Correlation between aggregated molecular cancer subtypes and selected clinical features

Lung Adenocarcinoma (Primary solid tumor)

28 January 2016 | analyses__2016_01_28

Maintainer Information

Citation Information

Maintained by TCGA GDAC Team (Broad Institute/MD Anderson Cancer Center/Harvard Medical School)

Cite as Broad Institute TCGA Genome Data Analysis Center (2016): Correlation between aggregated molecular cancer subtypes and selected clinical features. Broad Institute of MIT and Harvard. doi:10.7908/C1K35T23

Overview

Introduction

This pipeline computes the correlation between cancer subtypes identified by different molecular patterns and selected clinical features.

Summary

Testing the association between subtypes identified by 12 different clustering approaches and 15 clinical features across 520 patients, 67 significant findings detected with P value < 0.05 and Q value < 0.25.

CNMF clustering analysis on array-based mRNA expression data identified 3 subtypes that correlate to 'RACE'.
Consensus hierarchical clustering analysis on array-based mRNA expression data identified 3 subtypes that correlate to 'PATHOLOGIC_STAGE' and 'RACE'.
4 subtypes identified in current cancer cohort by 'Copy Number Ratio CNMF subtypes'. These subtypes correlate to 'Time to Death', 'YEARS_TO_BIRTH', 'GENDER', 'HISTOLOGICAL_TYPE', 'NUMBER_PACK_YEARS_SMOKED', and 'YEAR_OF_TOBACCO_SMOKING_ONSET'.
3 subtypes identified in current cancer cohort by 'METHLYATION CNMF'. These subtypes correlate to 'YEARS_TO_BIRTH', 'PATHOLOGIC_STAGE', 'PATHOLOGY_T_STAGE', 'PATHOLOGY_N_STAGE', 'GENDER', 'RADIATION_THERAPY', and 'NUMBER_PACK_YEARS_SMOKED'.
CNMF clustering analysis on RPPA data identified 5 subtypes that correlate to 'YEARS_TO_BIRTH', 'PATHOLOGY_M_STAGE', 'HISTOLOGICAL_TYPE', 'YEAR_OF_TOBACCO_SMOKING_ONSET', and 'RESIDUAL_TUMOR'.
Consensus hierarchical clustering analysis on RPPA data identified 3 subtypes that correlate to 'HISTOLOGICAL_TYPE', 'YEAR_OF_TOBACCO_SMOKING_ONSET', and 'ETHNICITY'.
CNMF clustering analysis on sequencing-based mRNA expression data identified 5 subtypes that correlate to 'Time to Death', 'YEARS_TO_BIRTH', 'PATHOLOGIC_STAGE', 'PATHOLOGY_T_STAGE', 'PATHOLOGY_N_STAGE', 'GENDER', and 'HISTOLOGICAL_TYPE'.
Consensus hierarchical clustering analysis on sequencing-based mRNA expression data identified 7 subtypes that correlate to 'Time to Death', 'YEARS_TO_BIRTH', 'PATHOLOGIC_STAGE', 'PATHOLOGY_T_STAGE', 'PATHOLOGY_N_STAGE', 'GENDER', 'HISTOLOGICAL_TYPE', 'YEAR_OF_TOBACCO_SMOKING_ONSET', and 'ETHNICITY'.
3 subtypes identified in current cancer cohort by 'MIRSEQ CNMF'. These subtypes correlate to 'YEARS_TO_BIRTH', 'PATHOLOGIC_STAGE', 'PATHOLOGY_T_STAGE', 'HISTOLOGICAL_TYPE', and 'NUMBER_PACK_YEARS_SMOKED'.
6 subtypes identified in current cancer cohort by 'MIRSEQ CHIERARCHICAL'. These subtypes correlate to 'YEARS_TO_BIRTH', 'GENDER', 'HISTOLOGICAL_TYPE', 'NUMBER_PACK_YEARS_SMOKED', and 'YEAR_OF_TOBACCO_SMOKING_ONSET'.
6 subtypes identified in current cancer cohort by 'MIRseq Mature CNMF subtypes'. These subtypes correlate to 'Time to Death', 'YEARS_TO_BIRTH', 'PATHOLOGIC_STAGE', 'PATHOLOGY_T_STAGE', 'PATHOLOGY_N_STAGE', 'HISTOLOGICAL_TYPE', 'NUMBER_PACK_YEARS_SMOKED', and 'RESIDUAL_TUMOR'.
3 subtypes identified in current cancer cohort by 'MIRseq Mature cHierClus subtypes'. These subtypes correlate to 'Time to Death', 'YEARS_TO_BIRTH', 'PATHOLOGY_T_STAGE', 'PATHOLOGY_N_STAGE', 'GENDER', 'RADIATION_THERAPY', 'HISTOLOGICAL_TYPE', 'NUMBER_PACK_YEARS_SMOKED', and 'RESIDUAL_TUMOR'.

Results

Overview of the results

Table 1. Get Full Table Overview of the association between subtypes identified by 12 different clustering approaches and 15 clinical features. Shown in the table are P values (Q values). Thresholded by P value < 0.05 and Q value < 0.25, 67 significant findings detected.


Clinical Features	Statistical Tests	mRNA CNMF subtypes	mRNA cHierClus subtypes	Copy Number Ratio CNMF subtypes	METHLYATION CNMF	RPPA CNMF subtypes	RPPA cHierClus subtypes	RNAseq CNMF subtypes	RNAseq cHierClus subtypes	MIRSEQ CNMF	MIRSEQ CHIERARCHICAL	MIRseq Mature CNMF subtypes	MIRseq Mature cHierClus subtypes
Time to Death	logrank test	0.934 (0.989)	0.899 (0.963)	0.0212 (0.0813)	0.195 (0.395)	0.991 (1.00)	0.413 (0.627)	3.96e-12 (7.12e-10)	9.1e-08 (8.19e-06)	0.204 (0.404)	0.709 (0.818)	0.00296 (0.0163)	0.0305 (0.102)
YEARS TO BIRTH	Kruskal-Wallis (anova)	0.369 (0.607)	0.513 (0.679)	0.00149 (0.0117)	0.0407 (0.119)	0.00173 (0.012)	0.092 (0.212)	0.000247 (0.00404)	0.00058 (0.00614)	0.0297 (0.102)	0.0026 (0.0151)	0.04 (0.119)	0.000126 (0.00253)
PATHOLOGIC STAGE	Fisher's exact test	0.0997 (0.227)	0.0491 (0.132)	0.458 (0.655)	6e-05 (0.00154)	0.329 (0.576)	0.717 (0.818)	0.00329 (0.0169)	0.00802 (0.037)	0.00613 (0.0298)	0.852 (0.929)	0.00226 (0.014)	0.376 (0.609)
PATHOLOGY T STAGE	Fisher's exact test	0.469 (0.662)	0.277 (0.515)	0.173 (0.361)	0.00018 (0.00324)	0.207 (0.405)	0.104 (0.235)	4e-05 (0.00144)	0.00171 (0.012)	0.0304 (0.102)	0.182 (0.376)	0.00051 (0.00574)	0.0163 (0.0654)
PATHOLOGY N STAGE	Fisher's exact test	0.392 (0.623)	0.456 (0.655)	0.666 (0.803)	0.032 (0.105)	0.436 (0.638)	0.482 (0.666)	0.00124 (0.0108)	0.00299 (0.0163)	0.308 (0.561)	0.414 (0.627)	0.0409 (0.119)	0.0301 (0.102)
PATHOLOGY M STAGE	Fisher's exact test	0.697 (0.815)	0.488 (0.666)	0.828 (0.915)	0.323 (0.576)	0.0484 (0.132)	0.789 (0.882)	0.471 (0.662)	0.509 (0.678)	0.72 (0.818)	0.667 (0.803)	0.722 (0.818)	0.697 (0.815)
GENDER	Fisher's exact test	0.425 (0.632)	0.671 (0.803)	0.00253 (0.0151)	2e-05 (9e-04)	0.155 (0.328)	0.533 (0.697)	0.00035 (0.00495)	1e-05 (6e-04)	0.48 (0.666)	0.00156 (0.0117)	0.0661 (0.159)	0.00075 (0.00741)
RADIATION THERAPY	Fisher's exact test	1 (1.00)	1 (1.00)	0.385 (0.619)	0.0272 (0.0998)	0.185 (0.378)	0.227 (0.44)	0.0517 (0.135)	0.0664 (0.159)	0.504 (0.677)	0.399 (0.624)	0.36 (0.604)	0.0427 (0.12)
KARNOFSKY PERFORMANCE SCORE	Kruskal-Wallis (anova)			0.371 (0.607)	0.403 (0.626)	0.237 (0.455)	0.644 (0.799)	0.573 (0.737)	0.431 (0.636)	0.5 (0.676)	0.678 (0.803)	0.0824 (0.193)	0.817 (0.908)
HISTOLOGICAL TYPE	Fisher's exact test	0.485 (0.666)	0.394 (0.623)	6e-05 (0.00154)	0.0573 (0.147)	0.004 (0.02)	0.00132 (0.0108)	0.00218 (0.014)	8e-05 (0.0018)	0.00205 (0.0137)	0.0198 (0.0775)	0.00039 (0.00495)	0.00041 (0.00495)
NUMBER PACK YEARS SMOKED	Kruskal-Wallis (anova)	0.362 (0.604)	0.362 (0.604)	0.0377 (0.116)	0.0121 (0.0509)	0.863 (0.934)	1 (1.00)	0.204 (0.404)	0.0637 (0.158)	0.0424 (0.12)	0.0137 (0.0562)	0.038 (0.116)	0.0231 (0.0867)
YEAR OF TOBACCO SMOKING ONSET	Kruskal-Wallis (anova)	0.676 (0.803)	0.676 (0.803)	0.0333 (0.107)	0.843 (0.925)	0.000782 (0.00741)	0.00327 (0.0169)	0.278 (0.515)	0.000412 (0.00495)	0.0579 (0.147)	0.0013 (0.0108)	0.0701 (0.166)	0.0507 (0.134)
RESIDUAL TUMOR	Fisher's exact test	0.591 (0.749)	0.458 (0.655)	0.996 (1.00)	0.931 (0.989)	0.00764 (0.0362)	0.867 (0.934)	0.709 (0.818)	0.329 (0.576)	0.656 (0.803)	0.939 (0.989)	0.0106 (0.0453)	0.0291 (0.102)
RACE	Fisher's exact test	0.01 (0.0441)	0.00942 (0.0424)	0.425 (0.632)	0.128 (0.278)	0.33 (0.576)	0.35 (0.6)	0.557 (0.721)	0.581 (0.742)	0.121 (0.265)	0.41 (0.627)	0.625 (0.781)	0.115 (0.256)
ETHNICITY	Fisher's exact test	1 (1.00)	1 (1.00)	0.297 (0.546)	0.0642 (0.158)	0.535 (0.697)	0.0471 (0.13)	0.746 (0.839)	0.0341 (0.108)	0.339 (0.587)	0.609 (0.766)	0.269 (0.51)	0.141 (0.303)

Clustering Approach #1: 'mRNA CNMF subtypes'

Table S1. Description of clustering approach #1: 'mRNA CNMF subtypes'

Cluster Labels	1	2	3
Number of samples	15	10	7

'mRNA CNMF subtypes' versus 'Time to Death'

P value = 0.934 (logrank test), Q value = 0.99

Table S2. Clustering Approach #1: 'mRNA CNMF subtypes' versus Clinical Feature #1: 'Time to Death'

	nPatients	nDeath	Duration Range (Median), Month
ALL	31	7	0.5 - 67.9 (34.1)
subtype1	14	3	0.5 - 47.0 (30.1)
subtype2	10	2	4.0 - 56.8 (36.2)
subtype3	7	2	20.1 - 67.9 (38.7)

Figure S1. Get High-res Image Clustering Approach #1: 'mRNA CNMF subtypes' versus Clinical Feature #1: 'Time to Death'

'mRNA CNMF subtypes' versus 'YEARS_TO_BIRTH'

P value = 0.369 (Kruskal-Wallis (anova)), Q value = 0.61

Table S3. Clustering Approach #1: 'mRNA CNMF subtypes' versus Clinical Feature #2: 'YEARS_TO_BIRTH'

	nPatients	Mean (Std.Dev)
ALL	30	65.7 (10.8)
subtype1	15	67.0 (10.2)
subtype2	10	61.9 (12.3)
subtype3	5	69.4 (9.0)

Figure S2. Get High-res Image Clustering Approach #1: 'mRNA CNMF subtypes' versus Clinical Feature #2: 'YEARS_TO_BIRTH'

'mRNA CNMF subtypes' versus 'PATHOLOGIC_STAGE'

P value = 0.0997 (Fisher's exact test), Q value = 0.23

Table S4. Clustering Approach #1: 'mRNA CNMF subtypes' versus Clinical Feature #3: 'PATHOLOGIC_STAGE'

nPatients	STAGE IA	STAGE IB	STAGE IIB	STAGE IIIA	STAGE IV
ALL	12	11	3	3	2
subtype1	4	8	1	0	2
subtype2	5	3	1	1	0
subtype3	3	0	1	2	0

Figure S3. Get High-res Image Clustering Approach #1: 'mRNA CNMF subtypes' versus Clinical Feature #3: 'PATHOLOGIC_STAGE'

'mRNA CNMF subtypes' versus 'PATHOLOGY_T_STAGE'

P value = 0.469 (Fisher's exact test), Q value = 0.66

Table S5. Clustering Approach #1: 'mRNA CNMF subtypes' versus Clinical Feature #4: 'PATHOLOGY_T_STAGE'

nPatients	T1	T2	T3
ALL	12	19	1
subtype1	5	10	0
subtype2	5	4	1
subtype3	2	5	0

Figure S4. Get High-res Image Clustering Approach #1: 'mRNA CNMF subtypes' versus Clinical Feature #4: 'PATHOLOGY_T_STAGE'

'mRNA CNMF subtypes' versus 'PATHOLOGY_N_STAGE'

P value = 0.392 (Fisher's exact test), Q value = 0.62

Table S6. Clustering Approach #1: 'mRNA CNMF subtypes' versus Clinical Feature #5: 'PATHOLOGY_N_STAGE'

nPatients	N0	N1	N2+N3
ALL	23	4	4
subtype1	11	1	2
subtype2	8	2	0
subtype3	4	1	2

Figure S5. Get High-res Image Clustering Approach #1: 'mRNA CNMF subtypes' versus Clinical Feature #5: 'PATHOLOGY_N_STAGE'

'mRNA CNMF subtypes' versus 'PATHOLOGY_M_STAGE'

P value = 0.697 (Fisher's exact test), Q value = 0.81

Table S7. Clustering Approach #1: 'mRNA CNMF subtypes' versus Clinical Feature #6: 'PATHOLOGY_M_STAGE'

nPatients	0	1
ALL	30	2
subtype1	13	2
subtype2	10	0
subtype3	7	0

Figure S6. Get High-res Image Clustering Approach #1: 'mRNA CNMF subtypes' versus Clinical Feature #6: 'PATHOLOGY_M_STAGE'

'mRNA CNMF subtypes' versus 'GENDER'

P value = 0.425 (Fisher's exact test), Q value = 0.63

Table S8. Clustering Approach #1: 'mRNA CNMF subtypes' versus Clinical Feature #7: 'GENDER'

nPatients	FEMALE	MALE
ALL	18	14
subtype1	10	5
subtype2	4	6
subtype3	4	3

Figure S7. Get High-res Image Clustering Approach #1: 'mRNA CNMF subtypes' versus Clinical Feature #7: 'GENDER'

'mRNA CNMF subtypes' versus 'RADIATION_THERAPY'

P value = 1 (Fisher's exact test), Q value = 1

Table S9. Clustering Approach #1: 'mRNA CNMF subtypes' versus Clinical Feature #8: 'RADIATION_THERAPY'

nPatients	NO	YES
ALL	20	1
subtype1	8	1
subtype2	7	0
subtype3	5	0

Figure S8. Get High-res Image Clustering Approach #1: 'mRNA CNMF subtypes' versus Clinical Feature #8: 'RADIATION_THERAPY'

'mRNA CNMF subtypes' versus 'HISTOLOGICAL_TYPE'

P value = 0.485 (Fisher's exact test), Q value = 0.67

Table S10. Clustering Approach #1: 'mRNA CNMF subtypes' versus Clinical Feature #10: 'HISTOLOGICAL_TYPE'

nPatients	LUNG ADENOCARCINOMA MIXED SUBTYPE	LUNG ADENOCARCINOMA- NOT OTHERWISE SPECIFIED (NOS)	LUNG CLEAR CELL ADENOCARCINOMA
ALL	1	30	1
subtype1	1	14	0
subtype2	0	10	0
subtype3	0	6	1

Figure S9. Get High-res Image Clustering Approach #1: 'mRNA CNMF subtypes' versus Clinical Feature #10: 'HISTOLOGICAL_TYPE'

'mRNA CNMF subtypes' versus 'NUMBER_PACK_YEARS_SMOKED'

P value = 0.362 (Kruskal-Wallis (anova)), Q value = 0.6

Table S11. Clustering Approach #1: 'mRNA CNMF subtypes' versus Clinical Feature #11: 'NUMBER_PACK_YEARS_SMOKED'

	nPatients	Mean (Std.Dev)
ALL	20	41.1 (15.0)
subtype1	8	35.4 (12.2)
subtype2	9	46.7 (16.1)
subtype3	3	40.0 (17.3)

Figure S10. Get High-res Image Clustering Approach #1: 'mRNA CNMF subtypes' versus Clinical Feature #11: 'NUMBER_PACK_YEARS_SMOKED'

'mRNA CNMF subtypes' versus 'YEAR_OF_TOBACCO_SMOKING_ONSET'

P value = 0.676 (Kruskal-Wallis (anova)), Q value = 0.8

Table S12. Clustering Approach #1: 'mRNA CNMF subtypes' versus Clinical Feature #12: 'YEAR_OF_TOBACCO_SMOKING_ONSET'

	nPatients	Mean (Std.Dev)
ALL	19	1968.5 (11.4)
subtype1	7	1969.9 (13.0)
subtype2	6	1970.5 (12.9)
subtype3	6	1965.0 (8.8)

