Pub Date : 2021-07-01DOI: 10.1158/1538-7445.AM2021-251
Caleb M Lindgren, Chelsie Minor, Lindsey K. Olsen, B. Henderson, Cptac Investigators, S. Payne
{"title":"Abstract 251: Data distribution for easy pancancer analysis","authors":"Caleb M Lindgren, Chelsie Minor, Lindsey K. Olsen, B. Henderson, Cptac Investigators, S. Payne","doi":"10.1158/1538-7445.AM2021-251","DOIUrl":"https://doi.org/10.1158/1538-7445.AM2021-251","url":null,"abstract":"","PeriodicalId":73617,"journal":{"name":"Journal of bioinformatics and systems biology : Open access","volume":"23 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74790788","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}
Pub Date : 2021-07-01DOI: 10.1158/1538-7445.AM2021-257
Auhood Nassar, Ahmed M. Lymona, Mai M. Lotfy, A. Youssef, A. N. Zekri
{"title":"Abstract 257: Tumor mutation burden of Egyptian breast cancer patients based on next generation sequencing","authors":"Auhood Nassar, Ahmed M. Lymona, Mai M. Lotfy, A. Youssef, A. N. Zekri","doi":"10.1158/1538-7445.AM2021-257","DOIUrl":"https://doi.org/10.1158/1538-7445.AM2021-257","url":null,"abstract":"","PeriodicalId":73617,"journal":{"name":"Journal of bioinformatics and systems biology : Open access","volume":"24 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74792845","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}
Pub Date : 2021-07-01DOI: 10.1158/1538-7445.AM2021-226
M. Ferrall-Fairbanks, N. Chakiryan, B. Chobrutskiy, Young-chul Kim, J. Teer, A. Berglund, J. Mulé, M. Fournier, E. Siegel, E. Katende, G. Blanck, B. Manley, P. Altrock
{"title":"Abstract 226: Tumor-infiltrating lymphocyte diversity and clear cell renal cell carcinoma","authors":"M. Ferrall-Fairbanks, N. Chakiryan, B. Chobrutskiy, Young-chul Kim, J. Teer, A. Berglund, J. Mulé, M. Fournier, E. Siegel, E. Katende, G. Blanck, B. Manley, P. Altrock","doi":"10.1158/1538-7445.AM2021-226","DOIUrl":"https://doi.org/10.1158/1538-7445.AM2021-226","url":null,"abstract":"","PeriodicalId":73617,"journal":{"name":"Journal of bioinformatics and systems biology : Open access","volume":"17 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75325906","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}
Pub Date : 2021-07-01DOI: 10.1158/1538-7445.AM2021-245
Somnath Tagore, A. Califano
{"title":"Abstract 245: A comprehensive characterization of hyper-morph, hypo-morph, and neo-morph mutations in cancer","authors":"Somnath Tagore, A. Califano","doi":"10.1158/1538-7445.AM2021-245","DOIUrl":"https://doi.org/10.1158/1538-7445.AM2021-245","url":null,"abstract":"","PeriodicalId":73617,"journal":{"name":"Journal of bioinformatics and systems biology : Open access","volume":"9 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"72723647","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}
Pub Date : 2021-07-01DOI: 10.1158/1538-7445.AM2021-264
J. Gilhodes, F. Penault-Llorca, J. Mazières, M. Pérol, C. Chouaid, E. Leconte, J. Delord, T. Filleron
{"title":"Abstract 264: Development of companion tests based on continuous markers: Illustration with blood-based tumor mutational burden in NSCLC cancer patients treated with atezolizumab","authors":"J. Gilhodes, F. Penault-Llorca, J. Mazières, M. Pérol, C. Chouaid, E. Leconte, J. Delord, T. Filleron","doi":"10.1158/1538-7445.AM2021-264","DOIUrl":"https://doi.org/10.1158/1538-7445.AM2021-264","url":null,"abstract":"","PeriodicalId":73617,"journal":{"name":"Journal of bioinformatics and systems biology : Open access","volume":"70 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76341685","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}
Pub Date : 2021-07-01DOI: 10.1158/1538-7445.AM2021-198
Gulden Olgun, Vishaka Gopalan, S. Hannenhalli
