Recent advances in biomedical applications of accelerator mass spectrometry

BioMed Central 2009 Journal of biomedical science Vol.16 No.1

<P>The use of radioisotopes has a long history in biomedical science, and the technique of accelerator mass spectrometry (AMS), an extremely sensitive nuclear physics technique for detection of very low-abundant, stable and long-lived isotopes, has now revolutionized high-sensitivity isotope detection in biomedical research, because it allows the direct determination of the amount of isotope in a sample rather than measuring its decay, and thus the quantitative analysis of the fate of the radiolabeled probes under the given conditions. Since AMS was first used in the early 90's for the analysis of biological samples containing enriched <SUP>14</SUP>C for toxicology and cancer research, the biomedical applications of AMS to date range from <I>in vitro </I>to <I>in vivo </I>studies, including the studies of 1) toxicant and drug metabolism, 2) neuroscience, 3) pharmacokinetics, and 4) nutrition and metabolism of endogenous molecules such as vitamins. In addition, a new drug development concept that relies on the ultrasensitivity of AMS, known as human microdosing, is being used to obtain early human metabolism information of candidate drugs. These various aspects of AMS are reviewed and a perspective on future applications of AMS to biomedical research is provided.</P>

An application of convolutional neural networks with salient features for relation classification

Dashdorj, Zolzaya,Song, Min BioMed Central 2019 BMC bioinformatics Vol.20 No.10

<P><B>Background</B></P><P>Due to the advent of deep learning, the increasing number of studies in the biomedical domain has attracted much interest in feature extraction and classification tasks. In this research, we seek the best combination of feature set and hyperparameter setting of deep learning algorithms for relation classification. To this end, we incorporate an entity and relation extraction tool, PKDE4J to extract biomedical features (i.e., biomedical entities, relations) for the relation classification. We compared the chosen Convolutional Neural Networks (CNN) based classification model with the most widely used learning algorithms.</P><P><B>Results</B></P><P>Our CNN based classification model outperforms the most widely used supervised algorithms. We achieved a significant performance on binary classification with a weighted macro-average F1-score: 94.79% using pre-extracted relevant feature combinations. For multi-class classification, the weighted macro-average F1-score is estimated around 86.95%.</P><P><B>Conclusions</B></P><P>Our results suggest that our proposed CNN based model using the not only single feature as the raw text of the sentences of biomedical literature, but also coupling with multiple and highlighted features extracted from the biomedical sentences could improve the classification performance significantly. We offer hyperparameter tuning and optimization approaches for our proposed model to obtain optimal hyperparameters of the models with the best performance.</P>

CollaboNet: collaboration of deep neural networks for biomedical named entity recognition

Yoon, Wonjin,So, Chan Ho,Lee, Jinhyuk,Kang, Jaewoo BioMed Central 2019 BMC bioinformatics Vol.20 No.10

<P><B>Background</B></P><P>Finding biomedical named entities is one of the most essential tasks in biomedical text mining. Recently, deep learning-based approaches have been applied to biomedical named entity recognition (BioNER) and showed promising results. However, as deep learning approaches need an abundant amount of training data, a lack of data can hinder performance. BioNER datasets are scarce resources and each dataset covers only a small subset of entity types. Furthermore, many bio entities are polysemous, which is one of the major obstacles in named entity recognition.</P><P><B>Results</B></P><P>To address the lack of data and the entity type misclassification problem, we propose CollaboNet which utilizes a combination of multiple NER models. In CollaboNet, models trained on a different dataset are connected to each other so that a target model obtains information from other collaborator models to reduce false positives. Every model is an expert on their target entity type and takes turns serving as a target and a collaborator model during training time. The experimental results show that CollaboNet can be used to greatly reduce the number of false positives and misclassified entities including polysemous words. CollaboNet achieved state-of-the-art performance in terms of precision, recall and F1 score.</P><P><B>Conclusions</B></P><P>We demonstrated the benefits of combining multiple models for BioNER. Our model has successfully reduced the number of misclassified entities and improved the performance by leveraging multiple datasets annotated for different entity types. Given the state-of-the-art performance of our model, we believe that CollaboNet can improve the accuracy of downstream biomedical text mining applications such as bio-entity relation extraction.</P>

Cystatin M loss is associated with the losses of estrogen receptor, progesterone receptor, and HER4 in invasive breast cancer