Figure S11. Get High-res Image Clustering Approach #1: 'mRNA CNMF subtypes' versus Clinical Feature #12: 'YEAR_OF_TOBACCO_SMOKING_ONSET'

'mRNA CNMF subtypes' versus 'RESIDUAL_TUMOR'

P value = 0.591 (Fisher's exact test), Q value = 0.75

Table S13. Clustering Approach #1: 'mRNA CNMF subtypes' versus Clinical Feature #13: 'RESIDUAL_TUMOR'

nPatients	R0	R2	RX
ALL	26	1	2
subtype1	11	0	2
subtype2	9	1	0
subtype3	6	0	0

Figure S12. Get High-res Image Clustering Approach #1: 'mRNA CNMF subtypes' versus Clinical Feature #13: 'RESIDUAL_TUMOR'

'mRNA CNMF subtypes' versus 'RACE'

P value = 0.01 (Fisher's exact test), Q value = 0.044

Table S14. Clustering Approach #1: 'mRNA CNMF subtypes' versus Clinical Feature #14: 'RACE'

nPatients	ASIAN	BLACK OR AFRICAN AMERICAN	WHITE
ALL	2	1	26
subtype1	0	0	14
subtype2	0	0	8
subtype3	2	1	4

Figure S13. Get High-res Image Clustering Approach #1: 'mRNA CNMF subtypes' versus Clinical Feature #14: 'RACE'

'mRNA CNMF subtypes' versus 'ETHNICITY'

P value = 1 (Fisher's exact test), Q value = 1

Table S15. Clustering Approach #1: 'mRNA CNMF subtypes' versus Clinical Feature #15: 'ETHNICITY'

nPatients	HISPANIC OR LATINO	NOT HISPANIC OR LATINO
ALL	1	28
subtype1	1	13
subtype2	0	8
subtype3	0	7

Figure S14. Get High-res Image Clustering Approach #1: 'mRNA CNMF subtypes' versus Clinical Feature #15: 'ETHNICITY'

Clustering Approach #2: 'mRNA cHierClus subtypes'

Table S16. Description of clustering approach #2: 'mRNA cHierClus subtypes'

Cluster Labels	1	2	3
Number of samples	14	11	7

'mRNA cHierClus subtypes' versus 'Time to Death'

P value = 0.899 (logrank test), Q value = 0.96

Table S17. Clustering Approach #2: 'mRNA cHierClus subtypes' versus Clinical Feature #1: 'Time to Death'

	nPatients	nDeath	Duration Range (Median), Month
ALL	31	7	0.5 - 67.9 (34.1)
subtype1	13	2	0.5 - 47.0 (26.6)
subtype2	11	3	4.0 - 56.8 (34.1)
subtype3	7	2	20.1 - 67.9 (38.7)

Figure S15. Get High-res Image Clustering Approach #2: 'mRNA cHierClus subtypes' versus Clinical Feature #1: 'Time to Death'

'mRNA cHierClus subtypes' versus 'YEARS_TO_BIRTH'

P value = 0.513 (Kruskal-Wallis (anova)), Q value = 0.68

Table S18. Clustering Approach #2: 'mRNA cHierClus subtypes' versus Clinical Feature #2: 'YEARS_TO_BIRTH'

	nPatients	Mean (Std.Dev)
ALL	30	65.7 (10.8)
subtype1	14	66.7 (10.5)
subtype2	11	62.7 (12.0)
subtype3	5	69.4 (9.0)

Figure S16. Get High-res Image Clustering Approach #2: 'mRNA cHierClus subtypes' versus Clinical Feature #2: 'YEARS_TO_BIRTH'

'mRNA cHierClus subtypes' versus 'PATHOLOGIC_STAGE'

P value = 0.0491 (Fisher's exact test), Q value = 0.13

Table S19. Clustering Approach #2: 'mRNA cHierClus subtypes' versus Clinical Feature #3: 'PATHOLOGIC_STAGE'

nPatients	STAGE IA	STAGE IB	STAGE IIB	STAGE IIIA	STAGE IV
ALL	12	11	3	3	2
subtype1	3	8	1	0	2
subtype2	6	3	1	1	0
subtype3	3	0	1	2	0

Figure S17. Get High-res Image Clustering Approach #2: 'mRNA cHierClus subtypes' versus Clinical Feature #3: 'PATHOLOGIC_STAGE'

'mRNA cHierClus subtypes' versus 'PATHOLOGY_T_STAGE'

P value = 0.277 (Fisher's exact test), Q value = 0.52

Table S20. Clustering Approach #2: 'mRNA cHierClus subtypes' versus Clinical Feature #4: 'PATHOLOGY_T_STAGE'

nPatients	T1	T2	T3
ALL	12	19	1
subtype1	4	10	0
subtype2	6	4	1
subtype3	2	5	0

Figure S18. Get High-res Image Clustering Approach #2: 'mRNA cHierClus subtypes' versus Clinical Feature #4: 'PATHOLOGY_T_STAGE'

'mRNA cHierClus subtypes' versus 'PATHOLOGY_N_STAGE'

P value = 0.456 (Fisher's exact test), Q value = 0.65

Table S21. Clustering Approach #2: 'mRNA cHierClus subtypes' versus Clinical Feature #5: 'PATHOLOGY_N_STAGE'

nPatients	N0	N1	N2+N3
ALL	23	4	4
subtype1	10	1	2
subtype2	9	2	0
subtype3	4	1	2

Figure S19. Get High-res Image Clustering Approach #2: 'mRNA cHierClus subtypes' versus Clinical Feature #5: 'PATHOLOGY_N_STAGE'

'mRNA cHierClus subtypes' versus 'PATHOLOGY_M_STAGE'

P value = 0.488 (Fisher's exact test), Q value = 0.67

Table S22. Clustering Approach #2: 'mRNA cHierClus subtypes' versus Clinical Feature #6: 'PATHOLOGY_M_STAGE'

nPatients	0	1
ALL	30	2
subtype1	12	2
subtype2	11	0
subtype3	7	0

Figure S20. Get High-res Image Clustering Approach #2: 'mRNA cHierClus subtypes' versus Clinical Feature #6: 'PATHOLOGY_M_STAGE'

'mRNA cHierClus subtypes' versus 'GENDER'

P value = 0.671 (Fisher's exact test), Q value = 0.8

Table S23. Clustering Approach #2: 'mRNA cHierClus subtypes' versus Clinical Feature #7: 'GENDER'

nPatients	FEMALE	MALE
ALL	18	14
subtype1	9	5
subtype2	5	6
subtype3	4	3

Figure S21. Get High-res Image Clustering Approach #2: 'mRNA cHierClus subtypes' versus Clinical Feature #7: 'GENDER'

'mRNA cHierClus subtypes' versus 'RADIATION_THERAPY'

P value = 1 (Fisher's exact test), Q value = 1

Table S24. Clustering Approach #2: 'mRNA cHierClus subtypes' versus Clinical Feature #8: 'RADIATION_THERAPY'

nPatients	NO	YES
ALL	20	1
subtype1	7	1
subtype2	8	0
subtype3	5	0

Figure S22. Get High-res Image Clustering Approach #2: 'mRNA cHierClus subtypes' versus Clinical Feature #8: 'RADIATION_THERAPY'

'mRNA cHierClus subtypes' versus 'HISTOLOGICAL_TYPE'

P value = 0.394 (Fisher's exact test), Q value = 0.62

Table S25. Clustering Approach #2: 'mRNA cHierClus subtypes' versus Clinical Feature #10: 'HISTOLOGICAL_TYPE'

nPatients	LUNG ADENOCARCINOMA MIXED SUBTYPE	LUNG ADENOCARCINOMA- NOT OTHERWISE SPECIFIED (NOS)	LUNG CLEAR CELL ADENOCARCINOMA
ALL	1	30	1
subtype1	1	13	0
subtype2	0	11	0
subtype3	0	6	1

Figure S23. Get High-res Image Clustering Approach #2: 'mRNA cHierClus subtypes' versus Clinical Feature #10: 'HISTOLOGICAL_TYPE'

'mRNA cHierClus subtypes' versus 'NUMBER_PACK_YEARS_SMOKED'

P value = 0.362 (Kruskal-Wallis (anova)), Q value = 0.6

Table S26. Clustering Approach #2: 'mRNA cHierClus subtypes' versus Clinical Feature #11: 'NUMBER_PACK_YEARS_SMOKED'

	nPatients	Mean (Std.Dev)
ALL	20	41.1 (15.0)
subtype1	8	35.4 (12.2)
subtype2	9	46.7 (16.1)
subtype3	3	40.0 (17.3)

Figure S24. Get High-res Image Clustering Approach #2: 'mRNA cHierClus subtypes' versus Clinical Feature #11: 'NUMBER_PACK_YEARS_SMOKED'

'mRNA cHierClus subtypes' versus 'YEAR_OF_TOBACCO_SMOKING_ONSET'

P value = 0.676 (Kruskal-Wallis (anova)), Q value = 0.8

Table S27. Clustering Approach #2: 'mRNA cHierClus subtypes' versus Clinical Feature #12: 'YEAR_OF_TOBACCO_SMOKING_ONSET'

	nPatients	Mean (Std.Dev)
ALL	19	1968.5 (11.4)
subtype1	7	1969.9 (13.0)
subtype2	6	1970.5 (12.9)
subtype3	6	1965.0 (8.8)

Figure S25. Get High-res Image Clustering Approach #2: 'mRNA cHierClus subtypes' versus Clinical Feature #12: 'YEAR_OF_TOBACCO_SMOKING_ONSET'

'mRNA cHierClus subtypes' versus 'RESIDUAL_TUMOR'

P value = 0.458 (Fisher's exact test), Q value = 0.65

Table S28. Clustering Approach #2: 'mRNA cHierClus subtypes' versus Clinical Feature #13: 'RESIDUAL_TUMOR'

nPatients	R0	R2	RX
ALL	26	1	2
subtype1	10	0	2
subtype2	10	1	0
subtype3	6	0	0

Figure S26. Get High-res Image Clustering Approach #2: 'mRNA cHierClus subtypes' versus Clinical Feature #13: 'RESIDUAL_TUMOR'

'mRNA cHierClus subtypes' versus 'RACE'

P value = 0.00942 (Fisher's exact test), Q value = 0.042

Table S29. Clustering Approach #2: 'mRNA cHierClus subtypes' versus Clinical Feature #14: 'RACE'

nPatients	ASIAN	BLACK OR AFRICAN AMERICAN	WHITE
ALL	2	1	26
subtype1	0	0	13
subtype2	0	0	9
subtype3	2	1	4

Figure S27. Get High-res Image Clustering Approach #2: 'mRNA cHierClus subtypes' versus Clinical Feature #14: 'RACE'

'mRNA cHierClus subtypes' versus 'ETHNICITY'

P value = 1 (Fisher's exact test), Q value = 1

Table S30. Clustering Approach #2: 'mRNA cHierClus subtypes' versus Clinical Feature #15: 'ETHNICITY'

nPatients	HISPANIC OR LATINO	NOT HISPANIC OR LATINO
ALL	1	28
subtype1	1	12
subtype2	0	9
subtype3	0	7

Figure S28. Get High-res Image Clustering Approach #2: 'mRNA cHierClus subtypes' versus Clinical Feature #15: 'ETHNICITY'

Clustering Approach #3: 'Copy Number Ratio CNMF subtypes'

Table S31. Description of clustering approach #3: 'Copy Number Ratio CNMF subtypes'

Cluster Labels	1	2	3	4
Number of samples	172	138	132	74

'Copy Number Ratio CNMF subtypes' versus 'Time to Death'

P value = 0.0212 (logrank test), Q value = 0.081

Table S32. Clustering Approach #3: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #1: 'Time to Death'

	nPatients	nDeath	Duration Range (Median), Month
ALL	504	181	0.0 - 238.3 (21.6)
subtype1	168	64	0.4 - 238.3 (23.4)
subtype2	136	58	0.0 - 123.6 (19.9)
subtype3	127	36	0.4 - 164.1 (22.7)
subtype4	73	23	0.6 - 129.5 (19.9)

Figure S29. Get High-res Image Clustering Approach #3: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #1: 'Time to Death'

'Copy Number Ratio CNMF subtypes' versus 'YEARS_TO_BIRTH'

P value = 0.00149 (Kruskal-Wallis (anova)), Q value = 0.012

Table S33. Clustering Approach #3: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #2: 'YEARS_TO_BIRTH'

	nPatients	Mean (Std.Dev)
ALL	485	65.2 (10.0)
subtype1	161	63.9 (10.0)
subtype2	131	64.5 (10.5)
subtype3	124	68.2 (8.9)
subtype4	69	64.5 (10.1)

Figure S30. Get High-res Image Clustering Approach #3: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #2: 'YEARS_TO_BIRTH'

'Copy Number Ratio CNMF subtypes' versus 'PATHOLOGIC_STAGE'

P value = 0.458 (Fisher's exact test), Q value = 0.65

Table S34. Clustering Approach #3: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #3: 'PATHOLOGIC_STAGE'

nPatients	STAGE I	STAGE IA	STAGE IB	STAGE II	STAGE IIA	STAGE IIB	STAGE IIIA	STAGE IIIB	STAGE IV
ALL	5	133	139	1	50	72	72	11	25
subtype1	2	40	53	1	22	16	27	3	6
subtype2	2	31	32	0	11	29	21	3	8
subtype3	1	41	34	0	10	20	14	2	7
subtype4	0	21	20	0	7	7	10	3	4

Figure S31. Get High-res Image Clustering Approach #3: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #3: 'PATHOLOGIC_STAGE'

'Copy Number Ratio CNMF subtypes' versus 'PATHOLOGY_T_STAGE'

P value = 0.173 (Fisher's exact test), Q value = 0.36

Table S35. Clustering Approach #3: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #4: 'PATHOLOGY_T_STAGE'

nPatients	T1	T2	T3	T4
ALL	171	278	46	19
subtype1	54	102	11	4
subtype2	38	78	17	4
subtype3	51	60	13	8
subtype4	28	38	5	3

Figure S32. Get High-res Image Clustering Approach #3: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #4: 'PATHOLOGY_T_STAGE'

'Copy Number Ratio CNMF subtypes' versus 'PATHOLOGY_N_STAGE'

P value = 0.666 (Fisher's exact test), Q value = 0.8

Table S36. Clustering Approach #3: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #5: 'PATHOLOGY_N_STAGE'

nPatients	N0	N1	N2+N3
ALL	333	96	76
subtype1	102	33	31
subtype2	90	26	21
subtype3	91	24	14
subtype4	50	13	10

Figure S33. Get High-res Image Clustering Approach #3: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #5: 'PATHOLOGY_N_STAGE'

'Copy Number Ratio CNMF subtypes' versus 'PATHOLOGY_M_STAGE'

P value = 0.828 (Fisher's exact test), Q value = 0.91

Table S37. Clustering Approach #3: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #6: 'PATHOLOGY_M_STAGE'

nPatients	0	1
ALL	349	25
subtype1	113	6
subtype2	91	8
subtype3	93	7
subtype4	52	4

Figure S34. Get High-res Image Clustering Approach #3: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #6: 'PATHOLOGY_M_STAGE'

'Copy Number Ratio CNMF subtypes' versus 'GENDER'

P value = 0.00253 (Fisher's exact test), Q value = 0.015

Table S38. Clustering Approach #3: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #7: 'GENDER'

nPatients	FEMALE	MALE
ALL	276	240
subtype1	107	65
subtype2	62	76
subtype3	76	56
subtype4	31	43

Figure S35. Get High-res Image Clustering Approach #3: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #7: 'GENDER'

'Copy Number Ratio CNMF subtypes' versus 'RADIATION_THERAPY'

P value = 0.385 (Fisher's exact test), Q value = 0.62

Table S39. Clustering Approach #3: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #8: 'RADIATION_THERAPY'

nPatients	NO	YES
ALL	410	60
subtype1	139	20
subtype2	108	19
subtype3	105	10
subtype4	58	11

Figure S36. Get High-res Image Clustering Approach #3: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #8: 'RADIATION_THERAPY'

'Copy Number Ratio CNMF subtypes' versus 'KARNOFSKY_PERFORMANCE_SCORE'

P value = 0.371 (Kruskal-Wallis (anova)), Q value = 0.61

Table S40. Clustering Approach #3: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #9: 'KARNOFSKY_PERFORMANCE_SCORE'

	nPatients	Mean (Std.Dev)
ALL	137	78.8 (28.3)
subtype1	49	81.8 (26.4)
subtype2	36	74.7 (31.9)
subtype3	30	81.3 (27.1)
subtype4	22	75.5 (28.6)

Figure S37. Get High-res Image Clustering Approach #3: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #9: 'KARNOFSKY_PERFORMANCE_SCORE'

'Copy Number Ratio CNMF subtypes' versus 'HISTOLOGICAL_TYPE'

P value = 6e-05 (Fisher's exact test), Q value = 0.0015

Table S41. Clustering Approach #3: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #10: 'HISTOLOGICAL_TYPE'

nPatients	LUNG ACINAR ADENOCARCINOMA	LUNG ADENOCARCINOMA MIXED SUBTYPE	LUNG ADENOCARCINOMA- NOT OTHERWISE SPECIFIED (NOS)	LUNG BRONCHIOLOALVEOLAR CARCINOMA MUCINOUS	LUNG BRONCHIOLOALVEOLAR CARCINOMA NONMUCINOUS	LUNG CLEAR CELL ADENOCARCINOMA	LUNG MICROPAPILLARY ADENOCARCINOMA	LUNG MUCINOUS ADENOCARCINOMA	LUNG PAPILLARY ADENOCARCINOMA	LUNG SIGNET RING ADENOCARCINOMA	LUNG SOLID PATTERN PREDOMINANT ADENOCARCINOMA	MUCINOUS (COLLOID) CARCINOMA
ALL	18	107	321	5	19	2	3	2	23	1	5	10
subtype1	4	30	117	2	9	1	2	0	5	0	2	0
subtype2	4	23	100	1	2	1	0	0	4	1	1	1
subtype3	2	37	64	2	7	0	1	2	9	0	0	8
subtype4	8	17	40	0	1	0	0	0	5	0	2	1

