Release 0.4.1 (#1)

Release 0.4.1 squashed commit. Refer to release notes and pull request.

Dockerfile

@@ -7,13 +7,14 @@ RUN pip install -r requirements.txt
 
 COPY example_data/ /example_data/
 COPY example_output/ /example_output/
-COPY test/ /test/
 
 RUN mkdir /moalmanac/
 RUN mkdir /moalmanac/datasources/
+RUN mkdir /docs/
 
+COPY moalmanac/test/ moalmanac/test/
 COPY moalmanac/datasources/acmg/ /moalmanac/datasources/acmg/
-COPY moalmanac/datasources/almanac/ /moalmanac/datasources/almanac/
+COPY moalmanac/datasources/moalmanac/ /moalmanac/datasources/moalmanac/
 COPY moalmanac/datasources/cancergenecensus/ /moalmanac/datasources/cancergenecensus/
 COPY moalmanac/datasources/cancerhotspots/ /moalmanac/datasources/cancerhotspots/
 COPY moalmanac/datasources/clinvar/ /moalmanac/datasources/clinvar/
@@ -38,6 +39,7 @@ COPY moalmanac/templates/ /moalmanac/templates/
 COPY moalmanac/wrapper_deconstructsigs.sh moalmanac/run_deconstructsigs.R /moalmanac/
 COPY moalmanac/*.py moalmanac/*.ini /moalmanac/
 
+COPY docs/* /docs/
 COPY README.md /
 COPY LICENSE /
 COPY Dockerfile /

README.md

@@ -59,6 +59,7 @@ Optional arguments:
     --snv_handle            <string>    handle for MAF file of somatic single nucleotide variants
     --indel_handle          <string>    handle for MAF file of somatic insertions and deletions
     --bases_covered_handle  <string>    handle for text file which contains the number of calcable somatic bases
+    --called_cn_handle      <string>    handle for text file which contained genes and copy number calls, will be used over `--cnv_handle`
     --cnv_handle            <string>    handle for annotated seg file for somatic copy number
     --fusion_handle         <string>    handle for STAR fusion output, .final.abridged
     --germline_handle       <string>    handle for MAF file of germline single nucleotide variants and insertions and deletions

docs/description-of-inputs.md

@@ -101,6 +101,24 @@ Required fields can be changed from their default expectations by editing the ap
 ### Required fields
 This input is looking for an integer value. 
 
+## Called copy number alterations
+`--called_cn_handle` anticipated a tab delimited file which contains one column for gene name and a second for the copy number call. For the latter, only the values `Amplification` and `Deletion` will be used by the Molecular Oncology Almanac.
+
+### Example
+|gene|call|
+|-|-|
+|TP53|Deletion|
+|CDKN2A|Deletion|
+|BRAF|Baseline|
+|EGFR|Amplification|
+
+The rows associated with _TP53_, _CDKN2A_, and _EGFR_ will be interpreted and scored by Molecular Oncology Almanac while _BRAF_ will be filtered.
+
+### Required files
+Required fields can be changed from their default expectations by editing the appropriate section of [colnames.ini](https://github.com/vanallenlab/moalmanac/blob/main/moalmanac/colnames.ini). Column names are case sensitive. 
+- `gene`, gene symbol associated with the copy number alteration
+- `call`, copy number event of the gene. `Amplification` and `Deletion` are accepted and all other values will be filtered.
+
 ## Copy number alterations
 `--cnv_handle` anticipates a tab delimited file which contains total copy number from a source such as GATK CNV or ReCapSeg, support for allele specific copy number is in progress. This file should have genes associated with segments. Amplifications are called from the top 2.5% of all unique segments and deletions called from the bottom 2.5% of all unique segments. 
 
@@ -124,16 +142,16 @@ Required fields can be changed from their default expectations by editing the ap
 `--fusion_handle` anticipates a tab delimited file which contains fusions, specifically in the format of STAR Fusion. 
 
