Upload folder using huggingface_hub (part 20)

.gitattributes

@@ -389,3 +389,7 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 .venv/lib/python3.11/site-packages/yaml/_yaml.cpython-311-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text
 .venv/lib/python3.11/site-packages/zarr/core/__pycache__/array.cpython-311.pyc filter=lfs diff=lfs merge=lfs -text
 .venv/lib/python3.11/site-packages/zarr/core/__pycache__/group.cpython-311.pyc filter=lfs diff=lfs merge=lfs -text
+analysis/replogle_source_to_filtered_schema/replogle_source_filtered_schema_no_xstate.h5ad filter=lfs diff=lfs merge=lfs -text
+analysis/replogle_source_to_filtered_schema/replogle_source_filtered_schema_with_xstate.h5ad filter=lfs diff=lfs merge=lfs -text
+analysis/replogle_xstate_reembed/replogle_concat_input_no_xstate.h5ad filter=lfs diff=lfs merge=lfs -text
+analysis/replogle_xstate_reembed/replogle_concat_reembedded_se600m.h5ad filter=lfs diff=lfs merge=lfs -text

.venv/pyvenv.cfg

@@ -0,0 +1,6 @@
+home = /home/ywn1043/.local/share/uv/python/cpython-3.11.12-linux-x86_64-gnu/bin
+implementation = CPython
+uv = 0.7.19
+version_info = 3.11.12
+include-system-site-packages = false
+prompt = state_parse_repro

.venv/share/man/man1/ttx.1

@@ -0,0 +1,225 @@
+.Dd May 18, 2004
+.\" ttx is not specific to any OS, but contrary to what groff_mdoc(7)
+.\" seems to imply, entirely omitting the .Os macro causes 'BSD' to
+.\" be used, so I give a zero-width space as its argument.
+.Os \&
+.\" The "FontTools Manual" argument apparently has no effect in
+.\" groff 1.18.1. I think it is a bug in the -mdoc groff package.
+.Dt TTX 1 "FontTools Manual"
+.Sh NAME
+.Nm ttx
+.Nd tool for manipulating TrueType and OpenType fonts
+.Sh SYNOPSIS
+.Nm
+.Bk
+.Op Ar option ...
+.Ek
+.Bk
+.Ar file ...
+.Ek
+.Sh DESCRIPTION
+.Nm
+is a tool for manipulating TrueType and OpenType fonts.  It can convert
+TrueType and OpenType fonts to and from an
+.Tn XML Ns -based format called
+.Tn TTX .
+.Tn TTX
+files have a
+.Ql .ttx
+extension.
+.Pp
+For each
+.Ar file
+argument it is given,
+.Nm
+detects whether it is a
+.Ql .ttf ,
+.Ql .otf
+or
+.Ql .ttx
+file and acts accordingly: if it is a
+.Ql .ttf
+or
+.Ql .otf
+file, it generates a
+.Ql .ttx
+file; if it is a
+.Ql .ttx
+file, it generates a
+.Ql .ttf
+or
+.Ql .otf
+file.
+.Pp
+By default, every output file is created in the same directory as the
+corresponding input file and with the same name except for the
+extension, which is substituted appropriately.
+.Nm
+never overwrites existing files; if necessary, it appends a suffix to
+the output file name before the extension, as in
+.Pa Arial#1.ttf .
+.Ss "General options"
+.Bl -tag -width ".Fl t Ar table"
+.It Fl h
+Display usage information.
+.It Fl d Ar dir
+Write the output files to directory
+.Ar dir
+instead of writing every output file to the same directory as the
+corresponding input file.
+.It Fl o Ar file
+Write the output to
+.Ar file
+instead of writing it to the same directory as the
+corresponding input file.
+.It Fl v
+Be verbose.  Write more messages to the standard output describing what
+is being done.
+.It Fl a
+Allow virtual glyphs ID's on compile or decompile.
+.El
+.Ss "Dump options"
+The following options control the process of dumping font files
+(TrueType or OpenType) to
+.Tn TTX
+files.
+.Bl -tag -width ".Fl t Ar table"
+.It Fl l
+List table information.  Instead of dumping the font to a
+.Tn TTX
+file, display minimal information about each table.
+.It Fl t Ar table
+Dump table
+.Ar table .
+This option may be given multiple times to dump several tables at
+once.  When not specified, all tables are dumped.
+.It Fl x Ar table
+Exclude table
+.Ar table
+from the list of tables to dump.  This option may be given multiple
+times to exclude several tables from the dump.  The
+.Fl t
+and
+.Fl x
+options are mutually exclusive.
+.It Fl s
+Split tables.  Dump each table to a separate
+.Tn TTX
+file and write (under the name that would have been used for the output
+file if the
+.Fl s
+option had not been given) one small
+.Tn TTX
+file containing references to the individual table dump files.  This
+file can be used as input to
+.Nm
+as long as the referenced files can be found in the same directory.
+.It Fl i
+.\" XXX: I suppose OpenType programs (exist and) are also affected.
+Don't disassemble TrueType instructions.  When this option is specified,
+all TrueType programs (glyph programs, the font program and the
+pre-program) are written to the
+.Tn TTX
+file as hexadecimal data instead of
+assembly.  This saves some time and results in smaller
+.Tn TTX
+files.
+.It Fl y Ar n
+When decompiling a TrueType Collection (TTC) file,
+decompile font number
+.Ar n ,
+starting from 0.
+.El
+.Ss "Compilation options"
+The following options control the process of compiling
+.Tn TTX
+files into font files (TrueType or OpenType):
+.Bl -tag -width ".Fl t Ar table"
+.It Fl m Ar fontfile
+Merge the input
+.Tn TTX
+file
+.Ar file
+with
+.Ar fontfile .
+No more than one
+.Ar file
+argument can be specified when this option is used.
+.It Fl b
+Don't recalculate glyph bounding boxes.  Use the values in the
+.Tn TTX
+file as is.
+.El
+.Sh "THE TTX FILE FORMAT"
+You can find some information about the
+.Tn TTX
+file format in
+.Pa documentation.html .
+In particular, you will find in that file the list of tables understood by
+.Nm
+and the relations between TrueType GlyphIDs and the glyph names used in
+.Tn TTX
+files.
+.Sh EXAMPLES
+In the following examples, all files are read from and written to the
+current directory.  Additionally, the name given for the output file
+assumes in every case that it did not exist before
+.Nm
+was invoked.
+.Pp
+Dump the TrueType font contained in
+.Pa FreeSans.ttf
+to
+.Pa FreeSans.ttx :
+.Pp
+.Dl ttx FreeSans.ttf
+.Pp
+Compile
+.Pa MyFont.ttx
+into a TrueType or OpenType font file:
+.Pp
+.Dl ttx MyFont.ttx
+.Pp
+List the tables in
+.Pa FreeSans.ttf
+along with some information:
+.Pp
+.Dl ttx -l FreeSans.ttf
+.Pp
+Dump the
+.Sq cmap
+table from
+.Pa FreeSans.ttf
+to
+.Pa FreeSans.ttx :
+.Pp
+.Dl ttx -t cmap FreeSans.ttf
+.Sh NOTES
+On MS\-Windows and MacOS,
+.Nm
+is available as a graphical application to which files can be dropped.
+.Sh SEE ALSO
+.Pa documentation.html
+.Pp
+.Xr fontforge 1 ,
+.Xr ftinfo 1 ,
+.Xr gfontview 1 ,
+.Xr xmbdfed 1 ,
+.Xr Font::TTF 3pm
+.Sh AUTHORS
+.Nm
+was written by
+.An -nosplit
+.An "Just van Rossum" Aq just@letterror.com .
+.Pp
+This manual page was written by
+.An "Florent Rougon" Aq f.rougon@free.fr
+for the Debian GNU/Linux system based on the existing FontTools
+documentation.  It may be freely used, modified and distributed without
+restrictions.
+.\" For Emacs:
+.\" Local Variables:
+.\" fill-column: 72
+.\" sentence-end: "[.?!][]\"')}]*\\($\\| $\\|   \\|  \\)[   \n]*"
+.\" sentence-end-double-space: t
+.\" End:

_100steps_nw0/config.yaml

@@ -0,0 +1,92 @@
+data:
+  name: PerturbationDataModule
+  kwargs:
+    toml_config_path: ''
+    embed_key: X_state
+    output_space: all
+    pert_rep: onehot
+    basal_rep: sample
+    num_workers: 0
+    pin_memory: true
+    n_basal_samples: 1
+    basal_mapping_strategy: random
+    should_yield_control_cells: true
+    batch_col: gem_group
+    pert_col: gene
+    cell_type_key: cell_line
+    control_pert: non-targeting
+    map_controls: true
+    perturbation_features_file: null
+    store_raw_basal: false
+    int_counts: false
+    barcode: true
+  output_dir: null
+  debug: true
+model:
+  name: state
+  checkpoint: null
+  device: cuda
+  kwargs:
+    cell_set_len: 512
+    blur: 0.05
+    hidden_dim: 696
+    loss: energy
+    confidence_head: false
+    n_encoder_layers: 4
+    n_decoder_layers: 4
+    predict_residual: true
+    softplus: true
+    freeze_pert: false
+    transformer_decoder: false
+    finetune_vci_decoder: false
+    residual_decoder: false
+    batch_encoder: false
+    nb_decoder: false
+    mask_attn: false
+    use_effect_gating_token: false
+    distributional_loss: energy
+    init_from: null
+    transformer_backbone_key: llama
+    transformer_backbone_kwargs:
+      max_position_embeddings: 512
+      hidden_size: 696
+      intermediate_size: 2784
+      num_hidden_layers: 8
+      num_attention_heads: 12
+      num_key_value_heads: 12
+      head_dim: 58
+      use_cache: false
+      attention_dropout: 0.0
+      hidden_dropout: 0.0
+      layer_norm_eps: 1.0e-06
+      pad_token_id: 0
+      bos_token_id: 1
+      eos_token_id: 2
+      tie_word_embeddings: false
+      rotary_dim: 0
+      use_rotary_embeddings: false
+training:
+  wandb_track: false
+  weight_decay: 0.0005
+  batch_size: 16
+  lr: 0.0001
+  max_steps: 100
+  train_seed: 42
+  val_freq: 2000
+  ckpt_every_n_steps: 2000
+  gradient_clip_val: 10
+  loss_fn: mse
+  devices: 1
+  strategy: auto
+wandb:
+  entity: your_entity_name
+  project: state
+  local_wandb_dir: ./wandb_logs
+  tags: []
+name: _100steps_nw0
+output_dir: ''
+use_wandb: true
+overwrite: false
+return_adatas: false
+pred_adata_path: null
+true_adata_path: null

_nw0/config.yaml

@@ -0,0 +1,92 @@
+data:
+  name: PerturbationDataModule
+  kwargs:
+    toml_config_path: ''
+    embed_key: X_state
+    output_space: all
+    pert_rep: onehot
+    basal_rep: sample
+    num_workers: 0
+    pin_memory: true
+    n_basal_samples: 1
+    basal_mapping_strategy: random
+    should_yield_control_cells: true
+    batch_col: gem_group
+    pert_col: gene
+    cell_type_key: cell_line
+    control_pert: non-targeting
+    map_controls: true
+    perturbation_features_file: null
+    store_raw_basal: false
+    int_counts: false
+    barcode: true
+  output_dir: null
+  debug: true
+model:
+  name: state
+  checkpoint: null
+  device: cuda
+  kwargs:
+    cell_set_len: 512
+    blur: 0.05
+    hidden_dim: 696
+    loss: energy
+    confidence_head: false
+    n_encoder_layers: 4
+    n_decoder_layers: 4
+    predict_residual: true
+    softplus: true
+    freeze_pert: false
+    transformer_decoder: false
+    finetune_vci_decoder: false
+    residual_decoder: false
+    batch_encoder: false
+    nb_decoder: false
+    mask_attn: false
+    use_effect_gating_token: false
+    distributional_loss: energy
+    init_from: null
+    transformer_backbone_key: llama
+    transformer_backbone_kwargs:
+      max_position_embeddings: 512
+      hidden_size: 696
+      intermediate_size: 2784
+      num_hidden_layers: 8
+      num_attention_heads: 12
+      num_key_value_heads: 12
+      head_dim: 58
+      use_cache: false
+      attention_dropout: 0.0
+      hidden_dropout: 0.0
+      layer_norm_eps: 1.0e-06
+      pad_token_id: 0
+      bos_token_id: 1
+      eos_token_id: 2
+      tie_word_embeddings: false
+      rotary_dim: 0
+      use_rotary_embeddings: false
+training:
+  wandb_track: false
+  weight_decay: 0.0005
+  batch_size: 16
+  lr: 0.0001
+  max_steps: 1000
+  train_seed: 42
+  val_freq: 2000
+  ckpt_every_n_steps: 2000
+  gradient_clip_val: 10
+  loss_fn: mse
+  devices: 1
+  strategy: auto
+wandb:
+  entity: your_entity_name
+  project: state
+  local_wandb_dir: ./wandb_logs
+  tags: []
+name: _nw0
+output_dir: ''
+use_wandb: true
+overwrite: false
+return_adatas: false
+pred_adata_path: null
+true_adata_path: null

_nw0_bs8/config.yaml

@@ -0,0 +1,92 @@
+data:
+  name: PerturbationDataModule
+  kwargs:
+    toml_config_path: ''
+    embed_key: X_state
+    output_space: all
+    pert_rep: onehot
+    basal_rep: sample
+    num_workers: 0
+    pin_memory: true
+    n_basal_samples: 1
+    basal_mapping_strategy: random
+    should_yield_control_cells: true
+    batch_col: gem_group
+    pert_col: gene
+    cell_type_key: cell_line
+    control_pert: non-targeting
+    map_controls: true
+    perturbation_features_file: null
+    store_raw_basal: false
+    int_counts: false
+    barcode: true
+  output_dir: null
+  debug: true
+model:
+  name: state
+  checkpoint: null
+  device: cuda
+  kwargs:
+    cell_set_len: 512
+    blur: 0.05
+    hidden_dim: 696
+    loss: energy
+    confidence_head: false
+    n_encoder_layers: 4
+    n_decoder_layers: 4
+    predict_residual: true
+    softplus: true
+    freeze_pert: false
+    transformer_decoder: false
+    finetune_vci_decoder: false
+    residual_decoder: false
+    batch_encoder: false
+    nb_decoder: false
+    mask_attn: false
+    use_effect_gating_token: false
+    distributional_loss: energy
+    init_from: null
+    transformer_backbone_key: llama
+    transformer_backbone_kwargs:
+      max_position_embeddings: 512
+      hidden_size: 696
+      intermediate_size: 2784
+      num_hidden_layers: 8
+      num_attention_heads: 12
+      num_key_value_heads: 12
+      head_dim: 58
+      use_cache: false
+      attention_dropout: 0.0
+      hidden_dropout: 0.0
+      layer_norm_eps: 1.0e-06
+      pad_token_id: 0
+      bos_token_id: 1
+      eos_token_id: 2
+      tie_word_embeddings: false
+      rotary_dim: 0
+      use_rotary_embeddings: false
+training:
+  wandb_track: false
+  weight_decay: 0.0005
+  batch_size: 16
+  lr: 0.0001
+  max_steps: 1000
+  train_seed: 42
+  val_freq: 2000
+  ckpt_every_n_steps: 2000
+  gradient_clip_val: 10
+  loss_fn: mse
+  devices: 1
+  strategy: auto
+wandb:
+  entity: your_entity_name
+  project: state
+  local_wandb_dir: ./wandb_logs
+  tags: []
+name: _nw0_bs8
+output_dir: ''
+use_wandb: true
+overwrite: false
+return_adatas: false
+pred_adata_path: null
+true_adata_path: null

