COSG

tools/cosg/.shed.yml

@@ -0,0 +1,11 @@
+name: cosg
+owner: iuc
+description: "Marker gene identification for single-cell sequencing data using COSG."
+homepage_url: https://github.com/genecell/COSG
+long_description: |
+    Accurate and fast cell marker gene identification with COSG. COSG is a cosine similarity-based method for more accurate and scalable marker gene identification.
+remote_repository_url: https://github.com/galaxyproject/tools-iuc/tree/master/tools/cosg/
+type: unrestricted
+categories:
+- Transcriptomics
+- Sequence Analysis

tools/cosg/cosg.xml

@@ -0,0 +1,174 @@
+<tool id="cosg" name="Cell marker gene identification" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="@profile@">
+    <description>with COSG</description>
+    <macros>
+        <import>macros.xml</import>
+    </macros>
+    <expand macro="requirements">
+    </expand>
+    <expand macro="version_command"/>
+    <command detect_errors="exit_code"><![CDATA[
+@CMD@
+      ]]></command>
+    <configfiles>
+        <configfile name="script_file"><![CDATA[
+@CMD_imports@
+@CMD_read_inputs@
+
+#if $method_options.groups != 'all'
+    #set $method_options.groups=[$groups]
+#end if
+
+cosg.cosg(adata,
+        groupby='$method_options.groupby',
+        groups='$method_options.groups',
+        n_genes_user=$method_options.n_genes_user,
+        mu=$advanced_options.mu,   
+        remove_lowly_expressed=$advanced_options.filter_expression.remove_lowly_expressed,
+        #if $advanced_options.filter_expression.remove_lowly_expressed == "True"
+        expressed_pct=$advanced_options.filter_expression.expressed_pct,  
+        #end ifs
+        key_added='$advanced_options.key_added',
+        use_raw=$advanced_options.layer_selection.use_raw,
+        #if $advanced_options.layer_selection.use_raw == "False"
+        #if $advanced_options.layer_selection.layer
+        layer='$advanced_options.layer_selection.layer',
+        #end if
+        #end if
+        reference='$advanced_options.reference'
+        )
+
+df=pd.DataFrame(adata.uns['cosg']['names']).T
+df.to_csv('marker.tsv', sep='\t', index=True)
+
+@CMD_anndata_write_outputs@
+]]></configfile>
+    </configfiles>
+    <inputs>
+        <expand macro="inputs_anndata"/>
+        <section name="method_options" title="Method Options" expanded="true">
+            <param argument="groupby" type="text" value="" optional="false" label="The key of the cell groups in .obs."/>
+            <param argument="groups" type="text" value="all" optional="false" label="Subset of cell groups" help="e.g. 'g1','g2','g3'."/>
+            <param argument="n_genes_user" type="integer" value="50" label="The number of genes that appear in the returned tables."/>
+        </section>
+        <section name="advanced_options" title="Advanced Options">
+            <param argument="mu" type="float" value="1.0" label="The penalty restricting marker genes expressing in non-target cell groups." help="Larger value represents more strict restrictions. mu should be >= 0, and by default, mu = 1."/>
+            <conditional name="filter_expression">
+                <param name="remove_lowly_expressed" type="select" label="Remove lowly expressed genes" help="If yes, genes that express a percentage of target cells smaller than a specific value (`expressed_pct`) are not considered as marker genes for the target cells.">
+                    <option value="False">No</option>
+                    <option value="True">Yes</option>
+                </param>
+                <when value="False"/>
+                <when value="True">
+                    <param argument="expressed_pct" type="float" value="0.1" label="Percentage of target cells" help="Genes that express a percentage of target cells smaller than a specific value (`expressed_pct`) are not considered as marker genes for the target cells."/>
+                </when>
+            </conditional>
+            <param argument="key_added" type="text" value="cosg" optional="false" label="The key in adata.uns information is saved to."/>
+            <conditional name="layer_selection">
+                <param name="use_raw" type="select" label="Use raw attribute of adata if present to perform tests on." help="If use_raw is set to True then adata.raw.X if it exists.">
+                    <option value="False">No</option>
+                    <option value="True">Yes</option>
+                </param>
+                <when value="False">
+                    <param argument="layer" type="text" value="" label="Key from adata.layers whose value will be used to perform tests on." help="If empty then adata.X will be used. If use_raw is set to True then adata.raw.X. If layers specified then use adata.layers[layer]."/>
+                </when>
+                <when value="True"/>
+            </conditional>