 ### Example
-|#fusion_name|SpanningFrags|LeftBreakpoint|RightBreakpoint|
+|#FusionName|SpanningFragCount|LeftBreakpoint|RightBreakpoint|
 |-|-|-|-|
 |EML4--ALK|0|6:47471176|11:66563752|
 |COL1A2--APBA3|6|9:35657873|21:46320255|
 |POLR2A--AP2M1|12|17:7406801|3:183898675|
 
 ### Required fields
 Required fields can be changed from their default expectations by editing the appropriate section of [colnames.ini](https://github.com/vanallenlab/moalmanac/blob/main/moalmanac/colnames.ini). Column names are case sensitive. 
-- `#fusion_name`, gene symbols associated with the fusion separated by `--`. Genes are labeled from 5' to 3'. 
-- `SpanningFrags`, counts of RNA-seq fragments supporting the fusion
+- `#FusionName`, gene symbols associated with the fusion separated by `--`. Genes are labeled from 5' to 3'. 
+- `SpanningFragCount`, counts of RNA-seq fragments supporting the fusion
 - `LeftBreakpoint`, genomic position of the fusion's left breakpoint
 - `RightBreakpoint`, genomic position of the fusion's right breakpoint
 

docs/description-of-outputs.md

@@ -169,24 +169,22 @@ Each molecular feature will also receive a label in the `score_bin` column based
   * Somatic and germline variants - Gene, variant classification, and protein change match a catalogued variant 
   * Copy number alterations - Gene and copy number direction match a catalogued event
   * Fusions - Both genes involved in a fusion event match a catalogued event
-* `Investigate Actionability - High`
-  * Somatic and germline variants - Gene and variant classification match a catalogued event but not a specific protein change
-* `Investigate Actionability - Low`
-  * Somatic and germline variants - Gene and feature type match a catalogued variant but not variant classification
+* `Investigate Actionability`
+  * Somatic and germline variants - Gene and feature type match a catalogued variant but not variant classification or a specific protein change
   * Copy number alterations - Gene and feature type match a catalogued copy number alteration but not direction
   * Fusions - One gene fusion partner is catalogued as a fusion in Molecular Oncology Almanac but not both
 * `Biologically Relevance`
   * The gene(s) associated with the molecular feature is present in Molecular Oncology Almanac but under a different feature type
 
 The following second-order molecular features are evaluated in `score_bin` as follows:
-* High mutational burden is labeled as `Investigate Actionability - High` 
-* MSI-High is labeled as `Investigate Actionability - High`
-* Whole-genome doubling is labeled as `Investigate Actionability - High`
-* Mutational signatures catalogued by Molecular Oncology Almanac are labeled as `Investigate Actionability - High` and otherwise labeled as `Biologically Relevant`
+* High mutational burden is labeled as `Investigate Actionability` 
+* MSI-High is labeled as `Investigate Actionability`
+* Whole-genome doubling is labeled as `Investigate Actionability`
+* Mutational signatures catalogued by Molecular Oncology Almanac are labeled as `Investigate Actionability` and otherwise labeled as `Biologically Relevant`
 * Variants associated with microsatellite instability are listed as "Supporting variants" as `Biologically Relevant`
 
 ### Evidence of clinical assertions
-If a molecular feature matched as `Putatively Actionable`, `Investigate Actionability - High`, or `Investigate Actionability - Low` in Molecular Oncology Almanac, the molecular feature will be associated with clinical evidence. A molecular feature will be matched independently on catalogued events associated with therapeutic sensitivity, therapeutic resistance, and disease prognosis.
+If a molecular feature matched as `Putatively Actionable`, or `Investigate Actionability` in Molecular Oncology Almanac, the molecular feature will be associated with clinical evidence. A molecular feature will be matched independently on catalogued events associated with therapeutic sensitivity, therapeutic resistance, and disease prognosis.
 
 #### Associated evidence, Predictive Implication
 All catalogued events in Molecular Oncology Almanac are cited and have associated evidence. Evidence tiers are as follows:

