1
|
Hakami MA. Harnessing machine learning potential for personalised drug design and overcoming drug resistance. J Drug Target 2024; 32:918-930. [PMID: 38842417 DOI: 10.1080/1061186x.2024.2365934] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/09/2024] [Revised: 06/01/2024] [Accepted: 06/04/2024] [Indexed: 06/07/2024]
Abstract
Drug resistance in cancer treatment presents a significant challenge, necessitating innovative approaches to improve therapeutic efficacy. Integrating machine learning (ML) in cancer research is promising as ML algorithms outrival in analysing complex datasets, identifying patterns, and predicting treatment outcomes. Leveraging diverse data sources such as genomic profiles, clinical records, and drug response assays, ML uncovers molecular mechanisms of drug resistance, enabling personalised treatment, maximising efficacy and minimising adverse effects. Various ML algorithms contribute to the drug discovery process - Random Forest and Decision Trees predict drug-target interactions and aid in virtual screening, and SVM classify leads on bioactivity data. Neural Networks model QSAR to optimise lead compounds and K-means clustering group compounds with similar chemical properties aiding compound selection. Gaussian Processes predict drug responses, Bayesian Networks infer causal relationships, Autoencoders generate novel compounds, and Genetic Algorithms optimise molecular structures. These algorithms collectively enhance efficiency and success rates in drug design endeavours, from lead identification to optimisation and are cost-effective, empowering clinicians with real-time treatment monitoring and improving patient outcomes. This review highlights the immense potential of ML in revolutionising cancer care through effective drug design to reduce drug resistance, and we have also discussed various limitations and research gaps to understand better.
Collapse
Affiliation(s)
- Mohammed Ageeli Hakami
- Department of Clinical Laboratory Sciences, College of Applied Medical Sciences, Shaqra University, Al-Quwayiyah, Riyadh, Saudi Arabia
| |
Collapse
|
2
|
Theparee T, Akroush M, Sabatini LM, Wang V, Mangold KA, Joseph N, Stocker SJ, Freedman A, Helseth DL, Talamonti MS, Kaul KL. Cell free DNA in patients with pancreatic adenocarcinoma: clinicopathologic correlations. Sci Rep 2024; 14:15744. [PMID: 38977725 PMCID: PMC11231234 DOI: 10.1038/s41598-024-65562-8] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/13/2023] [Accepted: 06/20/2024] [Indexed: 07/10/2024] Open
Abstract
Detection of circulating tumor DNA (ctDNA) from plasma cell free DNA (cfDNA) has shown promise for diagnosis, therapeutic targeting, and prognosis. This study explores ctDNA detection by next generation sequencing (NGS) and associated clinicopathologic factors in patients with pancreatic adenocarcinoma (PDAC). Patients undergoing surgical exploration or resection of pancreatic lesions were enrolled with informed consent. Plasma samples (4-6 ml) were collected prior to surgery and cfDNA was recovered from 95 plasma samples. Adequate cfDNA for NGS (20 ng) was obtained from 81 patients. NGS was performed using the Oncomine Lung cfDNA assay on the Ion Torrent S5 sequencing platform. Twenty-five patients (30.9%) had detectable mutations in KRAS and/or TP53 with allele frequencies ranging from 0.05 to 8.5%, while mutations in other genes were detected less frequently and always along with KRAS or TP53. Detectable ctDNA mutations were more frequent in patients with poorly differentiated tumors, and patients without detectable ctDNA mutations showed longer survival (medians of 10.5 months vs. 18 months, p = 0.019). The detection of circulating tumor DNA in pancreatic adenocarcinomas is correlated with worse survival outcomes.
