1
|
Hwang J, Lee Y, Yoo SK, Kim JI. Image-based deep learning model using DNA methylation data predicts the origin of cancer of unknown primary. Neoplasia 2024; 55:101021. [PMID: 38943996 PMCID: PMC11261876 DOI: 10.1016/j.neo.2024.101021] [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: 04/30/2024] [Accepted: 06/24/2024] [Indexed: 07/01/2024]
Abstract
Cancer of unknown primary (CUP) is a rare type of metastatic cancer in which the origin of the tumor is unknown. Since the treatment strategy for patients with metastatic tumors depends on knowing the primary site, accurate identification of the origin site is important. Here, we developed an image-based deep-learning model that utilizes a vision transformer algorithm for predicting the origin of CUP. Using DNA methylation dataset of 8,233 primary tumors from The Cancer Genome Atlas (TCGA), we categorized 29 cancer types into 18 organ classes and extracted 2,312 differentially methylated CpG sites (DMCs) from non-squamous cancer group and 420 DMCs from squamous cell cancer group. Using these DMCs, we created organ-specific DNA methylation images and used them for model training and testing. Model performance was evaluated using 394 metastatic cancer samples from TCGA (TCGA-meta) and 995 samples (693 primary and 302 metastatic cancers) obtained from 20 independent external studies. We identified that the DNA methylation image reveals a distinct pattern based on the origin of cancer. Our model achieved an overall accuracy of 96.95 % in the TCGA-meta dataset. In the external validation datasets, our classifier achieved overall accuracies of 96.39 % and 94.37 % in primary and metastatic tumors, respectively. Especially, the overall accuracies for both primary and metastatic samples of non-squamous cell cancer were exceptionally high, with 96.79 % and 96.85 %, respectively.
Collapse
Affiliation(s)
- Jinha Hwang
- Department of Laboratory Medicine, Korea University Anam Hospital, Seoul, the Republic of Korea
| | - Yeajina Lee
- Department of Biomedical Sciences, Seoul National University Graduate School, Seoul, the Republic of Korea; Genomic Medicine Institute, Medical Research Center, Seoul National University, Seoul, the Republic of Korea
| | - Seong-Keun Yoo
- Precision Immunology Institute, Icahn School of Medicine at Mount Sinai, New York, NY 10029, USA; Department of Oncological Sciences, Tisch Cancer Institute, Icahn School of Medicine at Mount Sinai, New York, NY 10029, USA; Department of Artificial Intelligence and Human Health, Icahn School of Medicine at Mount Sinai, New York, NY 10029, USA; Icahn Genomics Institute, Icahn School of Medicine at Mount Sinai, New York, NY 10029, USA.
| | - Jong-Il Kim
- Department of Biomedical Sciences, Seoul National University Graduate School, Seoul, the Republic of Korea; Genomic Medicine Institute, Medical Research Center, Seoul National University, Seoul, the Republic of Korea.
| |
Collapse
|
2
|
Moulaei K, Afrash MR, Parvin M, Shadnia S, Rahimi M, Mostafazadeh B, Evini PET, Sabet B, Vahabi SM, Soheili A, Fathy M, Kazemi A, Khani S, Mortazavi SM, Hosseini SM. Explainable artificial intelligence (XAI) for predicting the need for intubation in methanol-poisoned patients: a study comparing deep and machine learning models. Sci Rep 2024; 14:15751. [PMID: 38977750 PMCID: PMC11231277 DOI: 10.1038/s41598-024-66481-4] [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: 05/07/2024] [Accepted: 07/01/2024] [Indexed: 07/10/2024] Open
Abstract
The need for intubation in methanol-poisoned patients, if not predicted in time, can lead to irreparable complications and even death. Artificial intelligence (AI) techniques like machine learning (ML) and deep learning (DL) greatly aid in accurately predicting intubation needs for methanol-poisoned patients. So, our study aims to assess Explainable Artificial Intelligence (XAI) for predicting intubation necessity in methanol-poisoned patients, comparing deep learning and machine learning models. This study analyzed a dataset of 897 patient records from Loghman Hakim Hospital in Tehran, Iran, encompassing cases of methanol poisoning, including those requiring intubation (202 cases) and those not requiring it (695 cases). Eight established ML (SVM, XGB, DT, RF) and DL (DNN, FNN, LSTM, CNN) models were used. Techniques such as tenfold cross-validation and hyperparameter tuning were applied to prevent overfitting. The study also focused on interpretability through SHAP and LIME methods. Model performance was evaluated based on accuracy, specificity, sensitivity, F1-score, and ROC curve metrics. Among DL models, LSTM showed superior performance in accuracy (94.0%), sensitivity (99.0%), specificity (94.0%), and F1-score (97.0%). CNN led in ROC with 78.0%. For ML models, RF excelled in accuracy (97.0%) and specificity (100%), followed by XGB with sensitivity (99.37%), F1-score (98.27%), and ROC (96.08%). Overall, RF and XGB outperformed other models, with accuracy (97.0%) and specificity (100%) for RF, and sensitivity (99.37%), F1-score (98.27%), and ROC (96.08%) for XGB. ML models surpassed DL models across all metrics, with accuracies from 93.0% to 97.0% for DL and 93.0% to 99.0% for ML. Sensitivities ranged from 98.0% to 99.37% for DL and 93.0% to 99.0% for ML. DL models achieved specificities from 78.0% to 94.0%, while ML models ranged from 93.0% to 100%. F1-scores for DL were between 93.0% and 97.0%, and for ML between 96.0% and 98.27%. DL models scored ROC between 68.0% and 78.0%, while ML models ranged from 84.0% to 96.08%. Key features for predicting intubation necessity include GCS at admission, ICU admission, age, longer folic acid therapy duration, elevated BUN and AST levels, VBG_HCO3 at initial record, and hemodialysis presence. This study as the showcases XAI's effectiveness in predicting intubation necessity in methanol-poisoned patients. ML models, particularly RF and XGB, outperform DL counterparts, underscoring their potential for clinical decision-making.
Collapse
Affiliation(s)
- Khadijeh Moulaei
- Department of Health Information Technology, School of Paramedical, Ilam University of Medical Sciences, Ilam, Iran
| | - Mohammad Reza Afrash
- Deparment of Artificial Intelligence, Smart University of Medical Sciences, Tehran, Iran
| | - Mohammad Parvin
- Department of Industrial and Systems Engineering, Auburn University, Auburn, AL, USA
| | - Shahin Shadnia
- Toxicological Research Center, Excellence Center of Clinical Toxicology, Department of Clinical Toxicology, Loghman Hakim Hospital, Shahid Beheshti University of Medical Sciences, Tehran, Iran
| | - Mitra Rahimi
- Toxicological Research Center, Excellence Center of Clinical Toxicology, Department of Clinical Toxicology, Loghman Hakim Hospital, Shahid Beheshti University of Medical Sciences, Tehran, Iran
| | - Babak Mostafazadeh
- Toxicological Research Center, Excellence Center of Clinical Toxicology, Department of Clinical Toxicology, Loghman Hakim Hospital, Shahid Beheshti University of Medical Sciences, Tehran, Iran
| | - Peyman Erfan Talab Evini
- Toxicological Research Center, Excellence Center of Clinical Toxicology, Department of Clinical Toxicology, Loghman Hakim Hospital, Shahid Beheshti University of Medical Sciences, Tehran, Iran
| | - Babak Sabet
- Deparment of Artificial Intelligence, Smart University of Medical Sciences, Tehran, Iran
- Department of Surgery, Faculty of Medicine, Shahid Beheshti University of Medical Sciences, Tehran, Iran
| | | | - Amirali Soheili
- Rajaie Cardiovascular Medical and Research Center, Iran University of Medical Sciences, Tehran, Iran
| | - Mobin Fathy
- School of Medicine, Tehran University of Medical Sciences, Tehran, Iran
- Students Research Committee, School of Medicine, Shahid Beheshti University of Medical Sciences, Tehran, Iran
| | - Arya Kazemi
- Students Research Committee, School of Medicine, Shahid Beheshti University of Medical Sciences, Tehran, Iran
| | - Sina Khani
- Students Research Committee, School of Medicine, Shahid Beheshti University of Medical Sciences, Tehran, Iran
| | - Seyed Mohammad Mortazavi
- Students Research Committee, School of Medicine, Shahid Beheshti University of Medical Sciences, Tehran, Iran
| | - Sayed Masoud Hosseini
- Toxicological Research Center, Excellence Center of Clinical Toxicology, Department of Clinical Toxicology, Loghman Hakim Hospital, Shahid Beheshti University of Medical Sciences, Tehran, Iran.
