Changes in e478531: add ref

				Supplemental_Methods_and_Results.md
			
          @@ -59,7 +59,7 @@ We used another approach to assess the reproducibility of the Zhang study. In th

           ## Potential contribution of rare germline variants

          -As detailed in Supplemental Table S5, many of the studies contributing to our gene lists did not have matched germline DNA from every sample. It has been shown that some genes have disproportionately higher numbers of rare germline variants. The genes with the highest number of rare variants overall have been described in a recent study as FrequentLy mutAted GeneS (FLAGS). These genes should be considered with caution in any study that associates them with a phenotype. Insufficient removal of germline variants in the studies explored herein could explain some of the genes in Tiers 2 and 3. To evaluate this, we used the ranking of the frequency of rare mutations in all genes covered by common exome panels. This "FLAGS rank" assignes the lowest rank to genes with the highest number of rare variants (e.g. TTN = 1, MUC16 = 2, OBSCN = 3, etc). We used the distribution of ranks across the three tiers of DLBCL genes to evaluate the relative extent to which the genes on each list may be explained, in part, by inadequate removal of rare germline variants. If there is no influence on genes, the FLAGS_rank is expected to follow a uniform distribution. Accordingly, we compared each of the four gene lists to a uniform distribution using a negative binomial regression. Interestingly, the distributions of FLAGS_rank for Tier 2 and Tier 3 and the CGC genes were significantly different than the uniform distribution. In contrast, the distribution for Tier 1 genes was not significantly different from a uniform distribution. This is consistent with the Tier 1 DLBCL genes having minimal contamination of genes due to rare germline variants. To evaluate whether the separation of genes into Tiers 2 and 3 offers some benefit in this regard, we compared the Tier 2 DLBCL genes to the other lists. Indeed, Tier 2 showed a significant difference when compared to Tier 3 (P=3.86e-06). Based on this, we conclude that the Tier 3 gene list is dominated by FLAGS whereas Tier 2 represents a mixture of true DLBCL genes and FLAGS. 

          +As detailed in Supplemental Table S5, many of the studies contributing to our gene lists did not have matched germline DNA from every sample. It has been shown that some genes have disproportionately higher numbers of rare germline variants. The genes with the highest number of rare variants overall have been described in a recent study as FrequentLy mutAted GeneS (FLAGS)(@shyrFLAGSFrequentlyMutated2014). These genes should be considered with caution in any study that associates them with a phenotype. Insufficient removal of germline variants in the studies explored herein could explain some of the genes in Tiers 2 and 3. To evaluate this, we used the ranking of the frequency of rare mutations in all genes covered by common exome panels. This "FLAGS rank" assignes the lowest rank to genes with the highest number of rare variants (e.g. TTN = 1, MUC16 = 2, OBSCN = 3, etc). We used the distribution of ranks across the three tiers of DLBCL genes to evaluate the relative extent to which the genes on each list may be explained, in part, by inadequate removal of rare germline variants. If there is no influence on genes, the FLAGS_rank is expected to follow a uniform distribution. Accordingly, we compared each of the four gene lists to a uniform distribution using a negative binomial regression. Interestingly, the distributions of FLAGS_rank for Tier 2 and Tier 3 and the CGC genes were significantly different than the uniform distribution. In contrast, the distribution for Tier 1 genes was not significantly different from a uniform distribution. This is consistent with the Tier 1 DLBCL genes having minimal contamination of genes due to rare germline variants. To evaluate whether the separation of genes into Tiers 2 and 3 offers some benefit in this regard, we compared the Tier 2 DLBCL genes to the other lists. Indeed, Tier 2 showed a significant difference when compared to Tier 3 (P=3.86e-06). Based on this, we conclude that the Tier 3 gene list is dominated by FLAGS whereas Tier 2 represents a mixture of true DLBCL genes and FLAGS. 