Figure S38. Get High-res Image Clustering Approach #3: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #10: 'HISTOLOGICAL_TYPE'

'Copy Number Ratio CNMF subtypes' versus 'NUMBER_PACK_YEARS_SMOKED'

P value = 0.0377 (Kruskal-Wallis (anova)), Q value = 0.12

Table S42. Clustering Approach #3: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #11: 'NUMBER_PACK_YEARS_SMOKED'

	nPatients	Mean (Std.Dev)
ALL	354	41.8 (27.2)
subtype1	98	42.4 (26.3)
subtype2	105	45.0 (25.1)
subtype3	92	37.1 (27.2)
subtype4	59	42.7 (31.4)

Figure S39. Get High-res Image Clustering Approach #3: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #11: 'NUMBER_PACK_YEARS_SMOKED'

'Copy Number Ratio CNMF subtypes' versus 'YEAR_OF_TOBACCO_SMOKING_ONSET'

P value = 0.0333 (Kruskal-Wallis (anova)), Q value = 0.11

Table S43. Clustering Approach #3: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #12: 'YEAR_OF_TOBACCO_SMOKING_ONSET'

	nPatients	Mean (Std.Dev)
ALL	277	1965.0 (12.5)
subtype1	82	1965.5 (12.2)
subtype2	77	1967.3 (12.6)
subtype3	70	1961.2 (11.9)
subtype4	48	1966.3 (13.0)

Figure S40. Get High-res Image Clustering Approach #3: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #12: 'YEAR_OF_TOBACCO_SMOKING_ONSET'

'Copy Number Ratio CNMF subtypes' versus 'RESIDUAL_TUMOR'

P value = 0.996 (Fisher's exact test), Q value = 1

Table S44. Clustering Approach #3: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #13: 'RESIDUAL_TUMOR'

nPatients	R0	R1	R2	RX
ALL	344	13	4	26
subtype1	113	4	1	10
subtype2	96	4	1	6
subtype3	86	3	2	6
subtype4	49	2	0	4

Figure S41. Get High-res Image Clustering Approach #3: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #13: 'RESIDUAL_TUMOR'

'Copy Number Ratio CNMF subtypes' versus 'RACE'

P value = 0.425 (Fisher's exact test), Q value = 0.63

Table S45. Clustering Approach #3: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #14: 'RACE'

nPatients	AMERICAN INDIAN OR ALASKA NATIVE	ASIAN	BLACK OR AFRICAN AMERICAN	WHITE
ALL	1	7	52	390
subtype1	1	2	23	128
subtype2	0	3	15	98
subtype3	0	1	8	108
subtype4	0	1	6	56

Figure S42. Get High-res Image Clustering Approach #3: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #14: 'RACE'

'Copy Number Ratio CNMF subtypes' versus 'ETHNICITY'

P value = 0.297 (Fisher's exact test), Q value = 0.55

Table S46. Clustering Approach #3: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #15: 'ETHNICITY'

nPatients	HISPANIC OR LATINO	NOT HISPANIC OR LATINO
ALL	7	384
subtype1	1	131
subtype2	4	97
subtype3	1	102
subtype4	1	54

Figure S43. Get High-res Image Clustering Approach #3: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #15: 'ETHNICITY'

Clustering Approach #4: 'METHLYATION CNMF'

Table S47. Description of clustering approach #4: 'METHLYATION CNMF'

Cluster Labels	1	2	3
Number of samples	156	172	130

'METHLYATION CNMF' versus 'Time to Death'

P value = 0.195 (logrank test), Q value = 0.4

Table S48. Clustering Approach #4: 'METHLYATION CNMF' versus Clinical Feature #1: 'Time to Death'

	nPatients	nDeath	Duration Range (Median), Month
ALL	447	161	0.1 - 238.3 (20.8)
subtype1	154	64	0.7 - 232.2 (20.0)
subtype2	168	59	0.1 - 163.1 (20.4)
subtype3	125	38	0.4 - 238.3 (22.2)

Figure S44. Get High-res Image Clustering Approach #4: 'METHLYATION CNMF' versus Clinical Feature #1: 'Time to Death'

'METHLYATION CNMF' versus 'YEARS_TO_BIRTH'

P value = 0.0407 (Kruskal-Wallis (anova)), Q value = 0.12

Table S49. Clustering Approach #4: 'METHLYATION CNMF' versus Clinical Feature #2: 'YEARS_TO_BIRTH'

	nPatients	Mean (Std.Dev)
ALL	429	65.0 (10.2)
subtype1	147	63.9 (10.0)
subtype2	163	64.7 (10.4)
subtype3	119	66.9 (9.8)

Figure S45. Get High-res Image Clustering Approach #4: 'METHLYATION CNMF' versus Clinical Feature #2: 'YEARS_TO_BIRTH'

'METHLYATION CNMF' versus 'PATHOLOGIC_STAGE'

P value = 6e-05 (Fisher's exact test), Q value = 0.0015

Table S50. Clustering Approach #4: 'METHLYATION CNMF' versus Clinical Feature #3: 'PATHOLOGIC_STAGE'

nPatients	STAGE I	STAGE IA	STAGE IB	STAGE II	STAGE IIA	STAGE IIB	STAGE IIIA	STAGE IIIB	STAGE IV
ALL	5	119	124	1	49	62	64	9	20
subtype1	4	36	39	0	19	15	28	4	10
subtype2	0	29	58	0	15	31	27	4	6
subtype3	1	54	27	1	15	16	9	1	4

Figure S46. Get High-res Image Clustering Approach #4: 'METHLYATION CNMF' versus Clinical Feature #3: 'PATHOLOGIC_STAGE'

'METHLYATION CNMF' versus 'PATHOLOGY_T_STAGE'

P value = 0.00018 (Fisher's exact test), Q value = 0.0032

Table S51. Clustering Approach #4: 'METHLYATION CNMF' versus Clinical Feature #4: 'PATHOLOGY_T_STAGE'

nPatients	T1	T2	T3	T4
ALL	155	243	41	16
subtype1	51	87	12	5
subtype2	39	104	21	8
subtype3	65	52	8	3

Figure S47. Get High-res Image Clustering Approach #4: 'METHLYATION CNMF' versus Clinical Feature #4: 'PATHOLOGY_T_STAGE'

'METHLYATION CNMF' versus 'PATHOLOGY_N_STAGE'

P value = 0.032 (Fisher's exact test), Q value = 0.1

Table S52. Clustering Approach #4: 'METHLYATION CNMF' versus Clinical Feature #5: 'PATHOLOGY_N_STAGE'

nPatients	N0	N1	N2+N3
ALL	299	83	66
subtype1	97	25	32
subtype2	112	33	25
subtype3	90	25	9

Figure S48. Get High-res Image Clustering Approach #4: 'METHLYATION CNMF' versus Clinical Feature #5: 'PATHOLOGY_N_STAGE'

'METHLYATION CNMF' versus 'PATHOLOGY_M_STAGE'

P value = 0.323 (Fisher's exact test), Q value = 0.58

Table S53. Clustering Approach #4: 'METHLYATION CNMF' versus Clinical Feature #6: 'PATHOLOGY_M_STAGE'

nPatients	0	1
ALL	295	19
subtype1	102	10
subtype2	118	6
subtype3	75	3

Figure S49. Get High-res Image Clustering Approach #4: 'METHLYATION CNMF' versus Clinical Feature #6: 'PATHOLOGY_M_STAGE'

'METHLYATION CNMF' versus 'GENDER'

P value = 2e-05 (Fisher's exact test), Q value = 9e-04

Table S54. Clustering Approach #4: 'METHLYATION CNMF' versus Clinical Feature #7: 'GENDER'

nPatients	FEMALE	MALE
ALL	244	214
subtype1	63	93
subtype2	90	82
subtype3	91	39

Figure S50. Get High-res Image Clustering Approach #4: 'METHLYATION CNMF' versus Clinical Feature #7: 'GENDER'

'METHLYATION CNMF' versus 'RADIATION_THERAPY'

P value = 0.0272 (Fisher's exact test), Q value = 0.1

Table S55. Clustering Approach #4: 'METHLYATION CNMF' versus Clinical Feature #8: 'RADIATION_THERAPY'

nPatients	NO	YES
ALL	377	55
subtype1	120	26
subtype2	146	12
subtype3	111	17

Figure S51. Get High-res Image Clustering Approach #4: 'METHLYATION CNMF' versus Clinical Feature #8: 'RADIATION_THERAPY'

'METHLYATION CNMF' versus 'KARNOFSKY_PERFORMANCE_SCORE'

P value = 0.403 (Kruskal-Wallis (anova)), Q value = 0.63

Table S56. Clustering Approach #4: 'METHLYATION CNMF' versus Clinical Feature #9: 'KARNOFSKY_PERFORMANCE_SCORE'

	nPatients	Mean (Std.Dev)
ALL	123	79.8 (28.1)
subtype1	52	75.6 (31.6)
subtype2	42	83.1 (23.5)
subtype3	29	82.4 (27.3)

Figure S52. Get High-res Image Clustering Approach #4: 'METHLYATION CNMF' versus Clinical Feature #9: 'KARNOFSKY_PERFORMANCE_SCORE'

'METHLYATION CNMF' versus 'HISTOLOGICAL_TYPE'

P value = 0.0573 (Fisher's exact test), Q value = 0.15

Table S57. Clustering Approach #4: 'METHLYATION CNMF' versus Clinical Feature #10: 'HISTOLOGICAL_TYPE'

nPatients	LUNG ACINAR ADENOCARCINOMA	LUNG ADENOCARCINOMA MIXED SUBTYPE	LUNG ADENOCARCINOMA- NOT OTHERWISE SPECIFIED (NOS)	LUNG BRONCHIOLOALVEOLAR CARCINOMA MUCINOUS	LUNG BRONCHIOLOALVEOLAR CARCINOMA NONMUCINOUS	LUNG CLEAR CELL ADENOCARCINOMA	LUNG MICROPAPILLARY ADENOCARCINOMA	LUNG MUCINOUS ADENOCARCINOMA	LUNG PAPILLARY ADENOCARCINOMA	LUNG SIGNET RING ADENOCARCINOMA	LUNG SOLID PATTERN PREDOMINANT ADENOCARCINOMA	MUCINOUS (COLLOID) CARCINOMA
ALL	18	92	281	5	19	1	2	2	22	1	5	10
subtype1	9	30	98	0	3	1	0	0	9	0	3	3
subtype2	4	40	109	1	7	0	1	1	6	0	2	1
subtype3	5	22	74	4	9	0	1	1	7	1	0	6

Figure S53. Get High-res Image Clustering Approach #4: 'METHLYATION CNMF' versus Clinical Feature #10: 'HISTOLOGICAL_TYPE'

'METHLYATION CNMF' versus 'NUMBER_PACK_YEARS_SMOKED'

P value = 0.0121 (Kruskal-Wallis (anova)), Q value = 0.051

Table S58. Clustering Approach #4: 'METHLYATION CNMF' versus Clinical Feature #11: 'NUMBER_PACK_YEARS_SMOKED'

	nPatients	Mean (Std.Dev)
ALL	312	40.9 (27.1)
subtype1	118	47.0 (29.9)
subtype2	118	37.8 (26.3)
subtype3	76	36.3 (21.7)

Figure S54. Get High-res Image Clustering Approach #4: 'METHLYATION CNMF' versus Clinical Feature #11: 'NUMBER_PACK_YEARS_SMOKED'

'METHLYATION CNMF' versus 'YEAR_OF_TOBACCO_SMOKING_ONSET'

P value = 0.843 (Kruskal-Wallis (anova)), Q value = 0.93

Table S59. Clustering Approach #4: 'METHLYATION CNMF' versus Clinical Feature #12: 'YEAR_OF_TOBACCO_SMOKING_ONSET'

	nPatients	Mean (Std.Dev)
ALL	252	1965.3 (12.4)
subtype1	94	1965.2 (12.9)
subtype2	100	1965.7 (13.1)
subtype3	58	1964.7 (10.6)

Figure S55. Get High-res Image Clustering Approach #4: 'METHLYATION CNMF' versus Clinical Feature #12: 'YEAR_OF_TOBACCO_SMOKING_ONSET'

'METHLYATION CNMF' versus 'RESIDUAL_TUMOR'

P value = 0.931 (Fisher's exact test), Q value = 0.99

Table S60. Clustering Approach #4: 'METHLYATION CNMF' versus Clinical Feature #13: 'RESIDUAL_TUMOR'

nPatients	R0	R1	R2	RX
ALL	295	11	1	23
subtype1	98	4	0	8
subtype2	117	5	0	9
subtype3	80	2	1	6

Figure S56. Get High-res Image Clustering Approach #4: 'METHLYATION CNMF' versus Clinical Feature #13: 'RESIDUAL_TUMOR'

'METHLYATION CNMF' versus 'RACE'

P value = 0.128 (Fisher's exact test), Q value = 0.28

Table S61. Clustering Approach #4: 'METHLYATION CNMF' versus Clinical Feature #14: 'RACE'

nPatients	ASIAN	BLACK OR AFRICAN AMERICAN	WHITE
ALL	6	50	353
subtype1	2	20	119
subtype2	4	12	132
subtype3	0	18	102

Figure S57. Get High-res Image Clustering Approach #4: 'METHLYATION CNMF' versus Clinical Feature #14: 'RACE'

'METHLYATION CNMF' versus 'ETHNICITY'

P value = 0.0642 (Fisher's exact test), Q value = 0.16

Table S62. Clustering Approach #4: 'METHLYATION CNMF' versus Clinical Feature #15: 'ETHNICITY'

nPatients	HISPANIC OR LATINO	NOT HISPANIC OR LATINO
ALL	7	343
subtype1	5	113
subtype2	2	120
subtype3	0	110

Figure S58. Get High-res Image Clustering Approach #4: 'METHLYATION CNMF' versus Clinical Feature #15: 'ETHNICITY'

Clustering Approach #5: 'RPPA CNMF subtypes'

Table S63. Description of clustering approach #5: 'RPPA CNMF subtypes'

Cluster Labels	1	2	3	4	5
Number of samples	91	23	67	75	109

'RPPA CNMF subtypes' versus 'Time to Death'

P value = 0.991 (logrank test), Q value = 1

Table S64. Clustering Approach #5: 'RPPA CNMF subtypes' versus Clinical Feature #1: 'Time to Death'

	nPatients	nDeath	Duration Range (Median), Month
ALL	354	141	0.1 - 238.3 (23.2)
subtype1	86	32	0.7 - 123.6 (23.6)
subtype2	22	7	0.1 - 73.9 (18.8)
subtype3	66	33	0.4 - 163.1 (23.3)
subtype4	73	30	1.2 - 100.6 (24.0)
subtype5	107	39	0.4 - 238.3 (23.1)

Figure S59. Get High-res Image Clustering Approach #5: 'RPPA CNMF subtypes' versus Clinical Feature #1: 'Time to Death'

'RPPA CNMF subtypes' versus 'YEARS_TO_BIRTH'

P value = 0.00173 (Kruskal-Wallis (anova)), Q value = 0.012

Table S65. Clustering Approach #5: 'RPPA CNMF subtypes' versus Clinical Feature #2: 'YEARS_TO_BIRTH'

	nPatients	Mean (Std.Dev)
ALL	344	64.4 (9.8)
subtype1	83	63.7 (10.3)
subtype2	23	65.3 (9.6)
subtype3	66	64.9 (9.3)
subtype4	68	60.6 (9.4)
subtype5	104	66.9 (9.4)

Figure S60. Get High-res Image Clustering Approach #5: 'RPPA CNMF subtypes' versus Clinical Feature #2: 'YEARS_TO_BIRTH'

'RPPA CNMF subtypes' versus 'PATHOLOGIC_STAGE'

P value = 0.329 (Fisher's exact test), Q value = 0.58

Table S66. Clustering Approach #5: 'RPPA CNMF subtypes' versus Clinical Feature #3: 'PATHOLOGIC_STAGE'

nPatients	STAGE I	STAGE IA	STAGE IB	STAGE II	STAGE IIA	STAGE IIB	STAGE IIIA	STAGE IIIB	STAGE IV
ALL	2	94	95	1	35	51	57	8	17
subtype1	1	30	23	0	10	13	11	1	1
subtype2	0	8	6	0	1	1	4	0	3
subtype3	0	11	20	0	8	10	9	3	6
subtype4	0	14	20	1	5	14	13	3	4
subtype5	1	31	26	0	11	13	20	1	3

Figure S61. Get High-res Image Clustering Approach #5: 'RPPA CNMF subtypes' versus Clinical Feature #3: 'PATHOLOGIC_STAGE'

'RPPA CNMF subtypes' versus 'PATHOLOGY_T_STAGE'

P value = 0.207 (Fisher's exact test), Q value = 0.4

Table S67. Clustering Approach #5: 'RPPA CNMF subtypes' versus Clinical Feature #4: 'PATHOLOGY_T_STAGE'

nPatients	T1	T2	T3	T4
ALL	117	203	28	16
subtype1	35	50	5	1
subtype2	8	12	1	1
subtype3	15	39	6	7
subtype4	19	46	6	4
subtype5	40	56	10	3

Figure S62. Get High-res Image Clustering Approach #5: 'RPPA CNMF subtypes' versus Clinical Feature #4: 'PATHOLOGY_T_STAGE'

'RPPA CNMF subtypes' versus 'PATHOLOGY_N_STAGE'

P value = 0.436 (Fisher's exact test), Q value = 0.64

Table S68. Clustering Approach #5: 'RPPA CNMF subtypes' versus Clinical Feature #5: 'PATHOLOGY_N_STAGE'

nPatients	N0	N1	N2+N3
ALL	225	72	59
subtype1	54	20	13
subtype2	14	4	3
subtype3	44	14	8
subtype4	41	20	14
subtype5	72	14	21