| |
Collapse
|
3
|
El-Melegy M, Mamdouh A, Ali S, Badawy M, El-Ghar MA, Alghamdi NS, El-Baz A. Prostate Cancer Diagnosis via Visual Representation of Tabular Data and Deep Transfer Learning. Bioengineering (Basel) 2024; 11:635. [PMID: 39061717 PMCID: PMC11274351 DOI: 10.3390/bioengineering11070635] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/04/2024] [Revised: 06/10/2024] [Accepted: 06/17/2024] [Indexed: 07/28/2024] Open
Abstract
Prostate cancer (PC) is a prevalent and potentially fatal form of cancer that affects men globally. However, the existing diagnostic methods, such as biopsies or digital rectal examination (DRE), have limitations in terms of invasiveness, cost, and accuracy. This study proposes a novel machine learning approach for the diagnosis of PC by leveraging clinical biomarkers and personalized questionnaires. In our research, we explore various machine learning methods, including traditional, tree-based, and advanced tabular deep learning methods, to analyze tabular data related to PC. Additionally, we introduce the novel utilization of convolutional neural networks (CNNs) and transfer learning, which have been predominantly applied in image-related tasks, for handling tabular data after being transformed to proper graphical representations via our proposed Tab2Visual modeling framework. Furthermore, we investigate leveraging the prediction accuracy further by constructing ensemble models. An experimental evaluation of our proposed approach demonstrates its effectiveness in achieving superior performance attaining an F1-score of 0.907 and an AUC of 0.911. This offers promising potential for the accurate detection of PC without the reliance on invasive and high-cost procedures.
Collapse
Affiliation(s)
- Moumen El-Melegy
- Electrical Engineering Department, Assiut University, Assiut 71516, Egypt; (M.E.-M.); (A.M.); (S.A.)
| | - Ahmed Mamdouh
- Electrical Engineering Department, Assiut University, Assiut 71516, Egypt; (M.E.-M.); (A.M.); (S.A.)
| | - Samia Ali
- Electrical Engineering Department, Assiut University, Assiut 71516, Egypt; (M.E.-M.); (A.M.); (S.A.)
| | - Mohamed Badawy
- Radiology Department, Urology and Nephrology Center, Mansoura University, Mansoura 35516, Egypt; (M.B.); (M.A.E.-G.)
| | - Mohamed Abou El-Ghar
- Radiology Department, Urology and Nephrology Center, Mansoura University, Mansoura 35516, Egypt; (M.B.); (M.A.E.-G.)
| | - Norah Saleh Alghamdi
- Department of Computer Sciences, College of Computer and Information Sciences, Princess Nourah Bint Abdulrahman University, P.O. Box 84428, Riyadh 11671, Saudi Arabia;
| | - Ayman El-Baz
- Bioengineering Department, University of Louisville, Louisville, KY 40292, USA
| |
Collapse
|
4
|
Sharma A, López Y, Jia S, Lysenko A, Boroevich KA, Tsunoda T. Enhanced analysis of tabular data through Multi-representation DeepInsight. Sci Rep 2024; 14:12851. [PMID: 38834670 DOI: 10.1038/s41598-024-63630-7] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/06/2023] [Accepted: 05/30/2024] [Indexed: 06/06/2024] Open
Abstract
Tabular data analysis is a critical task in various domains, enabling us to uncover valuable insights from structured datasets. While traditional machine learning methods can be used for feature engineering and dimensionality reduction, they often struggle to capture the intricate relationships and dependencies within real-world datasets. In this paper, we present Multi-representation DeepInsight (MRep-DeepInsight), a novel extension of the DeepInsight method designed to enhance the analysis of tabular data. By generating multiple representations of samples using diverse feature extraction techniques, our approach is able to capture a broader range of features and reveal deeper insights. We demonstrate the effectiveness of MRep-DeepInsight on single-cell datasets, Alzheimer's data, and artificial data, showcasing an improved accuracy over the original DeepInsight approach and machine learning methods like random forest, XGBoost, LightGBM, FT-Transformer and L2-regularized logistic regression. Our results highlight the value of incorporating multiple representations for robust and accurate tabular data analysis. By leveraging the power of diverse representations, MRep-DeepInsight offers a promising new avenue for advancing decision-making and scientific discovery across a wide range of fields.
Collapse
Affiliation(s)
- Alok Sharma
- Laboratory for Medical Science Mathematics, RIKEN Center for Integrative Medical Sciences, Yokohama, Japan.
- Institute for Integrated and Intelligent Systems, Griffith University, Brisbane, Australia.
- Laboratory for Medical Science Mathematics, Department of Biological Sciences, School of Science, The University of Tokyo, Tokyo, Japan.
| | | | - Shangru Jia
- Laboratory for Medical Science Mathematics, Department of Computational Biology and Medical Sciences, Graduate School of Frontier Sciences, The University of Tokyo, Tokyo, Japan
| | - Artem Lysenko
- Laboratory for Medical Science Mathematics, RIKEN Center for Integrative Medical Sciences, Yokohama, Japan
- Laboratory for Medical Science Mathematics, Department of Biological Sciences, School of Science, The University of Tokyo, Tokyo, Japan
| | - Keith A Boroevich
- Laboratory for Medical Science Mathematics, RIKEN Center for Integrative Medical Sciences, Yokohama, Japan
| | - Tatsuhiko Tsunoda
- Laboratory for Medical Science Mathematics, RIKEN Center for Integrative Medical Sciences, Yokohama, Japan.
- Laboratory for Medical Science Mathematics, Department of Biological Sciences, School of Science, The University of Tokyo, Tokyo, Japan.
- Laboratory for Medical Science Mathematics, Department of Computational Biology and Medical Sciences, Graduate School of Frontier Sciences, The University of Tokyo, Tokyo, Japan.
| |
Collapse
|
5
|
Borisov V, Leemann T, Sebler K, Haug J, Pawelczyk M, Kasneci G. Deep Neural Networks and Tabular Data: A Survey. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2024; 35:7499-7519. [PMID: 37015381 DOI: 10.1109/tnnls.2022.3229161] [Citation(s) in RCA: 21] [Impact Index Per Article: 21.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/19/2023]
Abstract
Heterogeneous tabular data are the most commonly used form of data and are essential for numerous critical and computationally demanding applications. On homogeneous datasets, deep neural networks have repeatedly shown excellent performance and have therefore been widely adopted. However, their adaptation to tabular data for inference or data generation tasks remains highly challenging. To facilitate further progress in the field, this work provides an overview of state-of-the-art deep learning methods for tabular data. We categorize these methods into three groups: data transformations, specialized architectures, and regularization models. For each of these groups, our work offers a comprehensive overview of the main approaches. Moreover, we discuss deep learning approaches for generating tabular data and also provide an overview over strategies for explaining deep models on tabular data. Thus, our first contribution is to address the main research streams and existing methodologies in the mentioned areas while highlighting relevant challenges and open research questions. Our second contribution is to provide an empirical comparison of traditional machine learning methods with 11 deep learning approaches across five popular real-world tabular datasets of different sizes and with different learning objectives. Our results, which we have made publicly available as competitive benchmarks, indicate that algorithms based on gradient-boosted tree ensembles still mostly outperform deep learning models on supervised learning tasks, suggesting that the research progress on competitive deep learning models for tabular data is stagnating. To the best of our knowledge, this is the first in-depth overview of deep learning approaches for tabular data; as such, this work can serve as a valuable starting point to guide researchers and practitioners interested in deep learning with tabular data.
