Update README with new Aeon inference parameters and add required CSV data files

- Document new sex and tissue site parameters for improved Aeon inference
- Update all CSV examples to include optional Sex and Tissue Site columns
- Add required data files: sex_original_to_idx.csv, tissue_site_original_to_idx.csv, paladin_model_map.csv
- These files are needed for tests and application functionality

README.md

@@ -141,13 +141,15 @@ mosaic --slide-csv /path/to/your/wsi_list.csv --output-dir /path/to/output/direc
 ```
 
 The CSV file should at least contain columns `Slide`, and `Site Type`.
-Optionally, it can also contain `Cancer Subtype`, `Segmentation Config`, and `IHC Subtype`.
+Optionally, it can also contain `Cancer Subtype`, `Segmentation Config`, `IHC Subtype`, `Sex`, and `Tissue Site`.
 
 - `Slide` should contain the full path to the WSI file.
 - `Site Type` should be one of `Primary`, or `Metastatic`.
 - `Cancer Subtype` should be the oncotree code for the cancer subtype.
 - `Segmentation Config` should be one of `Biopsy`, `Resection`, or `TCGA`.
 - `IHC Subtype` should be one of `HR+/HER2+`, `HR+/HER2-`, `HR-/HER2+`, or `HR-/HER2-`.
+- `Sex` (optional): Patient sex for improved Aeon inference - one of `Male`, `Female`, or `Unknown`.
+- `Tissue Site` (optional): Primary tissue site for improved Aeon inference (e.g., `Lung`, `Breast`, `Colon`, `Liver`, `Brain`).
 
 See additional options with the help command. This command may take a few seconds to run:
 
@@ -188,7 +190,9 @@ mosaic --slide-path /data/slides/sample.svs \
        --output-dir /data/results \
        --site-type Primary \
        --cancer-subtype Unknown \
-       --segmentation-config Resection
+       --segmentation-config Resection \
+       --sex Female \
+       --tissue-site Lung
 ```
 
 ### Example 2: Process a single breast cancer slide with known IHC subtype
@@ -199,7 +203,9 @@ mosaic --slide-path /data/slides/breast_sample.svs \
        --site-type Primary \
        --cancer-subtype BRCA \
        --ihc-subtype "HR+/HER2-" \
-       --segmentation-config Biopsy
+       --segmentation-config Biopsy \
+       --sex Female \
+       --tissue-site Breast
 ```
 
 ### Example 3: Process multiple slides from CSV
@@ -207,10 +213,10 @@ mosaic --slide-path /data/slides/breast_sample.svs \
 Create a CSV file `slides.csv` with the following format:
 
 ```csv
-Slide,Site Type,Cancer Subtype,Segmentation Config,IHC Subtype
-/data/slides/sample1.svs,Primary,Unknown,Resection,
-/data/slides/sample2.svs,Metastatic,LUAD,Biopsy,
-/data/slides/sample3.svs,Primary,BRCA,TCGA,HR+/HER2-
+Slide,Site Type,Cancer Subtype,Segmentation Config,IHC Subtype,Sex,Tissue Site
+/data/slides/sample1.svs,Primary,Unknown,Resection,,Female,Lung
+/data/slides/sample2.svs,Metastatic,LUAD,Biopsy,,,Liver
+/data/slides/sample3.svs,Primary,BRCA,TCGA,HR+/HER2-,Female,Breast
 ```
 
 Then run:
@@ -280,14 +286,24 @@ When processing multiple slides using the `--slide-csv` option, the CSV file mus
   - `HR+/HER2-`
   - `HR-/HER2+`
   - `HR-/HER2-`
+- **Sex**: Patient sex for improved Aeon cancer subtype inference. One of `Male`, `Female`, or `Unknown`.
+- **Tissue Site**: Primary tissue site for improved Aeon cancer subtype inference. Examples include:
+  - `Lung`
+  - `Breast`
+  - `Colon`
+  - `Liver`
+  - `Brain`
+  - `Lymph Node`
+  - `Bone`
+  - See `data/tissue_site_original_to_idx.csv` for complete list of supported tissue sites.
