STAINING KIT AND METHOD OF IMMUNEPROFILING TO IDENTIFY CHARACTERIZED IMMUNE CELL SUBSETS OF DISEASE AND PREDICTING DISEASE USING THE SAME

Abstract

A staining kit is provided, including a first pattern including antibodies against T cell, B cell, NK cell, monocyte, regulatory cell, CD8, CD45, and CTLA4; a second pattern including antibodies against T cell, B cell, NK cell, monocyte, regulatory cell, dendritic cell, and CD45; a third pattern including antibodies against T cell, B cell, NK cell, monocyte, CD8, CD45, CD45RA, CD62L, CD197, CX3CR1 and TCR.sub.??; and a fourth pattern including antibodies against B cell, CD23, CD38, CD40, CD45 and IgM, wherein the antibodies of each pattern are labeled with fluorescent dyes. A method of identifying characterized immune cell subsets of a disease and a method of predicting the likelihood of NPC in a subject in the need thereof using the staining kit are also provided.

Claims

1. A staining kit, comprising a first pattern comprising antibodies against T cell, B cell, NK cell, monocyte, regulatory cell, CD8, CD45, and CTLA4; a second pattern comprising antibodies against T cell, B cell, NK cell, monocyte, regulatory cell, dendritic cell, and CD45; a third pattern comprising antibodies against T cell, B cell, NK cell, monocyte, CD8, CD45, CD45RA, CD62L, CD197, CX3CR1 and TCR.sub.??; and a fourth pattern comprising antibodies against B cell, CD23, CD38, CD40, CD45 and IgM, wherein the antibodies of each pattern are labeled with fluorescent dyes.

2. The staining kit of claim 1, wherein the T cell comprises CD3, CD4, CD25, CD45RO, CCR7 or any combination thereof; the B cell comprises CD10, CD19, CD21, CD127, IgG or any combination thereof; the NK cell comprises CD56; the monocyte comprises CD14; the regulatory cell comprises PD-1, PD-L1, FoxP3 or any combination thereof; and the dendritic cell comprises CD11c, HLA-DR or combination thereof.

3. A method of identifying characterized immune cell subsets of a disease, comprising steps of: (a) obtaining peripheral blood mononuclear cells (PBMCs) and/or white blood cells (WBCs) from a plurality of healthy controls and a plurality of patients having the disease, respectively; (b) staining the PBMCs and/or the WBCs of the healthy controls and the patients, respectively, by using the staining kit of claim 1, (c) performing data acquisition of fluorescent intensity of each antibody bound to the PBMCs and/or the WBCs of the healthy controls and the patients, respectively, by using flow cytometry; (d) identifying immune cell subsets in the PBMCs and/or the WBCs of the healthy controls and the patients, respectively, by using a pedigree method to obtain a dataset comprising data related to types of the immune cell subsets and proportions thereof; and (e) evaluating the dataset by using a machine learning software to obtain immune cell subsets of the patients distinguishable from those of the healthy controls as the characterized immune cell subsets of the disease.

4. The method of claim 3, wherein the step (e) further comprises the following steps performed by the machine learning software: (i) performing data preprocessing of the dataset; (ii) performing a feature selection from the preprocessed data by using a Boruta algorithm to obtain predetermined immune cell subsets of the disease as selected features; and (iii) applying data of the selected features to train machine learning models by at least one of a random forest (RF) algorithm, a logistic regression (LR) algorithm and a support vector machines (SVM) algorithm.

5. The method of claim 3, wherein the disease comprises a cancer, an immunological disease and an infectious disease.

6. The method of claim 5, wherein the cancer comprises nasopharyngeal carcinoma (NPC).

7. The method of claim 6, wherein the characterized immune cell subsets of NPC is selected from the group consisting of memory B cells, monocytes, T cells, na?ve CD4 ?? T cells, PD-1.sup.+CD4 T cells, PD-L1.sup.+CD4 T cells, PD-1.sup.+PD-L1.sup.+ monocytes, CD4 NKTreg cells, MHC II.sup.+ CD4 T cells and MHC II.sup.+ CD4 NKT cells.

8. A method of predicting the likelihood of nasopharyngeal carcinoma (NPC) in a subject in need thereof, comprising steps of: (a) staining peripheral blood mononuclear cells (PBMCs) from the subject by using the staining kit of claim 1; (b) performing data acquisition of fluorescent intensity of each antibody bound to characterized immune cell subsets of NPC by using flow cytometry to obtain a dataset comprising data related to types of the characterized immune cell subsets and proportions thereof; and (c) evaluating the dataset by using a machine learning software to predict whether the subject has nasopharyngeal carcinoma wherein the characterized immune cell subsets of NPC are elected from the group consisting of memory B cells, monocytes, T cells, na?ve CD4 ?? T cells, PD-1.sup.+CD4 T cells, PD-L1.sup.+CD4 T cells, PD-1.sup.+PD-L1.sup.+ monocytes, CD4 NKTreg cells, MHC II.sup.+ CD4 T cells and MHC II.sup.+ CD4 NKT cells.

9. The method of claim 8, wherein the step (c) further comprises the following steps performed by the machine learning software: (i) applying the hold-out set with the characterized immune cell subsets to test trained machine learning models; (ii) predicting the subject as nasopharyngeal carcinoma if a value of the predicted probability obtained from a RF algorithm or a LR algorithm is larger than a first threshold value, or a value of a decision function obtained from a SVM algorithm is larger than a second threshold value.

Description

BRIEF DESCRIPTION OF THE DRAWINGS

[0030] FIG. 1 illustrates a flow chart of identifying the characterized immune cell subsets of NPC.

[0031] FIGS. 2a-2k illustrate the filtrating processes to obtain immune cell subsets using a pedigree method, wherein FIGS. 2a-2c illustrate the pattern PT-67 pedigree; FIG. 2d illustrates the pattern PT-64 pedigree; FIG. 2e illustrates the pattern PT-65 pedigree; FIG. 2f illustrates the pattern PT-66 pedigree; FIG. 2g illustrates the pattern PT-68 pedigree; FIG. 2h illustrates the pattern PT-87 pedigree; FIG. 2i illustrates the pattern PT-83 pedigree; FIG. 2j illustrates the pattern PT-85 pedigree; and FIG. 2k illustrates the pattern PT-86 pedigree.

[0032] FIGS. 3A-3C illustrate the ROC results of the training set acquired from the machine learning method using the random forest (RF) algorithm, logistic regression (LR) algorithm, and support vector machines (SVM) algorithm, respectively.

[0033] FIGS. 4A-4C illustrate the SHAP results of the training set acquired from the machine learning method using the RF algorithm, the LR algorithm, and the SVM algorithm, respectively.

[0034] FIGS. 5A-5C illustrate the ROC results of the hold-out set acquired from the machine learning method using the RF algorithm, the LR algorithm, and the SVM algorithm, respectively.

[0035] FIGS. 6A-6C illustrate the SHAP results of the hold-out set acquired from the machine learning method using the RF algorithm, the LR algorithm, and the SVM algorithm, respectively.

