Bioinformatics, Convergence Science, and Systems Biology最新文献

筛选
英文 中文
Abstract 1635: A scalable, cloud-based, unsupervised deep learning system for identification, extraction, and summarization of potentially imperceptible patterns in whole-slide images of breast cancer tissue 1635:一个可扩展的、基于云的、无监督的深度学习系统,用于识别、提取和总结乳腺癌组织整张幻灯片图像中潜在的难以察觉的模式
Bioinformatics, Convergence Science, and Systems Biology Pub Date : 2019-07-01 DOI: 10.1158/1538-7445.AM2019-1635
J. L. Evans, William Seo, Mary Macheski-Preston, M. Fritz, S. Puvanesarajah, James M. Hodge, T. Gansler, S. Gapstur, M. Gaudet, M. Yi
{"title":"Abstract 1635: A scalable, cloud-based, unsupervised deep learning system for identification, extraction, and summarization of potentially imperceptible patterns in whole-slide images of breast cancer tissue","authors":"J. L. Evans, William Seo, Mary Macheski-Preston, M. Fritz, S. Puvanesarajah, James M. Hodge, T. Gansler, S. Gapstur, M. Gaudet, M. Yi","doi":"10.1158/1538-7445.AM2019-1635","DOIUrl":"https://doi.org/10.1158/1538-7445.AM2019-1635","url":null,"abstract":"Digital pathology images potentially contain novel patterns that may be perceived by modern deep learning models, but not humans. Prior unsupervised pattern recognition approaches have been used to reveal prognostically-relevant subtypes of glioblastoma (PMID: 28984190) and breast density segmentation (PMID: 26915120), and may complement supervised machine learning models trained using labeled data. In the Cancer Prevention Study II (CPS-II) cohort (PMID: 12015775), high-resolution, digitized hemotoxylin and eosin diagnostic slides are available for approximately 1,700 breast cancer cases providing an opportunity to perform unsupervised pattern recognition image analysis for epidemiologic breast cancer studies. Given the size of the dataset and complexity of the models, we constructed an end-to-end analytical pipeline, including preprocessing, feature engineering, and clustering, using cloud-based technologies that enable analysis at scale. Prior to training the unsupervised models, we faced issues converting raw images with open-source software. Specifically, OpenSlides could not open the Leica Versa SCN files due to their proprietary format while BioFormats inverted colors. To fix these issues, we altered the BioFormats library to successfully convert the files into a TIFF format. Since this issue likely affects other researchers, we are in discussions to provide the fix under a public license. TIFF formatted images were then denoised through color normalization to reduce hue variance and artifact detection to remove unwanted features such as pathologist annotations. Due to the computational complexity of analyzing the full image, images were padded with white space to ensure divisibility and broken into nine tiles of a predefined size. To further reduce computation time, uninformative tiles were filtered based on a predetermined threshold of artifact and white space composition. The remaining tiles were input to the unsupervised models. We used convolutional autoencoders, specifically a modified VGG-16 model without pretrained weights and a deep embedded clustering algorithm. These models learn representations of the images called ‘feature vectors’ and encode the images’ salient patterns. The final model was chosen based on iterative testing on a subsample of 100 images (N=21,472 tiles) and performance comparison of various VGG-inspired autoencoders. The feature vectors were clustered by K-means to summarize the information in a format suitable for statistical analyses. Our initial results show that the system captures macro-scale tissue patterns at lower magnifications (1x and 5x) and produces clusters that can be integrated into epidemiological studies of breast cancer etiology and prognosis. Citation Format: Jacob L. Evans, William Seo, Mary Macheski-Preston, Michelle Fritz, Samantha Puvanesarajah, James Hodge, Ted Gansler, Susan Gapstur, Mia M. Gaudet, Michelle Yi. A scalable, cloud-based, unsupervised deep learning system for identificati","PeriodicalId":445323,"journal":{"name":"Bioinformatics, Convergence Science, and Systems Biology","volume":"159 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131414881","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 1