+            <param argument="reference" type="text" value="rest" optional="false" label="If a group identifier, compare with respect to this group." help=" If you use the keyword 'rest', compare each group to the union of the rest of the group."/>
+        </section>
+        <expand macro="inputs_common_advanced"/>
+    </inputs>
+    <outputs>
+        <expand macro="anndata_outputs"/>
+        <data name="marker_out" format="tsv" from_work_dir="marker.tsv" label="${tool.name} on ${on_string}: Markers"/>
+    </outputs>
+    <tests>
+        <test expect_num_outputs="3">
+            <!-- test 1 -->
+            <param name="adata" value="tl.rank_genes_groups.newton-cg.pbmc68k_reduced.h5ad" />
+            <param name="groupby" value="bulk_labels"/>
+            <section name="advanced_common">
+                <param name="show_log" value="true" />
+            </section>
+            <output name="hidden_output">
+                <assert_contents>
+                    <has_text_matching expression="cosg.cosg"/>
+                    <has_text_matching expression="groupby='bulk_labels'"/>
+                    <has_text_matching expression="groups='all'"/>
+                    <has_text_matching expression="n_genes_user=50"/>
+                    <has_text_matching expression="mu=1.0"/>
+                    <has_text_matching expression="remove_lowly_expressed=False"/>
+                    <has_text_matching expression="key_added='cosg'"/>
+                    <has_text_matching expression="use_raw=False"/>
+                    <has_text_matching expression="reference='rest'"/>
+                </assert_contents>
+            </output>
+            <output name="anndata_out" file="cosg.rank_genes_groups.newton-cg.pbmc68k_reduced_1.h5ad" ftype="h5ad" compare="sim_size"/>
+            <output name="marker_out" file="marker_1.tsv" ftype="tsv" compare="sim_size"/>
+        </test>
+        <test expect_num_outputs="3">
+            <!-- test 2 -->
+            <param name="adata" value="tl.rank_genes_groups.newton-cg.pbmc68k_reduced.h5ad" />
+            <param name="groupby" value="louvain"/>
+            <param name="remove_lowly_expressed" value="True" />
+            <section name="advanced_common">
+                <param name="show_log" value="true" />
+            </section>
+            <output name="hidden_output">
+                <assert_contents>
+                    <has_text_matching expression="cosg.cosg"/>
+                    <has_text_matching expression="groupby='louvain'"/>
+                    <has_text_matching expression="groups='all'"/>
+                    <has_text_matching expression="n_genes_user=50"/>
+                    <has_text_matching expression="mu=1.0"/>
+                    <has_text_matching expression="remove_lowly_expressed=True"/>
+                    <has_text_matching expression="expressed_pct=0.1"/>
+                    <has_text_matching expression="key_added='cosg'"/>
+                    <has_text_matching expression="use_raw=False"/>
+                    <has_text_matching expression="reference='rest'"/>
+                </assert_contents>
+            </output>
+            <output name="anndata_out" file="cosg.rank_genes_groups.newton-cg.pbmc68k_reduced_2.h5ad" ftype="h5ad" compare="sim_size"/>
+            <output name="marker_out" file="marker_2.tsv" ftype="tsv" compare="sim_size"/>
+        </test>
+        <test expect_num_outputs="3">
+            <!-- test 3 -->
+            <param name="adata" value="tl.rank_genes_groups.newton-cg.pbmc68k_reduced.h5ad" />
+            <param name="groupby" value="bulk_labels"/>
+            <param name="use_raw" value="True"/>
+            <section name="advanced_common">
+                <param name="show_log" value="true" />
+            </section>
+            <output name="hidden_output">
+                <assert_contents>
+                    <has_text_matching expression="cosg.cosg"/>
+                    <has_text_matching expression="groupby='bulk_labels'"/>
+                    <has_text_matching expression="groups='all'"/>
+                    <has_text_matching expression="n_genes_user=50"/>
+                    <has_text_matching expression="mu=1.0"/>
+                    <has_text_matching expression="remove_lowly_expressed=False"/>
+                    <has_text_matching expression="key_added='cosg'"/>
+                    <has_text_matching expression="use_raw=True"/>
+                    <has_text_matching expression="reference='rest'"/>
+                </assert_contents>
+            </output>
+            <output name="anndata_out" file="cosg.rank_genes_groups.newton-cg.pbmc68k_reduced_3.h5ad" ftype="h5ad" compare="sim_size"/>
+            <output name="marker_out" file="marker_3.tsv" ftype="tsv" compare="sim_size"/>
+        </test>
+    </tests>
+    <help><![CDATA[
+Marker gene identification for single-cell sequencing data using COSG.