Ko, Eunkyung,Park, Seong-Eun,Cho, Eun Yoon,Kim, Yujin,Hwang, Jung-Ah,Lee, Yeon-Su,Nam, Seok Jin,Bang, Saik,Park, Joobae,Kim, Duk-Hwan BioMed Central 2010 Breast cancer research Vol.12 No.6

<P><B>Introduction</B></P><P>This study was aimed at understanding the clinicopathological significance of cystatin M loss, and investigating possible factors responsible for cystatin M loss in breast cancer.</P><P><B>Methods</B></P><P>The expression of estrogen receptor (ER), progesterone receptor (PR), HER2, HER4, and cystatin M was retrospectively analyzed using immunohistochemistry in 117 patients with ductal carcinoma <I>in situ </I>(DCIS) and in 175 patients with invasive breast cancer (IBC). The methylation status of <I>CST6 </I>gene encoding cystatin M was evaluated using methylation-specific polymerase chain reaction (PCR) in formalin-fixed paraffin-embedded tissues from 292 participants and using pyrosequencing in fresh-frozen tumor and matched normal tissues from 51 IBC patients.</P><P><B>Results</B></P><P>Cystatin M loss was found in 9 (8%) of 117 patients with DCIS and in 99 (57%) of 175 with invasive breast cancer (IBC) (<I>P </I>< 0.0001). Cystatin M loss was found in 58 (57%) of 101 HER2-negative IBCs and in 41 (55%) of 74 HER2-positive IBCs, and this difference was not statistically significant (<I>P </I>= 0.97). However, cystatin M loss was significantly associated with the loss of ER (<I>P </I>= 0.01), PR (<I>P </I>= 0.002), and HER4 (<I>P </I>= 0.003) in IBCs. Cystatin M loss occurred in 34 (76%) of the 45 HER4-negative IBCs and in 65 (50%) of the 130 HER4-positive IBCs. Multivariate analysis showed that cystatin M loss occurred at a 3.57 times (95% CI = 1.28 to 9.98; <I>P </I>= 0.01) higher prevalence in the triple-negative IBCs of ER, PR, and HER4 than in other subtypes, after adjusting for age. The quantity of <I>CST6 </I>methylation was associated with ER loss (<I>P </I>= 0.0002) in IBCs but not with the loss of PR (<I>P </I>= 0.64) or HER4 (<I>P </I>= 0.87).</P><P><B>Conclusions</B></P><P>The present study suggests that cystatin M loss may be associated with the losses of ER, PR, and HER4 in IBC.</P>

DBBP: database of binding pairs in protein-nucleic acid interactions

Park, Byungkyu,Kim, Hyungchan,Han, Kyungsook BioMed Central 2014 BMC bioinformatics Vol.15 No.suppl15

<P><B>Background</B></P><P>Interaction of proteins with other molecules plays an important role in many biological activities. As many structures of protein-DNA complexes and protein-RNA complexes have been determined in the past years, several databases have been constructed to provide structure data of the complexes. However, the information on the binding sites between proteins and nucleic acids is not readily available from the structure data since the data consists mostly of the three-dimensional coordinates of the atoms in the complexes.</P><P><B>Results</B></P><P>We analyzed the huge amount of structure data for the hydrogen bonding interactions between proteins and nucleic acids and developed a database called DBBP (<B>D</B>ata<B>B</B>ase of <B>B</B>inding <B>P</B>airs in protein-nucleic acid interactions, http://bclab.inha.ac.kr/dbbp). DBBP contains 44,955 hydrogen bonds (H-bonds) of protein-DNA interactions and 77,947 H-bonds of protein-RNA interactions.</P><P><B>Conclusions</B></P><P>Analysis of the huge amount of structure data of protein-nucleic acid complexes is labor-intensive, yet provides useful information for studying protein-nucleic acid interactions. DBBP provides the detailed information of hydrogen-bonding interactions between proteins and nucleic acids at various levels from the atomic level to the residue level. The binding information can be used as a valuable resource for developing a computational method aiming at predicting new binding sites in proteins or nucleic acids.</P>

Upfront systemic chemotherapy and preoperative short-course radiotherapy with delayed surgery for locally advanced rectal cancer with distant metastases

Shin, Sang Joon,Yoon, Hong In,Kim, Nam Kyu,Lee, Kang Young,Min, Byung Soh,Ahn, Joong Bae,Keum, Ki Chang,Koom, Woong Sub BioMed Central 2011 Radiation oncology Vol.6 No.-