DETAILED DESCRIPTION

Definitions

[0036] The term healthy control as used herein refers to a subject without a disease being studied but may have other conditions indirectly affecting outcome.

[0037] The term characterized immune cell subset as used herein refers to that a group of immune cell subsets having a comparative immune profiling between patients and healthy controls (HCs), such as amounts of the immune cell subsets in the patients significantly higher or lower than those in the HCs.

[0038] The term predicted probability as used as herein refers to the probability of the subject for each groups in the trained machine learning model.

[0039] The term decision function as used herein refers to a function that calculates the distance of the subject to the separating hyperplane of SVM classifier.

[0040] The term hold-out set as used herein refers to the dataset not used in a machine learning model training process.

EMBODIMENTS

[0041] Embodiment 1: A staining kit, including a first pattern including antibodies against T cell, B cell, NK cell, monocyte, regulatory cell, CD8, CD45, and CTLA4; a second pattern including antibodies against T cell, B cell, NK cell, monocyte, regulatory cell, dendritic cell, and CD45; a third pattern including antibodies against T cell, B cell, NK cell, monocyte, CD8, CD45, CD45RA, CD62L, CD197, CX3CR1 and TCR.sub.??; and a fourth pattern including antibodies against B cell, CD23, CD38, CD40, CD45 and IgM, wherein the antibodies of each pattern are labeled with fluorescent dyes.

[0042] Embodiment 2: The staining kit of embodiment 1, wherein the T cell includes CD3, CD4, CD25, CD45RO, CCR7 or any combination thereof; the B cell includes CD10, CD19, CD21, CD127, IgG or any combination thereof; the NK cell includes CD56; the monocyte includes CD14; the regulatory cell includes PD-1, PD-L1, FoxP3 or any combination thereof; and the dendritic cell includes CD11c, HLA-DR or combination thereof

[0043] Embodiment 3: The staining kit of embodiment 1 or 2, wherein the first pattern including antibodies against CD3, CD4, CD8, CD14, CD19, CD25, CD45, CD56, CTLA4, Foxp3 and PD-1; the second pattern including antibodies against CD3, CD4, CD11c, CD14, CD19, CD45, CD56, HLA-DR, PD-1 and PD-L1; the third pattern including antibodies against CD4, CD8, CD14, CD19, CD45, CD45RA, CD45RO, CD56, CD62L, CD197, CX3CR1 and TCR.sub.??; and the fourth pattern including antibodies against CD10, CD19, CD21, CD23, CD38, CD40, CD45, CD127, IgG and IgM, wherein the antibodies of each pattern are labeled with fluorescent dyes.

[0044] Embodiment 4: The staining kit of embodiment 3, wherein in the first pattern, the antibodies against CD3, CD4, CD8, CD14, CD25, CD45, CD56, CTLA4, Foxp3 and PD-1 are labeled with different fluorescent colors, and the antibodies against CD14 and CD19 are labeled with the same fluorescent color.

[0045] Embodiment 5: The staining kit of embodiment 3 or 4, wherein in the second pattern, the antibodies against CD3, CD4, CD11c, CD14, CD19, CD45, CD56, HLA-DR, PD-1 and PD-L1 are labeled with different fluorescent colors.

[0046] Embodiment 6: The staining kit of any one of embodiments 3 to 5, wherein in the third pattern, the antibodies against CD4, CD8, CD14, CD45, CD45RA, CD45RO, CD62L, CD197, CX3CR1 and TCR.sub.?? are labeled with different fluorescent colors, and the antibodies against CD14, CD19 and CD56 are labeled with the same fluorescent color.

[0047] Embodiment 7: The staining kit any one of embodiments 3 to 6, wherein in the fourth pattern, the antibodies against CD10, CD19, CD21, CD23, CD38, CD40, CD45, CD127, IgG and IgM are labeled with different fluorescent colors.

[0048] Embodiment 8: The staining kit of any one of embodiments 3 to 7, further including at least one of the following patterns: a fifth pattern including antibodies against CD3, CD4, CD8, CD14, CD19, CD25, CD45, CD56, CD69, PD-1, TCR.sub.?? and TCR.sub.??; a sixth pattern including antibodies against CD3, CD11b, CD11c, CD13, CD14, CD19, CD33, CD39, CD45, CD56, and HLA-DR; a seventh pattern including antibodies against CD3, CD4, CD8, CD14, CD19, CD27, CD28, CD45, CD56, PD-1, TCR.sub.?? and TCR.sub.??; an eighth pattern including antibodies against CD3, CD11b, CD14, CD16, CD19, CD45, CD56, CD64, CD66b, CD123, CD193, CD203c and Siglec-8; and a ninth pattern including antibodies against CD4, CD8, CD14, CD19, CD45, CD45RO, CD56, CX3CR1, CD197, LAG-3, TCR.sub.?? and TIM-3, wherein the antibodies of each pattern are labeled with fluorescent colors.

[0049] Embodiment 9: The staining kit of any one of embodiments 3 to 8, wherein in the fifth pattern, the antibodies against CD3, CD4, CD8, CD25, CD45, CD56, CD69, PD-1, TCR.sub.ap and TCR.sub.?? are labeled with different fluorescent colors, and the antibodies against CD3, CD14 and CD19 are labeled with the same fluorescent color.

[0050] Embodiment 10: The staining kit of any one of embodiments 3 to 9, wherein in the sixth pattern, the antibodies against CD3, CD11b, CD11c, CD13, CD14, CD33, CD39, CD45, and HLA-DR are labeled with different fluorescent colors, and the antibodies against CD3, CD19 and CD 56 are labeled with the same fluorescent color.

[0051] Embodiment 11: The staining kit of any one of embodiments 3 to 10, wherein in the seventh pattern, the antibodies against CD3, CD4, CD8, CD27, CD28, CD45, CD56, PD-1, TCR.sub.?? and TCR.sub.?? are labeled with different fluorescent colors, and the antibodies against CD3, CD14 and CD19 are labeled with the same fluorescent color.

[0052] Embodiment 12: The staining kit of any one of embodiments 3 to 11, wherein in the eighth pattern, the antibodies against CD3, CD11b, CD16, CD45, CD64, CD66b, CD123, CD193, CD203c and Siglec-8 are labeled with different fluorescent colors, and the antibodies against CD3, CD14, CD19 and CD56 are labeled with the same fluorescent color.

[0053] Embodiment 13: The staining kit of any one of embodiments 3 to 12, wherein in the ninth pattern, the antibodies against CD4, CD8, CD14, CD45, CD45RO, CX3CR1, CD197, LAG-3, TCR.sub.?? and TIM-3 are labeled with different fluorescent colors, and the antibodies against CD14, CD19 and CD56 are labeled with the same fluorescent color.