Background: MicroRNAs are small noncoding RNAs that mediate gene regulation at the post-transcriptional level via multiple mechanisms such as mRNA degradation, translational inhibition, and mRNA stabilization. They are involved in several cellular processes from development to homeostasis, and their deregulation is implicated in several diseases, including cancer. Since miRNA lacks the polyA tail, the standard single cell RNAseq protocols do not capture miRNAs, thus severely limiting our understanding of miRNA functions at cellular resolution. To overcome this limitation, we develop a novel machine learning method to infer the miRNA activity in a sample given its RNAseq profile. Methods: We develop a model using XGBoost, to predict miRNA profile in a sample from its global mRNA profile. We train and test the model using cross validation in the CCLE collection, as well as a number of healthy and cancer human tissue data obtained from GTEx and TCGA. We quantify the method9s performance as the correlation between actual and predicted miRNA expression values across the test samples. We validate our model in multiple single cell datasets where miRNA and mRNA profiles are available for the same cell types by assessing the model9s ability to identify cell type specific miRNAs based on a model trained on independent bulk datasets. Results: First, we show in CCLE collection, and multiple TCGA tissues, that a model based on all genes was far more accurate than the model based only on known targets. Our mean cross validation model accuracy across 10 tissues having greater than 100 paired miRNA and mRNA samples (in terms of Spearman correlation between predicted and actual expression of a miRNA) is 0.45 (min 0.39 in Pancreas to a max of 0.51 in Brain). In comparison to the normal tissues in GTEx, in the malignant counterpart in TCGA, due to greater heterogeneity, therefore greater variability in gene expression, our model performs significantly better (average cross validation accuracy improvement of 0.19). We have validated our model in independent single cell data. Using a model trained in bulk tissue data, we predict microRNA expression levels in a single cell based on the single cell RNA and compare our predicted fold difference by a miRNA9s expression between two cell types with the actual fold difference. We quantify the prediction accuracy as the correlation between the predicted and actual fold differences across all miRNAs. In a total of 4 cell type pair comparisons (different sets of kidney, brain, breast, and skin), our model achieves an average accuracy of 0.81 (ranging from 0.73 to 0.89), thus strongly validating our model. Our next step is to apply our model to study miRNA activities during T cell development, Pancreatic Ductal Adenocarcinoma, and Glioblastoma, in collaboration with experimentalists. Conclusions: Our method addresses a major bottleneck in studying miRNA activities at a cellular resolution and can be applied to any scRNA data to
{"title":"Abstract 198: Quantifying miRNA activity in single cell clusters","authors":"Gulden Olgun, Vishaka Gopalan, S. Hannenhalli","doi":"10.1158/1538-7445.AM2021-198","DOIUrl":"https://doi.org/10.1158/1538-7445.AM2021-198","url":null,"abstract":"Background: MicroRNAs are small noncoding RNAs that mediate gene regulation at the post-transcriptional level via multiple mechanisms such as mRNA degradation, translational inhibition, and mRNA stabilization. They are involved in several cellular processes from development to homeostasis, and their deregulation is implicated in several diseases, including cancer. Since miRNA lacks the polyA tail, the standard single cell RNAseq protocols do not capture miRNAs, thus severely limiting our understanding of miRNA functions at cellular resolution. To overcome this limitation, we develop a novel machine learning method to infer the miRNA activity in a sample given its RNAseq profile. Methods: We develop a model using XGBoost, to predict miRNA profile in a sample from its global mRNA profile. We train and test the model using cross validation in the CCLE collection, as well as a number of healthy and cancer human tissue data obtained from GTEx and TCGA. We quantify the method9s performance as the correlation between actual and predicted miRNA expression values across the test samples. We validate our model in multiple single cell datasets where miRNA and mRNA profiles are available for the same cell types by assessing the model9s ability to identify cell type specific miRNAs based on a model trained on independent bulk datasets. Results: First, we show in CCLE collection, and multiple TCGA tissues, that a model based on all genes was far more accurate than the model based only on known targets. Our mean