<P><B>Background</B></P><P>Choosing the most effective approach for treating rectal cancer with mesorectal fascia (MRF) involvement or closeness and synchronous distant metastases is a current clinical challenge. The aim of this retrospective study was to determine if upfront systemic chemotherapy and short-course radiotherapy (RT) with delayed surgery enables R0 resection.</P><P><B>Methods</B></P><P>Between March 2009 and October 2009, six patients were selected for upfront chemotherapy and short-course RT (5 × 5 Gy) with delayed surgery. The patients had locally advanced primary tumors with MRF involvement or closeness, as well as synchronous and potentially resectable distant metastases. Chemotherapy was administered to five patients between the end of the RT and surgery. All patients underwent total mesorectal excision (TME).</P><P><B>Results</B></P><P>The median patient age was 54 years (range 39-63). All primary and metastatic lesions were resected simultaneously. The median duration between short-course RT and surgery was 13 weeks (range, 7-18). R0 resection of rectal lesions was achieved in 5 patients. One patient, who had a very low-lying tumor, had an R1 resection. The median follow-up duration for all patients was 16.7 months (range, 15.5-23.5). One patient developed liver metastasis at 15.7 months. There have been no local recurrences or deaths.</P><P><B>Conclusions</B></P><P>Upfront chemotherapy and short course RT with delayed surgery is a valuable alternative treatment approach for patients with MRF involvement or closeness of rectal cancer with distant metastases.</P>

An integrative model of multi-organ drug-induced toxicity prediction using gene-expression data

Kim, Jinwoo,Shin, Miyoung BioMed Central 2014 BMC bioinformatics Vol.15 No.suppl16

<P><B>Background</B></P><P>In practice, some drugs produce a number of negative biological effects that can mitigate their effectiveness as a remedy. To address this issue, several studies have been performed for the prediction of drug-induced toxicity from gene-expression data, and a significant amount of work has been done on predicting limited drug-induced symptoms or single-organ toxicity. Since drugs often lead to some injuries in several organs like liver or kidney, however, it would be very useful to forecast the drug-induced injuries for multiple organs. Therefore, in this work, our aim was to develop a multi-organ toxicity prediction model using an integrative model of gene-expression data.</P><P><B>Results</B></P><P>To train our integrative model, we used 3708 <I>in-vivo </I>samples of gene-expression profiles exposed to one of 41 drugs related to 21 distinct physiological changes divided between liver and kidney (liver 11, kidney 10). Specifically, we used the gene-expression profiles to learn an ensemble classifier for each of 21 pathology prediction models. Subsequently, these classifiers were combined with weights to generate an integrative model for each pathological finding. The integrative model outputs the likeliness of presenting the trained pathology in a given test sample of gene-expression profile, called an <I>integrative prediction score </I>(IPS). For the evaluation of an integrative model, we estimated the prediction performance with the <I>k</I>-fold cross-validation. Our results demonstrate that the proposed integrative model is superior to individual pathology prediction models in predicting multi-organ drug-induced toxicities over all the targeted pathological findings. On average, the AUC of the integrative models was 88% while the AUC of individual pathology prediction models was 68%.</P><P><B>Conclusions</B></P><P>Not only does this integrative model produce comparable prediction performance to existing approaches, but also it produces very stable performance overall. In addition, our approach is easily expandable to a variety of other multi-organ toxicology applications.</P>

Prognostic value of volumetric metabolic parameters measured by [ ¹⁸ F]Fluorodeoxyglucose-positron emission tomography/computed tomography in patients with small cell lung cancer

Park, Soo Bin,Choi, Joon Young,Moon, Seung Hwan,Yoo, Jang,Kim, Hojoong,Ahn, Yong Chan,Ahn, Myung-Ju,Park, Keunchil,Kim, Byung-Tae BioMed Central 2014 Cancer imaging Vol.14 No.1