Collapse
Affiliation(s)
- Talent Theparee
- Department of Pathology and Laboratory Medicine, NorthShore University Health System, Evanston, IL, USA
- Department of Pathology, Chulalongkorn University Faculty of Medicine, Bangkok, Thailand
| | - Michael Akroush
- Department of Pathology and Laboratory Medicine, NorthShore University Health System, Evanston, IL, USA
| | - Linda M Sabatini
- Department of Pathology and Laboratory Medicine, NorthShore University Health System, Evanston, IL, USA
| | - Vivien Wang
- Department of Pathology and Laboratory Medicine, NorthShore University Health System, Evanston, IL, USA
| | - Kathy A Mangold
- Department of Pathology and Laboratory Medicine, NorthShore University Health System, Evanston, IL, USA
| | - Nora Joseph
- Department of Pathology, University of Michigan School of Medicine, Ann Arbor, MI, USA
| | - Susan Jane Stocker
- Department of Surgery, NorthShore University Health System, Evanston, IL, USA
| | - Alexa Freedman
- Northwestern University School of Medicine, Chicago, IL, USA
| | - Donald L Helseth
- Department of Pathology and Laboratory Medicine, NorthShore University Health System, Evanston, IL, USA
| | - Mark S Talamonti
- Department of Surgery, NorthShore University Health System, Evanston, IL, USA
| | - Karen L Kaul
- Department of Pathology and Laboratory Medicine, NorthShore University Health System, Evanston, IL, USA.
| |
Collapse
|
3
|
Huang L, Lv Y, Guan S, Yan H, Han L, Wang Z, Han Q, Dai G, Shi Y. High somatic mutations in circulating tumor DNA predict response of metastatic pancreatic ductal adenocarcinoma to first-line nab-paclitaxel plus S-1: prospective study. J Transl Med 2024; 22:184. [PMID: 38378604 PMCID: PMC10877900 DOI: 10.1186/s12967-024-04989-z] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/26/2023] [Accepted: 02/12/2024] [Indexed: 02/22/2024] Open
Abstract
AIMS We previously showed that the nab-paclitaxel plus S-1 (NPS) regimen had promising effects against metastatic pancreatic ducal adenocarcinoma (mPDAC), whose efficacy however could not be precisely predicted by routine biomarkers. This prospective study aimed to investigate the values of mutations in circulating tumor DNA (ctDNA) and their dynamic changes in predicting response of mPDAC to NPS chemotherapy. METHODS Paired tumor tissue and blood samples were prospectively collected from patients with mPDAC receiving first-line NPS chemotherapy, and underwent next-generation sequencing with genomic profiling of 425 genes for ctDNA. High mutation allelic frequency (MAF) was defined as ≥ 30% and ≥ 5% in tumor tissue and blood, respectively. Kappa statistics were used to assess agreement between mutant genes in tumor and ctDNA. Associations of mutations in ctDNA and their dynamic changes with tumor response, overall survival (OS), and progression-free survival (PFS) were assessed using the Kaplan-Meier method, multivariable-adjusted Cox proportional hazards regression, and longitudinal data analysis. RESULTS 147 blood samples and 43 paired tumor specimens from 43 patients with mPDAC were sequenced. The most common driver genes with high MAF were KRAS (tumor, 35%; ctDNA, 37%) and TP53 (tumor, 37%; ctDNA, 33%). Mutation rates of KRAS and TP53 in ctDNA were significantly higher in patients with liver metastasis, with baseline CA19-9 ≥ 2000 U/mL, and/or without an early CA19-9 response. κ values for the 5 most commonly mutated genes between tumor and ctDNA ranged from 0.48 to 0.76. MAFs of the genes mostly decreased sequentially during subsequent measurements, which significantly correlated with objective response, with an increase indicating cancer progression. High mutations of KRAS and ARID1A in both tumor and ctDNA, and of TP53, CDKN2A, and SMAD4 in ctDNA but not in tumor were significantly associated with shorter survival. When predicting 6-month OS, AUCs for the 5 most commonly mutated genes in ctDNA ranged from 0.59 to 0.84, larger than for genes in tumor (0.56 to 0.71) and for clinicopathologic characteristics (0.51 to 0.68). Repeated measurements of mutations in ctDNA significantly differentiated survival and tumor response. Among the 31 patients with ≥ 2 ctDNA tests, longitudinal analysis of changes in gene MAF showed that ctDNA progression was 60 and 58 days ahead of radiologic and CA19-9 progression for 48% and 42% of the patients, respectively. CONCLUSIONS High mutations of multiple driving genes in ctDNA and their dynamic changes could effectively predict response of mPDAC to NPS chemotherapy, with promising reliable predictive performance superior to routine clinicopathologic parameters. Inspiringly, longitudinal ctDNA tracking could predict disease progression about 2 months ahead of radiologic or CA19-9 evaluations, with the potential to precisely devise individualized therapeutic strategies for mPDAC.