+============================================================================================================
+
+Accurate and fast cell marker gene identification with COSG
+
+COSG is a cosine similarity-based method for more accurate and scalable marker gene identification.
+
+- COSG is a general method for cell marker gene identification across different data modalities, e.g., scRNA-seq, scATAC-seq and spatially resolved transcriptome data. 
+- Marker genes or genomic regions identified by COSG are more indicative and with greater cell-type specificity.
+- COSG is ultrafast for large-scale datasets, and is capable of identifying marker genes for one million cells in less than two minutes.
+
+Here is the R version for COSG, and the python version is hosted in https://github.com/genecell/COSG.
+
+    ]]></help>
+    <expand macro="citations"/>
+</tool>

tools/cosg/macros.xml

@@ -0,0 +1,85 @@
+<macros>
+    <token name="@TOOL_VERSION@">1.0.1</token>
+    <token name="@VERSION_SUFFIX@">1</token>
+    <token name="@profile@">22.05</token>
+    <xml name="requirements">
+        <requirements>
+            <requirement type="package" version="@TOOL_VERSION@">cosg</requirement>
+            <requirement type="package" version="1.9.8">scanpy</requirement>
+            <requirement type="package" version="1.5.3">pandas</requirement>
+            <requirement type="package" version="3.7">matplotlib</requirement>
+            <requirement type="package" version="0.12.2">seaborn</requirement>
+            <yield />
+        </requirements>
+    </xml>
+    <xml name="creators">
+        <creator>
+            <organization name="European Galaxy Team" url="https://galaxyproject.org/eu/" />
+        </creator>
+    </xml>
+    <xml name="citations">
+        <citations>
+            <citation type="doi">10.1093/bib/bbab579</citation>
+            <citation type="doi">10.1093/gigascience/giaa102</citation>
+        </citations>
+    </xml>
+    <xml name="version_command">
+        <version_command><![CDATA[python -c "import cosg;print('cosg version: @TOOL_VERSION@')"]]></version_command>
+    </xml>
+    <token name="@CMD@"><![CDATA[
+cp '$adata' 'anndata.h5ad' &&
+cat '$script_file' > '$hidden_output' &&
+python '$script_file' >> '$hidden_output' &&
+ls . >> '$hidden_output' &&
+touch 'anndata_info.txt' &&
+cat 'anndata_info.txt' @CMD_prettify_stdout@
+    ]]>
+    </token>
+    <token name="@CMD_imports@"><![CDATA[
+import scanpy as sc
+import pandas as pd
+import numpy as np
+import cosg