Collapse
|
6
|
Tang X, Prodduturi N, Thompson KJ, Weinshilboum RM, O'Sullivan CC, Boughey JC, Tizhoosh H, Klee EW, Wang L, Goetz MP, Suman V, Kalari KR. OmicsFootPrint: a framework to integrate and interpret multi-omics data using circular images and deep neural networks. BIORXIV : THE PREPRINT SERVER FOR BIOLOGY 2024:2024.03.21.586001. [PMID: 38585820 PMCID: PMC10996492 DOI: 10.1101/2024.03.21.586001] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 04/09/2024]
Abstract
The OmicsFootPrint framework addresses the need for advanced multi-omics data analysis methodologies by transforming data into intuitive two-dimensional circular images and facilitating the interpretation of complex diseases. Utilizing Deep Neural Networks and incorporating the SHapley Additive exPlanations (SHAP) algorithm, the framework enhances model interpretability. Tested with The Cancer Genome Atlas (TCGA) data, OmicsFootPrint effectively classified lung and breast cancer subtypes, achieving high Area Under Curve (AUC) scores - 0.98±0.02 for lung cancer subtype differentiation, 0.83±0.07 for breast cancer PAM50 subtypes, and successfully distinguishe between invasive lobular and ductal carcinomas in breast cancer, showcasing its robustness. It also demonstrated notable performance in predicting drug responses in cancer cell lines, with a median AUC of 0.74, surpassing existing algorithms. Furthermore, its effectiveness persists even with reduced training sample sizes. OmicsFootPrint marks an enhancement in multi-omics research, offering a novel, efficient, and interpretable approach that contributes to a deeper understanding of disease mechanisms.
Collapse
|
7
|
Sharma A, Lysenko A, Jia S, Boroevich KA, Tsunoda T. Advances in AI and machine learning for predictive medicine. J Hum Genet 2024:10.1038/s10038-024-01231-y. [PMID: 38424184 DOI: 10.1038/s10038-024-01231-y] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/31/2023] [Revised: 02/04/2024] [Accepted: 02/12/2024] [Indexed: 03/02/2024]
Abstract
The field of omics, driven by advances in high-throughput sequencing, faces a data explosion. This abundance of data offers unprecedented opportunities for predictive modeling in precision medicine, but also presents formidable challenges in data analysis and interpretation. Traditional machine learning (ML) techniques have been partly successful in generating predictive models for omics analysis but exhibit limitations in handling potential relationships within the data for more accurate prediction. This review explores a revolutionary shift in predictive modeling through the application of deep learning (DL), specifically convolutional neural networks (CNNs). Using transformation methods such as DeepInsight, omics data with independent variables in tabular (table-like, including vector) form can be turned into image-like representations, enabling CNNs to capture latent features effectively. This approach not only enhances predictive power but also leverages transfer learning, reducing computational time, and improving performance. However, integrating CNNs in predictive omics data analysis is not without challenges, including issues related to model interpretability, data heterogeneity, and data size. Addressing these challenges requires a multidisciplinary approach, involving collaborations between ML experts, bioinformatics researchers, biologists, and medical doctors. This review illuminates these complexities and charts a course for future research to unlock the full predictive potential of CNNs in omics data analysis and related fields.
Collapse
Affiliation(s)
- Alok Sharma
- Laboratory for Medical Science Mathematics, Department of Biological Sciences, School of Science, The University of Tokyo, Tokyo, Japan.
- Laboratory for Medical Science Mathematics, RIKEN Center for Integrative Medical Sciences, Yokohama, Japan.
- Institute for Integrated and Intelligent Systems, Griffith University, Queensland, Australia.
| | - Artem Lysenko
- Laboratory for Medical Science Mathematics, Department of Biological Sciences, School of Science, The University of Tokyo, Tokyo, Japan.
- Laboratory for Medical Science Mathematics, RIKEN Center for Integrative Medical Sciences, Yokohama, Japan.
| | - Shangru Jia
- Laboratory for Medical Science Mathematics, Department of Computational Biology and Medical Sciences, Graduate School of Frontier Sciences, The University of Tokyo, Tokyo, Japan
| | - Keith A Boroevich
- Laboratory for Medical Science Mathematics, RIKEN Center for Integrative Medical Sciences, Yokohama, Japan
| | - Tatsuhiko Tsunoda
- Laboratory for Medical Science Mathematics, Department of Biological Sciences, School of Science, The University of Tokyo, Tokyo, Japan.
- Laboratory for Medical Science Mathematics, RIKEN Center for Integrative Medical Sciences, Yokohama, Japan.
- Laboratory for Medical Science Mathematics, Department of Computational Biology and Medical Sciences, Graduate School of Frontier Sciences, The University of Tokyo, Tokyo, Japan.
| |
Collapse
|
8
|
Yin AA, Zhang X, He YL, Zhao JJ, Zhang X, Fei Z, Lin W, Song BQ. Machine learning prediction models for in-hospital postoperative functional outcome after moderate-to-severe traumatic brain injury. Eur J Trauma Emerg Surg 2024:10.1007/s00068-023-02434-2. [PMID: 38355915 DOI: 10.1007/s00068-023-02434-2] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/19/2023] [Accepted: 12/28/2023] [Indexed: 02/16/2024]
Abstract
AIM This study aims to utilize machine learning (ML) and logistic regression (LR) models to predict surgical outcomes among patients with traumatic brain injury (TBI) based on admission examination, assisting in making optimal surgical treatment decision for these patients. METHOD We conducted a retrospective review of patients hospitalized in our department for moderate-to-severe TBI. Patients admitted between October 2011 and October 2022 were assigned to the training set, while patients admitted between November 2022 and May 2023 were designated as the external validation set. Five ML algorithms and LR model were employed to predict the postoperative Glasgow Outcome Scale (GOS) status at discharge using clinical and routine blood data collected upon admission. The Shapley (SHAP) plot was utilized for interpreting the models. RESULTS A total of 416 patients were included in this study, and they were divided into the training set (n = 396) and the external validation set (n = 47). The ML models, using both clinical and routine blood data, were able to predict postoperative GOS outcomes with area under the curve (AUC) values ranging from 0.860 to 0.900 during the internal cross-validation and from 0.801 to 0.890 during the external validation. In contrast, the LR model had the lowest AUC values during the internal and external validation (0.844 and 0.567, respectively). When blood data was not available, the ML models achieved AUCs of 0.849 to 0.870 during the internal cross-validation and 0.714 to 0.861 during the external validation. Similarly, the LR model had the lowest AUC values (0.821 and 0.638, respectively). Through repeated cross-validation analysis, we found that routine blood data had a significant association with higher mean AUC values in all ML and LR models. The SHAP plot was used to visualize the contributions of all predictors and highlighted the significance of blood data in the lightGBM model. CONCLUSION The study concluded that ML models could provide rapid and accurate predictions for postoperative GOS outcomes at discharge following moderate-to-severe TBI. The study also highlighted the crucial role of routine blood tests in improving such predictions, and may contribute to the optimization of surgical treatment decision-making for patients with TBI.
Collapse
Affiliation(s)
- An-An Yin
- Department of Plastic and Reconstructive Surgery, Craniomaxillofacial Surgery Group, Xijing Hospital, Fourth Military Medical University, Changle West Road, No. 169, Xi'an, 710032, China
| | - Xi Zhang
- Department of Plastic and Reconstructive Surgery, Craniomaxillofacial Surgery Group, Xijing Hospital, Fourth Military Medical University, Changle West Road, No. 169, Xi'an, 710032, China
| | - Ya-Long He
- Department of Neurosurgery, Xijing Institute of Clinical Neuroscience, Xijing Hospital, Fourth Military Medical University, Changle West Road, No. 169, Xi'an, 710032, China
| | - Jun-Jie Zhao
- Department of Neurosurgery, Xijing Institute of Clinical Neuroscience, Xijing Hospital, Fourth Military Medical University, Changle West Road, No. 169, Xi'an, 710032, China
| | - Xiang Zhang
- Department of Neurosurgery, Xijing Institute of Clinical Neuroscience, Xijing Hospital, Fourth Military Medical University, Changle West Road, No. 169, Xi'an, 710032, China
| | - Zhou Fei
- Department of Neurosurgery, Xijing Institute of Clinical Neuroscience, Xijing Hospital, Fourth Military Medical University, Changle West Road, No. 169, Xi'an, 710032, China.