Figure S63. Get High-res Image Clustering Approach #5: 'RPPA CNMF subtypes' versus Clinical Feature #5: 'PATHOLOGY_N_STAGE'

'RPPA CNMF subtypes' versus 'PATHOLOGY_M_STAGE'

P value = 0.0484 (Fisher's exact test), Q value = 0.13

Table S69. Clustering Approach #5: 'RPPA CNMF subtypes' versus Clinical Feature #6: 'PATHOLOGY_M_STAGE'

nPatients	0	1
ALL	259	17
subtype1	67	1
subtype2	15	3
subtype3	51	6
subtype4	50	4
subtype5	76	3

Figure S64. Get High-res Image Clustering Approach #5: 'RPPA CNMF subtypes' versus Clinical Feature #6: 'PATHOLOGY_M_STAGE'

'RPPA CNMF subtypes' versus 'GENDER'

P value = 0.155 (Fisher's exact test), Q value = 0.33

Table S70. Clustering Approach #5: 'RPPA CNMF subtypes' versus Clinical Feature #7: 'GENDER'

nPatients	FEMALE	MALE
ALL	196	169
subtype1	57	34
subtype2	15	8
subtype3	32	35
subtype4	35	40
subtype5	57	52

Figure S65. Get High-res Image Clustering Approach #5: 'RPPA CNMF subtypes' versus Clinical Feature #7: 'GENDER'

'RPPA CNMF subtypes' versus 'RADIATION_THERAPY'

P value = 0.185 (Fisher's exact test), Q value = 0.38

Table S71. Clustering Approach #5: 'RPPA CNMF subtypes' versus Clinical Feature #8: 'RADIATION_THERAPY'

nPatients	NO	YES
ALL	284	46
subtype1	72	12
subtype2	16	4
subtype3	55	4
subtype4	54	14
subtype5	87	12

Figure S66. Get High-res Image Clustering Approach #5: 'RPPA CNMF subtypes' versus Clinical Feature #8: 'RADIATION_THERAPY'

'RPPA CNMF subtypes' versus 'KARNOFSKY_PERFORMANCE_SCORE'

P value = 0.237 (Kruskal-Wallis (anova)), Q value = 0.45

Table S72. Clustering Approach #5: 'RPPA CNMF subtypes' versus Clinical Feature #9: 'KARNOFSKY_PERFORMANCE_SCORE'

	nPatients	Mean (Std.Dev)
ALL	99	77.0 (30.4)
subtype1	24	69.2 (38.7)
subtype2	3	90.0 (10.0)
subtype3	23	87.0 (18.4)
subtype4	25	79.6 (29.6)
subtype5	24	70.8 (30.9)

Figure S67. Get High-res Image Clustering Approach #5: 'RPPA CNMF subtypes' versus Clinical Feature #9: 'KARNOFSKY_PERFORMANCE_SCORE'

'RPPA CNMF subtypes' versus 'HISTOLOGICAL_TYPE'

P value = 0.004 (Fisher's exact test), Q value = 0.02

Table S73. Clustering Approach #5: 'RPPA CNMF subtypes' versus Clinical Feature #10: 'HISTOLOGICAL_TYPE'

nPatients	LUNG ACINAR ADENOCARCINOMA	LUNG ADENOCARCINOMA MIXED SUBTYPE	LUNG ADENOCARCINOMA- NOT OTHERWISE SPECIFIED (NOS)	LUNG BRONCHIOLOALVEOLAR CARCINOMA MUCINOUS	LUNG BRONCHIOLOALVEOLAR CARCINOMA NONMUCINOUS	LUNG CLEAR CELL ADENOCARCINOMA	LUNG MICROPAPILLARY ADENOCARCINOMA	LUNG MUCINOUS ADENOCARCINOMA	LUNG PAPILLARY ADENOCARCINOMA	LUNG SIGNET RING ADENOCARCINOMA	LUNG SOLID PATTERN PREDOMINANT ADENOCARCINOMA	MUCINOUS (COLLOID) CARCINOMA
ALL	12	74	233	5	13	1	2	2	13	1	4	5
subtype1	2	12	67	1	3	0	0	1	4	0	0	1
subtype2	2	8	10	0	1	0	0	0	2	0	0	0
subtype3	1	22	35	0	5	0	1	0	2	0	0	1
subtype4	3	17	50	0	0	1	0	0	0	0	4	0
subtype5	4	15	71	4	4	0	1	1	5	1	0	3

Figure S68. Get High-res Image Clustering Approach #5: 'RPPA CNMF subtypes' versus Clinical Feature #10: 'HISTOLOGICAL_TYPE'

'RPPA CNMF subtypes' versus 'NUMBER_PACK_YEARS_SMOKED'

P value = 0.863 (Kruskal-Wallis (anova)), Q value = 0.93

Table S74. Clustering Approach #5: 'RPPA CNMF subtypes' versus Clinical Feature #11: 'NUMBER_PACK_YEARS_SMOKED'

	nPatients	Mean (Std.Dev)
ALL	257	41.9 (27.8)
subtype1	47	41.8 (24.1)
subtype2	19	41.3 (32.5)
subtype3	54	45.5 (31.0)
subtype4	61	41.9 (29.1)
subtype5	76	39.7 (25.5)

Figure S69. Get High-res Image Clustering Approach #5: 'RPPA CNMF subtypes' versus Clinical Feature #11: 'NUMBER_PACK_YEARS_SMOKED'

'RPPA CNMF subtypes' versus 'YEAR_OF_TOBACCO_SMOKING_ONSET'

P value = 0.000782 (Kruskal-Wallis (anova)), Q value = 0.0074

Table S75. Clustering Approach #5: 'RPPA CNMF subtypes' versus Clinical Feature #12: 'YEAR_OF_TOBACCO_SMOKING_ONSET'

	nPatients	Mean (Std.Dev)
ALL	205	1964.9 (13.0)
subtype1	33	1965.3 (13.2)
subtype2	14	1961.7 (10.8)
subtype3	45	1959.4 (11.5)
subtype4	48	1971.1 (13.5)
subtype5	65	1964.6 (12.3)

Figure S70. Get High-res Image Clustering Approach #5: 'RPPA CNMF subtypes' versus Clinical Feature #12: 'YEAR_OF_TOBACCO_SMOKING_ONSET'

'RPPA CNMF subtypes' versus 'RESIDUAL_TUMOR'

P value = 0.00764 (Fisher's exact test), Q value = 0.036

Table S76. Clustering Approach #5: 'RPPA CNMF subtypes' versus Clinical Feature #13: 'RESIDUAL_TUMOR'

nPatients	R0	R1	R2	RX
ALL	235	10	3	21
subtype1	59	3	0	5
subtype2	12	0	3	5
subtype3	50	3	0	4
subtype4	50	1	0	3
subtype5	64	3	0	4

Figure S71. Get High-res Image Clustering Approach #5: 'RPPA CNMF subtypes' versus Clinical Feature #13: 'RESIDUAL_TUMOR'

'RPPA CNMF subtypes' versus 'RACE'

P value = 0.33 (Fisher's exact test), Q value = 0.58

Table S77. Clustering Approach #5: 'RPPA CNMF subtypes' versus Clinical Feature #14: 'RACE'

nPatients	ASIAN	BLACK OR AFRICAN AMERICAN	WHITE
ALL	5	39	275
subtype1	1	6	73
subtype2	1	3	13
subtype3	1	6	52
subtype4	1	12	50
subtype5	1	12	87

Figure S72. Get High-res Image Clustering Approach #5: 'RPPA CNMF subtypes' versus Clinical Feature #14: 'RACE'

'RPPA CNMF subtypes' versus 'ETHNICITY'

P value = 0.535 (Fisher's exact test), Q value = 0.7

Table S78. Clustering Approach #5: 'RPPA CNMF subtypes' versus Clinical Feature #15: 'ETHNICITY'

nPatients	HISPANIC OR LATINO	NOT HISPANIC OR LATINO
ALL	6	261
subtype1	1	68
subtype2	0	15
subtype3	0	42
subtype4	3	51
subtype5	2	85

Figure S73. Get High-res Image Clustering Approach #5: 'RPPA CNMF subtypes' versus Clinical Feature #15: 'ETHNICITY'

Clustering Approach #6: 'RPPA cHierClus subtypes'

Table S79. Description of clustering approach #6: 'RPPA cHierClus subtypes'

Cluster Labels	1	2	3
Number of samples	167	135	63

'RPPA cHierClus subtypes' versus 'Time to Death'

P value = 0.413 (logrank test), Q value = 0.63

Table S80. Clustering Approach #6: 'RPPA cHierClus subtypes' versus Clinical Feature #1: 'Time to Death'

	nPatients	nDeath	Duration Range (Median), Month
ALL	354	141	0.1 - 238.3 (23.2)
subtype1	161	65	0.1 - 164.1 (23.1)
subtype2	130	55	0.4 - 101.7 (22.7)
subtype3	63	21	0.5 - 238.3 (23.8)

Figure S74. Get High-res Image Clustering Approach #6: 'RPPA cHierClus subtypes' versus Clinical Feature #1: 'Time to Death'

'RPPA cHierClus subtypes' versus 'YEARS_TO_BIRTH'

P value = 0.092 (Kruskal-Wallis (anova)), Q value = 0.21

Table S81. Clustering Approach #6: 'RPPA cHierClus subtypes' versus Clinical Feature #2: 'YEARS_TO_BIRTH'

	nPatients	Mean (Std.Dev)
ALL	344	64.4 (9.8)
subtype1	160	65.2 (9.3)
subtype2	124	62.7 (10.2)
subtype3	60	65.8 (10.2)

Figure S75. Get High-res Image Clustering Approach #6: 'RPPA cHierClus subtypes' versus Clinical Feature #2: 'YEARS_TO_BIRTH'

'RPPA cHierClus subtypes' versus 'PATHOLOGIC_STAGE'

P value = 0.717 (Fisher's exact test), Q value = 0.82

Table S82. Clustering Approach #6: 'RPPA cHierClus subtypes' versus Clinical Feature #3: 'PATHOLOGIC_STAGE'

nPatients	STAGE I	STAGE IA	STAGE IB	STAGE II	STAGE IIA	STAGE IIB	STAGE IIIA	STAGE IIIB	STAGE IV
ALL	2	94	95	1	35	51	57	8	17
subtype1	1	50	40	0	14	20	27	4	9
subtype2	1	27	38	1	13	26	20	3	5
subtype3	0	17	17	0	8	5	10	1	3

Figure S76. Get High-res Image Clustering Approach #6: 'RPPA cHierClus subtypes' versus Clinical Feature #3: 'PATHOLOGIC_STAGE'

'RPPA cHierClus subtypes' versus 'PATHOLOGY_T_STAGE'

P value = 0.104 (Fisher's exact test), Q value = 0.23

Table S83. Clustering Approach #6: 'RPPA cHierClus subtypes' versus Clinical Feature #4: 'PATHOLOGY_T_STAGE'

nPatients	T1	T2	T3	T4
ALL	117	203	28	16
subtype1	61	86	9	10
subtype2	34	83	15	3
subtype3	22	34	4	3

Figure S77. Get High-res Image Clustering Approach #6: 'RPPA cHierClus subtypes' versus Clinical Feature #4: 'PATHOLOGY_T_STAGE'

'RPPA cHierClus subtypes' versus 'PATHOLOGY_N_STAGE'

P value = 0.482 (Fisher's exact test), Q value = 0.67

Table S84. Clustering Approach #6: 'RPPA cHierClus subtypes' versus Clinical Feature #5: 'PATHOLOGY_N_STAGE'

nPatients	N0	N1	N2+N3
ALL	225	72	59
subtype1	102	31	27
subtype2	81	33	21
subtype3	42	8	11

Figure S78. Get High-res Image Clustering Approach #6: 'RPPA cHierClus subtypes' versus Clinical Feature #5: 'PATHOLOGY_N_STAGE'

'RPPA cHierClus subtypes' versus 'PATHOLOGY_M_STAGE'

P value = 0.789 (Fisher's exact test), Q value = 0.88

Table S85. Clustering Approach #6: 'RPPA cHierClus subtypes' versus Clinical Feature #6: 'PATHOLOGY_M_STAGE'

nPatients	0	1
ALL	259	17
subtype1	121	9
subtype2	97	5
subtype3	41	3

Figure S79. Get High-res Image Clustering Approach #6: 'RPPA cHierClus subtypes' versus Clinical Feature #6: 'PATHOLOGY_M_STAGE'

'RPPA cHierClus subtypes' versus 'GENDER'

P value = 0.533 (Fisher's exact test), Q value = 0.7

Table S86. Clustering Approach #6: 'RPPA cHierClus subtypes' versus Clinical Feature #7: 'GENDER'

nPatients	FEMALE	MALE
ALL	196	169
subtype1	91	76
subtype2	68	67
subtype3	37	26

Figure S80. Get High-res Image Clustering Approach #6: 'RPPA cHierClus subtypes' versus Clinical Feature #7: 'GENDER'

'RPPA cHierClus subtypes' versus 'RADIATION_THERAPY'

P value = 0.227 (Fisher's exact test), Q value = 0.44

Table S87. Clustering Approach #6: 'RPPA cHierClus subtypes' versus Clinical Feature #8: 'RADIATION_THERAPY'

nPatients	NO	YES
ALL	284	46
subtype1	133	17
subtype2	98	22
subtype3	53	7

Figure S81. Get High-res Image Clustering Approach #6: 'RPPA cHierClus subtypes' versus Clinical Feature #8: 'RADIATION_THERAPY'

'RPPA cHierClus subtypes' versus 'KARNOFSKY_PERFORMANCE_SCORE'

P value = 0.644 (Kruskal-Wallis (anova)), Q value = 0.8

Table S88. Clustering Approach #6: 'RPPA cHierClus subtypes' versus Clinical Feature #9: 'KARNOFSKY_PERFORMANCE_SCORE'

	nPatients	Mean (Std.Dev)
ALL	99	77.0 (30.4)
subtype1	42	77.4 (30.4)
subtype2	40	78.2 (31.1)
subtype3	17	72.9 (30.2)

Figure S82. Get High-res Image Clustering Approach #6: 'RPPA cHierClus subtypes' versus Clinical Feature #9: 'KARNOFSKY_PERFORMANCE_SCORE'

'RPPA cHierClus subtypes' versus 'HISTOLOGICAL_TYPE'

P value = 0.00132 (Fisher's exact test), Q value = 0.011

Table S89. Clustering Approach #6: 'RPPA cHierClus subtypes' versus Clinical Feature #10: 'HISTOLOGICAL_TYPE'

nPatients	LUNG ACINAR ADENOCARCINOMA	LUNG ADENOCARCINOMA MIXED SUBTYPE	LUNG ADENOCARCINOMA- NOT OTHERWISE SPECIFIED (NOS)	LUNG BRONCHIOLOALVEOLAR CARCINOMA MUCINOUS	LUNG BRONCHIOLOALVEOLAR CARCINOMA NONMUCINOUS	LUNG CLEAR CELL ADENOCARCINOMA	LUNG MICROPAPILLARY ADENOCARCINOMA	LUNG MUCINOUS ADENOCARCINOMA	LUNG PAPILLARY ADENOCARCINOMA	LUNG SIGNET RING ADENOCARCINOMA	LUNG SOLID PATTERN PREDOMINANT ADENOCARCINOMA	MUCINOUS (COLLOID) CARCINOMA
ALL	12	74	233	5	13	1	2	2	13	1	4	5
subtype1	5	42	94	2	8	1	2	1	8	1	0	3
subtype2	3	21	103	0	1	0	0	1	1	0	4	1
subtype3	4	11	36	3	4	0	0	0	4	0	0	1

Figure S83. Get High-res Image Clustering Approach #6: 'RPPA cHierClus subtypes' versus Clinical Feature #10: 'HISTOLOGICAL_TYPE'

'RPPA cHierClus subtypes' versus 'NUMBER_PACK_YEARS_SMOKED'

P value = 1 (Kruskal-Wallis (anova)), Q value = 1

Table S90. Clustering Approach #6: 'RPPA cHierClus subtypes' versus Clinical Feature #11: 'NUMBER_PACK_YEARS_SMOKED'

	nPatients	Mean (Std.Dev)
ALL	257	41.9 (27.8)
subtype1	111	42.8 (29.9)
subtype2	95	42.1 (28.1)
subtype3	51	39.7 (21.9)

Figure S84. Get High-res Image Clustering Approach #6: 'RPPA cHierClus subtypes' versus Clinical Feature #11: 'NUMBER_PACK_YEARS_SMOKED'

'RPPA cHierClus subtypes' versus 'YEAR_OF_TOBACCO_SMOKING_ONSET'

P value = 0.00327 (Kruskal-Wallis (anova)), Q value = 0.017

Table S91. Clustering Approach #6: 'RPPA cHierClus subtypes' versus Clinical Feature #12: 'YEAR_OF_TOBACCO_SMOKING_ONSET'

	nPatients	Mean (Std.Dev)
ALL	205	1964.9 (13.0)
subtype1	86	1961.1 (12.2)
subtype2	74	1968.4 (13.5)
subtype3	45	1966.3 (12.2)

Figure S85. Get High-res Image Clustering Approach #6: 'RPPA cHierClus subtypes' versus Clinical Feature #12: 'YEAR_OF_TOBACCO_SMOKING_ONSET'

'RPPA cHierClus subtypes' versus 'RESIDUAL_TUMOR'

P value = 0.867 (Fisher's exact test), Q value = 0.93

Table S92. Clustering Approach #6: 'RPPA cHierClus subtypes' versus Clinical Feature #13: 'RESIDUAL_TUMOR'

nPatients	R0	R1	R2	RX
ALL	235	10	3	21
subtype1	110	6	2	13
subtype2	88	3	1	5
subtype3	37	1	0	3

