Correlation between aggregated molecular cancer subtypes and selected clinical features

Lung Adenocarcinoma (Primary solid tumor)

23 May 2013 | analyses__2013_05_23

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 (2013): Correlation between aggregated molecular cancer subtypes and selected clinical features. Broad Institute of MIT and Harvard. doi:10.7908/C1NV9G9T

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 13 clinical features across 393 patients, 6 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 correlate to 'AGE'.
4 subtypes identified in current cancer cohort by 'METHLYATION CNMF'. These subtypes do not correlate to any clinical features.
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 4 subtypes that do not correlate to any clinical features.
CNMF clustering analysis on sequencing-based mRNA expression data identified 9 subtypes that correlate to 'AGE', 'GENDER', and 'HISTOLOGICAL.TYPE'.
Consensus hierarchical clustering analysis on sequencing-based mRNA expression data identified 3 subtypes that correlate to 'GENDER'.
3 subtypes identified in current cancer cohort by 'MIRSEQ CNMF'. These subtypes do not correlate to any clinical features.
3 subtypes identified in current cancer cohort by 'MIRSEQ CHIERARCHICAL'. These subtypes correlate to 'HISTOLOGICAL.TYPE'.
3 subtypes identified in current cancer cohort by 'MIRseq Mature CNMF subtypes'. These subtypes do not correlate to any clinical features.
3 subtypes identified in current cancer cohort by 'MIRseq Mature cHierClus subtypes'. These subtypes do not correlate to any clinical features.

Results

Overview of the results

Table 1. Get Full Table Overview of the association between subtypes identified by 12 different clustering approaches and 13 clinical features. Shown in the table are P values (Q values). Thresholded by P value < 0.05 and Q value < 0.25, 6 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	0.862 (1.00)	0.958 (1.00)	0.822 (1.00)	0.0572 (1.00)	0.14 (1.00)	0.157 (1.00)	0.0475 (1.00)	0.033 (1.00)	0.364 (1.00)	0.83 (1.00)	0.119 (1.00)	0.616 (1.00)
AGE	ANOVA	0.477 (1.00)	0.557 (1.00)	0.000435 (0.06)	0.0609 (1.00)	0.0292 (1.00)	0.0231 (1.00)	0.00121 (0.166)	0.0242 (1.00)	0.173 (1.00)	0.0544 (1.00)	0.109 (1.00)	0.0829 (1.00)
GENDER	Fisher's exact test	0.272 (1.00)	0.383 (1.00)	0.0463 (1.00)	0.0177 (1.00)	0.307 (1.00)	0.159 (1.00)	3.08e-08 (4.37e-06)	0.000305 (0.0424)	0.774 (1.00)	0.00639 (0.862)	0.107 (1.00)	0.0196 (1.00)
KARNOFSKY PERFORMANCE SCORE	ANOVA			0.408 (1.00)	0.77 (1.00)	0.0383 (1.00)	0.54 (1.00)	0.934 (1.00)	0.238 (1.00)	0.823 (1.00)	0.823 (1.00)	0.892 (1.00)	0.491 (1.00)
HISTOLOGICAL TYPE	Chi-square test	0.3 (1.00)	0.274 (1.00)	0.117 (1.00)	0.0611 (1.00)	0.101 (1.00)	0.00532 (0.723)	0.000278 (0.039)	0.0129 (1.00)	0.0283 (1.00)	0.000223 (0.0315)	0.0256 (1.00)	0.0216 (1.00)
RADIATIONS RADIATION REGIMENINDICATION	Fisher's exact test	1 (1.00)	1 (1.00)	0.342 (1.00)	0.219 (1.00)	0.826 (1.00)	0.208 (1.00)	0.525 (1.00)	0.38 (1.00)	0.73 (1.00)	1 (1.00)	0.942 (1.00)	1 (1.00)
NUMBERPACKYEARSSMOKED	ANOVA	0.448 (1.00)	0.357 (1.00)	0.288 (1.00)	0.0309 (1.00)	0.396 (1.00)	0.24 (1.00)	0.052 (1.00)	0.038 (1.00)	0.212 (1.00)	0.279 (1.00)	0.239 (1.00)	0.177 (1.00)
YEAROFTOBACCOSMOKINGONSET	ANOVA	0.616 (1.00)	0.68 (1.00)	0.144 (1.00)	0.637 (1.00)	0.0368 (1.00)	0.0257 (1.00)	0.00787 (1.00)	0.0853 (1.00)	0.0519 (1.00)	0.0223 (1.00)	0.027 (1.00)	0.0498 (1.00)
DISTANT METASTASIS	Chi-square test	0.504 (1.00)	1 (1.00)	0.669 (1.00)	0.553 (1.00)	0.668 (1.00)	0.841 (1.00)	0.313 (1.00)	0.826 (1.00)	0.571 (1.00)	0.989 (1.00)	0.413 (1.00)	0.683 (1.00)
LYMPH NODE METASTASIS	Chi-square test	0.675 (1.00)	0.675 (1.00)	0.321 (1.00)	0.809 (1.00)	0.42 (1.00)	0.541 (1.00)	0.705 (1.00)	0.208 (1.00)	0.77 (1.00)	0.343 (1.00)	0.519 (1.00)	0.0757 (1.00)
COMPLETENESS OF RESECTION	Chi-square test	0.188 (1.00)	0.58 (1.00)	0.944 (1.00)	0.623 (1.00)	0.119 (1.00)	0.502 (1.00)	0.887 (1.00)	0.55 (1.00)	0.565 (1.00)	0.664 (1.00)	0.672 (1.00)	0.497 (1.00)
TUMOR STAGECODE	ANOVA
NEOPLASM DISEASESTAGE	Chi-square test	0.127 (1.00)	0.127 (1.00)	0.645 (1.00)	0.662 (1.00)	0.846 (1.00)	0.972 (1.00)	0.835 (1.00)	0.0703 (1.00)	0.172 (1.00)	0.162 (1.00)	0.582 (1.00)	0.645 (1.00)

Clustering Approach #1: 'mRNA CNMF subtypes'

Table S1. Get Full Table 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 = 0.862 (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), Month
ALL	31	4	0.5 - 56.8 (14.0)
subtype1	4	0	6.0 - 48.6 (9.7)
subtype2	9	1	4.0 - 56.8 (8.3)
subtype3	12	1	0.5 - 37.0 (12.9)
subtype4	6	2	20.0 - 45.2 (30.9)

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 = 0.477 (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 'GENDER'

P value = 0.272 (Fisher's exact test), Q value = 1

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

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

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

'mRNA CNMF subtypes' versus 'HISTOLOGICAL.TYPE'

P value = 0.3 (Chi-square test), Q value = 1

Table S5. Clustering Approach #1: 'mRNA CNMF subtypes' versus Clinical Feature #5: '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 S4. Get High-res Image Clustering Approach #1: 'mRNA CNMF subtypes' versus Clinical Feature #5: 'HISTOLOGICAL.TYPE'

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

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

Table S6. Clustering Approach #1: 'mRNA CNMF subtypes' versus Clinical Feature #6: 'RADIATIONS.RADIATION.REGIMENINDICATION'

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

Figure S5. Get High-res Image Clustering Approach #1: 'mRNA CNMF subtypes' versus Clinical Feature #6: 'RADIATIONS.RADIATION.REGIMENINDICATION'

'mRNA CNMF subtypes' versus 'NUMBERPACKYEARSSMOKED'

P value = 0.448 (ANOVA), Q value = 1

Table S7. Clustering Approach #1: 'mRNA CNMF subtypes' versus Clinical Feature #7: '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 S6. Get High-res Image Clustering Approach #1: 'mRNA CNMF subtypes' versus Clinical Feature #7: 'NUMBERPACKYEARSSMOKED'

'mRNA CNMF subtypes' versus 'YEAROFTOBACCOSMOKINGONSET'

P value = 0.616 (ANOVA), Q value = 1

Table S8. Clustering Approach #1: 'mRNA CNMF subtypes' versus Clinical Feature #8: 'YEAROFTOBACCOSMOKINGONSET'

	nPatients	Mean (Std.Dev)
ALL	19	1968.5 (11.4)
subtype1	2	1977.0 (18.4)
subtype2	6	1971.2 (14.2)
subtype3	6	1965.8 (8.2)
subtype4	5	1965.2 (9.8)

Figure S7. Get High-res Image Clustering Approach #1: 'mRNA CNMF subtypes' versus Clinical Feature #8: 'YEAROFTOBACCOSMOKINGONSET'

'mRNA CNMF subtypes' versus 'DISTANT.METASTASIS'

P value = 0.504 (Fisher's exact test), Q value = 1

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

nPatients	M0	M1
ALL	30	2
subtype1	4	1
subtype2	9	0
subtype3	11	1
subtype4	6	0

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

'mRNA CNMF subtypes' versus 'LYMPH.NODE.METASTASIS'

P value = 0.675 (Chi-square test), Q value = 1

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

nPatients	N0	N1	N2	NX
ALL	23	4	4	1
subtype1	3	1	1	0
subtype2	8	1	0	0
subtype3	9	1	1	1
subtype4	3	1	2	0

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

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

P value = 0.188 (Chi-square test), Q value = 1

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

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

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

'mRNA CNMF subtypes' versus 'NEOPLASM.DISEASESTAGE'

P value = 0.127 (Chi-square test), Q value = 1

Table S12. Clustering Approach #1: 'mRNA CNMF subtypes' versus Clinical Feature #13: '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 S11. Get High-res Image Clustering Approach #1: 'mRNA CNMF subtypes' versus Clinical Feature #13: 'NEOPLASM.DISEASESTAGE'

Clustering Approach #2: 'mRNA cHierClus subtypes'

Table S13. Get Full Table Description of clustering approach #2: 'mRNA cHierClus subtypes'

Cluster Labels	1	2	3
Number of samples	7	13	12

'mRNA cHierClus subtypes' versus 'Time to Death'

P value = 0.958 (logrank test), Q value = 1

Table S14. Clustering Approach #2: 'mRNA cHierClus subtypes' versus Clinical Feature #1: 'Time to Death'

	nPatients	nDeath	Duration Range (Median), Month
ALL	31	4	0.5 - 56.8 (14.0)
subtype1	7	2	20.0 - 48.6 (38.7)
subtype2	13	1	0.5 - 37.0 (13.2)
subtype3	11	1	4.0 - 56.8 (8.1)

Figure S12. Get High-res Image Clustering Approach #2: 'mRNA cHierClus subtypes' versus Clinical Feature #1: 'Time to Death'

'mRNA cHierClus subtypes' versus 'AGE'

P value = 0.557 (ANOVA), Q value = 1

Table S15. Clustering Approach #2: 'mRNA cHierClus subtypes' versus Clinical Feature #2: 'AGE'

	nPatients	Mean (Std.Dev)
ALL	30	65.7 (10.8)
subtype1	5	69.4 (9.0)
subtype2	13	66.5 (10.9)
subtype3	12	63.3 (11.6)

Figure S13. Get High-res Image Clustering Approach #2: 'mRNA cHierClus subtypes' versus Clinical Feature #2: 'AGE'

'mRNA cHierClus subtypes' versus 'GENDER'

P value = 0.383 (Fisher's exact test), Q value = 1

Table S16. Clustering Approach #2: 'mRNA cHierClus subtypes' versus Clinical Feature #3: 'GENDER'

nPatients	FEMALE	MALE
ALL	18	14
subtype1	4	3
subtype2	9	4
subtype3	5	7

Figure S14. Get High-res Image Clustering Approach #2: 'mRNA cHierClus subtypes' versus Clinical Feature #3: 'GENDER'

'mRNA cHierClus subtypes' versus 'HISTOLOGICAL.TYPE'