+    ]]>
+    </token>
+    <xml name="sanitize_query" token_validinitial="string.printable">
+        <sanitizer>
+            <valid initial="@VALIDINITIAL@">
+                <remove value="&apos;" />
+            </valid>
+       </sanitizer>
+    </xml>
+    <xml name="sanitize_vectors" token_validinitial="string.digits">
+        <sanitizer>
+            <valid initial="@VALIDINITIAL@">
+                <add value=","/>
+            </valid>
+        </sanitizer>
+    </xml>
+    <xml name="inputs_anndata">
+        <param name="adata" type="data" format="h5ad" label="Annotated data matrix"/>
+    </xml>
+    <token name="@CMD_read_inputs@"><![CDATA[
+adata = sc.read_h5ad('anndata.h5ad')
+]]>
+    </token>
+    <xml name="inputs_common_advanced">
+        <section name="advanced_common" title="Advanced Output Options" expanded="false">
+            <param name="show_log" type="boolean" checked="false" label="Output Log?" />
+        </section>
+    </xml>
+    <xml name="anndata_outputs">
+        <data name="anndata_out" format="h5ad" from_work_dir="anndata.h5ad" label="${tool.name} on ${on_string}: Annotated data matrix"/>
+            <data name="hidden_output" format="txt" label="Log file" >
+            <filter>advanced_common['show_log']</filter>
+        </data>
+    </xml>
+    <token name="@CMD_anndata_write_outputs@"><![CDATA[
+adata.write_h5ad('anndata.h5ad')
+with open('anndata_info.txt','w', encoding='utf-8') as ainfo:
+    print(adata, file=ainfo)
+]]>
+    </token>
+    <token name="@CMD_prettify_stdout@"><![CDATA[ | sed -r '1 s|AnnData object with (.+) = (.*)\s*|\1: \2|g' | sed "s|'||g"  | sed -r 's|^\s*(.*):\s(.*)|[\1]\n-    \2|g' | sed 's|, |\n-    |g'
+    ]]></token>
+</macros>

tools/cosg/test-data/marker_1.tsv

@@ -0,0 +1,11 @@
+	0	1	2	3	4	5	6	7	8	9	10	11	12	13	14	15	16	17	18	19	20	21	22	23	24	25	26	27	28	29	30	31	32	33	34	35	36	37	38	39	40	41	42	43	44	45	46	47	48	49
+CD14+ Monocyte	FCGR3A	PSAP	FTL	CTSS	AIF1	RP11-290F20.3	TMEM176B	SAT1	CEBPB	CFD	FCER1G	SERPINA1	LST1	CD68	S100A11	HCK	TYROBP	MS4A7	DUSP1	STXBP2	OAZ1	PILRA	FCN1	FTH1	NPC2	IFITM3	SPI1	IFITM2	COTL1	S100A4	CFP	SESN2	MPP1	NFE2	PCIF1	FCGRT	GALE	PFN1	CORO1B	GSTP1	RP11-390E23.6	FOS	EAF2	CST3	SOX4	UBE2J1	MNDA	VIMP	FAM101B	ARHGDIB
+CD19+ B	CD79A	CD79B	MS4A1	TNFRSF13B	SMARCB1	BLK	BANK1	PDLIM1	FCRLA	NCF1	TPD52	SPIB	POU2AF1	AL928768.3	TNFRSF17	CCDC50	PNOC	SUB1	ISG20	IGJ	GNG7	MZB1	PLAC8	KIAA0125	IGLL5	PEBP1	DERL3	FKBP11	LTB	SSR4	XBP1	RPLP1	UBE2J1	EAF2	PTPRCAP	VIMP	SSR3	MANF	CD52	LY86	RPL3	RPSA	RPLP0	FAM63B	HLA-DMB	SNHG7	ETV2	ALOX5AP	CD27	RP3-467N11.1