example_data/example_patient.capture.germline.maf

@@ -1,11 +1,11 @@
-Hugo_Symbol	NCBI_Build	Chromosome	Start_position	End_position	Variant_Classification	Reference_Allele	Tumor_Seq_Allele1	Tumor_Seq_Allele2	Tumor_Sample_Barcode	Matched_Norm_Sample_Barcode	Annotation_Transcript	Protein_Change	t_alt_count	t_ref_count
-PRDM2	37	1	14105122	14105122	In_Frame_Del	GAA	GAA	-	__UNKNOWN__	example_normal_profile		p.E282del	50	50
-ALK	37	2	29416572	29416572	Missense_Mutation	T	T	C	__UNKNOWN__	example_normal_profile		p.I1461V	50	50
-BIRC6	37	2	32667182	32667182	Missense_Mutation	G	G	C	__UNKNOWN__	example_normal_profile		p.V1332L	50	50
-MSH6	37	2	48010488	48010488	Missense_Mutation	G	G	A	__UNKNOWN__	example_normal_profile		p.G39E	50	50
-FGFR4	37	5	176520243	176520243	Missense_Mutation	G	G	A	__UNKNOWN__	example_normal_profile		p.G388R	50	50
-BRAF	37	7	140476881	140476881	Nonsense_Mutation	G	G	A	__UNKNOWN__	example_normal_profile		p.R509*	50	50
-TP53	37	17	7579472	7579472	Missense_Mutation	G	G	C	__UNKNOWN__	example_normal_profile		p.P72R	50	50
-BRCA2	37	13	32906729	32906729	Missense_Mutation	A	A	C	__UNKNOWN__	example_normal_profile		p.N372H	50	50
-BRCA2	37	13	32914438	32914438	Frame_Shift_Del	T	T	-	__UNKNOWN__	example_normal_profile		p.S1982fs	50	50
-BCR	37	22	23627369	23627369	Missense_Mutation	A	A	G	__UNKNOWN__	example_normal_profile		p.N796S	50	50
+Hugo_Symbol	NCBI_Build	Chromosome	Start_position	End_position	Variant_Classification	Reference_Allele	Tumor_Seq_Allele1	Tumor_Seq_Allele2	Tumor_Sample_Barcode	Matched_Norm_Sample_Barcode	Annotation_Transcript	Protein_Change	t_alt_count	t_ref_count
+PRDM2	37	1	14105122	14105122	In_Frame_Del	GAA	GAA	-	example_tumor_profile	example_normal_profile		p.E282del	50	50
+ALK	37	2	29416572	29416572	Missense_Mutation	T	T	C	example_tumor_profile	example_normal_profile		p.I1461V	50	50
+BIRC6	37	2	32667182	32667182	Missense_Mutation	G	G	C	example_tumor_profile	example_normal_profile		p.V1332L	50	50
+MSH6	37	2	48010488	48010488	Missense_Mutation	G	G	A	example_tumor_profile	example_normal_profile		p.G39E	50	50
+FGFR4	37	5	176520243	176520243	Missense_Mutation	G	G	A	example_tumor_profile	example_normal_profile		p.G388R	50	50
+BRAF	37	7	140476881	140476881	Nonsense_Mutation	G	G	A	example_tumor_profile	example_normal_profile		p.R509*	50	50
+TP53	37	17	7579472	7579472	Missense_Mutation	G	G	C	example_tumor_profile	example_normal_profile		p.P72R	50	50
+BRCA2	37	13	32906729	32906729	Missense_Mutation	A	A	C	example_tumor_profile	example_normal_profile		p.N372H	50	50
+BRCA2	37	13	32914438	32914438	Frame_Shift_Del	T	T	-	example_tumor_profile	example_normal_profile		p.S1982fs	50	50
+BCR	37	22	23627369	23627369	Missense_Mutation	A	A	G	example_tumor_profile	example_normal_profile		p.N796S	50	50

example_data/example_patient.capture.somatic.called.cna.txt

@@ -0,0 +1,7 @@
+gene	call
+TP53	Deletion
+CDKN2A	Deletion
+BRAF	Amplification
+CDK4	Amplification
+BLM	Wild type
+FGFR2	Deletion

example_data/example_patient.capture.somatic.indels.maf

@@ -1 +1,3 @@
-Hugo_Symbol	NCBI_Build	Chromosome	Start_position	End_position	Variant_Classification	Reference_Allele	Tumor_Seq_Allele1	Tumor_Seq_Allele2	Tumor_Sample_Barcode	Matched_Norm_Sample_Barcode	Annotation_Transcript	Protein_Change	t_alt_count	t_ref_countPMPCA	37	9	139312448	139312449	Intron	-	-	G	example_patient_tumor	example_patient_normal	ENST00000371717.3		31	92C10orf2	37	10	102748300	102748301	Frame_Shift_Del	TC	TC	-	example_patient_tumor	example_patient_normal	ENST00000370228.1	p.L112fs	28	294
+Hugo_Symbol	NCBI_Build	Chromosome	Start_position	End_position	Variant_Classification	Reference_Allele	Tumor_Seq_Allele1	Tumor_Seq_Allele2	Tumor_Sample_Barcode	Matched_Norm_Sample_Barcode	Annotation_Transcript	Protein_Change	t_alt_count	t_ref_count
+PMPCA	37	9	139312448	139312449	Intron	-	-	G	example_tumor_profile	example_normal_profile	ENST00000371717.3		31	92
+C10orf2	37	10	102748300	102748301	Frame_Shift_Del	TC	TC	-	example_tumor_profile	example_normal_profile	ENST00000370228.1	p.L112fs	28	294