A Cancer Biologist's Primer on Machine Learning Applications in High‐Dimensional Cytometry

Keyes, Timothy; Domizi, Pablo; Lo, Yu‐Chen; Nolan, Garry P.; Davis, Kara L.

doi:10.1002/cyto.a.24158

Cited by 20 publications

(19 citation statements)

References 102 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One of the obvious limitations of this study was the low number of patients (14). However, the primary purpose of the study was to propose and develop a novel analytical framework, and to see if it compares favorably with the existing tools.…”

Section: Discussionmentioning

confidence: 99%

“…Identification of clinically useful markers (and, perhaps even more importantly, marker combinations) is a secondary data analysis task, belonging to the realm of computational systems biology. To the best of our knowledge, there is currently no systems biology data analysis pipeline aimed specifically at high-dimensional data (including cytometry) in the immuno-oncology domain [11][12][13][14]. For example, recent works in the field [15][16][17][18][19] either reduce the markers' deduction to classification and semi-manual / pairwise combinatorics, or rely on ontological protein-protein interaction networks.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Dissecting Response to Cancer Immunotherapy by Applying Bayesian Network Analysis to Flow Cytometry Data

Rodin

Gogoshin

Wang

et al. 2020

Preprint

View full text Add to dashboard Cite

Cancer immunotherapy, specifically immune checkpoint blockade therapy, has been found to be effective in the treatment of metastatic cancers. However, only a subset of patients with certain cancer types achieve clinical responses. Consequently, elucidating immune system-related pre-treatment biomarkers that are predictive with respect to sustained clinical response is a major research priority. Another research priority is evaluating changes in the immune system before and after treatment in responders and non-responders. Specifically, our group has been studying immune signaling networks as an accurate reflection of the global immune state. Flow cytometry data (FACS, Fluorescence-activated cell sorting) characterizing immune signaling in peripheral blood mononuclear cells (PBMC) from gastroesophageal adenocarcinoma (GEA) patients were used to analyze changes in immune signaling networks in this setting. We developed a novel computational pipeline to perform secondary analyses of FACS data using systems biology / machine learning / information-theoretic techniques and concepts, primarily based on Bayesian network modeling. Application of this novel pipeline resulted in determination of immune markers, combinations / interactions thereof, and corresponding immune cell population types that are associated with clinical responses. Future studies are planned to generalize our analytical approach to different cancer types and corresponding datasets. 6 Author SummaryIt is difficult to predict whether a cancer patient undergoing immunotherapy treatments will respond. As immunotherapy is expensive and may lead to autoimmune toxicities, patient selection is an important issue. One way to gain deeper insight into the underlying processes is to study changes in immune signaling networks during the treatment course. These networks can be modeled, visualized, and quantified using systems biology / machine learning methods, such as Bayesian networks (BNs). Here, we present a BN-based analytical strategy for devising and comparing immune signaling networks, and apply it to data obtained from patients in a gastrointestinal cancer immunotherapy clinical trial. We identify potentially predictive immune biomarkers, and compare and contrast the resulting network models in different groups of patients, before and after therapy. Our analytical strategy generalizes to different cancers and immunotherapy regimens.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Dissecting Response to Cancer Immunotherapy by Applying Bayesian Network Analysis to Flow Cytometry Data

Rodin

Gogoshin

Wang

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…The impact of AI in this field is significant, especially because it assists clinicians in the analysis and interpretation of medical images, has great accuracy, enhances workflow, and reduces medical errors; in addition, it assists patients through the use of algorithms in devices such as smartwatches (Fingas, 2018;Victory, 2018), recording the patient data and making it available for processing and tracking (Topol, 2019). Many recent studies have used AI technologies and their components, particularly ML and DL, to improve healthcare systems (Dzobo et al, 2020;Milstein & Topol, 2020), support disease and abnormality detection through medical imaging (Berzin & Topol, 2020;Nagendran et al, 2020;Thomford et al, 2020), analyze and handle big data (Keyes et al, 2020), and facilitate organ damage detection (Agur, Daniel & Ginosar, 2002).…”