| | - Wei Lin
- Department of Neurosurgery, Xijing Institute of Clinical Neuroscience, Xijing Hospital, Fourth Military Medical University, Changle West Road, No. 169, Xi'an, 710032, China.
| | - Bao-Qiang Song
- Department of Plastic and Reconstructive Surgery, Craniomaxillofacial Surgery Group, Xijing Hospital, Fourth Military Medical University, Changle West Road, No. 169, Xi'an, 710032, China.
| |
Collapse
|
9
|
Sha Y, Meng W, Luo G, Zhai X, Tong HHY, Wang Y, Li K. MetDIT: Transforming and Analyzing Clinical Metabolomics Data with Convolutional Neural Networks. Anal Chem 2024. [PMID: 38324756 DOI: 10.1021/acs.analchem.3c04607] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 02/09/2024]
Abstract
Clinical metabolomics is growing as an essential tool for precision medicine. However, classical machine learning algorithms struggle to comprehensively encode and analyze the metabolomics data due to their high dimensionality and complex intercorrelations. This article introduces a new method called MetDIT, designed to analyze intricate metabolomics data effectively using deep convolutional neural networks (CNN). MetDIT comprises two components: TransOmics and NetOmics. Since CNN models have difficulty in processing one-dimensional (1D) sequence data efficiently, we developed TransOmics, a framework that transforms sequence data into two-dimensional (2D) images while maintaining a one-to-one correspondence between the sequences and images. NetOmics, the second component, leverages a CNN architecture to extract more discriminative representations from the transformed samples. To overcome the overfitting due to the small sample size and class imbalance, we introduced a feature augmentation module (FAM) and a loss function to improve the model performance. Furthermore, we systematically optimized the model backbone and image resolution to balance the model parameters and computational costs. To demonstrate the performance of the proposed MetDIT, we conducted extensive experiments using three different clinical metabolomics data sets and achieved better classification performance than classical machine learning methods used in metabolomics, including Random Forest, SVM, XGBoost, and LightGBM. The source code is available at the GitHub repository at https://github.com/Li-OmicsLab/MetDIT, and the WebApp can be found at http://metdit.bioinformatics.vip/.
Collapse
Affiliation(s)
- Yuyang Sha
- Center for Artificial Intelligence Driven Drug Discovery, Faculty of Applied Sciences, Macao Polytechnic University, Macau SR 999708, China
| | - Weiyu Meng
- Center for Artificial Intelligence Driven Drug Discovery, Faculty of Applied Sciences, Macao Polytechnic University, Macau SR 999708, China
| | - Gang Luo
- Center for Artificial Intelligence Driven Drug Discovery, Faculty of Applied Sciences, Macao Polytechnic University, Macau SR 999708, China
| | - Xiaobing Zhai
- Center for Artificial Intelligence Driven Drug Discovery, Faculty of Applied Sciences, Macao Polytechnic University, Macau SR 999708, China
| | - Henry H Y Tong
- Center for Artificial Intelligence Driven Drug Discovery, Faculty of Applied Sciences, Macao Polytechnic University, Macau SR 999708, China
| | - Yuefei Wang
- National Key Laboratory of Chinese Medicine Modernization, State Key Laboratory of Component-Based Chinese Medicine, Tianjin University of Traditional Chinese Medicine, Tianjin 301617, China
- Haihe Laboratory of Modern Chinese Medicine, Tianjin 301617, China
| | - Kefeng Li
- Center for Artificial Intelligence Driven Drug Discovery, Faculty of Applied Sciences, Macao Polytechnic University, Macau SR 999708, China
| |
Collapse
|
10
|
Ravaee H, Manshaei MH, Safayani M, Sartakhti JS. Intelligent phenotype-detection and gene expression profile generation with generative adversarial networks. J Theor Biol 2024; 577:111636. [PMID: 37944593 DOI: 10.1016/j.jtbi.2023.111636] [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: 04/16/2023] [Revised: 08/11/2023] [Accepted: 10/05/2023] [Indexed: 11/12/2023]
Abstract
Gene expression analysis is valuable for cancer type classification and identifying diverse cancer phenotypes. The latest high-throughput RNA sequencing devices have enabled access to large volumes of gene expression data. However, we face several challenges, such as data security and privacy, when we develop machine learning-based classifiers for categorizing cancer types with these datasets. To address these issues, we propose IP3G (Intelligent Phenotype-detection and Gene expression profile Generation with Generative adversarial network), a model based on Generative Adversarial Networks. IP3G tackles two major problems: augmenting gene expression data and unsupervised phenotype discovery. By converting gene expression profiles into 2-Dimensional images and leveraging IP3G, we generate new profiles for specific phenotypes. IP3G learns disentangled representations of gene expression patterns and identifies phenotypes without labeled data. We improve the objective function of the GAN used in IP3G by employing the earth mover distance and a novel mutual information function. IP3G outperforms clustering methods like k-Means, DBSCAN, and GMM in unsupervised phenotype discovery, while also surpassing SVM and CNN classification accuracy by up to 6% through gene expression profile augmentation. The source code for the developed IP3G is accessible to the public on GitHub.
Collapse
Affiliation(s)
- Hamid Ravaee
- Department of Electrical and Computer Engineering, Isfahan University of Technology, Isfahan, 84156-83111, Iran
| | - Mohammad Hossein Manshaei
- Department of Electrical and Computer Engineering, Isfahan University of Technology, Isfahan, 84156-83111, Iran.
| | - Mehran Safayani
- Department of Electrical and Computer Engineering, Isfahan University of Technology, Isfahan, 84156-83111, Iran
| | | |
Collapse
|
11
|
Branson N, Cutillas PR, Bessant C. Comparison of multiple modalities for drug response prediction with learning curves using neural networks and XGBoost. BIOINFORMATICS ADVANCES 2023; 4:vbad190. [PMID: 38282976 PMCID: PMC10812874 DOI: 10.1093/bioadv/vbad190] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 09/22/2023] [Revised: 12/19/2023] [Accepted: 12/22/2023] [Indexed: 01/30/2024]
Abstract
Motivation Anti-cancer drug response prediction is a central problem within stratified medicine. Transcriptomic profiles of cancer cell lines are typically used for drug response prediction, but we hypothesize that proteomics or phosphoproteomics might be more suitable as they give a more direct insight into cellular processes. However, there has not yet been a systematic comparison between all three of these datatypes using consistent evaluation criteria. Results Due to the limited number of cell lines with phosphoproteomics profiles we use learning curves, a plot of predictive performance as a function of dataset size, to compare the current performance and predict the future performance of the three omics datasets with more data. We use neural networks and XGBoost and compare them against a simple rule-based benchmark. We show that phosphoproteomics slightly outperforms RNA-seq and proteomics using the 38 cell lines with profiles of all three omics data types. Furthermore, using the 877 cell lines with proteomics and RNA-seq profiles, we show that RNA-seq slightly outperforms proteomics. With the learning curves we predict that the mean squared error using the phosphoproteomics dataset would decrease by ∼ 15 % if a dataset of the same size as the proteomics/transcriptomics was collected. For the cell lines with proteomics and RNA-seq profiles the learning curves reveal that for smaller dataset sizes neural networks outperform XGBoost and vice versa for larger datasets. Furthermore, the trajectory of the XGBoost curve suggests that it will improve faster than the neural networks as more data are collected. Availability and implementation See https://github.com/Nik-BB/Learning-curves-for-DRP for the code used.