[0054] Embodiment 14: A method of identifying characterized immune cell subsets of a disease, including steps of: [0055] (a) obtaining peripheral blood mononuclear cells (PBMCs) and/or white blood cells (WBCs) from a plurality of healthy controls and a plurality of patients having the disease, respectively; [0056] (b) staining the PBMCs and/or the WBCs of the healthy controls and the patients, respectively, by using the staining kit of any one of embodiments 1 to 13; [0057] (c) performing data acquisition of fluorescent intensity of each antibody bound to the PBMCs and/or the WBCs of the healthy controls and the patients, respectively, by using flow cytometry; [0058] (d) identifying immune cell subsets in the PBMCs and/or the WBCs of the healthy controls and the patients, respectively, by using a pedigree method to obtain a dataset including data related to types of the immune cell subsets and proportions thereof; and [0059] (e) evaluating the dataset by using a machine learning software to obtain immune cell subsets of the patients distinguishable from those of the healthy controls as the characterized immune cell subsets of the disease.

[0060] Embodiment 15: The method of embodiment 14, wherein the step (e) further includes the following steps performed by the machine learning software: [0061] (i) performing data preprocessing of the dataset; [0062] (ii) performing a feature selection from the preprocessed data by using a Boruta algorithm to obtain predetermined immune cell subsets of the disease as selected features; and [0063] (iii) applying data of the selected features to train machine learning models by at least one of a random forest (RF) algorithm, a logistic regression (LR) algorithm and a support vector machines (SVM) algorithm.

[0064] Embodiment 16: The method of embodiment 14 or 15, wherein the disease includes a cancer, an immunological disease and an infectious disease.

[0065] Embodiment 17: The method of any one of embodiments 14 to 16, wherein the immunological disease includes, but are not limited to, idiopathic thrombocytopenic purpura, Guillain-Barre syndrome, myasthenia gravis, multiple sclerosis, optic neuritis, Kawasaki's disease, rheumatoid arthritis, systemic lupus erythematosus, atopic dermatitis, atherosclerosis, coronary artery disease, cardiomyopathy, reactive arthritis, Crohn's disease, ulcerative colitis, graft versus host disease, and type 1 diabetes mellitus

[0066] Embodiment 18: The method of any one of embodiments 14 to 16, wherein the infectious disease includes, but are not limited to, candidiasis, candidemia, aspergillosis, streptococcal pneumonia, streptococcal skin and oropharyngeal conditions, gram negative sepsis, tuberculosis, mononucleosis, influenza, respiratory illness caused by respiratory syncytial virus, human immunodeficiency virus, Hepatitis B, Hepatitis C, malaria, schistosomiasis, methicillin-resistant Staph aureus, vancomycin-resistant Enterococcus, carbapenem-resistant and carbapenemase-producing Enterobacteriaceae, mycobacterial disease, and trypanosomiasis.

[0067] Embodiment 19: The method of any one of embodiments 14 to 16, wherein the cancer includes, but are not limited to, brain cancer, bone cancer, skin cancer, esophageal cancer, stomach cancer, bile duct cancer, colorectal cancer, head and neck cancer, kidney cancer, fibrosarcoma, myxosarcoma, liposarcoma, chondrosarcoma, osteogenic sarcoma, chordoma, angiosarcoma, endotheliosarcoma, lymphangiosarcoma, lymphangioendotheliosarcoma, synovioma, mesothelioma, Ewing's tumor, leiomyosarcoma, rhabdomyosarcoma, colon carcinoma, pancreatic cancer, breast cancer, ovarian cancer, prostate cancer, squamous cell carcinoma, basal cell carcinoma, adenocarcinoma, sweat gland carcinoma, sebaceous gland carcinoma, papillary carcinoma, papillary adenocarcinomas, cystadenocarcinoma, medullary carcinoma, bronchogenic carcinoma, renal cell carcinoma, hepatoma, bile duct carcinoma, choriocarcinoma, seminoma, embryonal carcinoma, Wilms' tumor, cervical cancer, testicular tumor, lung carcinoma, small cell lung carcinoma, bladder carcinoma, epithelial carcinoma, glioma, astrocytoma, medulloblastoma, craniopharyngioma, ependymoma, pinealoma, hemangioblastoma, acoustic neuroma, oligodendroglioma, meningioma, melanoma, neuroblastoma, retinoblastoma, leukemia, lymphoma, multiple myeloma, Waldenstrom's macroglobulinemia, myelodysplastic disease, heavy chain disease, neuroendocrine tumors and Schwanoma.

[0068] Embodiment 20: The method of embodiment 19, wherein the head and neck cancer includes nasopharyngeal carcinoma (NPC).

[0069] Embodiment 21: The method of any one of embodiments 14 to 20, wherein the characterized immune cell subsets of NPC is selected from the group consisting of memory B cells, monocytes, T cells, na?ve CD4 ?? T cells, PD-1.sup.+CD4 T cells, PD-L1.sup.+CD4 T cells, PD-1.sup.+PD-L1.sup.+ monocytes, CD4 NKTreg cells, MHC II.sup.+ CD4 T cells and MHC II.sup.+ CD4 NKT cells.

[0070] Embodiment 22: A method of predicting the likelihood of nasopharyngeal carcinoma (NPC) in a subject in need thereof, including steps of: [0071] (a) staining peripheral blood mononuclear cells (PBMCs) from the subject by using the staining kit of any one of embodiments 1 to 13; [0072] (b) performing data acquisition of fluorescent intensity of each antibody bound to characterized immune cell subsets of NPC by using flow cytometry to obtain a dataset including data related to types of the characterized immune cell subsets and proportions thereof; and [0073] (c) evaluating the dataset by using a machine learning software to predict whether the subject has nasopharyngeal carcinoma, [0074] wherein the characterized immune cell subsets of NPC are elected from the group consisting of memory B cells, monocytes, T cells, na?ve CD4 ?? T cells, PD-1.sup.+CD4 T cells, PD-L1.sup.+CD4 T cells, PD-1.sup.+PD-L1.sup.+ monocytes, CD4 NKTreg cells, MHC II.sup.+ CD4 T cells and MHC II.sup.+ CD4 NKT cells.

[0075] Embodiment 23: The method of embodiment 22, wherein the step (c) further includes the following steps performed by the machine learning software: [0076] (i) applying the hold-out set with the characterized immune cell subsets to test trained machine learning models; [0077] (ii) predicting the subject as nasopharyngeal carcinoma if a value of the predicted probability obtained from a RF algorithm or a LR algorithm is larger than a first threshold value, or a value of a decision function obtained from a SVM algorithm is larger than a second threshold value.

[0078] Embodiment 24: The method of embodiment 22 or 23, wherein the first threshold value of the predicted probability is equal 0.5, and the second threshold value of the decision function is equal to 0.

Example 1: Identifying Characterized Immune Cell Subsets of NPC

[0079] Please see FIG. 1 for a flow chart of identifying the characterized immune cell subsets of NPC. The related steps thereof are described in detail below.