 
 ### CSV Example
 
 ```csv
-Slide,Site Type,Cancer Subtype,Segmentation Config,IHC Subtype
-/data/slides/lung1.svs,Primary,LUAD,Resection,
-/data/slides/breast1.svs,Primary,BRCA,Biopsy,HR+/HER2-
-/data/slides/unknown1.svs,Metastatic,Unknown,TCGA,
+Slide,Site Type,Cancer Subtype,Segmentation Config,IHC Subtype,Sex,Tissue Site
+/data/slides/lung1.svs,Primary,LUAD,Resection,,Male,Lung
+/data/slides/breast1.svs,Primary,BRCA,Biopsy,HR+/HER2-,Female,Breast
+/data/slides/unknown1.svs,Metastatic,Unknown,TCGA,,,Liver
 ```
 
 ## Cancer Subtypes

data/paladin_model_map.csv

@@ -0,0 +1,133 @@
+cancer_subtype,target_name,model_path
+AASTR,IDH1.R132H,data/paladin/xf9lhkpd.epoch=12-step=13.model.pkl
+AASTR,ATRX_TRUNC,data/paladin/nghmtwqq.epoch=12-step=13.model.pkl
+AASTR,ATRX_ONCOGENIC,data/paladin/j3pgp96i.epoch=14-step=15.model.pkl
+ADNOS,Del_17p,data/paladin/x474gdo3.epoch=16-step=51.model.pkl
+ASTR,TP53_hotspot,data/paladin/ed73u1uo.epoch=7-step=16.model.pkl
+ASTR,IDH1.R132H,data/paladin/7cxzdxfb.epoch=10-step=22.model.pkl
+ASTR,ATRX_ONCOGENIC,data/paladin/gq60pnxn.epoch=9-step=20.model.pkl
+ASTR,ATRX_TRUNC,data/paladin/0frn4tny.epoch=9-step=20.model.pkl
+ASTR,TP53_ONCOGENIC,data/paladin/ww18g380.epoch=17-step=36.model.pkl
+ASTR,IDH1_hotspot,data/paladin/uhfe7p8r.epoch=16-step=34.model.pkl
+ASTR,IDH1_ONCOGENIC,data/paladin/3ar8pu9i.epoch=16-step=34.model.pkl
+ASTR,RTK_RAS_PATHWAY,data/paladin/u91fy5r0.epoch=7-step=16.model.pkl
+BLCA,Del_6q,data/paladin/eqtpu2m2.epoch=6-step=91.model.pkl
+BLCA,TP53_PATHWAY,data/paladin/jaoqa2w3.epoch=7-step=104.model.pkl
+BLCA,RB1_TRUNC,data/paladin/v5yz6ndf.epoch=7-step=104.model.pkl
+BLCA,RB1_ONCOGENIC,data/paladin/54uvrvff.epoch=6-step=91.model.pkl
+BLCA,FGFR3_ONCOGENIC,data/paladin/jchzcaq5.epoch=4-step=65.model.pkl
+CCRCC,Del_14q,data/paladin/kr2wtldy.epoch=13-step=56.model.pkl
+COAD,NKX3-1_HomDel,data/paladin/cwh3r34l.epoch=12-step=104.model.pkl
+COAD,NKX3-1_ONCOGENIC,data/paladin/ji4ankxk.epoch=12-step=104.model.pkl
+COAD,Amp_10p,data/paladin/9lt8fu1i.epoch=17-step=144.model.pkl
+COAD,Del_5q,data/paladin/e3owivcb.epoch=11-step=96.model.pkl
+COAD,BRAF_hotspot,data/paladin/gi1mikgg.epoch=19-step=300.model.pkl
+COAD,Amp_13q,data/paladin/5fr6k4aq.epoch=2-step=45.model.pkl
+COAD,Amp_17q,data/paladin/gs0nknp6.epoch=17-step=270.model.pkl
+COAD,Del_18p,data/paladin/i9f8ace7.epoch=6-step=105.model.pkl
+COAD,SRC_Amp,data/paladin/nz6n2i3j.epoch=13-step=210.model.pkl
+COAD,Del_18q,data/paladin/46zyn9jd.epoch=5-step=48.model.pkl
+COAD,ASXL1_Amp,data/paladin/jtjvnzv8.epoch=13-step=210.model.pkl
+COAD,Del_21p,data/paladin/6m0qjb6j.epoch=16-step=255.model.pkl