P value = 0.274 (Chi-square test), Q value = 1

Table S17. Clustering Approach #2: 'mRNA cHierClus subtypes' versus Clinical Feature #5: 'HISTOLOGICAL.TYPE'

nPatients	LUNG ADENOCARCINOMA MIXED SUBTYPE	LUNG ADENOCARCINOMA- NOT OTHERWISE SPECIFIED (NOS)	LUNG CLEAR CELL ADENOCARCINOMA
ALL	1	30	1
subtype1	0	6	1
subtype2	1	12	0
subtype3	0	12	0

Figure S15. Get High-res Image Clustering Approach #2: 'mRNA cHierClus subtypes' versus Clinical Feature #5: 'HISTOLOGICAL.TYPE'

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

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

Table S18. Clustering Approach #2: 'mRNA cHierClus subtypes' versus Clinical Feature #6: 'RADIATIONS.RADIATION.REGIMENINDICATION'

nPatients	NO	YES
ALL	1	31
subtype1	0	7
subtype2	1	12
subtype3	0	12

Figure S16. Get High-res Image Clustering Approach #2: 'mRNA cHierClus subtypes' versus Clinical Feature #6: 'RADIATIONS.RADIATION.REGIMENINDICATION'

'mRNA cHierClus subtypes' versus 'NUMBERPACKYEARSSMOKED'

P value = 0.357 (ANOVA), Q value = 1

Table S19. Clustering Approach #2: 'mRNA cHierClus subtypes' versus Clinical Feature #7: 'NUMBERPACKYEARSSMOKED'

	nPatients	Mean (Std.Dev)
ALL	20	41.1 (15.0)
subtype1	3	40.0 (17.3)
subtype2	7	35.0 (13.1)
subtype3	10	45.8 (15.4)

Figure S17. Get High-res Image Clustering Approach #2: 'mRNA cHierClus subtypes' versus Clinical Feature #7: 'NUMBERPACKYEARSSMOKED'

'mRNA cHierClus subtypes' versus 'YEAROFTOBACCOSMOKINGONSET'

P value = 0.68 (ANOVA), Q value = 1

Table S20. Clustering Approach #2: 'mRNA cHierClus subtypes' versus Clinical Feature #8: 'YEAROFTOBACCOSMOKINGONSET'

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

Figure S18. Get High-res Image Clustering Approach #2: 'mRNA cHierClus subtypes' versus Clinical Feature #8: 'YEAROFTOBACCOSMOKINGONSET'

'mRNA cHierClus subtypes' versus 'DISTANT.METASTASIS'

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

Table S21. Clustering Approach #2: 'mRNA cHierClus subtypes' versus Clinical Feature #9: 'DISTANT.METASTASIS'

nPatients	M0	M1
ALL	30	2
subtype1	7	0
subtype2	12	1
subtype3	11	1

Figure S19. Get High-res Image Clustering Approach #2: 'mRNA cHierClus subtypes' versus Clinical Feature #9: 'DISTANT.METASTASIS'

'mRNA cHierClus subtypes' versus 'LYMPH.NODE.METASTASIS'

P value = 0.675 (Chi-square test), Q value = 1

Table S22. Clustering Approach #2: 'mRNA cHierClus subtypes' versus Clinical Feature #10: 'LYMPH.NODE.METASTASIS'

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

Figure S20. Get High-res Image Clustering Approach #2: 'mRNA cHierClus subtypes' versus Clinical Feature #10: 'LYMPH.NODE.METASTASIS'

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

P value = 0.58 (Chi-square test), Q value = 1

Table S23. Clustering Approach #2: 'mRNA cHierClus subtypes' versus Clinical Feature #11: 'COMPLETENESS.OF.RESECTION'

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

Figure S21. Get High-res Image Clustering Approach #2: 'mRNA cHierClus subtypes' versus Clinical Feature #11: 'COMPLETENESS.OF.RESECTION'

'mRNA cHierClus subtypes' versus 'NEOPLASM.DISEASESTAGE'

P value = 0.127 (Chi-square test), Q value = 1

Table S24. Clustering Approach #2: 'mRNA cHierClus subtypes' versus Clinical Feature #13: '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	1	1	2	0
subtype2	3	8	0	1	0	1
subtype3	6	3	0	1	1	1

Figure S22. Get High-res Image Clustering Approach #2: 'mRNA cHierClus subtypes' versus Clinical Feature #13: 'NEOPLASM.DISEASESTAGE'

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

Table S25. Get Full Table Description of clustering approach #3: 'Copy Number Ratio CNMF subtypes'

Cluster Labels	1	2	3
Number of samples	151	159	79

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

P value = 0.822 (logrank test), Q value = 1

Table S26. Clustering Approach #3: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #1: 'Time to Death'

	nPatients	nDeath	Duration Range (Median), Month
ALL	353	87	0.0 - 224.0 (8.4)
subtype1	133	35	0.0 - 224.0 (9.4)
subtype2	146	33	0.0 - 120.8 (8.1)
subtype3	74	19	0.1 - 97.7 (7.9)

Figure S23. 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 = 0.000435 (ANOVA), Q value = 0.06

Table S27. Clustering Approach #3: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #2: 'AGE'

	nPatients	Mean (Std.Dev)
ALL	358	65.2 (9.8)
subtype1	137	64.0 (10.1)
subtype2	147	67.6 (9.0)
subtype3	74	62.8 (9.9)

Figure S24. Get High-res Image Clustering Approach #3: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #2: 'AGE'

'Copy Number Ratio CNMF subtypes' versus 'GENDER'

P value = 0.0463 (Fisher's exact test), Q value = 1

Table S28. Clustering Approach #3: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #3: 'GENDER'

nPatients	FEMALE	MALE
ALL	211	178
subtype1	91	60
subtype2	86	73
subtype3	34	45

Figure S25. Get High-res Image Clustering Approach #3: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #3: 'GENDER'

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

P value = 0.408 (ANOVA), Q value = 1

Table S29. Clustering Approach #3: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #4: 'KARNOFSKY.PERFORMANCE.SCORE'

	nPatients	Mean (Std.Dev)
ALL	29	75.9 (32.4)
subtype1	14	69.3 (39.1)
subtype2	8	88.8 (8.3)
subtype3	7	74.3 (34.1)

Figure S26. Get High-res Image Clustering Approach #3: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #4: 'KARNOFSKY.PERFORMANCE.SCORE'

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

P value = 0.117 (Chi-square test), Q value = 1

Table S30. Clustering Approach #3: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #5: '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 SOLID PATTERN PREDOMINANT ADENOCARCINOMA	MUCINOUS (COLLOID) CARCINOMA
ALL	11	79	243	4	17	2	3	2	18	3	7
subtype1	6	25	98	2	10	1	2	0	6	1	0
subtype2	3	39	89	2	6	1	1	2	10	0	6
subtype3	2	15	56	0	1	0	0	0	2	2	1

Figure S27. Get High-res Image Clustering Approach #3: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #5: 'HISTOLOGICAL.TYPE'

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

P value = 0.342 (Fisher's exact test), Q value = 1

Table S31. Clustering Approach #3: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #6: 'RADIATIONS.RADIATION.REGIMENINDICATION'

nPatients	NO	YES
ALL	18	371
subtype1	5	146
subtype2	7	152
subtype3	6	73

Figure S28. Get High-res Image Clustering Approach #3: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #6: 'RADIATIONS.RADIATION.REGIMENINDICATION'

'Copy Number Ratio CNMF subtypes' versus 'NUMBERPACKYEARSSMOKED'

P value = 0.288 (ANOVA), Q value = 1

Table S32. Clustering Approach #3: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #7: 'NUMBERPACKYEARSSMOKED'

	nPatients	Mean (Std.Dev)
ALL	272	41.6 (26.9)
subtype1	97	44.4 (25.2)
subtype2	111	38.6 (27.5)
subtype3	64	42.7 (28.2)

Figure S29. Get High-res Image Clustering Approach #3: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #7: 'NUMBERPACKYEARSSMOKED'

'Copy Number Ratio CNMF subtypes' versus 'YEAROFTOBACCOSMOKINGONSET'

P value = 0.144 (ANOVA), Q value = 1

Table S33. Clustering Approach #3: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #8: 'YEAROFTOBACCOSMOKINGONSET'

	nPatients	Mean (Std.Dev)
ALL	212	1965.2 (12.5)
subtype1	76	1964.9 (13.0)
subtype2	85	1963.7 (12.5)
subtype3	51	1968.1 (11.7)

Figure S30. Get High-res Image Clustering Approach #3: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #8: 'YEAROFTOBACCOSMOKINGONSET'

'Copy Number Ratio CNMF subtypes' versus 'DISTANT.METASTASIS'

P value = 0.669 (Chi-square test), Q value = 1

Table S34. Clustering Approach #3: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #9: 'DISTANT.METASTASIS'

nPatients	M0	M1	M1A	M1B	MX
ALL	262	17	1	3	102
subtype1	100	8	1	0	40
subtype2	109	4	0	2	42
subtype3	53	5	0	1	20

Figure S31. Get High-res Image Clustering Approach #3: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #9: 'DISTANT.METASTASIS'

'Copy Number Ratio CNMF subtypes' versus 'LYMPH.NODE.METASTASIS'

P value = 0.321 (Chi-square test), Q value = 1

Table S35. Clustering Approach #3: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #10: 'LYMPH.NODE.METASTASIS'

nPatients	N0	N1	N2	N3	NX
ALL	248	72	58	2	7
subtype1	94	29	24	2	2
subtype2	103	33	19	0	2
subtype3	51	10	15	0	3

Figure S32. Get High-res Image Clustering Approach #3: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #10: 'LYMPH.NODE.METASTASIS'

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

P value = 0.944 (Chi-square test), Q value = 1

Table S36. Clustering Approach #3: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #11: 'COMPLETENESS.OF.RESECTION'

nPatients	R0	R1	R2	RX
ALL	243	9	4	14
subtype1	95	4	1	7
subtype2	99	4	2	4
subtype3	49	1	1	3

Figure S33. Get High-res Image Clustering Approach #3: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #11: 'COMPLETENESS.OF.RESECTION'

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

P value = 0.645 (Chi-square test), Q value = 1

Table S37. Clustering Approach #3: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #13: 'NEOPLASM.DISEASESTAGE'

nPatients	STAGE I	STAGE IA	STAGE IB	STAGE IIA	STAGE IIB	STAGE IIIA	STAGE IIIB	STAGE IV
ALL	3	97	113	32	53	57	11	21
subtype1	2	31	47	14	21	22	5	9
subtype2	0	46	46	13	24	18	3	7
subtype3	1	20	20	5	8	17	3	5

Figure S34. Get High-res Image Clustering Approach #3: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #13: 'NEOPLASM.DISEASESTAGE'

Clustering Approach #4: 'METHLYATION CNMF'

Table S38. Get Full Table Description of clustering approach #4: 'METHLYATION CNMF'

Cluster Labels	1	2	3	4
Number of samples	68	91	82	82

'METHLYATION CNMF' versus 'Time to Death'

P value = 0.0572 (logrank test), Q value = 1

Table S39. Clustering Approach #4: 'METHLYATION CNMF' versus Clinical Feature #1: 'Time to Death'

	nPatients	nDeath	Duration Range (Median), Month
ALL	290	66	0.0 - 224.0 (6.6)
subtype1	60	11	0.0 - 224.0 (7.5)
subtype2	81	24	0.1 - 88.1 (8.4)
subtype3	74	14	0.0 - 77.9 (5.6)
subtype4	75	17	0.0 - 71.5 (5.6)

Figure S35. Get High-res Image Clustering Approach #4: 'METHLYATION CNMF' versus Clinical Feature #1: 'Time to Death'

'METHLYATION CNMF' versus 'AGE'

P value = 0.0609 (ANOVA), Q value = 1

Table S40. Clustering Approach #4: 'METHLYATION CNMF' versus Clinical Feature #2: 'AGE'

	nPatients	Mean (Std.Dev)
ALL	295	65.1 (9.9)
subtype1	60	67.2 (8.9)
subtype2	84	62.8 (10.0)
subtype3	77	65.4 (10.0)
subtype4	74	65.8 (10.3)