Collapse
Affiliation(s)
- Nikhil Branson
- School of Biological and Behavioural Sciences, Queen Mary University of London, London E1 4NS, United Kingdom
- Digital Environment Research Institute, Queen Mary University of London, London E1 1HH, United Kingdom
| | - Pedro R Cutillas
- Centre for Genomics and Computational Biology, Barts Cancer Institute, Queen Mary University of London, London EC1M 6BQ, United Kingdom
| | - Conrad Bessant
- School of Biological and Behavioural Sciences, Queen Mary University of London, London E1 4NS, United Kingdom
- Digital Environment Research Institute, Queen Mary University of London, London E1 1HH, United Kingdom
| |
Collapse
|
12
|
Narykov O, Zhu Y, Brettin T, Evrard YA, Partin A, Shukla M, Xia F, Clyde A, Vasanthakumari P, Doroshow JH, Stevens RL. Integration of Computational Docking into Anti-Cancer Drug Response Prediction Models. Cancers (Basel) 2023; 16:50. [PMID: 38201477 PMCID: PMC10777918 DOI: 10.3390/cancers16010050] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/03/2023] [Revised: 12/01/2023] [Accepted: 12/07/2023] [Indexed: 01/12/2024] Open
Abstract
Cancer is a heterogeneous disease in that tumors of the same histology type can respond differently to a treatment. Anti-cancer drug response prediction is of paramount importance for both drug development and patient treatment design. Although various computational methods and data have been used to develop drug response prediction models, it remains a challenging problem due to the complexities of cancer mechanisms and cancer-drug interactions. To better characterize the interaction between cancer and drugs, we investigate the feasibility of integrating computationally derived features of molecular mechanisms of action into prediction models. Specifically, we add docking scores of drug molecules and target proteins in combination with cancer gene expressions and molecular drug descriptors for building response models. The results demonstrate a marginal improvement in drug response prediction performance when adding docking scores as additional features, through tests on large drug screening data. We discuss the limitations of the current approach and provide the research community with a baseline dataset of the large-scale computational docking for anti-cancer drugs.
Collapse
Affiliation(s)
- Oleksandr Narykov
- Computing, Environment and Life Sciences, Argonne National Laboratory, Lemont, IL 60439, USA; (Y.Z.); (T.B.); (A.P.); (M.S.); (F.X.); (P.V.); (R.L.S.)
| | - Yitan Zhu
- Computing, Environment and Life Sciences, Argonne National Laboratory, Lemont, IL 60439, USA; (Y.Z.); (T.B.); (A.P.); (M.S.); (F.X.); (P.V.); (R.L.S.)
| | - Thomas Brettin
- Computing, Environment and Life Sciences, Argonne National Laboratory, Lemont, IL 60439, USA; (Y.Z.); (T.B.); (A.P.); (M.S.); (F.X.); (P.V.); (R.L.S.)
| | - Yvonne A. Evrard
- Leidos Biomedical Research, Frederick National Laboratory for Cancer Research, Frederick, MD 21702, USA;
| | - Alexander Partin
- Computing, Environment and Life Sciences, Argonne National Laboratory, Lemont, IL 60439, USA; (Y.Z.); (T.B.); (A.P.); (M.S.); (F.X.); (P.V.); (R.L.S.)
| | - Maulik Shukla
- Computing, Environment and Life Sciences, Argonne National Laboratory, Lemont, IL 60439, USA; (Y.Z.); (T.B.); (A.P.); (M.S.); (F.X.); (P.V.); (R.L.S.)
| | - Fangfang Xia
- Computing, Environment and Life Sciences, Argonne National Laboratory, Lemont, IL 60439, USA; (Y.Z.); (T.B.); (A.P.); (M.S.); (F.X.); (P.V.); (R.L.S.)
| | - Austin Clyde
- Computing, Environment and Life Sciences, Argonne National Laboratory, Lemont, IL 60439, USA; (Y.Z.); (T.B.); (A.P.); (M.S.); (F.X.); (P.V.); (R.L.S.)
- Department of Computer Science, The University of Chicago, Chicago, IL 60637, USA
| | - Priyanka Vasanthakumari
- Computing, Environment and Life Sciences, Argonne National Laboratory, Lemont, IL 60439, USA; (Y.Z.); (T.B.); (A.P.); (M.S.); (F.X.); (P.V.); (R.L.S.)
| | - James H. Doroshow
- Developmental Therapeutics Branch, National Cancer Institute, Bethesda, MD 20892, USA;
| | - Rick L. Stevens
- Computing, Environment and Life Sciences, Argonne National Laboratory, Lemont, IL 60439, USA; (Y.Z.); (T.B.); (A.P.); (M.S.); (F.X.); (P.V.); (R.L.S.)
- Department of Computer Science, The University of Chicago, Chicago, IL 60637, USA
| |
Collapse
|
13
|
Medeiros Neto L, Rogerio da Silva Neto S, Endo PT. A comparative analysis of converters of tabular data into image for the classification of Arboviruses using Convolutional Neural Networks. PLoS One 2023; 18:e0295598. [PMID: 38064477 PMCID: PMC10707680 DOI: 10.1371/journal.pone.0295598] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/01/2023] [Accepted: 11/24/2023] [Indexed: 12/18/2023] Open
Abstract
Tabular data is commonly used in business and literature and can be analyzed using tree-based Machine Learning (ML) algorithms to extract meaningful information. Deep Learning (DL) excels in data such as image, sound, and text, but it is less frequently utilized with tabular data. However, it is possible to use tools to convert tabular data into images for use with Convolutional Neural Networks (CNNs) which are powerful DL models for image classification. The goal of this work is to compare the performance of converters for tabular data into images, select the best one, optimize a CNN using random search, and compare it with an optimized ML algorithm, the XGBoost. Results show that even a basic CNN, with only 1 convolutional layer, can reach comparable metrics to the XGBoost, which was trained on the original tabular data and optimized with grid search and feature selection. However, further optimization of the CNN with random search did not significantly improve its performance.
Collapse
|
14
|
Bazgir O, Lu J. REFINED-CNN framework for survival prediction with high-dimensional features. iScience 2023; 26:107627. [PMID: 37664631 PMCID: PMC10474067 DOI: 10.1016/j.isci.2023.107627] [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: 02/09/2023] [Revised: 06/21/2023] [Accepted: 08/10/2023] [Indexed: 09/05/2023] Open
Abstract
Robust and accurate survival prediction of clinical trials using high-throughput genomics data is a fundamental challenge in pharmacogenomics. Current machine learning tools often provide limited predictive performance and model interpretation in these settings. In the present study, we extend the application of REFINED-CNN from regression tasks to making survival predictions, by mapping high-dimensional RNA sequencing data into REFINED images which are conducive to CNN modeling. We show that the REFINED-CNN survival model can be easily adapted to new tasks of a similar nature (e.g., predicting on new cancer types) using transfer learning with a low number of patients. Furthermore, the model can also be interpreted both locally and globally through risk score back propagation that quantifies each feature (e.g., gene) importance in survival prediction task for the patient or cancer type of interest.
Collapse
Affiliation(s)
- Omid Bazgir
- Modeling & Simulation/Clinical Pharmacology, Genentech, 1 DNA Way, South San Francisco, CA 94080, USA
| | - James Lu
- Modeling & Simulation/Clinical Pharmacology, Genentech, 1 DNA Way, South San Francisco, CA 94080, USA
| |
Collapse
|
15
|
Partin A, Brettin T, Zhu Y, Dolezal JM, Kochanny S, Pearson AT, Shukla M, Evrard YA, Doroshow JH, Stevens RL. Data augmentation and multimodal learning for predicting drug response in patient-derived xenografts from gene expressions and histology images. Front Med (Lausanne) 2023; 10:1058919. [PMID: 36960342 PMCID: PMC10027779 DOI: 10.3389/fmed.2023.1058919] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/30/2022] [Accepted: 02/10/2023] [Indexed: 03/09/2023] Open
Abstract
Patient-derived xenografts (PDXs) are an appealing platform for preclinical drug studies. A primary challenge in modeling drug response prediction (DRP) with PDXs and neural networks (NNs) is the limited number of drug response samples. We investigate multimodal neural network (MM-Net) and data augmentation for DRP in PDXs. The MM-Net learns to predict response using drug descriptors, gene expressions (GE), and histology whole-slide images (WSIs). We explore whether combining WSIs with GE improves predictions as compared with models that use GE alone. We propose two data augmentation methods which allow us training multimodal and unimodal NNs without changing architectures with a single larger dataset: 1) combine single-drug and drug-pair treatments by homogenizing drug representations, and 2) augment drug-pairs which doubles the sample size of all drug-pair samples. Unimodal NNs which use GE are compared to assess the contribution of data augmentation. The NN that uses the original and the augmented drug-pair treatments as well as single-drug treatments outperforms NNs that ignore either the augmented drug-pairs or the single-drug treatments. In assessing the multimodal learning based on the MCC metric, MM-Net outperforms all the baselines. Our results show that data augmentation and integration of histology images with GE can improve prediction performance of drug response in PDXs.