+COAD,KRAS_hotspot,data/paladin/9y9vj6vn.epoch=5-step=90.model.pkl
+COAD,Del_21p,data/paladin/qih446gc.epoch=16-step=136.model.pkl
+COAD,DNMT3B_Amp,data/paladin/3cb7sra7.epoch=14-step=225.model.pkl
+COAD,SRC_ONCOGENIC,data/paladin/l4v77tuf.epoch=13-step=210.model.pkl
+COAD,Del_18q,data/paladin/5x3oo7bu.epoch=6-step=105.model.pkl
+COAD,Del_5q,data/paladin/aupfdkmm.epoch=8-step=135.model.pkl
+COAD,TOP1_Amp,data/paladin/llb4wrf5.epoch=17-step=270.model.pkl
+COAD,DNMT3B_ONCOGENIC,data/paladin/84q4qtj2.epoch=16-step=238.model.pkl
+COAD,Amp_20q,data/paladin/lvgc5hf4.epoch=9-step=80.model.pkl
+COAD,Amp_20q,data/paladin/3z7m1yvu.epoch=3-step=60.model.pkl
+COAD,BRAF.V600E,data/paladin/hszhjtww.epoch=19-step=300.model.pkl
+COAD,MSI_TYPE,data/paladin/7zkj9sa3.epoch=10-step=187.model.pkl
+COADREAD,MSI_TYPE,data/paladin/ef9g2g05.epoch=19-step=80.model.pkl
+GBM,TERT_ONCOGENIC,data/paladin/d2nctcc7.epoch=3-step=24.model.pkl
+GBM,EGFR_Amp,data/paladin/3ym64o1g.epoch=12-step=78.model.pkl
+GBM,EGFR_SV,data/paladin/c0piw4ym.epoch=14-step=90.model.pkl
+GIST,EPIGENETIC_PATHWAY,data/paladin/imjphv1j.epoch=17-step=72.model.pkl
+GIST,Del_10q,data/paladin/9c1quhjf.epoch=14-step=30.model.pkl
+GIST,Del_1p,data/paladin/711sspdl.epoch=7-step=32.model.pkl
+GIST,CELL_CYCLE_PATHWAY,data/paladin/tbty48me.epoch=13-step=56.model.pkl
+GIST,CDKN2B_HomDel,data/paladin/bvo5yd3x.epoch=19-step=80.model.pkl
+GIST,CDKN2B_ONCOGENIC,data/paladin/hchh1kxy.epoch=19-step=80.model.pkl
+GIST,KIT_ONCOGENIC,data/paladin/5qv1l577.epoch=16-step=68.model.pkl
+GIST,Del_9q,data/paladin/js5kwd8h.epoch=14-step=60.model.pkl
+HCC,Del_8p,data/paladin/414aigjv.epoch=13-step=28.model.pkl
+HGSOC,ZRSR2_HomDel,data/paladin/f49bti0v.epoch=18-step=152.model.pkl
+HGSOC,ZRSR2_ONCOGENIC,data/paladin/w65puu1d.epoch=18-step=152.model.pkl
+IDC,Del_14q,data/paladin/0332pa6g.epoch=4-step=80.model.pkl
+IDC,NBN_Amp,data/paladin/3dckgf7z.epoch=19-step=320.model.pkl
+IDC,Amp_10p,data/paladin/86dw519k.epoch=8-step=144.model.pkl
+IDC,TP53_PATHWAY,data/paladin/nnpm1j02.epoch=5-step=96.model.pkl
+IDC,Del_5q,data/paladin/qmd3pzkq.epoch=5-step=96.model.pkl
+IDC,TP53_ONCOGENIC,data/paladin/vreyb1om.epoch=6-step=112.model.pkl
+IDC,Amp_9p,data/paladin/03ag726b.epoch=18-step=304.model.pkl
+LUAD,ALK_ONCOGENIC,data/paladin/ovyxd2ob.epoch=19-step=520.model.pkl
+LUAD,CDKN2A_HomDel,data/paladin/jjzra532.epoch=8-step=243.model.pkl
+LUAD,Del_8p,data/paladin/50r2qwax.epoch=4-step=135.model.pkl
+LUAD,ALK_fusion,data/paladin/9yhryzl3.epoch=19-step=540.model.pkl
+LUAD,EGFR.L858R,data/paladin/m5ryhg9a.epoch=10-step=297.model.pkl
+LUAD,Amp_14q,data/paladin/ngn9k9im.epoch=10-step=297.model.pkl
