Cancer Genetics最新文献

{"title":"76. Automating immunogenomic tumor board decision-making for neoantigen cancer vaccine design","authors":"Jennie Yao ,&nbsp;Kartik Singhal ,&nbsp;Susanna Kiwala ,&nbsp;Peter Goedegebuure ,&nbsp;Christopher Miller ,&nbsp;Huiming Xia ,&nbsp;My Hoang ,&nbsp;Mariam Khanfar ,&nbsp;Kelsy Cotto ,&nbsp;Sherri Davies ,&nbsp;Feiyu Du ,&nbsp;Evelyn Schmidt ,&nbsp;Gue Su Chang ,&nbsp;Jasreet Hundal ,&nbsp;Jeffrey Ward ,&nbsp;William Inabinett ,&nbsp;William Hoos ,&nbsp;William Gillanders ,&nbsp;Obi Griffith ,&nbsp;Malachi Griffith","doi":"10.1016/j.cancergen.2024.08.078","DOIUrl":"10.1016/j.cancergen.2024.08.078","url":null,"abstract":"<div><div>Advancements in immunogenomics and immuno-oncology have enabled the development of neoantigen vaccines, offering personalized cancer therapies by targeting cancer cell-specific somatic mutations. These mutations produce neoantigens that, when presented on tumor cells by MHC molecules, can elicit a robust and specific immune response. To date, there are 108 interventional studies listed on clinicaltrials.gov that explore the use of cancer vaccines. We have supported a number of these trials through the creation of bioinformatic pipelines, tools and procedures for the identification of patient-specific neoantigen candidates. Final prioritization of neoantigen candidates relies on manual review by an Immunogenomics Tumor Board (ITB) that meets weekly, increasing turnaround time and presenting a barrier to scaling.</div><div>Addressing this challenge, we introduce a machine learning-based approach to automate the selection of neoantigens peptides. We implemented a random forest model to train and test on existing ITB results from 21 patients and 1,324 peptides, including 297 peptides prioritized for personalized vaccine inclusion. This model aims to use features such as mutation position, driver gene status, tumor variant allele frequency, RNA expression, and other features to automatically predict whether a peptide will be accepted, rejected, or require further review for the vaccine. The model achieved an 88.89% sensitivity and 86.4% specificity, with an area under the curve of 0.933. By integrating this model into the vaccine development pipeline, we foresee a significant reduction in the time required to transition from patient sample collection to vaccine manufacturing, thereby enhancing the efficiency and scalability of personalized cancer vaccine production.</div></div>","PeriodicalId":49225,"journal":{"name":"Cancer Genetics","volume":"286 ","pages":"Page S24"},"PeriodicalIF":1.4,"publicationDate":"2024-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142323336","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"44. UMI-based expanded NGS panel in precision molecular diagnosis of vascular anomalies: Early results","authors":"Avinash Dharmadhikari,&nbsp;Sara Kreimer,&nbsp;Jianling Ji,&nbsp;Ryan Schmidt,&nbsp;Miao Sun,&nbsp;Gordana Raca,&nbsp;Yachen Pan,&nbsp;Cindy Fong,&nbsp;Meagan Hughes,&nbsp;Jessica Lee,&nbsp;Minnelly Lu,&nbsp;Joseph Miller,&nbsp;Dean Anselmo,&nbsp;Jaclyn Biegel,&nbsp;Matthew Deardorff","doi":"10.1016/j.cancergen.2024.08.046","DOIUrl":"10.1016/j.cancergen.2024.08.046","url":null,"abstract":"<div><h3>Purpose</h3><div>To describe early results from a highly sensitive genetic panel to evaluate patients with largely mosaic vascular anomalies</div></div><div><h3>Methods</h3><div>This is a single-center study utilizing a 218 gene panel with unique molecular identifier (UMI) adapters and an average 1000X target coverage. DNA was obtained from fresh, frozen or paraffin-embedded tissue, blood, buccal brushes, or cells pelleted from fluid.</div></div><div><h3>Results</h3><div>24 patients were evaluated in a vascular anomalies center and 6 patients were evaluated by dermatology, genetics, or oncology. 23/30 patients (76.7%) had identified causal variants. 