analysis/replogle_source_to_filtered_schema/convert_source_to_filtered_schema.py

@@ -0,0 +1,153 @@
+import os
+from pathlib import Path
+import anndata as ad
+import pandas as pd
+import numpy as np
+import scipy.sparse as sp
+
+src_path = Path(os.environ["SRC_REPLOGLE_H5AD"])
+tpl_path = Path(os.environ["TEMPLATE_REPLOGLE_H5AD"])
+out_path = Path(os.environ["CONVERTED_NO_STATE_H5AD"])
+out_path.parent.mkdir(parents=True, exist_ok=True)
+
+print("Reading source:", src_path)
+src = ad.read_h5ad(src_path)
+
+print("Reading template:", tpl_path)
+tpl = ad.read_h5ad(tpl_path, backed="r")
+
+print("SOURCE:", src)
+print("TEMPLATE:", tpl)
+
+# ---------------------------------------------------------------------
+# 1. Standardize required obs columns.
+# ---------------------------------------------------------------------
+required_obs = list(tpl.obs.columns)
+
+# Try to construct key columns if missing.
+if "gene" not in src.obs.columns:
+    for alt in ["target_gene", "perturbation", "perturbation_name", "gene_name"]:
+        if alt in src.obs.columns:
+            src.obs["gene"] = src.obs[alt].astype(str)
+            print(f"Created obs['gene'] from obs['{alt}']")
+            break
+
+if "cell_line" not in src.obs.columns:
+    for alt in ["celltype", "cell_type", "celltype_name"]:
+        if alt in src.obs.columns:
+            src.obs["cell_line"] = src.obs[alt].astype(str)
+            print(f"Created obs['cell_line'] from obs['{alt}']")
+            break
+
+if "gem_group" not in src.obs.columns:
+    for alt in ["batch", "batch_id", "sample", "library", "gemgroup"]:
+        if alt in src.obs.columns:
+            src.obs["gem_group"] = src.obs[alt].astype(str)
+            print(f"Created obs['gem_group'] from obs['{alt}']")
+            break
+    else:
+        src.obs["gem_group"] = "batch0"
+        print("Created dummy obs['gem_group']='batch0'")
+
+for col in ["gene", "cell_line", "gem_group"]:
+    if col not in src.obs.columns:
+        raise ValueError(f"Could not create required obs column {col!r}")
+
+# ---------------------------------------------------------------------
+# 2. Filter cells to template cell lines and perturbations.
+# ---------------------------------------------------------------------
+template_cell_lines = set(tpl.obs["cell_line"].astype(str))
+template_perts = set(tpl.obs["gene"].astype(str))
+
+src.obs["cell_line"] = src.obs["cell_line"].astype(str)
+src.obs["gene"] = src.obs["gene"].astype(str)
+
+keep_cell = src.obs["cell_line"].isin(template_cell_lines)
+keep_pert = src.obs["gene"].isin(template_perts)
+
+print("cells before:", src.n_obs)
+print("keep template cell lines:", int(keep_cell.sum()))
+print("keep template perturbations:", int(keep_pert.sum()))
+print("keep both:", int((keep_cell & keep_pert).sum()))
+
+src = src[keep_cell & keep_pert].copy()
+
+# ---------------------------------------------------------------------
+# 3. Align genes/vars to template var_names.
+# ---------------------------------------------------------------------
+template_vars = list(tpl.var_names.astype(str))
+source_vars = list(src.var_names.astype(str))
+
+missing_vars = [g for g in template_vars if g not in set(source_vars)]
+extra_vars = [g for g in source_vars if g not in set(template_vars)]
+
+print("template vars:", len(template_vars))
+print("source vars after cell filtering:", len(source_vars))
+print("missing template vars from source:", len(missing_vars))
+print("extra source vars not in template:", len(extra_vars))
+
+if missing_vars:
+    print("First missing vars:", missing_vars[:30])
+    raise ValueError(
+        "Source file does not contain all template genes. "
+        "Do not zero-fill unless you intentionally want a non-equivalent dataset."
+    )
+
+src = src[:, template_vars].copy()
+
+# Copy template var annotations exactly, since we aligned var_names.
+src.var = tpl.var.copy()
+
+# ---------------------------------------------------------------------
+# 4. Standardize obs dataframe to template columns.
+# ---------------------------------------------------------------------
+for col in required_obs:
+    if col not in src.obs.columns:
+        src.obs[col] = pd.NA
+
+# Keep template obs column order. Extra columns are dropped for strict schema.
+src.obs = src.obs[required_obs].copy()
+
+# Match categorical-ish behavior for key columns.
+template_gene_order = list(pd.Series(tpl.obs["gene"].astype(str)).drop_duplicates())
+template_cell_order = list(pd.Series(tpl.obs["cell_line"].astype(str)).drop_duplicates())
+
+src.obs["gene"] = pd.Categorical(src.obs["gene"].astype(str), categories=template_gene_order)
+src.obs["cell_line"] = pd.Categorical(src.obs["cell_line"].astype(str), categories=template_cell_order)
+src.obs["gem_group"] = src.obs["gem_group"].astype(str).astype("category")
+
+# ---------------------------------------------------------------------
+# 5. Create X_hvg in the same var order as the template.
+# ---------------------------------------------------------------------
+if "highly_variable" in src.var.columns:
+    hvg_mask = src.var["highly_variable"].astype(bool).to_numpy()
+else:
+    raise ValueError("Template var did not contain highly_variable")
+
+x_hvg = src[:, hvg_mask].X
+if sp.issparse(x_hvg):
+    x_hvg = x_hvg.toarray()
+src.obsm["X_hvg"] = np.asarray(x_hvg, dtype=np.float32)
+
+# Remove old state/vci embeddings if inherited from source.
+for key in ["X_state", "X_vci"]:
+    if key in src.obsm:
+        del src.obsm[key]
+
+# Keep uns hvg if present.
+if "hvg" in tpl.uns:
+    src.uns["hvg"] = tpl.uns["hvg"]
+
+print("\nCONVERTED:", src)
+print("obs columns:", list(src.obs.columns))
+print("var columns:", list(src.var.columns))
+print("obsm keys:", list(src.obsm.keys()))
+print("X_hvg shape:", src.obsm["X_hvg"].shape)
+print("gene nunique observed:", src.obs["gene"].astype(str).nunique())
+print("cell_line counts:")
+print(src.obs["cell_line"].astype(str).value_counts())
+
+src.write_h5ad(out_path, compression="gzip")
+print("Wrote:", out_path)
+
+tpl.file.close()

analysis/replogle_source_to_filtered_schema/replogle_source_filtered_schema_no_xstate.h5ad

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a75a81eb9d15be6b9b9810e47f88a29c43b95a0746cfc0c7f35c20d0592593a
+size 6730798201

analysis/replogle_source_to_filtered_schema/replogle_source_filtered_schema_with_xstate.h5ad

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7363e01c57adccf90244044c959efdb1e5fdbda4778d62a6e0b2199c6c21ad83
+size 27342995251

analysis/replogle_source_to_filtered_schema/schema_report/schema_report.txt

@@ -0,0 +1,21 @@
+source_shape=(643413, 6642)
+template_shape=(643413, 6546)
+source_obs_cols=['gem_group', 'gene', 'gene_id', 'transcript', 'gene_transcript', 'sgID_AB', 'mitopercent', 'UMI_count', 'z_gemgroup_UMI', 'cell_line']
+template_obs_cols=['gem_group', 'gene', 'gene_id', 'transcript', 'gene_transcript', 'sgID_AB', 'mitopercent', 'UMI_count', 'z_gemgroup_UMI', 'cell_line']
+source_var_cols=['highly_variable', 'means', 'dispersions', 'dispersions_norm']
+template_var_cols=['start', 'end', 'class', 'strand', 'length', 'in_matrix', 'highly_variable', 'means', 'dispersions', 'dispersions_norm']
+source_obsm_keys=['X_hvg']
+template_obsm_keys=['X_hvg', 'X_state', 'X_vci']
+obs_cols_missing_from_source=[]
+obs_cols_extra_in_source=[]
+template_vars=6546
+source_vars=6642
+var_overlap=6546
+template_vars_missing_from_source=0
+source_vars_not_in_template=96
+source_cell_line_nunique=4
+template_cell_line_nunique=4
+source_gene_nunique=2024
+template_gene_nunique=2024
+source_gem_group_nunique=56
+template_gem_group_nunique=56

analysis/replogle_source_to_filtered_schema/schema_report/source_cell_line_counts.csv

@@ -0,0 +1,5 @@
+cell_line,count
+k562,188590
+jurkat,184470
+rpe1,173737
+hepg2,96616

analysis/replogle_source_to_filtered_schema/schema_report/source_gem_group_counts.csv

@@ -0,0 +1,57 @@
+gem_group,count
+25,14398
+44,13937
+3,13748
+7,13462
+12,13295
+31,13276
+16,13189
+42,13033
+33,13013
+2,12996
+22,12984
+29,12976
+11,12836
+38,12830
+14,12765
+34,12744
+39,12724
+20,12715
+13,12672
+24,12672
+40,12527
+47,12448
+8,12441
+35,12425
+5,12418
+30,12384
+6,12381
+18,12316
+43,12239
+26,12073
+10,12037
+19,11882
+17,11846
+28,11755
+15,11716
+46,11486
+9,11452
+27,11322
+32,11302
+37,11142
+23,11138
+4,10808
+45,10566
+48,10270
+36,9725
+1,9697
+55,9632
+53,8683
+21,8580
+54,8416
+49,8068
+41,7995
+52,7894
+51,7877
+56,6949
+50,5258