cross validation model accuracy across 10 tissues having greater than 100 paired miRNA and mRNA samples (in terms of Spearman correlation between predicted and actual expression of a miRNA) is 0.45 (min 0.39 in Pancreas to a max of 0.51 in Brain). In comparison to the normal tissues in GTEx, in the malignant counterpart in TCGA, due to greater heterogeneity, therefore greater variability in gene expression, our model performs significantly better (average cross validation accuracy improvement of 0.19). We have validated our model in independent single cell data. Using a model trained in bulk tissue data, we predict microRNA expression levels in a single cell based on the single cell RNA and compare our predicted fold difference by a miRNA9s expression between two cell types with the actual fold difference. We quantify the prediction accuracy as the correlation between the predicted and actual fold differences across all miRNAs. In a total of 4 cell type pair comparisons (different sets of kidney, brain, breast, and skin), our model achieves an average accuracy of 0.81 (ranging from 0.73 to 0.89), thus strongly validating our model. Our next step is to apply our model to study miRNA activities during T cell development, Pancreatic Ductal Adenocarcinoma, and Glioblastoma, in collaboration with experimentalists. Conclusions: Our method addresses a major bottleneck in studying miRNA activities at a cellular resolution and can be applied to any scRNA data to","PeriodicalId":73617,"journal":{"name":"Journal of bioinformatics and systems biology : Open access","volume":"33 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76103484","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}
Pub Date : 2021-07-01DOI: 10.1158/1538-7445.AM2021-241
C. Magnan, S. Rivera, F. Lopez-Diaz, Chenhui Ou, Kenneth B. Thomas, Hyunjun Nam, L. Weiss, Segun Jung, V. Funari
Background: The use of sequencing technologies to detect gene fusions (GFs) from RNA shows promising results for the future of cancer diagnosis and treatment. Major obstacles for this approach include target design and lack of well-curated databases of RNA breakpoints. Currently, off-the-shelf designs include full transcript targeting that results in massive and costly amounts of data. Directly targeting the known GFs from RNA by designing probes targeting the fusion junction sequence is studied here as an alternative to whole-exome sequencing (WES). We present notably a novel algorithm capable of designing the probes to accurately target the desired fusions from RNA. Methods: For a given GF detected either from DNA or from RNA, the algorithm is as follows: (1) Collect gene and isoform information for both partners from seven public databases; (2) For each candidate pair of isoforms, locate where the breakpoints will be observed and assign a score based on various criteria such as sequence completion, coding information, transcript support level, % identity with and % visible on hg38; (3) Select the top scoring pair of transcripts and extract the chimeric probe sequence. Two sets of probes extracted with this protocol targeting 524 and 1632 known GFs were synthetized and tested on several samples (Table 1). The Agilent SureSelect Human All Exon V6 capture kit was used to compare targeting efficiency against WES. Results: Targeted enrichment of a SeraSeq control showed a 5 to 20 fold increase in supporting evidence over WES. On 10 clinical samples, we observed 10-30x increase in supporting reads. A higher sensitivity is observed in both cases. Conclusion: We developed a novel algorithm capable of accurately identifying the most likely location of an RNA fusion junction and generating the probe sequences for oligo synthesis. This method not only enriches for more supporting data but also reduces the associated costs. Citation Format: Christophe N. Magnan, Steven P. Rivera, Fernando J. Lopez-Diaz, Chen-Yin Ou, Kenneth B. Thomas, Hyunjun Nam, Lawrence M. Weiss, Segun C. Jung, Vincent A. Funari. An efficient probe design algorithm for direct fusion targeting from RNA [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2021; 2021 Apr 10-15 and May 17-21. Philadelphia (PA): AACR; Cancer Res 2021;81(13_Suppl):Abstract nr 241.