Collapse
Affiliation(s)
- Lei Huang
- Medical Center on Aging of Ruijin Hospital, MCARJH, Shanghai Jiaotong University School of Medicine, 197 Ruijin Er Road, Shanghai, 200025, China.
- Department of Oncology, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, 200025, China.
| | - Yao Lv
- Department of Medical Oncology, Chinese PLA General Hospital, 28 Fuxing Road, Beijing, 100853, China
| | - Shasha Guan
- Department of Medical Oncology, Chinese PLA General Hospital, 28 Fuxing Road, Beijing, 100853, China
| | - Huan Yan
- Department of Medical Oncology, Chinese PLA General Hospital, 28 Fuxing Road, Beijing, 100853, China
| | - Lu Han
- Department of Medical Oncology, Chinese PLA General Hospital, 28 Fuxing Road, Beijing, 100853, China
| | - Zhikuan Wang
- Department of Medical Oncology, Chinese PLA General Hospital, 28 Fuxing Road, Beijing, 100853, China.
| | - Quanli Han
- Department of Medical Oncology, Chinese PLA General Hospital, 28 Fuxing Road, Beijing, 100853, China.
| | - Guanghai Dai
- Department of Medical Oncology, Chinese PLA General Hospital, 28 Fuxing Road, Beijing, 100853, China.
| | - Yan Shi
- Department of General Surgery, Shanghai Seventh People's Hospital, Shanghai University of Traditional Chinese Medicine, 358 Datong Road, Gaoqiao Town, Shanghai, 200137, China.
| |
Collapse
|
4
|
Salu P, Reindl KM. Advancements in Preclinical Models of Pancreatic Cancer. Pancreas 2024; 53:e205-e220. [PMID: 38206758 PMCID: PMC10842038 DOI: 10.1097/mpa.0000000000002277] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 01/13/2024]
Abstract
ABSTRACT Pancreatic cancer remains one of the deadliest of all cancer types with a 5-year overall survival rate of just 12%. Preclinical models available for understanding the disease pathophysiology have evolved significantly in recent years. Traditionally, commercially available 2-dimensional cell lines were developed to investigate mechanisms underlying tumorigenesis, metastasis, and drug resistance. However, these cells grow as monolayer cultures that lack heterogeneity and do not effectively represent tumor biology. Developing patient-derived xenografts and genetically engineered mouse models led to increased cellular heterogeneity, molecular diversity, and tissues that histologically represent the original patient tumors. However, these models are relatively expensive and very timing consuming. More recently, the advancement of fast and inexpensive in vitro models that better mimic disease conditions in vivo are on the rise. Three-dimensional cultures like organoids and spheroids have gained popularity and are considered to recapitulate complex disease characteristics. In addition, computational genomics, transcriptomics, and metabolomic models are being developed to simulate pancreatic cancer progression and predict better treatment strategies. Herein, we review the challenges associated with pancreatic cancer research and available analytical models. We suggest that an integrated approach toward using these models may allow for developing new strategies for pancreatic cancer precision medicine.