analysis/replogle_source_to_filtered_schema/schema_report/source_gene_counts.csv

@@ -0,0 +1,2025 @@
+gene,count
+non-targeting,39165
+TFAM,7145
+SLC1A5,4284
+GFM1,3969
+MRPL36,3254
+PPP6C,3210
+MRPL35,2881
+TARDBP,2523
+CCDC6,2230
+GTF3C4,2049
+HSD17B10,1685
+FBXO42,1628
+GTF2E2,1495
+ZDHHC7,1428
+PSMB5,1414
+TRNT1,1388
+TMEM214,1371
+TIMM23B,1327
+FAM136A,1308
+CPSF3,1274
+TMEM242,1265
+MRPL34,1241
+TWF1,1214
+POGLUT3,1147
+C7orf26,1104
+MYBL2,1091
+PPP1R37,1089
+MED19,1088
+CLOCK,1071
+THAP1,1068
+EIF4B,1053
+TPT1,994
+TRAPPC11,979
+SRP72,959
+HSD17B12,959
+ZBTB17,958
+RHOQ,954
+TSR2,935
+SSBP3,934
+CHMP6,927
+SMG5,904
+SLC39A9,884
+SLC7A5,880
+INTS14,877
+GPS1,867
+CLASRP,859
+CSE1L,858
+NCBP2,849
+PMF1,828
+EIF2B2,819
+PMPCB,819
+HSCB,810
+SHQ1,792
+NAA35,776
+TFDP1,767
+ZNF236,766
+EIF2B5,763
+SSU72,757
+DDX55,745
+INTS13,742
+RNF8,736
+LAMTOR1,735
+MCM3,731
+SLC35G2,731
+WTAP,718
+RAC3,718
+SART3,712
+RABGGTA,711
+BUB1,707
+MED12,706
+WDR4,705
+RAB4A,690
+EIF2B1,688
+DONSON,688
+SPC25,687
+ZMAT2,686
+MRPL39,677
+HUS1,675
+NLE1,670
+POLRMT,668
+BTF3L4,665
+MED14,664
+RPL23,659
+ANKRD11,659
+HMGCS1,659
+GOLT1B,655
+DDX19A,654
+UROD,652
+MCM6,651
+H2AFZ,650
+RPS13,650
+SRSF6,648
+RPS19,646
+PDCD6IP,644
+CNN2,641
+HSPA9,640
+PLK4,639
+ATP6V1B2,638
+MRPS21,638
+ZNHIT3,634
+RNF14,632
+POLR1E,631
+DNAJC8,627
+ARGLU1,627
+MAD2L2,626
+QARS,625
+WDR54,625
+TACC3,622
+SNRNP40,619
+GLRX5,617
+VPS41,616
+ADAM10,611
+INTS8,609
+NFRKB,606
+DNAJC19,606
+RNASEH2C,604
+SLU7,601
+DDX51,601
+NELFB,598
+FNBP4,593
+MRPL24,592
+NRDE2,592
+PPP2R1A,591
+BAP1,590
+VPS54,589
+PDCD5,589
+SNAPC3,586
+NAGLU,585
+BTF3,585
+METTL3,584
+RBMX2,582
+DCTN3,580
+SRA1,577
+ANKS6,576
+CHORDC1,574
+DDX5,574
+DSTYK,574
+LSM6,572
+PTMA,570
+INTS2,570
+NAA25,569
+MVK,568
+SRPRB,568
+ELL,567
+MRPL38,564
+RAB4B,563
+MRPS6,563
+MRPL16,562
+TEX10,562
+C9orf16,562
+CDK2,560
+ASF1B,559
+ISCA2,558
+RIOK1,558
+COX11,555
+ATP6AP2,554
+PPME1,553
+RPL41,551
+PFN1,551
+PPP2CA,551
+JMJD6,550
+PCBP1,549
+SDHAF2,547
+MBTPS1,545
+PARN,544
+MIS18BP1,544
+GNPNAT1,543
+PSMG3,543
+GPN3,543
+SRP68,543
+RARS2,541
+CDIPT,541
+GINS1,540
+XPO5,540
+CENPT,539
+SRP9,538
+NOM1,535
+ACTR1B,535
+THOC7,534
+ORC1,533
+WDR3,533
+TBCA,531
+ELP3,530
+CSTF1,530
+DRAP1,529
+MCMBP,529
+RPL24,528
+MRPL3,525
+DHX16,525
+NIFK,523
+GYG1,522
+KRR1,521
+TRMT112,521
+ACTR8,520
+TRAPPC5,519
+EIF4E,517
+MZT1,515
+DNMT1,514
+CENPJ,512
+CNOT3,511
+TAF13,510
+NAPG,508
+HARS,508
+GTF3C6,508
+NARS2,507
+MANF,506
+XRCC1,506
+ATP5MF,506
+ATR,506
+RARS,504
+RBM10,503
+NISCH,503
+TXNL4B,502
+RPS12,501
+PGAM1,499
+TMX2,498
+COG6,497
+EIF4G1,495
+MED10,495
+GTF2H1,495
+CS,494
+DOHH,493
+DHX37,492
+CMPK1,491
+EIF2B4,491
+MRPL27,489
+KIAA1143,489
+CHCHD4,486
+BRCA2,486
+STIL,486
+NUDCD3,485
+NDUFB4,485
+MSRB1,485
+URB2,484
+RTRAF,483
+TIMM8A,483
+DHX36,483
+LETM1,482
+MIOS,482
+PHB2,480
+EXOSC2,479
+COPS8,478
+GNL2,478
+MRPL41,477
+DCTN4,477
+FAM207A,476
+SNX15,475
+YRDC,474
+SSRP1,473
+UXS1,472
+COG2,472
+UBA2,470
+PRELID3B,470
+RABGGTB,469
+QRSL1,469
+UTP23,468
+COQ2,468
+COX7C,468
+ESF1,468
+DHX15,466
+MICOS10,464
+CIAPIN1,464
+MTG2,463
+HSP90B1,462
+COX10,462
+GFOD2,462
+E2F6,460
+TAF1D,460
+VARS,459
+BCL2L1,459
+EMC7,459
+ARPC4,459
+FASTKD5,458
+MLLT6,458
+IPO9,458
+MRPS16,457
+UBE2L3,456
+RPL7,456
+SP1,456
+MBTPS2,455
+DBR1,455
+POLR2I,455
+NDUFAB1,454
+KDM6A,454
+NDUFB8,453
+TARS2,453
+INTS9,453
+ELP5,452
+DLD,452
+MRPL54,452
+CCNH,452
+THAP11,452
+PI4KA,451
+ELOVL1,450
+DYNLL2,450
+ORC4,450
+NELFCD,449
+PPIA,449
+SOD2,448
+SMN2,446
+DAP3,446
+PAXBP1,446
+HJURP,446
+COX5A,446
+ACTR2,446
+YEATS2,446
+DDX52,445
+USP14,445
+PDCD6,445
+DCTN1,445
+PPA1,445
+URI1,444
+MRPL14,444
+C17orf58,444
+DDX23,442
+UFL1,442
+RCL1,441
+LTV1,441
+SBNO1,441
+KTI12,441
+RPL26,440
+EXOSC4,440
+METTL1,439
+RPP21,439
+MOB4,439
+MED11,438
+SDAD1,438
+TUBGCP2,437
+GRSF1,435
+TRRAP,435
+E4F1,435
+POP7,434
+NFATC2IP,434
+COA5,432
+PDCD11,432
+PET117,432
+SETDB1,431
+CCDC59,431
+PTPMT1,431
+LARS2,430
+DNAJA3,430
+DCTN2,429
+FAM32A,429
+TRA2B,429
+GET3,428
+SS18L2,428
+RPL36,427
+PNPT1,426
+CSNK2B,426
+TUBB2A,425
+SRRT,425
+HAUS8,425
+SF3B3,425
+TSEN2,424
+WDR12,424
+RPAP2,424
+NUDC,424
+CBX1,424
+SRP14,423
+PSMD4,423
+MON1A,423
+DRG1,422
+ALG2,422
+YARS2,421
+COASY,421
+EDC4,421
+GCLC,421
+RPS27A,421
+RPUSD3,421
+NAF1,420
+NOL8,420
+TTC1,420
+UBE2H,420
+DOLK,419
+TUBB,418
+CCDC115,418
+GFER,418
+THOC6,417
+OIP5,417
+NACA,416
+YEATS4,416
+CEBPZ,416
+MRPL50,415
+SUPT5H,415
+NSUN4,415
+IMPDH2,415
+RPL36A,414
+SCAP,414
+DCAF6,413
+NDUFB3,413
+MRPL1,413
+KDM1A,413
+GINS4,412
+TAF8,412
+UBL5,412
+RPL6,412
+MRPS35,412
+PHB,411
+NOL11,411
+MED30,411
+TM7SF2,411
+LSG1,410
+ING3,410
+CHTOP,410
+NUP133,409
+C9orf78,409
+DENR,409
+HSPA14,408
+AATF,408
+NPLOC4,407
+MED1,406
+IARS2,406
+NCAPH2,406
+PSAT1,406
+TRAPPC3,406
+CPNE7,405
+SLC39A10,404
+RRS1,404
+RAD51D,403
+TPX2,403
+MRPS34,403
+SUPT20H,403
+GRWD1,403
+ERAL1,402
+UTP15,402
+GINS2,402
+DERL2,402
+TUBE1,401
+WDR18,400
+RPS7,398
+CHMP7,398
+DCUN1D5,397
+ORC5,397
+MRPL4,396
+PRPF39,395
+RNF20,395
+UBE2M,395
+MRPS5,394
+RPS6,394
+PSME2,393
+OXA1L,393
+KEAP1,392
+SPCS3,392
+ATP5PD,391
+ALG14,391
+RPP14,391
+TIMM13,390
+SEPHS2,390
+RTEL1,390
+AAAS,389
+MPHOSPH6,389
+ANAPC13,389
+EIF3H,389
+ARL2,389
+YARS,388
+NAA20,388
+NDUFA6,387
+SNRPG,387
+NOP14,387
+NUBP2,387
+HAUS4,385
+MBD3,385
+TBP,385
+TAMM41,384
+COPS4,384
+EIF6,384
+EXOSC5,384
+IGBP1,384
+VPS35,384
+ELOB,383
+CD3EAP,383
+EIF1,383
+MTOR,383
+EFR3A,383
+MFN2,382
+TUBGCP5,382
+RMI1,382
+EHMT2,382
+TTI1,382
+RPL30,381
+EIF3M,381
+RRP12,380
+STXBP4,380
+MED4,380
+CCNB1,380
+TMEM127,379
+GMPPB,379
+ABCB7,379
+NUP54,379
+CENPE,378
+BRIP1,378
+MRGBP,377
+VPS13D,377
+SEM1,377
+NARS,377
+SNRNP48,377
+MMS19,376
+ABHD17A,376
+DDX1,376
+FDXR,376
+RINT1,376
+CCT4,375
+MRPS26,375
+POLR2B,375
+AARS2,375
+BRIX1,375
+FCF1,374
+CIAO1,374
+TRMT6,373
+TOMM22,373
+DPH6,372
+BDP1,371
+EIF2S1,371
+PRRC2A,370
+VEZT,370
+WDR36,369
+GRPEL1,369
+LSM2,369
+SPTSSA,368
+POP5,368
+VPS29,368
+TEFM,368
+LSM10,368
+ATP11B,367
+CAMLG,367
+PNN,367
+PELP1,367
+NOC3L,367
+U2SURP,366
+TTC4,366
+PCNX3,366
+INO80B,364
+EARS2,364
+UXT,364
+TUBD1,363
+H2AFX,363
+MNAT1,363
+EIF3B,363
+MAX,362
+DIMT1,362
+FARSA,362
+LAMTOR4,362
+TFRC,362
+XRCC2,362
+GUK1,361
+POP4,361
+MRPS25,361
+RPS24,361
+CMTR1,360
+DHODH,360
+FYN,360
+GSPT1,360
+DDX19B,360
+GEMIN5,359
+MRPL10,359
+TOE1,358
+ACTR6,358
+CHTF18,358
+TIMM9,357
+PPP1R8,357
+KANSL3,357
+ZCRB1,357
+ZNF292,357
+POLR2M,356
+CXXC1,356
+PSTK,355
+OSTC,355
+RPS27,355
+ACTB,355
+NASP,354
+BUB3,354
+CYCS,354
+NOLC1,353
+ERCC2,353
+SEH1L,353
+CABIN1,353
+TLCD1,353
+FAF2,353
+EIF3L,352
+TMED10,352
+DNTTIP2,352
+DDX17,351
+MRPL18,351
+GTF3C1,351
+IPO13,351
+DPY19L4,351
+TMSB10,351
+TAF2,350
+SETX,350
+CTU2,350
+IST1,349
+MRPL19,349
+EXOC5,349
+SPATA5L1,349
+PNKP,349
+HECTD1,348
+PPP1R2,348
+CNOT1,347
+CWF19L2,347
+ATP6AP1,346
+NUB1,346
+MRPS7,346
+RPP30,346
+TIMM10,346
+MCM7,345
+PTPN11,345
+EXOC1,345
+MMGT1,345
+RPS28,345
+MRPS10,344
+LAS1L,344
+EIF2B3,344
+ZRSR2,344
+CUL1,343
+NUP88,343
+SACM1L,343
+ABT1,343
+ATP6V0C,343
+NELFE,342
+TGS1,342
+METTL17,342
+SRF,341
+PXN,341
+DDX21,341
+MVD,341
+GTF2E1,340
+RNF123,340
+ELOF1,340
+TMEM258,340
+DNAJA1,340
+RPA3,339
+SRP54,339
+TNRC6A,339
+ELP2,338
+GTF2H4,338
+ALG13,338
+NDUFA3,338
+RUVBL1,338
+BUB1B,337
+DICER1,336
+NRBP1,336
+TUBA1B,336
+MED22,336
+DPH2,335
+NAA10,335
+SNF8,334
+RAC1,334
+TTK,333
+TOP3A,333
+COX6C,333
+GTF3C5,333
+TUFM,333
+SRBD1,332
+USP9X,332
+RPS15A,332
+HSPE1,331
+POLD1,331
+NIP7,331
+ELAC2,331
+PYROXD1,330
+MAT2A,330
+INO80C,330
+NDUFS3,329
+ATP6V1G1,329
+MKRN1,329
+UBQLN4,329
+RRP9,329
+ZW10,329
+WDHD1,328
+ATP2A2,328
+PAF1,328
+RTCB,327
+PTK2,327
+NDUFB6,327
+RPS3,325
+NVL,325
+COPS6,325
+TADA3,324
+EIF4H,324
+NCAPG2,324
+EXOSC8,323
+SMC1A,323
+TP53RK,323
+TAF6,322
+KRI1,322
+SNUPN,322
+EIF4G2,322
+IPO7,322
+MRPS27,322
+DCTN6,322
+HNRNPC,322
+UPF2,322
+POLR3C,321
+LSM12,321
+UQCRQ,321
+INTS12,320
+MED7,320
+MED20,320
+MRPS28,320
+DDX41,320
+PRORP,319
+TOMM40,319
+TSFM,319
+WDR5,319
+UBE2N,319
+CDK1,318
+ALDOA,318
+GPKOW,317
+MIPEP,317
+NKAPD1,317
+WDR75,316
+CCDC86,316
+CCT3,316
+GTF3C2,315
+WDR83OS,315
+DNM1L,315
+DNM1,315
+PRPF18,315
+TRAPPC4,315
+BMS1,314
+NUP85,314
+KIN,314
+MED6,314
+CCDC137,314
+DHX33,314
+ORC3,314
+SCAF1,313
+MRPS23,313
+SKA3,313
+GTF2A2,313
+NSMCE2,312
+SPRTN,312
+BPTF,312
+SYS1,311
+NELFA,311
+SPG7,311
+RPUSD4,311
+KATNB1,311
+RFC3,310
+BET1,310
+DDX10,310
+TSEN34,310
+MRPL9,309
+SRSF7,309
+ZFC3H1,309
+RPLP2,309
+SMC5,309
+CCT7,308
+MRPL37,308
+ZNF720,308
+PITRM1,308
+PMPCA,308
+TRAPPC1,307
+PSMG2,306
+MCM2,306
+MRPS11,306
+CD2BP2,306
+PGD,306
+CHCHD2,306
+COQ4,306
+KLC2,306
+VPS33A,306
+PPP4R2,305
+STRAP,305
+SURF6,304
+RPL31,304
+GEMIN4,304
+FBXW7,303
+PSME1,303
+POGZ,303
+ABCE1,303
+UTP20,303
+HERC1,303
+MBNL1,303
+GNL3,302
+SETD5,302
+RNF40,302
+SYMPK,302
+RPL17,302
+NDUFA11,301
+NMD3,301
+PES1,301
+MYBBP1A,301
+PGK1,301
+VPS37A,301
+SRSF10,300
+EGLN2,300
+TRAPPC8,300
+URM1,299
+SKP2,299
+MRPS17,299
+RPA2,299
+LONP1,298
+NBAS,298
+GTF2F2,297
+CDC6,297
+RPS14,297
+ARL4D,297
+CCT2,297
+MRPL55,297
+RPS4X,297
+EXOSC3,297
+MRPL20,296
+MCL1,296
+EXOC2,296
+MRPS9,295
+ATP6V0B,295
+NOB1,295
+NKAP,295
+ATP5ME,295
+TP53I13,295
+SCD,294
+TARS,294
+SARS2,293
+MRPL2,293
+HEATR1,293
+SAE1,293
+INO80,293
+NEDD8,292
+PRPF3,292
+N6AMT1,292
+DDX27,292
+IMP4,292
+INTS1,291
+DPM2,291
+WNK1,290
+MRPL33,290
+MALSU1,290
+PGS1,290
+NDUFAF3,290
+SUPT6H,289
+NDUFB10,289
+EEF1G,289
+GLRX3,289
+LRR1,289
+H3F3A,288
+NUP214,288
+KIF18B,288
+AIFM1,288
+CCNL1,286
+TNPO3,286
+BCS1L,286
+NSA2,286
+RPAP1,286
+ENO1,285
+DDX11,285
+ANAPC11,285
+AHCY,285
+BRF1,285
+SMAGP,284
+THOC3,284
+RPL14,284
+GTPBP4,284
+C19orf25,284
+HNRNPA1,284
+FXN,284
+ERCC3,284
+LST1,283
+PTPN1,282
+IWS1,282
+DPAGT1,282
+AKIRIN2,282
+TIPIN,281
+OSGEP,281
+SHC1,281
+BRK1,281
+CDC16,281
+HMGA1,280
+CENPW,280
+GTF2A1,280
+MRPS22,279
+SNRNP35,279
+TPR,279
+MRPS18A,279
+ATP1A1,279
+PPP2R3C,279
+CHD4,279
+RAB6A,278
+COG4,278
+C19orf53,278
+RPL10A,278
+PALB2,277
+PKMYT1,277
+CPSF1,277
+STAT5B,277
+ELP6,276
+COX17,276
+PPRC1,276
+MTBP,276
+NHLRC2,276
+COQ5,276
+WDR77,276
+RBM28,276
+ADSL,276
+PFDN4,275
+DDX18,275
+UQCRB,275
+ATRIP,275
+SERBP1,274
+SLC39A7,274
+METAP1,274
+NAA15,274
+CENPN,274
+POLD2,274
+MRPL51,274
+TMA16,273
+ILF3,273
+BRF2,273
+OGFOD1,273
+GAR1,273
+BNIP1,273
+LTBP3,272
+TBPL1,272
+DSN1,272
+ASCC3,272
+TADA2A,272
+HUWE1,272
+ATP6V0D1,271
+PNO1,271
+MAK16,271
+NDC1,271
+LSM3,271
+DDX24,271
+ZNHIT2,271
+KIF4A,271
+POLG2,271
+RAD51,270
+NDUFA4,270
+TRMT5,270
+NUP35,270
+ZC3H13,269
+NEMF,269
+PRELID1,269
+RPL35A,268
+NOP16,268
+TOX4,268
+COMTD1,267
+RPS2,267
+MED8,267
+NOL12,267
+UTP18,267
+PPA2,266
+NAA50,266
+CEP97,266
+EIF3J,266
+LSM7,266
+COTL1,266
+SEPSECS,265
+NHP2,265
+RBBP5,265
+RPS11,265
+RNF113A,264
+TINF2,264
+RNGTT,264
+SRRM1,264
+TEN1,264
+ZNF100,264
+PPIL1,264
+UBR5,264
+PPAN,263
+RFT1,263
+RPL26L1,263
+PGAM5,263
+NSF,262
+STRIP1,262
+NUP107,262
+EIF3D,262
+USP10,262
+VPS72,261
+TMEM199,261
+INTS3,261
+GTF2H3,261
+VPS25,261
+BRCA1,261
+DDX56,261
+DHDDS,261
+CNOT10,260
+MRPL15,260
+C1D,260
+GNB1L,260
+CPSF4,260
+DDX20,260
+PABPC4,260
+LDB1,260
+HDAC3,259
+MRPS24,259
+SEC61G,259
+NCAPD2,259
+TOP1,258
+MCM5,258
+MYSM1,258
+PPARGC1B,258
+FNTA,258
+GTF2H2,258