Figure S36. Get High-res Image Clustering Approach #4: 'METHLYATION CNMF' versus Clinical Feature #2: 'AGE'

'METHLYATION CNMF' versus 'GENDER'

P value = 0.0177 (Fisher's exact test), Q value = 1

Table S41. Clustering Approach #4: 'METHLYATION CNMF' versus Clinical Feature #3: 'GENDER'

nPatients	FEMALE	MALE
ALL	175	148
subtype1	42	26
subtype2	38	53
subtype3	43	39
subtype4	52	30

Figure S37. Get High-res Image Clustering Approach #4: 'METHLYATION CNMF' versus Clinical Feature #3: 'GENDER'

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

P value = 0.77 (ANOVA), Q value = 1

Table S42. Clustering Approach #4: 'METHLYATION CNMF' versus Clinical Feature #4: 'KARNOFSKY.PERFORMANCE.SCORE'

	nPatients	Mean (Std.Dev)
ALL	22	74.5 (31.9)
subtype1	7	80.0 (35.6)
subtype2	5	68.0 (38.3)
subtype3	7	80.0 (12.9)
subtype4	3	60.0 (52.9)

Figure S38. Get High-res Image Clustering Approach #4: 'METHLYATION CNMF' versus Clinical Feature #4: 'KARNOFSKY.PERFORMANCE.SCORE'

'METHLYATION CNMF' versus 'HISTOLOGICAL.TYPE'

P value = 0.0611 (Chi-square test), Q value = 1

Table S43. Clustering Approach #4: 'METHLYATION CNMF' versus Clinical Feature #5: '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 SOLID PATTERN PREDOMINANT ADENOCARCINOMA	MUCINOUS (COLLOID) CARCINOMA
ALL	11	64	195	4	17	1	2	2	17	3	7
subtype1	5	14	31	2	8	0	1	2	4	0	1
subtype2	5	18	59	0	2	0	0	0	4	1	2
subtype3	0	21	50	1	3	0	1	0	5	0	1
subtype4	1	11	55	1	4	1	0	0	4	2	3

Figure S39. Get High-res Image Clustering Approach #4: 'METHLYATION CNMF' versus Clinical Feature #5: 'HISTOLOGICAL.TYPE'

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

P value = 0.219 (Fisher's exact test), Q value = 1

Table S44. Clustering Approach #4: 'METHLYATION CNMF' versus Clinical Feature #6: 'RADIATIONS.RADIATION.REGIMENINDICATION'

nPatients	NO	YES
ALL	15	308
subtype1	1	67
subtype2	6	85
subtype3	2	80
subtype4	6	76

Figure S40. Get High-res Image Clustering Approach #4: 'METHLYATION CNMF' versus Clinical Feature #6: 'RADIATIONS.RADIATION.REGIMENINDICATION'

'METHLYATION CNMF' versus 'NUMBERPACKYEARSSMOKED'

P value = 0.0309 (ANOVA), Q value = 1

Table S45. Clustering Approach #4: 'METHLYATION CNMF' versus Clinical Feature #7: 'NUMBERPACKYEARSSMOKED'

	nPatients	Mean (Std.Dev)
ALL	224	40.6 (26.9)
subtype1	43	34.9 (21.6)
subtype2	71	48.2 (32.0)
subtype3	58	38.6 (25.8)
subtype4	52	37.2 (22.6)

Figure S41. Get High-res Image Clustering Approach #4: 'METHLYATION CNMF' versus Clinical Feature #7: 'NUMBERPACKYEARSSMOKED'

'METHLYATION CNMF' versus 'YEAROFTOBACCOSMOKINGONSET'

P value = 0.637 (ANOVA), Q value = 1

Table S46. Clustering Approach #4: 'METHLYATION CNMF' versus Clinical Feature #8: 'YEAROFTOBACCOSMOKINGONSET'

	nPatients	Mean (Std.Dev)
ALL	182	1965.2 (12.3)
subtype1	34	1963.2 (11.9)
subtype2	62	1966.5 (13.8)
subtype3	49	1964.7 (11.8)
subtype4	37	1965.4 (10.6)

Figure S42. Get High-res Image Clustering Approach #4: 'METHLYATION CNMF' versus Clinical Feature #8: 'YEAROFTOBACCOSMOKINGONSET'

'METHLYATION CNMF' versus 'DISTANT.METASTASIS'

P value = 0.553 (Chi-square test), Q value = 1

Table S47. Clustering Approach #4: 'METHLYATION CNMF' versus Clinical Feature #9: 'DISTANT.METASTASIS'

nPatients	M0	M1	M1A	M1B	MX
ALL	200	11	1	3	104
subtype1	41	1	1	1	22
subtype2	60	4	0	2	24
subtype3	49	4	0	0	28
subtype4	50	2	0	0	30

Figure S43. Get High-res Image Clustering Approach #4: 'METHLYATION CNMF' versus Clinical Feature #9: 'DISTANT.METASTASIS'

'METHLYATION CNMF' versus 'LYMPH.NODE.METASTASIS'

P value = 0.809 (Chi-square test), Q value = 1

Table S48. Clustering Approach #4: 'METHLYATION CNMF' versus Clinical Feature #10: 'LYMPH.NODE.METASTASIS'

nPatients	N0	N1	N2	N3	NX
ALL	207	58	49	1	6
subtype1	46	12	7	0	1
subtype2	60	13	16	1	1
subtype3	50	18	13	0	1
subtype4	51	15	13	0	3

Figure S44. Get High-res Image Clustering Approach #4: 'METHLYATION CNMF' versus Clinical Feature #10: 'LYMPH.NODE.METASTASIS'

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

P value = 0.623 (Chi-square test), Q value = 1

Table S49. Clustering Approach #4: 'METHLYATION CNMF' versus Clinical Feature #11: 'COMPLETENESS.OF.RESECTION'

nPatients	R0	R1	R2	RX
ALL	186	7	1	12
subtype1	34	0	0	2
subtype2	58	2	0	3
subtype3	52	4	0	4
subtype4	42	1	1	3

Figure S45. Get High-res Image Clustering Approach #4: 'METHLYATION CNMF' versus Clinical Feature #11: 'COMPLETENESS.OF.RESECTION'

'METHLYATION CNMF' versus 'NEOPLASM.DISEASESTAGE'

P value = 0.662 (Chi-square test), Q value = 1

Table S50. Clustering Approach #4: 'METHLYATION CNMF' versus Clinical Feature #13: 'NEOPLASM.DISEASESTAGE'

nPatients	STAGE I	STAGE IA	STAGE IB	STAGE IIA	STAGE IIB	STAGE IIIA	STAGE IIIB	STAGE IV
ALL	3	81	92	29	42	49	9	16
subtype1	0	23	18	5	10	7	0	3
subtype2	2	19	24	9	12	16	4	5
subtype3	1	13	28	9	9	14	3	5
subtype4	0	26	22	6	11	12	2	3

Figure S46. Get High-res Image Clustering Approach #4: 'METHLYATION CNMF' versus Clinical Feature #13: 'NEOPLASM.DISEASESTAGE'

Clustering Approach #5: 'RPPA CNMF subtypes'

Table S51. Get Full Table Description of clustering approach #5: 'RPPA CNMF subtypes'

Cluster Labels	1	2	3
Number of samples	86	75	76

'RPPA CNMF subtypes' versus 'Time to Death'

P value = 0.14 (logrank test), Q value = 1

Table S52. Clustering Approach #5: 'RPPA CNMF subtypes' versus Clinical Feature #1: 'Time to Death'

	nPatients	nDeath	Duration Range (Median), Month
ALL	215	68	0.0 - 224.0 (12.3)
subtype1	72	25	0.0 - 163.1 (12.1)
subtype2	71	18	0.1 - 224.0 (13.7)
subtype3	72	25	0.0 - 97.7 (11.0)

Figure S47. Get High-res Image Clustering Approach #5: 'RPPA CNMF subtypes' versus Clinical Feature #1: 'Time to Death'

'RPPA CNMF subtypes' versus 'AGE'

P value = 0.0292 (ANOVA), Q value = 1

Table S53. Clustering Approach #5: 'RPPA CNMF subtypes' versus Clinical Feature #2: 'AGE'

	nPatients	Mean (Std.Dev)
ALL	216	64.8 (9.8)
subtype1	75	64.1 (10.1)
subtype2	71	67.3 (8.9)
subtype3	70	63.0 (10.1)

Figure S48. Get High-res Image Clustering Approach #5: 'RPPA CNMF subtypes' versus Clinical Feature #2: 'AGE'

'RPPA CNMF subtypes' versus 'GENDER'

P value = 0.307 (Fisher's exact test), Q value = 1

Table S54. Clustering Approach #5: 'RPPA CNMF subtypes' versus Clinical Feature #3: 'GENDER'

nPatients	FEMALE	MALE
ALL	131	106
subtype1	53	33
subtype2	40	35
subtype3	38	38

Figure S49. Get High-res Image Clustering Approach #5: 'RPPA CNMF subtypes' versus Clinical Feature #3: 'GENDER'

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

P value = 0.0383 (ANOVA), Q value = 1

Table S55. Clustering Approach #5: 'RPPA CNMF subtypes' versus Clinical Feature #4: 'KARNOFSKY.PERFORMANCE.SCORE'

	nPatients	Mean (Std.Dev)
ALL	21	69.0 (35.5)
subtype1	6	41.7 (46.2)
subtype2	6	91.7 (7.5)
subtype3	9	72.2 (28.6)

Figure S50. Get High-res Image Clustering Approach #5: 'RPPA CNMF subtypes' versus Clinical Feature #4: 'KARNOFSKY.PERFORMANCE.SCORE'

'RPPA CNMF subtypes' versus 'HISTOLOGICAL.TYPE'

P value = 0.101 (Chi-square test), Q value = 1

Table S56. Clustering Approach #5: 'RPPA CNMF subtypes' versus Clinical Feature #5: '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 SOLID PATTERN PREDOMINANT ADENOCARCINOMA	MUCINOUS (COLLOID) CARCINOMA
ALL	6	52	151	3	10	1	2	2	6	1	3
subtype1	2	19	56	0	3	1	1	1	1	1	1
subtype2	3	21	36	3	6	0	1	0	3	0	2
subtype3	1	12	59	0	1	0	0	1	2	0	0

Figure S51. Get High-res Image Clustering Approach #5: 'RPPA CNMF subtypes' versus Clinical Feature #5: 'HISTOLOGICAL.TYPE'

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

P value = 0.826 (Fisher's exact test), Q value = 1

Table S57. Clustering Approach #5: 'RPPA CNMF subtypes' versus Clinical Feature #6: 'RADIATIONS.RADIATION.REGIMENINDICATION'

nPatients	NO	YES
ALL	13	224
subtype1	5	81
subtype2	3	72
subtype3	5	71

Figure S52. Get High-res Image Clustering Approach #5: 'RPPA CNMF subtypes' versus Clinical Feature #6: 'RADIATIONS.RADIATION.REGIMENINDICATION'

'RPPA CNMF subtypes' versus 'NUMBERPACKYEARSSMOKED'

P value = 0.396 (ANOVA), Q value = 1

Table S58. Clustering Approach #5: 'RPPA CNMF subtypes' versus Clinical Feature #7: 'NUMBERPACKYEARSSMOKED'

	nPatients	Mean (Std.Dev)
ALL	170	40.8 (26.6)
subtype1	51	43.1 (29.2)
subtype2	64	37.3 (25.2)
subtype3	55	42.9 (25.7)

Figure S53. Get High-res Image Clustering Approach #5: 'RPPA CNMF subtypes' versus Clinical Feature #7: 'NUMBERPACKYEARSSMOKED'

'RPPA CNMF subtypes' versus 'YEAROFTOBACCOSMOKINGONSET'

