Correlation between aggregated molecular cancer subtypes and selected clinical features

Lung Adenocarcinoma (Primary solid tumor)

17 October 2014 | analyses__2014_10_17

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 (2014): Correlation between aggregated molecular cancer subtypes and selected clinical features. Broad Institute of MIT and Harvard. doi:10.7908/C1251H3B

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 14 clinical features across 480 patients, 14 significant findings detected with P value < 0.05 and Q value < 0.25.

CNMF clustering analysis on array-based mRNA expression data identified 4 subtypes that do not correlate to any clinical features.
Consensus hierarchical clustering analysis on array-based mRNA expression data identified 3 subtypes that do not correlate to any clinical features.
3 subtypes identified in current cancer cohort by 'Copy Number Ratio CNMF subtypes'. These subtypes do not correlate to any clinical features.
4 subtypes identified in current cancer cohort by 'METHLYATION CNMF'. These subtypes correlate to 'GENDER' and 'HISTOLOGICAL.TYPE'.
CNMF clustering analysis on RPPA data identified 3 subtypes that do not correlate to any clinical features.
Consensus hierarchical clustering analysis on RPPA data identified 5 subtypes that do not correlate to any clinical features.
CNMF clustering analysis on sequencing-based mRNA expression data identified 5 subtypes that correlate to 'AGE', 'PATHOLOGY.T.STAGE', and 'GENDER'.
Consensus hierarchical clustering analysis on sequencing-based mRNA expression data identified 9 subtypes that correlate to 'AGE', 'NEOPLASM.DISEASESTAGE', 'PATHOLOGY.T.STAGE', 'GENDER', and 'HISTOLOGICAL.TYPE'.
3 subtypes identified in current cancer cohort by 'MIRSEQ CNMF'. These subtypes correlate to 'HISTOLOGICAL.TYPE'.
4 subtypes identified in current cancer cohort by 'MIRSEQ CHIERARCHICAL'. These subtypes do not correlate to any clinical features.
3 subtypes identified in current cancer cohort by 'MIRseq Mature CNMF subtypes'. These subtypes correlate to 'HISTOLOGICAL.TYPE'.
3 subtypes identified in current cancer cohort by 'MIRseq Mature cHierClus subtypes'. These subtypes correlate to 'AGE' and 'GENDER'.

Results

Overview of the results

Table 1. Get Full Table Overview of the association between subtypes identified by 12 different clustering approaches and 14 clinical features. Shown in the table are P values (Q values). Thresholded by P value < 0.05 and Q value < 0.25, 14 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	0.676 (1.00)	0.762 (1.00)	0.867 (1.00)	0.919 (1.00)	0.585 (1.00)	0.273 (1.00)	0.655 (1.00)	0.0346 (1.00)	0.59 (1.00)	0.552 (1.00)	0.00377 (0.554)	0.183 (1.00)
AGE	Kruskal-Wallis (anova)	0.65 (1.00)	0.513 (1.00)	0.00738 (1.00)	0.0602 (1.00)	0.0437 (1.00)	0.242 (1.00)	0.000755 (0.118)	0.000395 (0.0633)	0.0363 (1.00)	0.00333 (0.496)	0.747 (1.00)	0.000105 (0.0171)
NEOPLASM DISEASESTAGE	Fisher's exact test	0.0468 (1.00)	0.0356 (1.00)	0.181 (1.00)	0.322 (1.00)	0.595 (1.00)	0.06 (1.00)	0.00218 (0.329)	0.00063 (0.0989)	0.00657 (0.946)	0.413 (1.00)	0.761 (1.00)	0.757 (1.00)
PATHOLOGY T STAGE	Fisher's exact test	0.509 (1.00)	0.274 (1.00)	0.478 (1.00)	0.0535 (1.00)	0.862 (1.00)	0.0586 (1.00)	0.00149 (0.228)	0.00029 (0.0467)	0.0261 (1.00)	0.158 (1.00)	0.113 (1.00)	0.0225 (1.00)
PATHOLOGY N STAGE	Fisher's exact test	0.483 (1.00)	0.454 (1.00)	0.278 (1.00)	0.577 (1.00)	0.883 (1.00)	0.306 (1.00)	0.00609 (0.883)	0.0138 (1.00)	0.422 (1.00)	0.839 (1.00)	0.447 (1.00)	0.285 (1.00)
PATHOLOGY M STAGE	Fisher's exact test	0.503 (1.00)	0.493 (1.00)	0.51 (1.00)	0.241 (1.00)	0.449 (1.00)	0.0335 (1.00)	0.523 (1.00)	0.179 (1.00)	0.378 (1.00)	0.389 (1.00)	0.316 (1.00)	0.852 (1.00)
GENDER	Fisher's exact test	0.274 (1.00)	0.667 (1.00)	0.0164 (1.00)	0.00099 (0.152)	0.101 (1.00)	0.00599 (0.875)	0.00084 (0.13)	1e-05 (0.00166)	0.516 (1.00)	0.00362 (0.536)	0.785 (1.00)	0.00042 (0.0668)
KARNOFSKY PERFORMANCE SCORE	Kruskal-Wallis (anova)			0.795 (1.00)	0.779 (1.00)	0.154 (1.00)	0.12 (1.00)	0.0318 (1.00)	0.194 (1.00)	0.533 (1.00)	0.788 (1.00)	0.152 (1.00)	0.682 (1.00)
HISTOLOGICAL TYPE	Fisher's exact test	0.433 (1.00)	0.395 (1.00)	0.282 (1.00)	0.00057 (0.0901)	0.00894 (1.00)	0.0189 (1.00)	0.00282 (0.423)	1e-05 (0.00166)	0.00026 (0.0421)	0.0107 (1.00)	0.00017 (0.0277)	0.00214 (0.325)
RADIATIONS RADIATION REGIMENINDICATION	Fisher's exact test	1 (1.00)	1 (1.00)	0.28 (1.00)	0.31 (1.00)	0.255 (1.00)	0.634 (1.00)	0.587 (1.00)	0.0786 (1.00)	1 (1.00)	0.804 (1.00)	0.0389 (1.00)	0.0897 (1.00)
NUMBERPACKYEARSSMOKED	Kruskal-Wallis (anova)	0.46 (1.00)	0.362 (1.00)	0.00809 (1.00)	0.0252 (1.00)	0.109 (1.00)	0.031 (1.00)	0.117 (1.00)	0.00816 (1.00)	0.0485 (1.00)	0.0441 (1.00)	0.0155 (1.00)	0.287 (1.00)
COMPLETENESS OF RESECTION	Fisher's exact test	0.533 (1.00)	0.456 (1.00)	0.929 (1.00)	0.82 (1.00)	0.455 (1.00)	0.749 (1.00)	0.782 (1.00)	0.332 (1.00)	0.426 (1.00)	0.995 (1.00)	0.41 (1.00)	0.254 (1.00)
RACE	Fisher's exact test	0.078 (1.00)	0.00998 (1.00)	0.567 (1.00)	0.251 (1.00)	0.335 (1.00)	0.171 (1.00)	0.749 (1.00)	0.374 (1.00)	0.455 (1.00)	0.763 (1.00)	0.986 (1.00)	0.174 (1.00)
ETHNICITY	Fisher's exact test	1 (1.00)	1 (1.00)	0.11 (1.00)	0.411 (1.00)	1 (1.00)	0.63 (1.00)	0.978 (1.00)	0.107 (1.00)	0.37 (1.00)	0.822 (1.00)	0.134 (1.00)	0.467 (1.00)

Clustering Approach #1: 'mRNA CNMF subtypes'

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

Cluster Labels	1	2	3	4
Number of samples	5	9	12	6

'mRNA CNMF subtypes' versus 'Time to Death'

P value = 0.676 (logrank test), Q value = 1

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

	nPatients	nDeath	Duration Range (Median), Year
ALL	30	5	14.0 - 1728.0 (731.5)
subtype1	4	0	182.0 - 1479.0 (745.5)
subtype2	8	1	225.0 - 1728.0 (1221.5)
subtype3	12	2	14.0 - 1367.0 (500.0)
subtype4	6	2	610.0 - 1375.0 (939.5)

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

'mRNA CNMF subtypes' versus 'AGE'

P value = 0.65 (Kruskal-Wallis (anova)), Q value = 1

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

	nPatients	Mean (Std.Dev)
ALL	30	65.7 (10.8)
subtype1	4	58.5 (15.5)
subtype2	9	65.0 (9.1)
subtype3	12	67.1 (11.1)
subtype4	5	69.4 (9.0)

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

'mRNA CNMF subtypes' versus 'NEOPLASM.DISEASESTAGE'

P value = 0.0468 (Fisher's exact test), Q value = 1

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

nPatients	STAGE IA	STAGE IB	STAGE IIA	STAGE IIB	STAGE IIIA	STAGE IV
ALL	12	11	1	3	3	2
subtype1	3	0	0	1	0	1
subtype2	4	4	0	0	1	0
subtype3	3	7	0	1	0	1
subtype4	2	0	1	1	2	0

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

'mRNA CNMF subtypes' versus 'PATHOLOGY.T.STAGE'

P value = 0.509 (Fisher's exact test), Q value = 1

Table S5. Clustering Approach #1: 'mRNA CNMF subtypes' versus Clinical Feature #4: 'PATHOLOGY.T.STAGE'

nPatients	T1	T2	T3
ALL	12	19	1
subtype1	3	2	0
subtype2	4	4	1
subtype3	4	8	0
subtype4	1	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 = 0.483 (Fisher's exact test), Q value = 1

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	3	1	1
subtype2	8	1	0
subtype3	9	1	1
subtype4	3	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 = 0.503 (Fisher's exact test), Q value = 1

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

nPatients	M0	M1
ALL	30	2
subtype1	4	1
subtype2	9	0
subtype3	11	1
subtype4	6	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 = 0.274 (Fisher's exact test), Q value = 1

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

nPatients	FEMALE	MALE
ALL	18	14
subtype1	3	2
subtype2	3	6
subtype3	9	3
subtype4	3	3

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

'mRNA CNMF subtypes' versus 'HISTOLOGICAL.TYPE'

P value = 0.433 (Fisher's exact test), Q value = 1

Table S9. Clustering Approach #1: 'mRNA CNMF subtypes' versus Clinical Feature #9: 'HISTOLOGICAL.TYPE'

nPatients	LUNG ADENOCARCINOMA MIXED SUBTYPE	LUNG ADENOCARCINOMA- NOT OTHERWISE SPECIFIED (NOS)	LUNG CLEAR CELL ADENOCARCINOMA
ALL	1	30	1
subtype1	0	4	1
subtype2	0	9	0
subtype3	1	11	0
subtype4	0	6	0

Figure S8. Get High-res Image Clustering Approach #1: 'mRNA CNMF subtypes' versus Clinical Feature #9: 'HISTOLOGICAL.TYPE'

'mRNA CNMF subtypes' versus 'RADIATIONS.RADIATION.REGIMENINDICATION'

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

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

nPatients	NO	YES
ALL	1	31
subtype1	0	5
subtype2	0	9
subtype3	1	11
subtype4	0	6

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

'mRNA CNMF subtypes' versus 'NUMBERPACKYEARSSMOKED'

P value = 0.46 (Kruskal-Wallis (anova)), Q value = 1

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

	nPatients	Mean (Std.Dev)
ALL	20	41.1 (15.0)
subtype1	2	29.0 (12.7)
subtype2	9	47.0 (15.5)
subtype3	6	37.0 (13.1)
subtype4	3	40.0 (17.3)

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

'mRNA CNMF subtypes' versus 'COMPLETENESS.OF.RESECTION'

P value = 0.533 (Fisher's exact test), Q value = 1

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

nPatients	R0	R2	RX
ALL	26	1	2
subtype1	3	0	1
subtype2	7	1	0
subtype3	10	0	1
subtype4	6	0	0

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

'mRNA CNMF subtypes' versus 'RACE'

P value = 0.078 (Fisher's exact test), Q value = 1

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

nPatients	ASIAN	BLACK OR AFRICAN AMERICAN	WHITE
ALL	2	1	26
subtype1	1	0	3
subtype2	0	0	7
subtype3	0	0	12
subtype4	1	1	4

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

'mRNA CNMF subtypes' versus 'ETHNICITY'

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

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

nPatients	HISPANIC OR LATINO	NOT HISPANIC OR LATINO
ALL	1	28
subtype1	0	4
subtype2	0	7
subtype3	1	11
subtype4	0	6

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

Clustering Approach #2: 'mRNA cHierClus subtypes'

Table S15. 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 = 0.762 (logrank test), Q value = 1

Table S16. Clustering Approach #2: 'mRNA cHierClus subtypes' versus Clinical Feature #1: 'Time to Death'

	nPatients	nDeath	Duration Range (Median), Year
ALL	30	5	14.0 - 1728.0 (731.5)
subtype1	13	2	14.0 - 1429.0 (573.0)
subtype2	10	1	182.0 - 1728.0 (1099.5)
subtype3	7	2	610.0 - 1479.0 (1178.0)

Figure S14. Get High-res Image Clustering Approach #2: 'mRNA cHierClus subtypes' versus Clinical Feature #1: 'Time to Death'

'mRNA cHierClus subtypes' versus 'AGE'

P value = 0.513 (Kruskal-Wallis (anova)), Q value = 1

Table S17. Clustering Approach #2: 'mRNA cHierClus subtypes' versus Clinical Feature #2: 'AGE'

	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 S15. Get High-res Image Clustering Approach #2: 'mRNA cHierClus subtypes' versus Clinical Feature #2: 'AGE'