+C12orf45,258
+MEX3A,258
+MRPL17,257
+TRMT10C,257
+VHL,257
+INF2,256
+CUL2,256
+MPHOSPH10,256
+TUBG1,255
+SASS6,255
+PRPF4,255
+POLA2,255
+ENY2,254
+CCT6A,254
+MAGOH,254
+CDK9,254
+FEN1,254
+HNRNPR,254
+MYCBP,253
+RNMT,253
+CASC3,252
+GABPA,252
+CENPK,252
+RPS18,252
+CUL3,252
+CSNK1A1,252
+UFM1,252
+RFC2,252
+PPP2CB,252
+UBA1,251
+STARD7,250
+ANKRD49,250
+ILF2,250
+PTEN,250
+METAP2,249
+PPP1R15B,249
+PPP4C,249
+PPP1R11,249
+DYNC1H1,248
+ATF5,248
+GBF1,248
+XPO1,248
+ZNHIT6,248
+PRPF19,248
+HINFP,248
+POLR3F,248
+FBLIM1,247
+COX5B,247
+TCERG1,247
+ZNRD1,246
+LPIN1,246
+PAM16,246
+GTF3C3,246
+MEN1,245
+PHF10,245
+RPL36AL,245
+ARMC6,245
+FAU,245
+IFITM2,244
+GPS2,244
+SUPV3L1,244
+MRPL28,244
+VARS2,244
+CCAR1,244
+SNRNP27,244
+XRCC5,244
+WDR46,244
+TSEN54,243
+TAF11,243
+SRRM2,243
+DDOST,243
+LRP5,243
+RBMXL1,243
+DNAJC17,242
+SLC7A6OS,242
+CNIH4,242
+DBF4,242
+NOL7,242
+CCNC,242
+UBA5,242
+ATL2,241
+ALG1,241
+VBP1,241
+POLR3E,241
+RPL23A,241
+ANKLE2,241
+BARD1,241
+SEC63,241
+SNRPC,241
+THRAP3,240
+OPA1,240
+URB1,240
+NAA30,239
+EXOSC7,239
+RPL29,239
+RFC5,239
+LRPPRC,238
+CHCHD1,238
+METTL14,238
+SIRT7,237
+COG1,237
+SAMD4B,237
+PCNA,237
+DPH3,236
+RPF1,236
+SLBP,236
+RPE,236
+PPIL4,236
+CTR9,235
+CAPZB,235
+KANSL2,235
+SDHC,235
+ABHD11,235
+UHRF1,235
+TPRKB,234
+LARS,234
+PIK3C3,234
+HIST1H2BC,234
+KIF14,233
+SF3B5,233
+AP2M1,233
+YTHDC1,233
+MRPL44,233
+CSTF3,233
+GLE1,232
+TAZ,232
+ARMC7,232
+SCNM1,232
+TBCB,232
+EPRS,231
+ATP6V1D,231
+TCOF1,231
+TFB1M,231
+TOMM20,231
+CDC123,231
+PRPF4B,231
+EMC4,230
+NUP98,230
+SNAPC5,230
+POLR3D,229
+SMC6,229
+PRDM4,229
+SPCS2,228
+ADRM1,228
+NDUFB7,228
+BYSL,228
+NOC4L,228
+MIS18A,228
+MARS,228
+GGPS1,228
+WDR70,228
+MRPL43,227
+EXOSC1,227
+CEP85,226
+MCM3AP,226
+RRN3,226
+UBE2D3,226
+SBDS,226
+PRPF31,226
+TIMM44,226
+MT2A,225
+ZFR,225
+PRIM1,224
+HIST1H2BN,224
+SUDS3,224
+RPL39,224
+POP1,224
+SKA1,223
+LSM4,223
+CALR,223
+HS6ST1,223
+COX7B,223
+DYNLL1,223
+TAF7,223
+RIOK2,223
+POLR3B,223
+MFAP1,222
+POLE,222
+UCHL5,222
+WDR43,222
+POLR1B,222
+RPL27A,222
+INTS4,221
+EIF3I,221
+PFDN2,221
+EP400,221
+SMG7,221
+SUPT16H,221
+MRPS31,221
+MLST8,220
+PRPF40A,220
+ISG20L2,220
+CHMP5,220
+MRPS2,220
+RPS19BP1,219
+DHPS,219
+INTS10,219
+BCLAF1,219
+EXOC7,219
+RRP7A,218
+SEC61B,217
+PEX19,217
+ZC3H4,217
+ATP6V1E1,216
+SNAPC1,216
+TAF3,216
+ZCCHC9,216
+PTPN23,216
+THOC2,216
+TELO2,216
+NPM1,216
+WDR61,215
+ATP6V1H,215
+COX15,215
+ETF1,215
+UQCRFS1,215
+SOD1,215
+CEP152,215
+AFG3L2,215
+USF2,214
+GTF3A,214
+MRPS30,214
+PRIM2,214
+CYC1,214
+TWISTNB,214
+PABPN1,213
+CDC42,213
+RAD9A,213
+EMC1,213
+RPN1,213
+SRP19,213
+PPIH,213
+CNOT2,213
+TEAD3,212
+RTTN,212
+SRFBP1,212
+ATP5PO,212
+SUGP1,212
+CBLL1,212
+HBS1L,212
+BRD2,212
+SUGT1,212
+CWC25,211
+UBE2I,211
+BCR,211
+NFYC,211
+NOP9,211
+RPS26,211
+MDN1,210
+SEC16A,210
+COPS2,210
+UBE2Z,209
+RRM2,209
+TERF2,209
+KCTD10,208
+TXN,208
+NUP62,208
+ATP6V1A,208
+PIK3R4,207
+RPL28,207
+PIGH,207
+SNRNP25,207
+NUDT15,207
+MTPAP,206
+SNRNP200,206
+TADA1,206
+TADA2B,206
+DAXX,206
+RPN2,206
+MED17,206
+PDPK1,206
+TAF10,205
+PSMD9,205
+WARS,205
+UQCRC2,205
+SHOC2,205
+KXD1,204
+PSMC5,204
+RBM15,204
+NUP43,204
+RPL38,204
+ZNF468,204
+UTP6,203
+SSBP1,203
+UBAP1,203
+SLC25A3,203
+RPP40,203
+PPP1CB,202
+KDM5C,202
+TAF12,202
+COPS3,201
+EPB41L2,201
+AURKAIP1,201
+HIPK1,201
+SFSWAP,201
+CCT8,200
+REXO2,200
+GLB1,200
+HNRNPH1,200
+RRP1,200
+BTAF1,199
+AARS,199
+CLPB,199
+RBM14,199
+IPO11,198
+MRPL22,198
+KAT7,198
+RPL15,198
+PPIL2,198
+GARS,198
+TMED2,198
+CRLS1,198
+DKC1,198
+HMGCR,198
+RPL19,198
+KPNA6,198
+DDX6,198
+CLCC1,198
+SART1,198
+EXOC4,198
+BCAS2,197
+AASDHPPT,197
+COPE,197
+MTHFD1,197
+ZFP69B,197
+NUP153,197
+CDC73,196
+DDX59,196
+HMGB3,196
+GSK3B,195
+SYF2,195
+RBBP8,195
+DR1,195
+XRCC6,195
+RANGAP1,195
+CDT1,194
+GNL3L,194
+SNRPD1,194
+TKT,194
+CENPC,193
+RPL8,193
+MRPS33,193
+EIF4A3,193
+PDRG1,192
+KPNB1,192
+NDUFA8,192
+FAM50A,192
+PSMD13,192
+AURKA,192
+CASP8AP2,192
+VPS51,192
+CHMP3,191
+RPL37A,191
+RAMAC,191
+BAG6,191
+PSMA4,191
+RBX1,191
+PFDN5,190
+CYFIP1,190
+CHAF1B,190
+RAD51C,190
+MCM10,190
+LAMTOR2,189
+YPEL5,189
+SETD2,188
+LENG8,188
+POLR3H,188
+GEMIN6,188
+LZTR1,188
+SARNP,188
+GTF2H2C,188
+SP2,187
+SDE2,187
+MRPL45,187
+GEMIN8,187
+WDR44,187
+CWC15,186
+DCTN5,186
+NOP10,186
+HDAC7,186
+UBA3,186
+MRPL46,185
+TWNK,185
+PDAP1,185
+RAB18,185
+C1QBP,185
+SMC2,185
+HMGN2,185
+POLD3,184
+LSM5,184
+ZMAT5,184
+RPS3A,184
+ACTR10,184
+NCKAP1,183
+GABPB1,183
+CPOX,183
+IARS,183
+ZNF706,183
+SAMM50,183
+NOP58,183
+FGFR1OP,183
+PDCD2,183
+LIMS1,182
+HGS,182
+SMG8,182
+UBE3C,182
+NUBP1,181
+NAE1,181
+MAD2L1,181
+DAD1,181
+CTDP1,180
+RPS8,180
+POLR1A,180
+GPN1,180
+CTNNBL1,180
+RPL35,179
+CCP110,179
+AC118549.1,179
+RAD17,178
+SDHA,178
+TSPYL5,178
+RPL10,177
+MED21,177
+YKT6,176
+RPLP0,176
+TRPM7,176
+RSRC2,176
+DNAJC11,176
+SMG9,176
+TOR2A,175
+PUM1,175
+TRIAP1,175
+UBE3D,175
+VPS18,175
+CCDC84,174
+CEP68,174
+PSMB2,174
+TUBA1C,174
+SRSF1,174
+CINP,174
+MSL1,174
+CLNS1A,173
+VPS37C,173
+IMPA2,173
+FBL,173
+TUBGCP4,172
+DARS,172
+RBM42,172
+MRPL32,171
+CFL1,171
+HMX3,171
+TIMM22,171
+INTS5,171
+STAT5A,170
+POLR2G,170
+METTL23,170
+RPS9,170
+SPEN,170
+TRAIP,169
+SMUG1,169
+MRPL49,169
+RNPC3,169
+STX5,169
+SGPP1,169
+BOD1L1,169
+SLC35B1,168
+CLTC,168
+ATP5F1B,168
+TERF1,168
+NFYB,168
+TAF5,168
+CHMP4B,167
+GINS3,167
+TSG101,167
+UMPS,166
+RPRD1B,166
+PIAS1,166
+KCMF1,165
+EBNA1BP2,165
+AP2S1,164
+THG1L,164
+ADAT2,164
+SPC24,164
+MYC,164
+EIF2S3,163
+TFB2M,163
+ZNF787,163
+RACGAP1,162
+CSDE1,162
+NUFIP1,162
+TMEM161B,162
+CYREN,162
+POLR1C,161
+GEMIN7,161
+UPF1,161
+MED29,160
+TLN1,160
+INO80E,160
+RFC4,160
+RPS5,160
+EEF1B2,160
+MRPL42,160
+FDPS,160
+EIF3A,159
+NPM3,159
+CDC23,158
+NCAPD3,158
+ACD,158
+METTL21A,157
+ATP5F1A,157
+POLG,156
+ZNF143,156
+TTC27,156
+NOL6,156
+TOPBP1,156
+MARS2,156
+MCM4,155
+RPL32,155
+COPS5,155
+HYOU1,155
+LAMTOR3,155
+NCOA4,155
+CNOT11,154
+UNC50,154
+ZNHIT1,154
+HAUS3,154
+HAUS5,153
+ZNF24,153
+WBP1,153
+ATF4,153
+PPP1R12A,153
+STT3B,152
+FOXL2,152
+PRKRA,152
+RPAP3,152
+ARIH1,151
+FARSB,151
+SMARCE1,150
+GMPS,150
+CLK2,150
+TPI1,150
+ECD,150
+TSR1,150
+RPS23,149
+TUBGCP6,148
+DESI1,148
+DNAJC9,148
+KIAA0586,148
+WDR26,148
+RPL5,148
+TIGD1,147
+DMAP1,147
+HNRNPL,147
+TICRR,147
+RPL4,147
+WDR55,146
+PDCD7,146
+NUTF2,146
+SMNDC1,146
+NSMCE1,145
+HLA-C,145
+ITGB1BP1,145
+ANLN,145
+CHERP,145
+MED16,145
+WDR1,144
+INTS11,144
+RHPN1,144
+ANAPC1,144
+PRKCA,144
+SUMO2,143
+MRPS12,143
+CDC5L,143
+DHX9,143
+PFDN1,143
+EXOC3,142
+EFTUD2,142
+PEF1,142
+PYURF,142
+MBIP,141
+CDC7,141
+RBM17,141
+ZRANB2,141
+SAP18,141
+POLR3K,140
+NEDD1,140
+RBM33,140
+NBEAL1,140
+MRPL23,140
+SETD1A,140
+CCDC174,140
+NFS1,140
+XRN2,139
+INPPL1,139
+TIMELESS,139
+HTATSF1,139
+WAC,138
+ORC6,138
+EIF1AD,137
+CRKL,137
+BANP,137
+ATP6V1F,137
+VPS28,137
+SDC1,137
+UQCRH,137
+PDHA1,136
+HPS5,136
+RPS20,136
+C5orf30,136
+PRMT1,136
+TAF6L,135
+PRXL2A,135
+NDUFV2,135
+RPTOR,134
+UPF3A,134
+THOC5,134
+REV3L,134
+ZMYM4,134
+INTS6,134
+CRCP,134
+ANAPC5,134
+TAF1B,133
+RPL18,133
+SENP6,133
+POLR1D,132
+METTL16,132
+MPG,132
+GPN2,132
+USPL1,132
+MMS22L,131
+EIF1AX,131
+TTF2,131
+ARID5B,131
+KIF20A,130
+ZNF317,130
+MRPL13,130
+RCC1,130
+EXOSC10,130
+POLL,129
+PTGR2,129
+CENPH,129
+PSMD14,129
+MAU2,128
+DUT,128
+POLR2H,128
+RCOR1,127
+TAF1C,127
+PRPF8,127
+SPOUT1,126
+ARF4,126
+RPL7L1,126
+PHF12,125
+PFDN6,125
+MZF1,125
+INTS7,125
+HMBOX1,124
+AGBL5,124
+PWP1,124
+CPSF6,124
+ALG11,123
+POLR2E,123
+RBBP4,122
+SNTB2,122
+SNIP1,122
+TBCC,122
+AHCTF1,121
+HIST1H2AE,121
+EIF4A1,121
+MRTO4,121
+BRD8,121
+RPIA,120
+PSMC1,120
+WDR82,120
+F8A1,120
+RRP15,120
+ATIC,119
+CCND3,119
+FKBP9,119
+FAM102B,119
+C7orf50,119
+PTCD1,118
+RBMX,118
+NMT1,118
+NUP160,117
+TBL3,117
+EIF5A,116
+EXOSC9,116
+SLC2A8,116
+HNRNPU,115
+SKP1,115
+AAMP,115
+ATXN10,115
+ROMO1,115
+XRCC3,115
+HNRNPK,114
+PTCD3,113
+GTF2F1,113
+MED26,113
+UQCC2,113
+PLEKHN1,113
+GMIP,113
+MRPS14,112
+HEXIM1,112
+CMC4,111
+SPATA5,111
+MIS12,110
+USP37,110
+MRPS18C,110
+CDC45,110
+CHCHD3,110
+TBCD,110
+CARS,110
+STAG2,110
+POLA1,110
+LEO1,108
+ISCU,108
+LTBP4,108
+SCFD1,108
+ANKRD39,107
+FUNDC2,107
+BORA,107
+DTL,107
+RPL13,107
+CHEK1,106
+RBM48,106
+ARID3A,106
+NSL1,106
+ARFRP1,105
+RPS21,105
+GART,105
+ESYT2,105
+CCT5,105
+SNRPA,104
+MED9,104
+ICE1,104
+MED28,103
+FASN,103
+UBR4,103
+PRC1,103
+SFPQ,103
+C1orf131,102
+MASTL,102
+NDUFS5,102
+RPSA,102
+DTYMK,102
+NOL10,101
+DEPDC5,100
+NCAPH,100
+ATP6V1C1,100
+TUBGCP3,99
+RBM25,99
+C18orf21,99
+RPS10,98
+EIF2S2,98
+DYNC1I2,98
+RPL9,98
+RPA1,98
+RCCD1,98
+NCBP1,98
+WDR92,98
+HAUS1,97
+SF3B4,97
+TYK2,97
+RTF1,97
+GATA1,95
+LRRC37B,95
+RPAIN,95
+XRN1,95
+PREB,95
+NDC80,94
+RAE1,94
+WDR25,94
+KIF18A,94
+SET,94
+HNRNPDL,93
+PRMT5,92
+CDK12,92
+RPP38,92
+PGPEP1,92
+SPTLC1,92
+TAF1,92
+HAUS6,91
+RNF168,90
+RUVBL2,90
+RSL24D1,89
+DIS3,89
+ZC3H3,88
+PSMA3,88
+EWSR1,88
+RBM12,88
+CAST,88
+HSPD1,87
+EEFSEC,87
+ABCB10,87
+ZNF84,86
+CPNE1,86
+WDFY3,86
+USP5,85
+NOL9,85
+MRPL11,85
+RNF31,85
+CDCA5,84
+TRNP1,84
+KIF11,84
+KARS,84
+NEPRO,83
+POLR2K,83
+AAR2,83
+PSMB3,83
+FARS2,83
+PIAS4,83
+PTBP1,82
+AQR,82
+STX18,82
+SNRPE,81
+USP8,81
+SNRPB,81
+PPIE,80
+CNOT9,80
+SERF2,80
+RPL18A,80
+HOXC10,79
+DGCR8,79
+MED18,79
+RBM4,79
+SDR39U1,79
+WDR33,78
+NDUFAF7,78
+CADM4,78
+SNRPD3,78
+LYRM4,77
+GTF2B,77
+SMU1,77
+MED24,77
+ANAPC10,77
+RBM19,76
+OLFML3,76
+ZBTB44,76
+GOSR2,76
+SMARCC1,76
+GLMN,76
+SNAPC2,75
+CENPP,75
+CARF,75
+BUD13,75
+MOCS3,74
+GAK,74
+DDX49,74
+SPDL1,74
+YPEL1,73
+PLK1,73
+THUMPD1,72
+TXNL4A,72
+WDTC1,70
+THOC1,70
+UTP11,70
+ZNF207,70
+RBBP6,70
+POLR2F,70
+DHX29,69
+PUF60,69
+CAP1,69
+RPL12,69
+ZNF559,68
+HSPH1,68
+HSPA5,68
+WEE1,67
+KDM2A,67
+RPL37,67
+RPS25,67
+NCAPG,66
+PARS2,66
+GNPAT,65
+RRM1,65
+SERPINB1,65
+SNRNP70,65
+TWSG1,64
+EXOSC6,63
+TCP1,63
+HARS2,62
+NF1,62
+ZNF574,62
+PSMB6,61
+GLI4,61
+PAFAH1B1,61
+BANF1,61
+CA5A,61
+USP19,60
+ADNP2,60
+ZC3H18,59
+RPF2,59
+ARL6IP6,59
+ANAPC4,59
+YBX3,59
+PABPC1,59
+AP2A1,59
+INO80D,58
+NUF2,58
+CDC20,58
+PSMC4,58
+TFIP11,58
+POLR2C,58
+RAN,58
+NUDT21,57
+EIF3G,57
+YY1,57
+YBX1,57
+PLRG1,57
+PSMB1,57
+DCLRE1B,56
+MRPS18B,56
+NOP2,56
+SUPT4H1,55
+POLR2L,55
+PSMG1,55
+COG3,55
+PCID2,55
+SEC62,54
+TPP2,54
+SLC16A5,54
+GUCD1,54
+NOMO1,54
+CUL7,53
+CEP192,53
+MAP2K7,53
+HSPA8,53
+RPS15,53
+POLE2,53
+DNM2,52
+NUP205,52
+SMG6,52
+RPS17,52
+IFITM3,52
+CLP1,51
+PSMD2,51
+FAM133B,50
+SMC3,50
+ZWINT,49
+RPS16,48
+ECT2,48
+ELP4,48
+HHEX,48
+PPWD1,47
+NOC2L,47
+UTP3,47
+EXOC8,46
+S100A1,46
+KLF7,46
+SLC25A42,46
+EIF3E,46
+WDR7,46
+PHF5A,45
+ACTL6A,45
+ATP5F1C,44
+PAK1IP1,43
+FOXO1,43
+SEC13,43
+NOS1AP,43
+CAD,43
+RPL34,43
+ACTR5,43
+RELL2,42
+USP36,42
+UTP25,41
+BUD31,41
+EMG1,41
+PSMG4,41
+KANSL1,41
+RBM39,41
+FTSJ3,41
+PSMD11,40
+CCNQ,40
+NSRP1,40
+ZBTB14,40
+CHMP1A,40
+HAMP,40
+RAD21,40
+SPAG7,40
+ZC3H8,40
+LUC7L3,39
+CACTIN,39
+CDC26,38
+TAF1A,38
+CTCF,38
+MCEE,37
+RPL27,37
+SF3B2,37
+SLC35A4,37
+BMP2K,37
+ATP5MD,37
+DROSHA,36
+PRPF38A,36
+RPL11,36
+SNRPA1,35
+TOP2A,35
+HIST1H2BJ,35
+TTI2,35
+MED27,35
+MED31,35
+RANBP2,35
+SAP30BP,34
+NDUFA2,34
+PEX1,34
+PCM1,34
+NDUFAF5,34
+PSMC2,34
+RNF103,34
+CHAF1A,33
+ARPC1B,33
+LIN52,33
+TVP23C,32
+PSMC3,32
+LAMB1,32
+ACSS2,32
+KAT5,32
+CMTR2,32
+NAT10,32
+MRM1,32
+WBP1L,31
+VMP1,31
+RACK1,31
+NFKBIE,31
+SAP130,31
+CWC22,31
+MST1,31
+SNRPF,31
+OGT,31
+CDC27,30
+DDX3X,30
+DDX42,30

