From c6717c8ea69058b68817594c27cdfa891d36c4e5 Mon Sep 17 00:00:00 2001
From: root <1700011741@pku.edu.cn>
Date: Sat, 3 Feb 2024 17:18:08 +0800
Subject: [PATCH 1/4] enzyme benchmark

---
 .../data/00_scipaper_enzyme/auto_add.sh       | 15 +++++++++++
 .../data/00_scipaper_enzyme/sample_file       |  1 +
 .../data/00_scipaper_enzyme/samples.jsonl     |  3 +++
 .../auto_add.sh                               | 26 +++++++++++++++++++
 .../sample_file                               |  1 +
 .../samples.jsonl                             |  3 +++
 .../00_scipaper_enzyme_inhibitor/auto_add.sh  | 26 +++++++++++++++++++
 .../00_scipaper_enzyme_inhibitor/sample_file  |  1 +
 .../samples.jsonl                             |  3 +++
 .../auto_add.sh                               | 26 +++++++++++++++++++
 .../sample_file                               |  1 +
 .../samples.jsonl                             |  3 +++
 evals/registry/evals/00_scipaper_enzyme.yaml  | 19 ++++++++++++++
 .../00_scipaper_enzyme_activate_compound.yaml | 18 +++++++++++++
 .../evals/00_scipaper_enzyme_inhibitor.yaml   | 18 +++++++++++++
 .../00_scipaper_enzyme_localization.yaml      | 16 ++++++++++++
 16 files changed, 180 insertions(+)
 create mode 100644 evals/registry/data/00_scipaper_enzyme/auto_add.sh
 create mode 100644 evals/registry/data/00_scipaper_enzyme/sample_file
 create mode 100644 evals/registry/data/00_scipaper_enzyme/samples.jsonl
 create mode 100644 evals/registry/data/00_scipaper_enzyme_activate_compound/auto_add.sh
 create mode 100644 evals/registry/data/00_scipaper_enzyme_activate_compound/sample_file
 create mode 100644 evals/registry/data/00_scipaper_enzyme_activate_compound/samples.jsonl
 create mode 100644 evals/registry/data/00_scipaper_enzyme_inhibitor/auto_add.sh
 create mode 100644 evals/registry/data/00_scipaper_enzyme_inhibitor/sample_file
 create mode 100644 evals/registry/data/00_scipaper_enzyme_inhibitor/samples.jsonl
 create mode 100644 evals/registry/data/00_scipaper_enzyme_localization/auto_add.sh
 create mode 100644 evals/registry/data/00_scipaper_enzyme_localization/sample_file
 create mode 100644 evals/registry/data/00_scipaper_enzyme_localization/samples.jsonl
 create mode 100644 evals/registry/evals/00_scipaper_enzyme.yaml
 create mode 100644 evals/registry/evals/00_scipaper_enzyme_activate_compound.yaml
 create mode 100644 evals/registry/evals/00_scipaper_enzyme_inhibitor.yaml
 create mode 100644 evals/registry/evals/00_scipaper_enzyme_localization.yaml

diff --git a/evals/registry/data/00_scipaper_enzyme/auto_add.sh b/evals/registry/data/00_scipaper_enzyme/auto_add.sh
new file mode 100644
index 0000000000..4537d504c4
--- /dev/null
+++ b/evals/registry/data/00_scipaper_enzyme/auto_add.sh
@@ -0,0 +1,15 @@
+#!/bin/bash
+for paper in /root/uni-finder/enzyme/paper/*.pdf
+do
+	file_name="${paper##*/}"
+	name=${file_name%.*}
+	key_word=""
+	key_word=$(grep "${name}" samples.jsonl)
+        if [[ ${key_word} == "" ]]
+	then
+		echo "add ${name} to jsonl"
+		sed 's|target_mark|'"${name}"'|g' sample_file >> samples.jsonl
+	else
+		echo "${name}: was already in the jsonl"
+	fi
+done
diff --git a/evals/registry/data/00_scipaper_enzyme/sample_file b/evals/registry/data/00_scipaper_enzyme/sample_file
new file mode 100644
index 0000000000..530f8260c0
--- /dev/null
+++ b/evals/registry/data/00_scipaper_enzyme/sample_file
@@ -0,0 +1 @@
+{"file_name": "../uni-finder/enzyme/paper/target_mark.pdf", "file_link": "https://dp-filetrans-bj.oss-cn-beijing.aliyuncs.com/changjunhan/target_mark.pdf", "answerfile_name": "../uni-finder/enzyme/answer/target_mark.csv", "answerfile_link": "https://dp-filetrans-bj.oss-cn-beijing.aliyuncs.com/changjunhan/target_mark.csv", "compare_fields": [""], "index": ""}
diff --git a/evals/registry/data/00_scipaper_enzyme/samples.jsonl b/evals/registry/data/00_scipaper_enzyme/samples.jsonl
new file mode 100644
index 0000000000..01eb9d337f
--- /dev/null
+++ b/evals/registry/data/00_scipaper_enzyme/samples.jsonl
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2bf58abc2068a46085404efd770a640185ac65d831c49c3b98800a60ff62814b
+size 4699
