V.  and Friedman, C. ",
   Title={{G}ene{W}ays: a system for extracting, analyzing, visualizing, and integrating molecular pathway data},
   Journal="J Biomed Inform",
   Year="2004",
   Volume="37",
   Number="1",
   Pages="43--53",
   Month="Feb",
   Abstract={The immense growth in the volume of research literature and experimental data in the field of molecular biology calls for efficient automatic methods to capture and store information. In recent years, several groups have worked on specific problems in this area, such as automated selection of articles pertinent to molecular biology, or automated extraction of information using natural-language processing, information visualization, and generation of specialized knowledge bases for molecular biology. GeneWays is an integrated system that combines several such subtasks. It analyzes interactions between molecular substances, drawing on multiple sources of information to infer a consensus view of molecular networks. GeneWays is designed as an open platform, allowing researchers to query, review, and critique stored information.},
   DOI={http://dx.doi.org/10.1016/j.jbi.2003.10.001},
   PubMed={http://www.ncbi.nlm.nih.gov/pubmed/15016385}
}

% 14871876 
@Article{pmid14871876,
   Author="Iossifov, I.  and Krauthammer, M.  and Friedman, C.  and Hatzivassiloglou, V.  and Bader, J. S.  and White, K. P.  and Rzhetsky, A. ",
   Title={{P}robabilistic inference of molecular networks from noisy data sources},
   Journal="Bioinformatics",
   Year="2004",
   Volume="20",
   Number="8",
   Pages="1205--1213",
   Month="May",
   Abstract={Information on molecular networks, such as networks of interacting proteins, comes from diverse sources that contain remarkable differences in distribution and quantity of errors. Here, we introduce a probabilistic model useful for predicting protein interactions from heterogeneous data sources. The model describes stochastic generation of protein-protein interaction networks with real-world properties, as well as generation of two heterogeneous sources of protein-interaction information: research results automatically extracted from the literature and yeast two-hybrid experiments. Based on the domain composition of proteins, we use the model to predict protein interactions for pairs of proteins for which no experimental data are available. We further explore the prediction limits, given experimental data that cover only part of the underlying protein networks. This approach can be extended naturally to include other types of biological data sources.},
   DOI={http://dx.doi.org/10.1093/bioinformatics/bth061},
   PubMed={http://www.ncbi.nlm.nih.gov/pubmed/14871876}
}

% 14728388 
@Article{pmid14728388,
   Author="Johnson, S. B.  and Campbell, D. A.  and Krauthammer, M.  and Tulipano, P. K.  and Medonca, E. A.  and Friedman, C.  and Hripcsak, G. ",
   Title={{A} native {X}{M}{L} database design for clinical document research},
   Journal="AMIA Annu Symp Proc",
   Year="2003",
   Pages="883",
   Abstract={Health-care institutions are gaining an increasing interest in exploiting the data that are gathered through electronic medical records. Narrative data, generated by transcription or direct entry, represents a far greater challenge for analytic tasks. Moreover, a small number of institutions are beginning to explore deeper structuring of narrative data using natural language processing (NLP). The data produced by NLP systems has a complex, nested structure. Current electronic medical records do not have the ability to store and retrieve data of this complexity in a suitable way.},
   PubMedCentral={http://www.ncbi.nlm.nih.gov/pmc/articles/PMC1479907},
   PubMed={http://www.ncbi.nlm.nih.gov/pubmed/14728388}
}

% 12463856 
@Article{pmid12463856,
   Author="Krauthammer, M.  and Johnson, S. B.  and Hripcsak, G.  and Campbell, D. A.  and Friedman, C. ",
   Title={{R}epresenting nested semantic information in a linear string of text using {X}{M}{L}},
   Journal="Proc AMIA Symp",
   Year="2002",
   Pages="405--409",
   Abstract={XML has been widely adopted as an important data interchange language. The structure of XML enables sharing of data elements with variable degrees of nesting as long as the elements are grouped in a strict tree-like fashion. This requirement potentially restricts the usefulness of XML for marking up written text, which often includes features that do not properly nest within other features. We encountered this problem while marking up medical text with structured semantic information from a Natural Language Processor. Traditional approaches to this problem separate the structured information from the actual text mark up. This paper introduces an alternative solution, which tightly integrates the semantic structure with the text. The resulting XML markup preserves the linearity of the medical texts and can therefore be easily expanded with additional types of information.},
   PubMedCentral={http://www.ncbi.nlm.nih.gov/pmc/articles/PMC2244450},
   PubMed={http://www.ncbi.nlm.nih.gov/pubmed/12463856}
}

% 12169554 
@Article{pmid12169554,
   Author="Krauthammer, M.  and Kra, P.  and Iossifov, I.  and Gomez, S. M.  and Hripcsak, G.  and Hatzivassiloglou, V.  and Friedman, C.  and Rzhetsky, A. ",
   Title={{O}f truth and pathways: chasing bits of information through myriads of articles},
   Journal="Bioinformatics",
   Year="2002",
   Volume="18 Suppl 1",
   Pages="S249--257",
   Abstract={Knowledge on interactions between molecules in living cells is indispensable for theoretical analysis and practical applications in modern genomics and molecular biology. Building such networks relies on the assumption that the correct molecular interactions are known or can be identified by reading a few research articles. However, this assumption does not necessarily hold, as truth is rather an emerging property based on many potentially conflicting facts. This paper explores the processes of knowledge generation and publishing in the molecular biology literature using modelling and analysis of real molecular interaction data. The data analysed in this article were automatically extracted from 50000 research articles in molecular biology using a computer system called GeneWays containing a natural language processing module. The paper indicates that truthfulness of statements is associated in the minds of scientists with the relative importance (connectedness) of substances under study, revealing a potential selection bias in the reporting of research results. Aiming at understanding the statistical properties of the life cycle of biological facts reported in research articles, we formulate a stochastic model describing generation and propagation of knowledge about molecular interactions through scientific publications. We hope that in the future such a model can be useful for automatically producing consensus views of molecular interaction data.},
   PubMed={http://www.ncbi.nlm.nih.gov/pubmed/12169554}
}

Comments are closed.

Research in biomedical informatics

Recent Posts

Meta

Links

Krauthammer Lab

Pages

The Latest

Largest Melanoma Exome Sequencing Screen Published in Nature Genetics

More