analysis/replogle_source_to_filtered_schema/schema_report/source_vars_not_in_template.csv

@@ -0,0 +1,96 @@
+AC009107.2
+AC015871.1
+ADCK2
+AGTPBP1
+AKAP10
+AL441992.1
+ALKBH3
+AMMECR1L
+AMPD2
+AP4M1
+AREL1
+ARHGEF18
+ATG16L1
+BRF1
+BTBD10
+BTBD3
+C2CD5
+COQ6
+CTXN1
+CYB5D2
+EFNA4
+FAM160B2
+FARP2
+FBXL18
+FBXO8
+FLYWCH1
+FRS2
+GMPPB
+GNS
+GPAM
+GSKIP
+HACD2
+IDS
+IKBKG
+INPP5F
+IRF1
+IRF2
+KBTBD4
+KIAA1841
+KIF13B
+KLC2
+KRCC1
+LANCL2
+LINC02693
+MOSPD2
+MSANTD2
+MSANTD4
+NAA30
+NDEL1
+NEDD4
+NINJ1
+NIPA1
+OPN3
+PACRGL
+PDP2
+POLH
+PYGB
+RAB11FIP2
+RNF185
+SAT2
+SEC22A
+SGSM2
+SHFL
+SIPA1L1
+SLC15A4
+SLC23A2
+SLC25A28
+SLC2A11
+SLC35A2
+SMAD3
+SMCR8
+SNAPC1
+SNX24
+SNX29
+STIMATE
+TADA2B
+TCTA
+TEX2
+TIMM21
+TLCD5
+TMEM120A
+TMEM127
+TMEM184B
+TMEM39A
+TNFAIP1
+TRIM14
+TRIM23
+TTBK2
+TUBA4A
+UBASH3B
+UHRF2
+UNC119B
+WDSUB1
+ZMIZ2
+ZNF524
+ZNF654

analysis/replogle_source_to_filtered_schema/schema_report/template_cell_line_counts.csv

@@ -0,0 +1,5 @@
+cell_line,count
+k562,188590
+jurkat,184470
+rpe1,173737
+hepg2,96616

analysis/replogle_source_to_filtered_schema/schema_report/template_gem_group_counts.csv

@@ -0,0 +1,57 @@
+gem_group,count
+25,14398
+44,13937
+3,13748
+7,13462
+12,13295
+31,13276
+16,13189
+42,13033
+33,13013
+2,12996
+22,12984
+29,12976
+11,12836
+38,12830
+14,12765
+34,12744
+39,12724
+20,12715
+13,12672
+24,12672
+40,12527
+47,12448
+8,12441
+35,12425
+5,12418
+30,12384
+6,12381
+18,12316
+43,12239
+26,12073
+10,12037
+19,11882
+17,11846
+28,11755
+15,11716
+46,11486
+9,11452
+27,11322
+32,11302
+37,11142
+23,11138
+4,10808
+45,10566
+48,10270
+36,9725
+1,9697
+55,9632
+53,8683
+21,8580
+54,8416
+49,8068
+41,7995
+52,7894
+51,7877
+56,6949
+50,5258

analysis/replogle_source_to_filtered_schema/schema_report/template_gene_counts.csv