diff --git a/evals/registry/data/00_scipaper_enzyme_activate_compound/auto_add.sh b/evals/registry/data/00_scipaper_enzyme_activate_compound/auto_add.sh
new file mode 100644
index 0000000000..f699a14a86
--- /dev/null
+++ b/evals/registry/data/00_scipaper_enzyme_activate_compound/auto_add.sh
@@ -0,0 +1,26 @@
+#!/bin/bash
+target_job=$1
+if [[ ${target_job} == "" ]]
+then
+	echo ">>> Error: target_job is not define"
+	exit
+fi
+if [[ ! -f samples.jsonl ]]
+then
+	touch samples.jsonl
+fi
+for paper in /root/uni-finder/enzyme/"${target_job}"/paper/*.pdf
+do
+	echo "find file ${paper}"
+	file_name="${paper##*/}"
+	name=${file_name%.*}
+	key_word=""
+	key_word=$(grep "${name}" samples.jsonl)
+        if [[ ${key_word} == "" ]]
+	then
+		echo "add ${name} to jsonl"
+		sed 's|target_mark|'"${name}"'|g' sample_file | sed 's|target_Job|'"${target_job}"'|g' >> samples.jsonl
+	else
+		echo "${name}: was already in the jsonl"
+	fi
+done
diff --git a/evals/registry/data/00_scipaper_enzyme_activate_compound/sample_file b/evals/registry/data/00_scipaper_enzyme_activate_compound/sample_file
new file mode 100644
index 0000000000..95ce86b217
--- /dev/null
+++ b/evals/registry/data/00_scipaper_enzyme_activate_compound/sample_file
@@ -0,0 +1 @@
+{"file_name": "../uni-finder/enzyme/target_Job/paper/target_mark.pdf", "file_link": "https://dp-filetrans-bj.oss-cn-beijing.aliyuncs.com/changjunhan/target_mark.pdf", "answerfile_name": "../uni-finder/enzyme/target_Job/answer/target_mark.csv", "answerfile_link": "https://dp-filetrans-bj.oss-cn-beijing.aliyuncs.com/changjunhan/target_mark.csv", "compare_fields": ["Activating Compound", "Comment", "Organism"], "index": "Activating Compound"}
diff --git a/evals/registry/data/00_scipaper_enzyme_activate_compound/samples.jsonl b/evals/registry/data/00_scipaper_enzyme_activate_compound/samples.jsonl
new file mode 100644
index 0000000000..488ee911ff
--- /dev/null
+++ b/evals/registry/data/00_scipaper_enzyme_activate_compound/samples.jsonl
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfbe6bb20ea161238ab3d5e3404d9df76514d88c7ed9fe528d2984d0d9fb7d07
+size 538
diff --git a/evals/registry/data/00_scipaper_enzyme_inhibitor/auto_add.sh b/evals/registry/data/00_scipaper_enzyme_inhibitor/auto_add.sh
new file mode 100644
index 0000000000..f699a14a86
--- /dev/null
+++ b/evals/registry/data/00_scipaper_enzyme_inhibitor/auto_add.sh
@@ -0,0 +1,26 @@
+#!/bin/bash
+target_job=$1
+if [[ ${target_job} == "" ]]
+then
+	echo ">>> Error: target_job is not define"
+	exit
+fi
+if [[ ! -f samples.jsonl ]]
+then
+	touch samples.jsonl
+fi
+for paper in /root/uni-finder/enzyme/"${target_job}"/paper/*.pdf
+do
+	echo "find file ${paper}"
+	file_name="${paper##*/}"
+	name=${file_name%.*}
+	key_word=""
+	key_word=$(grep "${name}" samples.jsonl)
+        if [[ ${key_word} == "" ]]
+	then
+		echo "add ${name} to jsonl"
+		sed 's|target_mark|'"${name}"'|g' sample_file | sed 's|target_Job|'"${target_job}"'|g' >> samples.jsonl
+	else
+		echo "${name}: was already in the jsonl"
+	fi
+done
diff --git a/evals/registry/data/00_scipaper_enzyme_inhibitor/sample_file b/evals/registry/data/00_scipaper_enzyme_inhibitor/sample_file
new file mode 100644
index 0000000000..57bad47af5
--- /dev/null
+++ b/evals/registry/data/00_scipaper_enzyme_inhibitor/sample_file
@@ -0,0 +1 @@
+{"file_name": "../uni-finder/enzyme/target_Job/paper/target_mark.pdf", "file_link": "https://dp-filetrans-bj.oss-cn-beijing.aliyuncs.com/changjunhan/target_mark.pdf", "answerfile_name": "../uni-finder/enzyme/target_Job/answer/target_mark.csv", "answerfile_link": "https://dp-filetrans-bj.oss-cn-beijing.aliyuncs.com/changjunhan/target_mark.csv", "compare_fields": ["Inhibitors", "Comment", "Organism"], "index": "Inhibitors"}
diff --git a/evals/registry/data/00_scipaper_enzyme_inhibitor/samples.jsonl b/evals/registry/data/00_scipaper_enzyme_inhibitor/samples.jsonl
new file mode 100644
index 0000000000..116a945850
--- /dev/null
+++ b/evals/registry/data/00_scipaper_enzyme_inhibitor/samples.jsonl
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49193f70b4942b3ad8aaac0497da4b37b6de40ebde79edb2ec3df6bfc0972924
+size 1444