25 variants were described: 11 <em>PIK3CA</em>, 4 <em>TEK</em>, 2 <em>GNAQ</em>, 2 <em>KRAS</em>, 1 <em>KDR</em>, 1 <em>CELSR1</em>, 1 <em>PTEN</em>, 1 <em>SUFU</em>, 1 <em>MAP2K1</em>, and 1 <em>MTOR</em>. These variants were classified as 21 pathogenic, 1 likely pathogenic, and 3 variants of uncertain significance (VUS). Of the 11 variants in <em>PIK3CA</em>, the kinase domain substitution at p.His1047 was the most frequently observed (36.3%). Mean variant allele frequency (VAF) was 18.7%, with a minimum VAF of 1.9%, therefore most variants were consistent with somatic mosaicism. Variants in <em>CELSR1</em> and <em>SUFU</em> were identified at VAFs suggestive of a germline origin in patients who were not known to have germline variants. 6 patients had an alteration of clinical management based on the findings.</div></div><div><h3>Conclusions</h3><div>This genetic panel is highly effective in identifying somatic and germline clinically significant variants in patients with vascular anomalies. The prevalence of causative variants is higher than reported in previous studies. Future directions include validation of this panel in additional specimen types to extend utility.</div></div>","PeriodicalId":49225,"journal":{"name":"Cancer Genetics","volume":"286 ","pages":"Page S14"},"PeriodicalIF":1.4,"publicationDate":"2024-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142323202","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"45. Examining potential candidate genes within deletions of 3p14.2 to 3p14.1 in two cases of autism and developmental delay","authors":"Rebecca Smith,&nbsp;Ashwini Yenamandra,&nbsp;Meng-Chang Hsiao,&nbsp;Monica Guardado,&nbsp;Jeanette Saffir,&nbsp;Scott Ward","doi":"10.1016/j.cancergen.2024.08.047","DOIUrl":"10.1016/j.cancergen.2024.08.047","url":null,"abstract":"<div><div>Copy number deletions at chromosomal region 3p14 are rare constitutional occurrences and the genes within this region are mainly unclassified. The small number of publications describing patients with 3p14 deletions list phenotypes of multiple congenital anomalies, movement disorders, feeding difficulties, developmental delay, and autism. Despite these recurring patient phenotypes, no potential candidate genes within this region have been identified.</div><div>Here we describe two unrelated cases with overlapping 3p14.2 to 3p14.1 single-copy deletions. The first case is a 5-year-old male with childhood apraxia of speech, global developmental delay, autism spectrum disorder, and hyperkinesis. This patient's deletion is 3.1 Mb in size and contains 15 known genes and 8 OMIM genes. The second case is a 2-year-old female with prematurity, global developmental delay, failure to thrive, feeding difficulties, feeding tube dependency, short stature, microcephaly, PDA closure, autism spectrum disorder, and abnormalities on brain MRI. This patient's deletion is 3.5 Mb in size and contains 24 known genes and 10 OMIM genes.</div><div>Taken together, 7 OMIM genes are deleted in both patients: <em>PTPRG, FEZF2, CADPS, SNTN, THOC7, ATXN7, SCAANT1</em>. We will explore how deletion of these potential candidate genes may impact the patients' shared phenotypes of autism and global developmental delay. Additionally, we will examine the three genes (<em>PSMD6, PRICKLE2, ADAMTS9</em>) that are deleted only in the second patient, who displays a more severe phenotype. This assessment may identify candidate genes for follow-up functional studies and will contribute to the literature by describing patients with rare copy number losses in this region.