背景:利用测序技术从RNA中检测基因融合(GFs)，在未来的癌症诊断和治疗中显示出有希望的结果。这种方法的主要障碍包括目标设计和缺乏精心策划的RNA断点数据库。目前，现成的设计包括完整的转录目标，导致大量和昂贵的数据量。本文研究了通过设计靶向融合连接序列的探针直接靶向RNA中的已知基因，作为全外显子组测序(WES)的替代方法。值得注意的是，我们提出了一种新颖的算法，能够设计探针来准确地靶向RNA的所需融合。方法:对于从DNA或RNA中检测到的给定GF，算法如下:(1)从7个公共数据库中收集伴侣双方的基因和同工异构体信息;(2)对每一对候选同工异构体，根据序列完成度、编码信息、转录支持水平、与hg38的同源性%、在hg38上的可见性%等标准，定位观察到断点的位置，并给出评分;(3)选择得分最高的转录本对，提取嵌合探针序列。用该方案提取的两组探针分别靶向524和1632个已知基因，并在几个样品上进行了测试(表1)。使用Agilent SureSelect Human All Exon V6捕获试剂盒与WES比较靶向效率。结果:SeraSeq对照的靶向富集显示支持证据比WES增加5至20倍。在10个临床样本中，我们观察到支持读数增加了10-30倍。在这两种情况下观察到更高的灵敏度。结论:我们开发了一种新的算法，能够准确地识别RNA融合连接的最可能位置，并生成用于寡核苷酸合成的探针序列。该方法不仅丰富了更多的支持数据，而且降低了相关成本。引用格式:Christophe N. Magnan, Steven P. Rivera, Fernando J. Lopez-Diaz, Chen-Yin Ou, Kenneth B. Thomas, Hyunjun Nam, Lawrence M. Weiss, Segun C. Jung, Vincent A. Funari一种有效的RNA直接融合靶向探针设计算法[摘要]。见:美国癌症研究协会2021年年会论文集;2021年4月10日至15日和5月17日至21日。费城(PA): AACR;癌症杂志，2021;81(13 -增刊):摘要第241期。
{"title":"Abstract 241: An efficient probe design algorithm for direct fusion targeting from RNA","authors":"C. Magnan, S. Rivera, F. Lopez-Diaz, Chenhui Ou, Kenneth B. Thomas, Hyunjun Nam, L. Weiss, Segun Jung, V. Funari","doi":"10.1158/1538-7445.AM2021-241","DOIUrl":"https://doi.org/10.1158/1538-7445.AM2021-241","url":null,"abstract":"Background: The use of sequencing technologies to detect gene fusions (GFs) from RNA shows promising results for the future of cancer diagnosis and treatment. Major obstacles for this approach include target design and lack of well-curated databases of RNA breakpoints. Currently, off-the-shelf designs include full transcript targeting that results in massive and costly amounts of data. Directly targeting the known GFs from RNA by designing probes targeting the fusion junction sequence is studied here as an alternative to whole-exome sequencing (WES). We present notably a novel algorithm capable of designing the probes to accurately target the desired fusions from RNA. Methods: For a given GF detected either from DNA or from RNA, the algorithm is as follows: (1) Collect gene and isoform information for both partners from seven public databases; (2) For each candidate pair of isoforms, locate where the breakpoints will be observed and assign a score based on various criteria such as sequence completion, coding information, transcript support level, % identity with and % visible on hg38; (3) Select the top scoring pair of transcripts and extract the chimeric probe sequence. Two sets of probes extracted with this protocol targeting 524 and 1632 known GFs were synthetized and tested on several samples (Table 1). The Agilent SureSelect Human All Exon V6 capture kit was used to compare targeting efficiency against WES. Results: Targeted enrichment of a SeraSeq control showed a 5 to 20 fold increase in supporting evidence over WES. On 10 clinical samples, we observed 10-30x increase in supporting reads. A higher sensitivity is observed in both cases. Conclusion: We developed a novel algorithm capable of accurately identifying the most likely location of an RNA fusion junction and generating the probe sequences for oligo synthesis. This method not only enriches for more supporting data but also reduces the associated costs. Citation Format: Christophe N. Magnan, Steven P. Rivera, Fernando J. Lopez-Diaz, Chen-Yin Ou, Kenneth B. Thomas, Hyunjun Nam, Lawrence M. Weiss, Segun C. Jung, Vincent A. Funari. An efficient probe design algorithm for direct fusion targeting from RNA [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2021; 2021 Apr 10-15 and May 17-21. Philadelphia (PA): AACR; Cancer Res 2021;81(13_Suppl):Abstract nr 241.","PeriodicalId":73617,"journal":{"name":"Journal of bioinformatics and systems biology : Open access","volume":"11 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85179162","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}
Pub Date : 2021-07-01DOI: 10.1158/1538-7445.AM2021-238
Michael F. Sharpnack, Travis S. Johnson, R. Chalkley, Zhi Han, D. Carbone, Kun Huang, K. He