Figure S86. Get High-res Image Clustering Approach #6: 'RPPA cHierClus subtypes' versus Clinical Feature #13: 'RESIDUAL_TUMOR'

'RPPA cHierClus subtypes' versus 'RACE'

P value = 0.35 (Fisher's exact test), Q value = 0.6

Table S93. Clustering Approach #6: 'RPPA cHierClus subtypes' versus Clinical Feature #14: 'RACE'

nPatients	ASIAN	BLACK OR AFRICAN AMERICAN	WHITE
ALL	5	39	275
subtype1	2	14	126
subtype2	3	19	94
subtype3	0	6	55

Figure S87. Get High-res Image Clustering Approach #6: 'RPPA cHierClus subtypes' versus Clinical Feature #14: 'RACE'

'RPPA cHierClus subtypes' versus 'ETHNICITY'

P value = 0.0471 (Fisher's exact test), Q value = 0.13

Table S94. Clustering Approach #6: 'RPPA cHierClus subtypes' versus Clinical Feature #15: 'ETHNICITY'

nPatients	HISPANIC OR LATINO	NOT HISPANIC OR LATINO
ALL	6	261
subtype1	0	117
subtype2	4	95
subtype3	2	49

Figure S88. Get High-res Image Clustering Approach #6: 'RPPA cHierClus subtypes' versus Clinical Feature #15: 'ETHNICITY'

Clustering Approach #7: 'RNAseq CNMF subtypes'

Table S95. Description of clustering approach #7: 'RNAseq CNMF subtypes'

Cluster Labels	1	2	3	4	5
Number of samples	132	120	90	115	58

'RNAseq CNMF subtypes' versus 'Time to Death'

P value = 3.96e-12 (logrank test), Q value = 7.1e-10

Table S96. Clustering Approach #7: 'RNAseq CNMF subtypes' versus Clinical Feature #1: 'Time to Death'

	nPatients	nDeath	Duration Range (Median), Month
ALL	503	183	0.0 - 238.3 (21.6)
subtype1	129	49	0.4 - 163.1 (23.2)
subtype2	117	30	0.1 - 120.8 (21.4)
subtype3	89	55	0.0 - 100.6 (16.4)
subtype4	113	35	1.2 - 238.3 (25.0)
subtype5	55	14	0.5 - 164.1 (22.6)

Figure S89. Get High-res Image Clustering Approach #7: 'RNAseq CNMF subtypes' versus Clinical Feature #1: 'Time to Death'

'RNAseq CNMF subtypes' versus 'YEARS_TO_BIRTH'

P value = 0.000247 (Kruskal-Wallis (anova)), Q value = 0.004

Table S97. Clustering Approach #7: 'RNAseq CNMF subtypes' versus Clinical Feature #2: 'YEARS_TO_BIRTH'

	nPatients	Mean (Std.Dev)
ALL	484	65.3 (9.9)
subtype1	125	63.2 (10.0)
subtype2	113	68.4 (8.3)
subtype3	84	66.6 (10.2)
subtype4	108	63.5 (9.9)
subtype5	54	65.2 (11.1)

Figure S90. Get High-res Image Clustering Approach #7: 'RNAseq CNMF subtypes' versus Clinical Feature #2: 'YEARS_TO_BIRTH'

'RNAseq CNMF subtypes' versus 'PATHOLOGIC_STAGE'

P value = 0.00329 (Fisher's exact test), Q value = 0.017

Table S98. Clustering Approach #7: 'RNAseq CNMF subtypes' versus Clinical Feature #3: 'PATHOLOGIC_STAGE'

nPatients	STAGE I	STAGE IA	STAGE IB	STAGE II	STAGE IIA	STAGE IIB	STAGE IIIA	STAGE IIIB	STAGE IV
ALL	5	131	139	1	50	71	73	11	26
subtype1	2	23	37	1	15	26	17	4	5
subtype2	0	46	30	0	9	11	15	1	4
subtype3	1	11	22	0	7	16	22	3	8
subtype4	1	28	37	0	12	12	13	3	7
subtype5	1	23	13	0	7	6	6	0	2

Figure S91. Get High-res Image Clustering Approach #7: 'RNAseq CNMF subtypes' versus Clinical Feature #3: 'PATHOLOGIC_STAGE'

'RNAseq CNMF subtypes' versus 'PATHOLOGY_T_STAGE'

P value = 4e-05 (Fisher's exact test), Q value = 0.0014

Table S99. Clustering Approach #7: 'RNAseq CNMF subtypes' versus Clinical Feature #4: 'PATHOLOGY_T_STAGE'

nPatients	T1	T2	T3	T4
ALL	169	277	47	19
subtype1	33	82	11	5
subtype2	57	49	8	5
subtype3	16	54	13	6
subtype4	33	70	9	3
subtype5	30	22	6	0

Figure S92. Get High-res Image Clustering Approach #7: 'RNAseq CNMF subtypes' versus Clinical Feature #4: 'PATHOLOGY_T_STAGE'

'RNAseq CNMF subtypes' versus 'PATHOLOGY_N_STAGE'

P value = 0.00124 (Fisher's exact test), Q value = 0.011

Table S100. Clustering Approach #7: 'RNAseq CNMF subtypes' versus Clinical Feature #5: 'PATHOLOGY_N_STAGE'

nPatients	N0	N1	N2+N3
ALL	331	96	76
subtype1	72	35	22
subtype2	86	17	12
subtype3	47	20	22
subtype4	87	13	14
subtype5	39	11	6

Figure S93. Get High-res Image Clustering Approach #7: 'RNAseq CNMF subtypes' versus Clinical Feature #5: 'PATHOLOGY_N_STAGE'

'RNAseq CNMF subtypes' versus 'PATHOLOGY_M_STAGE'

P value = 0.471 (Fisher's exact test), Q value = 0.66

Table S101. Clustering Approach #7: 'RNAseq CNMF subtypes' versus Clinical Feature #6: 'PATHOLOGY_M_STAGE'

nPatients	0	1
ALL	346	25
subtype1	86	4
subtype2	81	4
subtype3	65	8
subtype4	79	7
subtype5	35	2

Figure S94. Get High-res Image Clustering Approach #7: 'RNAseq CNMF subtypes' versus Clinical Feature #6: 'PATHOLOGY_M_STAGE'

'RNAseq CNMF subtypes' versus 'GENDER'

P value = 0.00035 (Fisher's exact test), Q value = 0.0049

Table S102. Clustering Approach #7: 'RNAseq CNMF subtypes' versus Clinical Feature #7: 'GENDER'

nPatients	FEMALE	MALE
ALL	277	238
subtype1	76	56
subtype2	79	41
subtype3	39	51
subtype4	47	68
subtype5	36	22

Figure S95. Get High-res Image Clustering Approach #7: 'RNAseq CNMF subtypes' versus Clinical Feature #7: 'GENDER'

'RNAseq CNMF subtypes' versus 'RADIATION_THERAPY'

P value = 0.0517 (Fisher's exact test), Q value = 0.13

Table S103. Clustering Approach #7: 'RNAseq CNMF subtypes' versus Clinical Feature #8: 'RADIATION_THERAPY'

nPatients	NO	YES
ALL	408	61
subtype1	110	15
subtype2	99	8
subtype3	60	17
subtype4	89	16
subtype5	50	5

Figure S96. Get High-res Image Clustering Approach #7: 'RNAseq CNMF subtypes' versus Clinical Feature #8: 'RADIATION_THERAPY'

'RNAseq CNMF subtypes' versus 'KARNOFSKY_PERFORMANCE_SCORE'

P value = 0.573 (Kruskal-Wallis (anova)), Q value = 0.74

Table S104. Clustering Approach #7: 'RNAseq CNMF subtypes' versus Clinical Feature #9: 'KARNOFSKY_PERFORMANCE_SCORE'

	nPatients	Mean (Std.Dev)
ALL	135	78.4 (28.7)
subtype1	42	74.8 (32.3)
subtype2	26	86.2 (21.7)
subtype3	18	75.6 (32.6)
subtype4	32	78.8 (27.3)
subtype5	17	77.6 (27.5)

Figure S97. Get High-res Image Clustering Approach #7: 'RNAseq CNMF subtypes' versus Clinical Feature #9: 'KARNOFSKY_PERFORMANCE_SCORE'

'RNAseq CNMF subtypes' versus 'HISTOLOGICAL_TYPE'

P value = 0.00218 (Fisher's exact test), Q value = 0.014

Table S105. Clustering Approach #7: 'RNAseq CNMF subtypes' versus Clinical Feature #10: 'HISTOLOGICAL_TYPE'

nPatients	LUNG ACINAR ADENOCARCINOMA	LUNG ADENOCARCINOMA MIXED SUBTYPE	LUNG ADENOCARCINOMA- NOT OTHERWISE SPECIFIED (NOS)	LUNG BRONCHIOLOALVEOLAR CARCINOMA MUCINOUS	LUNG BRONCHIOLOALVEOLAR CARCINOMA NONMUCINOUS	LUNG CLEAR CELL ADENOCARCINOMA	LUNG MICROPAPILLARY ADENOCARCINOMA	LUNG MUCINOUS ADENOCARCINOMA	LUNG PAPILLARY ADENOCARCINOMA	LUNG SIGNET RING ADENOCARCINOMA	LUNG SOLID PATTERN PREDOMINANT ADENOCARCINOMA	MUCINOUS (COLLOID) CARCINOMA
ALL	18	107	320	5	19	2	3	2	23	1	5	10
subtype1	1	25	95	0	6	1	2	0	2	0	0	0
subtype2	7	29	61	3	7	0	1	1	9	0	0	2
subtype3	3	18	59	1	1	1	0	0	1	0	2	4
subtype4	6	21	75	0	2	0	0	0	8	0	2	1
subtype5	1	14	30	1	3	0	0	1	3	1	1	3

Figure S98. Get High-res Image Clustering Approach #7: 'RNAseq CNMF subtypes' versus Clinical Feature #10: 'HISTOLOGICAL_TYPE'

'RNAseq CNMF subtypes' versus 'NUMBER_PACK_YEARS_SMOKED'

P value = 0.204 (Kruskal-Wallis (anova)), Q value = 0.4

Table S106. Clustering Approach #7: 'RNAseq CNMF subtypes' versus Clinical Feature #11: 'NUMBER_PACK_YEARS_SMOKED'

	nPatients	Mean (Std.Dev)
ALL	350	41.8 (27.2)
subtype1	85	46.1 (28.2)
subtype2	73	36.5 (24.5)
subtype3	65	40.7 (24.6)
subtype4	91	43.2 (30.1)
subtype5	36	40.8 (25.8)

Figure S99. Get High-res Image Clustering Approach #7: 'RNAseq CNMF subtypes' versus Clinical Feature #11: 'NUMBER_PACK_YEARS_SMOKED'

'RNAseq CNMF subtypes' versus 'YEAR_OF_TOBACCO_SMOKING_ONSET'

P value = 0.278 (Kruskal-Wallis (anova)), Q value = 0.52

Table S107. Clustering Approach #7: 'RNAseq CNMF subtypes' versus Clinical Feature #12: 'YEAR_OF_TOBACCO_SMOKING_ONSET'

	nPatients	Mean (Std.Dev)
ALL	274	1965.0 (12.5)
subtype1	66	1966.0 (13.3)
subtype2	60	1962.2 (10.5)
subtype3	49	1963.6 (14.0)
subtype4	70	1966.3 (12.3)
subtype5	29	1967.5 (11.4)

Figure S100. Get High-res Image Clustering Approach #7: 'RNAseq CNMF subtypes' versus Clinical Feature #12: 'YEAR_OF_TOBACCO_SMOKING_ONSET'

'RNAseq CNMF subtypes' versus 'RESIDUAL_TUMOR'

P value = 0.709 (Fisher's exact test), Q value = 0.82

Table S108. Clustering Approach #7: 'RNAseq CNMF subtypes' versus Clinical Feature #13: 'RESIDUAL_TUMOR'

nPatients	R0	R1	R2	RX
ALL	344	13	4	25
subtype1	88	4	1	6
subtype2	76	4	0	6
subtype3	59	2	2	3
subtype4	83	3	0	5
subtype5	38	0	1	5

Figure S101. Get High-res Image Clustering Approach #7: 'RNAseq CNMF subtypes' versus Clinical Feature #13: 'RESIDUAL_TUMOR'

'RNAseq CNMF subtypes' versus 'RACE'

P value = 0.557 (Fisher's exact test), Q value = 0.72

Table S109. Clustering Approach #7: 'RNAseq CNMF subtypes' versus Clinical Feature #14: 'RACE'

nPatients	AMERICAN INDIAN OR ALASKA NATIVE	ASIAN	BLACK OR AFRICAN AMERICAN	WHITE
ALL	1	8	52	388
subtype1	1	3	14	99
subtype2	0	2	11	95
subtype3	0	1	4	70
subtype4	0	2	16	79
subtype5	0	0	7	45

Figure S102. Get High-res Image Clustering Approach #7: 'RNAseq CNMF subtypes' versus Clinical Feature #14: 'RACE'

'RNAseq CNMF subtypes' versus 'ETHNICITY'

P value = 0.746 (Fisher's exact test), Q value = 0.84

Table S110. Clustering Approach #7: 'RNAseq CNMF subtypes' versus Clinical Feature #15: 'ETHNICITY'

nPatients	HISPANIC OR LATINO	NOT HISPANIC OR LATINO
ALL	7	383
subtype1	1	102
subtype2	1	94
subtype3	2	59
subtype4	2	79
subtype5	1	49

Figure S103. Get High-res Image Clustering Approach #7: 'RNAseq CNMF subtypes' versus Clinical Feature #15: 'ETHNICITY'

Clustering Approach #8: 'RNAseq cHierClus subtypes'

Table S111. Description of clustering approach #8: 'RNAseq cHierClus subtypes'

Cluster Labels	1	2	3	4	5	6	7
Number of samples	79	112	97	48	53	49	77

'RNAseq cHierClus subtypes' versus 'Time to Death'

P value = 9.1e-08 (logrank test), Q value = 8.2e-06

Table S112. Clustering Approach #8: 'RNAseq cHierClus subtypes' versus Clinical Feature #1: 'Time to Death'

	nPatients	nDeath	Duration Range (Median), Month
ALL	503	183	0.0 - 238.3 (21.6)
subtype1	76	25	0.1 - 163.1 (21.5)
subtype2	108	35	0.4 - 97.7 (21.1)
subtype3	97	40	0.7 - 238.3 (21.4)
subtype4	47	17	0.4 - 129.5 (29.2)
subtype5	51	14	1.4 - 93.1 (20.3)
subtype6	49	33	0.0 - 100.6 (15.2)
subtype7	75	19	0.5 - 164.1 (23.9)

Figure S104. Get High-res Image Clustering Approach #8: 'RNAseq cHierClus subtypes' versus Clinical Feature #1: 'Time to Death'

'RNAseq cHierClus subtypes' versus 'YEARS_TO_BIRTH'

P value = 0.00058 (Kruskal-Wallis (anova)), Q value = 0.0061

Table S113. Clustering Approach #8: 'RNAseq cHierClus subtypes' versus Clinical Feature #2: 'YEARS_TO_BIRTH'

	nPatients	Mean (Std.Dev)
ALL	484	65.3 (9.9)
subtype1	75	68.3 (9.2)
subtype2	103	63.5 (10.8)
subtype3	90	65.5 (9.7)
subtype4	46	67.7 (7.7)
subtype5	50	60.7 (9.5)
subtype6	47	66.0 (9.9)
subtype7	73	65.5 (10.2)

Figure S105. Get High-res Image Clustering Approach #8: 'RNAseq cHierClus subtypes' versus Clinical Feature #2: 'YEARS_TO_BIRTH'

'RNAseq cHierClus subtypes' versus 'PATHOLOGIC_STAGE'

P value = 0.00802 (Fisher's exact test), Q value = 0.037

Table S114. Clustering Approach #8: 'RNAseq cHierClus subtypes' versus Clinical Feature #3: 'PATHOLOGIC_STAGE'

nPatients	STAGE I	STAGE IA	STAGE IB	STAGE II	STAGE IIA	STAGE IIB	STAGE IIIA	STAGE IIIB	STAGE IV
ALL	5	131	139	1	50	71	73	11	26
subtype1	0	30	22	0	6	7	9	1	3
subtype2	1	16	35	0	10	23	18	3	5
subtype3	3	25	27	1	14	7	11	2	6
subtype4	0	15	16	0	4	5	3	2	2
subtype5	0	11	15	0	6	5	12	1	2
subtype6	0	7	7	0	3	12	12	2	6
subtype7	1	27	17	0	7	12	8	0	2

Figure S106. Get High-res Image Clustering Approach #8: 'RNAseq cHierClus subtypes' versus Clinical Feature #3: 'PATHOLOGIC_STAGE'

'RNAseq cHierClus subtypes' versus 'PATHOLOGY_T_STAGE'

P value = 0.00171 (Fisher's exact test), Q value = 0.012

Table S115. Clustering Approach #8: 'RNAseq cHierClus subtypes' versus Clinical Feature #4: 'PATHOLOGY_T_STAGE'

nPatients	T1	T2	T3	T4
ALL	169	277	47	19
subtype1	36	36	4	3
subtype2	24	69	13	5
subtype3	39	51	3	3
subtype4	17	24	4	3
subtype5	12	35	5	1
subtype6	8	29	8	3
subtype7	33	33	10	1

Figure S107. Get High-res Image Clustering Approach #8: 'RNAseq cHierClus subtypes' versus Clinical Feature #4: 'PATHOLOGY_T_STAGE'

'RNAseq cHierClus subtypes' versus 'PATHOLOGY_N_STAGE'

P value = 0.00299 (Fisher's exact test), Q value = 0.016

Table S116. Clustering Approach #8: 'RNAseq cHierClus subtypes' versus Clinical Feature #5: 'PATHOLOGY_N_STAGE'

nPatients	N0	N1	N2+N3
ALL	331	96	76
subtype1	57	12	9
subtype2	66	25	19
subtype3	60	23	12
subtype4	37	8	2
subtype5	37	3	12
subtype6	22	12	14
subtype7	52	13	8