</div></div>","PeriodicalId":49225,"journal":{"name":"Cancer Genetics","volume":"286 ","pages":"Page S15"},"PeriodicalIF":1.4,"publicationDate":"2024-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142323203","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"47. Genomic characterization of the T-ALL cell line CCRF-CEM using optical genome mapping and nanopore sequencing","authors":"Hussain Alcassab,&nbsp;Chin-Ting Wu,&nbsp;Awdhesh Kalia,&nbsp;Manjunath Nimmakayalu,&nbsp;Xiaojun Liu","doi":"10.1016/j.cancergen.2024.08.049","DOIUrl":"10.1016/j.cancergen.2024.08.049","url":null,"abstract":"<div><div>Human Cancer cell lines provide a valuable model for detecting genomic alterations and chromosomal aberrations to identify and validate new diagnostic or therapeutic targets. Here, we recharacterize the T-cell acute lymphocytic leukemia (T-ALL) cell line CCRF-CEM (ATCC #CCL-119) using karyotyping, FISH, aCGH, and emerging genomic technologies of optical genome mapping (OGM) and nanopore long-read sequencing (LRS). Consistent with the previous literature, karyotyping and FISH indicated a modal number of 47, with t(8;9)(p12;p24) and trisomy 20 in analyzed metaphases. ACGH confirmed trisomy 20 apparent in the karyotype but also showed both an unbalanced der(5)t(5;14)(q35.2;q32.2) translocation, independently confirmed by FISH, and a 226-kb deletion at 10q23.31 containing the tumor suppressor gene <em>PTEN</em>, concordant with existing literature. Saphyr-based OGM analysis confirmed the aCGH data; however, OGM analysis additionally identified monosomy X (copy number fraction 1.579), which could arise from a subclonal population as previously reported, and the breakpoint at 8p11.21 as the true region of the balanced translocation. Strikingly, OGM also identified a novel likely pathogenic cryptic 81.9-kb deletion at 1p33 overlapping the <em>STIL</em> gene (80X coverage). Deletions of <em>STIL</em> are known to occur in T-cell leukemias although this aberration has not been described in the CCRF-CEM cell line. We are currently in the process of analyzing LRS data to validate OGM findings and determine precise deletion breakpoints. Collectively, our data have identified a novel chromosomal aberration in the CCRF-CEM cell line providing a framework for further functional characterization.</div></div>","PeriodicalId":49225,"journal":{"name":"Cancer Genetics","volume":"286 ","pages":"Page S15"},"PeriodicalIF":1.4,"publicationDate":"2024-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142323207","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"51. Utility of microarray in the diagnosis of hematologic neoplasms with normal FISH and karyotype","authors":"Marwa Daghsni,&nbsp;Taimoor Sheikh,&nbsp;Lynn H. Sniezek,&nbsp;Michaelia M. Austin,&nbsp;Mahmoud Aarabi,&nbsp;Svetlana Yatsenko","doi":"10.1016/j.cancergen.2024.08.053","DOIUrl":"10.1016/j.cancergen.2024.08.053","url":null,"abstract":"<div><div>Chromosome analysis and fluorescence in situ hybridization (FISH) testing are the standard techniques in diagnosis, classification, and risk assessment of hematologic neoplasms such as myelodysplastic syndrome (MDS), acute myelogenous leukemia (AML), B-cell acute lymphoblastic leukemia (B-ALL), and chronic lymphocytic leukemia (CLL). Notably, the result of conventional cytogenetic testing is normal or non-informative in at least 10% of B-ALL, 50% of MDS/AML, and 15% of CLL cases, preventing accurate characterization of cancer genomic profile. Chromosomal microarray analysis (CMA) is widely used for detection of cryptic chromosomal imbalances and copy-neutral loss of heterozygosity, which are beyond the resolution of conventional cytogenetic methodologies. This study has evaluated the CMA utility and diagnostic yield in patients with an established diagnosis of either B-ALL, MDS/AML, or CLL, and negative findings of G-banding karyotype and disease-relevant FISH panel testing. During a 5-year period, karyotype, FISH and CMA were performed on 3628 samples, including 2720 cases of MDS/AML, 240 B-ALL and 668 CLL cases. At diagnosis normal karyotype and FISH were reported for 1466/2720 (54%) of patients with MDS/AML, 23/240 (9.6%) of B-ALL, and 112/668 (16.8%) of CLL cases. Using CMA, submicroscopic copy number alterations of diagnostic and prognostic significance were identified in 14.6% of MDS/AML cases, 26.1% of B-ALL, and 6.3% of CLL patients. Additionally, CMA revealed clones with large chromosomal abnormalities that were not observed among metaphase cells. Implementation of CMA in diagnosis of hematologic malignancies can significantly improve the diagnostic yield and provide data for a patient-specific risk stratification, prognostication, and therapeutic decisions.