+CD34+	PRSS57	CYTL1	EGFL7	C19orf77	SPINK2	RP11-620J15.3	SNHG7	SOX4	SERPINB1	NFE2	SYPL1	EGR1	CDK6	NGFRAP1	IL1B	RPLP0	KIAA0125	NUCB2	H1FX	SPINT2	HMGA1	RPS3	MPP1	RP3-467N11.1	C1orf228	RPL3	MPHOSPH9	RNF34	RSBN1L-AS1	LDHB	ATXN7L3B	IGFBP7	RPLP1	JUN	RPSA	FAM63B	TRIM39	SESN2	GYPC	CHD4	ACOX1	RNF138	FAM101B	PRKCQ-AS1	STMN1	SELL	CTSW	PDLIM1	PEBP1	MATK
+CD4+/CD25 T Reg	ACTG1	ARHGDIB	AQP3	SIT1	LAT	CD2	AES	CD3D	CD3E	SPOCK2	CORO1B	CD27	IL32	LCK	SELL	ITM2A	LDHB	S1PR4	NOSIP	CD52	GIMAP4	FYB	TMSB10	SEPT1	GYPC	ADTRP	LY9	CD99	GIMAP7	CD3G	FLT3LG	PRKCQ-AS1	PTPRCAP	TTC39C	GIMAP5	RPSA	PFN1	RAB3IP	MAL	TSHZ2	IL7R	NGFRAP1	CD247	BTG1	B2M	LTB	CCR7	RPS3	DENND2D	GPR171
+CD4+/CD45RA+/CD25- Naive T	EAF2	SSR3	SSR4	DERL3	MZB1	UBE2J1	IGLL5	VIMP	RP3-467N11.1	XBP1	GNG7	CALR	IGJ	MANF	FKBP11	AL928768.3	TNFRSF17	PEBP1	SUB1	POU2AF1	ISG20	CD27	ATXN7L3B	CD79A	CDK6	TNFRSF13B	NCF1	MAL	RPLP0	LY9	RPLP1	SIT1	RPL3	KIAA0125	EXOG	B2M	GYPC	ITM2A	PNOC	SMARCB1	HCST	PTPRCAP	AQP3	GZMA	GZMM	AES	SEPT1	GIMAP7	RNF34	GPX1
+CD4+/CD45RO+ Memory	CHD4	TSHZ2	NOSIP	RNF138	LINC00402	SEPT1	ITM2A	LCK	SIT1	ACTG1	CD3E	CORO1B	CD52	AQP3	LDHB	SELL	GZMK	CALR	IL32	EXOG	ARHGDIB	ALOX5AP	GIMAP5	CD99	TTC39C	CD2	GIMAP4	PFN1	GIMAP7	RAB3IP	GYPC	RPSA	AES	IFITM1	RPS3	CD3D	NUCB2	RPLP0	MAL	S1PR4	LAT	DENND2D	STK17A	RARRES3	RP3-467N11.1	IL7R	HCST	B2M	CD3G	TMSB10
+CD56+ NK	CLIC3	SPON2	CTSW	CD7	GZMB	GNLY	MATK	PRF1	NKG7	IGFBP7	CST7	CD247	HOPX	KLRC2	GZMA	STMN1	GZMM	CD63	IFITM1	STK17A	FGFBP2	GZMH	C9orf142	ALOX5AP	RARRES3	PLAC8	NUCB2	PFN1	CALR	DENND2D	HCST	CD99	PAXBP1	CCL5	B2M	IFITM2	XBP1	RP11-473M20.7	SEPT1	PTPRCAP	PCIF1	GIMAP7	RNF34	SYPL1	CCDC163P	GZMK	RPSA	GYPC	PRKCQ-AS1	SELL
+CD8+ Cytotoxic T	CCL5	GZMH	HCST	CD8A	GZMA	FGFBP2	FAM101B	GZMK	NKG7	HOPX	B2M	IL32	CD3G	CST7	GPR171	TRIM39	CD8B	GNLY	GZMM	RARRES3	PRF1	CD3D	JUN	C9orf142	EXOG	GZMB	CTSW	CD99	CD2	LCK	LY9	IFITM1	PTPRCAP	CD3E	DENND2D	BTG1	FLT3LG	MATK	LINC00402	LAT	RPS3	CD247	RPL3	GIMAP7	NUCB2	RPSA	STK17A	MPHOSPH9	RNF34	CCDC132
+CD8+/CD45RA+ Naive Cytotoxic	RP11-291B21.2	CD8B	CCR7	CCDC163P	PRKCQ-AS1	CD8A	C1orf228	GIMAP5	IL7R	LDHB	MAL	RPS3	RPL3	GIMAP7	NOSIP	JUN	CD3E	AES	BTG1	ATXN7L3B	CD27	CD3D	RPSA	TTC39C	CD3G	LINC00402	LCK	GZMM	SPOCK2	GZMK	FLT3LG	FYB	GYPC	GALE	NGFRAP1	CD7	STK17A	HCST	IL32	LTB	RAB3IP	LAT	S1PR4	GIMAP4	FAM101B	RPLP1	PTPRCAP	SEPT1	C9orf142	ADTRP
+Dendritic	LYZ	CST3	HLA-DRA	HLA-DQB1	HLA-DPB1	HLA-DQA2	HLA-DQA1	HLA-DPA1	HLA-DRB1	FCER1A	CD74	ALDH2	HLA-DRB5	HLA-DMA	LGALS2	AMICA1	GSN	CPVL	GPX1	GSTP1	GRN	FCGRT	HLA-DMB	CLEC10A	VIM	FOS	MNDA	CFP	SPINT2	LY86	IL1B	SPI1	COTL1	RP11-390E23.6	IGFBP7	FTH1	NPC2	RP11-473M20.7	TYROBP	LST1	CD63	OAZ1	DUSP1	FCER1G	S100A11	AIF1	GALE	SAT1	S100A4	CTSS