P value = 0.0368 (ANOVA), Q value = 1

Table S59. Clustering Approach #5: 'RPPA CNMF subtypes' versus Clinical Feature #8: 'YEAROFTOBACCOSMOKINGONSET'

	nPatients	Mean (Std.Dev)
ALL	125	1964.5 (13.6)
subtype1	33	1965.4 (12.9)
subtype2	50	1960.9 (12.7)
subtype3	42	1968.0 (14.3)

Figure S54. Get High-res Image Clustering Approach #5: 'RPPA CNMF subtypes' versus Clinical Feature #8: 'YEAROFTOBACCOSMOKINGONSET'

'RPPA CNMF subtypes' versus 'DISTANT.METASTASIS'

P value = 0.668 (Chi-square test), Q value = 1

Table S60. Clustering Approach #5: 'RPPA CNMF subtypes' versus Clinical Feature #9: 'DISTANT.METASTASIS'

nPatients	M0	M1	MX
ALL	166	12	56
subtype1	60	5	19
subtype2	49	4	22
subtype3	57	3	15

Figure S55. Get High-res Image Clustering Approach #5: 'RPPA CNMF subtypes' versus Clinical Feature #9: 'DISTANT.METASTASIS'

'RPPA CNMF subtypes' versus 'LYMPH.NODE.METASTASIS'

P value = 0.42 (Chi-square test), Q value = 1

Table S61. Clustering Approach #5: 'RPPA CNMF subtypes' versus Clinical Feature #10: 'LYMPH.NODE.METASTASIS'

nPatients	N0	N1	N2	N3	NX
ALL	141	46	43	1	5
subtype1	45	22	14	1	3
subtype2	49	13	12	0	1
subtype3	47	11	17	0	1

Figure S56. Get High-res Image Clustering Approach #5: 'RPPA CNMF subtypes' versus Clinical Feature #10: 'LYMPH.NODE.METASTASIS'

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

P value = 0.119 (Chi-square test), Q value = 1

Table S62. Clustering Approach #5: 'RPPA CNMF subtypes' versus Clinical Feature #11: 'COMPLETENESS.OF.RESECTION'

nPatients	R0	R1	R2	RX
ALL	131	6	3	12
subtype1	44	2	3	5
subtype2	44	3	0	1
subtype3	43	1	0	6

Figure S57. Get High-res Image Clustering Approach #5: 'RPPA CNMF subtypes' versus Clinical Feature #11: 'COMPLETENESS.OF.RESECTION'

'RPPA CNMF subtypes' versus 'NEOPLASM.DISEASESTAGE'

P value = 0.846 (Chi-square test), Q value = 1

Table S63. Clustering Approach #5: 'RPPA CNMF subtypes' versus Clinical Feature #13: 'NEOPLASM.DISEASESTAGE'

nPatients	STAGE I	STAGE IA	STAGE IB	STAGE IIA	STAGE IIB	STAGE IIIA	STAGE IIIB	STAGE IV
ALL	1	54	68	19	32	42	7	13
subtype1	0	21	22	7	14	14	2	5
subtype2	1	18	19	7	11	11	3	5
subtype3	0	15	27	5	7	17	2	3

Figure S58. Get High-res Image Clustering Approach #5: 'RPPA CNMF subtypes' versus Clinical Feature #13: 'NEOPLASM.DISEASESTAGE'

Clustering Approach #6: 'RPPA cHierClus subtypes'

Table S64. Get Full Table Description of clustering approach #6: 'RPPA cHierClus subtypes'

Cluster Labels	1	2	3	4
Number of samples	23	90	66	58

'RPPA cHierClus subtypes' versus 'Time to Death'

P value = 0.157 (logrank test), Q value = 1

Table S65. Clustering Approach #6: 'RPPA cHierClus subtypes' versus Clinical Feature #1: 'Time to Death'

	nPatients	nDeath	Duration Range (Median), Month
ALL	215	68	0.0 - 224.0 (12.3)
subtype1	19	4	0.0 - 63.7 (8.2)
subtype2	77	30	0.7 - 163.1 (13.2)
subtype3	63	20	0.0 - 97.7 (9.0)
subtype4	56	14	0.1 - 224.0 (14.5)

Figure S59. Get High-res Image Clustering Approach #6: 'RPPA cHierClus subtypes' versus Clinical Feature #1: 'Time to Death'

'RPPA cHierClus subtypes' versus 'AGE'

P value = 0.0231 (ANOVA), Q value = 1

Table S66. Clustering Approach #6: 'RPPA cHierClus subtypes' versus Clinical Feature #2: 'AGE'

	nPatients	Mean (Std.Dev)
ALL	216	64.8 (9.8)
subtype1	20	68.0 (6.8)
subtype2	79	63.4 (10.0)
subtype3	62	63.1 (10.7)
subtype4	55	67.5 (8.9)

Figure S60. Get High-res Image Clustering Approach #6: 'RPPA cHierClus subtypes' versus Clinical Feature #2: 'AGE'

'RPPA cHierClus subtypes' versus 'GENDER'

P value = 0.159 (Fisher's exact test), Q value = 1

Table S67. Clustering Approach #6: 'RPPA cHierClus subtypes' versus Clinical Feature #3: 'GENDER'

nPatients	FEMALE	MALE
ALL	131	106
subtype1	15	8
subtype2	56	34
subtype3	33	33
subtype4	27	31

Figure S61. Get High-res Image Clustering Approach #6: 'RPPA cHierClus subtypes' versus Clinical Feature #3: 'GENDER'

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

P value = 0.54 (ANOVA), Q value = 1

Table S68. Clustering Approach #6: 'RPPA cHierClus subtypes' versus Clinical Feature #4: 'KARNOFSKY.PERFORMANCE.SCORE'

	nPatients	Mean (Std.Dev)
ALL	21	69.0 (35.5)
subtype1	4	70.0 (46.9)
subtype2	6	53.3 (42.7)
subtype3	6	70.0 (34.6)
subtype4	5	86.0 (11.4)

Figure S62. Get High-res Image Clustering Approach #6: 'RPPA cHierClus subtypes' versus Clinical Feature #4: 'KARNOFSKY.PERFORMANCE.SCORE'

'RPPA cHierClus subtypes' versus 'HISTOLOGICAL.TYPE'

P value = 0.00532 (Chi-square test), Q value = 0.72

Table S69. Clustering Approach #6: 'RPPA cHierClus subtypes' versus Clinical Feature #5: '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 SOLID PATTERN PREDOMINANT ADENOCARCINOMA	MUCINOUS (COLLOID) CARCINOMA
ALL	6	52	151	3	10	1	2	2	6	1	3
subtype1	1	4	12	0	3	0	2	0	1	0	0
subtype2	1	20	63	0	2	0	0	0	2	1	1
subtype3	2	10	49	0	2	1	0	1	1	0	0
subtype4	2	18	27	3	3	0	0	1	2	0	2

Figure S63. Get High-res Image Clustering Approach #6: 'RPPA cHierClus subtypes' versus Clinical Feature #5: 'HISTOLOGICAL.TYPE'

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

P value = 0.208 (Fisher's exact test), Q value = 1

Table S70. Clustering Approach #6: 'RPPA cHierClus subtypes' versus Clinical Feature #6: 'RADIATIONS.RADIATION.REGIMENINDICATION'

nPatients	NO	YES
ALL	13	224
subtype1	0	23
subtype2	4	86
subtype3	7	59
subtype4	2	56

Figure S64. Get High-res Image Clustering Approach #6: 'RPPA cHierClus subtypes' versus Clinical Feature #6: 'RADIATIONS.RADIATION.REGIMENINDICATION'

'RPPA cHierClus subtypes' versus 'NUMBERPACKYEARSSMOKED'

P value = 0.24 (ANOVA), Q value = 1

Table S71. Clustering Approach #6: 'RPPA cHierClus subtypes' versus Clinical Feature #7: 'NUMBERPACKYEARSSMOKED'

	nPatients	Mean (Std.Dev)
ALL	170	40.8 (26.6)
subtype1	17	48.7 (34.8)
subtype2	48	38.5 (24.9)
subtype3	53	44.6 (27.7)
subtype4	52	36.7 (23.5)

Figure S65. Get High-res Image Clustering Approach #6: 'RPPA cHierClus subtypes' versus Clinical Feature #7: 'NUMBERPACKYEARSSMOKED'

'RPPA cHierClus subtypes' versus 'YEAROFTOBACCOSMOKINGONSET'

P value = 0.0257 (ANOVA), Q value = 1

Table S72. Clustering Approach #6: 'RPPA cHierClus subtypes' versus Clinical Feature #8: 'YEAROFTOBACCOSMOKINGONSET'

	nPatients	Mean (Std.Dev)
ALL	125	1964.5 (13.6)
subtype1	11	1962.1 (10.6)
subtype2	32	1965.8 (12.6)
subtype3	40	1968.8 (13.7)
subtype4	42	1960.0 (13.7)

Figure S66. Get High-res Image Clustering Approach #6: 'RPPA cHierClus subtypes' versus Clinical Feature #8: 'YEAROFTOBACCOSMOKINGONSET'

'RPPA cHierClus subtypes' versus 'DISTANT.METASTASIS'

P value = 0.841 (Chi-square test), Q value = 1

Table S73. Clustering Approach #6: 'RPPA cHierClus subtypes' versus Clinical Feature #9: 'DISTANT.METASTASIS'

nPatients	M0	M1	MX
ALL	166	12	56
subtype1	14	1	8
subtype2	62	6	20
subtype3	48	2	15
subtype4	42	3	13

Figure S67. Get High-res Image Clustering Approach #6: 'RPPA cHierClus subtypes' versus Clinical Feature #9: 'DISTANT.METASTASIS'

'RPPA cHierClus subtypes' versus 'LYMPH.NODE.METASTASIS'

P value = 0.541 (Chi-square test), Q value = 1

Table S74. Clustering Approach #6: 'RPPA cHierClus subtypes' versus Clinical Feature #10: 'LYMPH.NODE.METASTASIS'

nPatients	N0	N1	N2	N3	NX
ALL	141	46	43	1	5
subtype1	15	4	4	0	0
subtype2	48	21	15	1	4
subtype3	40	9	16	0	1
subtype4	38	12	8	0	0

Figure S68. Get High-res Image Clustering Approach #6: 'RPPA cHierClus subtypes' versus Clinical Feature #10: 'LYMPH.NODE.METASTASIS'

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

P value = 0.502 (Chi-square test), Q value = 1

Table S75. Clustering Approach #6: 'RPPA cHierClus subtypes' versus Clinical Feature #11: 'COMPLETENESS.OF.RESECTION'

nPatients	R0	R1	R2	RX
ALL	131	6	3	12
subtype1	12	0	0	0
subtype2	47	3	3	4
subtype3	36	1	0	5
subtype4	36	2	0	3

Figure S69. Get High-res Image Clustering Approach #6: 'RPPA cHierClus subtypes' versus Clinical Feature #11: 'COMPLETENESS.OF.RESECTION'

'RPPA cHierClus subtypes' versus 'NEOPLASM.DISEASESTAGE'

P value = 0.972 (Chi-square test), Q value = 1

Table S76. Clustering Approach #6: 'RPPA cHierClus subtypes' versus Clinical Feature #13: 'NEOPLASM.DISEASESTAGE'

nPatients	STAGE I	STAGE IA	STAGE IB	STAGE IIA	STAGE IIB	STAGE IIIA	STAGE IIIB	STAGE IV
ALL	1	54	68	19	32	42	7	13
subtype1	0	6	6	2	3	4	1	1
subtype2	0	21	27	7	13	12	3	6
subtype3	1	11	21	5	7	17	1	3
subtype4	0	16	14	5	9	9	2	3

Figure S70. Get High-res Image Clustering Approach #6: 'RPPA cHierClus subtypes' versus Clinical Feature #13: 'NEOPLASM.DISEASESTAGE'

Clustering Approach #7: 'RNAseq CNMF subtypes'

Table S77. Get Full Table Description of clustering approach #7: 'RNAseq CNMF subtypes'

Cluster Labels	1	2	3	4	5	6	7	8	9
Number of samples	68	50	50	39	26	43	36	21	21

'RNAseq CNMF subtypes' versus 'Time to Death'