</div></div>","PeriodicalId":49225,"journal":{"name":"Cancer Genetics","volume":"286 ","pages":"Page S16"},"PeriodicalIF":1.4,"publicationDate":"2024-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142323211","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"60. AI-guided histopathology predicts brain metastasis in lung cancer patients","authors":"Brianna Munnich ,&nbsp;Haowen Zhou ,&nbsp;Mark Watson ,&nbsp;Cory Bernadt ,&nbsp;Steven (Siyu) Lin ,&nbsp;Jon Ritter ,&nbsp;Chieh-Yu Lin ,&nbsp;Ramaswamy Govindan ,&nbsp;Siddarth Rawal ,&nbsp;Changhuei Yang ,&nbsp;Richard Cote","doi":"10.1016/j.cancergen.2024.08.062","DOIUrl":"10.1016/j.cancergen.2024.08.062","url":null,"abstract":"<div><div>Brain metastases can occur in nearly half of patients with early and locally advanced (stage I-III) non-small cell lung cancer (NSCLC). There are no reliable histopathologic or molecular means to identify those who are likely to develop brain metastases. We sought to determine if deep learning (DL) could be applied to routine hematoxylin and eosin (H&amp;E) stained primary tumor tissue sections from Stage I-III NSCLC patients to predict the development of brain metastasis. Diagnostic slides from 158 patients with Stage I to III NSCLC followed for at least 5 years for development of brain metastases (Met+, 65 patients) versus no progression (Met-, 93 patients) were subjected to whole slide imaging. Three separate iterations of DL were performed by first selecting 118 cases (45 Met+, 73 Met-) to train and validate the DL algorithm, while 40 separate cases (20 Met+, 20 Met-) were used as the test set. DL algorithm results were compared to a blinded review by four expert pathologists. The DL-based algorithm was able to distinguish eventual development of brain metastases with an accuracy of 87% (p&lt;0.0001) compared to an average of 57.3% by the four pathologists, and appears to be particularly useful in predicting brain metastases in Stage I patients. DL-based algorithms using routine H&amp;E-stained slides may identify patients likely to develop brain metastases from those that will remain disease free over extended (&gt;5 year) follow-up and may thus be spared systemic therapy.</div></div>","PeriodicalId":49225,"journal":{"name":"Cancer Genetics","volume":"286 ","pages":"Pages S19-S20"},"PeriodicalIF":1.4,"publicationDate":"2024-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142322880","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Whole genome joint analysis reveals ATM:C.1564_1565del variant segregating with Ataxia-Telangiectasia and breast cancer","authors":"Mario Ćuk ,&nbsp;Busra Unal ,&nbsp;Connor P. Hayes ,&nbsp;McKenzie Walker ,&nbsp;Anđela Bevanda ,&nbsp;Viktorija Antolović ,&nbsp;Arezou A. Ghazani","doi":"10.1016/j.cancergen.2024.07.002","DOIUrl":"10.1016/j.cancergen.2024.07.002","url":null,"abstract":"<div><p><em>ATM</em> gene is implicated in the development of breast cancer in the heterozygous state, and Ataxia-telangiectasia (A-T) in a homozygous or compound heterozygous state. Ataxia-telangiectasia (A-T) is a rare cerebellar ataxia syndrome presenting with progressive neurologic impairment, telangiectasia, and an increased risk of leukemia and lymphoma.