Abstract 689: Heating of head tissues during TTFields therapy: A computational study 摘要:TTFields治疗过程中头部组织的加热:一项计算研究
Bioinformatics, Convergence Science, and Systems Biology Pub Date : 2019-07-01 DOI: 10.1158/1538-7445.AM2019-689
N. Gentilal, Ricardo Salvador, Pedro C. Miranda
{"title":"Abstract 689: Heating of head tissues during TTFields therapy: A computational study","authors":"N. Gentilal, Ricardo Salvador, Pedro C. Miranda","doi":"10.1158/1538-7445.AM2019-689","DOIUrl":"https://doi.org/10.1158/1538-7445.AM2019-689","url":null,"abstract":"Tumor Treating Fields (TTFields) is a non-invasive technique that can be applied jointly with chemotherapy to treat glioblastoma (GBM). It consists on delivering an alternating current (900 mA) with a frequency of 200 kHz in two perpendicular directions alternately: Anterior-Posterior (AP) and Left-Right (LR) via capacitively coupled transducer arrays placed on the shaved scalp. This technique showed an anti-mitotic effect when the electric field magnitude in the tumor is at least 1 V/cm and the results were enhanced for values up to 3 V/cm. Optune is the FDA-approved device that was created by Novocure to deliver TTFields in humans. Due to the high daily compliance that is necessary for this technique (at least 18 hours, every day) biological tissue heating can occur. To prevent an excessive temperature increase, Optune shuts down the applied field in both directions every time an electrode reaches 41oC. Our aim is to estimate Optune’s duty cycle, suggest ways to improve it and appraise possible thermal damage mechanisms. The simulations were performed in a realistic head model created from MR images and the software used to run these simulations was COMSOL Multiphysics. The results obtained showed that Optune is only effectively delivering the fields around 40% of the time and that the AP configuration is applied during more time than the LR. However, we show that it is possible to increase Optune’s duty cycle if 1) the current is shutdown only for the configuration that has the electrode that reached 41oC while maintaining the other configuration active; 2) the current is injected homogeneously across all the electrodes of the same array; 3) the room temperature is low. We also calculated the Cumulative number of Equivalent Minutes at 43oC (CEM 43oC) for 18 hours to evaluate the possible thermal damage mechanisms. Our results showed that thermal damage might occur for the scalp and for the brain. For the scalp, these findings are corroborated with what is seen experimentally because most of the patients treated with this technique suffer from dermatitis. Regarding the brain, the impact of the temperature increase is still unclear as no related effects have been reported to date in clinical trials. However, according to the literature, an increase in temperature may lead to a higher Blood-Brain Barrier (BBB) permeability, a variation of the brain’s blood flux and a change in the concentration of some neurotransmitters such as GABA, glycine and glutamate. An increased BBB permeability can be helpful if there is a more suitable drug that can be used for GBM that under normal conditions would not pass to the brain. An increased blood flux can also be helpful to reduce brain’s temperature, while a variation in the concentration of the neurotransmitters is unlikely to affect TTFields efficacy. These results can serve as a starting point for future studies to evaluate the thermal impact of this therapy. Citation Format: Nichal Gentilal, Ricardo Salva","PeriodicalId":445323,"journal":{"name":"Bioinformatics, Convergence Science, and Systems Biology","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124281734","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Abstract 1645: Data science for cancer research 摘要1645:癌症研究的数据科学
Bioinformatics, Convergence Science, and Systems Biology Pub Date : 2019-07-01 DOI: 10.1158/1538-7445.SABCS18-1645
W. J. Zheng