P value = 0.0475 (logrank test), Q value = 1

Table S78. Clustering Approach #7: 'RNAseq CNMF subtypes' versus Clinical Feature #1: 'Time to Death'

	nPatients	nDeath	Duration Range (Median), Month
ALL	319	83	0.0 - 224.0 (9.4)
subtype1	60	16	0.0 - 77.9 (8.6)
subtype2	47	10	0.1 - 224.0 (7.0)
subtype3	46	19	0.0 - 97.7 (11.6)
subtype4	34	13	0.5 - 104.2 (18.2)
subtype5	24	3	0.1 - 48.5 (4.5)
subtype6	40	4	0.2 - 83.8 (14.3)
subtype7	32	12	0.2 - 55.4 (8.6)
subtype8	20	2	0.1 - 49.3 (6.3)
subtype9	16	4	0.1 - 120.8 (3.9)

Figure S71. Get High-res Image Clustering Approach #7: 'RNAseq CNMF subtypes' versus Clinical Feature #1: 'Time to Death'

'RNAseq CNMF subtypes' versus 'AGE'

P value = 0.00121 (ANOVA), Q value = 0.17

Table S79. Clustering Approach #7: 'RNAseq CNMF subtypes' versus Clinical Feature #2: 'AGE'

	nPatients	Mean (Std.Dev)
ALL	323	65.2 (9.8)
subtype1	64	62.4 (11.0)
subtype2	47	65.9 (9.5)
subtype3	45	64.4 (8.6)
subtype4	37	67.8 (7.6)
subtype5	23	71.3 (8.4)
subtype6	38	61.4 (9.5)
subtype7	32	65.7 (9.2)
subtype8	20	66.5 (11.2)
subtype9	17	68.2 (9.5)

Figure S72. Get High-res Image Clustering Approach #7: 'RNAseq CNMF subtypes' versus Clinical Feature #2: 'AGE'

'RNAseq CNMF subtypes' versus 'GENDER'

P value = 3.08e-08 (Chi-square test), Q value = 4.4e-06

Table S80. Clustering Approach #7: 'RNAseq CNMF subtypes' versus Clinical Feature #3: 'GENDER'

nPatients	FEMALE	MALE
ALL	191	163
subtype1	37	31
subtype2	43	7
subtype3	20	30
subtype4	10	29
subtype5	9	17
subtype6	21	22
subtype7	20	16
subtype8	13	8
subtype9	18	3

Figure S73. Get High-res Image Clustering Approach #7: 'RNAseq CNMF subtypes' versus Clinical Feature #3: 'GENDER'

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

P value = 0.934 (ANOVA), Q value = 1

Table S81. Clustering Approach #7: 'RNAseq CNMF subtypes' versus Clinical Feature #4: 'KARNOFSKY.PERFORMANCE.SCORE'

	nPatients	Mean (Std.Dev)
ALL	29	75.9 (32.4)
subtype1	9	75.6 (31.7)
subtype2	4	75.0 (50.0)
subtype3	3	86.7 (5.8)
subtype4	1	90.0 (NA)
subtype6	5	66.0 (37.1)
subtype7	3	63.3 (55.1)
subtype8	1	90.0 (NA)
subtype9	3	86.7 (5.8)

Figure S74. Get High-res Image Clustering Approach #7: 'RNAseq CNMF subtypes' versus Clinical Feature #4: 'KARNOFSKY.PERFORMANCE.SCORE'

'RNAseq CNMF subtypes' versus 'HISTOLOGICAL.TYPE'

P value = 0.000278 (Chi-square test), Q value = 0.039

Table S82. Clustering Approach #7: 'RNAseq CNMF subtypes' versus Clinical Feature #5: '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 SOLID PATTERN PREDOMINANT ADENOCARCINOMA	MUCINOUS (COLLOID) CARCINOMA
ALL	10	75	214	4	17	2	3	2	17	3	7
subtype1	1	14	46	0	2	0	2	0	3	0	0
subtype2	2	9	30	2	4	0	0	0	3	0	0
subtype3	0	10	32	0	2	1	0	0	2	3	0
subtype4	1	16	15	0	2	0	0	0	5	0	0
subtype5	2	6	11	2	0	0	0	1	1	0	3
subtype6	3	8	28	0	2	1	0	0	0	0	1
subtype7	0	6	27	0	0	0	0	0	1	0	2
subtype8	1	5	11	0	1	0	0	1	1	0	1
subtype9	0	1	14	0	4	0	1	0	1	0	0

Figure S75. Get High-res Image Clustering Approach #7: 'RNAseq CNMF subtypes' versus Clinical Feature #5: 'HISTOLOGICAL.TYPE'

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

P value = 0.525 (Chi-square test), Q value = 1

Table S83. Clustering Approach #7: 'RNAseq CNMF subtypes' versus Clinical Feature #6: 'RADIATIONS.RADIATION.REGIMENINDICATION'

nPatients	NO	YES
ALL	17	337
subtype1	4	64
subtype2	1	49
subtype3	3	47
subtype4	1	38
subtype5	0	26
subtype6	2	41
subtype7	2	34
subtype8	1	20
subtype9	3	18

Figure S76. Get High-res Image Clustering Approach #7: 'RNAseq CNMF subtypes' versus Clinical Feature #6: 'RADIATIONS.RADIATION.REGIMENINDICATION'

'RNAseq CNMF subtypes' versus 'NUMBERPACKYEARSSMOKED'

P value = 0.052 (ANOVA), Q value = 1

Table S84. Clustering Approach #7: 'RNAseq CNMF subtypes' versus Clinical Feature #7: 'NUMBERPACKYEARSSMOKED'

	nPatients	Mean (Std.Dev)
ALL	242	41.0 (26.8)
subtype1	51	44.6 (25.0)
subtype2	25	30.5 (19.9)
subtype3	35	49.5 (30.4)
subtype4	30	43.6 (31.8)
subtype5	18	40.8 (27.0)
subtype6	34	36.7 (24.9)
subtype7	24	45.5 (28.7)
subtype8	11	39.7 (24.8)
subtype9	14	24.7 (15.7)

Figure S77. Get High-res Image Clustering Approach #7: 'RNAseq CNMF subtypes' versus Clinical Feature #7: 'NUMBERPACKYEARSSMOKED'

'RNAseq CNMF subtypes' versus 'YEAROFTOBACCOSMOKINGONSET'

P value = 0.00787 (ANOVA), Q value = 1

Table S85. Clustering Approach #7: 'RNAseq CNMF subtypes' versus Clinical Feature #8: 'YEAROFTOBACCOSMOKINGONSET'

	nPatients	Mean (Std.Dev)
ALL	185	1965.0 (12.8)
subtype1	36	1965.8 (14.4)
subtype2	21	1962.1 (10.5)
subtype3	27	1968.7 (13.7)
subtype4	27	1956.4 (12.8)
subtype5	10	1962.0 (11.4)
subtype6	29	1967.4 (10.2)
subtype7	14	1968.4 (10.5)
subtype8	9	1969.8 (13.9)
subtype9	12	1967.8 (9.8)

Figure S78. Get High-res Image Clustering Approach #7: 'RNAseq CNMF subtypes' versus Clinical Feature #8: 'YEAROFTOBACCOSMOKINGONSET'

'RNAseq CNMF subtypes' versus 'DISTANT.METASTASIS'

P value = 0.313 (Chi-square test), Q value = 1

Table S86. Clustering Approach #7: 'RNAseq CNMF subtypes' versus Clinical Feature #9: 'DISTANT.METASTASIS'

nPatients	M0	M1	M1A	M1B	MX
ALL	242	17	1	3	87
subtype1	45	3	0	0	20
subtype2	32	2	1	0	13
subtype3	34	3	0	1	12
subtype4	29	4	0	0	6
subtype5	15	0	0	1	9
subtype6	32	1	0	0	9
subtype7	30	2	0	0	4
subtype8	9	2	0	1	9
subtype9	16	0	0	0	5

Figure S79. Get High-res Image Clustering Approach #7: 'RNAseq CNMF subtypes' versus Clinical Feature #9: 'DISTANT.METASTASIS'

'RNAseq CNMF subtypes' versus 'LYMPH.NODE.METASTASIS'

P value = 0.705 (Chi-square test), Q value = 1

Table S87. Clustering Approach #7: 'RNAseq CNMF subtypes' versus Clinical Feature #10: 'LYMPH.NODE.METASTASIS'

nPatients	N0	N1	N2	N3	NX
ALL	218	71	55	1	7
subtype1	32	19	15	1	1
subtype2	32	9	6	0	2
subtype3	31	9	10	0	0
subtype4	24	9	4	0	2
subtype5	19	3	3	0	0
subtype6	30	4	8	0	1
subtype7	22	8	6	0	0
subtype8	14	4	2	0	1
subtype9	14	6	1	0	0

Figure S80. Get High-res Image Clustering Approach #7: 'RNAseq CNMF subtypes' versus Clinical Feature #10: 'LYMPH.NODE.METASTASIS'

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

P value = 0.887 (Chi-square test), Q value = 1

Table S88. Clustering Approach #7: 'RNAseq CNMF subtypes' versus Clinical Feature #11: 'COMPLETENESS.OF.RESECTION'

nPatients	R0	R1	R2	RX
ALL	213	9	4	12
subtype1	37	1	1	3
subtype2	30	3	1	2
subtype3	27	2	0	1
subtype4	24	0	0	2
subtype5	15	0	0	2
subtype6	28	1	0	1
subtype7	25	1	1	0
subtype8	12	0	1	1
subtype9	15	1	0	0

Figure S81. Get High-res Image Clustering Approach #7: 'RNAseq CNMF subtypes' versus Clinical Feature #11: 'COMPLETENESS.OF.RESECTION'

'RNAseq CNMF subtypes' versus 'NEOPLASM.DISEASESTAGE'

P value = 0.835 (Chi-square test), Q value = 1

Table S89. Clustering Approach #7: 'RNAseq CNMF subtypes' versus Clinical Feature #13: 'NEOPLASM.DISEASESTAGE'

nPatients	STAGE I	STAGE IA	STAGE IB	STAGE IIA	STAGE IIB	STAGE IIIA	STAGE IIIB	STAGE IV
ALL	2	82	103	28	51	55	10	21
subtype1	1	13	17	7	10	14	2	4
subtype2	0	14	17	5	5	4	2	3
subtype3	0	11	17	3	5	10	1	3
subtype4	0	10	10	2	7	4	2	4
subtype5	0	4	10	0	7	3	0	1
subtype6	1	7	15	4	5	9	1	1
subtype7	0	9	8	2	7	6	2	2
subtype8	0	9	4	1	3	1	0	3
subtype9	0	5	5	4	2	4	0	0

Figure S82. Get High-res Image Clustering Approach #7: 'RNAseq CNMF subtypes' versus Clinical Feature #13: 'NEOPLASM.DISEASESTAGE'

Clustering Approach #8: 'RNAseq cHierClus subtypes'

Table S90. Get Full Table Description of clustering approach #8: 'RNAseq cHierClus subtypes'

Cluster Labels	1	2	3
Number of samples	146	96	112

'RNAseq cHierClus subtypes' versus 'Time to Death'

P value = 0.033 (logrank test), Q value = 1

Table S91. Clustering Approach #8: 'RNAseq cHierClus subtypes' versus Clinical Feature #1: 'Time to Death'

	nPatients	nDeath	Duration Range (Median), Month
ALL	319	83	0.0 - 224.0 (9.4)
subtype1	132	29	0.1 - 224.0 (11.5)
subtype2	84	25	0.0 - 97.7 (7.9)
subtype3	103	29	0.0 - 83.8 (9.0)

Figure S83. Get High-res Image Clustering Approach #8: 'RNAseq cHierClus subtypes' versus Clinical Feature #1: 'Time to Death'

'RNAseq cHierClus subtypes' versus 'AGE'