'mRNA cHierClus subtypes' versus 'NEOPLASM.DISEASESTAGE'

P value = 0.0356 (Fisher's exact test), Q value = 1

Table S18. Clustering Approach #2: 'mRNA cHierClus subtypes' versus Clinical Feature #3: 'NEOPLASM.DISEASESTAGE'

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

Figure S16. Get High-res Image Clustering Approach #2: 'mRNA cHierClus subtypes' versus Clinical Feature #3: 'NEOPLASM.DISEASESTAGE'

'mRNA cHierClus subtypes' versus 'PATHOLOGY.T.STAGE'

P value = 0.274 (Fisher's exact test), Q value = 1

Table S19. 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 S17. 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 = 0.454 (Fisher's exact test), Q value = 1

Table S20. 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 S18. 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 = 0.493 (Fisher's exact test), Q value = 1

Table S21. Clustering Approach #2: 'mRNA cHierClus subtypes' versus Clinical Feature #6: 'PATHOLOGY.M.STAGE'

nPatients	M0	M1
ALL	30	2
subtype1	12	2
subtype2	11	0
subtype3	7	0

Figure S19. Get High-res Image Clustering Approach #2: 'mRNA cHierClus subtypes' versus Clinical Feature #6: 'PATHOLOGY.M.STAGE'

'mRNA cHierClus subtypes' versus 'GENDER'

P value = 0.667 (Fisher's exact test), Q value = 1

Table S22. 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 S20. Get High-res Image Clustering Approach #2: 'mRNA cHierClus subtypes' versus Clinical Feature #7: 'GENDER'

'mRNA cHierClus subtypes' versus 'HISTOLOGICAL.TYPE'

P value = 0.395 (Fisher's exact test), Q value = 1

Table S23. Clustering Approach #2: 'mRNA cHierClus subtypes' versus Clinical Feature #9: '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 S21. Get High-res Image Clustering Approach #2: 'mRNA cHierClus subtypes' versus Clinical Feature #9: 'HISTOLOGICAL.TYPE'

'mRNA cHierClus subtypes' versus 'RADIATIONS.RADIATION.REGIMENINDICATION'

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

Table S24. Clustering Approach #2: 'mRNA cHierClus subtypes' versus Clinical Feature #10: 'RADIATIONS.RADIATION.REGIMENINDICATION'

nPatients	NO	YES
ALL	1	31
subtype1	1	13
subtype2	0	11
subtype3	0	7

Figure S22. Get High-res Image Clustering Approach #2: 'mRNA cHierClus subtypes' versus Clinical Feature #10: 'RADIATIONS.RADIATION.REGIMENINDICATION'

'mRNA cHierClus subtypes' versus 'NUMBERPACKYEARSSMOKED'

P value = 0.362 (Kruskal-Wallis (anova)), Q value = 1

Table S25. Clustering Approach #2: 'mRNA cHierClus subtypes' versus Clinical Feature #11: 'NUMBERPACKYEARSSMOKED'

	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 S23. Get High-res Image Clustering Approach #2: 'mRNA cHierClus subtypes' versus Clinical Feature #11: 'NUMBERPACKYEARSSMOKED'

'mRNA cHierClus subtypes' versus 'COMPLETENESS.OF.RESECTION'

P value = 0.456 (Fisher's exact test), Q value = 1

Table S26. Clustering Approach #2: 'mRNA cHierClus subtypes' versus Clinical Feature #12: 'COMPLETENESS.OF.RESECTION'

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

Figure S24. Get High-res Image Clustering Approach #2: 'mRNA cHierClus subtypes' versus Clinical Feature #12: 'COMPLETENESS.OF.RESECTION'

'mRNA cHierClus subtypes' versus 'RACE'

P value = 0.00998 (Fisher's exact test), Q value = 1

Table S27. Clustering Approach #2: 'mRNA cHierClus subtypes' versus Clinical Feature #13: '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 S25. Get High-res Image Clustering Approach #2: 'mRNA cHierClus subtypes' versus Clinical Feature #13: 'RACE'

'mRNA cHierClus subtypes' versus 'ETHNICITY'

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

Table S28. Clustering Approach #2: 'mRNA cHierClus subtypes' versus Clinical Feature #14: 'ETHNICITY'

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

Figure S26. Get High-res Image Clustering Approach #2: 'mRNA cHierClus subtypes' versus Clinical Feature #14: 'ETHNICITY'

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

Table S29. Description of clustering approach #3: 'Copy Number Ratio CNMF subtypes'

Cluster Labels	1	2	3
Number of samples	185	203	88

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

P value = 0.867 (logrank test), Q value = 1

Table S30. Clustering Approach #3: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #1: 'Time to Death'

	nPatients	nDeath	Duration Range (Median), Year
ALL	416	87	1.0 - 6443.0 (476.0)
subtype1	161	39	2.0 - 6443.0 (578.0)
subtype2	177	33	1.0 - 2174.0 (426.0)
subtype3	78	15	2.0 - 2199.0 (484.0)

Figure S27. 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 'AGE'

P value = 0.00738 (Kruskal-Wallis (anova)), Q value = 1

Table S31. Clustering Approach #3: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #2: 'AGE'

	nPatients	Mean (Std.Dev)
ALL	445	65.5 (9.8)
subtype1	174	64.1 (10.3)
subtype2	188	67.3 (9.1)
subtype3	83	64.3 (9.8)

Figure S28. Get High-res Image Clustering Approach #3: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #2: 'AGE'

'Copy Number Ratio CNMF subtypes' versus 'NEOPLASM.DISEASESTAGE'

P value = 0.181 (Fisher's exact test), Q value = 1

Table S32. Clustering Approach #3: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #3: 'NEOPLASM.DISEASESTAGE'

nPatients	STAGE I	STAGE IA	STAGE IB	STAGE IIA	STAGE IIB	STAGE IIIA	STAGE IIIB	STAGE IV
ALL	5	116	132	49	70	68	11	24
subtype1	3	32	55	24	29	25	6	11
subtype2	1	60	56	19	31	25	3	7
subtype3	1	24	21	6	10	18	2	6

Figure S29. Get High-res Image Clustering Approach #3: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #3: 'NEOPLASM.DISEASESTAGE'

'Copy Number Ratio CNMF subtypes' versus 'PATHOLOGY.T.STAGE'

P value = 0.478 (Fisher's exact test), Q value = 1

Table S33. Clustering Approach #3: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #4: 'PATHOLOGY.T.STAGE'

nPatients	T1	T2	T3	T4
ALL	147	267	42	18
subtype1	48	113	18	6
subtype2	72	107	15	9
subtype3	27	47	9	3

Figure S30. 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 = 0.278 (Fisher's exact test), Q value = 1

Table S34. Clustering Approach #3: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #5: 'PATHOLOGY.N.STAGE'

nPatients	N0	N1	N2+N3
ALL	301	91	74
subtype1	112	40	31
subtype2	132	40	26
subtype3	57	11	17

Figure S31. 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 = 0.51 (Fisher's exact test), Q value = 1

Table S35. Clustering Approach #3: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #6: 'PATHOLOGY.M.STAGE'

nPatients	M0	M1	M1A	M1B	MX
ALL	326	18	1	4	123
subtype1	125	8	0	3	47
subtype2	141	5	0	1	54
subtype3	60	5	1	0	22

Figure S32. 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 = 0.0164 (Fisher's exact test), Q value = 1

Table S36. Clustering Approach #3: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #7: 'GENDER'

nPatients	FEMALE	MALE
ALL	255	221
subtype1	104	81
subtype2	116	87
subtype3	35	53

Figure S33. Get High-res Image Clustering Approach #3: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #7: 'GENDER'

'Copy Number Ratio CNMF subtypes' versus 'KARNOFSKY.PERFORMANCE.SCORE'

P value = 0.795 (Kruskal-Wallis (anova)), Q value = 1

Table S37. Clustering Approach #3: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #8: 'KARNOFSKY.PERFORMANCE.SCORE'

	nPatients	Mean (Std.Dev)
ALL	84	84.4 (22.3)
subtype1	41	83.7 (22.3)
subtype2	27	86.7 (20.0)
subtype3	16	82.5 (26.7)

Figure S34. Get High-res Image Clustering Approach #3: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #8: 'KARNOFSKY.PERFORMANCE.SCORE'

'Copy Number Ratio CNMF subtypes' versus 'HISTOLOGICAL.TYPE'

P value = 0.282 (Fisher's exact test), Q value = 1

Table S38. Clustering Approach #3: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #9: '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	15	94	303	5	19	2	4	2	19	1	5	7
subtype1	6	35	126	2	7	1	3	0	4	0	1	0
subtype2	4	42	119	3	11	1	1	2	10	1	3	6
subtype3	5	17	58	0	1	0	0	0	5	0	1	1

Figure S35. Get High-res Image Clustering Approach #3: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #9: 'HISTOLOGICAL.TYPE'

'Copy Number Ratio CNMF subtypes' versus 'RADIATIONS.RADIATION.REGIMENINDICATION'

P value = 0.28 (Fisher's exact test), Q value = 1

Table S39. Clustering Approach #3: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #10: 'RADIATIONS.RADIATION.REGIMENINDICATION'

nPatients	NO	YES
ALL	21	455
subtype1	5	180
subtype2	10	193
subtype3	6	82

Figure S36. Get High-res Image Clustering Approach #3: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #10: 'RADIATIONS.RADIATION.REGIMENINDICATION'

'Copy Number Ratio CNMF subtypes' versus 'NUMBERPACKYEARSSMOKED'

P value = 0.00809 (Kruskal-Wallis (anova)), Q value = 1

Table S40. Clustering Approach #3: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #11: 'NUMBERPACKYEARSSMOKED'

	nPatients	Mean (Std.Dev)
ALL	328	42.1 (27.3)
subtype1	121	46.6 (28.4)
subtype2	136	37.2 (24.7)
subtype3	71	44.0 (29.0)

Figure S37. Get High-res Image Clustering Approach #3: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #11: 'NUMBERPACKYEARSSMOKED'

'Copy Number Ratio CNMF subtypes' versus 'COMPLETENESS.OF.RESECTION'

P value = 0.929 (Fisher's exact test), Q value = 1

Table S41. Clustering Approach #3: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #12: 'COMPLETENESS.OF.RESECTION'

nPatients	R0	R1	R2	RX
ALL	327	12	4	21
subtype1	133	6	1	10
subtype2	138	4	2	7
subtype3	56	2	1	4

Figure S38. Get High-res Image Clustering Approach #3: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #12: 'COMPLETENESS.OF.RESECTION'

'Copy Number Ratio CNMF subtypes' versus 'RACE'

P value = 0.567 (Fisher's exact test), Q value = 1

Table S42. Clustering Approach #3: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #13: 'RACE'

nPatients	AMERICAN INDIAN OR ALASKA NATIVE	ASIAN	BLACK OR AFRICAN AMERICAN	WHITE
ALL	1	6	35	367
subtype1	1	3	16	139
subtype2	0	1	14	161
subtype3	0	2	5	67

Figure S39. Get High-res Image Clustering Approach #3: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #13: 'RACE'

'Copy Number Ratio CNMF subtypes' versus 'ETHNICITY'

P value = 0.11 (Fisher's exact test), Q value = 1

Table S43. Clustering Approach #3: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #14: 'ETHNICITY'

nPatients	HISPANIC OR LATINO	NOT HISPANIC OR LATINO
ALL	7	345
subtype1	3	133
subtype2	1	152
subtype3	3	60

Figure S40. Get High-res Image Clustering Approach #3: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #14: 'ETHNICITY'

Clustering Approach #4: 'METHLYATION CNMF'

Table S44. Description of clustering approach #4: 'METHLYATION CNMF'

Cluster Labels	1	2	3	4
Number of samples	87	117	106	107

'METHLYATION CNMF' versus 'Time to Death'

P value = 0.919 (logrank test), Q value = 1

Table S45. Clustering Approach #4: 'METHLYATION CNMF' versus Clinical Feature #1: 'Time to Death'

	nPatients	nDeath	Duration Range (Median), Year
ALL	364	72	1.0 - 2696.0 (426.5)
subtype1	77	14	1.0 - 2151.0 (392.0)
subtype2	103	24	2.0 - 2696.0 (492.0)
subtype3	95	18	3.0 - 2370.0 (354.0)
subtype4	89	16	10.0 - 2174.0 (415.0)

Figure S41. Get High-res Image Clustering Approach #4: 'METHLYATION CNMF' versus Clinical Feature #1: 'Time to Death'

'METHLYATION CNMF' versus 'AGE'

P value = 0.0602 (Kruskal-Wallis (anova)), Q value = 1

Table S46. Clustering Approach #4: 'METHLYATION CNMF' versus Clinical Feature #2: 'AGE'

	nPatients	Mean (Std.Dev)
ALL	388	65.3 (9.9)
subtype1	78	67.4 (9.2)
subtype2	110	63.6 (10.0)
subtype3	101	65.5 (10.2)
subtype4	99	65.4 (9.9)

Figure S42. Get High-res Image Clustering Approach #4: 'METHLYATION CNMF' versus Clinical Feature #2: 'AGE'

'METHLYATION CNMF' versus 'NEOPLASM.DISEASESTAGE'

P value = 0.322 (Fisher's exact test), Q value = 1

Table S47. Clustering Approach #4: 'METHLYATION CNMF' versus Clinical Feature #3: 'NEOPLASM.DISEASESTAGE'

nPatients	STAGE I	STAGE IA	STAGE IB	STAGE IIA	STAGE IIB	STAGE IIIA	STAGE IIIB	STAGE IV
ALL	4	101	118	46	59	60	9	19
subtype1	1	29	22	7	12	11	1	3
subtype2	2	25	30	15	13	19	5	8
subtype3	1	15	35	12	21	15	2	5
subtype4	0	32	31	12	13	15	1	3