tools/cosg/test-data/marker_2.tsv

@@ -0,0 +1,8 @@
+	0	1	2	3	4	5	6	7	8	9	10	11	12	13	14	15	16	17	18	19	20	21	22	23	24	25	26	27	28	29	30	31	32	33	34	35	36	37	38	39	40	41	42	43	44	45	46	47	48	49
+0	CD3E	CD3D	IL32	LCK	CD247	LAT	GZMM	CD3G	AES	LDHB	NOSIP	GZMA	CD2	CD7	GIMAP7	CCL5	SEPT1	NKG7	IFITM1	HCST	CTSW	CD99	PRF1	SIT1	GZMH	CST7	CD8A	GIMAP5	HOPX	GNLY	STK17A	SPOCK2	CCR7	GZMK	PRKCQ-AS1	GZMB	CD8B	MATK	GYPC	RPSA	ITM2A	FGFBP2	B2M	RPS3	PTPRCAP	AQP3	FLT3LG	STMN1	RARRES3	GIMAP4
+1	CTSS	FTL	RP11-290F20.3	FCGR3A	LST1	SAT1	AIF1	PSAP	CFD	SERPINA1	CD68	FCER1G	CEBPB	FTH1	TYROBP	TMEM176B	S100A11	MS4A7	DUSP1	HCK	PILRA	OAZ1	NPC2	IFITM2	FCN1	IFITM3	STXBP2	COTL1	SPI1	S100A4	CFP	MPP1	SESN2	PCIF1	GALE	CORO1B	FCGRT	NFE2	FOS	MNDA	PFN1	GSTP1	RP11-390E23.6	ARHGDIB	SOX4	CST3	FAM101B	RNF138	B2M	EAF2
+2	FCER1A	LYZ	AMICA1	GSN	ALDH2	CLEC10A	HLA-DQA1	HLA-DQA2	GPX1	HLA-DRA	HLA-DQB1	LGALS2	HLA-DMA	HLA-DRB1	CD74	HLA-DPB1	GRN	HLA-DRB5	CST3	HLA-DMB	FOS	HLA-DPA1	FCGRT	MNDA	IL1B	GSTP1	SPINT2	CFP	VIM	IGFBP7	LY86	CD63	RP11-473M20.7	RP11-390E23.6	TMSB10	CCDC50	CPVL	SPIB	GALE	COTL1	SPI1	S100A4	TYROBP	RPLP0	CCDC132	NPC2	TRIM39	OAZ1	ATXN7L3B	PCIF1
+3	CD79B	MS4A1	BANK1	BLK	FCRLA	SPIB	CD79A	SMARCB1	PDLIM1	PLAC8	TNFRSF13B	LTB	CCDC50	NCF1	PNOC	POU2AF1	KIAA0125	PTPRCAP	ETV2	LY86	RPLP1	TPD52	CD52	HLA-DMB	EXOG	SYPL1	AL928768.3	ALOX5AP	SNHG7	RPSA	RPL3	GNG7	CD74	FAM63B	SELL	HLA-DMA	HLA-DRA	HLA-DPB1	IGLL5	STK17A	JUN	HLA-DQA2	EGR1	RNF34	ISG20	HLA-DQA1	SUB1	SIT1	C1orf228	HLA-DRB1
+4	CPVL	HLA-DPA1	CST3	GSTP1	VIM	HLA-DPB1	FCGRT	HLA-DQB1	CD74	HMGA1	HLA-DRA	HLA-DRB5	HLA-DRB1	RAB3IP	HLA-DQA1	SPINT2	HLA-DQA2	HLA-DMA	LGALS2	GRN	IGFBP7	LYZ	CALR	H1FX	GPX1	SESN2	HLA-DMB	LY86	GNG7	SPI1	ACTG1	ALDH2	FTH1	SERPINB1	SOX4	ATXN7L3B	GYPC	CD63	FOS	NPC2	SAT1	MATK	MNDA	HCK	PSAP	CTSS	AIF1	NCF1	FCGR3A	COTL1
+5	TNFRSF17	MZB1	IGJ	DERL3	XBP1	SSR4	FKBP11	ISG20	SSR3	SUB1	UBE2J1	PEBP1	VIMP	EAF2	MANF	AL928768.3	IGLL5	GNG7	TPD52	RP3-467N11.1	CD79A	POU2AF1	TNFRSF13B	CALR	CCDC132	TMSB10	CD27	RPLP0	TRIM39	LY9	SMARCB1	NCF1	NUCB2	RPLP1	PDLIM1	RSBN1L-AS1	CD63	S1PR4	PNOC	KIAA0125	AQP3	SESN2	RARRES3	RAB3IP	CD99	CCDC50	B2M	RPL3	VIM	ATXN7L3B
+6	PRSS57	CYTL1	EGFL7	C19orf77	SPINK2	RP11-620J15.3	SERPINB1	SNHG7	SOX4	NFE2	EGR1	CDK6	NGFRAP1	SYPL1	IL1B	NUCB2	H1FX	RPLP0	KIAA0125	SPINT2	MPHOSPH9	MPP1	C1orf228	RPS3	IGFBP7	RP3-467N11.1	RPL3	RNF34	HMGA1	ATXN7L3B	RSBN1L-AS1	LDHB	JUN	RPLP1	TRIM39	FAM63B	RNF138	RPSA	SESN2	FAM101B	ACOX1	MATK	PRKCQ-AS1	GYPC	PDLIM1	PCIF1	ITM2A	SELL	SPON2	CTSW