P value = 0.0242 (ANOVA), Q value = 1

Table S92. Clustering Approach #8: 'RNAseq cHierClus subtypes' versus Clinical Feature #2: 'AGE'

	nPatients	Mean (Std.Dev)
ALL	323	65.2 (9.8)
subtype1	133	66.9 (9.3)
subtype2	87	63.6 (10.7)
subtype3	103	64.3 (9.2)

Figure S84. Get High-res Image Clustering Approach #8: 'RNAseq cHierClus subtypes' versus Clinical Feature #2: 'AGE'

'RNAseq cHierClus subtypes' versus 'GENDER'

P value = 0.000305 (Fisher's exact test), Q value = 0.042

Table S93. Clustering Approach #8: 'RNAseq cHierClus subtypes' versus Clinical Feature #3: 'GENDER'

nPatients	FEMALE	MALE
ALL	191	163
subtype1	94	52
subtype2	53	43
subtype3	44	68

Figure S85. Get High-res Image Clustering Approach #8: 'RNAseq cHierClus subtypes' versus Clinical Feature #3: 'GENDER'

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

P value = 0.238 (ANOVA), Q value = 1

Table S94. Clustering Approach #8: 'RNAseq cHierClus subtypes' versus Clinical Feature #4: 'KARNOFSKY.PERFORMANCE.SCORE'

	nPatients	Mean (Std.Dev)
ALL	29	75.9 (32.4)
subtype1	11	83.6 (28.7)
subtype2	11	62.7 (42.2)
subtype3	7	84.3 (5.3)

Figure S86. Get High-res Image Clustering Approach #8: 'RNAseq cHierClus subtypes' versus Clinical Feature #4: 'KARNOFSKY.PERFORMANCE.SCORE'

'RNAseq cHierClus subtypes' versus 'HISTOLOGICAL.TYPE'

P value = 0.0129 (Chi-square test), Q value = 1

Table S95. Clustering Approach #8: 'RNAseq cHierClus subtypes' versus Clinical Feature #5: '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 SOLID PATTERN PREDOMINANT ADENOCARCINOMA	MUCINOUS (COLLOID) CARCINOMA
ALL	10	75	214	4	17	2	3	2	17	3	7
subtype1	7	36	72	4	10	0	1	2	9	0	5
subtype2	1	16	68	0	4	1	2	0	4	0	0
subtype3	2	23	74	0	3	1	0	0	4	3	2

Figure S87. Get High-res Image Clustering Approach #8: 'RNAseq cHierClus subtypes' versus Clinical Feature #5: 'HISTOLOGICAL.TYPE'

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

P value = 0.38 (Fisher's exact test), Q value = 1

Table S96. Clustering Approach #8: 'RNAseq cHierClus subtypes' versus Clinical Feature #6: 'RADIATIONS.RADIATION.REGIMENINDICATION'

nPatients	NO	YES
ALL	17	337
subtype1	5	141
subtype2	4	92
subtype3	8	104

Figure S88. Get High-res Image Clustering Approach #8: 'RNAseq cHierClus subtypes' versus Clinical Feature #6: 'RADIATIONS.RADIATION.REGIMENINDICATION'

'RNAseq cHierClus subtypes' versus 'NUMBERPACKYEARSSMOKED'

P value = 0.038 (ANOVA), Q value = 1

Table S97. Clustering Approach #8: 'RNAseq cHierClus subtypes' versus Clinical Feature #7: 'NUMBERPACKYEARSSMOKED'

	nPatients	Mean (Std.Dev)
ALL	242	41.0 (26.8)
subtype1	91	35.4 (25.4)
subtype2	65	44.7 (25.4)
subtype3	86	44.2 (28.6)

Figure S89. Get High-res Image Clustering Approach #8: 'RNAseq cHierClus subtypes' versus Clinical Feature #7: 'NUMBERPACKYEARSSMOKED'

'RNAseq cHierClus subtypes' versus 'YEAROFTOBACCOSMOKINGONSET'

P value = 0.0853 (ANOVA), Q value = 1

Table S98. Clustering Approach #8: 'RNAseq cHierClus subtypes' versus Clinical Feature #8: 'YEAROFTOBACCOSMOKINGONSET'

	nPatients	Mean (Std.Dev)
ALL	185	1965.0 (12.8)
subtype1	71	1962.6 (13.0)
subtype2	48	1965.1 (13.2)
subtype3	66	1967.5 (11.9)

Figure S90. Get High-res Image Clustering Approach #8: 'RNAseq cHierClus subtypes' versus Clinical Feature #8: 'YEAROFTOBACCOSMOKINGONSET'

'RNAseq cHierClus subtypes' versus 'DISTANT.METASTASIS'

P value = 0.826 (Chi-square test), Q value = 1

Table S99. Clustering Approach #8: 'RNAseq cHierClus subtypes' versus Clinical Feature #9: 'DISTANT.METASTASIS'

nPatients	M0	M1	M1A	M1B	MX
ALL	242	17	1	3	87
subtype1	100	6	1	1	36
subtype2	66	4	0	0	25
subtype3	76	7	0	2	26

Figure S91. Get High-res Image Clustering Approach #8: 'RNAseq cHierClus subtypes' versus Clinical Feature #9: 'DISTANT.METASTASIS'

'RNAseq cHierClus subtypes' versus 'LYMPH.NODE.METASTASIS'

P value = 0.208 (Chi-square test), Q value = 1

Table S100. Clustering Approach #8: 'RNAseq cHierClus subtypes' versus Clinical Feature #10: 'LYMPH.NODE.METASTASIS'

nPatients	N0	N1	N2	N3	NX
ALL	218	71	55	1	7
subtype1	97	29	15	0	3
subtype2	51	24	18	1	2
subtype3	70	18	22	0	2

Figure S92. Get High-res Image Clustering Approach #8: 'RNAseq cHierClus subtypes' versus Clinical Feature #10: 'LYMPH.NODE.METASTASIS'

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

P value = 0.55 (Chi-square test), Q value = 1

Table S101. Clustering Approach #8: 'RNAseq cHierClus subtypes' versus Clinical Feature #11: 'COMPLETENESS.OF.RESECTION'

nPatients	R0	R1	R2	RX
ALL	213	9	4	12
subtype1	84	2	2	6
subtype2	60	2	2	3
subtype3	69	5	0	3

Figure S93. Get High-res Image Clustering Approach #8: 'RNAseq cHierClus subtypes' versus Clinical Feature #11: 'COMPLETENESS.OF.RESECTION'

'RNAseq cHierClus subtypes' versus 'NEOPLASM.DISEASESTAGE'

P value = 0.0703 (Chi-square test), Q value = 1

Table S102. Clustering Approach #8: 'RNAseq cHierClus subtypes' versus Clinical Feature #13: 'NEOPLASM.DISEASESTAGE'

nPatients	STAGE I	STAGE IA	STAGE IB	STAGE IIA	STAGE IIB	STAGE IIIA	STAGE IIIB	STAGE IV
ALL	2	82	103	28	51	55	10	21
subtype1	0	46	39	12	21	15	3	8
subtype2	0	12	33	10	13	19	4	5
subtype3	2	24	31	6	17	21	3	8

Figure S94. Get High-res Image Clustering Approach #8: 'RNAseq cHierClus subtypes' versus Clinical Feature #13: 'NEOPLASM.DISEASESTAGE'

Clustering Approach #9: 'MIRSEQ CNMF'

Table S103. Get Full Table Description of clustering approach #9: 'MIRSEQ CNMF'

Cluster Labels	1	2	3
Number of samples	140	165	81

'MIRSEQ CNMF' versus 'Time to Death'

P value = 0.364 (logrank test), Q value = 1

Table S104. Clustering Approach #9: 'MIRSEQ CNMF' versus Clinical Feature #1: 'Time to Death'

	nPatients	nDeath	Duration Range (Median), Month
ALL	350	85	0.0 - 224.0 (8.4)
subtype1	128	27	0.0 - 163.1 (8.3)
subtype2	147	38	0.0 - 97.7 (8.8)
subtype3	75	20	0.0 - 224.0 (8.1)

Figure S95. Get High-res Image Clustering Approach #9: 'MIRSEQ CNMF' versus Clinical Feature #1: 'Time to Death'

'MIRSEQ CNMF' versus 'AGE'

P value = 0.173 (ANOVA), Q value = 1

Table S105. Clustering Approach #9: 'MIRSEQ CNMF' versus Clinical Feature #2: 'AGE'

	nPatients	Mean (Std.Dev)
ALL	356	65.2 (9.9)
subtype1	131	66.5 (9.6)
subtype2	154	64.5 (10.3)
subtype3	71	64.5 (9.2)

Figure S96. Get High-res Image Clustering Approach #9: 'MIRSEQ CNMF' versus Clinical Feature #2: 'AGE'

'MIRSEQ CNMF' versus 'GENDER'

P value = 0.774 (Fisher's exact test), Q value = 1

Table S106. Clustering Approach #9: 'MIRSEQ CNMF' versus Clinical Feature #3: 'GENDER'

nPatients	FEMALE	MALE
ALL	209	177
subtype1	77	63
subtype2	86	79
subtype3	46	35

Figure S97. Get High-res Image Clustering Approach #9: 'MIRSEQ CNMF' versus Clinical Feature #3: 'GENDER'

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

P value = 0.823 (ANOVA), Q value = 1

Table S107. Clustering Approach #9: 'MIRSEQ CNMF' versus Clinical Feature #4: 'KARNOFSKY.PERFORMANCE.SCORE'

	nPatients	Mean (Std.Dev)
ALL	27	74.1 (32.8)
subtype1	11	71.8 (36.6)
subtype2	14	75.0 (32.5)
subtype3	2	80.0 (28.3)

Figure S98. Get High-res Image Clustering Approach #9: 'MIRSEQ CNMF' versus Clinical Feature #4: 'KARNOFSKY.PERFORMANCE.SCORE'

'MIRSEQ CNMF' versus 'HISTOLOGICAL.TYPE'

P value = 0.0283 (Chi-square test), Q value = 1

Table S108. Clustering Approach #9: 'MIRSEQ CNMF' versus Clinical Feature #5: '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 SOLID PATTERN PREDOMINANT ADENOCARCINOMA	MUCINOUS (COLLOID) CARCINOMA
ALL	11	78	242	4	17	2	2	2	18	3	7
subtype1	5	29	78	3	10	0	1	2	8	0	4
subtype2	6	40	104	0	4	2	0	0	5	3	1
subtype3	0	9	60	1	3	0	1	0	5	0	2

Figure S99. Get High-res Image Clustering Approach #9: 'MIRSEQ CNMF' versus Clinical Feature #5: 'HISTOLOGICAL.TYPE'

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

P value = 0.73 (Fisher's exact test), Q value = 1

Table S109. Clustering Approach #9: 'MIRSEQ CNMF' versus Clinical Feature #6: 'RADIATIONS.RADIATION.REGIMENINDICATION'

nPatients	NO	YES
ALL	17	369
subtype1	7	133
subtype2	8	157
subtype3	2	79

Figure S100. Get High-res Image Clustering Approach #9: 'MIRSEQ CNMF' versus Clinical Feature #6: 'RADIATIONS.RADIATION.REGIMENINDICATION'

'MIRSEQ CNMF' versus 'NUMBERPACKYEARSSMOKED'

P value = 0.212 (ANOVA), Q value = 1

Table S110. Clustering Approach #9: 'MIRSEQ CNMF' versus Clinical Feature #7: 'NUMBERPACKYEARSSMOKED'

	nPatients	Mean (Std.Dev)
ALL	269	41.7 (26.9)
subtype1	94	38.1 (24.5)
subtype2	122	42.7 (28.3)
subtype3	53	45.8 (27.5)

Figure S101. Get High-res Image Clustering Approach #9: 'MIRSEQ CNMF' versus Clinical Feature #7: 'NUMBERPACKYEARSSMOKED'

'MIRSEQ CNMF' versus 'YEAROFTOBACCOSMOKINGONSET'