Background: Tumor specific antigen (TSA) identification in human cancer predicts response to immunotherapy and provides vaccine targets for precision medicine. In addition to neoantigens from somatic coding mutations, numerous non-mutated TSAs can elicit T-cell responses but are often overlooked by current methods. We present a method that accurately and comprehensively predict TSAs from RNAseq data regardless of mutation status. Methods: HLA-I genotypes were predicted with seq2HLA. RNAseq fastq files were translated into all possible peptides of length 8-11, and peptides with high expression in the tumor and comparatively low expression in normal were tested for their MHC-I binding potential with netMHCpan-4.0. We defined our predicted TSA by i) high expression in tumor samples, ii) low expression in normal samples, and iii) high predicted patient-specific MHC-I binding affinity. Results: We developed a novel pipeline for TSA prediction from RNAseq that is not limited to mutation-derived TSAs. This pipeline was used to predict all possible unique peptides size 8-11 on previously published murine and human lung and lymphoma tumors then validated on matched tumor and control lung adenocarcinoma (LUAD) samples. This pipeline is able to predict TSAs in MHC-I ligand-purified proteomics data with favorable performance to existing methods. Furthermore, neoantigens predicted by exomeSeq are typically poorly expressed at the RNA level, (28% of predicted neoantigens with >0 expression, mean of 15.6 reads/sample) and a fraction of them (47/6,928, 0.68%) are expressed in matched normal samples. Finally, a set of 6 TSAs are expressed in 22/39 (56%) of LUAD tumors and represent attractive vaccine targets. Conclusion: Direct quantification of RNAseq evidence of the potential peptidome in matched tumor and control RNAseq samples, via our novel pipeline, allows for exhaustive detection of TSAs. Citation Format: Michael Sharpnack, Travis Johnson, Robert Chalkley, Zhi Han, David Carbone, Kun Huang, Kai He. Exhaustive tumor specific antigen detection with RNAseq [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2021; 2021 Apr 10-15 and May 17-21. Philadelphia (PA): AACR; Cancer Res 2021;81(13_Suppl):Abstract nr 238.
背景:肿瘤特异性抗原(Tumor specific antigen, TSA)在人类癌症中的鉴定可预测免疫治疗反应，为精准医疗提供疫苗靶点。除了来自体细胞编码突变的新抗原外，许多未突变的tsa可以引起t细胞反应，但通常被当前的方法所忽视。我们提出了一种从RNAseq数据中准确、全面地预测tsa的方法，而不考虑突变状态。方法:采用seq2HLA预测hla - 1基因型。将RNAseq fastq文件翻译成长度为8-11的所有可能的肽段，用netMHCpan-4.0检测肿瘤中高表达和正常中低表达的肽段的MHC-I结合潜力。我们将预测的TSA定义为:i)肿瘤样本中的高表达，ii)正常样本中的低表达，以及iii)高预测的患者特异性MHC-I结合亲和力。结果:我们开发了一种新的RNAseq预测TSA的管道，该管道不限于突变衍生的TSA。该管道用于预测先前发表的小鼠和人类肺和淋巴瘤肿瘤中所有可能的8-11大小的独特肽，然后在匹配的肿瘤和对照肺腺癌(LUAD)样本中进行验证。该管道能够预测MHC-I配体纯化蛋白质组学数据中的tsa，与现有方法相比具有良好的性能。此外，exomeSeq预测的新抗原通常在RNA水平上表达较差(28%的预测新抗原表达>0，平均15.6 reads/样本)，其中一小部分(47/6,928,0.68%)在匹配的正常样本中表达。最后，一组6个tsa在22/39(56%)的LUAD肿瘤中表达，代表了有吸引力的疫苗靶点。结论:通过我们的新管道，直接定量匹配肿瘤和对照RNAseq样本中潜在肽肽的RNAseq证据，可以彻底检测tsa。引文格式:Michael Sharpnack, Travis Johnson, Robert Chalkley, Zhi Han, David Carbone, Kun Huang, Kai He。用RNAseq技术检测肿瘤特异性抗原[摘要]。见:美国癌症研究协会2021年年会论文集;2021年4月10日至15日和5月17日至21日。费城(PA): AACR;癌症杂志，2021;81(13 -增刊):摘要第238期。
{"title":"Abstract 238: Exhaustive tumor specific antigen detection with RNAseq","authors":"Michael F. Sharpnack, Travis S. Johnson, R. Chalkley, Zhi Han, D. Carbone, Kun Huang, K. He","doi":"10.1158/1538-7445.AM2021-238","DOIUrl":"https://doi.org/10.1158/1538-7445.AM2021-238","url":null,"abstract":"Background: Tumor specific antigen (TSA) identification in human cancer predicts response to immunotherapy and provides vaccine targets for precision medicine. In addition to neoantigens from somatic coding mutations, numerous non-mutated TSAs can elicit T-cell responses but are often overlooked by current methods. We present a method that accurately and comprehensively predict TSAs from RNAseq data regardless of mutation status. Methods: HLA-I genotypes were predicted with seq2HLA. RNAseq fastq files were translated into all possible peptides of length 8-11, and peptides with high expression in the tumor and comparatively low expression in normal were tested for their MHC-I binding potential with netMHCpan-4.0. We defined our predicted TSA by i) high expression in tumor samples, ii) low expression in normal samples, and iii) high predicted patient-specific MHC-I binding affinity. Results: We developed a novel pipeline for TSA prediction from RNAseq that is not limited to mutation-derived TSAs. This pipeline was used to predict all possible unique peptides size 8-11 on previously published murine and human lung and lymphoma tumors then validated