Collapse
Affiliation(s)
- Alexander Partin
- Division of Data Science and Learning, Argonne National Laboratory, Lemont, IL, United States
| | - Thomas Brettin
- Division of Data Science and Learning, Argonne National Laboratory, Lemont, IL, United States
| | - Yitan Zhu
- Division of Data Science and Learning, Argonne National Laboratory, Lemont, IL, United States
| | - James M. Dolezal
- Section of Hematology/Oncology, Department of Medicine, University of Chicago Medical Center, Chicago, IL, United States
| | - Sara Kochanny
- Section of Hematology/Oncology, Department of Medicine, University of Chicago Medical Center, Chicago, IL, United States
| | - Alexander T. Pearson
- Section of Hematology/Oncology, Department of Medicine, University of Chicago Medical Center, Chicago, IL, United States
| | - Maulik Shukla
- Division of Data Science and Learning, Argonne National Laboratory, Lemont, IL, United States
| | - Yvonne A. Evrard
- Frederick National Laboratory for Cancer Research, Leidos Biomedical Research, Inc., Frederick, MD, United States
| | - James H. Doroshow
- Division of Cancer Therapeutics and Diagnosis, National Cancer Institute, Bethesda, MD, United States
| | - Rick L. Stevens
- Division of Data Science and Learning, Argonne National Laboratory, Lemont, IL, United States
- Department of Computer Science, The University of Chicago, Chicago, IL, United States
| |
Collapse
|
16
|
Feed-Forward Deep Neural Network (FFDNN)-Based Deep Features for Static Malware Detection. INT J INTELL SYST 2023. [DOI: 10.1155/2023/9544481] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 02/22/2023]
Abstract
The portable executable header (PEH) information is commonly used as a feature for malware detection systems to train and validate machine learning (ML) or deep learning (DL) classifiers. We propose to extract the deep features from the PEH information through hidden layers of a feed-forward deep neural network (FFDNN). The extraction of deep features of hidden layers represents the dataset with a better generalization for malware detection. While feeding the deep feature of one hidden layer to the succeeding layer, the Gaussian error linear unit (GeLU) activation function is applied. The FFDNN is trained with the GeLU activation function using the deep features of individual layers as well as concatenated deep features of all hidden layers. Similarly, the ML classifiers are also trained and validated in with individual layer deep features and concatenated features. Three highly effective ML classifiers, random forest (RF), support vector machine (SVM), and k-nearest neighbour (k-NN) have been investigated. The performance of the proposed model is demonstrated using a statically significant large dataset. The obtained results are interesting and encouraging in terms of classification accuracy. The classification accuracy reaches 99.15% with the internal discriminative deep feature for the proposed FFDNN-ML classifier with the GeLU activation function.
Collapse
|
17
|
Partin A, Brettin TS, Zhu Y, Narykov O, Clyde A, Overbeek J, Stevens RL. Deep learning methods for drug response prediction in cancer: Predominant and emerging trends. Front Med (Lausanne) 2023; 10:1086097. [PMID: 36873878 PMCID: PMC9975164 DOI: 10.3389/fmed.2023.1086097] [Citation(s) in RCA: 19] [Impact Index Per Article: 19.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/01/2022] [Accepted: 01/23/2023] [Indexed: 02/17/2023] Open
Abstract
Cancer claims millions of lives yearly worldwide. While many therapies have been made available in recent years, by in large cancer remains unsolved. Exploiting computational predictive models to study and treat cancer holds great promise in improving drug development and personalized design of treatment plans, ultimately suppressing tumors, alleviating suffering, and prolonging lives of patients. A wave of recent papers demonstrates promising results in predicting cancer response to drug treatments while utilizing deep learning methods. These papers investigate diverse data representations, neural network architectures, learning methodologies, and evaluations schemes. However, deciphering promising predominant and emerging trends is difficult due to the variety of explored methods and lack of standardized framework for comparing drug response prediction models. To obtain a comprehensive landscape of deep learning methods, we conducted an extensive search and analysis of deep learning models that predict the response to single drug treatments. A total of 61 deep learning-based models have been curated, and summary plots were generated. Based on the analysis, observable patterns and prevalence of methods have been revealed. This review allows to better understand the current state of the field and identify major challenges and promising solution paths.
Collapse
Affiliation(s)
- Alexander Partin
- Division of Data Science and Learning, Argonne National Laboratory, Lemont, IL, United States
| | - Thomas S. Brettin
- Division of Data Science and Learning, Argonne National Laboratory, Lemont, IL, United States
| | - Yitan Zhu
- Division of Data Science and Learning, Argonne National Laboratory, Lemont, IL, United States
| | - Oleksandr Narykov
- Division of Data Science and Learning, Argonne National Laboratory, Lemont, IL, United States
| | - Austin Clyde
- Division of Data Science and Learning, Argonne National Laboratory, Lemont, IL, United States
| | - Jamie Overbeek
- Division of Data Science and Learning, Argonne National Laboratory, Lemont, IL, United States
| | - Rick L. Stevens
- Division of Data Science and Learning, Argonne National Laboratory, Lemont, IL, United States
- Department of Computer Science, The University of Chicago, Chicago, IL, United States
| |
Collapse
|
18
|
Sharma A, Lysenko A, Boroevich KA, Tsunoda T. DeepInsight-3D architecture for anti-cancer drug response prediction with deep-learning on multi-omics. Sci Rep 2023; 13:2483. [PMID: 36774402 PMCID: PMC9922304 DOI: 10.1038/s41598-023-29644-3] [Citation(s) in RCA: 4] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/21/2022] [Accepted: 02/08/2023] [Indexed: 02/13/2023] Open
Abstract
Modern oncology offers a wide range of treatments and therefore choosing the best option for particular patient is very important for optimal outcome. Multi-omics profiling in combination with AI-based predictive models have great potential for streamlining these treatment decisions. However, these encouraging developments continue to be hampered by very high dimensionality of the datasets in combination with insufficiently large numbers of annotated samples. Here we proposed a novel deep learning-based method to predict patient-specific anticancer drug response from three types of multi-omics data. The proposed DeepInsight-3D approach relies on structured data-to-image conversion that then allows use of convolutional neural networks, which are particularly robust to high dimensionality of the inputs while retaining capabilities to model highly complex relationships between variables. Of particular note, we demonstrate that in this formalism additional channels of an image can be effectively used to accommodate data from different omics layers while implicitly encoding the connection between them. DeepInsight-3D was able to outperform other state-of-the-art methods applied to this task. The proposed improvements can facilitate the development of better personalized treatment strategies for different cancers in the future.
Collapse
Affiliation(s)
- Alok Sharma
- Laboratory for Medical Science Mathematics, RIKEN Center for Integrative Medical Sciences, Yokohama, Japan.
- Institute for Integrated and Intelligent Systems, Griffith University, Brisbane, Australia.
| | - Artem Lysenko
- Laboratory for Medical Science Mathematics, RIKEN Center for Integrative Medical Sciences, Yokohama, Japan.
- Laboratory for Medical Science Mathematics, Department of Biological Sciences, School of Science, The University of Tokyo, Tokyo, Japan.
| | - Keith A Boroevich
- Laboratory for Medical Science Mathematics, RIKEN Center for Integrative Medical Sciences, Yokohama, Japan
| | - Tatsuhiko Tsunoda
- Laboratory for Medical Science Mathematics, RIKEN Center for Integrative Medical Sciences, Yokohama, Japan.
- Laboratory for Medical Science Mathematics, Department of Biological Sciences, School of Science, The University of Tokyo, Tokyo, Japan.