+LUAD,Del_10q,data/paladin/zb1foppw.epoch=15-step=432.model.pkl
+LUAD,TP53_PATHWAY,data/paladin/1h5j6lcv.epoch=3-step=108.model.pkl
+LUAD,Del_19p,data/paladin/eqkh5ixz.epoch=7-step=216.model.pkl
+LUAD,STK11_TRUNC,data/paladin/k60w4up0.epoch=12-step=208.model.pkl
+LUAD,EGFR_hotspot,data/paladin/8chbkvr2.epoch=3-step=108.model.pkl
+LUAD,STK11_ONCOGENIC,data/paladin/0g4nz14y.epoch=6-step=112.model.pkl
+LUAD,Del_21q,data/paladin/f1vh8j1d.epoch=11-step=324.model.pkl
+LUAD,Amp_1q,data/paladin/nkik9rcn.epoch=6-step=189.model.pkl
+LUAD,NRF2_PATHWAY,data/paladin/yqlfdrvs.epoch=8-step=243.model.pkl
+LUAD,Del_21p,data/paladin/3szdaukp.epoch=16-step=459.model.pkl
+LUAD,STK11_ONCOGENIC,data/paladin/uanm5qpb.epoch=6-step=189.model.pkl
+LUSC,Del_10q,data/paladin/gbsuatlf.epoch=12-step=65.model.pkl
+LUSC,Del_5q,data/paladin/otxp4y9q.epoch=15-step=80.model.pkl
+LUSC,Del_3p,data/paladin/1gkyhld8.epoch=8-step=45.model.pkl
+NBL,Del_Xp,data/paladin/7y3lp7vw.epoch=14-step=45.model.pkl
+NBL,Del_Xq,data/paladin/ludvrs24.epoch=19-step=60.model.pkl
+NBL,Amp_17q,data/paladin/qia84b7i.epoch=11-step=36.model.pkl
+NBL,RTK_RAS_PATHWAY,data/paladin/wyd7ada7.epoch=0-step=2.model.pkl
+NBL,MYCN_Amp,data/paladin/k88gw2io.epoch=14-step=45.model.pkl
+NBL,MYCN_ONCOGENIC,data/paladin/sp7lpt88.epoch=14-step=45.model.pkl
+NBL,MYC_PATHWAY,data/paladin/1onmwcqf.epoch=11-step=36.model.pkl
+PAAD,Del_12p,data/paladin/cofs6tb2.epoch=14-step=210.model.pkl
+PAAD,Del_15q,data/paladin/4366o7so.epoch=19-step=280.model.pkl
+PAAD,MTAP_ONCOGENIC,data/paladin/h14fuggs.epoch=13-step=70.model.pkl
+PAAD,CDKN2B_ONCOGENIC,data/paladin/c9onh7cc.epoch=5-step=54.model.pkl
+PAAD,CDKN2B_HomDel,data/paladin/e6y1suye.epoch=5-step=54.model.pkl
+PAAD,CDKN2A_HomDel,data/paladin/yci9dso2.epoch=5-step=54.model.pkl
+PAAD,Del_21p,data/paladin/p3sgty9x.epoch=17-step=162.model.pkl
+PANET,Amp_7q,data/paladin/8w0pcfqg.epoch=3-step=8.model.pkl
+PANET,Amp_14q,data/paladin/kvqfszzv.epoch=11-step=24.model.pkl
+PANET,Amp_17q,data/paladin/n05xwpfv.epoch=1-step=4.model.pkl
+PANET,Del_2q,data/paladin/iway7gvk.epoch=19-step=40.model.pkl
+PANET,Del_1q,data/paladin/nnv3biwl.epoch=14-step=30.model.pkl
+PANET,Del_10p,data/paladin/ivcnueik.epoch=15-step=32.model.pkl
+PANET,Del_3p,data/paladin/i18cwtml.epoch=10-step=22.model.pkl
+PANET,Del_10q,data/paladin/lhdb8n6t.epoch=15-step=32.model.pkl
+PANET,Del_2p,data/paladin/simlsmym.epoch=18-step=38.model.pkl
+PANET,Del_3q,data/paladin/z9pxdil3.epoch=10-step=22.model.pkl
+PRAD,Amp_11q,data/paladin/rlppqzob.epoch=19-step=300.model.pkl
+PRAD,Del_15q,data/paladin/8y9cu8ti.epoch=5-step=90.model.pkl