Collapse
Affiliation(s)
- Philip Salu
- From the Department of Biological Sciences, North Dakota State University, Fargo, ND
| | | |
Collapse
|
5
|
Dayimu A, Di Lisio L, Anand S, Roca-Carreras I, Qian W, Al-Mohammad A, Basu B, Valle JW, Jodrell D, Demiris N, Corrie P. Clinical and biological markers predictive of treatment response associated with metastatic pancreatic adenocarcinoma. Br J Cancer 2023; 128:1672-1680. [PMID: 36813867 PMCID: PMC10133256 DOI: 10.1038/s41416-023-02170-9] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/14/2022] [Revised: 01/05/2023] [Accepted: 01/17/2023] [Indexed: 02/24/2023] Open
Abstract
BACKGROUND Chemotherapy for metastatic pancreatic adenocarcinoma (PDAC) offers limited benefits, but survival outcomes vary. Reliable predictive response biomarkers to guide patient management are lacking. METHODS Patient performance status, tumour burden (determined by the presence or absence of liver metastases), plasma protein biomarkers (CA19-9, albumin, C-reactive protein and neutrophils) and circulating tumour DNA (ctDNA) were assessed in 146 patients with metastatic PDAC prior to starting either concomitant or sequential nab-paclitaxel + gemcitabine chemotherapy in the SIEGE randomised prospective clinical trial, as well as during the first 8 weeks of treatment. Correlations were made with objective response, death within 1 year and overall survival (OS). RESULTS Initial poor patient performance status, presence of liver metastases and detectable mutKRAS ctDNA all correlated with worse OS after adjusting for the different biomarkers of interest. Objective response at 8 weeks also correlated with OS (P = 0.026). Plasma biomarkers measured during treatment and prior to the first response assessment identified ≥10% decrease in albumin at 4 weeks predicted for worse OS (HR 4.75, 95% CI 1.43-16.94, P = 0.012), while any association of longitudinal evaluation of mutKRAS ctDNA with OS was unclear (β = 0.024, P = 0.057). CONCLUSIONS Readily measurable patient variables can aid the prediction of outcomes from combination chemotherapy used to treat metastatic PDAC. The role of mutKRAS ctDNA as a tool to guide treatment warrants further exploration. CLINICAL TRIAL REGISTRATION ISRCTN71070888; ClinialTrials.gov (NCT03529175).
Collapse
Affiliation(s)
- Alimu Dayimu
- Clinical Trials Unit, Department of Oncology, University of Cambridge, Cambridge, UK
| | - Lorena Di Lisio
- Cancer Molecular Diagnostics Laboratory, Department of Oncology, University of Cambridge, Cambridge, UK
| | - Shubha Anand
- Cancer Molecular Diagnostics Laboratory, Department of Oncology, University of Cambridge, Cambridge, UK
| | - Isart Roca-Carreras
- Cancer Molecular Diagnostics Laboratory, Department of Oncology, University of Cambridge, Cambridge, UK
| | - Wendi Qian
- Cambridge Clinical Trials Unit, Cambridge University Hospitals NHS Foundation Trust, Cambridge, UK
| | | | - Bristi Basu
- Department of Oncology, University of Cambridge, Cambridge, UK
| | - Juan W Valle
- University of Manchester and The Christie NHS Foundation Trust, Manchester, UK
| | - Duncan Jodrell
- Department of Oncology, University of Cambridge, Cambridge, UK
| | - Nikos Demiris
- Cambridge Clinical Trials Unit, Cambridge University Hospitals NHS Foundation Trust, Cambridge, UK
- Department of Statistics, Athens University of Economics and Business, Athens, Greece
| | - Pippa Corrie
- Oncology Department, Cambridge University Hospitals NHS Foundation Trust, Cambridge, UK.
| |
Collapse
|
6
|
Clinical Features and Prognostic Impact of Pancreatic Ductal Adenocarcinoma without Dilatation of the Main Pancreatic Duct: A Single-Center Retrospective Analysis. Diagnostics (Basel) 2023; 13:diagnostics13050963. [PMID: 36900107 PMCID: PMC10000697 DOI: 10.3390/diagnostics13050963] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/30/2023] [Revised: 02/25/2023] [Accepted: 03/01/2023] [Indexed: 03/06/2023] Open
Abstract
The presence of main pancreatic duct (MPD) dilatation is important for diagnosing pancreatic ductal adenocarcinomas (PDACs). However, we occasionally encounter PDAC cases without MPD dilatation. The objectives of this study were to compare the clinical findings and prognosis of pathologically diagnosed PDAC cases with and without MPD dilatation and to extract factors related to the prognosis of PDAC. The 281 patients pathologically diagnosed with PDAC were divided into two groups: the dilatation group (n = 215), consisting of patients with MPD dilatation of 3 mm or more, and the non-dilatation group (n = 66), consisting of patients with MPD dilatation less than 3 mm. We found that the non-dilatation group had more cancers in the pancreatic tail, more advanced disease stage, lower resectability, and worse prognoses than the dilatation group. Clinical stage and history of surgery or chemotherapy were identified as significant prognostic factors for PDAC, while tumor location was not. Endoscopic ultrasonography (EUS), diffusion-weighted magnetic resonance imaging (DW-MRI), and contrast-enhanced computed tomography had a high tumor detection rate for PDAC even in the non-dilatation group. Construction of a diagnostic system centered on EUS and DW-MRI is necessary for the early diagnosis of PDAC without MPD dilatation, which can improve its prognosis.