diff --git a/evals/registry/data/00_scipaper_enzyme_localization/auto_add.sh b/evals/registry/data/00_scipaper_enzyme_localization/auto_add.sh
new file mode 100644
index 0000000000..f699a14a86
--- /dev/null
+++ b/evals/registry/data/00_scipaper_enzyme_localization/auto_add.sh
@@ -0,0 +1,26 @@
+#!/bin/bash
+target_job=$1
+if [[ ${target_job} == "" ]]
+then
+	echo ">>> Error: target_job is not define"
+	exit
+fi
+if [[ ! -f samples.jsonl ]]
+then
+	touch samples.jsonl
+fi
+for paper in /root/uni-finder/enzyme/"${target_job}"/paper/*.pdf
+do
+	echo "find file ${paper}"
+	file_name="${paper##*/}"
+	name=${file_name%.*}
+	key_word=""
+	key_word=$(grep "${name}" samples.jsonl)
+        if [[ ${key_word} == "" ]]
+	then
+		echo "add ${name} to jsonl"
+		sed 's|target_mark|'"${name}"'|g' sample_file | sed 's|target_Job|'"${target_job}"'|g' >> samples.jsonl
+	else
+		echo "${name}: was already in the jsonl"
+	fi
+done
diff --git a/evals/registry/data/00_scipaper_enzyme_localization/sample_file b/evals/registry/data/00_scipaper_enzyme_localization/sample_file
new file mode 100644
index 0000000000..ec5ce35204
--- /dev/null
+++ b/evals/registry/data/00_scipaper_enzyme_localization/sample_file
@@ -0,0 +1 @@
+{"file_name": "../uni-finder/enzyme/target_Job/paper/target_mark.pdf", "file_link": "https://dp-filetrans-bj.oss-cn-beijing.aliyuncs.com/changjunhan/target_mark.pdf", "answerfile_name": "../uni-finder/enzyme/target_Job/answer/target_mark.csv", "answerfile_link": "https://dp-filetrans-bj.oss-cn-beijing.aliyuncs.com/changjunhan/target_mark.csv", "compare_fields": [ "Localization", "Organism"], "index":"Localization"}
diff --git a/evals/registry/data/00_scipaper_enzyme_localization/samples.jsonl b/evals/registry/data/00_scipaper_enzyme_localization/samples.jsonl
new file mode 100644
index 0000000000..ecf84e1650
--- /dev/null
+++ b/evals/registry/data/00_scipaper_enzyme_localization/samples.jsonl
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2909201b52e0c8f3e71ee569a65a72e4dfbdede7dde2d427c04e3e43185a86ca
+size 467
diff --git a/evals/registry/evals/00_scipaper_enzyme.yaml b/evals/registry/evals/00_scipaper_enzyme.yaml
new file mode 100644
index 0000000000..1ab8ea7d40
--- /dev/null
+++ b/evals/registry/evals/00_scipaper_enzyme.yaml
@@ -0,0 +1,19 @@
+scipaper_enzyme:
+  id: scipaper_enzyme.val.csv
+  metrics: [accuracy]
+
+scipaper_enzyme.val.csv:
+  class: evals.elsuite.rag_table_extract:TableExtract
+  args:
+    samples_jsonl: 00_scipaper_enzyme/samples.jsonl
+    instructions: |
+      Please give a complete list of SMILES structures, Km values, Vmax values, target info (protein or cell line), and organism of all substrates in the paper. Usually the substrates' tags are numbers or IUPAC names.
+      1. Output in csv format, write units not in header but in the value like "10.5 µM". Quote the value if it has comma! For example:
+      ```csv
+      Substrate,Inhibitors, Km value,Km max,Comment,organism,Vmax value,SMILES,Target info,Activating Compound,
+      ATP,Cu2+,0.001 mM,-,-,Homo sapiens,-,-,ATP-linker aldehyde,Carboxybenzaldehyde,
+      p-xylene,NADH,0.004 mM,-,-,Homo sapiens,-,C1CCCCC1,-,Methylbenzaldehyde
+      NADPH,benzaldehyde, 0.12 mM,125 mM,enzyme form ATP,Bos taurus,-,-,NH4+
+
+      ```
+      2. If there are multiple tables, concat them. Don't give me reference or using "...", give me complete table!
diff --git a/evals/registry/evals/00_scipaper_enzyme_activate_compound.yaml b/evals/registry/evals/00_scipaper_enzyme_activate_compound.yaml
new file mode 100644
index 0000000000..7241a1fe5c
--- /dev/null
+++ b/evals/registry/evals/00_scipaper_enzyme_activate_compound.yaml
@@ -0,0 +1,18 @@
+scipaper_enzyme_activate_compound:
+  id: scipaper_enzyme_activate_compound.val.csv
+  metrics: [accuracy]
+
+scipaper_enzyme_activate_compound.val.csv:
+  class: evals.elsuite.rag_table_extract:TableExtract
+  args:
+    samples_jsonl: 00_scipaper_enzyme_activate_compound/samples.jsonl
+    instructions: |
+      Please give a complete list of Activating Compound, Commentand Organism of all substrates in the paper. Usually the substrates' tags are numbers or IUPAC names.