Figure S43. Get High-res Image Clustering Approach #4: 'METHLYATION CNMF' versus Clinical Feature #3: 'NEOPLASM.DISEASESTAGE'

'METHLYATION CNMF' versus 'PATHOLOGY.T.STAGE'

P value = 0.0535 (Fisher's exact test), Q value = 1

Table S48. Clustering Approach #4: 'METHLYATION CNMF' versus Clinical Feature #4: 'PATHOLOGY.T.STAGE'

nPatients	T1	T2	T3	T4
ALL	131	232	36	15
subtype1	37	40	7	3
subtype2	31	69	11	5
subtype3	23	65	13	5
subtype4	40	58	5	2

Figure S44. Get High-res Image Clustering Approach #4: 'METHLYATION CNMF' versus Clinical Feature #4: 'PATHOLOGY.T.STAGE'

'METHLYATION CNMF' versus 'PATHOLOGY.N.STAGE'

P value = 0.577 (Fisher's exact test), Q value = 1

Table S49. Clustering Approach #4: 'METHLYATION CNMF' versus Clinical Feature #5: 'PATHOLOGY.N.STAGE'

nPatients	N0	N1	N2+N3
ALL	266	78	64
subtype1	60	13	11
subtype2	73	19	23
subtype3	67	25	14
subtype4	66	21	16

Figure S45. Get High-res Image Clustering Approach #4: 'METHLYATION CNMF' versus Clinical Feature #5: 'PATHOLOGY.N.STAGE'

'METHLYATION CNMF' versus 'PATHOLOGY.M.STAGE'

P value = 0.241 (Fisher's exact test), Q value = 1

Table S50. Clustering Approach #4: 'METHLYATION CNMF' versus Clinical Feature #6: 'PATHOLOGY.M.STAGE'

nPatients	M0	M1	M1A	M1B	MX
ALL	272	12	1	4	124
subtype1	53	1	1	1	28
subtype2	80	5	0	3	28
subtype3	73	4	0	0	29
subtype4	66	2	0	0	39

Figure S46. Get High-res Image Clustering Approach #4: 'METHLYATION CNMF' versus Clinical Feature #6: 'PATHOLOGY.M.STAGE'

'METHLYATION CNMF' versus 'GENDER'

P value = 0.00099 (Fisher's exact test), Q value = 0.15

Table S51. Clustering Approach #4: 'METHLYATION CNMF' versus Clinical Feature #7: 'GENDER'

nPatients	FEMALE	MALE
ALL	223	194
subtype1	55	32
subtype2	49	68
subtype3	50	56
subtype4	69	38

Figure S47. Get High-res Image Clustering Approach #4: 'METHLYATION CNMF' versus Clinical Feature #7: 'GENDER'

'METHLYATION CNMF' versus 'KARNOFSKY.PERFORMANCE.SCORE'

P value = 0.779 (Kruskal-Wallis (anova)), Q value = 1

Table S52. Clustering Approach #4: 'METHLYATION CNMF' versus Clinical Feature #8: 'KARNOFSKY.PERFORMANCE.SCORE'

	nPatients	Mean (Std.Dev)
ALL	76	84.2 (21.7)
subtype1	15	86.0 (24.7)
subtype2	29	84.5 (21.8)
subtype3	21	84.3 (15.7)
subtype4	11	80.9 (28.8)

Figure S48. Get High-res Image Clustering Approach #4: 'METHLYATION CNMF' versus Clinical Feature #8: 'KARNOFSKY.PERFORMANCE.SCORE'

'METHLYATION CNMF' versus 'HISTOLOGICAL.TYPE'

P value = 0.00057 (Fisher's exact test), Q value = 0.09

Table S53. Clustering Approach #4: 'METHLYATION CNMF' versus Clinical Feature #9: '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	15	79	262	5	19	1	3	2	18	1	5	7
subtype1	6	18	41	2	10	0	1	2	5	0	0	2
subtype2	7	25	73	0	2	0	0	0	6	0	1	3
subtype3	1	25	69	1	4	0	2	0	3	0	1	0
subtype4	1	11	79	2	3	1	0	0	4	1	3	2

Figure S49. Get High-res Image Clustering Approach #4: 'METHLYATION CNMF' versus Clinical Feature #9: 'HISTOLOGICAL.TYPE'

'METHLYATION CNMF' versus 'RADIATIONS.RADIATION.REGIMENINDICATION'

P value = 0.31 (Fisher's exact test), Q value = 1

Table S54. Clustering Approach #4: 'METHLYATION CNMF' versus Clinical Feature #10: 'RADIATIONS.RADIATION.REGIMENINDICATION'

nPatients	NO	YES
ALL	18	399
subtype1	2	85
subtype2	5	112
subtype3	3	103
subtype4	8	99

Figure S50. Get High-res Image Clustering Approach #4: 'METHLYATION CNMF' versus Clinical Feature #10: 'RADIATIONS.RADIATION.REGIMENINDICATION'

'METHLYATION CNMF' versus 'NUMBERPACKYEARSSMOKED'

P value = 0.0252 (Kruskal-Wallis (anova)), Q value = 1

Table S55. Clustering Approach #4: 'METHLYATION CNMF' versus Clinical Feature #11: 'NUMBERPACKYEARSSMOKED'

	nPatients	Mean (Std.Dev)
ALL	285	41.1 (27.3)
subtype1	50	35.4 (22.4)
subtype2	90	48.6 (31.1)
subtype3	73	36.6 (25.7)
subtype4	72	40.4 (25.0)

Figure S51. Get High-res Image Clustering Approach #4: 'METHLYATION CNMF' versus Clinical Feature #11: 'NUMBERPACKYEARSSMOKED'

'METHLYATION CNMF' versus 'COMPLETENESS.OF.RESECTION'

P value = 0.82 (Fisher's exact test), Q value = 1

Table S56. Clustering Approach #4: 'METHLYATION CNMF' versus Clinical Feature #12: 'COMPLETENESS.OF.RESECTION'

nPatients	R0	R1	R2	RX
ALL	276	10	1	18
subtype1	57	3	0	3
subtype2	80	4	0	5
subtype3	77	2	0	7
subtype4	62	1	1	3

Figure S52. Get High-res Image Clustering Approach #4: 'METHLYATION CNMF' versus Clinical Feature #12: 'COMPLETENESS.OF.RESECTION'

'METHLYATION CNMF' versus 'RACE'

P value = 0.251 (Fisher's exact test), Q value = 1

Table S57. Clustering Approach #4: 'METHLYATION CNMF' versus Clinical Feature #13: 'RACE'

nPatients	ASIAN	BLACK OR AFRICAN AMERICAN	WHITE
ALL	5	31	331
subtype1	1	6	69
subtype2	0	8	97
subtype3	4	8	76
subtype4	0	9	89

Figure S53. Get High-res Image Clustering Approach #4: 'METHLYATION CNMF' versus Clinical Feature #13: 'RACE'

'METHLYATION CNMF' versus 'ETHNICITY'

P value = 0.411 (Fisher's exact test), Q value = 1

Table S58. Clustering Approach #4: 'METHLYATION CNMF' versus Clinical Feature #14: 'ETHNICITY'

nPatients	HISPANIC OR LATINO	NOT HISPANIC OR LATINO
ALL	7	303
subtype1	1	66
subtype2	3	83
subtype3	0	74
subtype4	3	80

Figure S54. Get High-res Image Clustering Approach #4: 'METHLYATION CNMF' versus Clinical Feature #14: 'ETHNICITY'

Clustering Approach #5: 'RPPA CNMF subtypes'

Table S59. Description of clustering approach #5: 'RPPA CNMF subtypes'

Cluster Labels	1	2	3
Number of samples	44	73	64

'RPPA CNMF subtypes' versus 'Time to Death'

P value = 0.585 (logrank test), Q value = 1

Table S60. Clustering Approach #5: 'RPPA CNMF subtypes' versus Clinical Feature #1: 'Time to Death'

	nPatients	nDeath	Duration Range (Median), Year
ALL	155	43	2.0 - 2370.0 (741.0)
subtype1	41	12	14.0 - 1971.0 (690.0)
subtype2	57	12	4.0 - 2146.0 (701.0)
subtype3	57	19	2.0 - 2370.0 (881.0)

Figure S55. Get High-res Image Clustering Approach #5: 'RPPA CNMF subtypes' versus Clinical Feature #1: 'Time to Death'

'RPPA CNMF subtypes' versus 'AGE'

P value = 0.0437 (Kruskal-Wallis (anova)), Q value = 1

Table S61. Clustering Approach #5: 'RPPA CNMF subtypes' versus Clinical Feature #2: 'AGE'

	nPatients	Mean (Std.Dev)
ALL	164	65.5 (9.6)
subtype1	43	67.0 (8.6)
subtype2	63	63.3 (10.1)
subtype3	58	66.7 (9.5)

Figure S56. Get High-res Image Clustering Approach #5: 'RPPA CNMF subtypes' versus Clinical Feature #2: 'AGE'

'RPPA CNMF subtypes' versus 'NEOPLASM.DISEASESTAGE'

P value = 0.595 (Fisher's exact test), Q value = 1

Table S62. Clustering Approach #5: 'RPPA CNMF subtypes' versus Clinical Feature #3: 'NEOPLASM.DISEASESTAGE'

nPatients	STAGE I	STAGE IA	STAGE IB	STAGE IIA	STAGE IIB	STAGE IIIA	STAGE IIIB	STAGE IV
ALL	1	41	52	15	25	33	7	7
subtype1	0	12	9	6	7	6	1	3
subtype2	0	18	20	5	12	14	2	2
subtype3	1	11	23	4	6	13	4	2

Figure S57. Get High-res Image Clustering Approach #5: 'RPPA CNMF subtypes' versus Clinical Feature #3: 'NEOPLASM.DISEASESTAGE'

'RPPA CNMF subtypes' versus 'PATHOLOGY.T.STAGE'

P value = 0.862 (Fisher's exact test), Q value = 1

Table S63. Clustering Approach #5: 'RPPA CNMF subtypes' versus Clinical Feature #4: 'PATHOLOGY.T.STAGE'

nPatients	T1	T2	T3	T4
ALL	47	108	13	12
subtype1	12	27	2	3
subtype2	20	43	7	3
subtype3	15	38	4	6

Figure S58. 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 = 0.883 (Fisher's exact test), Q value = 1

Table S64. Clustering Approach #5: 'RPPA CNMF subtypes' versus Clinical Feature #5: 'PATHOLOGY.N.STAGE'

nPatients	N0	N1	N2+N3
ALL	106	34	35
subtype1	27	9	7
subtype2	40	15	14
subtype3	39	10	14

Figure S59. 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 = 0.449 (Fisher's exact test), Q value = 1

Table S65. Clustering Approach #5: 'RPPA CNMF subtypes' versus Clinical Feature #6: 'PATHOLOGY.M.STAGE'

nPatients	M0	M1	MX
ALL	136	6	37
subtype1	30	3	11
subtype2	57	2	12
subtype3	49	1	14

Figure S60. Get High-res Image Clustering Approach #5: 'RPPA CNMF subtypes' versus Clinical Feature #6: 'PATHOLOGY.M.STAGE'

'RPPA CNMF subtypes' versus 'GENDER'

P value = 0.101 (Fisher's exact test), Q value = 1

Table S66. Clustering Approach #5: 'RPPA CNMF subtypes' versus Clinical Feature #7: 'GENDER'

nPatients	FEMALE	MALE
ALL	105	76
subtype1	20	24
subtype2	48	25
subtype3	37	27

Figure S61. Get High-res Image Clustering Approach #5: 'RPPA CNMF subtypes' versus Clinical Feature #7: 'GENDER'

'RPPA CNMF subtypes' versus 'KARNOFSKY.PERFORMANCE.SCORE'

P value = 0.154 (Kruskal-Wallis (anova)), Q value = 1

Table S67. Clustering Approach #5: 'RPPA CNMF subtypes' versus Clinical Feature #8: 'KARNOFSKY.PERFORMANCE.SCORE'

	nPatients	Mean (Std.Dev)
ALL	14	60.0 (40.6)
subtype1	6	83.3 (8.2)
subtype2	5	30.0 (42.4)
subtype3	3	63.3 (55.1)

Figure S62. Get High-res Image Clustering Approach #5: 'RPPA CNMF subtypes' versus Clinical Feature #8: 'KARNOFSKY.PERFORMANCE.SCORE'

'RPPA CNMF subtypes' versus 'HISTOLOGICAL.TYPE'

P value = 0.00894 (Fisher's exact test), Q value = 1

Table S68. Clustering Approach #5: 'RPPA CNMF subtypes' versus Clinical Feature #9: '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 MICROPAPILLARY ADENOCARCINOMA	LUNG MUCINOUS ADENOCARCINOMA	LUNG PAPILLARY ADENOCARCINOMA	MUCINOUS (COLLOID) CARCINOMA
ALL	5	43	111	3	8	2	1	5	3
subtype1	3	15	17	0	5	1	0	2	1
subtype2	2	14	51	0	2	1	1	1	1
subtype3	0	14	43	3	1	0	0	2	1

Figure S63. Get High-res Image Clustering Approach #5: 'RPPA CNMF subtypes' versus Clinical Feature #9: 'HISTOLOGICAL.TYPE'

'RPPA CNMF subtypes' versus 'RADIATIONS.RADIATION.REGIMENINDICATION'