Collapse
|
7
|
Nakaoka K, Ohno E, Kawabe N, Kuzuya T, Funasaka K, Nakagawa Y, Nagasaka M, Ishikawa T, Watanabe A, Tochio T, Miyahara R, Shibata T, Kawashima H, Hashimoto S, Hirooka Y. Current Status of the Diagnosis of Early-Stage Pancreatic Ductal Adenocarcinoma. Diagnostics (Basel) 2023; 13:diagnostics13020215. [PMID: 36673023 PMCID: PMC9857526 DOI: 10.3390/diagnostics13020215] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/04/2022] [Revised: 12/15/2022] [Accepted: 01/04/2023] [Indexed: 01/09/2023] Open
Abstract
Pancreatic ductal adenocarcinoma (PDAC) can be treated with surgery, chemotherapy, and radiotherapy. Despite medical progress in each field in recent years, it is still insufficient for managing PDAC, and at present, the only curative treatment is surgery. A typical pancreatic cancer is relatively easy to diagnose with imaging. However, it is often not recommended for surgical treatment at the time of diagnosis due to metastatic spread beyond the pancreas. Even if it is operable, it often recurs during postoperative follow-up. In the case of PDAC with a diameter of 10 mm or less, the 5-year survival rate is as good as 80% or more, and the best index for curative treatment is tumor size. The early detection of pancreatic cancer with a diameter of less than 10 mm or carcinoma in situ is critical. Here, we provide an overview of the current status of diagnostic imaging features and genetic tests for the accurate diagnosis of early-stage PDAC.
Collapse
Affiliation(s)
- Kazunori Nakaoka
- Department of Gastroenterology and Hepatology, Fujita Health University, Toyoake 470-1192, Aichi, Japan
| | - Eizaburo Ohno
- Department of Gastroenterology and Hepatology, Fujita Health University, Toyoake 470-1192, Aichi, Japan
| | - Naoto Kawabe
- Department of Gastroenterology and Hepatology, Fujita Health University, Toyoake 470-1192, Aichi, Japan
| | - Teiji Kuzuya
- Department of Gastroenterology and Hepatology, Fujita Health University, Toyoake 470-1192, Aichi, Japan
| | - Kohei Funasaka
- Department of Gastroenterology and Hepatology, Fujita Health University, Toyoake 470-1192, Aichi, Japan
| | - Yoshihito Nakagawa
- Department of Gastroenterology and Hepatology, Fujita Health University, Toyoake 470-1192, Aichi, Japan
| | - Mitsuo Nagasaka
- Department of Gastroenterology and Hepatology, Fujita Health University, Toyoake 470-1192, Aichi, Japan
| | - Takuya Ishikawa
- Department of Gastroenterology and Hepatology, Nagoya University Graduate School of Medicine, Nagoya 464-0813, Aichi, Japan
| | - Ayako Watanabe
- Department of Gastroenterology and Hepatology, Fujita Health University, Toyoake 470-1192, Aichi, Japan
| | - Takumi Tochio
- Department of Medical Research on Prebiotics and Probiotics, Fujita Health University, Toyoake 470-1101, Aichi, Japan
| | - Ryoji Miyahara
- Department of Gastroenterology and Hepatology, Fujita Health University, Toyoake 470-1192, Aichi, Japan
| | - Tomoyuki Shibata
- Department of Gastroenterology and Hepatology, Fujita Health University, Toyoake 470-1192, Aichi, Japan
| | - Hiroki Kawashima
- Department of Gastroenterology and Hepatology, Nagoya University Graduate School of Medicine, Nagoya 464-0813, Aichi, Japan
| | - Senju Hashimoto
- Department of Gastroenterology and Hepatology, Fujita Health University, Toyoake 470-1192, Aichi, Japan
| | - Yoshiki Hirooka
- Department of Gastroenterology and Hepatology, Fujita Health University, Toyoake 470-1192, Aichi, Japan
- Correspondence: ; Tel.: +81-562-93-2324; Fax: +81-562-93-8601
| |
Collapse
|