+      1. Output in csv format, write units not in header but in the value like "10.5 µM". Quote the value if it has comma! For example:
+      ```csv
+      Activating Compound,Comment,Organism
+      Cu2+,at 0.001 mM of the activity without activator,Homo sapiens
+      p-xylene,"11.4 mM, slight activation",Bos taurus
+      NH4+, 0.002 mM,Bos taurus
+      ```
+      2. If there are multiple tables, concat them. Don't give me reference or using "...", give me complete table!
diff --git a/evals/registry/evals/00_scipaper_enzyme_inhibitor.yaml b/evals/registry/evals/00_scipaper_enzyme_inhibitor.yaml
new file mode 100644
index 0000000000..3c712c4701
--- /dev/null
+++ b/evals/registry/evals/00_scipaper_enzyme_inhibitor.yaml
@@ -0,0 +1,18 @@
+scipaper_enzyme_inhibitor:
+  id: scipaper_enzyme_inhibitor.val.csv
+  metrics: [accuracy]
+
+scipaper_enzyme_inhibitor.val.csv:
+  class: evals.elsuite.rag_table_extract:TableExtract
+  args:
+    samples_jsonl: 00_scipaper_enzyme_inhibitor/samples.jsonl
+    instructions: |
+      Please give a complete list of Inhibitor, Commentand Organism of all substrates in the paper. Usually the substrates' tags are numbers or IUPAC names.
+      1. Output in csv format, write units not in header but in the value like "10.5 µM". Quote the value if it has comma! For example:
+      ```csv
+      Inhibitor,Comment,Organism
+      ATP,"competitive inhibition of verapamil-dependent ATPase-activity",Homo sapiens
+      p-xylene,"11.4 mM, slight inhibitor",Bos taurus
+      NH4+, 0.002 mM,Bos taurus
+      ```
+      2. If there are multiple tables, concat them. Don't give me reference or using "...", give me complete table!
diff --git a/evals/registry/evals/00_scipaper_enzyme_localization.yaml b/evals/registry/evals/00_scipaper_enzyme_localization.yaml
new file mode 100644
index 0000000000..3c6ca4e590
--- /dev/null
+++ b/evals/registry/evals/00_scipaper_enzyme_localization.yaml
@@ -0,0 +1,16 @@
+scipaper_enzyme_localization:
+  id: scipaper_enzyme_localization.val.csv
+  metrics: [accuracy]
+
+scipaper_enzyme_localization.val.csv:
+  class: evals.elsuite.rag_table_extract:TableExtract
+  args:
+    samples_jsonl: 00_scipaper_enzyme_localization/samples.jsonl
+    instructions: |
+      Please give a complete list of Localization, Commentand and Organism of all substrates in the paper. Usually the substrates' tags are numbers or IUPAC names.
+      1. Output in csv format, write units not in header but in the value like "10.5 µM". Quote the value if it has comma! For example:
+      ```csv
+      Localization,Organism
+      periplasm,Bos taurus
+      ```
+      2. If there are multiple tables, concat them. Don't give me reference or using "...", give me complete table!

From 0888cfc8ae8a606b5365fb10db949781c3fa6e97 Mon Sep 17 00:00:00 2001
From: root <1700011741@pku.edu.cn>
Date: Mon, 5 Feb 2024 22:32:41 +0800
Subject: [PATCH 2/4] add km

---
 .../data/00_scipaper_enzyme_km/auto_add.sh    | 26 +++++++++++++++++++
 .../data/00_scipaper_enzyme_km/sample_file    |  1 +
 .../data/00_scipaper_enzyme_km/samples.jsonl  |  3 +++
 3 files changed, 30 insertions(+)
 create mode 100644 evals/registry/data/00_scipaper_enzyme_km/auto_add.sh
 create mode 100644 evals/registry/data/00_scipaper_enzyme_km/sample_file
 create mode 100644 evals/registry/data/00_scipaper_enzyme_km/samples.jsonl