           <figure>

           <img src="FLAGS_rank_boxplot.png" alt="flags1" style="width:500px;"/>

          @@ -928,3 +928,5 @@ Average rating: &starf; &starf; &starf; &star; &star;

           <div style="page-break-after: always;"></div>

          +## References

          +

				morinlab.bib
			
          @@ -1,3 +1,21 @@

          +@article{shyrFLAGSFrequentlyMutated2014,

          +	title = {{FLAGS}, frequently mutated genes in public exomes},

          +	volume = {7},

          +	issn = {1755-8794},

          +	url = {https://doi.org/10.1186/s12920-014-0064-y},

          +	doi = {10.1186/s12920-014-0064-y},

          +	abstract = {Dramatic improvements in DNA-sequencing technologies and computational analyses have led to wide use of whole exome sequencing (WES) to identify the genetic basis of Mendelian disorders. More than 180 novel rare-disease-causing genes with Mendelian inheritance patterns have been discovered through sequencing the exomes of just a few unrelated individuals or family members. As rare/novel genetic variants continue to be uncovered, there is a major challenge in distinguishing true pathogenic variants from rare benign mutations.},

          +	number = {1},

          +	urldate = {2024-11-21},

          +	journal = {BMC Medical Genomics},

          +	author = {Shyr, Casper and Tarailo-Graovac, Maja and Gottlieb, Michael and Lee, Jessica JY and van Karnebeek, Clara and Wasserman, Wyeth W.},

          +	month = dec,

          +	year = {2014},

          +	keywords = {Whole Exome Sequencing, Exome Sequencing, Exome Variant Server, Open Reading Frame Length, Rare Variant},

          +	pages = {64},

          +	file = {Full Text PDF:/Users/rmorin/Zotero/storage/9MJ4B8NY/Shyr et al. - 2014 - FLAGS, frequently mutated genes in public exomes.pdf:application/pdf},

          +}

          +

           @article{miloudiXPO1E571KMutationModifies2020,

             title = {{{XPO1E571K Mutation Modifies Exportin}} 1 {{Localisation}} and {{Interactome}} in {{B-cell Lymphoma}}},

             author = {Miloudi, Hadjer and Bohers, Élodie and Guillonneau, François and Taly, Antoine and Gibouin, Vincent Cabaud and Viailly, Pierre-Julien and Jego, Gaëtan and Grumolato, Luca and Jardin, Fabrice and Sola, Brigitte},

...	...	@@ -59,7 +59,7 @@ We used another approach to assess the reproducibility of the Zhang study. In th
59	59
60	60	## Potential contribution of rare germline variants
61	61
62		-As detailed in Supplemental Table S5, many of the studies contributing to our gene lists did not have matched germline DNA from every sample. It has been shown that some genes have disproportionately higher numbers of rare germline variants. The genes with the highest number of rare variants overall have been described in a recent study as FrequentLy mutAted GeneS (FLAGS). These genes should be considered with caution in any study that associates them with a phenotype. Insufficient removal of germline variants in the studies explored herein could explain some of the genes in Tiers 2 and 3. To evaluate this, we used the ranking of the frequency of rare mutations in all genes covered by common exome panels. This "FLAGS rank" assignes the lowest rank to genes with the highest number of rare variants (e.g. TTN = 1, MUC16 = 2, OBSCN = 3, etc). We used the distribution of ranks across the three tiers of DLBCL genes to evaluate the relative extent to which the genes on each list may be explained, in part, by inadequate removal of rare germline variants. If there is no influence on genes, the FLAGS_rank is expected to follow a uniform distribution. Accordingly, we compared each of the four gene lists to a uniform distribution using a negative binomial regression. Interestingly, the distributions of FLAGS_rank for Tier 2 and Tier 3 and the CGC genes were significantly different than the uniform distribution. In contrast, the distribution for Tier 1 genes was not significantly different from a uniform distribution. This is consistent with the Tier 1 DLBCL genes having minimal contamination of genes due to rare germline variants. To evaluate whether the separation of genes into Tiers 2 and 3 offers some benefit in this regard, we compared the Tier 2 DLBCL genes to the other lists. Indeed, Tier 2 showed a significant difference when compared to Tier 3 (P=3.86e-06). Based on this, we conclude that the Tier 3 gene list is dominated by FLAGS whereas Tier 2 represents a mixture of true DLBCL genes and FLAGS.
	62	+As detailed in Supplemental Table S5, many of the studies contributing to our gene lists did not have matched germline DNA from every sample. It has been shown that some genes have disproportionately higher numbers of rare germline variants. The genes with the highest number of rare variants overall have been described in a recent study as FrequentLy mutAted GeneS (FLAGS)(@shyrFLAGSFrequentlyMutated2014). These genes should be considered with caution in any study that associates them with a phenotype. Insufficient removal of germline variants in the studies explored herein could explain some of the genes in Tiers 2 and 3. To evaluate this, we used the ranking of the frequency of rare mutations in all genes covered by common exome panels. This "FLAGS rank" assignes the lowest rank to genes with the highest number of rare variants (e.g. TTN = 1, MUC16 = 2, OBSCN = 3, etc). We used the distribution of ranks across the three tiers of DLBCL genes to evaluate the relative extent to which the genes on each list may be explained, in part, by inadequate removal of rare germline variants. If there is no influence on genes, the FLAGS_rank is expected to follow a uniform distribution. Accordingly, we compared each of the four gene lists to a uniform distribution using a negative binomial regression. Interestingly, the distributions of FLAGS_rank for Tier 2 and Tier 3 and the CGC genes were significantly different than the uniform distribution. In contrast, the distribution for Tier 1 genes was not significantly different from a uniform distribution. This is consistent with the Tier 1 DLBCL genes having minimal contamination of genes due to rare germline variants. To evaluate whether the separation of genes into Tiers 2 and 3 offers some benefit in this regard, we compared the Tier 2 DLBCL genes to the other lists. Indeed, Tier 2 showed a significant difference when compared to Tier 3 (P=3.86e-06). Based on this, we conclude that the Tier 3 gene list is dominated by FLAGS whereas Tier 2 represents a mixture of true DLBCL genes and FLAGS.
63	63
64	64	<figure>
65	65	<img src="FLAGS_rank_boxplot.png" alt="flags1" style="width:500px;"/>
...	...	@@ -928,3 +928,5 @@ Average rating: &starf; &starf; &starf; &star; &star;
928	928
929	929	<div style="page-break-after: always;"></div>
930	930
	931	+## References
	932	+