P value = 0.255 (Fisher's exact test), Q value = 1

Table S69. Clustering Approach #5: 'RPPA CNMF subtypes' versus Clinical Feature #10: 'RADIATIONS.RADIATION.REGIMENINDICATION'

nPatients	NO	YES
ALL	12	169
subtype1	2	42
subtype2	3	70
subtype3	7	57

Figure S64. Get High-res Image Clustering Approach #5: 'RPPA CNMF subtypes' versus Clinical Feature #10: 'RADIATIONS.RADIATION.REGIMENINDICATION'

'RPPA CNMF subtypes' versus 'NUMBERPACKYEARSSMOKED'

P value = 0.109 (Kruskal-Wallis (anova)), Q value = 1

Table S70. Clustering Approach #5: 'RPPA CNMF subtypes' versus Clinical Feature #11: 'NUMBERPACKYEARSSMOKED'

	nPatients	Mean (Std.Dev)
ALL	127	41.8 (27.1)
subtype1	38	35.3 (23.7)
subtype2	38	44.1 (32.0)
subtype3	51	44.9 (25.3)

Figure S65. Get High-res Image Clustering Approach #5: 'RPPA CNMF subtypes' versus Clinical Feature #11: 'NUMBERPACKYEARSSMOKED'

'RPPA CNMF subtypes' versus 'COMPLETENESS.OF.RESECTION'

P value = 0.455 (Fisher's exact test), Q value = 1

Table S71. Clustering Approach #5: 'RPPA CNMF subtypes' versus Clinical Feature #12: 'COMPLETENESS.OF.RESECTION'

nPatients	R0	R1	R2	RX
ALL	119	8	1	5
subtype1	30	3	0	1
subtype2	47	3	1	4
subtype3	42	2	0	0

Figure S66. Get High-res Image Clustering Approach #5: 'RPPA CNMF subtypes' versus Clinical Feature #12: 'COMPLETENESS.OF.RESECTION'

'RPPA CNMF subtypes' versus 'RACE'

P value = 0.335 (Fisher's exact test), Q value = 1

Table S72. Clustering Approach #5: 'RPPA CNMF subtypes' versus Clinical Feature #13: 'RACE'

nPatients	ASIAN	BLACK OR AFRICAN AMERICAN	WHITE
ALL	2	6	141
subtype1	0	3	36
subtype2	2	1	52
subtype3	0	2	53

Figure S67. Get High-res Image Clustering Approach #5: 'RPPA CNMF subtypes' versus Clinical Feature #13: 'RACE'

'RPPA CNMF subtypes' versus 'ETHNICITY'

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

Table S73. Clustering Approach #5: 'RPPA CNMF subtypes' versus Clinical Feature #14: 'ETHNICITY'

nPatients	HISPANIC OR LATINO	NOT HISPANIC OR LATINO
ALL	2	106
subtype1	0	28
subtype2	1	42
subtype3	1	36

Figure S68. Get High-res Image Clustering Approach #5: 'RPPA CNMF subtypes' versus Clinical Feature #14: 'ETHNICITY'

Clustering Approach #6: 'RPPA cHierClus subtypes'

Table S74. Description of clustering approach #6: 'RPPA cHierClus subtypes'

Cluster Labels	1	2	3	4	5
Number of samples	40	33	45	31	32

'RPPA cHierClus subtypes' versus 'Time to Death'

P value = 0.273 (logrank test), Q value = 1

Table S75. Clustering Approach #6: 'RPPA cHierClus subtypes' versus Clinical Feature #1: 'Time to Death'

	nPatients	nDeath	Duration Range (Median), Year
ALL	155	43	2.0 - 2370.0 (741.0)
subtype1	33	6	4.0 - 1968.0 (476.0)
subtype2	31	11	2.0 - 1961.0 (896.0)
subtype3	33	10	2.0 - 2370.0 (1178.0)
subtype4	28	11	24.0 - 1978.0 (940.5)
subtype5	30	5	22.0 - 1972.0 (505.5)

Figure S69. Get High-res Image Clustering Approach #6: 'RPPA cHierClus subtypes' versus Clinical Feature #1: 'Time to Death'

'RPPA cHierClus subtypes' versus 'AGE'

P value = 0.242 (Kruskal-Wallis (anova)), Q value = 1

Table S76. Clustering Approach #6: 'RPPA cHierClus subtypes' versus Clinical Feature #2: 'AGE'

	nPatients	Mean (Std.Dev)
ALL	164	65.5 (9.6)
subtype1	38	64.7 (9.0)
subtype2	30	64.7 (9.5)
subtype3	38	64.1 (10.4)
subtype4	28	65.9 (9.8)
subtype5	30	68.7 (9.1)

Figure S70. Get High-res Image Clustering Approach #6: 'RPPA cHierClus subtypes' versus Clinical Feature #2: 'AGE'

'RPPA cHierClus subtypes' versus 'NEOPLASM.DISEASESTAGE'

P value = 0.06 (Fisher's exact test), Q value = 1

Table S77. Clustering Approach #6: 'RPPA cHierClus subtypes' versus Clinical Feature #3: 'NEOPLASM.DISEASESTAGE'

nPatients	STAGE I	STAGE IA	STAGE IB	STAGE IIA	STAGE IIB	STAGE IIIA	STAGE IIIB	STAGE IV
ALL	1	41	52	15	25	33	7	7
subtype1	0	17	12	3	3	3	0	2
subtype2	0	7	12	1	3	5	2	3
subtype3	0	5	14	4	9	9	3	1
subtype4	1	3	8	2	6	10	1	0
subtype5	0	9	6	5	4	6	1	1

Figure S71. Get High-res Image Clustering Approach #6: 'RPPA cHierClus subtypes' versus Clinical Feature #3: 'NEOPLASM.DISEASESTAGE'

'RPPA cHierClus subtypes' versus 'PATHOLOGY.T.STAGE'

P value = 0.0586 (Fisher's exact test), Q value = 1

Table S78. Clustering Approach #6: 'RPPA cHierClus subtypes' versus Clinical Feature #4: 'PATHOLOGY.T.STAGE'

nPatients	T1	T2	T3	T4
ALL	47	108	13	12
subtype1	17	22	1	0
subtype2	6	21	2	4
subtype3	8	29	3	4
subtype4	6	18	6	1
subtype5	10	18	1	3

Figure S72. 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 = 0.306 (Fisher's exact test), Q value = 1

Table S79. Clustering Approach #6: 'RPPA cHierClus subtypes' versus Clinical Feature #5: 'PATHOLOGY.N.STAGE'

nPatients	N0	N1	N2+N3
ALL	106	34	35
subtype1	27	7	3
subtype2	23	4	6
subtype3	22	11	11
subtype4	15	6	9
subtype5	19	6	6

Figure S73. 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 = 0.0335 (Fisher's exact test), Q value = 1

Table S80. Clustering Approach #6: 'RPPA cHierClus subtypes' versus Clinical Feature #6: 'PATHOLOGY.M.STAGE'

nPatients	M0	M1	MX
ALL	136	6	37
subtype1	31	2	6
subtype2	28	3	2
subtype3	32	1	11
subtype4	25	0	6
subtype5	20	0	12

Figure S74. Get High-res Image Clustering Approach #6: 'RPPA cHierClus subtypes' versus Clinical Feature #6: 'PATHOLOGY.M.STAGE'

'RPPA cHierClus subtypes' versus 'GENDER'

P value = 0.00599 (Fisher's exact test), Q value = 0.87

Table S81. Clustering Approach #6: 'RPPA cHierClus subtypes' versus Clinical Feature #7: 'GENDER'

nPatients	FEMALE	MALE
ALL	105	76
subtype1	30	10
subtype2	11	22
subtype3	27	18
subtype4	16	15
subtype5	21	11

Figure S75. Get High-res Image Clustering Approach #6: 'RPPA cHierClus subtypes' versus Clinical Feature #7: 'GENDER'

'RPPA cHierClus subtypes' versus 'KARNOFSKY.PERFORMANCE.SCORE'

P value = 0.12 (Kruskal-Wallis (anova)), Q value = 1

Table S82. Clustering Approach #6: 'RPPA cHierClus subtypes' versus Clinical Feature #8: 'KARNOFSKY.PERFORMANCE.SCORE'

	nPatients	Mean (Std.Dev)
ALL	14	60.0 (40.6)
subtype1	3	50.0 (45.8)
subtype2	2	80.0 (0.0)
subtype3	2	0.0 (0.0)
subtype4	1	0.0 (NA)
subtype5	6	88.3 (9.8)

Figure S76. Get High-res Image Clustering Approach #6: 'RPPA cHierClus subtypes' versus Clinical Feature #8: 'KARNOFSKY.PERFORMANCE.SCORE'

'RPPA cHierClus subtypes' versus 'HISTOLOGICAL.TYPE'

P value = 0.0189 (Fisher's exact test), Q value = 1

Table S83. Clustering Approach #6: 'RPPA cHierClus subtypes' versus Clinical Feature #9: '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 MICROPAPILLARY ADENOCARCINOMA	LUNG MUCINOUS ADENOCARCINOMA	LUNG PAPILLARY ADENOCARCINOMA	MUCINOUS (COLLOID) CARCINOMA
ALL	5	43	111	3	8	2	1	5	3
subtype1	1	7	29	0	1	1	0	1	0
subtype2	0	17	13	1	1	0	0	1	0
subtype3	1	8	33	0	2	0	0	0	1
subtype4	1	4	20	2	1	0	1	1	1
subtype5	2	7	16	0	3	1	0	2	1

Figure S77. Get High-res Image Clustering Approach #6: 'RPPA cHierClus subtypes' versus Clinical Feature #9: 'HISTOLOGICAL.TYPE'

'RPPA cHierClus subtypes' versus 'RADIATIONS.RADIATION.REGIMENINDICATION'

P value = 0.634 (Fisher's exact test), Q value = 1

Table S84. Clustering Approach #6: 'RPPA cHierClus subtypes' versus Clinical Feature #10: 'RADIATIONS.RADIATION.REGIMENINDICATION'

nPatients	NO	YES
ALL	12	169
subtype1	2	38
subtype2	1	32
subtype3	3	42
subtype4	4	27
subtype5	2	30

Figure S78. Get High-res Image Clustering Approach #6: 'RPPA cHierClus subtypes' versus Clinical Feature #10: 'RADIATIONS.RADIATION.REGIMENINDICATION'

'RPPA cHierClus subtypes' versus 'NUMBERPACKYEARSSMOKED'

P value = 0.031 (Kruskal-Wallis (anova)), Q value = 1

Table S85. Clustering Approach #6: 'RPPA cHierClus subtypes' versus Clinical Feature #11: 'NUMBERPACKYEARSSMOKED'

	nPatients	Mean (Std.Dev)
ALL	127	41.8 (27.1)
subtype1	17	50.4 (28.5)
subtype2	29	45.9 (32.3)
subtype3	26	41.1 (21.8)
subtype4	27	46.7 (30.8)
subtype5	28	28.4 (15.7)

Figure S79. Get High-res Image Clustering Approach #6: 'RPPA cHierClus subtypes' versus Clinical Feature #11: 'NUMBERPACKYEARSSMOKED'

'RPPA cHierClus subtypes' versus 'COMPLETENESS.OF.RESECTION'

P value = 0.749 (Fisher's exact test), Q value = 1

Table S86. Clustering Approach #6: 'RPPA cHierClus subtypes' versus Clinical Feature #12: 'COMPLETENESS.OF.RESECTION'

nPatients	R0	R1	R2	RX
ALL	119	8	1	5
subtype1	30	1	1	3
subtype2	28	1	0	1
subtype3	22	2	0	1
subtype4	19	1	0	0
subtype5	20	3	0	0

Figure S80. Get High-res Image Clustering Approach #6: 'RPPA cHierClus subtypes' versus Clinical Feature #12: 'COMPLETENESS.OF.RESECTION'

'RPPA cHierClus subtypes' versus 'RACE'

P value = 0.171 (Fisher's exact test), Q value = 1

Table S87. Clustering Approach #6: 'RPPA cHierClus subtypes' versus Clinical Feature #13: 'RACE'

nPatients	ASIAN	BLACK OR AFRICAN AMERICAN	WHITE
ALL	2	6	141
subtype1	1	1	30
subtype2	0	3	22
subtype3	1	0	38
subtype4	0	0	25
subtype5	0	2	26

Figure S81. Get High-res Image Clustering Approach #6: 'RPPA cHierClus subtypes' versus Clinical Feature #13: 'RACE'

'RPPA cHierClus subtypes' versus 'ETHNICITY'

P value = 0.63 (Fisher's exact test), Q value = 1

Table S88. Clustering Approach #6: 'RPPA cHierClus subtypes' versus Clinical Feature #14: 'ETHNICITY'

nPatients	HISPANIC OR LATINO	NOT HISPANIC OR LATINO
ALL	2	106
subtype1	0	27
subtype2	0	11
subtype3	1	28
subtype4	1	16
subtype5	0	24

Figure S82. Get High-res Image Clustering Approach #6: 'RPPA cHierClus subtypes' versus Clinical Feature #14: 'ETHNICITY'

Clustering Approach #7: 'RNAseq CNMF subtypes'

Table S89. Description of clustering approach #7: 'RNAseq CNMF subtypes'

Cluster Labels	1	2	3	4	5
Number of samples	136	103	72	102	51

'RNAseq CNMF subtypes' versus 'Time to Death'