+PRAD,Amp_7q,data/paladin/4z9wd7oh.epoch=15-step=240.model.pkl
+PRAD,SPOP_hotspot,data/paladin/tyqig7ov.epoch=14-step=225.model.pkl
+SARCNOS,TP53_ONCOGENIC,data/paladin/xvpxs12a.epoch=12-step=39.model.pkl
+SKCM,Del_10p,data/paladin/9dadxrr4.epoch=11-step=60.model.pkl
+SKCM,Del_10q,data/paladin/f6l6c2v8.epoch=9-step=50.model.pkl
+STAD,MSI_TYPE,data/paladin/kmi9hl2z.epoch=19-step=80.model.pkl
+THPA,BRAF_hotspot,data/paladin/u0ec035p.epoch=13-step=28.model.pkl
+UEC,ARID1A_ONCOGENIC,data/paladin/hrn4ehsm.epoch=11-step=108.model.pkl
+UEC,Amp_10q,data/paladin/0kh0uesc.epoch=10-step=99.model.pkl
+UEC,CTNNB1_ONCOGENIC,data/paladin/rmg2u8mw.epoch=12-step=26.model.pkl
+UEC,CTNNB1_hotspot,data/paladin/0y5oa83k.epoch=13-step=28.model.pkl
+UEC,KRAS_ONCOGENIC,data/paladin/wc3cv24o.epoch=12-step=117.model.pkl
+UEC,Amp_10p,data/paladin/cpq494o0.epoch=18-step=171.model.pkl
+UEC,TP53_hotspot,data/paladin/52dr57pb.epoch=14-step=135.model.pkl
+UEC,TGF_BETA_PATHWAY,data/paladin/8uxv3vc8.epoch=17-step=162.model.pkl
+UEC,Amp_8q,data/paladin/uzp4fgfa.epoch=14-step=135.model.pkl
+UEC,Amp_1q,data/paladin/ce6wob99.epoch=14-step=135.model.pkl
+UEC,MSI_TYPE,data/paladin/zrsfn6kz.epoch=13-step=126.model.pkl
+UEC,CTNNB1_ONCOGENIC,data/paladin/lrfqme6d.epoch=11-step=108.model.pkl
+UEC,CTNNB1_hotspot,data/paladin/hf3samzm.epoch=13-step=126.model.pkl
+USC,Del_16q,data/paladin/eq6jer0f.epoch=9-step=30.model.pkl
+UTUC,FGFR3_hotspot,data/paladin/qgajjknw.epoch=10-step=33.model.pkl

data/sex_original_to_idx.csv

@@ -0,0 +1,6 @@
+idx,SEX
+0,Male
+0,MALE
+1,Female
+1,FEMALE
+2,Unknown

data/tissue_site_original_to_idx.csv

@@ -0,0 +1,74 @@
+idx,TISSUE_SITE
+0,Lung
+1,Liver
+2,Lymph Node
+2,Lymph node
+2,"Lymph Node, Regional"
+3,Breast
+4,Colon
+4,Sigmoid Colon
+4,Ascending Colon
+4,Cecum
+4,Rectosigmoid Colon
+4,Transverse Colon
+4,Descending Colon
+5,Brain
+6,Bone
+6,Iliac Bone
+6,Spine
+6,Femur
+6,Rib
+7,Pancreas
+8,Not Applicable
+8,Not available
+9,Uterus
+10,Prostate
+11,Bladder
+12,Soft Tissue
+13,Ovary
+14,Rectum
+15,Kidney
+16,Skin
+17,Stomach
+18,Pleura
+19,Esophagus
+20,Peritoneum
+21,Omentum
+22,Retroperitoneum
+23,Pelvis
+24,Adrenal Gland
+24,Adrenal
+25,Endometrium
+26,Thyroid
+27,Chest Wall
+28,Abdomen
+29,Small Bowel
+29,Small Intestine
+30,GE Junction
+30,Gastroesophageal Junction
+31,Cervix
+32,Bile Duct
+33,Neck
+34,Mediastinum
+35,Testis
+36,Bowel
+37,Eye
+38,Thigh
+39,Vagina
+40,Pleural Fluid
+41,Upper Tract
+42,Axilla
+43,Diaphragm
+44,Gallbladder
+45,Abdominal Wall
+46,Appendix
+47,Anus
+48,Duodenum
+49,Renal Pelvis
+50,Tongue
+51,Mesentery
+52,Vulva
+53,Oral Cavity
+54,Fallopian tube
+55,Epidural
+56,Leg