P value = 0.0519 (ANOVA), Q value = 1

Table S111. Clustering Approach #9: 'MIRSEQ CNMF' versus Clinical Feature #8: 'YEAROFTOBACCOSMOKINGONSET'

	nPatients	Mean (Std.Dev)
ALL	210	1965.0 (12.5)
subtype1	75	1962.2 (12.7)
subtype2	98	1966.9 (12.6)
subtype3	37	1965.5 (11.2)

Figure S102. Get High-res Image Clustering Approach #9: 'MIRSEQ CNMF' versus Clinical Feature #8: 'YEAROFTOBACCOSMOKINGONSET'

'MIRSEQ CNMF' versus 'DISTANT.METASTASIS'

P value = 0.571 (Chi-square test), Q value = 1

Table S112. Clustering Approach #9: 'MIRSEQ CNMF' versus Clinical Feature #9: 'DISTANT.METASTASIS'

nPatients	M0	M1	M1A	M1B	MX
ALL	259	15	1	3	104
subtype1	92	6	0	1	39
subtype2	117	7	1	2	37
subtype3	50	2	0	0	28

Figure S103. Get High-res Image Clustering Approach #9: 'MIRSEQ CNMF' versus Clinical Feature #9: 'DISTANT.METASTASIS'

'MIRSEQ CNMF' versus 'LYMPH.NODE.METASTASIS'

P value = 0.77 (Chi-square test), Q value = 1

Table S113. Clustering Approach #9: 'MIRSEQ CNMF' versus Clinical Feature #10: 'LYMPH.NODE.METASTASIS'

nPatients	N0	N1	N2	N3	NX
ALL	245	71	58	2	8
subtype1	87	30	18	0	3
subtype2	107	26	27	2	3
subtype3	51	15	13	0	2

Figure S104. Get High-res Image Clustering Approach #9: 'MIRSEQ CNMF' versus Clinical Feature #10: 'LYMPH.NODE.METASTASIS'

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

P value = 0.565 (Chi-square test), Q value = 1

Table S114. Clustering Approach #9: 'MIRSEQ CNMF' versus Clinical Feature #11: 'COMPLETENESS.OF.RESECTION'

nPatients	R0	R1	R2	RX
ALL	239	9	4	14
subtype1	86	1	2	5
subtype2	110	5	2	5
subtype3	43	3	0	4

Figure S105. Get High-res Image Clustering Approach #9: 'MIRSEQ CNMF' versus Clinical Feature #11: 'COMPLETENESS.OF.RESECTION'

'MIRSEQ CNMF' versus 'NEOPLASM.DISEASESTAGE'

P value = 0.172 (Chi-square test), Q value = 1

Table S115. Clustering Approach #9: 'MIRSEQ CNMF' versus Clinical Feature #13: 'NEOPLASM.DISEASESTAGE'

nPatients	STAGE I	STAGE IA	STAGE IB	STAGE IIA	STAGE IIB	STAGE IIIA	STAGE IIIB	STAGE IV
ALL	3	96	113	32	51	58	11	20
subtype1	0	48	31	12	20	18	1	8
subtype2	2	34	54	13	20	26	7	9
subtype3	1	14	28	7	11	14	3	3

Figure S106. Get High-res Image Clustering Approach #9: 'MIRSEQ CNMF' versus Clinical Feature #13: 'NEOPLASM.DISEASESTAGE'

Clustering Approach #10: 'MIRSEQ CHIERARCHICAL'

Table S116. Get Full Table Description of clustering approach #10: 'MIRSEQ CHIERARCHICAL'

Cluster Labels	1	2	3
Number of samples	133	208	45

'MIRSEQ CHIERARCHICAL' versus 'Time to Death'

P value = 0.83 (logrank test), Q value = 1

Table S117. Clustering Approach #10: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #1: 'Time to Death'

	nPatients	nDeath	Duration Range (Median), Month
ALL	350	85	0.0 - 224.0 (8.4)
subtype1	120	26	0.0 - 104.2 (8.4)
subtype2	189	45	0.0 - 97.7 (8.5)
subtype3	41	14	0.1 - 224.0 (6.2)

Figure S107. Get High-res Image Clustering Approach #10: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #1: 'Time to Death'

'MIRSEQ CHIERARCHICAL' versus 'AGE'

P value = 0.0544 (ANOVA), Q value = 1

Table S118. Clustering Approach #10: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #2: 'AGE'

	nPatients	Mean (Std.Dev)
ALL	356	65.2 (9.9)
subtype1	121	66.9 (9.4)
subtype2	194	64.2 (10.3)
subtype3	41	64.8 (8.7)

Figure S108. Get High-res Image Clustering Approach #10: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #2: 'AGE'

'MIRSEQ CHIERARCHICAL' versus 'GENDER'

P value = 0.00639 (Fisher's exact test), Q value = 0.86

Table S119. Clustering Approach #10: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #3: 'GENDER'

nPatients	FEMALE	MALE
ALL	209	177
subtype1	71	62
subtype2	104	104
subtype3	34	11

Figure S109. Get High-res Image Clustering Approach #10: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #3: 'GENDER'

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

P value = 0.823 (ANOVA), Q value = 1

Table S120. Clustering Approach #10: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #4: 'KARNOFSKY.PERFORMANCE.SCORE'

	nPatients	Mean (Std.Dev)
ALL	27	74.1 (32.8)
subtype1	11	71.8 (36.6)
subtype2	14	75.0 (32.5)
subtype3	2	80.0 (28.3)

Figure S110. Get High-res Image Clustering Approach #10: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #4: 'KARNOFSKY.PERFORMANCE.SCORE'

'MIRSEQ CHIERARCHICAL' versus 'HISTOLOGICAL.TYPE'

P value = 0.000223 (Chi-square test), Q value = 0.031

Table S121. Clustering Approach #10: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #5: '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 SOLID PATTERN PREDOMINANT ADENOCARCINOMA	MUCINOUS (COLLOID) CARCINOMA
ALL	11	78	242	4	17	2	2	2	18	3	7
subtype1	4	30	72	2	10	1	0	2	7	0	5
subtype2	7	45	138	0	6	1	0	0	7	3	1
subtype3	0	3	32	2	1	0	2	0	4	0	1

Figure S111. Get High-res Image Clustering Approach #10: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #5: 'HISTOLOGICAL.TYPE'

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

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

Table S122. Clustering Approach #10: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #6: 'RADIATIONS.RADIATION.REGIMENINDICATION'

nPatients	NO	YES
ALL	17	369
subtype1	6	127
subtype2	9	199
subtype3	2	43

Figure S112. Get High-res Image Clustering Approach #10: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #6: 'RADIATIONS.RADIATION.REGIMENINDICATION'

'MIRSEQ CHIERARCHICAL' versus 'NUMBERPACKYEARSSMOKED'

P value = 0.279 (ANOVA), Q value = 1

Table S123. Clustering Approach #10: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #7: 'NUMBERPACKYEARSSMOKED'

	nPatients	Mean (Std.Dev)
ALL	269	41.7 (26.9)
subtype1	88	38.6 (25.0)
subtype2	153	44.0 (28.9)
subtype3	28	39.2 (20.9)

Figure S113. Get High-res Image Clustering Approach #10: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #7: 'NUMBERPACKYEARSSMOKED'

'MIRSEQ CHIERARCHICAL' versus 'YEAROFTOBACCOSMOKINGONSET'

P value = 0.0223 (ANOVA), Q value = 1

Table S124. Clustering Approach #10: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #8: 'YEAROFTOBACCOSMOKINGONSET'

	nPatients	Mean (Std.Dev)
ALL	210	1965.0 (12.5)
subtype1	74	1962.9 (11.7)
subtype2	116	1967.1 (13.0)
subtype3	20	1960.8 (11.0)

Figure S114. Get High-res Image Clustering Approach #10: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #8: 'YEAROFTOBACCOSMOKINGONSET'

'MIRSEQ CHIERARCHICAL' versus 'DISTANT.METASTASIS'

P value = 0.989 (Chi-square test), Q value = 1

Table S125. Clustering Approach #10: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #9: 'DISTANT.METASTASIS'

nPatients	M0	M1	M1A	M1B	MX
ALL	259	15	1	3	104
subtype1	87	5	0	1	38
subtype2	141	8	1	2	55
subtype3	31	2	0	0	11

Figure S115. Get High-res Image Clustering Approach #10: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #9: 'DISTANT.METASTASIS'

'MIRSEQ CHIERARCHICAL' versus 'LYMPH.NODE.METASTASIS'

P value = 0.343 (Chi-square test), Q value = 1

Table S126. Clustering Approach #10: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #10: 'LYMPH.NODE.METASTASIS'

nPatients	N0	N1	N2	N3	NX
ALL	245	71	58	2	8
subtype1	82	27	17	0	5
subtype2	137	32	34	2	3
subtype3	26	12	7	0	0

Figure S116. Get High-res Image Clustering Approach #10: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #10: 'LYMPH.NODE.METASTASIS'

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

P value = 0.664 (Chi-square test), Q value = 1

Table S127. Clustering Approach #10: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #11: 'COMPLETENESS.OF.RESECTION'

nPatients	R0	R1	R2	RX
ALL	239	9	4	14
subtype1	77	1	2	6
subtype2	134	6	2	6
subtype3	28	2	0	2

Figure S117. Get High-res Image Clustering Approach #10: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #11: 'COMPLETENESS.OF.RESECTION'

'MIRSEQ CHIERARCHICAL' versus 'NEOPLASM.DISEASESTAGE'

P value = 0.162 (Chi-square test), Q value = 1

Table S128. Clustering Approach #10: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #13: 'NEOPLASM.DISEASESTAGE'

nPatients	STAGE I	STAGE IA	STAGE IB	STAGE IIA	STAGE IIB	STAGE IIIA	STAGE IIIB	STAGE IV
ALL	3	96	113	32	51	58	11	20
subtype1	0	43	31	9	20	19	1	8
subtype2	3	41	71	16	26	33	8	10
subtype3	0	12	11	7	5	6	2	2

Figure S118. Get High-res Image Clustering Approach #10: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #13: 'NEOPLASM.DISEASESTAGE'

Clustering Approach #11: 'MIRseq Mature CNMF subtypes'

Table S129. Get Full Table Description of clustering approach #11: 'MIRseq Mature CNMF subtypes'

Cluster Labels	1	2	3
Number of samples	128	137	58

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

P value = 0.119 (logrank test), Q value = 1

Table S130. Clustering Approach #11: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #1: 'Time to Death'

	nPatients	nDeath	Duration Range (Median), Month
ALL	289	65	0.0 - 224.0 (6.6)
subtype1	118	27	0.0 - 163.1 (9.6)
subtype2	119	27	0.0 - 83.8 (5.3)
subtype3	52	11	0.0 - 224.0 (5.3)

Figure S119. 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 = 0.109 (ANOVA), Q value = 1

Table S131. Clustering Approach #11: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #2: 'AGE'

	nPatients	Mean (Std.Dev)
ALL	295	65.1 (9.9)
subtype1	120	66.6 (9.8)
subtype2	124	64.3 (10.1)
subtype3	51	63.8 (9.5)

Figure S120. Get High-res Image Clustering Approach #11: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #2: 'AGE'

'MIRseq Mature CNMF subtypes' versus 'GENDER'

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

Table S132. Clustering Approach #11: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #3: 'GENDER'

nPatients	FEMALE	MALE
ALL	175	148
subtype1	70	58
subtype2	67	70
subtype3	38	20

Figure S121. Get High-res Image Clustering Approach #11: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #3: 'GENDER'

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

P value = 0.892 (ANOVA), Q value = 1

Table S133. Clustering Approach #11: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #4: 'KARNOFSKY.PERFORMANCE.SCORE'

	nPatients	Mean (Std.Dev)
ALL	22	74.5 (31.9)
subtype1	10	71.0 (38.4)
subtype2	9	76.7 (29.6)
subtype3	3	80.0 (20.0)