P value = 0.655 (logrank test), Q value = 1

Table S90. Clustering Approach #7: 'RNAseq CNMF subtypes' versus Clinical Feature #1: 'Time to Death'

	nPatients	nDeath	Duration Range (Median), Year
ALL	405	84	1.0 - 2696.0 (477.0)
subtype1	114	30	3.0 - 2370.0 (544.5)
subtype2	96	17	1.0 - 2696.0 (424.0)
subtype3	60	20	15.0 - 1997.0 (451.0)
subtype4	91	14	2.0 - 1972.0 (508.0)
subtype5	44	3	3.0 - 1968.0 (483.0)

Figure S83. Get High-res Image Clustering Approach #7: 'RNAseq CNMF subtypes' versus Clinical Feature #1: 'Time to Death'

'RNAseq CNMF subtypes' versus 'AGE'

P value = 0.000755 (Kruskal-Wallis (anova)), Q value = 0.12

Table S91. Clustering Approach #7: 'RNAseq CNMF subtypes' versus Clinical Feature #2: 'AGE'

	nPatients	Mean (Std.Dev)
ALL	433	65.6 (9.7)
subtype1	127	63.7 (10.0)
subtype2	97	68.4 (7.8)
subtype3	67	67.6 (9.7)
subtype4	95	63.8 (9.5)
subtype5	47	65.8 (10.7)

Figure S84. Get High-res Image Clustering Approach #7: 'RNAseq CNMF subtypes' versus Clinical Feature #2: 'AGE'

'RNAseq CNMF subtypes' versus 'NEOPLASM.DISEASESTAGE'

P value = 0.00218 (Fisher's exact test), Q value = 0.33

Table S92. Clustering Approach #7: 'RNAseq CNMF subtypes' versus Clinical Feature #3: 'NEOPLASM.DISEASESTAGE'

nPatients	STAGE I	STAGE IA	STAGE IB	STAGE IIA	STAGE IIB	STAGE IIIA	STAGE IIIB	STAGE IV
ALL	4	113	132	43	68	69	11	23
subtype1	2	21	39	17	26	21	4	6
subtype2	0	41	29	9	9	12	1	2
subtype3	0	11	17	2	17	17	3	5
subtype4	1	22	35	10	11	13	3	7
subtype5	1	18	12	5	5	6	0	3

Figure S85. Get High-res Image Clustering Approach #7: 'RNAseq CNMF subtypes' versus Clinical Feature #3: 'NEOPLASM.DISEASESTAGE'

'RNAseq CNMF subtypes' versus 'PATHOLOGY.T.STAGE'

P value = 0.00149 (Fisher's exact test), Q value = 0.23

Table S93. Clustering Approach #7: 'RNAseq CNMF subtypes' versus Clinical Feature #4: 'PATHOLOGY.T.STAGE'

nPatients	T1	T2	T3	T4
ALL	143	260	41	18
subtype1	31	87	12	6
subtype2	48	45	6	4
subtype3	14	43	10	4
subtype4	26	64	8	3
subtype5	24	21	5	1

Figure S86. 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 = 0.00609 (Fisher's exact test), Q value = 0.88

Table S94. Clustering Approach #7: 'RNAseq CNMF subtypes' versus Clinical Feature #5: 'PATHOLOGY.N.STAGE'

nPatients	N0	N1	N2+N3
ALL	293	88	73
subtype1	73	36	25
subtype2	76	14	10
subtype3	38	15	18
subtype4	74	13	14
subtype5	32	10	6

Figure S87. 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 = 0.523 (Fisher's exact test), Q value = 1

Table S95. Clustering Approach #7: 'RNAseq CNMF subtypes' versus Clinical Feature #6: 'PATHOLOGY.M.STAGE'

nPatients	M0	M1	M1A	M1B	MX
ALL	319	18	1	3	119
subtype1	94	5	0	0	36
subtype2	71	2	0	0	30
subtype3	53	5	0	0	14
subtype4	70	4	1	2	24
subtype5	31	2	0	1	15

Figure S88. Get High-res Image Clustering Approach #7: 'RNAseq CNMF subtypes' versus Clinical Feature #6: 'PATHOLOGY.M.STAGE'

'RNAseq CNMF subtypes' versus 'GENDER'

P value = 0.00084 (Fisher's exact test), Q value = 0.13

Table S96. Clustering Approach #7: 'RNAseq CNMF subtypes' versus Clinical Feature #7: 'GENDER'

nPatients	FEMALE	MALE
ALL	252	212
subtype1	78	58
subtype2	67	36
subtype3	35	37
subtype4	39	63
subtype5	33	18

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

'RNAseq CNMF subtypes' versus 'KARNOFSKY.PERFORMANCE.SCORE'

P value = 0.0318 (Kruskal-Wallis (anova)), Q value = 1

Table S97. Clustering Approach #7: 'RNAseq CNMF subtypes' versus Clinical Feature #8: 'KARNOFSKY.PERFORMANCE.SCORE'

	nPatients	Mean (Std.Dev)
ALL	82	83.9 (23.1)
subtype1	28	75.0 (30.1)
subtype2	16	94.4 (7.3)
subtype3	8	93.8 (9.2)
subtype4	20	86.0 (15.7)
subtype5	10	80.0 (29.1)

Figure S90. Get High-res Image Clustering Approach #7: 'RNAseq CNMF subtypes' versus Clinical Feature #8: 'KARNOFSKY.PERFORMANCE.SCORE'

'RNAseq CNMF subtypes' versus 'HISTOLOGICAL.TYPE'

P value = 0.00282 (Fisher's exact test), Q value = 0.42

Table S98. Clustering Approach #7: 'RNAseq CNMF subtypes' versus Clinical Feature #9: '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	15	93	293	4	19	2	4	2	19	1	5	7
subtype1	2	23	100	0	5	1	3	0	2	0	0	0
subtype2	6	22	58	2	8	0	1	0	6	0	0	0
subtype3	1	15	44	1	1	1	0	1	2	0	2	4
subtype4	5	19	66	0	2	0	0	0	7	0	2	1
subtype5	1	14	25	1	3	0	0	1	2	1	1	2

Figure S91. Get High-res Image Clustering Approach #7: 'RNAseq CNMF subtypes' versus Clinical Feature #9: 'HISTOLOGICAL.TYPE'

'RNAseq CNMF subtypes' versus 'RADIATIONS.RADIATION.REGIMENINDICATION'

P value = 0.587 (Fisher's exact test), Q value = 1

Table S99. Clustering Approach #7: 'RNAseq CNMF subtypes' versus Clinical Feature #10: 'RADIATIONS.RADIATION.REGIMENINDICATION'

nPatients	NO	YES
ALL	21	443
subtype1	6	130
subtype2	4	99
subtype3	6	66
subtype4	3	99
subtype5	2	49

Figure S92. Get High-res Image Clustering Approach #7: 'RNAseq CNMF subtypes' versus Clinical Feature #10: 'RADIATIONS.RADIATION.REGIMENINDICATION'

'RNAseq CNMF subtypes' versus 'NUMBERPACKYEARSSMOKED'

P value = 0.117 (Kruskal-Wallis (anova)), Q value = 1

Table S100. Clustering Approach #7: 'RNAseq CNMF subtypes' versus Clinical Feature #11: 'NUMBERPACKYEARSSMOKED'

	nPatients	Mean (Std.Dev)
ALL	315	41.9 (27.3)
subtype1	90	45.3 (28.1)
subtype2	63	34.5 (23.7)
subtype3	52	41.3 (23.9)
subtype4	78	44.3 (31.6)
subtype5	32	42.0 (23.4)

Figure S93. Get High-res Image Clustering Approach #7: 'RNAseq CNMF subtypes' versus Clinical Feature #11: 'NUMBERPACKYEARSSMOKED'

'RNAseq CNMF subtypes' versus 'COMPLETENESS.OF.RESECTION'

P value = 0.782 (Fisher's exact test), Q value = 1

Table S101. Clustering Approach #7: 'RNAseq CNMF subtypes' versus Clinical Feature #12: 'COMPLETENESS.OF.RESECTION'

nPatients	R0	R1	R2	RX
ALL	318	11	4	19
subtype1	91	3	1	6
subtype2	73	3	0	4
subtype3	49	2	1	2
subtype4	71	3	0	4
subtype5	34	0	2	3

Figure S94. Get High-res Image Clustering Approach #7: 'RNAseq CNMF subtypes' versus Clinical Feature #12: 'COMPLETENESS.OF.RESECTION'

'RNAseq CNMF subtypes' versus 'RACE'

P value = 0.749 (Fisher's exact test), Q value = 1

Table S102. Clustering Approach #7: 'RNAseq CNMF subtypes' versus Clinical Feature #13: 'RACE'

nPatients	AMERICAN INDIAN OR ALASKA NATIVE	ASIAN	BLACK OR AFRICAN AMERICAN	WHITE
ALL	1	7	27	362
subtype1	1	3	10	105
subtype2	0	1	5	86
subtype3	0	1	1	56
subtype4	0	2	8	74
subtype5	0	0	3	41

Figure S95. Get High-res Image Clustering Approach #7: 'RNAseq CNMF subtypes' versus Clinical Feature #13: 'RACE'

'RNAseq CNMF subtypes' versus 'ETHNICITY'

P value = 0.978 (Fisher's exact test), Q value = 1

Table S103. Clustering Approach #7: 'RNAseq CNMF subtypes' versus Clinical Feature #14: 'ETHNICITY'

nPatients	HISPANIC OR LATINO	NOT HISPANIC OR LATINO
ALL	7	333
subtype1	2	102
subtype2	1	79
subtype3	1	44
subtype4	2	67
subtype5	1	41

Figure S96. Get High-res Image Clustering Approach #7: 'RNAseq CNMF subtypes' versus Clinical Feature #14: 'ETHNICITY'

Clustering Approach #8: 'RNAseq cHierClus subtypes'

Table S104. Description of clustering approach #8: 'RNAseq cHierClus subtypes'

Cluster Labels	1	2	3	4	5	6	7	8	9
Number of samples	82	52	44	80	43	48	47	16	52

'RNAseq cHierClus subtypes' versus 'Time to Death'

P value = 0.0346 (logrank test), Q value = 1

Table S105. Clustering Approach #8: 'RNAseq cHierClus subtypes' versus Clinical Feature #1: 'Time to Death'

	nPatients	nDeath	Duration Range (Median), Year
ALL	405	84	1.0 - 2696.0 (477.0)
subtype1	74	14	3.0 - 2696.0 (441.5)
subtype2	48	7	3.0 - 2151.0 (431.0)
subtype3	32	8	23.0 - 2370.0 (661.0)
subtype4	67	15	2.0 - 1973.0 (592.0)
subtype5	39	11	1.0 - 1965.0 (690.0)
subtype6	45	5	4.0 - 1972.0 (455.0)
subtype7	39	17	15.0 - 1997.0 (678.0)
subtype8	14	2	22.0 - 1932.0 (139.5)
subtype9	47	5	3.0 - 2174.0 (459.0)

Figure S97. Get High-res Image Clustering Approach #8: 'RNAseq cHierClus subtypes' versus Clinical Feature #1: 'Time to Death'

'RNAseq cHierClus subtypes' versus 'AGE'

P value = 0.000395 (Kruskal-Wallis (anova)), Q value = 0.063

Table S106. Clustering Approach #8: 'RNAseq cHierClus subtypes' versus Clinical Feature #2: 'AGE'

	nPatients	Mean (Std.Dev)
ALL	433	65.6 (9.7)
subtype1	80	64.0 (9.8)
subtype2	48	68.4 (8.9)
subtype3	37	64.6 (11.3)
subtype4	73	66.8 (9.0)
subtype5	41	68.0 (7.1)
subtype6	45	61.1 (9.7)
subtype7	45	66.1 (9.8)
subtype8	14	73.3 (7.9)
subtype9	50	64.2 (9.6)

Figure S98. Get High-res Image Clustering Approach #8: 'RNAseq cHierClus subtypes' versus Clinical Feature #2: 'AGE'

'RNAseq cHierClus subtypes' versus 'NEOPLASM.DISEASESTAGE'

P value = 0.00063 (Fisher's exact test), Q value = 0.099

Table S107. Clustering Approach #8: 'RNAseq cHierClus subtypes' versus Clinical Feature #3: 'NEOPLASM.DISEASESTAGE'

nPatients	STAGE I	STAGE IA	STAGE IB	STAGE IIA	STAGE IIB	STAGE IIIA	STAGE IIIB	STAGE IV
ALL	4	113	132	43	68	69	11	23
subtype1	1	18	28	3	17	11	0	4
subtype2	0	15	16	7	6	5	1	2
subtype3	0	6	12	5	7	10	3	1
subtype4	1	21	23	13	5	10	2	5
subtype5	0	15	13	2	6	3	2	2
subtype6	1	6	15	6	5	12	1	2
subtype7	0	7	8	1	12	12	2	5
subtype8	0	1	7	0	6	1	0	0
subtype9	1	24	10	6	4	5	0	2

Figure S99. Get High-res Image Clustering Approach #8: 'RNAseq cHierClus subtypes' versus Clinical Feature #3: 'NEOPLASM.DISEASESTAGE'

'RNAseq cHierClus subtypes' versus 'PATHOLOGY.T.STAGE'

P value = 0.00029 (Fisher's exact test), Q value = 0.047

Table S108. Clustering Approach #8: 'RNAseq cHierClus subtypes' versus Clinical Feature #4: 'PATHOLOGY.T.STAGE'

nPatients	T1	T2	T3	T4
ALL	143	260	41	18
subtype1	22	48	9	3
subtype2	21	28	2	1
subtype3	9	26	6	3
subtype4	32	42	2	3
subtype5	14	22	4	3
subtype6	8	34	5	1
subtype7	8	30	5	3
subtype8	1	9	6	0
subtype9	28	21	2	1