Section: Convolutional Neural Network In Medical Analysismentioning

confidence: 99%

Stem cell imaging through convolutional neural networks: current issues and future directions in artificial intelligence technology

Ramakrishna

Hamid

Zaki

et al. 2020

PeerJ

View full text Add to dashboard Cite

Stem cells are primitive and precursor cells with the potential to reproduce into diverse mature and functional cell types in the body throughout the developmental stages of life. Their remarkable potential has led to numerous medical discoveries and breakthroughs in science. As a result, stem cell–based therapy has emerged as a new subspecialty in medicine. One promising stem cell being investigated is the induced pluripotent stem cell (iPSC), which is obtained by genetically reprogramming mature cells to convert them into embryonic-like stem cells. These iPSCs are used to study the onset of disease, drug development, and medical therapies. However, functional studies on iPSCs involve the analysis of iPSC-derived colonies through manual identification, which is time-consuming, error-prone, and training-dependent. Thus, an automated instrument for the analysis of iPSC colonies is needed. Recently, artificial intelligence (AI) has emerged as a novel technology to tackle this challenge. In particular, deep learning, a subfield of AI, offers an automated platform for analyzing iPSC colonies and other colony-forming stem cells. Deep learning rectifies data features using a convolutional neural network (CNN), a type of multi-layered neural network that can play an innovative role in image recognition. CNNs are able to distinguish cells with high accuracy based on morphologic and textural changes. Therefore, CNNs have the potential to create a future field of deep learning tasks aimed at solving various challenges in stem cell studies. This review discusses the progress and future of CNNs in stem cell imaging for therapy and research.

show abstract

“…Manuscript to be reviewed and handle big data (Keyes et al, 2020), and facilitate organ damage detection (Agur, Daniel & Ginosar, 2002).…”

Section: Convolutional Neural Network In Medical Analysismentioning

confidence: 99%

Peer Review #2 of "Stem cell imaging through convolutional neural networks: current issues and future directions in artificial intelligence technology (v0.1)"

Miriuka¹

2020

View full text Add to dashboard Cite

Stem cells are primitive and precursor cells with the potential to reproduce into diverse mature and functional cell types in the body throughout the developmental stages of life. Their remarkable potential has led to numerous medical discoveries and breakthroughs in science. As a result, stem cell-based therapy has emerged as a new subspecialty in medicine. One promising stem cell being investigated is the induced pluripotent stem cell (iPSC), which is obtained by genetically reprogramming mature cells to convert them into embryonic-like stem cells. These iPSCs are used to study the onset of disease, drug development, and medical therapies. However, functional studies on iPSCs involve the analysis of iPSC-derived colonies through manual identification, which is time-consuming, error-prone, and training-dependent. Thus, an automated instrument for the analysis of iPSC colonies is needed. Recently, artificial intelligence (AI) has emerged as a novel technology to tackle this challenge. In particular, deep learning, a subfield of AI, offers an automated platform for analyzing iPSC colonies and other colony-forming stem cells. Deep learning rectifies data features using a convolutional neural network (CNN), a type of multi-layered neural network that can play an innovative role in image recognition. CNNs are able to distinguish cells with high accuracy based on morphologic and textural changes. Therefore, CNNs have the potential to create a future field of deep learning tasks aimed at solving various challenges in stem cell studies. This review discusses the progress and future of CNNs in stem cell imaging for therapy and research.

show abstract

A Cancer Biologist's Primer on Machine Learning Applications in High‐Dimensional Cytometry

Cited by 20 publications

References 102 publications

Dissecting Response to Cancer Immunotherapy by Applying Bayesian Network Analysis to Flow Cytometry Data

Dissecting Response to Cancer Immunotherapy by Applying Bayesian Network Analysis to Flow Cytometry Data

Stem cell imaging through convolutional neural networks: current issues and future directions in artificial intelligence technology

Peer Review #2 of "Stem cell imaging through convolutional neural networks: current issues and future directions in artificial intelligence technology (v0.1)"

Contact Info

Product

Resources

About