- Laboratory for Medical Science Mathematics, Department of Computational Biology and Medical Sciences, Graduate School of Frontier Sciences, The University of Tokyo, Tokyo, Japan.
| |
Collapse
|
19
|
Silva Rocha ED, de Morais Melo FL, de Mello MEF, Figueiroa B, Sampaio V, Endo PT. On usage of artificial intelligence for predicting mortality during and post-pregnancy: a systematic review of literature. BMC Med Inform Decis Mak 2022; 22:334. [PMID: 36536413 PMCID: PMC9764498 DOI: 10.1186/s12911-022-02082-3] [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: 08/13/2022] [Accepted: 12/13/2022] [Indexed: 12/23/2022] Open
Abstract
BACKGROUND Care during pregnancy, childbirth and puerperium are fundamental to avoid pathologies for the mother and her baby. However, health issues can occur during this period, causing misfortunes, such as the death of the fetus or neonate. Predictive models of fetal and infant deaths are important technological tools that can help to reduce mortality indexes. The main goal of this work is to present a systematic review of literature focused on computational models to predict mortality, covering stillbirth, perinatal, neonatal, and infant deaths, highlighting their methodology and the description of the proposed computational models. METHODS We conducted a systematic review of literature, limiting the search to the last 10 years of publications considering the five main scientific databases as source. RESULTS From 671 works, 18 of them were selected as primary studies for further analysis. We found that most of works are focused on prediction of neonatal deaths, using machine learning models (more specifically Random Forest). The top five most common features used to train models are birth weight, gestational age, sex of the child, Apgar score and mother's age. Having predictive models for preventing mortality during and post-pregnancy not only improve the mother's quality of life, as well as it can be a powerful and low-cost tool to decrease mortality ratios. CONCLUSION Based on the results of this SRL, we can state that scientific efforts have been done in this area, but there are many open research opportunities to be developed by the community.
Collapse
Affiliation(s)
- Elisson da Silva Rocha
- grid.26141.300000 0000 9011 5442Programa de Pós-Graduação em Engenharia da Computação, Universidade de Pernambuco, Recife, Brazil
| | - Flavio Leandro de Morais Melo
- grid.26141.300000 0000 9011 5442Programa de Pós-Graduação em Engenharia da Computação, Universidade de Pernambuco, Recife, Brazil
| | | | - Barbara Figueiroa
- Programa Mãe Coruja Pernambucana, Secretaria de Saúde do Estado de Pernambuco, Recife, Brazil
| | | | - Patricia Takako Endo
- grid.26141.300000 0000 9011 5442Programa de Pós-Graduação em Engenharia da Computação, Universidade de Pernambuco, Recife, Brazil
| |
Collapse
|
20
|
Kim T, Lee SJ, Jang T. Application of several machine learning algorithms for the prediction of afatinib treatment outcome in advanced-stage EGFR-mutated non-small-cell lung cancer. Thorac Cancer 2022; 13:3353-3361. [PMID: 36278315 PMCID: PMC9715822 DOI: 10.1111/1759-7714.14694] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/20/2022] [Revised: 09/28/2022] [Accepted: 09/30/2022] [Indexed: 01/09/2023] Open
Abstract
BACKGROUND The present study aimed to evaluate the performance of several machine learning (ML) algorithms in predicting 1-year afatinib continuation and 2-year survival after afatinib initiation and to identify the differences in survival outcomes between ML-classified strata. METHODS Data that were also used in the RESET study were retrospectively collected from 16 hospitals in South Korea. A stratified random sampling method was applied to split the data into training and test sets (70:30 split ratio). Clinical information, such as age, sex, tumor stage, smoking, performance status, metastasis, type of metastasis, dose adjustment, and pathologic information on EGFR mutations were inputted. Training was performed using eight ML algorithms: logistic regression, decision tree, deep neural network, random forest, support vector machine, boosting, bagging, and the naïve Bayes classifier. The model performance was assessed based on sensitivity, specificity, and accuracy. Area under the receiver operator characteristic curve (AUC) was calculated and compared between the ML models using DeLong's test. A Kaplan-Meier (KM) curve was used to visualize the identified strata obtained from the ML models. RESULTS No significant differences in the input variables were observed between the training and test datasets. The best-performing models were support vector machine in predicting 1-year afatinib continuation (AUC 0.626) and decision tree in 2-year survival after afatinib start (AUC 0.644), although the performances of the ML models were comparable and did not display any predictive roles. KM analysis and log-rank test revealed significant differences between the strata identified from the ML model (p < 0.001) in terms of both time-on-treatment (TOT) and overall survival (OS). CONCLUSION The performances of ML models in our study found no discernible roles in predicting afatinib-related outcomes, although the identified strata revealed different TOT and OS in the KM analysis. This implies the strength of ML in predicting the survival outcome, as well as the limitation of electronic medical record-based variables in ML algorithms. Careful consideration of variable inclusion is likely to improve the general model performance.
Collapse
Affiliation(s)
- Taeyun Kim
- Division of Pulmonology, Department of Internal MedicineThe Armed Forces Goyang HospitalGoyangRepublic of Korea
| | - Sang Jin Lee
- Department of StatisticsPusan National UniversityBusanRepublic of Korea
| | - Tae‐Won Jang
- Division of Pulmonology, Department of Internal MedicineKosin University College of Medicine, Kosin University Gospel HospitalBusanRepublic of Korea
| |
Collapse
|
21
|
Image-Based Approach to Intrusion Detection in Cyber-Physical Objects. INFORMATION 2022. [DOI: 10.3390/info13120553] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/27/2022] Open
Abstract
Recently, approaches based on the transformation of tabular data into images have gained a lot of scientific attention. This is explained by the fact that convolutional neural networks (CNNs) have shown good results in computer vision and other image-based classification tasks. Transformation of features without spatial relations to images allows the application of deep neural networks to a wide range of analysis tasks. This paper analyzes existing approaches to feature transformation based on the conversion of the features of network traffic into images and discusses their advantages and disadvantages. The authors also propose an approach to the transformation of raw network packets into images and analyze its efficiency in the task of network attack detection in a cyber-physical object, including its robustness to novel and unseen attacks.
Collapse
|
22
|
Explainable artificial intelligence through graph theory by generalized social network analysis-based classifier. Sci Rep 2022; 12:15210. [PMID: 36075941 PMCID: PMC9458666 DOI: 10.1038/s41598-022-19419-7] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/13/2022] [Accepted: 08/29/2022] [Indexed: 12/05/2022] Open
Abstract
We propose a new type of supervised visual machine learning classifier, GSNAc, based on graph theory and social network analysis techniques. In a previous study, we employed social network analysis techniques and introduced a novel classification model (called Social Network Analysis-based Classifier—SNAc) which efficiently works with time-series numerical datasets. In this study, we have extended SNAc to work with any type of tabular data by showing its classification efficiency on a broader collection of datasets that may contain numerical and categorical features. This version of GSNAc simply works by transforming traditional tabular data into a network where samples of the tabular dataset are represented as nodes and similarities between the samples are reflected as edges connecting the corresponding nodes. The raw network graph is further simplified and enriched by its edge space to extract a visualizable ‘graph classifier model—GCM’. The concept of the GSNAc classification model relies on the study of node similarities over network graphs. In the prediction step, the GSNAc model maps test nodes into GCM, and evaluates their average similarity to classes by employing vectorial and topological metrics. The novel side of this research lies in transforming multidimensional data into a 2D visualizable domain. This is realized by converting a conventional dataset into a network of ‘samples’ and predicting classes after a careful and detailed network analysis. We exhibit the classification performance of GSNAc as an effective classifier by comparing it with several well-established machine learning classifiers using some popular benchmark datasets. GSNAc has demonstrated superior or comparable performance compared to other classifiers. Additionally, it introduces a visually comprehensible process for the benefit of end-users. As a result, the spin-off contribution of GSNAc lies in the interpretability of the prediction task since the process is human-comprehensible; and it is highly visual.