@@ -0,0 +1,2025 @@
+gene,count
+non-targeting,39165
+TFAM,7145
+SLC1A5,4284
+GFM1,3969
+MRPL36,3254
+PPP6C,3210
+MRPL35,2881
+TARDBP,2523
+CCDC6,2230
+GTF3C4,2049
+HSD17B10,1685
+FBXO42,1628
+GTF2E2,1495
+ZDHHC7,1428
+PSMB5,1414
+TRNT1,1388
+TMEM214,1371
+TIMM23B,1327
+FAM136A,1308
+CPSF3,1274
+TMEM242,1265
+MRPL34,1241
+TWF1,1214
+POGLUT3,1147
+C7orf26,1104
+MYBL2,1091
+PPP1R37,1089
+MED19,1088
+CLOCK,1071
+THAP1,1068
+EIF4B,1053
+TPT1,994
+TRAPPC11,979
+SRP72,959
+HSD17B12,959
+ZBTB17,958
+RHOQ,954
+TSR2,935
+SSBP3,934
+CHMP6,927
+SMG5,904
+SLC39A9,884
+SLC7A5,880
+INTS14,877
+GPS1,867
+CLASRP,859
+CSE1L,858
+NCBP2,849
+PMF1,828
+EIF2B2,819
+PMPCB,819
+HSCB,810
+SHQ1,792
+NAA35,776
+TFDP1,767
+ZNF236,766
+EIF2B5,763
+SSU72,757
+DDX55,745
+INTS13,742
+RNF8,736
+LAMTOR1,735
+MCM3,731
+SLC35G2,731
+WTAP,718
+RAC3,718
+SART3,712
+RABGGTA,711
+BUB1,707
+MED12,706
+WDR4,705
+RAB4A,690
+EIF2B1,688
+DONSON,688
+SPC25,687
+ZMAT2,686
+MRPL39,677
+HUS1,675
+NLE1,670
+POLRMT,668
+BTF3L4,665
+MED14,664
+RPL23,659
+ANKRD11,659
+HMGCS1,659
+GOLT1B,655
+DDX19A,654
+UROD,652
+MCM6,651
+H2AFZ,650
+RPS13,650
+SRSF6,648
+RPS19,646
+PDCD6IP,644
+CNN2,641
+HSPA9,640
+PLK4,639
+ATP6V1B2,638
+MRPS21,638
+ZNHIT3,634
+RNF14,632
+POLR1E,631
+DNAJC8,627
+ARGLU1,627
+MAD2L2,626
+QARS,625
+WDR54,625
+TACC3,622
+SNRNP40,619
+GLRX5,617
+VPS41,616
+ADAM10,611
+INTS8,609
+NFRKB,606
+DNAJC19,606
+RNASEH2C,604
+SLU7,601
+DDX51,601
+NELFB,598
+FNBP4,593
+MRPL24,592
+NRDE2,592
+PPP2R1A,591
+BAP1,590
+VPS54,589
+PDCD5,589
+SNAPC3,586
+NAGLU,585
+BTF3,585
+METTL3,584
+RBMX2,582
+DCTN3,580
+SRA1,577
+ANKS6,576
+CHORDC1,574
+DDX5,574
+DSTYK,574
+LSM6,572
+PTMA,570
+INTS2,570
+NAA25,569
+MVK,568
+SRPRB,568
+ELL,567
+MRPL38,564
+RAB4B,563
+MRPS6,563
+MRPL16,562
+TEX10,562
+C9orf16,562
+CDK2,560
+ASF1B,559
+ISCA2,558
+RIOK1,558
+COX11,555
+ATP6AP2,554
+PPME1,553
+RPL41,551
+PFN1,551
+PPP2CA,551
+JMJD6,550
+PCBP1,549
+SDHAF2,547
+MBTPS1,545
+PARN,544
+MIS18BP1,544
+GNPNAT1,543
+PSMG3,543
+GPN3,543
+SRP68,543
+RARS2,541
+CDIPT,541
+GINS1,540
+XPO5,540
+CENPT,539
+SRP9,538
+NOM1,535
+ACTR1B,535
+THOC7,534
+ORC1,533
+WDR3,533
+TBCA,531
+ELP3,530
+CSTF1,530
+DRAP1,529
+MCMBP,529
+RPL24,528
+MRPL3,525
+DHX16,525
+NIFK,523
+GYG1,522
+KRR1,521
+TRMT112,521
+ACTR8,520
+TRAPPC5,519
+EIF4E,517
+MZT1,515
+DNMT1,514
+CENPJ,512
+CNOT3,511
+TAF13,510
+NAPG,508
+HARS,508
+GTF3C6,508
+NARS2,507
+MANF,506
+XRCC1,506
+ATP5MF,506
+ATR,506
+RARS,504
+RBM10,503
+NISCH,503
+TXNL4B,502
+RPS12,501
+PGAM1,499
+TMX2,498
+COG6,497
+EIF4G1,495
+MED10,495
+GTF2H1,495
+CS,494
+DOHH,493
+DHX37,492
+CMPK1,491
+EIF2B4,491
+MRPL27,489
+KIAA1143,489
+CHCHD4,486
+BRCA2,486
+STIL,486
+NUDCD3,485
+NDUFB4,485
+MSRB1,485
+URB2,484
+RTRAF,483
+TIMM8A,483
+DHX36,483
+LETM1,482
+MIOS,482
+PHB2,480
+EXOSC2,479
+COPS8,478
+GNL2,478
+MRPL41,477
+DCTN4,477
+FAM207A,476
+SNX15,475
+YRDC,474
+SSRP1,473
+UXS1,472
+COG2,472
+UBA2,470
+PRELID3B,470
+RABGGTB,469
+QRSL1,469
+UTP23,468
+COQ2,468
+COX7C,468
+ESF1,468
+DHX15,466
+MICOS10,464
+CIAPIN1,464
+MTG2,463
+HSP90B1,462
+COX10,462
+GFOD2,462
+E2F6,460
+TAF1D,460
+VARS,459
+BCL2L1,459
+EMC7,459
+ARPC4,459
+FASTKD5,458
+MLLT6,458
+IPO9,458
+MRPS16,457
+UBE2L3,456
+RPL7,456
+SP1,456
+MBTPS2,455
+DBR1,455
+POLR2I,455
+NDUFAB1,454
+KDM6A,454
+NDUFB8,453
+TARS2,453
+INTS9,453
+ELP5,452
+DLD,452
+MRPL54,452
+CCNH,452
+THAP11,452
+PI4KA,451
+ELOVL1,450
+DYNLL2,450
+ORC4,450
+NELFCD,449
+PPIA,449
+SOD2,448
+SMN2,446
+DAP3,446
+PAXBP1,446
+HJURP,446
+COX5A,446
+ACTR2,446
+YEATS2,446
+DDX52,445
+USP14,445
+PDCD6,445
+DCTN1,445
+PPA1,445
+URI1,444
+MRPL14,444
+C17orf58,444
+DDX23,442
+UFL1,442
+RCL1,441
+LTV1,441
+SBNO1,441
+KTI12,441
+RPL26,440
+EXOSC4,440
+METTL1,439
+RPP21,439
+MOB4,439
+MED11,438
+SDAD1,438
+TUBGCP2,437
+GRSF1,435
+TRRAP,435
+E4F1,435
+POP7,434
+NFATC2IP,434
+COA5,432
+PDCD11,432
+PET117,432
+SETDB1,431
+CCDC59,431
+PTPMT1,431
+LARS2,430
+DNAJA3,430
+DCTN2,429
+FAM32A,429
+TRA2B,429
+GET3,428
+SS18L2,428
+RPL36,427
+PNPT1,426
+CSNK2B,426
+TUBB2A,425
+SRRT,425
+HAUS8,425
+SF3B3,425
+TSEN2,424
+WDR12,424
+RPAP2,424
+NUDC,424
+CBX1,424
+SRP14,423
+PSMD4,423
+MON1A,423
+DRG1,422
+ALG2,422
+YARS2,421
+COASY,421
+EDC4,421
+GCLC,421
+RPS27A,421
+RPUSD3,421
+NAF1,420
+NOL8,420
+TTC1,420
+UBE2H,420
+DOLK,419
+TUBB,418
+CCDC115,418
+GFER,418
+THOC6,417
+OIP5,417
+NACA,416
+YEATS4,416
+CEBPZ,416
+MRPL50,415
+SUPT5H,415
+NSUN4,415
+IMPDH2,415
+RPL36A,414
+SCAP,414
+DCAF6,413
+NDUFB3,413
+MRPL1,413
+KDM1A,413
+GINS4,412
+TAF8,412
+UBL5,412
+RPL6,412
+MRPS35,412
+PHB,411
+NOL11,411
+MED30,411
+TM7SF2,411
+LSG1,410
+ING3,410
+CHTOP,410
+NUP133,409
+C9orf78,409
+DENR,409
+HSPA14,408
+AATF,408
+NPLOC4,407
+MED1,406
+IARS2,406
+NCAPH2,406
+PSAT1,406
+TRAPPC3,406
+CPNE7,405
+SLC39A10,404
+RRS1,404
+RAD51D,403
+TPX2,403
+MRPS34,403
+SUPT20H,403
+GRWD1,403
+ERAL1,402
+UTP15,402
+GINS2,402
+DERL2,402
+TUBE1,401
+WDR18,400
+RPS7,398
+CHMP7,398
+DCUN1D5,397
+ORC5,397
+MRPL4,396
+PRPF39,395
+RNF20,395
+UBE2M,395
+MRPS5,394
+RPS6,394
+PSME2,393
+OXA1L,393
+KEAP1,392
+SPCS3,392
+ATP5PD,391
+ALG14,391
+RPP14,391
+TIMM13,390
+SEPHS2,390
+RTEL1,390
+AAAS,389
+MPHOSPH6,389
+ANAPC13,389
+EIF3H,389
+ARL2,389
+YARS,388
+NAA20,388
+NDUFA6,387
+SNRPG,387
+NOP14,387
+NUBP2,387
+HAUS4,385
+MBD3,385
+TBP,385
+TAMM41,384
+COPS4,384
+EIF6,384
+EXOSC5,384
+IGBP1,384
+VPS35,384
+ELOB,383
+CD3EAP,383
+EIF1,383
+MTOR,383
+EFR3A,383
+MFN2,382
+TUBGCP5,382
+RMI1,382
+EHMT2,382
+TTI1,382
+RPL30,381
+EIF3M,381
+RRP12,380
+STXBP4,380
+MED4,380
+CCNB1,380
+TMEM127,379
+GMPPB,379
+ABCB7,379
+NUP54,379
+CENPE,378
+BRIP1,378
+MRGBP,377
+VPS13D,377
+SEM1,377
+NARS,377
+SNRNP48,377
+MMS19,376
+ABHD17A,376
+DDX1,376
+FDXR,376
+RINT1,376
+CCT4,375
+MRPS26,375
+POLR2B,375
+AARS2,375
+BRIX1,375
+FCF1,374
+CIAO1,374
+TRMT6,373
+TOMM22,373
+DPH6,372
+BDP1,371
+EIF2S1,371
+PRRC2A,370
+VEZT,370
+WDR36,369
+GRPEL1,369
+LSM2,369
+SPTSSA,368
+POP5,368
+VPS29,368
+TEFM,368
+LSM10,368
+ATP11B,367
+CAMLG,367
+PNN,367
+PELP1,367
+NOC3L,367
+U2SURP,366
+TTC4,366
+PCNX3,366
+INO80B,364
+EARS2,364
+UXT,364
+TUBD1,363
+H2AFX,363
+MNAT1,363
+EIF3B,363
+MAX,362
+DIMT1,362
+FARSA,362
+LAMTOR4,362
+TFRC,362
+XRCC2,362
+GUK1,361
+POP4,361
+MRPS25,361
+RPS24,361
+CMTR1,360
+DHODH,360
+FYN,360
+GSPT1,360
+DDX19B,360
+GEMIN5,359
+MRPL10,359
+TOE1,358
+ACTR6,358
+CHTF18,358
+TIMM9,357
+PPP1R8,357
+KANSL3,357
+ZCRB1,357
+ZNF292,357
+POLR2M,356
+CXXC1,356
+PSTK,355
+OSTC,355
+RPS27,355
+ACTB,355
+NASP,354
+BUB3,354
+CYCS,354
+NOLC1,353
+ERCC2,353
+SEH1L,353
+CABIN1,353
+TLCD1,353
+FAF2,353
+EIF3L,352
+TMED10,352
+DNTTIP2,352
+DDX17,351
+MRPL18,351
+GTF3C1,351
+IPO13,351
+DPY19L4,351
+TMSB10,351
+TAF2,350
+SETX,350
+CTU2,350
+IST1,349
+MRPL19,349
+EXOC5,349
+SPATA5L1,349
+PNKP,349
+HECTD1,348
+PPP1R2,348
+CNOT1,347
+CWF19L2,347
+ATP6AP1,346
+NUB1,346
+MRPS7,346
+RPP30,346
+TIMM10,346
+MCM7,345
+PTPN11,345
+EXOC1,345
+MMGT1,345
+RPS28,345
+MRPS10,344
+LAS1L,344
+EIF2B3,344
+ZRSR2,344
+CUL1,343
+NUP88,343
+SACM1L,343
+ABT1,343
+ATP6V0C,343
+NELFE,342
+TGS1,342
+METTL17,342
+SRF,341
+PXN,341
+DDX21,341
+MVD,341
+GTF2E1,340
+RNF123,340
+ELOF1,340
+TMEM258,340
+DNAJA1,340
+RPA3,339
+SRP54,339
+TNRC6A,339
+ELP2,338
+GTF2H4,338
+ALG13,338
+NDUFA3,338
+RUVBL1,338
+BUB1B,337
+DICER1,336
+NRBP1,336
+TUBA1B,336
+MED22,336
+DPH2,335
+NAA10,335
+SNF8,334
+RAC1,334
+TTK,333
+TOP3A,333
+COX6C,333
+GTF3C5,333
+TUFM,333
+SRBD1,332
+USP9X,332
+RPS15A,332
+HSPE1,331
+POLD1,331
+NIP7,331
+ELAC2,331
+PYROXD1,330
+MAT2A,330
+INO80C,330
+NDUFS3,329
+ATP6V1G1,329
+MKRN1,329
+UBQLN4,329
+RRP9,329
+ZW10,329
+WDHD1,328
+ATP2A2,328
+PAF1,328
+RTCB,327
+PTK2,327
+NDUFB6,327
+RPS3,325
+NVL,325
+COPS6,325
+TADA3,324
+EIF4H,324
+NCAPG2,324
+EXOSC8,323
+SMC1A,323
+TP53RK,323
+TAF6,322
+KRI1,322
+SNUPN,322
+EIF4G2,322
+IPO7,322
+MRPS27,322
+DCTN6,322
+HNRNPC,322
+UPF2,322
+POLR3C,321
+LSM12,321
+UQCRQ,321
+INTS12,320
+MED7,320
+MED20,320
+MRPS28,320
+DDX41,320
+PRORP,319
+TOMM40,319
+TSFM,319
+WDR5,319
+UBE2N,319
+CDK1,318
+ALDOA,318
+GPKOW,317
+MIPEP,317
+NKAPD1,317
+WDR75,316
+CCDC86,316
+CCT3,316
+GTF3C2,315
+WDR83OS,315
+DNM1L,315
+DNM1,315
+PRPF18,315
+TRAPPC4,315
+BMS1,314
+NUP85,314
+KIN,314
+MED6,314
+CCDC137,314
+DHX33,314
+ORC3,314
+SCAF1,313
+MRPS23,313
+SKA3,313
+GTF2A2,313
+NSMCE2,312
+SPRTN,312
+BPTF,312
+SYS1,311
+NELFA,311
+SPG7,311
+RPUSD4,311
+KATNB1,311
+RFC3,310
+BET1,310
+DDX10,310
+TSEN34,310
+MRPL9,309
+SRSF7,309
+ZFC3H1,309
+RPLP2,309
+SMC5,309
+CCT7,308
+MRPL37,308
+ZNF720,308
+PITRM1,308
+PMPCA,308
+TRAPPC1,307
+PSMG2,306
+MCM2,306
+MRPS11,306
+CD2BP2,306
+PGD,306
+CHCHD2,306
+COQ4,306
+KLC2,306
+VPS33A,306
+PPP4R2,305
+STRAP,305
+SURF6,304
+RPL31,304
+GEMIN4,304
+FBXW7,303
+PSME1,303
+POGZ,303
+ABCE1,303
+UTP20,303
+HERC1,303
+MBNL1,303
+GNL3,302
+SETD5,302
+RNF40,302
+SYMPK,302
+RPL17,302
+NDUFA11,301
+NMD3,301
+PES1,301
+MYBBP1A,301
+PGK1,301
+VPS37A,301
+SRSF10,300
+EGLN2,300
+TRAPPC8,300
+URM1,299
+SKP2,299
+MRPS17,299
+RPA2,299
+LONP1,298
+NBAS,298
+GTF2F2,297
+CDC6,297
+RPS14,297
+ARL4D,297
+CCT2,297
+MRPL55,297
+RPS4X,297
+EXOSC3,297
+MRPL20,296
+MCL1,296
+EXOC2,296
+MRPS9,295
+ATP6V0B,295
+NOB1,295
+NKAP,295
+ATP5ME,295
+TP53I13,295
+SCD,294
+TARS,294
+SARS2,293
+MRPL2,293
+HEATR1,293
+SAE1,293
+INO80,293
+NEDD8,292
+PRPF3,292
+N6AMT1,292
+DDX27,292
+IMP4,292
+INTS1,291
+DPM2,291
+WNK1,290
+MRPL33,290
+MALSU1,290
+PGS1,290
+NDUFAF3,290
+SUPT6H,289
+NDUFB10,289
+EEF1G,289
+GLRX3,289
+LRR1,289
+H3F3A,288
+NUP214,288
+KIF18B,288
+AIFM1,288
+CCNL1,286
+TNPO3,286
+BCS1L,286
+NSA2,286
+RPAP1,286
+ENO1,285
+DDX11,285
+ANAPC11,285
+AHCY,285
+BRF1,285
+SMAGP,284
+THOC3,284
+RPL14,284
+GTPBP4,284
+C19orf25,284
+HNRNPA1,284
+FXN,284
+ERCC3,284
+LST1,283
+PTPN1,282
+IWS1,282
+DPAGT1,282
+AKIRIN2,282
+TIPIN,281
+OSGEP,281
+SHC1,281
+BRK1,281
+CDC16,281
+HMGA1,280
+CENPW,280
+GTF2A1,280
+MRPS22,279
+SNRNP35,279
+TPR,279
+MRPS18A,279
+ATP1A1,279
+PPP2R3C,279
+CHD4,279
+RAB6A,278
+COG4,278
+C19orf53,278
+RPL10A,278
+PALB2,277
+PKMYT1,277
+CPSF1,277
+STAT5B,277
+ELP6,276
+COX17,276
+PPRC1,276
+MTBP,276
+NHLRC2,276
+COQ5,276
+WDR77,276
+RBM28,276
+ADSL,276
+PFDN4,275
+DDX18,275
+UQCRB,275
+ATRIP,275
+SERBP1,274
+SLC39A7,274
+METAP1,274
+NAA15,274
+CENPN,274
+POLD2,274
+MRPL51,274
+TMA16,273
+ILF3,273
+BRF2,273
+OGFOD1,273
+GAR1,273
+BNIP1,273
+LTBP3,272
+TBPL1,272
+DSN1,272
+ASCC3,272
+TADA2A,272
+HUWE1,272
+ATP6V0D1,271
+PNO1,271
+MAK16,271
+NDC1,271
+LSM3,271
+DDX24,271
+ZNHIT2,271
+KIF4A,271
+POLG2,271
+RAD51,270
+NDUFA4,270
+TRMT5,270
+NUP35,270
+ZC3H13,269
+NEMF,269
+PRELID1,269
+RPL35A,268
+NOP16,268
+TOX4,268
+COMTD1,267
+RPS2,267
+MED8,267
+NOL12,267
+UTP18,267
+PPA2,266
+NAA50,266
+CEP97,266
+EIF3J,266
+LSM7,266
+COTL1,266
+SEPSECS,265
+NHP2,265
+RBBP5,265
+RPS11,265
+RNF113A,264
+TINF2,264
+RNGTT,264
+SRRM1,264
+TEN1,264
+ZNF100,264
+PPIL1,264
+UBR5,264
+PPAN,263
+RFT1,263
+RPL26L1,263
+PGAM5,263
+NSF,262
+STRIP1,262
+NUP107,262
+EIF3D,262
+USP10,262
+VPS72,261
+TMEM199,261
+INTS3,261
+GTF2H3,261
+VPS25,261
+BRCA1,261
+DDX56,261
+DHDDS,261
+CNOT10,260
+MRPL15,260
+C1D,260
+GNB1L,260
+CPSF4,260
+DDX20,260
+PABPC4,260
+LDB1,260
+HDAC3,259
+MRPS24,259
+SEC61G,259
+NCAPD2,259
+TOP1,258
+MCM5,258
+MYSM1,258
+PPARGC1B,258
+FNTA,258
+GTF2H2,258
+C12orf45,258
+MEX3A,258
+MRPL17,257
+TRMT10C,257