on matched tumor and control lung adenocarcinoma (LUAD) samples. This pipeline is able to predict TSAs in MHC-I ligand-purified proteomics data with favorable performance to existing methods. Furthermore, neoantigens predicted by exomeSeq are typically poorly expressed at the RNA level, (28% of predicted neoantigens with >0 expression, mean of 15.6 reads/sample) and a fraction of them (47/6,928, 0.68%) are expressed in matched normal samples. Finally, a set of 6 TSAs are expressed in 22/39 (56%) of LUAD tumors and represent attractive vaccine targets. Conclusion: Direct quantification of RNAseq evidence of the potential peptidome in matched tumor and control RNAseq samples, via our novel pipeline, allows for exhaustive detection of TSAs. Citation Format: Michael Sharpnack, Travis Johnson, Robert Chalkley, Zhi Han, David Carbone, Kun Huang, Kai He. Exhaustive tumor specific antigen detection with RNAseq [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2021; 2021 Apr 10-15 and May 17-21. Philadelphia (PA): AACR; Cancer Res 2021;81(13_Suppl):Abstract nr 238.","PeriodicalId":73617,"journal":{"name":"Journal of bioinformatics and systems biology : Open access","volume":"8 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86912116","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}
Pub Date : 2021-07-01DOI: 10.1158/1538-7445.AM2021-2
A. Vasciaveo, Francisca Nunes de Almeida, Min Zou, Matteo Di Bernardo, A. Califano, C. Abate-Shen
{"title":"Abstract 2: Addressing treatment resistance in models of lethal prostate cancer","authors":"A. Vasciaveo, Francisca Nunes de Almeida, Min Zou, Matteo Di Bernardo, A. Califano, C. Abate-Shen","doi":"10.1158/1538-7445.AM2021-2","DOIUrl":"https://doi.org/10.1158/1538-7445.AM2021-2","url":null,"abstract":"","PeriodicalId":73617,"journal":{"name":"Journal of bioinformatics and systems biology : Open access","volume":"1 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89557443","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}
Human embryonic stem cells (hESCs) and pluripotent stem cells (iPSCs)-based disease modelings are potential platforms for cancer research and development of new cancer therapeutics. Differentiation of stem cells is an essential step for those disease models. For tissue-specific differentiation, hESCs or iPSCs are cultured in specific receipts of induction and differentiation media for developing different types of tissue cells such as muscle, skin, and liver providing further study or clinical applications. During lineage differentiation, researcher needs to closely monitor stem cell differentiation to be on track via checking cell morphological changes under microscope since this procedure has high probability of failed differentiation results (e.g., no differentiation or differentiating unwanted tissue types). However, monitoring via microscopy is labor-intensive and time-consuming, and also has high inter-observer variation issues. Therefore, it significantly impedes the progression of stem cell research and clinical applications nowadays. In recent years, machine learning has shown promising results in many applications of artificial intelligence (AI) in different fields, especially computer vision and image analysis. AI-based computational tool will bring benefits like high-throughput, high accuracy, and reproductivity in many medical applications. In stem cell culture and differentiation, we believe that applying this new technology will help researcher detect abnormal stem cell differentiation at the early stage via microscopy to save time, labor, and cost for the study and aggregate reproducible data along the process. To this end, we developed a machine learning-based AI model to assist in monitoring morphological changes of hESCs culture in bright-field microscopy images obtained from different differentiation stages to mature hepatocytes. We conducted a pilot study to train an AI model estimating efficiency of stem cell differentiation at Hepatic Progenitor Cell (HPC) stage, which is a critical checkpoint for hepatocyte differentiation. To prepare datasets for training, experienced researchers annotated the morphology of HPC in hundreds of microscope images and determined a differentiation result (success/fail) for every image. During