</p><p>Although the role of <em>ATM,</em> separately, in association with A-T and breast cancer is well documented, there is a limited number of studies investigating <em>ATM</em> variants when segregating with both phenotypes in the same family. Here, using joint analysis and whole genome sequencing, we investigated <em>ATM</em> c.1564_1565del in a family with one homozygous member presenting with A-T (OMIM # <span><span>208900</span><svg><path></path></svg></span>) and three heterozygous members, of whom one had breast cancer (OMIM #<span><span>114480</span><svg><path></path></svg></span>). To our knowledge, this is the first study of <em>ATM</em> c.1564_1565del segregation with both A-T and breast cancer phenotypes within the same kindred. This study highlights the need for a comprehensive genomic approach in the appropriate cancer risk management of heterozygote carriers of <em>ATM</em> in families with A-T.</p></div>","PeriodicalId":49225,"journal":{"name":"Cancer Genetics","volume":"286 ","pages":"Pages 43-47"},"PeriodicalIF":1.4,"publicationDate":"2024-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141789616","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"32. pVACsplice: A Computational tool for predicting and prioritizing alternative splicing neoantigens","authors":"My Hoang,&nbsp;Megan Richters,&nbsp;Susanna Kiwala,&nbsp;Obi Griffith,&nbsp;Malachi Griffith","doi":"10.1016/j.cancergen.2024.08.034","DOIUrl":"10.1016/j.cancergen.2024.08.034","url":null,"abstract":"<div><div>Splicing neoantigens represent a rich yet underexplored source of tumor-specific targets for immunotherapy. Tumors exhibit increased mis-splicing events compared to normal tissues, which in turn create diverse isoforms that encode novel peptides. These peptides, especially ones derived from frameshifts, are highly distinct from self-antigens, hence presenting an opportunity for enhanced immune recognition.</div><div>Though neoantigens arising from somatic single-point mutations in coding regions have been widely targeted by cancer therapies, other neoantigen sources, including alternative splicing neoantigens haven't received the same amount of attention. Here, we develop pVACsplice, a tool that predicts and prioritizes cis-splicing associated neoantigen candidates. pVACsplice takes alternative transcripts as input, translates them into altered peptides, then constructs neoantigens of user-defined sizes. It then estimates binding affinities of neoepitopes with user-input MHC alleles, and prioritizes candidates based on various criteria (binding affinity, solubility, transcript quality, and more).</div><div>We then utilize pVACsplice to explore the splicing neoantigen landscape of a Small Cell Lung Cancer (SCLC) cohort. We find numerous neojunctions and neoantigen candidates associated with genes frequently mutated in this malignancy.</div></div>","PeriodicalId":49225,"journal":{"name":"Cancer Genetics","volume":"286 ","pages":"Page S10"},"PeriodicalIF":1.4,"publicationDate":"2024-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142323286","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"19. High resolution cytogenomic analysis reveals characterizing abnormalities in APL-like leukemia","authors":"Shivaprasad H. Sathyanarayana,&nbsp;Michelle A. Bickford,&nbsp;Narcisa A. Smuliac,&nbsp;Kyle A. Tonseth,&nbsp;Farzana Murad,&nbsp;Jing Bao,&nbsp;Heather B. Steinmetz,&nbsp;Matthew R. Sullivan,&nbsp;Prabhjot Kaur,&nbsp;Jeremiah X. Karrs,&nbsp;Wahab A. Khan","doi":"10.1016/j.cancergen.2024.08.021","DOIUrl":"10.1016/j.cancergen.2024.08.021","url":null,"abstract":"<div><div>We report comprehensive characterization of cytogenomic findings from a bone marrow sample with suspected acute promyelocytic leukemia (APL) based on morphology and immunophenotype. Fluorescence <em>in situ</em> hybridization (FISH) and chromosome banding analysis (CBA) were negative for canonical <em>PML::RARA</em> and variant <em>RARA</em> translocations. PCR was negative for increased <em>PML::RARA</em> transcripts. CBA analysis detected loss of 5q, 17p as well