{"title":"Abstract 1645: Data science for cancer research","authors":"W. J. Zheng","doi":"10.1158/1538-7445.SABCS18-1645","DOIUrl":"https://doi.org/10.1158/1538-7445.SABCS18-1645","url":null,"abstract":"","PeriodicalId":445323,"journal":{"name":"Bioinformatics, Convergence Science, and Systems Biology","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114814281","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Abstract 909: Single-cell transcriptomic profiling of non-small cell lung cancer uncovers inter- and intracell population structure across TCGA lung adenocarcinoma and lung squamous cancer subtypes 摘要:非小细胞肺癌的单细胞转录组学分析揭示了TCGA肺腺癌和肺鳞癌亚型的细胞间和细胞内群体结构
Bioinformatics, Convergence Science, and Systems Biology Pub Date : 2019-07-01 DOI: 10.1158/1538-7445.AM2019-909
K. Gyan, Aditya Deshpande, Shaham Beg, Huasong Tian, J. Rosiene, Marlon Stoeckius, Peter Smibert, D. Risso, J. Mosquera, M. Imieliński
{"title":"Abstract 909: Single-cell transcriptomic profiling of non-small cell lung cancer uncovers inter- and intracell population structure across TCGA lung adenocarcinoma and lung squamous cancer subtypes","authors":"K. Gyan, Aditya Deshpande, Shaham Beg, Huasong Tian, J. Rosiene, Marlon Stoeckius, Peter Smibert, D. Risso, J. Mosquera, M. Imieliński","doi":"10.1158/1538-7445.AM2019-909","DOIUrl":"https://doi.org/10.1158/1538-7445.AM2019-909","url":null,"abstract":"Lung adenocarcinoma (LUAD) and squamous cell carcinoma (LUSC) are the most prevalent types of non-all cell lung cancer (NSCLC), a leading cause of cancer death worldwide. In this study, we analyzed the transcriptomes of ~45,000 single cells (scRNA) from 13 NSCLC patients, including 5 LUAD cases which were collected and profiled at our institution. To correlate genomes and transcriptomes we performed Whole-Genome Sequencing (WGS) on 3 of these 5 LUAD cases. By comparing tumor tissue with matched adjacent non-malignant lung tissue we are able to confidently distinguish 13 cell-type specific clusters that unambiguously match previously characterized lineages. We developed algorithms for the identification of malignant cells derived from tumor tissue through scRNA analysis of copy number alterations and single nucleotide variants (SNV). Joint analysis of WGS and scRNA confirmed an enrichment of tobacco-associated SNVs among malignant cells of the tumor. Stromal cell types demonstrated consistent expression patterns across cases, while malignant cells demonstrated both inter- and intra-tumoral heterogeneity in their expression of signatures related to GPCR signaling, 3’ UTR mediated translational regulation, and cell-cell junction organization. In particular, one case displayed a unique pattern of intra-tumoral heterogeneity, as a subset of malignant cells robustly express a marker of pulmonary neuroendocrine cells, CGRP. Employing immunohistochemistry, the spatial organization of these malignant cells is revealed to be mutually exclusive within the tumor microenvironment and overlapping in expression of clinical markers of small-cell lung cancer. Finally, we deconvolved bulk TCGA LUAD and LUSC gene expression samples and analyzed the relationship between cell type specific gene expression in cell types of the lung and passenger mutation topographies. Our results provide insight into the molecular and clinical correlates of deconvolved NSCLC transcriptomes and provide a novel methodology with which to explore genomic variation at a single cell resolution. Furthermore, our dataset provides a resource for illuminating cancer-cell transcriptional changes and revealing key molecular drivers of tumor-stromal interactions in lung cancer. Citation Format: Kofi E. Gyan, Aditya Deshpande, Shaham Beg, Huasong Tian, Joel Rosiene, Marlon Stoeckius, Peter Smibert, Davide Risso, Juan Miguel Mosquera, Marcin Imielinski. Single-cell transcriptomic profiling of non-small cell lung cancer uncovers inter- and intracell population structure across TCGA lung adenocarcinoma and lung squamous cancer subtypes [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2019; 2019 Mar 29-Apr 3; Atlanta, GA. Philadelphia (PA): AACR; Cancer Res 2019;79(13 Suppl):Abstract nr 909.","PeriodicalId":445323,"journal":{"name":"Bioinformatics, Convergence Science, and Systems Biology","volume":"21 2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123538445","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Abstract 3388: Tumor suppressor genes may promote tumorigenesis through allele specific expression 摘要3388:肿瘤抑制基因可能通过等位基因特异性表达促进肿瘤发生