Figure S100. 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 = 0.0138 (Fisher's exact test), Q value = 1

Table S109. Clustering Approach #8: 'RNAseq cHierClus subtypes' versus Clinical Feature #5: 'PATHOLOGY.N.STAGE'

nPatients	N0	N1	N2+N3
ALL	293	88	73
subtype1	55	16	10
subtype2	34	10	7
subtype3	24	9	11
subtype4	48	20	11
subtype5	33	7	2
subtype6	32	3	12
subtype7	21	11	14
subtype8	13	1	1
subtype9	33	11	5

Figure S101. 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 = 0.179 (Fisher's exact test), Q value = 1

Table S110. Clustering Approach #8: 'RNAseq cHierClus subtypes' versus Clinical Feature #6: 'PATHOLOGY.M.STAGE'

nPatients	M0	M1	M1A	M1B	MX
ALL	319	18	1	3	119
subtype1	55	3	0	0	24
subtype2	35	1	1	0	15
subtype3	33	1	0	0	10
subtype4	47	4	0	1	27
subtype5	34	2	0	0	7
subtype6	34	1	0	1	11
subtype7	37	5	0	0	5
subtype8	8	0	0	0	7
subtype9	36	1	0	1	13

Figure S102. 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 = 0.0017

Table S111. Clustering Approach #8: 'RNAseq cHierClus subtypes' versus Clinical Feature #7: 'GENDER'

nPatients	FEMALE	MALE
ALL	252	212
subtype1	50	32
subtype2	45	7
subtype3	20	24
subtype4	45	35
subtype5	14	29
subtype6	20	28
subtype7	18	29
subtype8	6	10
subtype9	34	18

Figure S103. Get High-res Image Clustering Approach #8: 'RNAseq cHierClus subtypes' versus Clinical Feature #7: 'GENDER'

'RNAseq cHierClus subtypes' versus 'KARNOFSKY.PERFORMANCE.SCORE'

P value = 0.194 (Kruskal-Wallis (anova)), Q value = 1

Table S112. Clustering Approach #8: 'RNAseq cHierClus subtypes' versus Clinical Feature #8: 'KARNOFSKY.PERFORMANCE.SCORE'

	nPatients	Mean (Std.Dev)
ALL	82	83.9 (23.1)
subtype1	12	85.8 (18.8)
subtype2	10	93.0 (8.2)
subtype3	7	75.7 (35.1)
subtype4	18	82.8 (23.5)
subtype5	6	95.0 (8.4)
subtype6	12	81.7 (17.5)
subtype7	5	96.0 (8.9)
subtype8	2	85.0 (7.1)
subtype9	10	70.0 (38.0)

Figure S104. Get High-res Image Clustering Approach #8: 'RNAseq cHierClus subtypes' versus Clinical Feature #8: 'KARNOFSKY.PERFORMANCE.SCORE'

'RNAseq cHierClus subtypes' versus 'HISTOLOGICAL.TYPE'

P value = 1e-05 (Fisher's exact test), Q value = 0.0017

Table S113. Clustering Approach #8: 'RNAseq cHierClus subtypes' versus Clinical Feature #9: '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	15	93	293	4	19	2	4	2	19	1	5	7
subtype1	3	14	52	0	5	1	3	0	3	0	1	0
subtype2	3	9	30	1	4	0	1	0	4	0	0	0
subtype3	0	4	39	0	0	0	0	0	1	0	0	0
subtype4	2	13	59	1	2	1	0	0	1	0	1	0
subtype5	1	17	18	0	1	0	0	0	6	0	0	0
subtype6	4	8	34	0	1	0	0	0	0	0	0	1
subtype7	0	13	28	0	0	0	0	0	2	0	2	2
subtype8	2	4	3	2	1	0	0	1	0	0	0	3
subtype9	0	11	30	0	5	0	0	1	2	1	1	1

Figure S105. Get High-res Image Clustering Approach #8: 'RNAseq cHierClus subtypes' versus Clinical Feature #9: 'HISTOLOGICAL.TYPE'

'RNAseq cHierClus subtypes' versus 'RADIATIONS.RADIATION.REGIMENINDICATION'

P value = 0.0786 (Fisher's exact test), Q value = 1

Table S114. Clustering Approach #8: 'RNAseq cHierClus subtypes' versus Clinical Feature #10: 'RADIATIONS.RADIATION.REGIMENINDICATION'

nPatients	NO	YES
ALL	21	443
subtype1	2	80
subtype2	2	50
subtype3	3	41
subtype4	1	79
subtype5	0	43
subtype6	3	45
subtype7	5	42
subtype8	0	16
subtype9	5	47

Figure S106. Get High-res Image Clustering Approach #8: 'RNAseq cHierClus subtypes' versus Clinical Feature #10: 'RADIATIONS.RADIATION.REGIMENINDICATION'

'RNAseq cHierClus subtypes' versus 'NUMBERPACKYEARSSMOKED'

P value = 0.00816 (Kruskal-Wallis (anova)), Q value = 1

Table S115. Clustering Approach #8: 'RNAseq cHierClus subtypes' versus Clinical Feature #11: 'NUMBERPACKYEARSSMOKED'

	nPatients	Mean (Std.Dev)
ALL	315	41.9 (27.3)
subtype1	51	36.9 (24.7)
subtype2	28	34.9 (24.2)
subtype3	35	44.8 (25.6)
subtype4	54	51.0 (30.8)
subtype5	33	41.2 (31.5)
subtype6	38	37.2 (27.5)
subtype7	37	46.0 (24.8)
subtype8	8	22.6 (13.6)
subtype9	31	43.9 (25.3)

Figure S107. Get High-res Image Clustering Approach #8: 'RNAseq cHierClus subtypes' versus Clinical Feature #11: 'NUMBERPACKYEARSSMOKED'

'RNAseq cHierClus subtypes' versus 'COMPLETENESS.OF.RESECTION'

P value = 0.332 (Fisher's exact test), Q value = 1

Table S116. Clustering Approach #8: 'RNAseq cHierClus subtypes' versus Clinical Feature #12: 'COMPLETENESS.OF.RESECTION'

nPatients	R0	R1	R2	RX
ALL	318	11	4	19
subtype1	57	3	0	4
subtype2	40	2	0	0
subtype3	30	0	2	0
subtype4	47	3	2	6
subtype5	27	0	0	3
subtype6	35	1	0	1
subtype7	33	2	0	2
subtype8	11	0	0	0
subtype9	38	0	0	3

Figure S108. Get High-res Image Clustering Approach #8: 'RNAseq cHierClus subtypes' versus Clinical Feature #12: 'COMPLETENESS.OF.RESECTION'

'RNAseq cHierClus subtypes' versus 'RACE'

P value = 0.374 (Fisher's exact test), Q value = 1

Table S117. Clustering Approach #8: 'RNAseq cHierClus subtypes' versus Clinical Feature #13: 'RACE'

nPatients	AMERICAN INDIAN OR ALASKA NATIVE	ASIAN	BLACK OR AFRICAN AMERICAN	WHITE
ALL	1	7	27	362
subtype1	1	3	6	62
subtype2	0	2	1	42
subtype3	0	0	2	34
subtype4	0	0	7	62
subtype5	0	0	4	33
subtype6	0	0	3	36
subtype7	0	2	0	38
subtype8	0	0	0	11
subtype9	0	0	4	44

Figure S109. Get High-res Image Clustering Approach #8: 'RNAseq cHierClus subtypes' versus Clinical Feature #13: 'RACE'

'RNAseq cHierClus subtypes' versus 'ETHNICITY'

P value = 0.107 (Fisher's exact test), Q value = 1

Table S118. Clustering Approach #8: 'RNAseq cHierClus subtypes' versus Clinical Feature #14: 'ETHNICITY'

nPatients	HISPANIC OR LATINO	NOT HISPANIC OR LATINO
ALL	7	333
subtype1	0	63
subtype2	1	39
subtype3	0	30
subtype4	4	56
subtype5	0	29
subtype6	0	32
subtype7	2	29
subtype8	0	10
subtype9	0	45

Figure S110. Get High-res Image Clustering Approach #8: 'RNAseq cHierClus subtypes' versus Clinical Feature #14: 'ETHNICITY'

Clustering Approach #9: 'MIRSEQ CNMF'

Table S119. Description of clustering approach #9: 'MIRSEQ CNMF'

Cluster Labels	1	2	3
Number of samples	172	215	87

'MIRSEQ CNMF' versus 'Time to Death'

P value = 0.59 (logrank test), Q value = 1

Table S120. Clustering Approach #9: 'MIRSEQ CNMF' versus Clinical Feature #1: 'Time to Death'

	nPatients	nDeath	Duration Range (Median), Year
ALL	415	86	1.0 - 6443.0 (476.0)
subtype1	154	30	1.0 - 2696.0 (467.5)
subtype2	189	37	2.0 - 6443.0 (486.0)
subtype3	72	19	2.0 - 2370.0 (446.5)

Figure S111. Get High-res Image Clustering Approach #9: 'MIRSEQ CNMF' versus Clinical Feature #1: 'Time to Death'

'MIRSEQ CNMF' versus 'AGE'

P value = 0.0363 (Kruskal-Wallis (anova)), Q value = 1

Table S121. Clustering Approach #9: 'MIRSEQ CNMF' versus Clinical Feature #2: 'AGE'

	nPatients	Mean (Std.Dev)
ALL	444	65.5 (9.8)
subtype1	162	66.9 (9.3)
subtype2	205	64.3 (10.4)
subtype3	77	65.4 (9.1)

Figure S112. Get High-res Image Clustering Approach #9: 'MIRSEQ CNMF' versus Clinical Feature #2: 'AGE'

'MIRSEQ CNMF' versus 'NEOPLASM.DISEASESTAGE'

P value = 0.00657 (Fisher's exact test), Q value = 0.95

Table S122. Clustering Approach #9: 'MIRSEQ CNMF' versus Clinical Feature #3: 'NEOPLASM.DISEASESTAGE'

nPatients	STAGE I	STAGE IA	STAGE IB	STAGE IIA	STAGE IIB	STAGE IIIA	STAGE IIIB	STAGE IV
ALL	5	115	133	49	68	69	11	23
subtype1	1	61	36	17	25	21	1	9
subtype2	3	40	68	22	33	29	8	12
subtype3	1	14	29	10	10	19	2	2

Figure S113. Get High-res Image Clustering Approach #9: 'MIRSEQ CNMF' versus Clinical Feature #3: 'NEOPLASM.DISEASESTAGE'

'MIRSEQ CNMF' versus 'PATHOLOGY.T.STAGE'

P value = 0.0261 (Fisher's exact test), Q value = 1

Table S123. Clustering Approach #9: 'MIRSEQ CNMF' versus Clinical Feature #4: 'PATHOLOGY.T.STAGE'

nPatients	T1	T2	T3	T4
ALL	146	264	43	18
subtype1	71	81	14	6
subtype2	51	131	22	9
subtype3	24	52	7	3

Figure S114. Get High-res Image Clustering Approach #9: 'MIRSEQ CNMF' versus Clinical Feature #4: 'PATHOLOGY.T.STAGE'

'MIRSEQ CNMF' versus 'PATHOLOGY.N.STAGE'

P value = 0.422 (Fisher's exact test), Q value = 1

Table S124. Clustering Approach #9: 'MIRSEQ CNMF' versus Clinical Feature #5: 'PATHOLOGY.N.STAGE'

nPatients	N0	N1	N2+N3
ALL	299	90	74
subtype1	108	37	21
subtype2	139	38	35
subtype3	52	15	18

Figure S115. Get High-res Image Clustering Approach #9: 'MIRSEQ CNMF' versus Clinical Feature #5: 'PATHOLOGY.N.STAGE'

'MIRSEQ CNMF' versus 'PATHOLOGY.M.STAGE'

P value = 0.378 (Fisher's exact test), Q value = 1

Table S125. Clustering Approach #9: 'MIRSEQ CNMF' versus Clinical Feature #6: 'PATHOLOGY.M.STAGE'

nPatients	M0	M1	M1A	M1B	MX
ALL	324	16	1	4	125
subtype1	118	7	0	1	44
subtype2	152	8	1	3	50
subtype3	54	1	0	0	31

Figure S116. Get High-res Image Clustering Approach #9: 'MIRSEQ CNMF' versus Clinical Feature #6: 'PATHOLOGY.M.STAGE'

'MIRSEQ CNMF' versus 'GENDER'

P value = 0.516 (Fisher's exact test), Q value = 1

Table S126. Clustering Approach #9: 'MIRSEQ CNMF' versus Clinical Feature #7: 'GENDER'

nPatients	FEMALE	MALE
ALL	254	220
subtype1	98	74
subtype2	110	105
subtype3	46	41

Figure S117. Get High-res Image Clustering Approach #9: 'MIRSEQ CNMF' versus Clinical Feature #7: 'GENDER'

'MIRSEQ CNMF' versus 'KARNOFSKY.PERFORMANCE.SCORE'

P value = 0.533 (Kruskal-Wallis (anova)), Q value = 1

Table S127. Clustering Approach #9: 'MIRSEQ CNMF' versus Clinical Feature #8: 'KARNOFSKY.PERFORMANCE.SCORE'

	nPatients	Mean (Std.Dev)
ALL	83	83.5 (22.8)
subtype1	27	83.0 (25.4)
subtype2	48	84.6 (22.0)
subtype3	8	78.8 (20.3)

Figure S118. Get High-res Image Clustering Approach #9: 'MIRSEQ CNMF' versus Clinical Feature #8: 'KARNOFSKY.PERFORMANCE.SCORE'