[0080] NPCs and HCs

[0081] For NPCs, eligible criteria included: older than 20 years, heavier than 50 kilograms, newly diagnosed according to the practical guideline, no history of severe infectious diseases such as human immunodeficiency virus and syphilis, no radiotherapy, chemotherapy, or autoimmune treatment received within one month. Patients with central nerve system metastasis, pulmonary fibrosis or fibrotic pneumonia, and pulmonary edema or ascites fitted Common Terminology Criteria for Adverse Events (CTCAE) level 2 or higher were ineligible. Subjects enrolled in HCs had the same eligibility criteria as NPCs except for NPC diagnosed. The outcome of this trial relied on the comparison of the typing and proportion of immune cell subsets between NPCs and the HCs. Therefore, the clinician drew 20 mL of anticoagulated peripheral blood from the subjects for PBMCs and granulocyte isolation and identification during a consultation. The study design of this clinical trial complied with the Declaration of Helsinki, and the Institutional Review Board of Far Eastern Memorial Hospital approved the protocol of this clinical trial (Approval code 108170-E).

[0082] Reagents and Antibodies

[0083] All reagents and antibodies used in this study were listed in Tables 1 and 2. Reagents were from Cytiva (Marlborough, MA, USA), Lonza (Basel, Switzerland), and Sigma-Aldrich (Merck KGaA, Darmstadt, Germany). Antibodies were all from Beckman-Coulter (Brea, CA, USA), Biolegend (San Diego, CA, USA), and Thermo-Fisher (Waltham, MA, USA).

TABLE-US-00001 TABLE 1 Reagents Name Manufacture Catalogue number For PBMCs and granulocyte isolation Ficoll-Paque? PREMIUM Cytiva 17544202 medium 1.077 g/mL Phosphate buffer saline Lonza BE17-516F ACK lysis buffer Biolegend 420301 For immunostaining Bovine serum albumin Sigma-Aldrich A7030 Sodium azide Sigma-Aldrich S2002 Foxp3/Transcription Factor Thermo-Fisher 00-5523-00 Staining Buffer Set

TABLE-US-00002 TABLE 2 Antibodies and fluorescent dyes conjugated therewith Catalogue Target Conjugation Host Manufacture number CCR7 PE/Cy7 Mouse Biolegend 353226 (also called CD197) CD3 APC?AF750 Mouse Beckman A66329 Coulter CD3 KO Mouse Beckman B00068 Coulter CD4 APC?AF700 Mouse Beckman B10824 Coulter CD4 PE?Cy7 Mouse Beckman 6607101 Coulter CD8 KO Mouse Beckman B00067 Coulter CD8 PB Mouse Biolegend 301023 CD10 PE/Cy7 Mouse Biolegend 312214 CD11b PE/Cy7 Mouse Beckman A54822 Coulter CD11c APC Mouse Biolegend 301614 CD13 PerCP/Cy5.5 Mouse Biolegend 301714 CD14 APC?AF750 Mouse Beckman A86052 Coulter CD14 PB Mouse Beckman B00846 Coulter CD14 PC5.5 Mouse Beckman A70204 Coulter CD16 KC Mouse Beckman B00069 Coulter CD19 APC?AF750 Mouse Beckman A78838 Coulter CD21 APC Mouse Biolegend 354906 CD23 PE Mouse Biolegend 338508 CD25 PE Mouse Biolegend 302606 CD25 BB515 Mouse BD 564467 CD27 PB Mouse Biolegend 356414 CD28 PE/Cy5 Mouse Biolegend 302910 CD33 FITC Mouse Beckman IM1135U Coulter CD38 PerCP/Cy5.5 Mouse Biolegend 356614 CD39 PE Mouse Biolegend 328208 CD40 FITC Mouse Biolegend 334306 CD45 ECD Mouse Beckman A07784 Coulter CD45RA PerCP/Cy5.5 Mouse Biolegend 304121 CD45RO APC Mouse Biolegend 304210 CD56 APC?AF700 Mouse Beckman B10822 Coulter CD56 APC/Cy7 Mouse Biolegend 318332 CD62L PB Mouse Biolegend 304825 CD64 A700 Mouse Biolegend 305040 CD66b PB Mouse Biolegend 305112 CD69 PB Mouse Biolegend 310919 CD123 PE Mouse Biolegend 306006 CD127 BV421 Mouse Biolegend 351310 CD193 FITC Mouse Biolegend 310720 CD203c APC Mouse Biolegend 354906 CTLA4 PE Mouse Biolegend 349906 CX3CR1 PE Mouse Biolegend 341604 Foxp3 APC Mouse Thermo-Fisher 17-4777- 42 HLA?DR PB Mouse Beckman A74781 (also called Coulter MHC II) HLA?DR KO Mouse Beckman B00070 (also called Coulter MHC II) IgG BV510 Mouse BD 563247 IgM A700 Mouse Biolegend 314538 PD-1 A488 Mouse Biolegend 329936 PD-1 PE Mouse Biolegend 329906 PD-1 PerCP/Cy5.5 Mouse Biolegend 329914 PD-L1 PE Mouse Biolegend 329706 Siglec-8 PerCP/Cy5.5 Mouse Biolegend 347108 TCR.sub.?? FITC Mouse Biolegend 306705 TCR.sub.?? APC Mouse Biolegend 331212 LAG-3 PerCP/Cy5.5 Mouse Biolegend 369312 TIM-3 PB Mouse Biolegend 345042

[0084] PBMCs and Granulocyte Isolation and Immunostaining

[0085] EDTA-anti coagulated peripheral blood (abbreviated as whole blood in the following) was aliquoted into two in which one was for PBMCs isolation and the other was for granulocyte isolation. For PBMCs isolation, whole blood mixed with an aliquot of PBS was loaded into Ficoll-preloaded centrifuged tubes and centrifuged with 930?g (X-15R, Beckman-Coulter) for 30 minutes at room temperature. PBMCs were collected from the buffy coat and washed by PBS followed by being centrifuged with 750?g for 7 minutes, and then re-suspended for stained buffer (0.5% bovine serum albumin/PBS with 0.02% (w/v) sodium azide) and went through immunostaining.

[0086] The ammonium-chloride-potassium (ACK) lysis method was applied for the lysis of red blood cells (RBCs) in granulocyte isolation based on the protocol in the manual of the lysis buffer. Briefly, one part of whole blood mixed with twenty part of ACK lysis buffer followed by gently shaking at room temperature for 10 minutes. Then, the mixture was centrifuged with 400?g for 5 minutes to eliminate the lysed erythrocyte. The remaining white blood cells (WBCs) was washed by PBS and followed by immunostaining.

[0087] All PBMCs were stained with cell surface markers and a part of them was further stained with intracellular cell markers. Each pattern see the cell staining pattern page. All staining procedures were kept in dark. All staining procedure were kept in dark. For surface marker staining, PBMCs were directly incubated with desired antibodies labeled with fluorescent dyes in the staining kit (see Tables 2 and 3) for 10 minutes at 4? C. For intracellular marker staining, a part of surface marker labeled PBMCs was fixed and permeabilized using Foxp3/Transcription Factor Staining Buffer Set (eBioscience?) with recommended protocol from manual. Later, permeabilized PBMCs were stained with CTLA4 or Foxp3 for 30 minutes at room temperature. Afterward, stained PBMCs were washed with staining buffer once and followed by analysis by flow cytometer.