...	...	@@ -1,3 +1,21 @@
	1	+@article{shyrFLAGSFrequentlyMutated2014,
	2	+ title = {{FLAGS}, frequently mutated genes in public exomes},
	3	+ volume = {7},
	4	+ issn = {1755-8794},
	5	+ url = {https://doi.org/10.1186/s12920-014-0064-y},
	6	+ doi = {10.1186/s12920-014-0064-y},
	7	+ abstract = {Dramatic improvements in DNA-sequencing technologies and computational analyses have led to wide use of whole exome sequencing (WES) to identify the genetic basis of Mendelian disorders. More than 180 novel rare-disease-causing genes with Mendelian inheritance patterns have been discovered through sequencing the exomes of just a few unrelated individuals or family members. As rare/novel genetic variants continue to be uncovered, there is a major challenge in distinguishing true pathogenic variants from rare benign mutations.},
	8	+ number = {1},
	9	+ urldate = {2024-11-21},
	10	+ journal = {BMC Medical Genomics},
	11	+ author = {Shyr, Casper and Tarailo-Graovac, Maja and Gottlieb, Michael and Lee, Jessica JY and van Karnebeek, Clara and Wasserman, Wyeth W.},
	12	+ month = dec,
	13	+ year = {2014},
	14	+ keywords = {Whole Exome Sequencing, Exome Sequencing, Exome Variant Server, Open Reading Frame Length, Rare Variant},
	15	+ pages = {64},
	16	+ file = {Full Text PDF:/Users/rmorin/Zotero/storage/9MJ4B8NY/Shyr et al. - 2014 - FLAGS, frequently mutated genes in public exomes.pdf:application/pdf},
	17	+}
	18	+
1	19	@article{miloudiXPO1E571KMutationModifies2020,
2	20	title = {{{XPO1E571K Mutation Modifies Exportin}} 1 {{Localisation}} and {{Interactome}} in {{B-cell Lymphoma}}},
3	21	author = {Miloudi, Hadjer and Bohers, Élodie and Guillonneau, François and Taly, Antoine and Gibouin, Vincent Cabaud and Viailly, Pierre-Julien and Jego, Gaëtan and Grumolato, Luca and Jardin, Fabrice and Sola, Brigitte},