Figure S108. Get High-res Image Clustering Approach #8: 'RNAseq cHierClus subtypes' versus Clinical Feature #5: 'PATHOLOGY_N_STAGE'

'RNAseq cHierClus subtypes' versus 'PATHOLOGY_M_STAGE'

P value = 0.509 (Fisher's exact test), Q value = 0.68

Table S117. Clustering Approach #8: 'RNAseq cHierClus subtypes' versus Clinical Feature #6: 'PATHOLOGY_M_STAGE'

nPatients	0	1
ALL	346	25
subtype1	52	3
subtype2	79	4
subtype3	55	6
subtype4	38	2
subtype5	38	2
subtype6	37	6
subtype7	47	2

Figure S109. Get High-res Image Clustering Approach #8: 'RNAseq cHierClus subtypes' versus Clinical Feature #6: 'PATHOLOGY_M_STAGE'

'RNAseq cHierClus subtypes' versus 'GENDER'

P value = 1e-05 (Fisher's exact test), Q value = 6e-04

Table S118. Clustering Approach #8: 'RNAseq cHierClus subtypes' versus Clinical Feature #7: 'GENDER'

nPatients	FEMALE	MALE
ALL	277	238
subtype1	63	16
subtype2	59	53
subtype3	52	45
subtype4	16	32
subtype5	24	29
subtype6	19	30
subtype7	44	33

Figure S110. Get High-res Image Clustering Approach #8: 'RNAseq cHierClus subtypes' versus Clinical Feature #7: 'GENDER'

'RNAseq cHierClus subtypes' versus 'RADIATION_THERAPY'

P value = 0.0664 (Fisher's exact test), Q value = 0.16

Table S119. Clustering Approach #8: 'RNAseq cHierClus subtypes' versus Clinical Feature #8: 'RADIATION_THERAPY'

nPatients	NO	YES
ALL	408	61
subtype1	68	4
subtype2	92	11
subtype3	75	15
subtype4	38	3
subtype5	43	6
subtype6	34	11
subtype7	58	11

Figure S111. Get High-res Image Clustering Approach #8: 'RNAseq cHierClus subtypes' versus Clinical Feature #8: 'RADIATION_THERAPY'

'RNAseq cHierClus subtypes' versus 'KARNOFSKY_PERFORMANCE_SCORE'

P value = 0.431 (Kruskal-Wallis (anova)), Q value = 0.64

Table S120. Clustering Approach #8: 'RNAseq cHierClus subtypes' versus Clinical Feature #9: 'KARNOFSKY_PERFORMANCE_SCORE'

	nPatients	Mean (Std.Dev)
ALL	135	78.4 (28.7)
subtype1	16	85.6 (26.3)
subtype2	28	77.9 (28.6)
subtype3	34	79.7 (28.4)
subtype4	11	89.1 (13.0)
subtype5	15	68.0 (35.9)
subtype6	10	72.0 (33.3)
subtype7	21	76.2 (29.1)

Figure S112. Get High-res Image Clustering Approach #8: 'RNAseq cHierClus subtypes' versus Clinical Feature #9: 'KARNOFSKY_PERFORMANCE_SCORE'

'RNAseq cHierClus subtypes' versus 'HISTOLOGICAL_TYPE'

P value = 8e-05 (Fisher's exact test), Q value = 0.0018

Table S121. Clustering Approach #8: 'RNAseq cHierClus subtypes' versus Clinical Feature #10: 'HISTOLOGICAL_TYPE'

nPatients	LUNG ACINAR ADENOCARCINOMA	LUNG ADENOCARCINOMA MIXED SUBTYPE	LUNG ADENOCARCINOMA- NOT OTHERWISE SPECIFIED (NOS)	LUNG BRONCHIOLOALVEOLAR CARCINOMA MUCINOUS	LUNG BRONCHIOLOALVEOLAR CARCINOMA NONMUCINOUS	LUNG CLEAR CELL ADENOCARCINOMA	LUNG MICROPAPILLARY ADENOCARCINOMA	LUNG MUCINOUS ADENOCARCINOMA	LUNG PAPILLARY ADENOCARCINOMA	LUNG SIGNET RING ADENOCARCINOMA	LUNG SOLID PATTERN PREDOMINANT ADENOCARCINOMA	MUCINOUS (COLLOID) CARCINOMA
ALL	18	107	320	5	19	2	3	2	23	1	5	10
subtype1	5	16	45	1	6	0	1	0	5	0	0	0
subtype2	1	19	81	0	3	1	2	0	4	0	1	0
subtype3	3	15	71	1	2	1	0	0	2	0	2	0
subtype4	2	19	18	0	1	0	0	0	7	0	0	1
subtype5	4	10	37	0	1	0	0	0	0	0	0	1
subtype6	1	12	31	0	0	0	0	0	2	0	1	2
subtype7	2	16	37	3	6	0	0	2	3	1	1	6

Figure S113. Get High-res Image Clustering Approach #8: 'RNAseq cHierClus subtypes' versus Clinical Feature #10: 'HISTOLOGICAL_TYPE'

'RNAseq cHierClus subtypes' versus 'NUMBER_PACK_YEARS_SMOKED'

P value = 0.0637 (Kruskal-Wallis (anova)), Q value = 0.16

Table S122. Clustering Approach #8: 'RNAseq cHierClus subtypes' versus Clinical Feature #11: 'NUMBER_PACK_YEARS_SMOKED'

	nPatients	Mean (Std.Dev)
ALL	350	41.8 (27.2)
subtype1	45	36.2 (25.4)
subtype2	78	41.1 (25.7)
subtype3	64	49.9 (31.5)
subtype4	37	40.4 (30.5)
subtype5	42	38.2 (25.6)
subtype6	39	45.9 (24.1)
subtype7	45	38.2 (24.2)

Figure S114. Get High-res Image Clustering Approach #8: 'RNAseq cHierClus subtypes' versus Clinical Feature #11: 'NUMBER_PACK_YEARS_SMOKED'

'RNAseq cHierClus subtypes' versus 'YEAR_OF_TOBACCO_SMOKING_ONSET'

P value = 0.000412 (Kruskal-Wallis (anova)), Q value = 0.0049

Table S123. Clustering Approach #8: 'RNAseq cHierClus subtypes' versus Clinical Feature #12: 'YEAR_OF_TOBACCO_SMOKING_ONSET'

	nPatients	Mean (Std.Dev)
ALL	274	1965.0 (12.5)
subtype1	37	1963.0 (10.3)
subtype2	59	1967.5 (14.2)
subtype3	50	1963.5 (12.3)
subtype4	29	1956.9 (11.4)
subtype5	35	1970.3 (9.6)
subtype6	29	1965.1 (13.3)
subtype7	35	1966.2 (11.2)

Figure S115. Get High-res Image Clustering Approach #8: 'RNAseq cHierClus subtypes' versus Clinical Feature #12: 'YEAR_OF_TOBACCO_SMOKING_ONSET'

'RNAseq cHierClus subtypes' versus 'RESIDUAL_TUMOR'

P value = 0.329 (Fisher's exact test), Q value = 0.58

Table S124. Clustering Approach #8: 'RNAseq cHierClus subtypes' versus Clinical Feature #13: 'RESIDUAL_TUMOR'

nPatients	R0	R1	R2	RX
ALL	344	13	4	25
subtype1	55	4	0	2
subtype2	77	2	2	3
subtype3	58	3	2	9
subtype4	28	0	0	3
subtype5	38	1	0	2
subtype6	35	3	0	2
subtype7	53	0	0	4

Figure S116. Get High-res Image Clustering Approach #8: 'RNAseq cHierClus subtypes' versus Clinical Feature #13: 'RESIDUAL_TUMOR'

'RNAseq cHierClus subtypes' versus 'RACE'

P value = 0.581 (Fisher's exact test), Q value = 0.74

Table S125. Clustering Approach #8: 'RNAseq cHierClus subtypes' versus Clinical Feature #14: 'RACE'

nPatients	AMERICAN INDIAN OR ALASKA NATIVE	ASIAN	BLACK OR AFRICAN AMERICAN	WHITE
ALL	1	8	52	388
subtype1	0	2	6	62
subtype2	1	3	9	84
subtype3	0	1	14	70
subtype4	0	0	5	37
subtype5	0	0	6	38
subtype6	0	2	2	38
subtype7	0	0	10	59

Figure S117. Get High-res Image Clustering Approach #8: 'RNAseq cHierClus subtypes' versus Clinical Feature #14: 'RACE'

'RNAseq cHierClus subtypes' versus 'ETHNICITY'

P value = 0.0341 (Fisher's exact test), Q value = 0.11

Table S126. Clustering Approach #8: 'RNAseq cHierClus subtypes' versus Clinical Feature #15: 'ETHNICITY'

nPatients	HISPANIC OR LATINO	NOT HISPANIC OR LATINO
ALL	7	383
subtype1	1	60
subtype2	0	85
subtype3	4	71
subtype4	0	34
subtype5	0	37
subtype6	2	31
subtype7	0	65

Figure S118. Get High-res Image Clustering Approach #8: 'RNAseq cHierClus subtypes' versus Clinical Feature #15: 'ETHNICITY'

Clustering Approach #9: 'MIRSEQ CNMF'

Table S127. Description of clustering approach #9: 'MIRSEQ CNMF'

Cluster Labels	1	2	3
Number of samples	187	221	105

'MIRSEQ CNMF' versus 'Time to Death'

P value = 0.204 (logrank test), Q value = 0.4

Table S128. Clustering Approach #9: 'MIRSEQ CNMF' versus Clinical Feature #1: 'Time to Death'

	nPatients	nDeath	Duration Range (Median), Month
ALL	501	182	0.0 - 238.3 (21.6)
subtype1	182	61	0.4 - 164.1 (21.5)
subtype2	217	75	0.0 - 232.2 (21.9)
subtype3	102	46	0.1 - 238.3 (21.6)

Figure S119. Get High-res Image Clustering Approach #9: 'MIRSEQ CNMF' versus Clinical Feature #1: 'Time to Death'

'MIRSEQ CNMF' versus 'YEARS_TO_BIRTH'

P value = 0.0297 (Kruskal-Wallis (anova)), Q value = 0.1

Table S129. Clustering Approach #9: 'MIRSEQ CNMF' versus Clinical Feature #2: 'YEARS_TO_BIRTH'

	nPatients	Mean (Std.Dev)
ALL	483	65.3 (9.9)
subtype1	178	66.8 (9.6)
subtype2	211	64.3 (10.1)
subtype3	94	64.7 (10.0)

Figure S120. Get High-res Image Clustering Approach #9: 'MIRSEQ CNMF' versus Clinical Feature #2: 'YEARS_TO_BIRTH'

'MIRSEQ CNMF' versus 'PATHOLOGIC_STAGE'

P value = 0.00613 (Fisher's exact test), Q value = 0.03

Table S130. Clustering Approach #9: 'MIRSEQ CNMF' versus Clinical Feature #3: 'PATHOLOGIC_STAGE'

nPatients	STAGE I	STAGE IA	STAGE IB	STAGE II	STAGE IIA	STAGE IIB	STAGE IIIA	STAGE IIIB	STAGE IV
ALL	5	133	139	1	50	70	73	11	24
subtype1	1	67	40	0	18	24	22	2	8
subtype2	4	51	66	0	20	32	27	7	12
subtype3	0	15	33	1	12	14	24	2	4

Figure S121. Get High-res Image Clustering Approach #9: 'MIRSEQ CNMF' versus Clinical Feature #3: 'PATHOLOGIC_STAGE'

'MIRSEQ CNMF' versus 'PATHOLOGY_T_STAGE'

P value = 0.0304 (Fisher's exact test), Q value = 0.1

Table S131. Clustering Approach #9: 'MIRSEQ CNMF' versus Clinical Feature #4: 'PATHOLOGY_T_STAGE'

nPatients	T1	T2	T3	T4
ALL	170	274	47	19
subtype1	80	85	15	7
subtype2	65	123	23	8
subtype3	25	66	9	4

Figure S122. Get High-res Image Clustering Approach #9: 'MIRSEQ CNMF' versus Clinical Feature #4: 'PATHOLOGY_T_STAGE'

'MIRSEQ CNMF' versus 'PATHOLOGY_N_STAGE'

P value = 0.308 (Fisher's exact test), Q value = 0.56

Table S132. Clustering Approach #9: 'MIRSEQ CNMF' versus Clinical Feature #5: 'PATHOLOGY_N_STAGE'

nPatients	N0	N1	N2+N3
ALL	330	95	76
subtype1	120	38	23
subtype2	148	37	31
subtype3	62	20	22

Figure S123. Get High-res Image Clustering Approach #9: 'MIRSEQ CNMF' versus Clinical Feature #5: 'PATHOLOGY_N_STAGE'

'MIRSEQ CNMF' versus 'PATHOLOGY_M_STAGE'

P value = 0.72 (Fisher's exact test), Q value = 0.82

Table S133. Clustering Approach #9: 'MIRSEQ CNMF' versus Clinical Feature #6: 'PATHOLOGY_M_STAGE'

nPatients	0	1
ALL	346	23
subtype1	127	8
subtype2	152	12
subtype3	67	3

Figure S124. Get High-res Image Clustering Approach #9: 'MIRSEQ CNMF' versus Clinical Feature #6: 'PATHOLOGY_M_STAGE'

'MIRSEQ CNMF' versus 'GENDER'

P value = 0.48 (Fisher's exact test), Q value = 0.67

Table S134. Clustering Approach #9: 'MIRSEQ CNMF' versus Clinical Feature #7: 'GENDER'

nPatients	FEMALE	MALE
ALL	274	239
subtype1	106	81
subtype2	112	109
subtype3	56	49

Figure S125. Get High-res Image Clustering Approach #9: 'MIRSEQ CNMF' versus Clinical Feature #7: 'GENDER'

'MIRSEQ CNMF' versus 'RADIATION_THERAPY'

P value = 0.504 (Fisher's exact test), Q value = 0.68

Table S135. Clustering Approach #9: 'MIRSEQ CNMF' versus Clinical Feature #8: 'RADIATION_THERAPY'

nPatients	NO	YES
ALL	407	60
subtype1	154	19
subtype2	164	29
subtype3	89	12

Figure S126. Get High-res Image Clustering Approach #9: 'MIRSEQ CNMF' versus Clinical Feature #8: 'RADIATION_THERAPY'

'MIRSEQ CNMF' versus 'KARNOFSKY_PERFORMANCE_SCORE'

P value = 0.5 (Kruskal-Wallis (anova)), Q value = 0.68

Table S136. Clustering Approach #9: 'MIRSEQ CNMF' versus Clinical Feature #9: 'KARNOFSKY_PERFORMANCE_SCORE'

	nPatients	Mean (Std.Dev)
ALL	133	78.5 (28.8)
subtype1	41	80.5 (28.6)
subtype2	69	80.0 (27.4)
subtype3	23	70.4 (32.8)

Figure S127. Get High-res Image Clustering Approach #9: 'MIRSEQ CNMF' versus Clinical Feature #9: 'KARNOFSKY_PERFORMANCE_SCORE'

'MIRSEQ CNMF' versus 'HISTOLOGICAL_TYPE'

P value = 0.00205 (Fisher's exact test), Q value = 0.014

Table S137. Clustering Approach #9: 'MIRSEQ CNMF' versus Clinical Feature #10: 'HISTOLOGICAL_TYPE'

nPatients	LUNG ACINAR ADENOCARCINOMA	LUNG ADENOCARCINOMA MIXED SUBTYPE	LUNG ADENOCARCINOMA- NOT OTHERWISE SPECIFIED (NOS)	LUNG BRONCHIOLOALVEOLAR CARCINOMA MUCINOUS	LUNG BRONCHIOLOALVEOLAR CARCINOMA NONMUCINOUS	LUNG CLEAR CELL ADENOCARCINOMA	LUNG MICROPAPILLARY ADENOCARCINOMA	LUNG MUCINOUS ADENOCARCINOMA	LUNG PAPILLARY ADENOCARCINOMA	LUNG SIGNET RING ADENOCARCINOMA	LUNG SOLID PATTERN PREDOMINANT ADENOCARCINOMA	MUCINOUS (COLLOID) CARCINOMA
ALL	18	106	320	5	19	2	2	2	23	1	5	10
subtype1	9	47	97	4	12	0	1	1	8	1	2	5
subtype2	8	48	145	0	4	2	0	1	8	0	3	2
subtype3	1	11	78	1	3	0	1	0	7	0	0	3

Figure S128. Get High-res Image Clustering Approach #9: 'MIRSEQ CNMF' versus Clinical Feature #10: 'HISTOLOGICAL_TYPE'

'MIRSEQ CNMF' versus 'NUMBER_PACK_YEARS_SMOKED'

P value = 0.0424 (Kruskal-Wallis (anova)), Q value = 0.12

Table S138. Clustering Approach #9: 'MIRSEQ CNMF' versus Clinical Feature #11: 'NUMBER_PACK_YEARS_SMOKED'

	nPatients	Mean (Std.Dev)
ALL	350	42.0 (27.2)
subtype1	124	38.4 (26.6)
subtype2	162	43.3 (27.7)
subtype3	64	45.5 (26.7)

Figure S129. Get High-res Image Clustering Approach #9: 'MIRSEQ CNMF' versus Clinical Feature #11: 'NUMBER_PACK_YEARS_SMOKED'

'MIRSEQ CNMF' versus 'YEAR_OF_TOBACCO_SMOKING_ONSET'

P value = 0.0579 (Kruskal-Wallis (anova)), Q value = 0.15

Table S139. Clustering Approach #9: 'MIRSEQ CNMF' versus Clinical Feature #12: 'YEAR_OF_TOBACCO_SMOKING_ONSET'

	nPatients	Mean (Std.Dev)
ALL	274	1964.8 (12.4)
subtype1	102	1962.7 (12.4)
subtype2	127	1966.7 (12.6)
subtype3	45	1964.0 (11.5)