TABLE-US-00003 TABLE 3 Staining kit Codes of Patterns/ Dyes PT?64 PT-65 PT-66 PT-67 PT-68 FL1 FITC-TCR.sub.?? BB515-CD25 FITC-CD33 FITC-PD-1 FITC-TCR.sub.?? FL2 PE-CD25 PE-CTLA4 PE-CD39 PE-PD-L1 PE-PD-1 FL3 ECD-CD45 ECD-CD45 ECD-CD45 ECD-CD45 ECD-CD45 FL4 PerCP/Cy5.5 PerCP/Cy5.5 PerCP/Cy5.5- PerCP/Cy5.5- PE/Cy5- -PD-1 -PD-1 CD13 CD14 CD28 FL5 PE/Cy7-CD4 PE/Cy7-CD4 PE/Cy7-CD11b PE/Cy7-CD4 PE/Cy7-CD4 FL6 APC-TCR.sub.?? APC-Foxp3 APC-CD11c APC-CD11c APC-TCR.sub.?? FL7 APC-AF700- APC-AF700- APC-AF700- APC-AF700- CD56 CD56 CD56 CD56 FL8 APC-AF750- APC-AF750- APC-AF750- CD3 CD3 CD3 APC/Cy7-CD56 APC-AF750- APC-AF750- APC-AF750- CD14 CD14 CD14 APC-AF750- APC-AF750- APC-AF750- APC-AF750- APC-AF750- CD19 CD19 CD19 CD19 CD19 FL9 PB-CD69 PB-CD8 PB-CD14 PB-HLA-DR PB-CD27 FL10 KO-CD8 KO-CD3 KO-HLA-DR KO-CD3 KO-CD3 Codes of Patterns/ Dyes PT-83 PT-85 PT-86 PT-87 FL1 FITC-CD193 FITC-TCR.sub.?? FITC-TCR.sub.?? FITC-CD40 FL2 PE-CD123 PE-CX3CR1 PE-CX3CR1 PE-CD23 FL3 ECD-CD45 ECD-CD45 ECD-CD45 ECD-CD45 FL4 PerCP/Cy5.5- PerCP/Cy5.5- PerCP/Cy5.5- PerCP/Cy5.5- Siglec-8 CD45RA LAG-3 CD38 FL5 PE/Cy7- PE/Cy7- PE/Cy7-CD197 PE/Cy7-CD10 CD11b CD197 FL6 APC- APC- APC- APC- CD203c CD45RO CD45RO CD21 FL7 A700-CD64 APC-AF700- APC-AF700- A700-IgM CD4 CD4 FL8 APC-AF750- CD3 APC/Cy7- APC/Cy7- APC/Cy7-CD56 CD56 CD56 APC-AF750- APC-AF750- APC-AF750- CD14 CD14 CD14 APC-AF750- APC-AF750- APC-AF750- APC-AF750- CD19 CD19 CD19 CD19 FL9 PB-CD66b PB-CD62L PB-TIM-3 PB-CD127 FL10 KO-CD16 KO-CD8 KO-CD8 BV510-IgG

[0088] Data Acquisition and Data Modulation

[0089] For data acquisition, the fluorescent intensity of PBMCs was measured by flow cytometer (Navios, Beckman Coulter), and raw data were collected by Kaluza analysis software V1.3 (Beckman Coulter). Immune cell subsets were defined by a pedigree method using filtration with two-marker sets (parameter of X-axis and Y-axis). The definition of cell subsets were listed in Table 4. As shown in FIGS. 2a-2k, the detailed filtrating processes were performed based on Table 4 so as to obtain the raw dataset related to at least 82 types of immune cell subsets and proportions thereof.