the model training, the initial model was first trained by a training dataset consisting of 341 success and 366 fail HPC results. Subsequently, a smaller separate dataset comprising of 86 success and 51 fail HPC results was then used for cross-validation. Finally, the test set containing 64 success and 29 fail HPC results was used to evaluate the AI model performance. In result, the AI model presented an excellent performance (accuracy= 0.978 and F1 score= 0.975). Our study suggests a potential application of AI-assisted monitoring model for stem cell culture and differentiation in the future. Citation Format: Wei-Lei Yang, Zijun Huo, ShihYu Chen, Dandan Zhu, Tien-Jen Liu, Dung-Fang Lee. Monitoring of ste
{"title":"Abstract 185: Monitoring of stem cell differentiation to mature hepatocytes with a machine learning-based AI model","authors":"Wei-Lei Yang, Zijun Huo, Shih‐Chen Chen, Dandan Zhu, Tien-Jen Liu, Dung-Fang Lee","doi":"10.1158/1538-7445.AM2021-185","DOIUrl":"https://doi.org/10.1158/1538-7445.AM2021-185","url":null,"abstract":"Human embryonic stem cells (hESCs) and pluripotent stem cells (iPSCs)-based disease modelings are potential platforms for cancer research and development of new cancer therapeutics. Differentiation of stem cells is an essential step for those disease models. For tissue-specific differentiation, hESCs or iPSCs are cultured in specific receipts of induction and differentiation media for developing different types of tissue cells such as muscle, skin, and liver providing further study or clinical applications. During lineage differentiation, researcher needs to closely monitor stem cell differentiation to be on track via checking cell morphological changes under microscope since this procedure has high probability of failed differentiation results (e.g., no differentiation or differentiating unwanted tissue types). However, monitoring via microscopy is labor-intensive and time-consuming, and also has high inter-observer variation issues. Therefore, it significantly impedes the progression of stem cell research and clinical applications nowadays. In recent years, machine learning has shown promising results in many applications of artificial intelligence (AI) in different fields, especially computer vision and image analysis. AI-based computational tool will bring benefits like high-throughput, high accuracy, and reproductivity in many medical applications. In stem cell culture and differentiation, we believe that applying this new technology will help researcher detect abnormal stem cell differentiation at the early stage via microscopy to save time, labor, and cost for the study and aggregate reproducible data along the process. To this end, we developed a machine learning-based AI model to assist in monitoring morphological changes of hESCs culture in bright-field microscopy images obtained from different differentiation stages to mature hepatocytes. We conducted a pilot study to train an AI model estimating efficiency of stem cell differentiation at Hepatic Progenitor Cell (HPC) stage, which is a critical checkpoint for hepatocyte differentiation. To prepare datasets for training, experienced researchers annotated the morphology of HPC in hundreds of microscope images and determined a differentiation result (success/fail) for every image. During the model training, the initial model was first trained by a training dataset consisting of 341 success and 366 fail HPC results. Subsequently, a smaller separate dataset comprising of 86 success and 51 fail HPC results was then used for cross-validation. Finally, the test set containing 64 success and 29 fail HPC results was used to evaluate the AI model performance. In result, the AI model presented an excellent performance (accuracy= 0.978 and F1 score= 0.975). Our study suggests a potential application of AI-assisted monitoring model for stem cell culture and differentiation in the future. Citation Format: Wei-Lei Yang, Zijun Huo, ShihYu Chen, Dandan Zhu, Tien-Jen Liu, Dung-Fang Lee. Monitoring of ste","PeriodicalId":73617,"journal":{"name":"Journal of bioinformatics and systems biology : Open access","volume":"31 3 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79584796","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：