Figure S130. Get High-res Image Clustering Approach #9: 'MIRSEQ CNMF' versus Clinical Feature #12: 'YEAR_OF_TOBACCO_SMOKING_ONSET'

'MIRSEQ CNMF' versus 'RESIDUAL_TUMOR'

P value = 0.656 (Fisher's exact test), Q value = 0.8

Table S140. Clustering Approach #9: 'MIRSEQ CNMF' versus Clinical Feature #13: 'RESIDUAL_TUMOR'

nPatients	R0	R1	R2	RX
ALL	341	13	4	26
subtype1	121	4	1	10
subtype2	157	5	3	9
subtype3	63	4	0	7

Figure S131. Get High-res Image Clustering Approach #9: 'MIRSEQ CNMF' versus Clinical Feature #13: 'RESIDUAL_TUMOR'

'MIRSEQ CNMF' versus 'RACE'

P value = 0.121 (Fisher's exact test), Q value = 0.26

Table S141. Clustering Approach #9: 'MIRSEQ CNMF' versus Clinical Feature #14: 'RACE'

nPatients	ASIAN	BLACK OR AFRICAN AMERICAN	WHITE
ALL	8	52	387
subtype1	0	18	150
subtype2	6	25	155
subtype3	2	9	82

Figure S132. Get High-res Image Clustering Approach #9: 'MIRSEQ CNMF' versus Clinical Feature #14: 'RACE'

'MIRSEQ CNMF' versus 'ETHNICITY'

P value = 0.339 (Fisher's exact test), Q value = 0.59

Table S142. Clustering Approach #9: 'MIRSEQ CNMF' versus Clinical Feature #15: 'ETHNICITY'

nPatients	HISPANIC OR LATINO	NOT HISPANIC OR LATINO
ALL	7	381
subtype1	1	140
subtype2	5	161
subtype3	1	80

Figure S133. Get High-res Image Clustering Approach #9: 'MIRSEQ CNMF' versus Clinical Feature #15: 'ETHNICITY'

Clustering Approach #10: 'MIRSEQ CHIERARCHICAL'

Table S143. Description of clustering approach #10: 'MIRSEQ CHIERARCHICAL'

Cluster Labels	1	2	3	4	5	6
Number of samples	72	39	145	131	96	30

'MIRSEQ CHIERARCHICAL' versus 'Time to Death'

P value = 0.709 (logrank test), Q value = 0.82

Table S144. Clustering Approach #10: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #1: 'Time to Death'

	nPatients	nDeath	Duration Range (Median), Month
ALL	501	182	0.0 - 238.3 (21.6)
subtype1	71	22	0.4 - 129.5 (23.6)
subtype2	38	12	1.4 - 93.1 (18.8)
subtype3	143	53	0.0 - 221.3 (22.0)
subtype4	127	49	0.5 - 164.1 (20.1)
subtype5	94	35	0.7 - 232.2 (23.7)
subtype6	28	11	0.1 - 238.3 (22.5)

Figure S134. Get High-res Image Clustering Approach #10: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #1: 'Time to Death'

'MIRSEQ CHIERARCHICAL' versus 'YEARS_TO_BIRTH'

P value = 0.0026 (Kruskal-Wallis (anova)), Q value = 0.015

Table S145. Clustering Approach #10: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #2: 'YEARS_TO_BIRTH'

	nPatients	Mean (Std.Dev)
ALL	483	65.3 (9.9)
subtype1	68	68.2 (7.8)
subtype2	37	62.6 (10.2)
subtype3	139	63.6 (10.1)
subtype4	124	66.9 (9.9)
subtype5	89	64.0 (10.8)
subtype6	26	66.9 (8.5)

Figure S135. Get High-res Image Clustering Approach #10: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #2: 'YEARS_TO_BIRTH'

'MIRSEQ CHIERARCHICAL' versus 'PATHOLOGIC_STAGE'

P value = 0.852 (Fisher's exact test), Q value = 0.93

Table S146. Clustering Approach #10: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #3: 'PATHOLOGIC_STAGE'

nPatients	STAGE I	STAGE IA	STAGE IB	STAGE II	STAGE IIA	STAGE IIB	STAGE IIIA	STAGE IIIB	STAGE IV
ALL	5	133	139	1	50	70	73	11	24
subtype1	0	27	19	0	4	8	9	1	2
subtype2	0	11	10	0	4	6	4	2	1
subtype3	3	26	48	0	12	22	22	4	7
subtype4	1	38	30	1	15	18	15	2	9
subtype5	1	22	25	0	12	11	17	2	5
subtype6	0	9	7	0	3	5	6	0	0

Figure S136. Get High-res Image Clustering Approach #10: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #3: 'PATHOLOGIC_STAGE'

'MIRSEQ CHIERARCHICAL' versus 'PATHOLOGY_T_STAGE'

P value = 0.182 (Fisher's exact test), Q value = 0.38

Table S147. Clustering Approach #10: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #4: 'PATHOLOGY_T_STAGE'

nPatients	T1	T2	T3	T4
ALL	170	274	47	19
subtype1	31	33	4	4
subtype2	11	22	4	2
subtype3	34	90	16	4
subtype4	50	61	13	5
subtype5	32	51	10	3
subtype6	12	17	0	1

Figure S137. Get High-res Image Clustering Approach #10: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #4: 'PATHOLOGY_T_STAGE'

'MIRSEQ CHIERARCHICAL' versus 'PATHOLOGY_N_STAGE'

P value = 0.414 (Fisher's exact test), Q value = 0.63

Table S148. Clustering Approach #10: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #5: 'PATHOLOGY_N_STAGE'

nPatients	N0	N1	N2+N3
ALL	330	95	76
subtype1	50	13	6
subtype2	28	5	5
subtype3	97	23	24
subtype4	80	29	17
subtype5	59	16	19
subtype6	16	9	5

Figure S138. Get High-res Image Clustering Approach #10: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #5: 'PATHOLOGY_N_STAGE'

'MIRSEQ CHIERARCHICAL' versus 'PATHOLOGY_M_STAGE'

P value = 0.667 (Fisher's exact test), Q value = 0.8

Table S149. Clustering Approach #10: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #6: 'PATHOLOGY_M_STAGE'

nPatients	0	1
ALL	346	23
subtype1	50	2
subtype2	33	1
subtype3	102	7
subtype4	80	8
subtype5	59	5
subtype6	22	0

Figure S139. Get High-res Image Clustering Approach #10: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #6: 'PATHOLOGY_M_STAGE'

'MIRSEQ CHIERARCHICAL' versus 'GENDER'

P value = 0.00156 (Fisher's exact test), Q value = 0.012

Table S150. Clustering Approach #10: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #7: 'GENDER'

nPatients	FEMALE	MALE
ALL	274	239
subtype1	36	36
subtype2	25	14
subtype3	73	72
subtype4	79	52
subtype5	38	58
subtype6	23	7

Figure S140. Get High-res Image Clustering Approach #10: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #7: 'GENDER'

'MIRSEQ CHIERARCHICAL' versus 'RADIATION_THERAPY'

P value = 0.399 (Fisher's exact test), Q value = 0.62

Table S151. Clustering Approach #10: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #8: 'RADIATION_THERAPY'

nPatients	NO	YES
ALL	407	60
subtype1	59	10
subtype2	33	3
subtype3	108	20
subtype4	104	12
subtype5	75	14
subtype6	28	1

Figure S141. Get High-res Image Clustering Approach #10: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #8: 'RADIATION_THERAPY'

'MIRSEQ CHIERARCHICAL' versus 'KARNOFSKY_PERFORMANCE_SCORE'

P value = 0.678 (Kruskal-Wallis (anova)), Q value = 0.8

Table S152. Clustering Approach #10: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #9: 'KARNOFSKY_PERFORMANCE_SCORE'

	nPatients	Mean (Std.Dev)
ALL	133	78.5 (28.8)
subtype1	14	80.0 (25.7)
subtype2	12	75.0 (36.1)
subtype3	42	78.1 (31.5)
subtype4	28	81.8 (26.0)
subtype5	29	74.1 (28.6)
subtype6	8	87.5 (20.5)

Figure S142. Get High-res Image Clustering Approach #10: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #9: 'KARNOFSKY_PERFORMANCE_SCORE'

'MIRSEQ CHIERARCHICAL' versus 'HISTOLOGICAL_TYPE'

P value = 0.0198 (Fisher's exact test), Q value = 0.077

Table S153. Clustering Approach #10: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #10: 'HISTOLOGICAL_TYPE'

nPatients	LUNG ACINAR ADENOCARCINOMA	LUNG ADENOCARCINOMA MIXED SUBTYPE	LUNG ADENOCARCINOMA- NOT OTHERWISE SPECIFIED (NOS)	LUNG BRONCHIOLOALVEOLAR CARCINOMA MUCINOUS	LUNG BRONCHIOLOALVEOLAR CARCINOMA NONMUCINOUS	LUNG CLEAR CELL ADENOCARCINOMA	LUNG MICROPAPILLARY ADENOCARCINOMA	LUNG MUCINOUS ADENOCARCINOMA	LUNG PAPILLARY ADENOCARCINOMA	LUNG SIGNET RING ADENOCARCINOMA	LUNG SOLID PATTERN PREDOMINANT ADENOCARCINOMA	MUCINOUS (COLLOID) CARCINOMA
ALL	18	106	320	5	19	2	2	2	23	1	5	10
subtype1	6	19	37	0	4	1	0	0	4	0	0	1
subtype2	1	11	24	0	2	0	0	0	1	0	0	0
subtype3	2	28	101	0	3	0	1	0	9	0	1	0
subtype4	6	28	68	3	8	0	0	2	6	1	2	7
subtype5	3	17	67	0	2	1	0	0	2	0	2	2
subtype6	0	3	23	2	0	0	1	0	1	0	0	0

Figure S143. Get High-res Image Clustering Approach #10: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #10: 'HISTOLOGICAL_TYPE'

'MIRSEQ CHIERARCHICAL' versus 'NUMBER_PACK_YEARS_SMOKED'

P value = 0.0137 (Kruskal-Wallis (anova)), Q value = 0.056

Table S154. Clustering Approach #10: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #11: 'NUMBER_PACK_YEARS_SMOKED'

	nPatients	Mean (Std.Dev)
ALL	350	42.0 (27.2)
subtype1	49	42.4 (28.0)
subtype2	26	33.6 (21.9)
subtype3	101	44.0 (25.7)
subtype4	89	36.1 (25.4)
subtype5	70	49.0 (32.1)
subtype6	15	43.5 (21.7)

Figure S144. Get High-res Image Clustering Approach #10: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #11: 'NUMBER_PACK_YEARS_SMOKED'

'MIRSEQ CHIERARCHICAL' versus 'YEAR_OF_TOBACCO_SMOKING_ONSET'

P value = 0.0013 (Kruskal-Wallis (anova)), Q value = 0.011

Table S155. Clustering Approach #10: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #12: 'YEAR_OF_TOBACCO_SMOKING_ONSET'

	nPatients	Mean (Std.Dev)
ALL	274	1964.8 (12.4)
subtype1	47	1959.9 (12.4)
subtype2	22	1969.2 (11.2)
subtype3	77	1966.6 (12.0)
subtype4	67	1963.9 (12.0)
subtype5	51	1967.3 (13.0)
subtype6	10	1956.6 (9.3)

Figure S145. Get High-res Image Clustering Approach #10: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #12: 'YEAR_OF_TOBACCO_SMOKING_ONSET'

'MIRSEQ CHIERARCHICAL' versus 'RESIDUAL_TUMOR'

P value = 0.939 (Fisher's exact test), Q value = 0.99

Table S156. Clustering Approach #10: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #13: 'RESIDUAL_TUMOR'

nPatients	R0	R1	R2	RX
ALL	341	13	4	26
subtype1	41	1	0	4
subtype2	29	1	0	2
subtype3	97	5	0	7
subtype4	84	3	3	8
subtype5	65	2	1	5
subtype6	25	1	0	0

Figure S146. Get High-res Image Clustering Approach #10: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #13: 'RESIDUAL_TUMOR'

'MIRSEQ CHIERARCHICAL' versus 'RACE'

P value = 0.41 (Fisher's exact test), Q value = 0.63

Table S157. Clustering Approach #10: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #14: 'RACE'

nPatients	ASIAN	BLACK OR AFRICAN AMERICAN	WHITE
ALL	8	52	387
subtype1	1	6	59
subtype2	0	3	30
subtype3	4	16	108
subtype4	1	11	105
subtype5	1	15	61
subtype6	1	1	24

Figure S147. Get High-res Image Clustering Approach #10: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #14: 'RACE'

'MIRSEQ CHIERARCHICAL' versus 'ETHNICITY'

P value = 0.609 (Fisher's exact test), Q value = 0.77

Table S158. Clustering Approach #10: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #15: 'ETHNICITY'

nPatients	HISPANIC OR LATINO	NOT HISPANIC OR LATINO
ALL	7	381
subtype1	0	52
subtype2	1	26
subtype3	3	113
subtype4	1	101
subtype5	2	66
subtype6	0	23

Figure S148. Get High-res Image Clustering Approach #10: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #15: 'ETHNICITY'

Clustering Approach #11: 'MIRseq Mature CNMF subtypes'

Table S159. Description of clustering approach #11: 'MIRseq Mature CNMF subtypes'

Cluster Labels	1	2	3	4	5	6
Number of samples	59	90	97	44	70	77

'MIRseq Mature CNMF subtypes' versus 'Time to Death'

P value = 0.00296 (logrank test), Q value = 0.016

Table S160. Clustering Approach #11: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #1: 'Time to Death'

	nPatients	nDeath	Duration Range (Median), Month
ALL	426	155	0.1 - 238.3 (20.8)
subtype1	58	12	0.4 - 164.1 (22.1)
subtype2	88	34	0.4 - 232.2 (19.4)
subtype3	92	49	0.6 - 163.1 (21.9)
subtype4	42	14	0.1 - 238.3 (17.5)
subtype5	70	25	0.9 - 156.7 (20.6)
subtype6	76	21	0.7 - 221.3 (23.4)

Figure S149. Get High-res Image Clustering Approach #11: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #1: 'Time to Death'

'MIRseq Mature CNMF subtypes' versus 'YEARS_TO_BIRTH'

P value = 0.04 (Kruskal-Wallis (anova)), Q value = 0.12

Table S161. Clustering Approach #11: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #2: 'YEARS_TO_BIRTH'

	nPatients	Mean (Std.Dev)
ALL	409	65.1 (10.0)
subtype1	55	67.8 (8.6)
subtype2	86	62.5 (9.7)
subtype3	90	65.0 (10.7)
subtype4	39	66.4 (9.2)
subtype5	70	66.3 (9.6)
subtype6	69	64.2 (11.0)

Figure S150. Get High-res Image Clustering Approach #11: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #2: 'YEARS_TO_BIRTH'

'MIRseq Mature CNMF subtypes' versus 'PATHOLOGIC_STAGE'

P value = 0.00226 (Fisher's exact test), Q value = 0.014

Table S162. Clustering Approach #11: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #3: 'PATHOLOGIC_STAGE'

nPatients	STAGE I	STAGE IA	STAGE IB	STAGE II	STAGE IIA	STAGE IIB	STAGE IIIA	STAGE IIIB	STAGE IV
ALL	5	112	114	1	49	60	64	8	20
subtype1	1	21	15	0	5	9	5	0	2
subtype2	1	15	28	0	16	11	8	5	5
subtype3	0	18	21	0	9	14	25	2	7
subtype4	0	7	14	0	5	7	10	0	1
subtype5	0	31	11	1	6	9	7	1	4
subtype6	3	20	25	0	8	10	9	0	1

Figure S151. Get High-res Image Clustering Approach #11: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #3: 'PATHOLOGIC_STAGE'

'MIRseq Mature CNMF subtypes' versus 'PATHOLOGY_T_STAGE'

P value = 0.00051 (Fisher's exact test), Q value = 0.0057

Table S163. Clustering Approach #11: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #4: 'PATHOLOGY_T_STAGE'

nPatients	T1	T2	T3	T4
ALL	148	231	40	15
subtype1	26	21	10	2
subtype2	22	54	9	5
subtype3	26	54	9	7
subtype4	11	28	4	1
subtype5	37	28	4	0
subtype6	26	46	4	0

Figure S152. Get High-res Image Clustering Approach #11: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #4: 'PATHOLOGY_T_STAGE'

'MIRseq Mature CNMF subtypes' versus 'PATHOLOGY_N_STAGE'

P value = 0.0409 (Fisher's exact test), Q value = 0.12

Table S164. Clustering Approach #11: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #5: 'PATHOLOGY_N_STAGE'

nPatients	N0	N1	N2+N3
ALL	281	81	65
subtype1	44	7	4
subtype2	62	16	11
subtype3	48	23	24
subtype4	28	7	9
subtype5	46	15	8
subtype6	53	13	9

Figure S153. Get High-res Image Clustering Approach #11: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #5: 'PATHOLOGY_N_STAGE'

'MIRseq Mature CNMF subtypes' versus 'PATHOLOGY_M_STAGE'

P value = 0.722 (Fisher's exact test), Q value = 0.82

Table S165. Clustering Approach #11: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #6: 'PATHOLOGY_M_STAGE'

nPatients	0	1
ALL	280	19
subtype1	34	2
subtype2	62	5
subtype3	66	6
subtype4	28	1
subtype5	42	4
subtype6	48	1

Figure S154. Get High-res Image Clustering Approach #11: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #6: 'PATHOLOGY_M_STAGE'

'MIRseq Mature CNMF subtypes' versus 'GENDER'

P value = 0.0661 (Fisher's exact test), Q value = 0.16

Table S166. Clustering Approach #11: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #7: 'GENDER'

nPatients	FEMALE	MALE
ALL	234	203
subtype1	34	25
subtype2	37	53
subtype3	53	44
subtype4	22	22
subtype5	38	32
subtype6	50	27

Figure S155. Get High-res Image Clustering Approach #11: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #7: 'GENDER'