TABLE-US-00004 TABLE 4 Definition of immune cell subsets with markers Name of cell subsets Markers Granulocytes Neutrophil CD3.sup.?CD14.sup.?CD19.sup.?CD56.sup.?CD11b.sup.+CD16.sup.+CD64.sup.?CD66b.sup.+CD123.sup.?CD193.sup.? Eosinophil CD3.sup.?CD14.sup.?CD19.sup.?CD56.sup.?CD11b.sup.+CD16.sup.?CD66b.sup.+CD123.sup.+CD193.sup.+ Basophil CD3.sup.?CD14.sup.?CD19.sup.?CD56.sup.?CD11b.sup.+CD16.sup.?CD66b.sup.?CD123.sup.+CD193.sup.+ NK cell NK cell CD3.sup.?CD14.sup.?CD19.sup.?CD56.sup.+ CD8 NK cell CD3.sup.?CD14.sup.?CD19.sup.?CD56.sup.+CD4.sup.?CD8.sup.+ DN NK cell CD3.sup.?CD14.sup.?CD19.sup.?CD56.sup.+CD4.sup.?CD8.sup.? NKT cell NKT cell CD3.sup.+CD14.sup.?CD19.sup.?CD56.sup.+ CD4 NKT cell CD3.sup.+CD14.sup.?CD19.sup.?CD56.sup.+CD4.sup.+CD8.sup.? CD8 NKT cell CD3.sup.+CD14.sup.?CD19.sup.?CD56.sup.+CD4.sup.?CD8.sup.+ Dendritic cell DC CD3.sup.?CD14.sup.?CD19.sup.?CD56.sup.?CD11c.sup.+ MHC II.sup.+DC CD3.sup.?CD14.sup.?CD19.sup.?CD56.sup.?CD11c.sup.+MHC II.sup.+ B cell B cell CD3.sup.?CD14.sup.?CD19.sup.+CD56.sup.? Long lived plasma cell CD3.sup.?CD14.sup.?CD19.sup.+CD56.sup.?CD21.sup.+CD127.sup.?CD10.sup.+IgG.sup.+IgM Germinal center B cell CD3.sup.?CD14.sup.?CD19.sup.+CD56.sup.?CD21.sup.?CD127.sup.?CD10.sup.+IgG.sup.+IgM.sup.? Memory B cell CD3.sup.?CD14.sup.?CD19.sup.+CD56.sup.?CD21.sup.+CD127.sup.?CD10.sup.?CD23.sup.?CD38.sup.+IgG.sup.+IgM.sup.? Follicular B cell CD3.sup.?CD14.sup.?CD19.sup.+CD56.sup.?CD21.sup.+CD127.sup.?CD10.sup.?CD23.sup.+CD38.sup.+IgG.sup.+IgM.sup.dim Short lived plasma cell CD3.sup.?CD14.sup.?CD19.sup.+CD56.sup.?CD21.sup.+CD127.sup.?CD10.sup.?CD23.sup.?CD38.sup.+IgG.sup.+IgM.sup.dim Marginal Zone B cell CD3.sup.?CD14.sup.?CD19.sup.+CD56.sup.?CD21.sup.+CD127.sup.?CD10.sup.?CD23.sup.?CD38.sup.+IgG.sup.+IgM.sup.hi Transitional B cell CD3.sup.?CD14.sup.?CD19.sup.+CD56.sup.?CD21.sup.?CD127.sup.?CD10.sup.+CD23.sup.?CD38.sup.+IgG.sup.+IgM.sup.hi MHC II.sup.+ B cell CD3.sup.?CD14.sup.?CD19.sup.+CD56.sup.?MHC II.sup.+ Monocyte Monocyte CD3.sup.?CD14.sup.+CD19.sup.+CD56.sup.dim MHC II.sup.+ monocyte CD3.sup.?CD14.sup.+CD19.sup.+CD56.sup.dimMHC II.sup.+ T lymphocyte Total T cell CD3.sup.+CD14.sup.?CD19.sup.?CD56.sup.? CD4 a? T cell CD3.sup.+CD14.sup.?CD19.sup.?CD56.sup.?TCR.sub.??.sup.+TCR.sub.??.sup.?CD4.sup.+CD8.sup.? Terminal CD4 a? T cell CD3.sup.+CD14.sup.?CD19.sup.?CD56.sup.?TCR.sub.??.sup.+TCR.sub.??.sup.?CD4.sup.+CD8.sup.?CD25.sup.?CD69.sup.+ Immediately activated CD3.sup.+CD14.sup.?CD19.sup.?CD56.sup.?TCR.sub.??.sup.+TCR.sub.??.sup.?CD4.sup.+CD8.sup.?CD27.sup.?CD28.sup.? CD4 a? T cell Naive CD4 a? T cell CD3.sup.+CD14.sup.?CD19.sup.?CD56.sup.?TCR.sub.??.sup.+TCR.sub.??.sup.?CD4.sup.+CD8.sup.?CD45RO.sup.?CCR7.sup.+ Effector CD4 a? T cell CD3.sup.+CD14.sup.?CD19.sup.?CD56.sup.?TCR.sub.??.sup.+TCR.sub.??.sup.?CD4.sup.+CD8.sup.?CD45RO.sup.?CCR7.sup.? Exhausted effector CD3.sup.+CD14.sup.?CD19.sup.?CD56.sup.?TCR.sub.??.sup.+TCR.sub.??.sup.?CD4.sup.+CD8.sup.?CD45RO.sup.?CCR7.sup.?TIM.sup.? CD4 a? T cell 3.sup.+LAG?3.sup.+ Central memory CD4 CD3.sup.+CD14.sup.?CD19.sup.?CD56.sup.?TCR.sub.??.sup.+TCR.sub.??.sup.?CD4.sup.+CD8.sup.?CD45RO.sup.+CCR7.sup.+ a? T cell Exhausted central CD3.sup.+CD14.sup.?CD19.sup.?CD56.sup.?TCR.sub.??.sup.+TCR.sub.??.sup.?CD4.sup.+CD8.sup.?CD45RO.sup.+CCR7.sup.+TIM.sup.? memory CD4 a? T cell 3.sup.+LAG-3.sup.+ Effector memory CD4 CD3.sup.+CD14.sup.?CD19.sup.?CD56.sup.?TCR.sub.??.sup.+TCR.sub.??.sup.?CD4.sup.+CD8.sup.?CD45RO.sup.+CCR7.sup.? a? T cell Exhausted effector CD3.sup.+CD14.sup.?CD19.sup.?CD56.sup.?TCR.sub.??.sup.+TCR.sub.??.sup.?CD4.sup.+CD8.sup.?CD45RO.sup.+CCR7.sup.?TIM.sup.? memory CD4 a? T cell 3.sup.+LAG-3.sup.+ CD8 a? T cell CD3.sup.+CD14.sup.?CD19.sup.?CD56.sup.?TCR.sub.??.sup.+TCR.sub.??.sup.?CD4.sup.?CD8.sup.+ Terminal CD8 a? T cell CD3.sup.+CD14.sup.?CD19.sup.?CD56.sup.?TCR.sub.??.sup.+TCR.sub.??.sup.?CD4.sup.?CD8.sup.+CD25.sup.?CD69.sup.+ Immediately activated CD3.sup.+CD14.sup.?CD19.sup.?CD56.sup.?TCR.sub.??.sup.+TCR.sub.??.sup.?CD4.sup.?CD8.sup.+CD27.sup.?CD28.sup.? CD8 a? T cell Naive CD8 a? T cell CD3.sup.+CD14.sup.?CD19.sup.?CD56.sup.?TCR.sub.??.sup.+TCR.sub.??.sup.?CD4.sup.?CD8.sup.+CD45RO.sup.?CCR7.sup.+ Effector CD8 a? T cell CD3.sup.+CD14.sup.?CD19.sup.?CD56.sup.?TCR.sub.??.sup.+TCR.sub.??.sup.?CD4.sup.?CD8.sup.+CD45RO.sup.?CCR7.sup.? Exhausted effector CD3.sup.+CD14.sup.?CD19.sup.?CD56.sup.?TCR.sub.??.sup.+TCR.sub.??.sup.?CD4.sup.?CD8.sup.+CD45RO.sup.?CCR7.sup.?TIM.sup.? CD8 a? T cell 3.sup.