Bioinformatics, Convergence Science, and Systems Biology Pub Date : 2019-07-01 DOI: 10.1158/1538-7445.SABCS18-3388
Evan A. Clayton
{"title":"Abstract 3388: Tumor suppressor genes may promote tumorigenesis through allele specific expression","authors":"Evan A. Clayton","doi":"10.1158/1538-7445.SABCS18-3388","DOIUrl":"https://doi.org/10.1158/1538-7445.SABCS18-3388","url":null,"abstract":"","PeriodicalId":445323,"journal":{"name":"Bioinformatics, Convergence Science, and Systems Biology","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116809146","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Abstract 1648: Deep learning tissue "fingerprints" to identify patients and predict clinical subtypes of breast cancer from digital pathology images 摘要1648:深度学习组织“指纹”,从数字病理图像中识别患者并预测乳腺癌临床亚型
Bioinformatics, Convergence Science, and Systems Biology Pub Date : 2019-07-01 DOI: 10.1158/1538-7445.SABCS18-1648
R. Rawat, Fei Sha, D. Shibata, D. Ruderman, D. Agus
{"title":"Abstract 1648: Deep learning tissue \"fingerprints\" to identify patients and predict clinical subtypes of breast cancer from digital pathology images","authors":"R. Rawat, Fei Sha, D. Shibata, D. Ruderman, D. Agus","doi":"10.1158/1538-7445.SABCS18-1648","DOIUrl":"https://doi.org/10.1158/1538-7445.SABCS18-1648","url":null,"abstract":"","PeriodicalId":445323,"journal":{"name":"Bioinformatics, Convergence Science, and Systems Biology","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123920880","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Abstract 5095: Statistical modeling of transcriptional regulatory states in single-cell RNA-Seq data of tumor and infiltrated immune cells 摘要 5095:肿瘤和浸润免疫细胞单细胞 RNA-Seq 数据转录调控状态的统计建模
Bioinformatics, Convergence Science, and Systems Biology Pub Date : 2019-07-01 DOI: 10.1158/1538-7445.SABCS18-5095
Changlin Wan, Wennan Chang, Xiaoyu Lu, Yifan Sun, K. So, Sha Cao, Xiongbin Lu, Chi Zhang
{"title":"Abstract 5095: Statistical modeling of transcriptional regulatory states in single-cell RNA-Seq data of tumor and infiltrated immune cells","authors":"Changlin Wan, Wennan Chang, Xiaoyu Lu, Yifan Sun, K. So, Sha Cao, Xiongbin Lu, Chi Zhang","doi":"10.1158/1538-7445.SABCS18-5095","DOIUrl":"https://doi.org/10.1158/1538-7445.SABCS18-5095","url":null,"abstract":"Single-cell RNA-seq of tumor tissue has greatly strengthened our understanding of tumor development as well as the heterogeneous tissue micro-environment. Many models are dedicated to detect deferentially expressed genes among single cells of different conditions, or to discover (novel) sub-cell types via various clustering methods. However, current statistical models often neglect the zero/low expressions, and use one single modality to fit the rest of the non-zero ones. We believe that zero and low expressions are observed partly due to limited experimental resolution; on the other hand, occasionally, low expressions are falsely observed as non-zero due to the existence of incompletely degraded mRNA. In addition, the severe heterogeneity and fast dynamics of single cells makes it invalid to fit their expressions in one single modality. Here, we propose a left truncated mixture Gaussian (LTMG) distribution to uncover the multimodality in single cells’ gene expression while properly handling the zero and low expressions. LTMG is motivated by the kinetic relationships among the mRNA abundance, transcriptional regulatory signals (TRSs), and mRNA metabolism in a cell. Specifically, observations of a gene’s expression are fitted as mixture Gaussian distributions which assumes zero and low expressions as left censored data. By treating each mixing component as one state of the transcriptional regulators, we combined our LTMG model and our in-house bi-clustering algorithm to infer modules of genes co-regulated by certain (unknown) transcriptional regulatory signal, which is only shared by a subset of all the single cells. Application of the method to three high quality single-cell RNA-seq data sets of T cells extracted from liver, colon and lung cancer micro-environments, identified varied transcriptional regulations specific to subclasses of T cells. Citation Format: Changlin Wan, Wennan Chang, Xiaoyu Lu, Yifan Sun, Kaman So, Sha Cao, Xiongbin Lu, Chi Zhang. Statistical modeling