+VHL,257
+INF2,256
+CUL2,256
+MPHOSPH10,256
+TUBG1,255
+SASS6,255
+PRPF4,255
+POLA2,255
+ENY2,254
+CCT6A,254
+MAGOH,254
+CDK9,254
+FEN1,254
+HNRNPR,254
+MYCBP,253
+RNMT,253
+CASC3,252
+GABPA,252
+CENPK,252
+RPS18,252
+CUL3,252
+CSNK1A1,252
+UFM1,252
+RFC2,252
+PPP2CB,252
+UBA1,251
+STARD7,250
+ANKRD49,250
+ILF2,250
+PTEN,250
+METAP2,249
+PPP1R15B,249
+PPP4C,249
+PPP1R11,249
+DYNC1H1,248
+ATF5,248
+GBF1,248
+XPO1,248
+ZNHIT6,248
+PRPF19,248
+HINFP,248
+POLR3F,248
+FBLIM1,247
+COX5B,247
+TCERG1,247
+ZNRD1,246
+LPIN1,246
+PAM16,246
+GTF3C3,246
+MEN1,245
+PHF10,245
+RPL36AL,245
+ARMC6,245
+FAU,245
+IFITM2,244
+GPS2,244
+SUPV3L1,244
+MRPL28,244
+VARS2,244
+CCAR1,244
+SNRNP27,244
+XRCC5,244
+WDR46,244
+TSEN54,243
+TAF11,243
+SRRM2,243
+DDOST,243
+LRP5,243
+RBMXL1,243
+DNAJC17,242
+SLC7A6OS,242
+CNIH4,242
+DBF4,242
+NOL7,242
+CCNC,242
+UBA5,242
+ATL2,241
+ALG1,241
+VBP1,241
+POLR3E,241
+RPL23A,241
+ANKLE2,241
+BARD1,241
+SEC63,241
+SNRPC,241
+THRAP3,240
+OPA1,240
+URB1,240
+NAA30,239
+EXOSC7,239
+RPL29,239
+RFC5,239
+LRPPRC,238
+CHCHD1,238
+METTL14,238
+SIRT7,237
+COG1,237
+SAMD4B,237
+PCNA,237
+DPH3,236
+RPF1,236
+SLBP,236
+RPE,236
+PPIL4,236
+CTR9,235
+CAPZB,235
+KANSL2,235
+SDHC,235
+ABHD11,235
+UHRF1,235
+TPRKB,234
+LARS,234
+PIK3C3,234
+HIST1H2BC,234
+KIF14,233
+SF3B5,233
+AP2M1,233
+YTHDC1,233
+MRPL44,233
+CSTF3,233
+GLE1,232
+TAZ,232
+ARMC7,232
+SCNM1,232
+TBCB,232
+EPRS,231
+ATP6V1D,231
+TCOF1,231
+TFB1M,231
+TOMM20,231
+CDC123,231
+PRPF4B,231
+EMC4,230
+NUP98,230
+SNAPC5,230
+POLR3D,229
+SMC6,229
+PRDM4,229
+SPCS2,228
+ADRM1,228
+NDUFB7,228
+BYSL,228
+NOC4L,228
+MIS18A,228
+MARS,228
+GGPS1,228
+WDR70,228
+MRPL43,227
+EXOSC1,227
+CEP85,226
+MCM3AP,226
+RRN3,226
+UBE2D3,226
+SBDS,226
+PRPF31,226
+TIMM44,226
+MT2A,225
+ZFR,225
+PRIM1,224
+HIST1H2BN,224
+SUDS3,224
+RPL39,224
+POP1,224
+SKA1,223
+LSM4,223
+CALR,223
+HS6ST1,223
+COX7B,223
+DYNLL1,223
+TAF7,223
+RIOK2,223
+POLR3B,223
+MFAP1,222
+POLE,222
+UCHL5,222
+WDR43,222
+POLR1B,222
+RPL27A,222
+INTS4,221
+EIF3I,221
+PFDN2,221
+EP400,221
+SMG7,221
+SUPT16H,221
+MRPS31,221
+MLST8,220
+PRPF40A,220
+ISG20L2,220
+CHMP5,220
+MRPS2,220
+RPS19BP1,219
+DHPS,219
+INTS10,219
+BCLAF1,219
+EXOC7,219
+RRP7A,218
+SEC61B,217
+PEX19,217
+ZC3H4,217
+ATP6V1E1,216
+SNAPC1,216
+TAF3,216
+ZCCHC9,216
+PTPN23,216
+THOC2,216
+TELO2,216
+NPM1,216
+WDR61,215
+ATP6V1H,215
+COX15,215
+ETF1,215
+UQCRFS1,215
+SOD1,215
+CEP152,215
+AFG3L2,215
+USF2,214
+GTF3A,214
+MRPS30,214
+PRIM2,214
+CYC1,214
+TWISTNB,214
+PABPN1,213
+CDC42,213
+RAD9A,213
+EMC1,213
+RPN1,213
+SRP19,213
+PPIH,213
+CNOT2,213
+TEAD3,212
+RTTN,212
+SRFBP1,212
+ATP5PO,212
+SUGP1,212
+CBLL1,212
+HBS1L,212
+BRD2,212
+SUGT1,212
+CWC25,211
+UBE2I,211
+BCR,211
+NFYC,211
+NOP9,211
+RPS26,211
+MDN1,210
+SEC16A,210
+COPS2,210
+UBE2Z,209
+RRM2,209
+TERF2,209
+KCTD10,208
+TXN,208
+NUP62,208
+ATP6V1A,208
+PIK3R4,207
+RPL28,207
+PIGH,207
+SNRNP25,207
+NUDT15,207
+MTPAP,206
+SNRNP200,206
+TADA1,206
+TADA2B,206
+DAXX,206
+RPN2,206
+MED17,206
+PDPK1,206
+TAF10,205
+PSMD9,205
+WARS,205
+UQCRC2,205
+SHOC2,205
+KXD1,204
+PSMC5,204
+RBM15,204
+NUP43,204
+RPL38,204
+ZNF468,204
+UTP6,203
+SSBP1,203
+UBAP1,203
+SLC25A3,203
+RPP40,203
+PPP1CB,202
+KDM5C,202
+TAF12,202
+COPS3,201
+EPB41L2,201
+AURKAIP1,201
+HIPK1,201
+SFSWAP,201
+CCT8,200
+REXO2,200
+GLB1,200
+HNRNPH1,200
+RRP1,200
+BTAF1,199
+AARS,199
+CLPB,199
+RBM14,199
+IPO11,198
+MRPL22,198
+KAT7,198
+RPL15,198
+PPIL2,198
+GARS,198
+TMED2,198
+CRLS1,198
+DKC1,198
+HMGCR,198
+RPL19,198
+KPNA6,198
+DDX6,198
+CLCC1,198
+SART1,198
+EXOC4,198
+BCAS2,197
+AASDHPPT,197
+COPE,197
+MTHFD1,197
+ZFP69B,197
+NUP153,197
+CDC73,196
+DDX59,196
+HMGB3,196
+GSK3B,195
+SYF2,195
+RBBP8,195
+DR1,195
+XRCC6,195
+RANGAP1,195
+CDT1,194
+GNL3L,194
+SNRPD1,194
+TKT,194
+CENPC,193
+RPL8,193
+MRPS33,193
+EIF4A3,193
+PDRG1,192
+KPNB1,192
+NDUFA8,192
+FAM50A,192
+PSMD13,192
+AURKA,192
+CASP8AP2,192
+VPS51,192
+CHMP3,191
+RPL37A,191
+RAMAC,191
+BAG6,191
+PSMA4,191
+RBX1,191
+PFDN5,190
+CYFIP1,190
+CHAF1B,190
+RAD51C,190
+MCM10,190
+LAMTOR2,189
+YPEL5,189
+SETD2,188
+LENG8,188
+POLR3H,188
+GEMIN6,188
+LZTR1,188
+SARNP,188
+GTF2H2C,188
+SP2,187
+SDE2,187
+MRPL45,187
+GEMIN8,187
+WDR44,187
+CWC15,186
+DCTN5,186
+NOP10,186
+HDAC7,186
+UBA3,186
+MRPL46,185
+TWNK,185
+PDAP1,185
+RAB18,185
+C1QBP,185
+SMC2,185
+HMGN2,185
+POLD3,184
+LSM5,184
+ZMAT5,184
+RPS3A,184
+ACTR10,184
+NCKAP1,183
+GABPB1,183
+CPOX,183
+IARS,183
+ZNF706,183
+SAMM50,183
+NOP58,183
+FGFR1OP,183
+PDCD2,183
+LIMS1,182
+HGS,182
+SMG8,182
+UBE3C,182
+NUBP1,181
+NAE1,181
+MAD2L1,181
+DAD1,181
+CTDP1,180
+RPS8,180
+POLR1A,180
+GPN1,180
+CTNNBL1,180
+RPL35,179
+CCP110,179
+AC118549.1,179
+RAD17,178
+SDHA,178
+TSPYL5,178
+RPL10,177
+MED21,177
+YKT6,176
+RPLP0,176
+TRPM7,176
+RSRC2,176
+DNAJC11,176
+SMG9,176
+TOR2A,175
+PUM1,175
+TRIAP1,175
+UBE3D,175
+VPS18,175
+CCDC84,174
+CEP68,174
+PSMB2,174
+TUBA1C,174
+SRSF1,174
+CINP,174
+MSL1,174
+CLNS1A,173
+VPS37C,173
+IMPA2,173
+FBL,173
+TUBGCP4,172
+DARS,172
+RBM42,172
+MRPL32,171
+CFL1,171
+HMX3,171
+TIMM22,171
+INTS5,171
+STAT5A,170
+POLR2G,170
+METTL23,170
+RPS9,170
+SPEN,170
+TRAIP,169
+SMUG1,169
+MRPL49,169
+RNPC3,169
+STX5,169
+SGPP1,169
+BOD1L1,169
+SLC35B1,168
+CLTC,168
+ATP5F1B,168
+TERF1,168
+NFYB,168
+TAF5,168
+CHMP4B,167
+GINS3,167
+TSG101,167
+UMPS,166
+RPRD1B,166
+PIAS1,166
+KCMF1,165
+EBNA1BP2,165
+AP2S1,164
+THG1L,164
+ADAT2,164
+SPC24,164
+MYC,164
+EIF2S3,163
+TFB2M,163
+ZNF787,163
+RACGAP1,162
+CSDE1,162
+NUFIP1,162
+TMEM161B,162
+CYREN,162
+POLR1C,161
+GEMIN7,161
+UPF1,161
+MED29,160
+TLN1,160
+INO80E,160
+RFC4,160
+RPS5,160
+EEF1B2,160
+MRPL42,160
+FDPS,160
+EIF3A,159
+NPM3,159
+CDC23,158
+NCAPD3,158
+ACD,158
+METTL21A,157
+ATP5F1A,157
+POLG,156
+ZNF143,156
+TTC27,156
+NOL6,156
+TOPBP1,156
+MARS2,156
+MCM4,155
+RPL32,155
+COPS5,155
+HYOU1,155
+LAMTOR3,155
+NCOA4,155
+CNOT11,154
+UNC50,154
+ZNHIT1,154
+HAUS3,154
+HAUS5,153
+ZNF24,153
+WBP1,153
+ATF4,153
+PPP1R12A,153
+STT3B,152
+FOXL2,152
+PRKRA,152
+RPAP3,152
+ARIH1,151
+FARSB,151
+SMARCE1,150
+GMPS,150
+CLK2,150
+TPI1,150
+ECD,150
+TSR1,150
+RPS23,149
+TUBGCP6,148
+DESI1,148
+DNAJC9,148
+KIAA0586,148
+WDR26,148
+RPL5,148
+TIGD1,147
+DMAP1,147
+HNRNPL,147
+TICRR,147
+RPL4,147
+WDR55,146
+PDCD7,146
+NUTF2,146
+SMNDC1,146
+NSMCE1,145
+HLA-C,145
+ITGB1BP1,145
+ANLN,145
+CHERP,145
+MED16,145
+WDR1,144
+INTS11,144
+RHPN1,144
+ANAPC1,144
+PRKCA,144
+SUMO2,143
+MRPS12,143
+CDC5L,143
+DHX9,143
+PFDN1,143
+EXOC3,142
+EFTUD2,142
+PEF1,142
+PYURF,142
+MBIP,141
+CDC7,141
+RBM17,141
+ZRANB2,141
+SAP18,141
+POLR3K,140
+NEDD1,140
+RBM33,140
+NBEAL1,140
+MRPL23,140
+SETD1A,140
+CCDC174,140
+NFS1,140
+XRN2,139
+INPPL1,139
+TIMELESS,139
+HTATSF1,139
+WAC,138
+ORC6,138
+EIF1AD,137
+CRKL,137
+BANP,137
+ATP6V1F,137
+VPS28,137
+SDC1,137
+UQCRH,137
+PDHA1,136
+HPS5,136
+RPS20,136
+C5orf30,136
+PRMT1,136
+TAF6L,135
+PRXL2A,135
+NDUFV2,135
+RPTOR,134
+UPF3A,134
+THOC5,134
+REV3L,134
+ZMYM4,134
+INTS6,134
+CRCP,134
+ANAPC5,134
+TAF1B,133
+RPL18,133
+SENP6,133
+POLR1D,132
+METTL16,132
+MPG,132
+GPN2,132
+USPL1,132
+MMS22L,131
+EIF1AX,131
+TTF2,131
+ARID5B,131
+KIF20A,130
+ZNF317,130
+MRPL13,130
+RCC1,130
+EXOSC10,130
+POLL,129
+PTGR2,129
+CENPH,129
+PSMD14,129
+MAU2,128
+DUT,128
+POLR2H,128
+RCOR1,127
+TAF1C,127
+PRPF8,127
+SPOUT1,126
+ARF4,126
+RPL7L1,126
+PHF12,125
+PFDN6,125
+MZF1,125
+INTS7,125
+HMBOX1,124
+AGBL5,124
+PWP1,124
+CPSF6,124
+ALG11,123
+POLR2E,123
+RBBP4,122
+SNTB2,122
+SNIP1,122
+TBCC,122
+AHCTF1,121
+HIST1H2AE,121
+EIF4A1,121
+MRTO4,121
+BRD8,121
+RPIA,120
+PSMC1,120
+WDR82,120
+F8A1,120
+RRP15,120
+ATIC,119
+CCND3,119
+FKBP9,119
+FAM102B,119
+C7orf50,119
+PTCD1,118
+RBMX,118
+NMT1,118
+NUP160,117
+TBL3,117
+EIF5A,116
+EXOSC9,116
+SLC2A8,116
+HNRNPU,115
+SKP1,115
+AAMP,115
+ATXN10,115
+ROMO1,115
+XRCC3,115
+HNRNPK,114
+PTCD3,113
+GTF2F1,113
+MED26,113
+UQCC2,113
+PLEKHN1,113
+GMIP,113
+MRPS14,112
+HEXIM1,112
+CMC4,111
+SPATA5,111
+MIS12,110
+USP37,110
+MRPS18C,110
+CDC45,110
+CHCHD3,110
+TBCD,110
+CARS,110
+STAG2,110
+POLA1,110
+LEO1,108
+ISCU,108
+LTBP4,108
+SCFD1,108
+ANKRD39,107
+FUNDC2,107
+BORA,107
+DTL,107
+RPL13,107
+CHEK1,106
+RBM48,106
+ARID3A,106
+NSL1,106
+ARFRP1,105
+RPS21,105
+GART,105
+ESYT2,105
+CCT5,105
+SNRPA,104
+MED9,104
+ICE1,104
+MED28,103
+FASN,103
+UBR4,103
+PRC1,103
+SFPQ,103
+C1orf131,102
+MASTL,102
+NDUFS5,102
+RPSA,102
+DTYMK,102
+NOL10,101
+DEPDC5,100
+NCAPH,100
+ATP6V1C1,100
+TUBGCP3,99
+RBM25,99
+C18orf21,99
+RPS10,98
+EIF2S2,98
+DYNC1I2,98
+RPL9,98
+RPA1,98
+RCCD1,98
+NCBP1,98
+WDR92,98
+HAUS1,97
+SF3B4,97
+TYK2,97
+RTF1,97
+GATA1,95
+LRRC37B,95
+RPAIN,95
+XRN1,95
+PREB,95
+NDC80,94
+RAE1,94
+WDR25,94
+KIF18A,94
+SET,94
+HNRNPDL,93
+PRMT5,92
+CDK12,92
+RPP38,92
+PGPEP1,92
+SPTLC1,92
+TAF1,92
+HAUS6,91
+RNF168,90
+RUVBL2,90
+RSL24D1,89
+DIS3,89
+ZC3H3,88
+PSMA3,88
+EWSR1,88
+RBM12,88
+CAST,88
+HSPD1,87
+EEFSEC,87
+ABCB10,87
+ZNF84,86
+CPNE1,86
+WDFY3,86
+USP5,85
+NOL9,85
+MRPL11,85
+RNF31,85
+CDCA5,84
+TRNP1,84
+KIF11,84
+KARS,84
+NEPRO,83
+POLR2K,83
+AAR2,83
+PSMB3,83
+FARS2,83
+PIAS4,83
+PTBP1,82
+AQR,82
+STX18,82
+SNRPE,81
+USP8,81
+SNRPB,81
+PPIE,80
+CNOT9,80
+SERF2,80
+RPL18A,80
+HOXC10,79
+DGCR8,79
+MED18,79
+RBM4,79
+SDR39U1,79
+WDR33,78
+NDUFAF7,78
+CADM4,78
+SNRPD3,78
+LYRM4,77
+GTF2B,77
+SMU1,77
+MED24,77
+ANAPC10,77
+RBM19,76
+OLFML3,76
+ZBTB44,76
+GOSR2,76
+SMARCC1,76
+GLMN,76
+SNAPC2,75
+CENPP,75
+CARF,75
+BUD13,75
+MOCS3,74
+GAK,74
+DDX49,74
+SPDL1,74
+YPEL1,73
+PLK1,73
+THUMPD1,72
+TXNL4A,72
+WDTC1,70
+THOC1,70
+UTP11,70
+ZNF207,70
+RBBP6,70
+POLR2F,70
+DHX29,69
+PUF60,69
+CAP1,69
+RPL12,69
+ZNF559,68
+HSPH1,68
+HSPA5,68
+WEE1,67
+KDM2A,67
+RPL37,67
+RPS25,67
+NCAPG,66
+PARS2,66
+GNPAT,65
+RRM1,65
+SERPINB1,65
+SNRNP70,65
+TWSG1,64
+EXOSC6,63
+TCP1,63
+HARS2,62
+NF1,62
+ZNF574,62
+PSMB6,61
+GLI4,61
+PAFAH1B1,61
+BANF1,61
+CA5A,61
+USP19,60
+ADNP2,60
+ZC3H18,59
+RPF2,59
+ARL6IP6,59
+ANAPC4,59
+YBX3,59
+PABPC1,59
+AP2A1,59
+INO80D,58
+NUF2,58
+CDC20,58
+PSMC4,58
+TFIP11,58
+POLR2C,58
+RAN,58
+NUDT21,57
+EIF3G,57
+YY1,57
+YBX1,57
+PLRG1,57
+PSMB1,57
+DCLRE1B,56
+MRPS18B,56
+NOP2,56
+SUPT4H1,55
+POLR2L,55
+PSMG1,55
+COG3,55
+PCID2,55
+SEC62,54
+TPP2,54
+SLC16A5,54
+GUCD1,54
+NOMO1,54
+CUL7,53
+CEP192,53
+MAP2K7,53
+HSPA8,53
+RPS15,53
+POLE2,53
+DNM2,52
+NUP205,52
+SMG6,52
+RPS17,52
+IFITM3,52
+CLP1,51
+PSMD2,51
+FAM133B,50
+SMC3,50
+ZWINT,49
+RPS16,48
+ECT2,48
+ELP4,48
+HHEX,48
+PPWD1,47
+NOC2L,47
+UTP3,47
+EXOC8,46
+S100A1,46
+KLF7,46
+SLC25A42,46
+EIF3E,46
+WDR7,46
+PHF5A,45
+ACTL6A,45
+ATP5F1C,44
+PAK1IP1,43
+FOXO1,43
+SEC13,43
+NOS1AP,43
+CAD,43
+RPL34,43
+ACTR5,43
+RELL2,42
+USP36,42
+UTP25,41
+BUD31,41
+EMG1,41
+PSMG4,41
+KANSL1,41
+RBM39,41
+FTSJ3,41
+PSMD11,40
+CCNQ,40
+NSRP1,40
+ZBTB14,40
+CHMP1A,40
+HAMP,40
+RAD21,40
+SPAG7,40
+ZC3H8,40
+LUC7L3,39
+CACTIN,39
+CDC26,38
+TAF1A,38
+CTCF,38
+MCEE,37
+RPL27,37
+SF3B2,37
+SLC35A4,37
+BMP2K,37
+ATP5MD,37
+DROSHA,36
+PRPF38A,36
+RPL11,36
+SNRPA1,35
+TOP2A,35
+HIST1H2BJ,35
+TTI2,35
+MED27,35
+MED31,35
+RANBP2,35
+SAP30BP,34
+NDUFA2,34
+PEX1,34
+PCM1,34
+NDUFAF5,34
+PSMC2,34
+RNF103,34
+CHAF1A,33
+ARPC1B,33
+LIN52,33
+TVP23C,32
+PSMC3,32
+LAMB1,32
+ACSS2,32
+KAT5,32
+CMTR2,32
+NAT10,32
+MRM1,32
+WBP1L,31
+VMP1,31
+RACK1,31
+NFKBIE,31
+SAP130,31
+CWC22,31
+MST1,31
+SNRPF,31
+OGT,31
+CDC27,30
+DDX3X,30
+DDX42,30