+LAG-3.sup.+ Central memory CD8 CD3.sup.+CD14.sup.?CD19.sup.?CD56.sup.?TCR.sub.??.sup.+TCR.sub.??.sup.?CD4.sup.?CD8.sup.+CD45RO.sup.+CCR7.sup.+ a? T cell Exhausted central CD3.sup.+CD14.sup.?CD19.sup.?CD56.sup.?TCR.sub.??.sup.+TCR.sub.??.sup.?CD4.sup.?CD8.sup.+CD45RO.sup.+CCR7.sup.+TIM.sup.? memory CD8 a? T cell 3.sup.+LAG-3.sup.+ Effector memory CD8 CD3.sup.+CD14.sup.?CD19.sup.?CD56.sup.?TCR.sub.??.sup.+TCR.sub.??.sup.?CD4.sup.?CD8.sup.+CD45RO.sup.+CCR7.sup.? a? T cell Exhausted effector CD3.sup.+CD14.sup.?CD19.sup.?CD56.sup.?TCR.sub.??.sup.+TCR.sub.??.sup.?CD4.sup.?CD8.sup.+CD45RO.sup.+CCR7.sup.?TIM.sup.? memory CD8 a? T cell 3.sup.+LAG-3.sup.+ CD8 y& T cell CD3.sup.+CD14.sup.?CD19.sup.?CD56.sup.?TCR.sub.??.sup.?TCR.sub.??.sup.+CD4.sup.?CD8.sup.+ DN y& T cell CD3.sup.+CD14.sup.?CD19.sup.?CD56.sup.?TCR.sub.??.sup.?TCR.sub.??.sup.+CD4.sup.?CD8.sup.? PD-1.sup.+ cells PD-1.sup.+ NK cell CD3.sup.?CD14.sup.?CD19.sup.?CD56.sup.+PD-1.sup.+PD-L1.sup.? PD-1.sup.+ CD4 NKT cell CD3.sup.+CD14.sup.?CD19.sup.?CD56.sup.+CD4.sup.+CD8.sup.?PD-1.sup.+PD-L1.sup.? PD-1.sup.+ CD8 NKT cell CD3.sup.+CD14.sup.?CD19.sup.?CD56.sup.+ CD4.sup.?CD8.sup.+PD-1.sup.+PD-L1.sup.? PD-1.sup.+ DC CD3.sup.?CD14.sup.?CD19.sup.?CD56.sup.?CD11c.sup.+PD-1.sup.+PD-L1.sup.? PD-1.sup.+ monocyte CD3.sup.?CD14.sup.+CD19.sup.?CD56.sup.dimPD.sup.?1.sup.+PD-L1.sup.? PD-1.sup.+ B cell CD3.sup.?CD14.sup.?CD19.sup.+CD56.sup.?PD-1.sup.+PD-L1.sup.? PD-1.sup.+ CD4 T cell CD3.sup.+CD14.sup.?CD19.sup.?CD56.sup.?CD4.sup.+CD8.sup.?PD-1+PD-L1.sup.? PD-1.sup.+ CD8 T cell CD3.sup.+CD14.sup.?CD19.sup.?CD56.sup.?CD4.sup.?CD8.sup.+PD-1+PD-L1.sup.? PD-L1.sup.+ cells PD-L1.sup.+ NK cell CD3.sup.?CD14.sup.?CD19.sup.?CD56.sup.+PD-1.sup.?PD-L1.sup.+ PD-L1.sup.+ CD4 NKT cell CD3.sup.+CD14.sup.?CD19.sup.?CD56.sup.+CD4.sup.+CD8.sup.?PD-1.sup.?PD-L1.sup.+ PD-L1.sup.+ CD8 NKT cell CD3.sup.+CD14.sup.?CD19.sup.?CD56.sup.+ CD4.sup.?CD8.sup.+PD-1.sup.?PD-L1.sup.+ PD-L1.sup.+ DC CD3.sup.?CD14.sup.?CD19.sup.?CD56.sup.?CD11c.sup.+PD-1.sup.?PD-L1.sup.+ PD-L1.sup.+ monocyte CD3.sup.?CD14.sup.+CD19.sup.?CD56.sup.dimPD-1.sup.?PD-L1.sup.+ PD-L1.sup.+ B cell CD3.sup.?CD14.sup.?CD19.sup.+CD56.sup.?PD-1.sup.?PD-L1.sup.+ PD-L1.sup.+ CD4 T cell CD3.sup.+CD14.sup.?CD19.sup.?CD56.sup.?CD4.sup.+CD8.sup.?PD-1.sup.?PD-L1.sup.+ PD-L1.sup.+ CD8 T cell CD3.sup.+CD14.sup.?CD19.sup.?CD56.sup.?CD4.sup.?CD8.sup.+PD-1.sup.?PD-L1.sup.+ PD-1.sup.+ PD-L1.sup.+ cells PD-1.sup.+ PD-L1.sup.+ NK cell CD3.sup.?CD14.sup.?CD19.sup.?CD56.sup.+PD-1.sup.+PD-L1.sup.+ PD-1.sup.+ PD-L1.sup.+ CD4 CD3.sup.+CD14.sup.?CD19.sup.?CD56.sup.+CD4.sup.+CD8.sup.?PD-1.sup.+PD-L1.sup.+ NKT cell PD-1.sup.+ PD-L1.sup.+ CD8 CD3.sup.+CD14.sup.?CD19.sup.?CD56.sup.+ CD4.sup.?CD8.sup.+PD-1.sup.+PD-L1.sup.+ NKT cell PD-1.sup.+ PD-L1.sup.+ DC CD3.sup.?CD14.sup.?CD19.sup.?CD56.sup.?CD11c.sup.+PD-1.sup.+PD-L1.sup.+ PD-1.sup.+ PD-L1.sup.+ CD3.sup.?CD14.sup.+CD19.sup.?CD56.sup.dimPD-1.sup.+PD-L1.sup.+ monocyte PD-1.sup.+ PD-L1.sup.+ B cell CD3.sup.?CD14.sup.?CD19.sup.+CD56.sup.?PD-1.sup.+PD-L1.sup.+ PD-1.sup.+ PD-L1.sup.+ CD4 T CD3.sup.+CD14.sup.?CD19.sup.?CD56.sup.?CD4.sup.+CD8.sup.?PD-1.sup.+PD-L1.sup.+ cell PD-1.sup.+ PD-L1.sup.+ CD8 T CD3.sup.+CD14.sup.?CD19.sup.?CD56.sup.?CD4.sup.?CD8.sup.+PD-1.sup.+PD-L1.sup.+ cell Regulatory cells CD4 Treg cell CD3.sup.+CD14.sup.?CD19.sup.?CD56.sup.?CD4.sup.+CD8.sup.?FoxP3.sup.+CD25.sup.+ CD8 Treg cell CD3.sup.+CD14.sup.?CD19.sup.?CD56.sup.?CD4.sup.?CD8.sup.+FoxP3.sup.+CD25.sup.+ CD8 NKreg cell CD3.sup.?CD14.sup.?CD19.sup.?CD56.sup.+CD4.sup.?CD8.sup.+FoxP3.sup.+CD25.sup.+ DN NKreg cell CD3.sup.?CD14.sup.?CD19.sup.?CD56.sup.+CD4.sup.?CD8.sup.?FoxP3.sup.+CD25.sup.+ CD4 NKreg cell CD3.sup.+CD14.sup.?CD19.sup.?CD56.sup.+CD4.sup.+CD8.sup.?FoxP3.sup.+CD25.sup.+ CD8 NKreg cell CD3.sup.+CD14.sup.?CD19.sup.?CD56.sup.+CD4.sup.?CD8.sup.+FoxP3.sup.+CD25.sup.+ MHC II.sup.? MDSC CD3.sup.?CD14.sup.+CD19.sup.?CD56.sup.?CD11b.sup.+MHC II.sup.? MHC II.sup.dim MDSC CD3.sup.?CD14.sup.+CD19.sup.?CD56.sup.?CD11b.sup.+MHC II.sup.dim MHC II.sup.+ NK cell CD3.sup.?CD14.sup.?CD19.sup.?CD56.sup.+MHC II.sup.+ MHC II.sup.+ CD4 NKT cell CD3.sup.+CD14.sup.?CD19.sup.?CD56.sup.+CD4.sup.+CD8.sup.?MHC II.sup.+ MHC II.sup.+ CD8 NKT cell CD3.sup.+CD14.sup.?CD19.sup.?CD56.sup.+CD4.sup.?CD8.sup.+MHC II.sup.+ MHC II.sup.+ CD4 T cell CD3.sup.+CD14.sup.?CD19.sup.?CD56.sup.?CD4.sup.+CD8.sup.?MHC II.sup.+ MHC II.sup.+ CD8 T cell CD3.sup.+CD14.sup.?CD19.sup.?CD56.sup.?CD4.sup.?CD8.sup.+MHC II.sup.+