of transcriptional regulatory states in single-cell RNA-Seq data of tumor and infiltrated immune cells [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2019; 2019 Mar 29-Apr 3; Atlanta, GA. Philadelphia (PA): AACR; Cancer Res 2019;79(13 Suppl):Abstract nr 5095.","PeriodicalId":445323,"journal":{"name":"Bioinformatics, Convergence Science, and Systems Biology","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128255591","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Abstract 1669: Full length transcriptome sequencing of melanoma cell line complements long read sequencing assessment of genomic rearrangements 摘要1669:黑色素瘤细胞系的全长转录组测序补充了基因组重排的长读测序评估
Bioinformatics, Convergence Science, and Systems Biology Pub Date : 2019-07-01 DOI: 10.1158/1538-7445.AM2019-1669
Elizabeth Tseng, Brendan D Galvin, T. Hon, W. Kloosterman, Meredith Ashby
{"title":"Abstract 1669: Full length transcriptome sequencing of melanoma cell line complements long read sequencing assessment of genomic rearrangements","authors":"Elizabeth Tseng, Brendan D Galvin, T. Hon, W. Kloosterman, Meredith Ashby","doi":"10.1158/1538-7445.AM2019-1669","DOIUrl":"https://doi.org/10.1158/1538-7445.AM2019-1669","url":null,"abstract":"Transcriptome sequencing has proven to be an important tool for understanding the biological changes in cancer genomes including the consequences of structural rearrangements. Short read sequencing has been the method of choice, as the high throughput at low cost allows for transcript quantitation and the detection of even rare transcripts. However, the reads are generally too short to reconstruct complete isoforms. Conversely, long-read approaches can provide unambiguous full-length isoforms, but lower throughput has complicated quantitation and high RNA input requirements has made working with cancer samples challenging. Recently, the COLO 829 cell line was sequenced to 50-fold coverage with PacBio SMRT Sequencing. To validate and extend the findings from this effort, we have generated long-read transcriptome data using an updated PacBio Iso-Seq method, the results of which will be shared at the AACR 2019 General Meeting. With this complimentary transcriptome data, we demonstrate how recent innovations in the PacBio Iso-Seq method sample preparation and sequencing chemistry have made long-read sequencing of cancer transcriptomes more practical. In particular, library preparation has been simplified and throughput has increased. The improved protocol has reduced sample prep time from several days to one day while reducing the sample input requirements ten-fold. In addition, the incorporation of unique molecular identifier (UMI) tags into the workflow has improved the bioinformatics analysis. Yield has also increased, with v3 sequencing chemistry typically delivering > 30 Gb per SMRT Cell 1M. By integrating long and short read data, we demonstrate that the Iso-Seq method is a practical tool for annotating cancer genomes with high-quality transcript information. Citation Format: Elizabeth Tseng, Brendan Galvin, Ting Hon, Wigard P. Kloosterman, Meredith Ashby. Full length transcriptome sequencing of melanoma cell line complements long read sequencing assessment of genomic rearrangements [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2019; 2019 Mar 29-Apr 3; Atlanta, GA. Philadelphia (PA): AACR; Cancer Res 2019;79(13 Suppl):Abstract nr 1669.","PeriodicalId":445323,"journal":{"name":"Bioinformatics, Convergence Science, and Systems Biology","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128181377","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Abstract 1672: Clinical validation of a genomics-based classifier to predict tissue of origin from targeted tumor sequencing 1672:基于基因组学的分类器预测肿瘤来源的临床验证
Bioinformatics, Convergence Science, and Systems Biology Pub Date : 2019-07-01 DOI: 10.1158/1538-7445.AM2019-1672
Youyun Zheng, A. Penson, Niedzica Camacho, Evan Biederstedt, A. Zehir, C. Kandoth, Aijazuddin Syed, A. Varghese, H. Al-Ahmadie, N. Schultz, M. Ladanyi, D. Solit, D. Klimstra, D. Hyman, B. Taylor, M. Berger