as double minutes (dmin). To further rule out other retinoic acid receptor (RAR) partners, such as <em>RARB, RARG</em>, and identify the dmin, we employed genome-wide structural variant analysis (gSVA) using optical genome mapping. Interestingly, gSVA unmasked the dmin to be of <em>MYC</em> origin with ∼44 copies; this abnormality has been reported in APL-like leukemia and explained the immunophenotype. gSVA also identified loss of <em>TP53</em>, loss of chromosomes 1, 2, 8, 9 (includes <em>CDKN2A</em>), 10, and 11 along with gains of chromosomes 3, 6, 7, and 15 as separate clonal events.</div><div>No additional RAR partner translocations were observed. gSVA also showed a complex translocation, adjacent to 3Mb euploid region of 17p, in a rearrangement with chromosome 5, fusing genes <em>DMGDH-AKAP10</em>. As part of the testing algorithm, heme exome-based panel analysis detected a Tier I deleterious variant in <em>TP53</em> (p.S241C). A 4-month follow up bone marrow again analyzed by gSVA, post induction therapy, showed a reduction in <em>MYC</em> amplification (∼4 copies). This work helped explain the APL-like phenotype for this rare leukemia in an initially emergent situation, provided a marker for follow-up testing, and merits integrated genomic analysis of similar cases.</div></div>","PeriodicalId":49225,"journal":{"name":"Cancer Genetics","volume":"286 ","pages":"Pages S6-S7"},"PeriodicalIF":1.4,"publicationDate":"2024-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142323384","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"22. Advancing personalized prostate cancer care: Utilizing miRNA profiling and machine learning for metastasis prediction","authors":"Arun Seth ,&nbsp;Gobi Thillainadesan ,&nbsp;Yutaka Amemiya ,&nbsp;Robert Nam","doi":"10.1016/j.cancergen.2024.08.024","DOIUrl":"10.1016/j.cancergen.2024.08.024","url":null,"abstract":"<div><div>In the pursuit of advancing personalized medicine for prostate cancer treatment, the identification of critical biomarkers is crucial for tailoring therapies and improving patient outcomes. Building upon our prior research, where we conducted high-throughput small RNA sequencing on 38 post-operative prostate cancer patients matched by Gleason scores, this study aims to refine our understanding and enhance the accuracy of microRNA-based predictions through sophisticated computational biology techniques.</div><div>Through meticulous computational approaches and rigorous statistical analysis, we have identified microRNAs exhibiting significant expression differences between metastatic and non-metastatic cases post-surgery. This has led to the identification of six high-confidence microRNAs: <em>miR-6761, miR-93-5p, miR-92a-3p, miR-149-5p, miR-429</em>, and <em>miR-671-5p</em>, marking a significant advancement in post-operative care.</div><div>Expanding our dataset with an additional 100 supporting microRNAs, we are pioneering the training of a neural network machine learning algorithm. This innovative approach aims to accurately predict the risk of metastasis after surgery, providing a ground-breaking tool for personalized patient monitoring and treatment decision-making.</div><div>By integrating these biomarkers into a neural network model, we anticipate establishing a new standard in post-operative care for prostate cancer patients, ultimately guiding more effective monitoring strategies and improving quality of life. This study not only emphasizes the importance of microRNA profiling in prostate cancer prognosis clinical scenario but also showcases the potential of machine learning in revolutionizing cancer care.</div></div>","PeriodicalId":49225,"journal":{"name":"Cancer Genetics","volume":"286 ","pages":"Pages S7-S8"},"PeriodicalIF":1.4,"publicationDate":"2024-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142323386","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}