diff --git a/evals/registry/data/00_scipaper_enzyme_km/auto_add.sh b/evals/registry/data/00_scipaper_enzyme_km/auto_add.sh
new file mode 100644
index 0000000000..f699a14a86
--- /dev/null
+++ b/evals/registry/data/00_scipaper_enzyme_km/auto_add.sh
@@ -0,0 +1,26 @@
+#!/bin/bash
+target_job=$1
+if [[ ${target_job} == "" ]]
+then
+	echo ">>> Error: target_job is not define"
+	exit
+fi
+if [[ ! -f samples.jsonl ]]
+then
+	touch samples.jsonl
+fi
+for paper in /root/uni-finder/enzyme/"${target_job}"/paper/*.pdf
+do
+	echo "find file ${paper}"
+	file_name="${paper##*/}"
+	name=${file_name%.*}
+	key_word=""
+	key_word=$(grep "${name}" samples.jsonl)
+        if [[ ${key_word} == "" ]]
+	then
+		echo "add ${name} to jsonl"
+		sed 's|target_mark|'"${name}"'|g' sample_file | sed 's|target_Job|'"${target_job}"'|g' >> samples.jsonl
+	else
+		echo "${name}: was already in the jsonl"
+	fi
+done
diff --git a/evals/registry/data/00_scipaper_enzyme_km/sample_file b/evals/registry/data/00_scipaper_enzyme_km/sample_file
new file mode 100644
index 0000000000..a218a4803b
--- /dev/null
+++ b/evals/registry/data/00_scipaper_enzyme_km/sample_file
@@ -0,0 +1 @@
+{"file_name": "../uni-finder/enzyme/target_Job/paper/target_mark.pdf", "file_link": "https://dp-filetrans-bj.oss-cn-beijing.aliyuncs.com/changjunhan/target_mark.pdf", "answerfile_name": "../uni-finder/enzyme/target_Job/answer/target_mark.csv", "answerfile_link": "https://dp-filetrans-bj.oss-cn-beijing.aliyuncs.com/changjunhan/target_mark.csv", "compare_fields": ["Substrate", "SMILES", "Km value", "Km vmax", "organism"], "index": "Substrate"}
diff --git a/evals/registry/data/00_scipaper_enzyme_km/samples.jsonl b/evals/registry/data/00_scipaper_enzyme_km/samples.jsonl
new file mode 100644
index 0000000000..d699617478
--- /dev/null
+++ b/evals/registry/data/00_scipaper_enzyme_km/samples.jsonl
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d526411b82df30527d64c8d35afe4a09152d6669637fd876242f4ae0539c447e
+size 510

From a2315db834200c66006b45b28e8ff7f63a5aa216 Mon Sep 17 00:00:00 2001
From: root <1700011741@pku.edu.cn>
Date: Mon, 5 Feb 2024 22:33:00 +0800
Subject: [PATCH 3/4] add km

---
 ...00_scipaper_enzyme.yaml => 00_scipaper_enzyme_km.yaml} | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)
 rename evals/registry/evals/{00_scipaper_enzyme.yaml => 00_scipaper_enzyme_km.yaml} (87%)

diff --git a/evals/registry/evals/00_scipaper_enzyme.yaml b/evals/registry/evals/00_scipaper_enzyme_km.yaml
similarity index 87%
rename from evals/registry/evals/00_scipaper_enzyme.yaml
rename to evals/registry/evals/00_scipaper_enzyme_km.yaml
index 1ab8ea7d40..9e5d4d0734 100644
--- a/evals/registry/evals/00_scipaper_enzyme.yaml
+++ b/evals/registry/evals/00_scipaper_enzyme_km.yaml
@@ -1,11 +1,11 @@
-scipaper_enzyme:
-  id: scipaper_enzyme.val.csv
+scipaper_enzyme_km:
+  id: scipaper_enzyme_km.val.csv
   metrics: [accuracy]
 
-scipaper_enzyme.val.csv:
+scipaper_enzyme_km.val.csv:
   class: evals.elsuite.rag_table_extract:TableExtract
   args:
-    samples_jsonl: 00_scipaper_enzyme/samples.jsonl
+    samples_jsonl: 00_scipaper_enzyme_km/samples.jsonl
     instructions: |
       Please give a complete list of SMILES structures, Km values, Vmax values, target info (protein or cell line), and organism of all substrates in the paper. Usually the substrates' tags are numbers or IUPAC names.