'MIRSEQ CNMF' versus 'HISTOLOGICAL.TYPE'

P value = 0.00026 (Fisher's exact test), Q value = 0.042

Table S128. Clustering Approach #9: 'MIRSEQ CNMF' versus Clinical Feature #9: '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	15	93	303	5	19	2	3	2	19	1	5	7
subtype1	8	37	93	4	12	1	1	2	8	1	2	3
subtype2	7	50	140	0	4	1	0	0	8	0	3	2
subtype3	0	6	70	1	3	0	2	0	3	0	0	2

Figure S119. Get High-res Image Clustering Approach #9: 'MIRSEQ CNMF' versus Clinical Feature #9: 'HISTOLOGICAL.TYPE'

'MIRSEQ CNMF' versus 'RADIATIONS.RADIATION.REGIMENINDICATION'

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

Table S129. Clustering Approach #9: 'MIRSEQ CNMF' versus Clinical Feature #10: 'RADIATIONS.RADIATION.REGIMENINDICATION'

nPatients	NO	YES
ALL	20	454
subtype1	7	165
subtype2	9	206
subtype3	4	83

Figure S120. Get High-res Image Clustering Approach #9: 'MIRSEQ CNMF' versus Clinical Feature #10: 'RADIATIONS.RADIATION.REGIMENINDICATION'

'MIRSEQ CNMF' versus 'NUMBERPACKYEARSSMOKED'

P value = 0.0485 (Kruskal-Wallis (anova)), Q value = 1

Table S130. Clustering Approach #9: 'MIRSEQ CNMF' versus Clinical Feature #11: 'NUMBERPACKYEARSSMOKED'

	nPatients	Mean (Std.Dev)
ALL	325	42.2 (27.3)
subtype1	111	37.8 (24.8)
subtype2	160	43.8 (28.2)
subtype3	54	46.6 (28.8)

Figure S121. Get High-res Image Clustering Approach #9: 'MIRSEQ CNMF' versus Clinical Feature #11: 'NUMBERPACKYEARSSMOKED'

'MIRSEQ CNMF' versus 'COMPLETENESS.OF.RESECTION'

P value = 0.426 (Fisher's exact test), Q value = 1

Table S131. Clustering Approach #9: 'MIRSEQ CNMF' versus Clinical Feature #12: 'COMPLETENESS.OF.RESECTION'

nPatients	R0	R1	R2	RX
ALL	324	12	4	21
subtype1	117	2	2	8
subtype2	155	7	2	7
subtype3	52	3	0	6

Figure S122. Get High-res Image Clustering Approach #9: 'MIRSEQ CNMF' versus Clinical Feature #12: 'COMPLETENESS.OF.RESECTION'

'MIRSEQ CNMF' versus 'RACE'

P value = 0.455 (Fisher's exact test), Q value = 1

Table S132. Clustering Approach #9: 'MIRSEQ CNMF' versus Clinical Feature #13: 'RACE'

nPatients	ASIAN	BLACK OR AFRICAN AMERICAN	WHITE
ALL	7	35	365
subtype1	1	13	139
subtype2	4	18	154
subtype3	2	4	72

Figure S123. Get High-res Image Clustering Approach #9: 'MIRSEQ CNMF' versus Clinical Feature #13: 'RACE'

'MIRSEQ CNMF' versus 'ETHNICITY'

P value = 0.37 (Fisher's exact test), Q value = 1

Table S133. Clustering Approach #9: 'MIRSEQ CNMF' versus Clinical Feature #14: 'ETHNICITY'

nPatients	HISPANIC OR LATINO	NOT HISPANIC OR LATINO
ALL	7	343
subtype1	1	127
subtype2	5	149
subtype3	1	67

Figure S124. Get High-res Image Clustering Approach #9: 'MIRSEQ CNMF' versus Clinical Feature #14: 'ETHNICITY'

Clustering Approach #10: 'MIRSEQ CHIERARCHICAL'

Table S134. Description of clustering approach #10: 'MIRSEQ CHIERARCHICAL'

Cluster Labels	1	2	3	4
Number of samples	64	190	129	91

'MIRSEQ CHIERARCHICAL' versus 'Time to Death'

P value = 0.552 (logrank test), Q value = 1

Table S135. Clustering Approach #10: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #1: 'Time to Death'

	nPatients	nDeath	Duration Range (Median), Year
ALL	415	86	1.0 - 6443.0 (476.0)
subtype1	60	15	1.0 - 2174.0 (743.0)
subtype2	167	33	2.0 - 6443.0 (422.0)
subtype3	109	21	3.0 - 1980.0 (383.0)
subtype4	79	17	4.0 - 2696.0 (674.0)

Figure S125. Get High-res Image Clustering Approach #10: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #1: 'Time to Death'

'MIRSEQ CHIERARCHICAL' versus 'AGE'

P value = 0.00333 (Kruskal-Wallis (anova)), Q value = 0.5

Table S136. Clustering Approach #10: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #2: 'AGE'

	nPatients	Mean (Std.Dev)
ALL	444	65.5 (9.8)
subtype1	60	68.6 (7.4)
subtype2	180	63.9 (9.8)
subtype3	120	66.8 (9.9)
subtype4	84	64.5 (10.7)

Figure S126. Get High-res Image Clustering Approach #10: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #2: 'AGE'

'MIRSEQ CHIERARCHICAL' versus 'NEOPLASM.DISEASESTAGE'

P value = 0.413 (Fisher's exact test), Q value = 1

Table S137. Clustering Approach #10: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #3: 'NEOPLASM.DISEASESTAGE'

nPatients	STAGE I	STAGE IA	STAGE IB	STAGE IIA	STAGE IIB	STAGE IIIA	STAGE IIIB	STAGE IV
ALL	5	115	133	49	68	69	11	23
subtype1	0	25	13	2	11	9	1	3
subtype2	4	35	59	20	29	28	6	9
subtype3	1	36	35	15	17	16	2	6
subtype4	0	19	26	12	11	16	2	5

Figure S127. Get High-res Image Clustering Approach #10: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #3: 'NEOPLASM.DISEASESTAGE'

'MIRSEQ CHIERARCHICAL' versus 'PATHOLOGY.T.STAGE'

P value = 0.158 (Fisher's exact test), Q value = 1

Table S138. Clustering Approach #10: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #4: 'PATHOLOGY.T.STAGE'

nPatients	T1	T2	T3	T4
ALL	146	264	43	18
subtype1	27	30	3	4
subtype2	45	117	19	7
subtype3	47	65	12	4
subtype4	27	52	9	3

Figure S128. Get High-res Image Clustering Approach #10: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #4: 'PATHOLOGY.T.STAGE'

'MIRSEQ CHIERARCHICAL' versus 'PATHOLOGY.N.STAGE'

P value = 0.839 (Fisher's exact test), Q value = 1

Table S139. Clustering Approach #10: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #5: 'PATHOLOGY.N.STAGE'

nPatients	N0	N1	N2+N3
ALL	299	90	74
subtype1	41	13	7
subtype2	123	34	31
subtype3	79	27	18
subtype4	56	16	18

Figure S129. Get High-res Image Clustering Approach #10: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #5: 'PATHOLOGY.N.STAGE'

'MIRSEQ CHIERARCHICAL' versus 'PATHOLOGY.M.STAGE'

P value = 0.389 (Fisher's exact test), Q value = 1

Table S140. Clustering Approach #10: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #6: 'PATHOLOGY.M.STAGE'

nPatients	M0	M1	M1A	M1B	MX
ALL	324	16	1	4	125
subtype1	45	2	0	0	17
subtype2	137	8	1	0	43
subtype3	82	4	0	1	40
subtype4	60	2	0	3	25

Figure S130. Get High-res Image Clustering Approach #10: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #6: 'PATHOLOGY.M.STAGE'

'MIRSEQ CHIERARCHICAL' versus 'GENDER'

P value = 0.00362 (Fisher's exact test), Q value = 0.54

Table S141. Clustering Approach #10: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #7: 'GENDER'

nPatients	FEMALE	MALE
ALL	254	220
subtype1	31	33
subtype2	108	82
subtype3	80	49
subtype4	35	56

Figure S131. Get High-res Image Clustering Approach #10: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #7: 'GENDER'

'MIRSEQ CHIERARCHICAL' versus 'KARNOFSKY.PERFORMANCE.SCORE'

P value = 0.788 (Kruskal-Wallis (anova)), Q value = 1

Table S142. Clustering Approach #10: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #8: 'KARNOFSKY.PERFORMANCE.SCORE'

	nPatients	Mean (Std.Dev)
ALL	83	83.5 (22.8)
subtype1	7	90.0 (8.2)
subtype2	44	84.5 (22.7)
subtype3	17	78.2 (30.7)
subtype4	15	83.3 (17.6)

Figure S132. Get High-res Image Clustering Approach #10: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #8: 'KARNOFSKY.PERFORMANCE.SCORE'

'MIRSEQ CHIERARCHICAL' versus 'HISTOLOGICAL.TYPE'

P value = 0.0107 (Fisher's exact test), Q value = 1

Table S143. Clustering Approach #10: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #9: '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	15	93	303	5	19	2	3	2	19	1	5	7
subtype1	4	15	36	0	4	1	0	0	4	0	0	0
subtype2	4	36	132	2	4	0	3	0	8	0	1	0
subtype3	5	25	70	3	10	0	0	2	6	1	2	5
subtype4	2	17	65	0	1	1	0	0	1	0	2	2

Figure S133. Get High-res Image Clustering Approach #10: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #9: 'HISTOLOGICAL.TYPE'

'MIRSEQ CHIERARCHICAL' versus 'RADIATIONS.RADIATION.REGIMENINDICATION'

P value = 0.804 (Fisher's exact test), Q value = 1

Table S144. Clustering Approach #10: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #10: 'RADIATIONS.RADIATION.REGIMENINDICATION'

nPatients	NO	YES
ALL	20	454
subtype1	4	60
subtype2	7	183
subtype3	5	124
subtype4	4	87

Figure S134. Get High-res Image Clustering Approach #10: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #10: 'RADIATIONS.RADIATION.REGIMENINDICATION'

'MIRSEQ CHIERARCHICAL' versus 'NUMBERPACKYEARSSMOKED'

P value = 0.0441 (Kruskal-Wallis (anova)), Q value = 1

Table S145. Clustering Approach #10: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #11: 'NUMBERPACKYEARSSMOKED'

	nPatients	Mean (Std.Dev)
ALL	325	42.2 (27.3)
subtype1	43	40.5 (28.0)
subtype2	131	41.7 (25.5)
subtype3	82	37.5 (24.7)
subtype4	69	50.0 (31.8)

Figure S135. Get High-res Image Clustering Approach #10: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #11: 'NUMBERPACKYEARSSMOKED'

'MIRSEQ CHIERARCHICAL' versus 'COMPLETENESS.OF.RESECTION'

P value = 0.995 (Fisher's exact test), Q value = 1

Table S146. Clustering Approach #10: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #12: 'COMPLETENESS.OF.RESECTION'

nPatients	R0	R1	R2	RX
ALL	324	12	4	21
subtype1	39	1	0	3
subtype2	137	6	1	8
subtype3	87	3	2	6
subtype4	61	2	1	4

Figure S136. Get High-res Image Clustering Approach #10: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #12: 'COMPLETENESS.OF.RESECTION'

'MIRSEQ CHIERARCHICAL' versus 'RACE'

P value = 0.763 (Fisher's exact test), Q value = 1

Table S147. Clustering Approach #10: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #13: 'RACE'

nPatients	ASIAN	BLACK OR AFRICAN AMERICAN	WHITE
ALL	7	35	365
subtype1	1	5	51
subtype2	4	14	146
subtype3	1	7	106
subtype4	1	9	62

Figure S137. Get High-res Image Clustering Approach #10: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #13: 'RACE'

'MIRSEQ CHIERARCHICAL' versus 'ETHNICITY'

P value = 0.822 (Fisher's exact test), Q value = 1

Table S148. Clustering Approach #10: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #14: 'ETHNICITY'

nPatients	HISPANIC OR LATINO	NOT HISPANIC OR LATINO
ALL	7	343
subtype1	0	45
subtype2	3	142
subtype3	2	95
subtype4	2	61

Figure S138. Get High-res Image Clustering Approach #10: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #14: 'ETHNICITY'

Clustering Approach #11: 'MIRseq Mature CNMF subtypes'

Table S149. Description of clustering approach #11: 'MIRseq Mature CNMF subtypes'

Cluster Labels	1	2	3
Number of samples	139	175	84

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

P value = 0.00377 (logrank test), Q value = 0.55

Table S150. Clustering Approach #11: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #1: 'Time to Death'

	nPatients	nDeath	Duration Range (Median), Year
ALL	347	67	1.0 - 6443.0 (426.0)
subtype1	122	33	3.0 - 1988.0 (567.5)
subtype2	155	20	1.0 - 6443.0 (351.0)
subtype3	70	14	2.0 - 2370.0 (354.0)

Figure S139. Get High-res Image Clustering Approach #11: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #1: 'Time to Death'

'MIRseq Mature CNMF subtypes' versus 'AGE'

P value = 0.747 (Kruskal-Wallis (anova)), Q value = 1

Table S151. Clustering Approach #11: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #2: 'AGE'

	nPatients	Mean (Std.Dev)
ALL	370	65.2 (9.9)
subtype1	130	65.5 (10.6)
subtype2	166	64.9 (9.6)
subtype3	74	65.6 (9.3)

Figure S140. Get High-res Image Clustering Approach #11: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #2: 'AGE'