Figure S122. Get High-res Image Clustering Approach #11: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #4: 'KARNOFSKY.PERFORMANCE.SCORE'

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

P value = 0.0256 (Chi-square test), Q value = 1

Table S134. Clustering Approach #11: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #5: '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 SOLID PATTERN PREDOMINANT ADENOCARCINOMA	MUCINOUS (COLLOID) CARCINOMA
ALL	11	63	196	4	17	1	2	2	17	3	7
subtype1	4	33	66	2	9	0	1	2	8	0	3
subtype2	6	24	91	0	7	0	0	0	5	3	1
subtype3	1	6	39	2	1	1	1	0	4	0	3

Figure S123. Get High-res Image Clustering Approach #11: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #5: 'HISTOLOGICAL.TYPE'

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

P value = 0.942 (Fisher's exact test), Q value = 1

Table S135. Clustering Approach #11: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #6: 'RADIATIONS.RADIATION.REGIMENINDICATION'

nPatients	NO	YES
ALL	15	308
subtype1	6	122
subtype2	6	131
subtype3	3	55

Figure S124. Get High-res Image Clustering Approach #11: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #6: 'RADIATIONS.RADIATION.REGIMENINDICATION'

'MIRseq Mature CNMF subtypes' versus 'NUMBERPACKYEARSSMOKED'

P value = 0.239 (ANOVA), Q value = 1

Table S136. Clustering Approach #11: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #7: 'NUMBERPACKYEARSSMOKED'

	nPatients	Mean (Std.Dev)
ALL	225	40.5 (26.9)
subtype1	88	38.8 (27.2)
subtype2	99	43.8 (28.0)
subtype3	38	36.0 (22.6)

Figure S125. Get High-res Image Clustering Approach #11: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #7: 'NUMBERPACKYEARSSMOKED'

'MIRseq Mature CNMF subtypes' versus 'YEAROFTOBACCOSMOKINGONSET'

P value = 0.027 (ANOVA), Q value = 1

Table S137. Clustering Approach #11: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #8: 'YEAROFTOBACCOSMOKINGONSET'

	nPatients	Mean (Std.Dev)
ALL	182	1965.2 (12.3)
subtype1	70	1962.1 (12.3)
subtype2	84	1967.4 (12.0)
subtype3	28	1966.2 (11.9)

Figure S126. Get High-res Image Clustering Approach #11: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #8: 'YEAROFTOBACCOSMOKINGONSET'

'MIRseq Mature CNMF subtypes' versus 'DISTANT.METASTASIS'

P value = 0.413 (Chi-square test), Q value = 1

Table S138. Clustering Approach #11: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #9: 'DISTANT.METASTASIS'

nPatients	M0	M1	M1A	M1B	MX
ALL	200	11	1	3	104
subtype1	80	4	0	1	41
subtype2	91	5	1	2	37
subtype3	29	2	0	0	26

Figure S127. Get High-res Image Clustering Approach #11: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #9: 'DISTANT.METASTASIS'

'MIRseq Mature CNMF subtypes' versus 'LYMPH.NODE.METASTASIS'

P value = 0.519 (Chi-square test), Q value = 1

Table S139. Clustering Approach #11: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #10: 'LYMPH.NODE.METASTASIS'

nPatients	N0	N1	N2	N3	NX
ALL	208	57	49	1	6
subtype1	81	26	17	0	2
subtype2	95	19	19	1	3
subtype3	32	12	13	0	1

Figure S128. Get High-res Image Clustering Approach #11: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #10: 'LYMPH.NODE.METASTASIS'

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

P value = 0.672 (Chi-square test), Q value = 1

Table S140. Clustering Approach #11: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #11: 'COMPLETENESS.OF.RESECTION'

nPatients	R0	R1	R2	RX
ALL	187	7	1	12
subtype1	69	3	1	5
subtype2	89	2	0	4
subtype3	29	2	0	3

Figure S129. Get High-res Image Clustering Approach #11: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #11: 'COMPLETENESS.OF.RESECTION'

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

P value = 0.582 (Chi-square test), Q value = 1

Table S141. Clustering Approach #11: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #13: 'NEOPLASM.DISEASESTAGE'

nPatients	STAGE I	STAGE IA	STAGE IB	STAGE IIA	STAGE IIB	STAGE IIIA	STAGE IIIB	STAGE IV
ALL	3	81	93	29	41	49	9	16
subtype1	1	40	32	8	18	18	4	5
subtype2	2	30	47	15	14	19	3	7
subtype3	0	11	14	6	9	12	2	4

Figure S130. Get High-res Image Clustering Approach #11: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #13: 'NEOPLASM.DISEASESTAGE'

Clustering Approach #12: 'MIRseq Mature cHierClus subtypes'

Table S142. Get Full Table Description of clustering approach #12: 'MIRseq Mature cHierClus subtypes'

Cluster Labels	1	2	3
Number of samples	124	33	166

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

P value = 0.616 (logrank test), Q value = 1

Table S143. Clustering Approach #12: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #1: 'Time to Death'

	nPatients	nDeath	Duration Range (Median), Month
ALL	289	65	0.0 - 224.0 (6.6)
subtype1	112	25	0.0 - 163.1 (8.3)
subtype2	27	9	0.1 - 224.0 (4.8)
subtype3	150	31	0.0 - 88.1 (6.3)

Figure S131. 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 = 0.0829 (ANOVA), Q value = 1

Table S144. Clustering Approach #12: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #2: 'AGE'

	nPatients	Mean (Std.Dev)
ALL	295	65.1 (9.9)
subtype1	115	66.7 (9.6)
subtype2	27	64.4 (10.2)
subtype3	153	64.1 (10.0)

Figure S132. Get High-res Image Clustering Approach #12: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #2: 'AGE'

'MIRseq Mature cHierClus subtypes' versus 'GENDER'

P value = 0.0196 (Fisher's exact test), Q value = 1

Table S145. Clustering Approach #12: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #3: 'GENDER'

nPatients	FEMALE	MALE
ALL	175	148
subtype1	68	56
subtype2	25	8
subtype3	82	84

Figure S133. Get High-res Image Clustering Approach #12: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #3: 'GENDER'

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

P value = 0.491 (ANOVA), Q value = 1

Table S146. Clustering Approach #12: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #4: 'KARNOFSKY.PERFORMANCE.SCORE'

	nPatients	Mean (Std.Dev)
ALL	22	74.5 (31.9)
subtype1	10	68.0 (37.9)
subtype2	1	100.0 (NA)
subtype3	11	78.2 (26.8)

Figure S134. Get High-res Image Clustering Approach #12: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #4: 'KARNOFSKY.PERFORMANCE.SCORE'

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

P value = 0.0216 (Chi-square test), Q value = 1

Table S147. Clustering Approach #12: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #5: '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 SOLID PATTERN PREDOMINANT ADENOCARCINOMA	MUCINOUS (COLLOID) CARCINOMA
ALL	11	63	196	4	17	1	2	2	17	3	7
subtype1	5	27	64	2	10	0	1	2	8	0	5
subtype2	1	3	22	2	0	0	1	0	3	0	1
subtype3	5	33	110	0	7	1	0	0	6	3	1

Figure S135. Get High-res Image Clustering Approach #12: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #5: 'HISTOLOGICAL.TYPE'

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

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

Table S148. Clustering Approach #12: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #6: 'RADIATIONS.RADIATION.REGIMENINDICATION'

nPatients	NO	YES
ALL	15	308
subtype1	6	118
subtype2	1	32
subtype3	8	158

Figure S136. Get High-res Image Clustering Approach #12: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #6: 'RADIATIONS.RADIATION.REGIMENINDICATION'

'MIRseq Mature cHierClus subtypes' versus 'NUMBERPACKYEARSSMOKED'

P value = 0.177 (ANOVA), Q value = 1

Table S149. Clustering Approach #12: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #7: 'NUMBERPACKYEARSSMOKED'

	nPatients	Mean (Std.Dev)
ALL	225	40.5 (26.9)
subtype1	82	38.4 (25.8)
subtype2	19	32.4 (22.0)
subtype3	124	43.2 (28.1)

Figure S137. Get High-res Image Clustering Approach #12: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #7: 'NUMBERPACKYEARSSMOKED'

'MIRseq Mature cHierClus subtypes' versus 'YEAROFTOBACCOSMOKINGONSET'

P value = 0.0498 (ANOVA), Q value = 1

Table S150. Clustering Approach #12: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #8: 'YEAROFTOBACCOSMOKINGONSET'

	nPatients	Mean (Std.Dev)
ALL	182	1965.2 (12.3)
subtype1	70	1962.4 (11.7)
subtype2	13	1966.5 (15.2)
subtype3	99	1967.0 (12.0)

Figure S138. Get High-res Image Clustering Approach #12: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #8: 'YEAROFTOBACCOSMOKINGONSET'

'MIRseq Mature cHierClus subtypes' versus 'DISTANT.METASTASIS'

P value = 0.683 (Chi-square test), Q value = 1

Table S151. Clustering Approach #12: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #9: 'DISTANT.METASTASIS'

nPatients	M0	M1	M1A	M1B	MX
ALL	200	11	1	3	104
subtype1	74	3	0	1	44
subtype2	24	2	0	0	6
subtype3	102	6	1	2	54

Figure S139. Get High-res Image Clustering Approach #12: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #9: 'DISTANT.METASTASIS'

'MIRseq Mature cHierClus subtypes' versus 'LYMPH.NODE.METASTASIS'

P value = 0.0757 (Chi-square test), Q value = 1

Table S152. Clustering Approach #12: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #10: 'LYMPH.NODE.METASTASIS'

nPatients	N0	N1	N2	N3	NX
ALL	208	57	49	1	6
subtype1	76	27	15	0	4
subtype2	16	10	7	0	0
subtype3	116	20	27	1	2

Figure S140. Get High-res Image Clustering Approach #12: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #10: 'LYMPH.NODE.METASTASIS'

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

P value = 0.497 (Chi-square test), Q value = 1

Table S153. Clustering Approach #12: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #11: 'COMPLETENESS.OF.RESECTION'

nPatients	R0	R1	R2	RX
ALL	187	7	1	12
subtype1	65	2	1	7
subtype2	21	1	0	0
subtype3	101	4	0	5

Figure S141. Get High-res Image Clustering Approach #12: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #11: 'COMPLETENESS.OF.RESECTION'

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

P value = 0.645 (Chi-square test), Q value = 1

Table S154. Clustering Approach #12: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #13: 'NEOPLASM.DISEASESTAGE'

nPatients	STAGE I	STAGE IA	STAGE IB	STAGE IIA	STAGE IIB	STAGE IIIA	STAGE IIIB	STAGE IV
ALL	3	81	93	29	41	49	9	16
subtype1	0	37	31	11	18	17	2	6
subtype2	0	8	7	5	3	7	1	2
subtype3	3	36	55	13	20	25	6	8

Figure S142. Get High-res Image Clustering Approach #12: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #13: 'NEOPLASM.DISEASESTAGE'

Methods & Data

Input

Cluster data file = LUAD-TP.mergedcluster.txt
Clinical data file = LUAD-TP.clin.merged.picked.txt
Number of patients = 393
Number of clustering approaches = 12
Number of selected clinical features = 13
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

ANOVA analysis

For continuous numerical clinical features, one-way analysis of variance (Howell 2002) was applied to compare the clinical values between tumor subtypes using 'anova' 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

Chi-square test

For multi-class clinical features (nominal or ordinal), Chi-square tests (Greenwood and Nikulin 1996) were used to estimate the P values using the 'chisq.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

This is an experimental feature. The full results of the analysis summarized in this report can be downloaded from the TCGA Data Coordination Center.

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] Howell, D, Statistical Methods for Psychology. (5th ed.), Duxbury Press:324-5 (2002)

[5] 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)

[6] Greenwood and Nikulin, A guide to chi-squared testing, Wiley, New York. ISBN 047155779X (1996)

[7] 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