'MIRseq Mature CNMF subtypes' versus 'RADIATION_THERAPY'

P value = 0.36 (Fisher's exact test), Q value = 0.6

Table S167. Clustering Approach #11: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #8: 'RADIATION_THERAPY'

nPatients	NO	YES
ALL	357	55
subtype1	48	6
subtype2	73	11
subtype3	73	17
subtype4	40	2
subtype5	60	8
subtype6	63	11

Figure S156. Get High-res Image Clustering Approach #11: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #8: 'RADIATION_THERAPY'

'MIRseq Mature CNMF subtypes' versus 'KARNOFSKY_PERFORMANCE_SCORE'

P value = 0.0824 (Kruskal-Wallis (anova)), Q value = 0.19

Table S168. Clustering Approach #11: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #9: 'KARNOFSKY_PERFORMANCE_SCORE'

	nPatients	Mean (Std.Dev)
ALL	117	79.4 (28.6)
subtype1	14	88.6 (11.0)
subtype2	29	80.0 (29.4)
subtype3	16	55.0 (42.0)
subtype4	10	73.0 (30.9)
subtype5	23	87.0 (17.2)
subtype6	25	84.8 (24.7)

Figure S157. Get High-res Image Clustering Approach #11: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #9: 'KARNOFSKY_PERFORMANCE_SCORE'

'MIRseq Mature CNMF subtypes' versus 'HISTOLOGICAL_TYPE'

P value = 0.00039 (Fisher's exact test), Q value = 0.0049

Table S169. Clustering Approach #11: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #10: 'HISTOLOGICAL_TYPE'

nPatients	LUNG ACINAR ADENOCARCINOMA	LUNG ADENOCARCINOMA MIXED SUBTYPE	LUNG ADENOCARCINOMA- NOT OTHERWISE SPECIFIED (NOS)	LUNG BRONCHIOLOALVEOLAR CARCINOMA MUCINOUS	LUNG BRONCHIOLOALVEOLAR CARCINOMA NONMUCINOUS	LUNG CLEAR CELL ADENOCARCINOMA	LUNG MICROPAPILLARY ADENOCARCINOMA	LUNG MUCINOUS ADENOCARCINOMA	LUNG PAPILLARY ADENOCARCINOMA	LUNG SIGNET RING ADENOCARCINOMA	LUNG SOLID PATTERN PREDOMINANT ADENOCARCINOMA	MUCINOUS (COLLOID) CARCINOMA
ALL	16	86	268	5	19	1	2	2	22	1	5	10
subtype1	4	15	22	3	6	0	0	2	2	0	0	5
subtype2	3	19	59	0	2	0	0	0	5	0	1	1
subtype3	1	21	62	0	4	1	2	0	4	0	0	2
subtype4	0	4	32	2	1	0	0	0	3	0	0	2
subtype5	6	14	45	0	0	0	0	0	3	1	1	0
subtype6	2	13	48	0	6	0	0	0	5	0	3	0

Figure S158. Get High-res Image Clustering Approach #11: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #10: 'HISTOLOGICAL_TYPE'

'MIRseq Mature CNMF subtypes' versus 'NUMBER_PACK_YEARS_SMOKED'

P value = 0.038 (Kruskal-Wallis (anova)), Q value = 0.12

Table S170. Clustering Approach #11: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #11: 'NUMBER_PACK_YEARS_SMOKED'

	nPatients	Mean (Std.Dev)
ALL	295	41.6 (27.3)
subtype1	33	32.6 (24.0)
subtype2	70	40.6 (28.4)
subtype3	70	39.1 (26.5)
subtype4	28	44.4 (22.5)
subtype5	53	47.1 (30.8)
subtype6	41	46.0 (26.6)

Figure S159. Get High-res Image Clustering Approach #11: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #11: 'NUMBER_PACK_YEARS_SMOKED'

'MIRseq Mature CNMF subtypes' versus 'YEAR_OF_TOBACCO_SMOKING_ONSET'

P value = 0.0701 (Kruskal-Wallis (anova)), Q value = 0.17

Table S171. Clustering Approach #11: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #12: 'YEAR_OF_TOBACCO_SMOKING_ONSET'

	nPatients	Mean (Std.Dev)
ALL	236	1965.1 (12.3)
subtype1	26	1966.5 (9.7)
subtype2	63	1967.9 (14.1)
subtype3	46	1964.9 (12.4)
subtype4	21	1959.0 (11.2)
subtype5	48	1962.5 (10.5)
subtype6	32	1966.5 (11.9)

Figure S160. Get High-res Image Clustering Approach #11: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #12: 'YEAR_OF_TOBACCO_SMOKING_ONSET'

'MIRseq Mature CNMF subtypes' versus 'RESIDUAL_TUMOR'

P value = 0.0106 (Fisher's exact test), Q value = 0.045

Table S172. Clustering Approach #11: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #13: 'RESIDUAL_TUMOR'

nPatients	R0	R1	R2	RX
ALL	281	10	1	22
subtype1	34	0	0	3
subtype2	66	1	0	3
subtype3	56	6	1	2
subtype4	30	1	0	2
subtype5	47	1	0	11
subtype6	48	1	0	1

Figure S161. Get High-res Image Clustering Approach #11: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #13: 'RESIDUAL_TUMOR'

'MIRseq Mature CNMF subtypes' versus 'RACE'

P value = 0.625 (Fisher's exact test), Q value = 0.78

Table S173. Clustering Approach #11: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #14: 'RACE'

nPatients	ASIAN	BLACK OR AFRICAN AMERICAN	WHITE
ALL	5	50	333
subtype1	0	7	45
subtype2	1	14	64
subtype3	1	7	74
subtype4	1	3	34
subtype5	2	9	54
subtype6	0	10	62

Figure S162. Get High-res Image Clustering Approach #11: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #14: 'RACE'

'MIRseq Mature CNMF subtypes' versus 'ETHNICITY'

P value = 0.269 (Fisher's exact test), Q value = 0.51

Table S174. Clustering Approach #11: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #15: 'ETHNICITY'

nPatients	HISPANIC OR LATINO	NOT HISPANIC OR LATINO
ALL	6	326
subtype1	0	48
subtype2	1	68
subtype3	3	56
subtype4	0	33
subtype5	2	59
subtype6	0	62

Figure S163. Get High-res Image Clustering Approach #11: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #15: 'ETHNICITY'

Clustering Approach #12: 'MIRseq Mature cHierClus subtypes'

Table S175. Description of clustering approach #12: 'MIRseq Mature cHierClus subtypes'

Cluster Labels	1	2	3
Number of samples	104	238	95

'MIRseq Mature cHierClus subtypes' versus 'Time to Death'

P value = 0.0305 (logrank test), Q value = 0.1

Table S176. Clustering Approach #12: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #1: 'Time to Death'

	nPatients	nDeath	Duration Range (Median), Month
ALL	426	155	0.1 - 238.3 (20.8)
subtype1	101	24	0.4 - 164.1 (22.4)
subtype2	234	89	0.4 - 232.2 (19.7)
subtype3	91	42	0.1 - 238.3 (22.0)

Figure S164. Get High-res Image Clustering Approach #12: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #1: 'Time to Death'

'MIRseq Mature cHierClus subtypes' versus 'YEARS_TO_BIRTH'

P value = 0.000126 (Kruskal-Wallis (anova)), Q value = 0.0025

Table S177. Clustering Approach #12: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #2: 'YEARS_TO_BIRTH'

	nPatients	Mean (Std.Dev)
ALL	409	65.1 (10.0)
subtype1	99	67.8 (8.4)
subtype2	222	63.3 (10.2)
subtype3	88	66.4 (10.4)

Figure S165. Get High-res Image Clustering Approach #12: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #2: 'YEARS_TO_BIRTH'

'MIRseq Mature cHierClus subtypes' versus 'PATHOLOGIC_STAGE'

P value = 0.376 (Fisher's exact test), Q value = 0.61

Table S178. Clustering Approach #12: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #3: 'PATHOLOGIC_STAGE'

nPatients	STAGE I	STAGE IA	STAGE IB	STAGE II	STAGE IIA	STAGE IIB	STAGE IIIA	STAGE IIIB	STAGE IV
ALL	5	112	114	1	49	60	64	8	20
subtype1	1	35	25	1	10	15	9	1	6
subtype2	4	52	64	0	30	36	36	5	9
subtype3	0	25	25	0	9	9	19	2	5

Figure S166. Get High-res Image Clustering Approach #12: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #3: 'PATHOLOGIC_STAGE'

'MIRseq Mature cHierClus subtypes' versus 'PATHOLOGY_T_STAGE'

P value = 0.0163 (Fisher's exact test), Q value = 0.065

Table S179. Clustering Approach #12: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #4: 'PATHOLOGY_T_STAGE'

nPatients	T1	T2	T3	T4
ALL	148	231	40	15
subtype1	44	43	13	3
subtype2	71	139	22	5
subtype3	33	49	5	7

Figure S167. Get High-res Image Clustering Approach #12: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #4: 'PATHOLOGY_T_STAGE'

'MIRseq Mature cHierClus subtypes' versus 'PATHOLOGY_N_STAGE'

P value = 0.0301 (Fisher's exact test), Q value = 0.1

Table S180. Clustering Approach #12: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #5: 'PATHOLOGY_N_STAGE'

nPatients	N0	N1	N2+N3
ALL	281	81	65
subtype1	77	13	8
subtype2	150	47	39
subtype3	54	21	18

Figure S168. Get High-res Image Clustering Approach #12: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #5: 'PATHOLOGY_N_STAGE'

'MIRseq Mature cHierClus subtypes' versus 'PATHOLOGY_M_STAGE'

P value = 0.697 (Fisher's exact test), Q value = 0.81

Table S181. Clustering Approach #12: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #6: 'PATHOLOGY_M_STAGE'

nPatients	0	1
ALL	280	19
subtype1	67	6
subtype2	154	9
subtype3	59	4

Figure S169. Get High-res Image Clustering Approach #12: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #6: 'PATHOLOGY_M_STAGE'

'MIRseq Mature cHierClus subtypes' versus 'GENDER'

P value = 0.00075 (Fisher's exact test), Q value = 0.0074

Table S182. Clustering Approach #12: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #7: 'GENDER'

nPatients	FEMALE	MALE
ALL	234	203
subtype1	53	51
subtype2	114	124
subtype3	67	28

Figure S170. Get High-res Image Clustering Approach #12: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #7: 'GENDER'

'MIRseq Mature cHierClus subtypes' versus 'RADIATION_THERAPY'

P value = 0.0427 (Fisher's exact test), Q value = 0.12

Table S183. Clustering Approach #12: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #8: 'RADIATION_THERAPY'

nPatients	NO	YES
ALL	357	55
subtype1	92	6
subtype2	187	36
subtype3	78	13

Figure S171. Get High-res Image Clustering Approach #12: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #8: 'RADIATION_THERAPY'

'MIRseq Mature cHierClus subtypes' versus 'KARNOFSKY_PERFORMANCE_SCORE'

P value = 0.817 (Kruskal-Wallis (anova)), Q value = 0.91

Table S184. Clustering Approach #12: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #9: 'KARNOFSKY_PERFORMANCE_SCORE'

	nPatients	Mean (Std.Dev)
ALL	117	79.4 (28.6)
subtype1	28	81.1 (28.1)
subtype2	72	80.0 (28.0)
subtype3	17	74.1 (33.2)

Figure S172. Get High-res Image Clustering Approach #12: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #9: 'KARNOFSKY_PERFORMANCE_SCORE'

'MIRseq Mature cHierClus subtypes' versus 'HISTOLOGICAL_TYPE'

P value = 0.00041 (Fisher's exact test), Q value = 0.0049

Table S185. Clustering Approach #12: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #10: 'HISTOLOGICAL_TYPE'

nPatients	LUNG ACINAR ADENOCARCINOMA	LUNG ADENOCARCINOMA MIXED SUBTYPE	LUNG ADENOCARCINOMA- NOT OTHERWISE SPECIFIED (NOS)	LUNG BRONCHIOLOALVEOLAR CARCINOMA MUCINOUS	LUNG BRONCHIOLOALVEOLAR CARCINOMA NONMUCINOUS	LUNG CLEAR CELL ADENOCARCINOMA	LUNG MICROPAPILLARY ADENOCARCINOMA	LUNG MUCINOUS ADENOCARCINOMA	LUNG PAPILLARY ADENOCARCINOMA	LUNG SIGNET RING ADENOCARCINOMA	LUNG SOLID PATTERN PREDOMINANT ADENOCARCINOMA	MUCINOUS (COLLOID) CARCINOMA
ALL	16	86	268	5	19	1	2	2	22	1	5	10
subtype1	5	27	44	3	7	0	0	1	9	1	1	6
subtype2	9	40	164	0	7	1	0	1	9	0	4	3
subtype3	2	19	60	2	5	0	2	0	4	0	0	1

Figure S173. Get High-res Image Clustering Approach #12: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #10: 'HISTOLOGICAL_TYPE'

'MIRseq Mature cHierClus subtypes' versus 'NUMBER_PACK_YEARS_SMOKED'

P value = 0.0231 (Kruskal-Wallis (anova)), Q value = 0.087

Table S186. Clustering Approach #12: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #11: 'NUMBER_PACK_YEARS_SMOKED'

	nPatients	Mean (Std.Dev)
ALL	295	41.6 (27.3)
subtype1	67	38.5 (28.9)
subtype2	169	44.9 (28.3)
subtype3	59	35.8 (21.0)

Figure S174. Get High-res Image Clustering Approach #12: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #11: 'NUMBER_PACK_YEARS_SMOKED'

'MIRseq Mature cHierClus subtypes' versus 'YEAR_OF_TOBACCO_SMOKING_ONSET'

P value = 0.0507 (Kruskal-Wallis (anova)), Q value = 0.13

Table S187. Clustering Approach #12: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #12: 'YEAR_OF_TOBACCO_SMOKING_ONSET'

	nPatients	Mean (Std.Dev)
ALL	236	1965.1 (12.3)
subtype1	56	1962.4 (11.5)
subtype2	135	1966.4 (12.4)
subtype3	45	1964.3 (12.4)

Figure S175. Get High-res Image Clustering Approach #12: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #12: 'YEAR_OF_TOBACCO_SMOKING_ONSET'

'MIRseq Mature cHierClus subtypes' versus 'RESIDUAL_TUMOR'

P value = 0.0291 (Fisher's exact test), Q value = 0.1

Table S188. Clustering Approach #12: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #13: 'RESIDUAL_TUMOR'

nPatients	R0	R1	R2	RX
ALL	281	10	1	22
subtype1	66	0	0	8
subtype2	157	4	1	12
subtype3	58	6	0	2

Figure S176. Get High-res Image Clustering Approach #12: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #13: 'RESIDUAL_TUMOR'

'MIRseq Mature cHierClus subtypes' versus 'RACE'

P value = 0.115 (Fisher's exact test), Q value = 0.26

Table S189. Clustering Approach #12: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #14: 'RACE'

nPatients	ASIAN	BLACK OR AFRICAN AMERICAN	WHITE
ALL	5	50	333
subtype1	2	9	83
subtype2	1	34	176
subtype3	2	7	74

Figure S177. Get High-res Image Clustering Approach #12: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #14: 'RACE'

'MIRseq Mature cHierClus subtypes' versus 'ETHNICITY'

P value = 0.141 (Fisher's exact test), Q value = 0.3

Table S190. Clustering Approach #12: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #15: 'ETHNICITY'

nPatients	HISPANIC OR LATINO	NOT HISPANIC OR LATINO
ALL	6	326
subtype1	0	84
subtype2	6	177
subtype3	0	65

Figure S178. Get High-res Image Clustering Approach #12: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #15: 'ETHNICITY'

Methods & Data

Input

Cluster data file = /xchip/cga/gdac-prod/tcga-gdac/jobResults/GDAC_mergedClustering/LUAD-TP/22552673/LUAD-TP.mergedcluster.txt
Clinical data file = /xchip/cga/gdac-prod/tcga-gdac/jobResults/Append_Data/LUAD-TP/22506767/LUAD-TP.merged_data.txt
Number of patients = 520
Number of clustering approaches = 12
Number of selected clinical features = 15
Exclude small clusters that include fewer than K patients, K = 3

Clustering approaches

CNMF clustering

consensus non-negative matrix factorization clustering approach (Brunet et al. 2004)

Consensus hierarchical clustering

Resampling-based clustering method (Monti et al. 2003)

Survival analysis

For survival clinical features, the Kaplan-Meier survival curves of tumors with and without gene mutations were plotted and the statistical significance P values were estimated by logrank test (Bland and Altman 2004) using the 'survdiff' function in R

Fisher's exact test

For binary clinical features, two-tailed Fisher's exact tests (Fisher 1922) were used to estimate the P values using the 'fisher.test' function in R

Q value calculation

For multiple hypothesis correction, Q value is the False Discovery Rate (FDR) analogue of the P value (Benjamini and Hochberg 1995), defined as the minimum FDR at which the test may be called significant. We used the 'Benjamini and Hochberg' method of 'p.adjust' function in R to convert P values into Q values.

Download Results

In addition to the links below, the full results of the analysis summarized in this report can also be downloaded programmatically using firehose_get, or interactively from either the Broad GDAC website or TCGA Data Coordination Center Portal.

References

[1] Brunet et al., Metagenes and molecular pattern discovery using matrix factorization, PNAS 101(12):4164-9 (2004)

[2] Monti et al., Consensus Clustering: A Resampling-Based Method for Class Discovery and Visualization of Gene Expression Microarray Data, Machine Learning 52(1):91-118 (2003)

[3] Bland and Altman, Statistics notes: The logrank test, BMJ 328(7447):1073 (2004)

[4] Fisher, R.A., On the interpretation of chi-square from contingency tables, and the calculation of P, Journal of the Royal Statistical Society 85(1):87-94 (1922)

[5] Benjamini and Hochberg, Controlling the false discovery rate: a practical and powerful approach to multiple testing, Journal of the Royal Statistical Society Series B 59:289-300 (1995)

Made with Nozzle