'MIRseq Mature CNMF subtypes' versus 'NEOPLASM.DISEASESTAGE'

P value = 0.761 (Fisher's exact test), Q value = 1

Table S152. Clustering Approach #11: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #3: 'NEOPLASM.DISEASESTAGE'

nPatients	STAGE I	STAGE IA	STAGE IB	STAGE IIA	STAGE IIB	STAGE IIIA	STAGE IIIB	STAGE IV
ALL	5	94	107	46	58	60	8	19
subtype1	2	31	33	17	18	23	4	10
subtype2	3	46	48	22	26	21	3	6
subtype3	0	17	26	7	14	16	1	3

Figure S141. Get High-res Image Clustering Approach #11: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #3: 'NEOPLASM.DISEASESTAGE'

'MIRseq Mature CNMF subtypes' versus 'PATHOLOGY.T.STAGE'

P value = 0.113 (Fisher's exact test), Q value = 1

Table S153. Clustering Approach #11: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #4: 'PATHOLOGY.T.STAGE'

nPatients	T1	T2	T3	T4
ALL	124	221	36	14
subtype1	43	73	13	10
subtype2	60	96	16	2
subtype3	21	52	7	2

Figure S142. 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 = 0.447 (Fisher's exact test), Q value = 1

Table S154. Clustering Approach #11: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #5: 'PATHOLOGY.N.STAGE'

nPatients	N0	N1	N2+N3
ALL	250	76	63
subtype1	81	32	21
subtype2	119	29	26
subtype3	50	15	16

Figure S143. 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 = 0.316 (Fisher's exact test), Q value = 1

Table S155. Clustering Approach #11: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #6: 'PATHOLOGY.M.STAGE'

nPatients	M0	M1	M1A	M1B	MX
ALL	258	12	1	4	119
subtype1	90	8	0	1	37
subtype2	114	2	1	3	55
subtype3	54	2	0	0	27

Figure S144. 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 = 0.785 (Fisher's exact test), Q value = 1

Table S156. Clustering Approach #11: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #7: 'GENDER'

nPatients	FEMALE	MALE
ALL	214	184
subtype1	73	66
subtype2	93	82
subtype3	48	36

Figure S145. Get High-res Image Clustering Approach #11: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #7: 'GENDER'

'MIRseq Mature CNMF subtypes' versus 'KARNOFSKY.PERFORMANCE.SCORE'

P value = 0.152 (Kruskal-Wallis (anova)), Q value = 1

Table S157. Clustering Approach #11: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #8: 'KARNOFSKY.PERFORMANCE.SCORE'

	nPatients	Mean (Std.Dev)
ALL	76	84.2 (21.7)
subtype1	17	75.3 (30.2)
subtype2	46	87.4 (18.4)
subtype3	13	84.6 (17.1)

Figure S146. Get High-res Image Clustering Approach #11: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #8: 'KARNOFSKY.PERFORMANCE.SCORE'

'MIRseq Mature CNMF subtypes' versus 'HISTOLOGICAL.TYPE'

P value = 0.00017 (Fisher's exact test), Q value = 0.028

Table S158. Clustering Approach #11: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #9: '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	13	73	251	5	19	1	3	2	18	1	5	7
subtype1	4	35	73	3	11	1	2	1	7	0	0	2
subtype2	9	30	109	0	7	0	0	0	10	1	5	4
subtype3	0	8	69	2	1	0	1	1	1	0	0	1

Figure S147. Get High-res Image Clustering Approach #11: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #9: 'HISTOLOGICAL.TYPE'

'MIRseq Mature CNMF subtypes' versus 'RADIATIONS.RADIATION.REGIMENINDICATION'

P value = 0.0389 (Fisher's exact test), Q value = 1

Table S159. Clustering Approach #11: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #10: 'RADIATIONS.RADIATION.REGIMENINDICATION'

nPatients	NO	YES
ALL	18	380
subtype1	9	130
subtype2	3	172
subtype3	6	78

Figure S148. Get High-res Image Clustering Approach #11: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #10: 'RADIATIONS.RADIATION.REGIMENINDICATION'

'MIRseq Mature CNMF subtypes' versus 'NUMBERPACKYEARSSMOKED'

P value = 0.0155 (Kruskal-Wallis (anova)), Q value = 1

Table S160. Clustering Approach #11: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #11: 'NUMBERPACKYEARSSMOKED'

	nPatients	Mean (Std.Dev)
ALL	270	41.9 (27.5)
subtype1	98	37.2 (27.2)
subtype2	125	44.1 (28.3)
subtype3	47	45.6 (25.0)

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

'MIRseq Mature CNMF subtypes' versus 'COMPLETENESS.OF.RESECTION'

P value = 0.41 (Fisher's exact test), Q value = 1

Table S161. Clustering Approach #11: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #12: 'COMPLETENESS.OF.RESECTION'

nPatients	R0	R1	R2	RX
ALL	264	9	1	17
subtype1	82	5	1	4
subtype2	129	2	0	10
subtype3	53	2	0	3

Figure S150. Get High-res Image Clustering Approach #11: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #12: 'COMPLETENESS.OF.RESECTION'

'MIRseq Mature CNMF subtypes' versus 'RACE'

P value = 0.986 (Fisher's exact test), Q value = 1

Table S162. Clustering Approach #11: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #13: 'RACE'

nPatients	ASIAN	BLACK OR AFRICAN AMERICAN	WHITE
ALL	4	33	311
subtype1	1	12	106
subtype2	2	15	136
subtype3	1	6	69

Figure S151. Get High-res Image Clustering Approach #11: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #13: 'RACE'

'MIRseq Mature CNMF subtypes' versus 'ETHNICITY'

P value = 0.134 (Fisher's exact test), Q value = 1

Table S163. Clustering Approach #11: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #14: 'ETHNICITY'

nPatients	HISPANIC OR LATINO	NOT HISPANIC OR LATINO
ALL	6	288
subtype1	4	84
subtype2	2	137
subtype3	0	67

Figure S152. Get High-res Image Clustering Approach #11: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #14: 'ETHNICITY'

Clustering Approach #12: 'MIRseq Mature cHierClus subtypes'

Table S164. Description of clustering approach #12: 'MIRseq Mature cHierClus subtypes'

Cluster Labels	1	2	3
Number of samples	84	230	84

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

P value = 0.183 (logrank test), Q value = 1

Table S165. Clustering Approach #12: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #1: 'Time to Death'

	nPatients	nDeath	Duration Range (Median), Year
ALL	347	67	1.0 - 6443.0 (426.0)
subtype1	76	12	1.0 - 1980.0 (332.0)
subtype2	197	37	2.0 - 6443.0 (445.0)
subtype3	74	18	2.0 - 2370.0 (488.5)

Figure S153. Get High-res Image Clustering Approach #12: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #1: 'Time to Death'

'MIRseq Mature cHierClus subtypes' versus 'AGE'

P value = 0.000105 (Kruskal-Wallis (anova)), Q value = 0.017

Table S166. Clustering Approach #12: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #2: 'AGE'

	nPatients	Mean (Std.Dev)
ALL	370	65.2 (9.9)
subtype1	79	68.1 (8.1)
subtype2	212	63.4 (10.4)
subtype3	79	67.2 (9.3)

Figure S154. Get High-res Image Clustering Approach #12: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #2: 'AGE'

'MIRseq Mature cHierClus subtypes' versus 'NEOPLASM.DISEASESTAGE'

P value = 0.757 (Fisher's exact test), Q value = 1

Table S167. Clustering Approach #12: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #3: 'NEOPLASM.DISEASESTAGE'

nPatients	STAGE I	STAGE IA	STAGE IB	STAGE IIA	STAGE IIB	STAGE IIIA	STAGE IIIB	STAGE IV
ALL	5	94	107	46	58	60	8	19
subtype1	1	26	18	9	14	9	2	4
subtype2	3	45	65	29	36	37	4	11
subtype3	1	23	24	8	8	14	2	4

Figure S155. Get High-res Image Clustering Approach #12: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #3: 'NEOPLASM.DISEASESTAGE'

'MIRseq Mature cHierClus subtypes' versus 'PATHOLOGY.T.STAGE'

P value = 0.0225 (Fisher's exact test), Q value = 1

Table S168. Clustering Approach #12: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #4: 'PATHOLOGY.T.STAGE'

nPatients	T1	T2	T3	T4
ALL	124	221	36	14
subtype1	32	37	11	4
subtype2	62	139	22	5
subtype3	30	45	3	5

Figure S156. 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 = 0.285 (Fisher's exact test), Q value = 1

Table S169. Clustering Approach #12: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #5: 'PATHOLOGY.N.STAGE'

nPatients	N0	N1	N2+N3
ALL	250	76	63
subtype1	59	13	8
subtype2	141	44	42
subtype3	50	19	13

Figure S157. 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 = 0.852 (Fisher's exact test), Q value = 1

Table S170. Clustering Approach #12: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #6: 'PATHOLOGY.M.STAGE'

nPatients	M0	M1	M1A	M1B	MX
ALL	258	12	1	4	119
subtype1	54	3	0	1	24
subtype2	154	7	1	3	64
subtype3	50	2	0	0	31

Figure S158. 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 = 0.00042 (Fisher's exact test), Q value = 0.067

Table S171. Clustering Approach #12: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #7: 'GENDER'

nPatients	FEMALE	MALE
ALL	214	184
subtype1	42	42
subtype2	111	119
subtype3	61	23

Figure S159. Get High-res Image Clustering Approach #12: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #7: 'GENDER'

'MIRseq Mature cHierClus subtypes' versus 'KARNOFSKY.PERFORMANCE.SCORE'

P value = 0.682 (Kruskal-Wallis (anova)), Q value = 1

Table S172. Clustering Approach #12: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #8: 'KARNOFSKY.PERFORMANCE.SCORE'

	nPatients	Mean (Std.Dev)
ALL	76	84.2 (21.7)
subtype1	12	90.8 (7.9)
subtype2	50	83.6 (21.5)
subtype3	14	80.7 (29.2)

Figure S160. Get High-res Image Clustering Approach #12: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #8: 'KARNOFSKY.PERFORMANCE.SCORE'

'MIRseq Mature cHierClus subtypes' versus 'HISTOLOGICAL.TYPE'

P value = 0.00214 (Fisher's exact test), Q value = 0.33

Table S173. Clustering Approach #12: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #9: '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	13	73	251	5	19	1	3	2	18	1	5	7
subtype1	4	18	38	3	6	0	0	2	7	1	1	4
subtype2	6	40	159	0	8	1	1	0	8	0	4	3
subtype3	3	15	54	2	5	0	2	0	3	0	0	0

Figure S161. Get High-res Image Clustering Approach #12: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #9: 'HISTOLOGICAL.TYPE'

'MIRseq Mature cHierClus subtypes' versus 'RADIATIONS.RADIATION.REGIMENINDICATION'

P value = 0.0897 (Fisher's exact test), Q value = 1

Table S174. Clustering Approach #12: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #10: 'RADIATIONS.RADIATION.REGIMENINDICATION'

nPatients	NO	YES
ALL	18	380
subtype1	1	83
subtype2	10	220
subtype3	7	77

Figure S162. Get High-res Image Clustering Approach #12: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #10: 'RADIATIONS.RADIATION.REGIMENINDICATION'

'MIRseq Mature cHierClus subtypes' versus 'NUMBERPACKYEARSSMOKED'

P value = 0.287 (Kruskal-Wallis (anova)), Q value = 1

Table S175. Clustering Approach #12: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #11: 'NUMBERPACKYEARSSMOKED'

	nPatients	Mean (Std.Dev)
ALL	270	41.9 (27.5)
subtype1	52	39.6 (28.1)
subtype2	166	43.7 (28.3)
subtype3	52	38.2 (24.2)

Figure S163. Get High-res Image Clustering Approach #12: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #11: 'NUMBERPACKYEARSSMOKED'

'MIRseq Mature cHierClus subtypes' versus 'COMPLETENESS.OF.RESECTION'

P value = 0.254 (Fisher's exact test), Q value = 1

Table S176. Clustering Approach #12: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #12: 'COMPLETENESS.OF.RESECTION'

nPatients	R0	R1	R2	RX
ALL	264	9	1	17
subtype1	61	0	0	6
subtype2	153	5	1	8
subtype3	50	4	0	3

Figure S164. Get High-res Image Clustering Approach #12: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #12: 'COMPLETENESS.OF.RESECTION'

'MIRseq Mature cHierClus subtypes' versus 'RACE'

P value = 0.174 (Fisher's exact test), Q value = 1

Table S177. Clustering Approach #12: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #13: 'RACE'

nPatients	ASIAN	BLACK OR AFRICAN AMERICAN	WHITE
ALL	4	33	311
subtype1	1	4	68
subtype2	1	24	174
subtype3	2	5	69

Figure S165. Get High-res Image Clustering Approach #12: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #13: 'RACE'

'MIRseq Mature cHierClus subtypes' versus 'ETHNICITY'

P value = 0.467 (Fisher's exact test), Q value = 1

Table S178. Clustering Approach #12: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #14: 'ETHNICITY'

nPatients	HISPANIC OR LATINO	NOT HISPANIC OR LATINO
ALL	6	288
subtype1	0	64
subtype2	5	165
subtype3	1	59

Figure S166. Get High-res Image Clustering Approach #12: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #14: 'ETHNICITY'

Methods & Data

Input

Cluster data file = LUAD-TP.mergedcluster.txt
Clinical data file = LUAD-TP.merged_data.txt
Number of patients = 480
Number of clustering approaches = 12
Number of selected clinical features = 14
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