       1. Output in csv format, write units not in header but in the value like "10.5 µM". Quote the value if it has comma! For example:

From c32d3fb083058bd3c5679e77e0696c02ed736396 Mon Sep 17 00:00:00 2001
From: TablewareBox <1700011741@pku.edu.cn>
Date: Tue, 6 Feb 2024 06:20:12 +0800
Subject: [PATCH 4/4] add enzyme testset and fix data

---
 .../data/00_scipaper_enzyme/auto_add.sh       | 15 -----------
 .../data/00_scipaper_enzyme/sample_file       |  1 -
 .../data/00_scipaper_enzyme/samples.jsonl     |  3 ---
 .../auto_add.sh                               | 26 -------------------
 .../sample_file                               |  1 -
 .../00_scipaper_enzyme_inhibitor/auto_add.sh  | 26 -------------------
 .../00_scipaper_enzyme_inhibitor/sample_file  |  1 -
 .../data/00_scipaper_enzyme_km/auto_add.sh    | 26 -------------------
 .../data/00_scipaper_enzyme_km/sample_file    |  1 -
 .../data/00_scipaper_enzyme_km/samples.jsonl  |  3 ---
 .../auto_add.sh                               | 26 -------------------
 .../sample_file                               |  1 -
 .../samples.jsonl                             |  3 +++
 .../registry/eval_sets/chemistry_enzyme.yaml  |  6 +++++
 ...yaml => 00_scipaper_enzyme_substrate.yaml} |  8 +++---
 15 files changed, 13 insertions(+), 134 deletions(-)
 delete mode 100644 evals/registry/data/00_scipaper_enzyme/auto_add.sh
 delete mode 100644 evals/registry/data/00_scipaper_enzyme/sample_file
 delete mode 100644 evals/registry/data/00_scipaper_enzyme/samples.jsonl
 delete mode 100644 evals/registry/data/00_scipaper_enzyme_activate_compound/auto_add.sh
 delete mode 100644 evals/registry/data/00_scipaper_enzyme_activate_compound/sample_file
 delete mode 100644 evals/registry/data/00_scipaper_enzyme_inhibitor/auto_add.sh
 delete mode 100644 evals/registry/data/00_scipaper_enzyme_inhibitor/sample_file
 delete mode 100644 evals/registry/data/00_scipaper_enzyme_km/auto_add.sh
 delete mode 100644 evals/registry/data/00_scipaper_enzyme_km/sample_file
 delete mode 100644 evals/registry/data/00_scipaper_enzyme_km/samples.jsonl
 delete mode 100644 evals/registry/data/00_scipaper_enzyme_localization/auto_add.sh
 delete mode 100644 evals/registry/data/00_scipaper_enzyme_localization/sample_file
 create mode 100644 evals/registry/data/00_scipaper_enzyme_substrate/samples.jsonl
 create mode 100644 evals/registry/eval_sets/chemistry_enzyme.yaml
 rename evals/registry/evals/{00_scipaper_enzyme_km.yaml => 00_scipaper_enzyme_substrate.yaml} (85%)

diff --git a/evals/registry/data/00_scipaper_enzyme/auto_add.sh b/evals/registry/data/00_scipaper_enzyme/auto_add.sh
deleted file mode 100644
index 4537d504c4..0000000000
--- a/evals/registry/data/00_scipaper_enzyme/auto_add.sh
+++ /dev/null
@@ -1,15 +0,0 @@
-#!/bin/bash
-for paper in /root/uni-finder/enzyme/paper/*.pdf
-do
-	file_name="${paper##*/}"
-	name=${file_name%.*}
-	key_word=""
-	key_word=$(grep "${name}" samples.jsonl)
-        if [[ ${key_word} == "" ]]
-	then
-		echo "add ${name} to jsonl"
-		sed 's|target_mark|'"${name}"'|g' sample_file >> samples.jsonl
-	else
-		echo "${name}: was already in the jsonl"
-	fi
-done
diff --git a/evals/registry/data/00_scipaper_enzyme/sample_file b/evals/registry/data/00_scipaper_enzyme/sample_file
deleted file mode 100644
index 530f8260c0..0000000000
--- a/evals/registry/data/00_scipaper_enzyme/sample_file
+++ /dev/null
@@ -1 +0,0 @@
-{"file_name": "../uni-finder/enzyme/paper/target_mark.pdf", "file_link": "https://dp-filetrans-bj.oss-cn-beijing.aliyuncs.com/changjunhan/target_mark.pdf", "answerfile_name": "../uni-finder/enzyme/answer/target_mark.csv", "answerfile_link": "https://dp-filetrans-bj.oss-cn-beijing.aliyuncs.com/changjunhan/target_mark.csv", "compare_fields": [""], "index": ""}
diff --git a/evals/registry/data/00_scipaper_enzyme/samples.jsonl b/evals/registry/data/00_scipaper_enzyme/samples.jsonl
deleted file mode 100644
index 01eb9d337f..0000000000
--- a/evals/registry/data/00_scipaper_enzyme/samples.jsonl
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:2bf58abc2068a46085404efd770a640185ac65d831c49c3b98800a60ff62814b
-size 4699
diff --git a/evals/registry/data/00_scipaper_enzyme_activate_compound/auto_add.sh b/evals/registry/data/00_scipaper_enzyme_activate_compound/auto_add.sh
deleted file mode 100644
index f699a14a86..0000000000
--- a/evals/registry/data/00_scipaper_enzyme_activate_compound/auto_add.sh