<P><B>Background</B></P><P>We evaluated the prognostic value of volume-based metabolic positron emission tomography (PET) parameters in patients with small cell lung cancer (SCLC) compared with other factors.</P><P><B>Methods</B></P><P>The subjects were 202 patients with pathologically proven SCLC who underwent pretreatment <SUP>18</SUP>F-fluorodeoxyglucose (FDG) PET/computed tomography (CT). Volumetric metabolic parameters of intrathoracic malignant hypermetabolic lesions, including maximum and average standardized uptake value, sum of metabolic tumor volume (MTV), and sum of total lesion glycolysis (TLG) were measured.</P><P><B>Results</B></P><P>164 patients had died during follow-up (median 17.4 months) and median overall survival was 14 months. On univariate survival analysis, age, stage, treatment modality, sum of MTV (cutoff = 100 cm<SUP>3</SUP>), and sum of TLG (cutoff = 555) were significant predictors of survival. There was a very high correlation between the sum of MTV and the sum of TLG (r = 0.963, <I>P</I> < 0.001). On multivariate survival analysis, age (HR = 1.04, <I>P</I> < 0.001), stage (HR = 2.442, <I>P</I> < 0.001), and sum of MTV (HR = 1.662, <I>P</I> = 0.002) were independent prognostic factors. On subgroup analysis based on limited disease (LD) and extensive disease (ED), sum of MTV and sum of TLG were significant prognostic factors only in LD.</P><P><B>Conclusion</B></P><P>Both sum of MTV and sum of TLG of intrathoracic malignant hypermetabolic lesions are important independent prognostic factors for survival in patients with SCLC, in addition to age and clinical stage. However, it may be more useful in limited disease rather than in extensive disease.</P>

Immunoproteomic identification of immunodominant antigens independent of the time of infection in <i>Brucella abortus</i> 2308-challenged cattle

Lee, Jin Ju,Simborio, Hannah Leah,Reyes, Alisha Wehdnesday Bernardo,Kim, Dae Geun,Hop, Huynh Tan,Min, Wongi,Her, Moon,Jung, Suk Chan,Yoo, Han Sang,Kim, Suk BioMed Central 2015 VETERINARY RESEARCH Vol.46 No.-

<P>Brucellosis is a vital zoonotic disease caused by <I>Brucella</I>, which infects a wide range of animals and humans. Accurate diagnosis and reliable vaccination can control brucellosis in domestic animals. This study examined novel immunogenic proteins that can be used to detect <I>Brucella abortus</I> infection or as an effective subcellular vaccine. In an immunoproteomic assay, 55 immunodominant proteins from <I>B. abortus</I> 544 were observed using two dimensional electrophoresis (2DE) and immunoblot profiles with antisera from <I>B. abortus</I>-infected cattle at the early (week 3), middle (week 7), and late (week 10) periods, after excluding protein spots reacting with antisera from <I>Yersinia enterocolitica</I> O:9-infected and non-infected cattle. Twenty-three selected immunodominant proteins whose spots were observed at all three infection periods were identified using MALDI-MS/MS. Most of these proteins identified by immunoblot and mass spectrometry were determined by their subcellular localization and predicted function. We suggest that the detection of prominent immunogenic proteins during the infection period can support the development of advanced diagnostic methods with high specificity and accuracy; subsidiarily, these proteins can provide supporting data to aid in developing novel vaccine candidates.</P>

Searching for transcription factor binding sites in vector spaces

Lee, Chih,Huang, Chun-Hsi BioMed Central 2012 BMC bioinformatics Vol.13 No.suppl17

<P><B>Background</B></P><P>Computational approaches to transcription factor binding site identification have been actively researched in the past decade. Learning from known binding sites, new binding sites of a transcription factor in unannotated sequences can be identified. A number of search methods have been introduced over the years. However, one can rarely find one single method that performs the best on all the transcription factors. Instead, to identify the best method for a particular transcription factor, one usually has to compare a handful of methods. Hence, it is highly desirable for a method to perform automatic optimization for individual transcription factors.</P><P><B>Results</B></P><P>We proposed to search for transcription factor binding sites in vector spaces. This framework allows us to identify the best method for each individual transcription factor. We further introduced two novel methods, the negative-to-positive vector (NPV) and optimal discriminating vector (ODV) methods, to construct query vectors to search for binding sites in vector spaces. Extensive cross-validation experiments showed that the proposed methods significantly outperformed the ungapped likelihood under positional background method, a state-of-the-art method, and the widely-used position-specific scoring matrix method. We further demonstrated that motif subtypes of a TF can be readily identified in this framework and two variants called the <I>k</I> NPV and <I>k</I> ODV methods benefited significantly from motif subtype identification. Finally, independent validation on ChIP-seq data showed that the ODV and NPV methods significantly outperformed the other compared methods.</P><P><B>Conclusions</B></P><P>We conclude that the proposed framework is highly flexible. It enables the two novel methods to automatically identify a TF-specific subspace to search for binding sites. Implementations are available as source code at: http://biogrid.engr.uconn.edu/tfbs_search/.</P>