Collapse
|
23
|
Cao H, Xie X, Shi J, Jiang G, Wang Y. Siamese Network-Based Transfer Learning Model to Predict Geogenic Contaminated Groundwaters. ENVIRONMENTAL SCIENCE & TECHNOLOGY 2022; 56:11071-11079. [PMID: 35816418 DOI: 10.1021/acs.est.1c08682] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/15/2023]
Abstract
Exposure to geogenic contaminated groundwaters (GCGs) is a significant public health concern. Machine learning models are powerful tools for the discovery of potential GCGs. However, the insufficient groundwater quality data and the fact that GCGs are typically a minority class in data hinder models to produce meaningful GCG predictions. To address this issue, a deep learning method, Siamese network-based transfer learning (SNTL), is used to estimate the probability that hazardous substances are present in groundwater above a threshold based on limited and class-imbalanced data. SNTL greatly reduces the amount of required training data and eliminates negative effects of class-imbalanced data on prediction model performance. The predictions of three typical GCGs (high arsenic/fluoride/iodine groundwater) show that the SNTL models provide higher (about 80%) and more balanced sensitivity and specificity than benchmark Random Forest models, indicating that SNTL models can predict both GCGs and non-GCGs. Therefore, protecting populations from GCG exposure in areas where other prediction methods fail to contribute risk information due to poor groundwater quality data can be enabled by SNTL.
Collapse
Affiliation(s)
- Hailong Cao
- School of Environmental Studies & State Key Laboratory of Biogeology and Environmental Geology, China University of Geosciences, Wuhan 430074, China
| | - Xianjun Xie
- School of Environmental Studies & State Key Laboratory of Biogeology and Environmental Geology, China University of Geosciences, Wuhan 430074, China
| | - Jianbo Shi
- School of Environmental Studies & State Key Laboratory of Biogeology and Environmental Geology, China University of Geosciences, Wuhan 430074, China
| | - Guibin Jiang
- State Key Laboratory of Environmental Chemistry and Ecotoxicology, Research Center for Eco-Environmental Sciences, Chinese Academy of Sciences, Beijing 100085, China
| | - Yanxin Wang
- School of Environmental Studies & State Key Laboratory of Biogeology and Environmental Geology, China University of Geosciences, Wuhan 430074, China
| |
Collapse
|
24
|
Stevens JM, Li J, Simmons EM, Wisniewski SR, DiSomma S, Fraunhoffer KJ, Geng P, Hao B, Jackson EW. Advancing Base Metal Catalysis through Data Science: Insight and Predictive Models for Ni-Catalyzed Borylation through Supervised Machine Learning. Organometallics 2022. [DOI: 10.1021/acs.organomet.2c00089] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/28/2022]
Affiliation(s)
- Jason M. Stevens
- Chemical Process Development, Bristol-Myers Squibb, 556 Morris Avenue, Summit, New Jersey 07901, United States
| | - Jun Li
- Chemical Process Development, Bristol-Myers Squibb, 1 Squibb Drive, New Brunswick, New Jersey 08901, United States
| | - Eric M. Simmons
- Chemical Process Development, Bristol-Myers Squibb, 1 Squibb Drive, New Brunswick, New Jersey 08901, United States
| | - Steven R. Wisniewski
- Chemical Process Development, Bristol-Myers Squibb, 1 Squibb Drive, New Brunswick, New Jersey 08901, United States
| | - Stacey DiSomma
- Chemical Process Development, Bristol-Myers Squibb, 1 Squibb Drive, New Brunswick, New Jersey 08901, United States
| | - Kenneth J. Fraunhoffer
- Chemical Process Development, Bristol-Myers Squibb, 1 Squibb Drive, New Brunswick, New Jersey 08901, United States
| | - Peng Geng
- Chemical Process Development, Bristol-Myers Squibb, 1 Squibb Drive, New Brunswick, New Jersey 08901, United States
| | - Bo Hao
- Chemical Process Development, Bristol-Myers Squibb, 1 Squibb Drive, New Brunswick, New Jersey 08901, United States
| | - Erika W. Jackson
- Chemical Process Development, Bristol-Myers Squibb, 1 Squibb Drive, New Brunswick, New Jersey 08901, United States
| |
Collapse
|
25
|
Trapotsi MA, Hosseini-Gerami L, Bender A. Computational analyses of mechanism of action (MoA): data, methods and integration. RSC Chem Biol 2022; 3:170-200. [PMID: 35360890 PMCID: PMC8827085 DOI: 10.1039/d1cb00069a] [Citation(s) in RCA: 8] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/30/2021] [Accepted: 12/09/2021] [Indexed: 12/15/2022] Open
Abstract
The elucidation of a compound's Mechanism of Action (MoA) is a challenging task in the drug discovery process, but it is important in order to rationalise phenotypic findings and to anticipate potential side-effects. Bioinformatic approaches, advances in machine learning techniques and the increasing deposition of high-throughput data in public databases have significantly contributed to recent advances in the field, but it is not straightforward to decide which data and methods are most suitable to use in a given case. In this review, we focus on these methods and data and their applications in generating MoA hypotheses for subsequent experimental validation. We discuss compound-specific data such as -omics, cell morphology and bioactivity data, as well as commonly used supplementary prior knowledge such as network and pathway data, and provide information on databases where this data can be accessed. In terms of methodologies, we discuss both well-established methods (connectivity mapping, pathway enrichment) as well as more developing methods (neural networks and multi-omics integration). Finally, we review case studies where the MoA of a compound was successfully suggested from computational analysis by incorporating multiple data modalities and/or methodologies. Our aim for this review is to provide researchers with insights into the benefits and drawbacks of both the data and methods in terms of level of understanding, biases and interpretation - and to highlight future avenues of investigation which we foresee will improve the field of MoA elucidation, including greater public access to -omics data and methodologies which are capable of data integration.
Collapse
Affiliation(s)
- Maria-Anna Trapotsi
- Centre for Molecular Informatics, Yusuf Hamied Department of Chemistry, University of Cambridge UK
| | - Layla Hosseini-Gerami
- Centre for Molecular Informatics, Yusuf Hamied Department of Chemistry, University of Cambridge UK
| | - Andreas Bender
- Centre for Molecular Informatics, Yusuf Hamied Department of Chemistry, University of Cambridge UK
| |
Collapse
|
26
|
Tang H, Yu X, Liu R, Zeng T. Vec2image: an explainable artificial intelligence model for the feature representation and classification of high-dimensional biological data by vector-to-image conversion. Brief Bioinform 2022; 23:6518046. [PMID: 35106553 PMCID: PMC8921615 DOI: 10.1093/bib/bbab584] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/14/2021] [Revised: 12/06/2021] [Accepted: 12/20/2021] [Indexed: 01/05/2023] Open
Abstract
Feature representation and discriminative learning are proven models and technologies in artificial intelligence fields; however, major challenges for machine learning on large biological datasets are learning an effective model with mechanistical explanation on the model determination and prediction. To satisfy such demands, we developed Vec2image, an explainable convolutional neural network framework for characterizing the feature engineering, feature selection and classifier training that is mainly based on the collaboration of principal component coordinate conversion, deep residual neural networks and embedded k-nearest neighbor representation on pseudo images of high-dimensional biological data, where the pseudo images represent feature measurements and feature associations simultaneously. Vec2image has achieved better performance compared with other popular methods and illustrated its efficiency on feature selection in cell marker identification from tissue-specific single-cell datasets. In particular, in a case study on type 2 diabetes (T2D) by multiple human islet scRNA-seq datasets, Vec2image first displayed robust performance on T2D classification model building across different datasets, then a specific Vec2image model was trained to accurately recognize the cell state and efficiently rank feature genes relevant to T2D which uncovered potential T2D cellular pathogenesis; and next the cell activity changes, cell composition imbalances and cell–cell communication dysfunctions were associated to our finding T2D feature genes from both population-shared and individual-specific perspectives. Collectively, Vec2image is a new and efficient explainable artificial intelligence methodology that can be widely applied in human-readable classification and prediction on the basis of pseudo image representation of biological deep sequencing data.
Collapse
Affiliation(s)
- Hui Tang
- School of Mathematics, South China University of Technology, Guangzhou, 510640, China
| | - Xiangtian Yu
- Clinical Research Center, Shanghai Jiao Tong University Affiliated Sixth People's Hospital, Shanghai, 200233, China
| | - Rui Liu
- School of Mathematics, South China University of Technology, Guangzhou, 510640, China.,Pazhou Lab, Guangzhou 510330, China
| | - Tao Zeng
- Guangzhou Laboratory, Guangzhou, China.,Bio-Med Big Data Center, Shanghai Institute of Nutrition and Health, University of Chinese Academy of Sciences, Chinese Academy of Sciences, Shanghai 200031, China
| |
Collapse
|