analysis/replogle_xstate_reembed/replogle_concat_input_no_xstate.h5ad

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d46dba973128cdb5c89867167223d9db8f2bff9fa70a02ad7ad64a62720e04e
+size 9173527297

analysis/replogle_xstate_reembed/replogle_concat_reembedded_se600m.h5ad

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac9644b41e9bd84ff00b029184c210f03363eb31e193f1c1713f75b7b3ba6ee3
+size 30010775846

data/adamson_state_compatible/patch_adamson_to_state_schema.py

@@ -0,0 +1,219 @@
+import os
+from pathlib import Path
+
+import anndata as ad
+import numpy as np
+import pandas as pd
+import scipy.sparse as sp
+
+src = Path(os.environ["ADAMSON_RAW_H5AD"])
+dst = Path(os.environ["ADAMSON_NO_STATE_H5AD"])
+report_dir = Path(os.environ["ADAMSON_REPORT_DIR"])
+
+dst.parent.mkdir(parents=True, exist_ok=True)
+report_dir.mkdir(parents=True, exist_ok=True)
+
+print("Reading:", src)
+a = ad.read_h5ad(src)
+
+print("\nRAW ANNData")
+print(a)
+print("obs columns:", list(a.obs.columns))
+print("var columns:", list(a.var.columns))
+print("layers:", list(a.layers.keys()))
+print("obsm:", list(a.obsm.keys()))
+
+# ---------------------------------------------------------------------
+# 1. Confirm expression matrix.
+# ---------------------------------------------------------------------
+# Your inspection showed:
+#   X == layer["logNor"]
+#   layer["counts"] is raw counts
+# Therefore we keep a.X as the SE input matrix.
+if "logNor" in a.layers:
+    x_sample = a.X[:1000, :1000]
+    l_sample = a.layers["logNor"][:1000, :1000]
+
+    if sp.issparse(x_sample):
+        x_sample = x_sample.toarray()
+    if sp.issparse(l_sample):
+        l_sample = l_sample.toarray()
+
+    mad = float(np.mean(np.abs(np.asarray(x_sample) - np.asarray(l_sample))))
+    print("\nX vs layer['logNor'] sample mean abs diff:", mad)
+
+    if mad > 1e-8:
+        print("WARNING: X differs from layer['logNor']; keeping X as-is.")
+else:
+    print("\nNo layer['logNor'] found; keeping X as-is.")
+
+# ---------------------------------------------------------------------
+# 2. Ensure gene names are usable.
+# ---------------------------------------------------------------------
+# Adamson var_names appear to be the expression gene names.
+# Ensembl IDs are stored separately in var["Ensembl_ID"].
+a.var_names_make_unique()
+
+print("\nvar_names sample:")
+print(list(a.var_names[:20]))
+
+if "Ensembl_ID" in a.var.columns:
+    print("\nEnsembl_ID sample:")
+    print(a.var["Ensembl_ID"].astype(str).head(20).to_list())
+
+# ---------------------------------------------------------------------
+# 3. Perturbation column -> obs["gene"].
+# ---------------------------------------------------------------------
+# Adamson already has obs["gene"], with CTRL as the control.
+if "gene" not in a.obs.columns:
+    raise ValueError("Expected obs['gene'] in Adamson file, but it is missing.")
+
+a.obs["gene_original"] = a.obs["gene"].astype(str)
+a.obs["gene"] = a.obs["gene"].astype(str)
+
+print("\nTop raw perturbations:")
+print(a.obs["gene"].value_counts().head(30))
+
+# Normalize controls to the STATE-style label.
+control_aliases = {
+    "CTRL",
+    "ctrl",
+    "Control",
+    "control",
+    "CONTROL",
+    "NT",
+    "NTC",
+    "non-targeting",
+    "non_targeting",
+    "nontargeting",
+    "negative_control",
+    "negctrl",
+    "mock",
+    "unperturbed",
+}
+
+mask_control = a.obs["gene"].astype(str).str.lower().isin(
+    {x.lower() for x in control_aliases}
+)
+a.obs.loc[mask_control, "gene"] = "non-targeting"
+
+print("\nTop perturbations after control normalization:")
+print(a.obs["gene"].value_counts().head(30))
+print("non-targeting cells:", int((a.obs["gene"] == "non-targeting").sum()))
+
+if int((a.obs["gene"] == "non-targeting").sum()) == 0:
+    raise ValueError("No non-targeting controls found after control normalization.")
+
+# ---------------------------------------------------------------------
+# 4. Biological context -> obs["cell_line"].
+# ---------------------------------------------------------------------
+# Adamson is conventionally K562 in these perturbation benchmarks.
+if "cell_line" not in a.obs.columns:
+    a.obs["cell_line"] = "k562"
+else:
+    a.obs["cell_line"] = a.obs["cell_line"].astype(str)
+
+# ---------------------------------------------------------------------
+# 5. Batch/sample -> obs["gem_group"].
+# ---------------------------------------------------------------------
+# This Adamson h5ad does not expose a clear batch column in the inspection.
+# Use a dummy batch for now.
+if "gem_group" not in a.obs.columns:
+    a.obs["gem_group"] = "batch0"
+else:
+    a.obs["gem_group"] = a.obs["gem_group"].astype(str)
+
+# ---------------------------------------------------------------------
+# 6. Convert key columns to categories.
+# ---------------------------------------------------------------------
+for col in ["gene", "cell_line", "gem_group"]:
+    a.obs[col] = a.obs[col].astype(str).astype("category")
+    a.obs[col] = a.obs[col].cat.remove_unused_categories()
+
+# ---------------------------------------------------------------------
+# 7. Remove stale embeddings.
+# ---------------------------------------------------------------------
+for key in ["X_state", "X_vci"]:
+    if key in a.obsm:
+        del a.obsm[key]
+        print(f"Deleted stale obsm[{key!r}]")
+
+# ---------------------------------------------------------------------
+# 8. Create X_hvg from var["highly_variable_2000"].
+# ---------------------------------------------------------------------
+preferred_hvg_col = "highly_variable_2000"
+
+if preferred_hvg_col not in a.var.columns:
+    raise ValueError(
+        f"Expected var[{preferred_hvg_col!r}], but it is missing. "
+        "Use another HVG column or compute HVGs first."
+    )
+
+hvg_mask = a.var[preferred_hvg_col].astype(bool).to_numpy()
+print(f"\nUsing var[{preferred_hvg_col!r}] for X_hvg")
+print("HVG count:", int(hvg_mask.sum()))
+
+if int(hvg_mask.sum()) != 2000:
+    raise ValueError(f"Expected 2000 HVGs, found {int(hvg_mask.sum())}")
+
+x_hvg = a[:, hvg_mask].X
+if sp.issparse(x_hvg):
+    x_hvg = x_hvg.toarray()
+
+a.obsm["X_hvg"] = np.asarray(x_hvg, dtype=np.float32)
+print("Created obsm['X_hvg']:", a.obsm["X_hvg"].shape)
+
+# ---------------------------------------------------------------------
+# 9. Save reports.
+# ---------------------------------------------------------------------
+a.obs["gene"].astype(str).value_counts().to_csv(
+    report_dir / "patched_gene_counts.csv"
+)
+a.obs["cell_line"].astype(str).value_counts().to_csv(
+    report_dir / "patched_cell_line_counts.csv"
+)
+a.obs["gem_group"].astype(str).value_counts().to_csv(
+    report_dir / "patched_gem_group_counts.csv"
+)
+
+summary = []
+summary.append(f"source={src}")
+summary.append(f"output={dst}")
+summary.append(f"shape={a.shape}")
+summary.append(f"obs_columns={list(a.obs.columns)}")
+summary.append(f"var_columns={list(a.var.columns)}")
+summary.append(f"layers={list(a.layers.keys())}")
+summary.append(f"obsm_keys={list(a.obsm.keys())}")
+summary.append(f"gene_nunique={a.obs['gene'].astype(str).nunique()}")
+summary.append(f"cell_line_nunique={a.obs['cell_line'].astype(str).nunique()}")
+summary.append(f"gem_group_nunique={a.obs['gem_group'].astype(str).nunique()}")
+summary.append(f"non_targeting_cells={int((a.obs['gene'].astype(str) == 'non-targeting').sum())}")
+summary.append(f"X_hvg_shape={a.obsm['X_hvg'].shape}")
+
+(report_dir / "patched_schema_summary.txt").write_text(
+    "\n".join(summary) + "\n"
+)
+
+# ---------------------------------------------------------------------
+# 10. Final print and write.
+# ---------------------------------------------------------------------
+print("\nFINAL PATCHED ANNData")
+print(a)
+print("obs columns:", list(a.obs.columns))
+print("var columns:", list(a.var.columns))
+print("layers:", list(a.layers.keys()))
+print("obsm keys:", list(a.obsm.keys()))
+
+print("\ngene counts:")
+print(a.obs["gene"].astype(str).value_counts().head(30))
+
+print("\ncell_line counts:")
+print(a.obs["cell_line"].astype(str).value_counts())
+
+print("\ngem_group counts:")
+print(a.obs["gem_group"].astype(str).value_counts())
+
+print("\nWriting:", dst)
+a.write_h5ad(dst, compression="gzip")
+print("Done.")
+print("Summary:", report_dir / "patched_schema_summary.txt")