{"title":"Abstract 1672: Clinical validation of a genomics-based classifier to predict tissue of origin from targeted tumor sequencing","authors":"Youyun Zheng, A. Penson, Niedzica Camacho, Evan Biederstedt, A. Zehir, C. Kandoth, Aijazuddin Syed, A. Varghese, H. Al-Ahmadie, N. Schultz, M. Ladanyi, D. Solit, D. Klimstra, D. Hyman, B. Taylor, M. Berger","doi":"10.1158/1538-7445.AM2019-1672","DOIUrl":"https://doi.org/10.1158/1538-7445.AM2019-1672","url":null,"abstract":"Introduction Various classes of genomic alterations can now be robustly detected from targeted Next Generation Sequencing (NGS)-based tumor profiling assays. Despite recent advances in genome-directed cancer therapies and lineage-agnostic basket clinical trials, tissue of origin remains a critical determinant of tumor biology and therapeutic sensitivity. Therefore, efficiently harnessing the mutational information to predict tissue of origin from NGS data can further aid diagnosis and treatment. Methods We have developed a novel random forest machine learning classifier that infers tissue of origin from the mutational features of each tumor NGS profile. We trained and validated the model using prospective sequencing data from >30,000 patients profiled by MSK-IMPACT, a custom FDA-authorized clinical sequencing assay. An initial version of this classifier trained on a smaller cohort, presented previously, has been further optimized to incorporate additional tumor types, genomic features, mutational signatures, and accessibility features for clinicians. Altogether, the model evaluates a comprehensive range of mutational features to generate predictions. In addition, we developed a framework for the prospective clinical implementation of our method that allows for extension to the expanding MSK-IMPACT cohort and utilization at the point of care. Results Overall, we predicted the correct cancer type in 74% of cases, with nearly half of cases predicted with high confidence (>95%). In order to make this tool accessible to pathologists for real-time diagnostic and treatment decisions, we also have implemented APIs that transmit our classifier predictions to the cBioPortal for Cancer Genomics and the MPath console from MSK Molecular Diagnostics Service. With the additional samples and genomic features, our model predictions have been improved and are considered during clinical review and sign-out. This practice has brought about critical diagnostic changes and orthogonal validation in several cases. In one case, a patient referred to MSK with a misdiagnosis of metastatic breast cancer to the bladder underwent MSK-IMPACT sequencing for her primary breast tumor and bladder lesion. The model predictions, confirmed by orthogonal testing, classified two lesions as independent primaries of breast and bladder origins, leading to significant changes in treatment regimens. Conclusion Our work delineates the framework of utilizing and optimizing machine learning models on NGS-based sequencing data to aid diagnosis and treatment. The same framework can be applied to cell-free DNA sequencing, which will capture tumor spatial heterogeneity and improve classifier performance. These results indicate that leveraging machine learning to predict tissue of origin complements conventional histologic review to provide integrated diagnoses, often with critical therapeutic implications. Citation Format: Youyun Zheng, Alexander V. Penson, Niedzica Camacho, Evan Biederstedt, Ahme","PeriodicalId":445323,"journal":{"name":"Bioinformatics, Convergence Science, and Systems Biology","volume":"106 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128611884","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Abstract 4239: Development of pan-cancer transcriptional signatures that predict chemosensitivity 4239:泛癌症转录特征预测化学敏感性的发展
Bioinformatics, Convergence Science, and Systems Biology Pub Date : 2019-07-01 DOI: 10.1158/1538-7445.am2019-4239
J. D. Wells, T. Miller
{"title":"Abstract 4239: Development of pan-cancer transcriptional signatures that predict chemosensitivity","authors":"J. D. Wells, T. Miller","doi":"10.1158/1538-7445.am2019-4239","DOIUrl":"https://doi.org/10.1158/1538-7445.am2019-4239","url":null,"abstract":"","PeriodicalId":445323,"journal":{"name":"Bioinformatics, Convergence Science, and Systems Biology","volume":"21 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128638629","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信
小红书