+++ /dev/null
@@ -1,26 +0,0 @@
-#!/bin/bash
-target_job=$1
-if [[ ${target_job} == "" ]]
-then
-	echo ">>> Error: target_job is not define"
-	exit
-fi
-if [[ ! -f samples.jsonl ]]
-then
-	touch samples.jsonl
-fi
-for paper in /root/uni-finder/enzyme/"${target_job}"/paper/*.pdf
-do
-	echo "find file ${paper}"
-	file_name="${paper##*/}"
-	name=${file_name%.*}
-	key_word=""
-	key_word=$(grep "${name}" samples.jsonl)
-        if [[ ${key_word} == "" ]]
-	then
-		echo "add ${name} to jsonl"
-		sed 's|target_mark|'"${name}"'|g' sample_file | sed 's|target_Job|'"${target_job}"'|g' >> samples.jsonl
-	else
-		echo "${name}: was already in the jsonl"
-	fi
-done
diff --git a/evals/registry/data/00_scipaper_enzyme_activate_compound/sample_file b/evals/registry/data/00_scipaper_enzyme_activate_compound/sample_file
deleted file mode 100644
index 95ce86b217..0000000000
--- a/evals/registry/data/00_scipaper_enzyme_activate_compound/sample_file
+++ /dev/null
@@ -1 +0,0 @@
-{"file_name": "../uni-finder/enzyme/target_Job/paper/target_mark.pdf", "file_link": "https://dp-filetrans-bj.oss-cn-beijing.aliyuncs.com/changjunhan/target_mark.pdf", "answerfile_name": "../uni-finder/enzyme/target_Job/answer/target_mark.csv", "answerfile_link": "https://dp-filetrans-bj.oss-cn-beijing.aliyuncs.com/changjunhan/target_mark.csv", "compare_fields": ["Activating Compound", "Comment", "Organism"], "index": "Activating Compound"}
diff --git a/evals/registry/data/00_scipaper_enzyme_inhibitor/auto_add.sh b/evals/registry/data/00_scipaper_enzyme_inhibitor/auto_add.sh
deleted file mode 100644
index f699a14a86..0000000000
--- a/evals/registry/data/00_scipaper_enzyme_inhibitor/auto_add.sh
+++ /dev/null
@@ -1,26 +0,0 @@
-#!/bin/bash
-target_job=$1
-if [[ ${target_job} == "" ]]
-then
-	echo ">>> Error: target_job is not define"
-	exit
-fi
-if [[ ! -f samples.jsonl ]]
-then
-	touch samples.jsonl
-fi
-for paper in /root/uni-finder/enzyme/"${target_job}"/paper/*.pdf
-do
-	echo "find file ${paper}"
-	file_name="${paper##*/}"
-	name=${file_name%.*}
-	key_word=""
-	key_word=$(grep "${name}" samples.jsonl)
-        if [[ ${key_word} == "" ]]
-	then
-		echo "add ${name} to jsonl"
-		sed 's|target_mark|'"${name}"'|g' sample_file | sed 's|target_Job|'"${target_job}"'|g' >> samples.jsonl
-	else
-		echo "${name}: was already in the jsonl"
-	fi
-done
diff --git a/evals/registry/data/00_scipaper_enzyme_inhibitor/sample_file b/evals/registry/data/00_scipaper_enzyme_inhibitor/sample_file
deleted file mode 100644
index 57bad47af5..0000000000
--- a/evals/registry/data/00_scipaper_enzyme_inhibitor/sample_file
+++ /dev/null
@@ -1 +0,0 @@
-{"file_name": "../uni-finder/enzyme/target_Job/paper/target_mark.pdf", "file_link": "https://dp-filetrans-bj.oss-cn-beijing.aliyuncs.com/changjunhan/target_mark.pdf", "answerfile_name": "../uni-finder/enzyme/target_Job/answer/target_mark.csv", "answerfile_link": "https://dp-filetrans-bj.oss-cn-beijing.aliyuncs.com/changjunhan/target_mark.csv", "compare_fields": ["Inhibitors", "Comment", "Organism"], "index": "Inhibitors"}
diff --git a/evals/registry/data/00_scipaper_enzyme_km/auto_add.sh b/evals/registry/data/00_scipaper_enzyme_km/auto_add.sh
deleted file mode 100644
index f699a14a86..0000000000
--- a/evals/registry/data/00_scipaper_enzyme_km/auto_add.sh
+++ /dev/null
@@ -1,26 +0,0 @@
-#!/bin/bash
-target_job=$1
-if [[ ${target_job} == "" ]]
-then
-	echo ">>> Error: target_job is not define"
-	exit
-fi
-if [[ ! -f samples.jsonl ]]
-then
-	touch samples.jsonl
-fi
-for paper in /root/uni-finder/enzyme/"${target_job}"/paper/*.pdf
-do
-	echo "find file ${paper}"
-	file_name="${paper##*/}"
-	name=${file_name%.*}
-	key_word=""
-	key_word=$(grep "${name}" samples.jsonl)
-        if [[ ${key_word} == "" ]]
-	then
-		echo "add ${name} to jsonl"
-		sed 's|target_mark|'"${name}"'|g' sample_file | sed 's|target_Job|'"${target_job}"'|g' >> samples.jsonl
-	else
-		echo "${name}: was already in the jsonl"
-	fi
-done
diff --git a/evals/registry/data/00_scipaper_enzyme_km/sample_file b/evals/registry/data/00_scipaper_enzyme_km/sample_file
deleted file mode 100644
index a218a4803b..0000000000
--- a/evals/registry/data/00_scipaper_enzyme_km/sample_file
+++ /dev/null
@@ -1 +0,0 @@