[0090] Machine Learning with Python Program

[0091] The raw dataset described above consisted of HC (n=34) and NPC (n=15) subjects. Data preprocessing was performed by the following steps. First, the target labels were converted to the numerical value 0 for HC and the numerical value 1 for NPC. Since one of the NPC subjects had 7 missing values of the pattern PT-87, missing values imputation was applied based on the mean of the other features of NPCs (PT-87). 82 types of immune cell subsets were reserved for each subject after data preprocessing. The hold-out set consisted of some HC subjects (n=20), which were split from the 34 HC subjects, and NPC subjects (n=10), which were based on the percentile and mean of the original 15 NPC subjects. The remaining HC subjects (n=14) and the original NPC subjects (n=15) were used as the training set. Feature selection in the training set was performed using the Boruta algorithm, which is a wrapper-based technique based on the random forest classification algorithm. Boruta compared the Z-scores of the shuffled shadow features and the original features to determine feature importance in every iteration. After the predefined iterations, predetermined immune cell subsets of the disease as selected features were obtained, which are more significantly relevant to classification than randomly permuted features. The selected features of the present example are shown in Table 5. The training set with the selected features was applied to train the models using three different types of machine learning (ML) algorithms. Random Forest (RF), Logistic Regression (LR), and Support Vector Machines (SVM) were used to classify flow cytometry data from 2 classes of HC and NPC subjects. To minimize the impact of the feature with a relatively higher magnitude on the distance calculation, the Min-Max scaling was applied for SVM to ensure that every feature had a similar effect when the classifier constructed the hyperplane. The Min-Max scaling is a normalization technique that transforms the minimal feature value to 0 and the maximal feature value to 1. The discriminative ability of the models was then evaluated by the area under curve (AUC) of the receiver operating characteristic (ROC) curve. The ROC curve is often used to compare the model performance in a clinical classification problem. It shows the relation of the true positive rate (sensitivity) against the false positive rate (1-specificity) for each possibility threshold. The better the discriminative ability of the model, the closer the ROC curve is to the upper left corner of the plot. Finally, the discriminative ability of the models was quantified by computing the area under the ROC curve using the trapezoidal rule to obtain the AUC results. The ROC curves and the AUC results of the training set were visualized to compare the model performance. The plots are shown in FIGS. 3A-3C. The Shapley Additive exPlanations (SHAP) was applied to explain the model by computing the contribution of each selected feature to prediction. The SHAP summary plot was depicted to visualize the ranking of feature importance and the value of the feature per subject with the SHAP values. The color of the data point in each feature represents a high or a low feature value, in which each data point represents one subject. Red indicates high feature value, and blue indicates low feature value. The y-axis of the plot is the feature importance ranking of the selected features, and the x-axis is the SHAP value range. According to the trained model, the higher the SHAP value, the higher the risk of NPC. The summary plots of the training set are shown in FIGS. 4A-4C.

TABLE-US-00005 TABLE 5 Selected Features via Boruta algorithm Selected features Selected features Monocyte MHC II.sup.+ CD4 NKT Na?ve CD4 ?? T CD4 NKTreg PD-1.sup.+PD-L1.sup.+ monocyte PD-1.sup.+ CD4 T PD-1.sup.+CD4 T Memory B MHC II.sup.+ CD4 T T cell

Example 2: Predicting Likelihood of NPC in Subject by Machine Learning with Python Program

[0092] The hold-out set consisted of HC (n=20) and pseudo NPC (n=10) based on the percentile and mean of the original 15 NPC subjects. 82 types of immune cell subsets were reserved for each subject. For each subject, 10 selected features shown in Table 5 were used.

[0093] The hold-out set with the selected features was applied to test the trained models of three different ML algorithms (RF, LR, and SVM). The trained models were used to classify flow cytometry data from 2 classes of HC and NPC subjects.

[0094] For SVM, the Min-Max scaling range obtained from the training process was applied to the hold-out set to ensure that there is no data leakage and that every feature had a similar effect when the classifier constructed the hyperplane.

[0095] The sensitivity and specificity of the trained models were then tested using the hold-out set. If the predicted probability of the trained RF or LR model was greater than 0.5, the model predicted the subject as NPC. If the decision function of the trained SVM model was greater than 0, the model predicted the subject as NPC. The prediction results of the hold-out set are shown in Table 6.

TABLE-US-00006 TABLE 6 Model performance- Sensitivity and Specificity of the hold-out set Sensitivity and Specificity of the hold-out set (%) Algorithm HCs (n = 20) NPCs (n = 10) Random forest 80.0 100.0 Logistic regression 90.0 100.0 Support vector 80.0 100.0 machines

[0096] Finally, the AUC of the ROC curve was used to evaluate the discriminative ability of the models. The ROC curve is often used to compare the model performance in a clinical classification problem. It shows the relation of the true positive rate (sensitivity) against the false positive rate (1-specificity) for each possibility threshold. The better the discriminative ability of the model, the closer the ROC curve is to the upper left corner of the plot.

[0097] After the ROC curve was formed, the discriminative ability of the models was quantified by computing the area under the ROC curve using the trapezoidal rule to obtain the AUC results. The ROC curves and the AUC results of the hold-out set were visualized to compare the model performance. The plots are shown in FIGS. 5A-5C.

[0098] The SHAP method was applied to explain the model by computing the contribution of each selected feature to prediction. The SHAP summary plot was depicted to visualize the ranking of feature importance and the value of the feature per subject with the SHAP values. The color of the data point (subject) in each feature represents a high or a low feature value, in which each data point represents one subject. Red indicates high feature value, and blue indicates low feature value. The y-axis of the plot is the feature importance ranking of the selected features, and the x-axis is the SHAP value range. According to the trained model, the higher the SHAP value, the higher the risk of NPC. The summary plots of the hold-out set were shown in FIGS. 6A-6C.

[0099] In summary, the present invention not only can use to diagnosis a disease, such as NPC, but also can provide the prediction about immunotherapy based on states of PD-L1, PD-1 and T cells in the 10 immune cell subsets selected by said machine learning. For example, a subject can be administrated with Atezolizumab for treatment while an amount of PD-L1 expression of immune cells increases; can be administrated with Nivolumab or Pembrolizumab for treatment while an amount of PD-1 expression of immune cells increases; or can be supplemented with immune cells such as NK, DC, Cytokine-induced Killer (CIK), and T cells for treatment while T cells decreases.

[0100] Unless defined otherwise, all technical and scientific terms and any acronyms used herein have the same meanings as commonly understood by one of ordinary skill in the art in the field of this invention. Although any compositions, methods, kits, and means for communicating information similar or equivalent to those described herein can be used to practice this invention, the preferred compositions, methods, kits, and means for communicating information are described herein.

[0101] All references cited herein are incorporated herein by reference to the full extent allowed by law. The discussion of those references is intended merely to summarize the assertions made by their authors. No admission is made that any reference (or a portion of any reference) is relevant prior art. Applicants reserve the right to challenge the accuracy and pertinence of any cited reference.

REFERENCES

[0102] 1. Chuang, W Y, Chang, S H, Yu, W H, Yang, C K, Yeh, C J, Ueng, S H, et al., Successful Identification of Nasopharyngeal Carcinoma in Nasopharyngeal Biopsies Using Deep Learning. Cancers (Basel) 2020; 12:507. [0103] 2. Gong, L, Kwong, DL, Dai, W, Wu, P, Li, S, Yan, Q, et al., Comprehensive single-cell sequencing reveals the stromal dynamics and tumor-specific characteristics in the microenvironment of nasopharyngeal carcinoma. Nat Commun 2021; 12:1540.