-{"file_name": "../uni-finder/enzyme/target_Job/paper/target_mark.pdf", "file_link": "https://dp-filetrans-bj.oss-cn-beijing.aliyuncs.com/changjunhan/target_mark.pdf", "answerfile_name": "../uni-finder/enzyme/target_Job/answer/target_mark.csv", "answerfile_link": "https://dp-filetrans-bj.oss-cn-beijing.aliyuncs.com/changjunhan/target_mark.csv", "compare_fields": ["Substrate", "SMILES", "Km value", "Km vmax", "organism"], "index": "Substrate"}
diff --git a/evals/registry/data/00_scipaper_enzyme_km/samples.jsonl b/evals/registry/data/00_scipaper_enzyme_km/samples.jsonl
deleted file mode 100644
index d699617478..0000000000
--- a/evals/registry/data/00_scipaper_enzyme_km/samples.jsonl
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:d526411b82df30527d64c8d35afe4a09152d6669637fd876242f4ae0539c447e
-size 510
diff --git a/evals/registry/data/00_scipaper_enzyme_localization/auto_add.sh b/evals/registry/data/00_scipaper_enzyme_localization/auto_add.sh
deleted file mode 100644
index f699a14a86..0000000000
--- a/evals/registry/data/00_scipaper_enzyme_localization/auto_add.sh
+++ /dev/null
@@ -1,26 +0,0 @@
-#!/bin/bash
-target_job=$1
-if [[ ${target_job} == "" ]]
-then
-	echo ">>> Error: target_job is not define"
-	exit
-fi
-if [[ ! -f samples.jsonl ]]
-then
-	touch samples.jsonl
-fi
-for paper in /root/uni-finder/enzyme/"${target_job}"/paper/*.pdf
-do
-	echo "find file ${paper}"
-	file_name="${paper##*/}"
-	name=${file_name%.*}
-	key_word=""
-	key_word=$(grep "${name}" samples.jsonl)
-        if [[ ${key_word} == "" ]]
-	then
-		echo "add ${name} to jsonl"
-		sed 's|target_mark|'"${name}"'|g' sample_file | sed 's|target_Job|'"${target_job}"'|g' >> samples.jsonl
-	else
-		echo "${name}: was already in the jsonl"
-	fi
-done
diff --git a/evals/registry/data/00_scipaper_enzyme_localization/sample_file b/evals/registry/data/00_scipaper_enzyme_localization/sample_file
deleted file mode 100644
index ec5ce35204..0000000000
--- a/evals/registry/data/00_scipaper_enzyme_localization/sample_file
+++ /dev/null
@@ -1 +0,0 @@
-{"file_name": "../uni-finder/enzyme/target_Job/paper/target_mark.pdf", "file_link": "https://dp-filetrans-bj.oss-cn-beijing.aliyuncs.com/changjunhan/target_mark.pdf", "answerfile_name": "../uni-finder/enzyme/target_Job/answer/target_mark.csv", "answerfile_link": "https://dp-filetrans-bj.oss-cn-beijing.aliyuncs.com/changjunhan/target_mark.csv", "compare_fields": [ "Localization", "Organism"], "index":"Localization"}
diff --git a/evals/registry/data/00_scipaper_enzyme_substrate/samples.jsonl b/evals/registry/data/00_scipaper_enzyme_substrate/samples.jsonl
new file mode 100644
index 0000000000..5cf918e3d3
--- /dev/null
+++ b/evals/registry/data/00_scipaper_enzyme_substrate/samples.jsonl
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6316846852a855013f98ee678e945582013c1269fcad311c8e933859ade77c68
+size 1919
diff --git a/evals/registry/eval_sets/chemistry_enzyme.yaml b/evals/registry/eval_sets/chemistry_enzyme.yaml
new file mode 100644
index 0000000000..7a9b3525df
--- /dev/null
+++ b/evals/registry/eval_sets/chemistry_enzyme.yaml
@@ -0,0 +1,6 @@
+chemistry_enzyme:
+  evals:
+    - scipaper_enzyme_substrate
+    - scipaper_enzyme_activate_compound
+    - scipaper_enzyme_inhibitor
+    - scipaper_enzyme_localization
\ No newline at end of file
diff --git a/evals/registry/evals/00_scipaper_enzyme_km.yaml b/evals/registry/evals/00_scipaper_enzyme_substrate.yaml
similarity index 85%
rename from evals/registry/evals/00_scipaper_enzyme_km.yaml
rename to evals/registry/evals/00_scipaper_enzyme_substrate.yaml
index 9e5d4d0734..b266b07e05 100644
--- a/evals/registry/evals/00_scipaper_enzyme_km.yaml
+++ b/evals/registry/evals/00_scipaper_enzyme_substrate.yaml
@@ -1,11 +1,11 @@
-scipaper_enzyme_km:
-  id: scipaper_enzyme_km.val.csv
+scipaper_enzyme_substrate:
+  id: scipaper_enzyme_substrate.val.csv
   metrics: [accuracy]
 
-scipaper_enzyme_km.val.csv:
+scipaper_enzyme_substrate.val.csv:
   class: evals.elsuite.rag_table_extract:TableExtract
   args:
-    samples_jsonl: 00_scipaper_enzyme_km/samples.jsonl
+    samples_jsonl: 00_scipaper_enzyme_substrate/samples.jsonl
     instructions: |
       Please give a complete list of SMILES structures, Km values, Vmax values, target info (protein or cell line), and organism of all substrates in the paper. Usually the substrates' tags are numbers or IUPAC names.
       1. Output in csv format, write units not in header but in the value like "10.5 µM". Quote the value if it has comma! For example: