diff --git a/evals/registry/data/00_scipaper_enzyme_activate_compound/samples.jsonl b/evals/registry/data/00_scipaper_enzyme_activate_compound/samples.jsonl deleted file mode 100644 index 488ee911ff..0000000000 --- a/evals/registry/data/00_scipaper_enzyme_activate_compound/samples.jsonl +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:cfbe6bb20ea161238ab3d5e3404d9df76514d88c7ed9fe528d2984d0d9fb7d07 -size 538 diff --git a/evals/registry/data/00_scipaper_enzyme_inhibitor/samples.jsonl b/evals/registry/data/00_scipaper_enzyme_inhibitor/samples.jsonl deleted file mode 100644 index 116a945850..0000000000 --- a/evals/registry/data/00_scipaper_enzyme_inhibitor/samples.jsonl +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:49193f70b4942b3ad8aaac0497da4b37b6de40ebde79edb2ec3df6bfc0972924 -size 1444 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 100755 index 0000000000..8d6e2ce091 --- /dev/null +++ b/evals/registry/data/00_scipaper_enzyme_km/samples.jsonl @@ -0,0 +1,14 @@ +{"file_name": "../uni-finder/enzyme/km/paper/10.1007_s00425-014-2102-6.pdf", "file_link": "https://dp-filetrans-bj.oss-cn-beijing.aliyuncs.com/changjunhan/10.1007_s00425-014-2102-6.pdf", "answerfile_name": "../uni-finder/enzyme/km/answer/10.1007_s00425-014-2102-6.csv", "answerfile_link": "https://dp-filetrans-bj.oss-cn-beijing.aliyuncs.com/changjunhan/10.1007_s00425-014-2102-6.csv", "compare_fields": ["Substrate", "Comment", "Organism", "Km Value (mM)"], "index": "Substrate"} +{"file_name": "../uni-finder/enzyme/km/paper/10.1007_s10725-019-00528-9.pdf", "file_link": "https://dp-filetrans-bj.oss-cn-beijing.aliyuncs.com/changjunhan/10.1007_s10725-019-00528-9.pdf", "answerfile_name": "../uni-finder/enzyme/km/answer/10.1007_s10725-019-00528-9.csv", "answerfile_link": "https://dp-filetrans-bj.oss-cn-beijing.aliyuncs.com/changjunhan/10.1007_s10725-019-00528-9.csv", "compare_fields": ["Substrate", "Comment", "Organism", "Km Value (mM)"], "index": "Substrate"} +{"file_name": "../uni-finder/enzyme/km/paper/10.1016_j.bbrep.2016.11.003.pdf", "file_link": "https://dp-filetrans-bj.oss-cn-beijing.aliyuncs.com/changjunhan/10.1016_j.bbrep.2016.11.003.pdf", "answerfile_name": "../uni-finder/enzyme/km/answer/10.1016_j.bbrep.2016.11.003.csv", "answerfile_link": "https://dp-filetrans-bj.oss-cn-beijing.aliyuncs.com/changjunhan/10.1016_j.bbrep.2016.11.003.csv", "compare_fields": ["Substrate", "Comment", "Organism", "Km Value (mM)"], "index": "Substrate"} +{"file_name": "../uni-finder/enzyme/km/paper/10.1016_s0005-2728__97__00090-x.pdf", "file_link": "https://dp-filetrans-bj.oss-cn-beijing.aliyuncs.com/changjunhan/10.1016_s0005-2728__97__00090-x.pdf", "answerfile_name": "../uni-finder/enzyme/km/answer/10.1016_s0005-2728__97__00090-x.csv", "answerfile_link": "https://dp-filetrans-bj.oss-cn-beijing.aliyuncs.com/changjunhan/10.1016_s0005-2728__97__00090-x.csv", "compare_fields": ["Substrate", "Comment", "Organism", "Km Value (mM)"], "index": "Substrate"} +{"file_name": "../uni-finder/enzyme/km/paper/10.1016_s0021-9258__18__96277-0.pdf", "file_link": "https://dp-filetrans-bj.oss-cn-beijing.aliyuncs.com/changjunhan/10.1016_s0021-9258__18__96277-0.pdf", "answerfile_name": "../uni-finder/enzyme/km/answer/10.1016_s0021-9258__18__96277-0.csv", "answerfile_link": "https://dp-filetrans-bj.oss-cn-beijing.aliyuncs.com/changjunhan/10.1016_s0021-9258__18__96277-0.csv", "compare_fields": ["Substrate", "Comment", "Organism", "Km Value (mM)"], "index": "Substrate"} +{"file_name": "../uni-finder/enzyme/km/paper/10.1016_s0021-9258__18__96427-6.pdf", "file_link": "https://dp-filetrans-bj.oss-cn-beijing.aliyuncs.com/changjunhan/10.1016_s0021-9258__18__96427-6.pdf", "answerfile_name": "../uni-finder/enzyme/km/answer/10.1016_s0021-9258__18__96427-6.csv", "answerfile_link": "https://dp-filetrans-bj.oss-cn-beijing.aliyuncs.com/changjunhan/10.1016_s0021-9258__18__96427-6.csv", "compare_fields": ["Substrate", "Comment", "Organism", "Km Value (mM)"], "index": "Substrate"} +{"file_name": "../uni-finder/enzyme/km/paper/10.1016_S0076-6879__75__41082-5.pdf", "file_link": "https://dp-filetrans-bj.oss-cn-beijing.aliyuncs.com/changjunhan/10.1016_S0076-6879__75__41082-5.pdf", "answerfile_name": "../uni-finder/enzyme/km/answer/10.1016_S0076-6879__75__41082-5.csv", "answerfile_link": "https://dp-filetrans-bj.oss-cn-beijing.aliyuncs.com/changjunhan/10.1016_S0076-6879__75__41082-5.csv", "compare_fields": ["Substrate", "Comment", "Organism", "Km Value (mM)"], "index": "Substrate"} +{"file_name": "../uni-finder/enzyme/km/paper/10.1016_s0141-8130__01__00188-x.pdf", "file_link": "https://dp-filetrans-bj.oss-cn-beijing.aliyuncs.com/changjunhan/10.1016_s0141-8130__01__00188-x.pdf", "answerfile_name": "../uni-finder/enzyme/km/answer/10.1016_s0141-8130__01__00188-x.csv", "answerfile_link": "https://dp-filetrans-bj.oss-cn-beijing.aliyuncs.com/changjunhan/10.1016_s0141-8130__01__00188-x.csv", "compare_fields": ["Substrate", "Comment", "Organism", "Km Value (mM)"], "index": "Substrate"} +{"file_name": "../uni-finder/enzyme/km/paper/10.1021_acs.biochem.6b00536.pdf", "file_link": "https://dp-filetrans-bj.oss-cn-beijing.aliyuncs.com/changjunhan/10.1021_acs.biochem.6b00536.pdf", "answerfile_name": "../uni-finder/enzyme/km/answer/10.1021_acs.biochem.6b00536.csv", "answerfile_link": "https://dp-filetrans-bj.oss-cn-beijing.aliyuncs.com/changjunhan/10.1021_acs.biochem.6b00536.csv", "compare_fields": ["Substrate", "Comment", "Organism", "Km Value (mM)"], "index": "Substrate"} +{"file_name": "../uni-finder/enzyme/km/paper/10.1080_09168451.2020.1751582.pdf", "file_link": "https://dp-filetrans-bj.oss-cn-beijing.aliyuncs.com/changjunhan/10.1080_09168451.2020.1751582.pdf", "answerfile_name": "../uni-finder/enzyme/km/answer/10.1080_09168451.2020.1751582.csv", "answerfile_link": "https://dp-filetrans-bj.oss-cn-beijing.aliyuncs.com/changjunhan/10.1080_09168451.2020.1751582.csv", "compare_fields": ["Substrate", "Comment", "Organism", "Km Value (mM)"], "index": "Substrate"} +{"file_name": "../uni-finder/enzyme/km/paper/10.1080_09168451.2020.1799749.pdf", "file_link": "https://dp-filetrans-bj.oss-cn-beijing.aliyuncs.com/changjunhan/10.1080_09168451.2020.1799749.pdf", "answerfile_name": "../uni-finder/enzyme/km/answer/10.1080_09168451.2020.1799749.csv", "answerfile_link": "https://dp-filetrans-bj.oss-cn-beijing.aliyuncs.com/changjunhan/10.1080_09168451.2020.1799749.csv", "compare_fields": ["Substrate", "Comment", "Organism", "Km Value (mM)"], "index": "Substrate"} +{"file_name": "../uni-finder/enzyme/km/paper/10.1104_pp.19.01225.pdf", "file_link": "https://dp-filetrans-bj.oss-cn-beijing.aliyuncs.com/changjunhan/10.1104_pp.19.01225.pdf", "answerfile_name": "../uni-finder/enzyme/km/answer/10.1104_pp.19.01225.csv", "answerfile_link": "https://dp-filetrans-bj.oss-cn-beijing.aliyuncs.com/changjunhan/10.1104_pp.19.01225.csv", "compare_fields": ["Substrate", "Comment", "Organism", "Km Value (mM)"], "index": "Substrate"} +{"file_name": "../uni-finder/enzyme/km/paper/10.1139_b07-081.pdf", "file_link": "https://dp-filetrans-bj.oss-cn-beijing.aliyuncs.com/changjunhan/10.1139_b07-081.pdf", "answerfile_name": "../uni-finder/enzyme/km/answer/10.1139_b07-081.csv", "answerfile_link": "https://dp-filetrans-bj.oss-cn-beijing.aliyuncs.com/changjunhan/10.1139_b07-081.csv", "compare_fields": ["Substrate", "Comment", "Organism", "Km Value (mM)"], "index": "Substrate"} +{"file_name": "../uni-finder/enzyme/km/paper/j.1432-1033.1986.tb09548.x.pdf", "file_link": "https://dp-filetrans-bj.oss-cn-beijing.aliyuncs.com/changjunhan/j.1432-1033.1986.tb09548.x.pdf", "answerfile_name": "../uni-finder/enzyme/km/answer/j.1432-1033.1986.tb09548.x.csv", "answerfile_link": "https://dp-filetrans-bj.oss-cn-beijing.aliyuncs.com/changjunhan/j.1432-1033.1986.tb09548.x.csv", "compare_fields": ["Substrate", "Comment", "Organism", "Km Value (mM)"], "index": "Substrate"} diff --git a/evals/registry/data/00_scipaper_enzyme_localization/samples.jsonl b/evals/registry/data/00_scipaper_enzyme_localization/samples.jsonl deleted file mode 100644 index ecf84e1650..0000000000 --- a/evals/registry/data/00_scipaper_enzyme_localization/samples.jsonl +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:2909201b52e0c8f3e71ee569a65a72e4dfbdede7dde2d427c04e3e43185a86ca -size 467 diff --git a/evals/registry/data/00_scipaper_enzyme_substrate/samples.jsonl b/evals/registry/data/00_scipaper_enzyme_substrate/samples.jsonl old mode 100644 new mode 100755 index 5cf918e3d3..ef5f199679 --- a/evals/registry/data/00_scipaper_enzyme_substrate/samples.jsonl +++ b/evals/registry/data/00_scipaper_enzyme_substrate/samples.jsonl @@ -1,3 +1,14 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:6316846852a855013f98ee678e945582013c1269fcad311c8e933859ade77c68 -size 1919 +{"file_name": "../uni-finder/enzyme/substrate/paper/s_10.1007_s00425-014-2102-6.pdf", "file_link": "https://dp-filetrans-bj.oss-cn-beijing.aliyuncs.com/changjunhan/s_10.1007_s00425-014-2102-6.pdf", "answerfile_name": "../uni-finder/enzyme/substrate/answer/s_10.1007_s00425-014-2102-6.csv", "answerfile_link": "https://dp-filetrans-bj.oss-cn-beijing.aliyuncs.com/changjunhan/s_10.1007_s00425-014-2102-6.csv", "compare_fields": ["Substrate", "Comment", "Organism", "Products", "Comment (Product)"], "index": "Substrate"} +{"file_name": "../uni-finder/enzyme/substrate/paper/s_10.1007_s10725-019-00528-9.pdf", "file_link": "https://dp-filetrans-bj.oss-cn-beijing.aliyuncs.com/changjunhan/s_10.1007_s10725-019-00528-9.pdf", "answerfile_name": "../uni-finder/enzyme/substrate/answer/s_10.1007_s10725-019-00528-9.csv", "answerfile_link": "https://dp-filetrans-bj.oss-cn-beijing.aliyuncs.com/changjunhan/s_10.1007_s10725-019-00528-9.csv", "compare_fields": ["Substrate", "Comment", "Organism", "Products", "Comment (Product)"], "index": "Substrate"} +{"file_name": "../uni-finder/enzyme/substrate/paper/s_10.1007_s11103-006-0040-9.pdf", "file_link": "https://dp-filetrans-bj.oss-cn-beijing.aliyuncs.com/changjunhan/s_10.1007_s11103-006-0040-9.pdf", "answerfile_name": "../uni-finder/enzyme/substrate/answer/s_10.1007_s11103-006-0040-9.csv", "answerfile_link": "https://dp-filetrans-bj.oss-cn-beijing.aliyuncs.com/changjunhan/s_10.1007_s11103-006-0040-9.csv", "compare_fields": ["Substrate", "Comment", "Organism", "Products", "Comment (Product)"], "index": "Substrate"} +{"file_name": "../uni-finder/enzyme/substrate/paper/s_10.1016_j.bbrep.2016.11.003.pdf", "file_link": "https://dp-filetrans-bj.oss-cn-beijing.aliyuncs.com/changjunhan/s_10.1016_j.bbrep.2016.11.003.pdf", "answerfile_name": "../uni-finder/enzyme/substrate/answer/s_10.1016_j.bbrep.2016.11.003.csv", "answerfile_link": "https://dp-filetrans-bj.oss-cn-beijing.aliyuncs.com/changjunhan/s_10.1016_j.bbrep.2016.11.003.csv", "compare_fields": ["Substrate", "Comment", "Organism", "Products", "Comment (Product)"], "index": "Substrate"} +{"file_name": "../uni-finder/enzyme/substrate/paper/s_10.1016_s0005-2728__97__00090-x.pdf", "file_link": "https://dp-filetrans-bj.oss-cn-beijing.aliyuncs.com/changjunhan/s_10.1016_s0005-2728__97__00090-x.pdf", "answerfile_name": "../uni-finder/enzyme/substrate/answer/s_10.1016_s0005-2728__97__00090-x.csv", "answerfile_link": "https://dp-filetrans-bj.oss-cn-beijing.aliyuncs.com/changjunhan/s_10.1016_s0005-2728__97__00090-x.csv", "compare_fields": ["Substrate", "Comment", "Organism", "Products", "Comment (Product)"], "index": "Substrate"} +{"file_name": "../uni-finder/enzyme/substrate/paper/s_10.1016_s0021-9258__18__96277-0.pdf", "file_link": "https://dp-filetrans-bj.oss-cn-beijing.aliyuncs.com/changjunhan/s_10.1016_s0021-9258__18__96277-0.pdf", "answerfile_name": "../uni-finder/enzyme/substrate/answer/s_10.1016_s0021-9258__18__96277-0.csv", "answerfile_link": "https://dp-filetrans-bj.oss-cn-beijing.aliyuncs.com/changjunhan/s_10.1016_s0021-9258__18__96277-0.csv", "compare_fields": ["Substrate", "Comment", "Organism", "Products", "Comment (Product)"], "index": "Substrate"} +{"file_name": "../uni-finder/enzyme/substrate/paper/s_10.1016_s0021-9258__18__96427-6.pdf", "file_link": "https://dp-filetrans-bj.oss-cn-beijing.aliyuncs.com/changjunhan/s_10.1016_s0021-9258__18__96427-6.pdf", "answerfile_name": "../uni-finder/enzyme/substrate/answer/s_10.1016_s0021-9258__18__96427-6.csv", "answerfile_link": "https://dp-filetrans-bj.oss-cn-beijing.aliyuncs.com/changjunhan/s_10.1016_s0021-9258__18__96427-6.csv", "compare_fields": ["Substrate", "Comment", "Organism", "Products", "Comment (Product)"], "index": "Substrate"} +{"file_name": "../uni-finder/enzyme/substrate/paper/s_10.1016_S0076-6879__75__41082-5.pdf", "file_link": "https://dp-filetrans-bj.oss-cn-beijing.aliyuncs.com/changjunhan/s_10.1016_S0076-6879__75__41082-5.pdf", "answerfile_name": "../uni-finder/enzyme/substrate/answer/s_10.1016_S0076-6879__75__41082-5.csv", "answerfile_link": "https://dp-filetrans-bj.oss-cn-beijing.aliyuncs.com/changjunhan/s_10.1016_S0076-6879__75__41082-5.csv", "compare_fields": ["Substrate", "Comment", "Organism", "Products", "Comment (Product)"], "index": "Substrate"} +{"file_name": "../uni-finder/enzyme/substrate/paper/s_10.1021_acs.biochem.6b00536.pdf", "file_link": "https://dp-filetrans-bj.oss-cn-beijing.aliyuncs.com/changjunhan/s_10.1021_acs.biochem.6b00536.pdf", "answerfile_name": "../uni-finder/enzyme/substrate/answer/s_10.1021_acs.biochem.6b00536.csv", "answerfile_link": "https://dp-filetrans-bj.oss-cn-beijing.aliyuncs.com/changjunhan/s_10.1021_acs.biochem.6b00536.csv", "compare_fields": ["Substrate", "Comment", "Organism", "Products", "Comment (Product)"], "index": "Substrate"} +{"file_name": "../uni-finder/enzyme/substrate/paper/s_10.1080_09168451.2020.1751582.pdf", "file_link": "https://dp-filetrans-bj.oss-cn-beijing.aliyuncs.com/changjunhan/s_10.1080_09168451.2020.1751582.pdf", "answerfile_name": "../uni-finder/enzyme/substrate/answer/s_10.1080_09168451.2020.1751582.csv", "answerfile_link": "https://dp-filetrans-bj.oss-cn-beijing.aliyuncs.com/changjunhan/s_10.1080_09168451.2020.1751582.csv", "compare_fields": ["Substrate", "Comment", "Organism", "Products", "Comment (Product)"], "index": "Substrate"} +{"file_name": "../uni-finder/enzyme/substrate/paper/s_10.1080_09168451.2020.1799749.pdf", "file_link": "https://dp-filetrans-bj.oss-cn-beijing.aliyuncs.com/changjunhan/s_10.1080_09168451.2020.1799749.pdf", "answerfile_name": "../uni-finder/enzyme/substrate/answer/s_10.1080_09168451.2020.1799749.csv", "answerfile_link": "https://dp-filetrans-bj.oss-cn-beijing.aliyuncs.com/changjunhan/s_10.1080_09168451.2020.1799749.csv", "compare_fields": ["Substrate", "Comment", "Organism", "Products", "Comment (Product)"], "index": "Substrate"} +{"file_name": "../uni-finder/enzyme/substrate/paper/s_10.1104_pp.19.01225.pdf", "file_link": "https://dp-filetrans-bj.oss-cn-beijing.aliyuncs.com/changjunhan/s_10.1104_pp.19.01225.pdf", "answerfile_name": "../uni-finder/enzyme/substrate/answer/s_10.1104_pp.19.01225.csv", "answerfile_link": "https://dp-filetrans-bj.oss-cn-beijing.aliyuncs.com/changjunhan/s_10.1104_pp.19.01225.csv", "compare_fields": ["Substrate", "Comment", "Organism", "Products", "Comment (Product)"], "index": "Substrate"} +{"file_name": "../uni-finder/enzyme/substrate/paper/s_10.1139_b07-081.pdf", "file_link": "https://dp-filetrans-bj.oss-cn-beijing.aliyuncs.com/changjunhan/s_10.1139_b07-081.pdf", "answerfile_name": "../uni-finder/enzyme/substrate/answer/s_10.1139_b07-081.csv", "answerfile_link": "https://dp-filetrans-bj.oss-cn-beijing.aliyuncs.com/changjunhan/s_10.1139_b07-081.csv", "compare_fields": ["Substrate", "Comment", "Organism", "Products", "Comment (Product)"], "index": "Substrate"} +{"file_name": "../uni-finder/enzyme/substrate/paper/s_j.1432-1033.1986.tb09548.x.pdf", "file_link": "https://dp-filetrans-bj.oss-cn-beijing.aliyuncs.com/changjunhan/s_j.1432-1033.1986.tb09548.x.pdf", "answerfile_name": "../uni-finder/enzyme/substrate/answer/s_j.1432-1033.1986.tb09548.x.csv", "answerfile_link": "https://dp-filetrans-bj.oss-cn-beijing.aliyuncs.com/changjunhan/s_j.1432-1033.1986.tb09548.x.csv", "compare_fields": ["Substrate", "Comment", "Organism", "Products", "Comment (Product)"], "index": "Substrate"} diff --git a/evals/registry/evals/00_scipaper_enzyme_activate_compound.yaml b/evals/registry/evals/00_scipaper_enzyme_activate_compound.yaml deleted file mode 100644 index 7241a1fe5c..0000000000 --- a/evals/registry/evals/00_scipaper_enzyme_activate_compound.yaml +++ /dev/null @@ -1,18 +0,0 @@ -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_km.yaml old mode 100644 new mode 100755 similarity index 51% rename from evals/registry/evals/00_scipaper_enzyme_inhibitor.yaml rename to evals/registry/evals/00_scipaper_enzyme_km.yaml index 3c712c4701..dbc25868d8 --- a/evals/registry/evals/00_scipaper_enzyme_inhibitor.yaml +++ b/evals/registry/evals/00_scipaper_enzyme_km.yaml @@ -1,18 +1,19 @@ -scipaper_enzyme_inhibitor: - id: scipaper_enzyme_inhibitor.val.csv +scipaper_enzyme_km: + id: scipaper_enzyme_km.val.csv metrics: [accuracy] -scipaper_enzyme_inhibitor.val.csv: +scipaper_enzyme_km.val.csv: class: evals.elsuite.rag_table_extract:TableExtract args: - samples_jsonl: 00_scipaper_enzyme_inhibitor/samples.jsonl + samples_jsonl: 00_scipaper_enzyme_km/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. + Please give a complete list of Substrate, 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 + Substrate,Comment,Organism,Km Value + ATP,"competitive inhibition of verapamil-dependent ATPase-activity",Homo sapiens, 3.5 nM + p-xylene,"20 mM Tris-HCl(pH 7.0), 5 mM MgCl2, at 25 ℃"",Bos taurus, 12 nM + D-ribose 6-phosphate, - , Homo sapiens, 120 nM ``` 2. If there are multiple tables, concat them. Don't give me reference or using "...", give me complete table! + 3. If no relevant information was found in the paper, use '-' to fill in the form in CSV. diff --git a/evals/registry/evals/00_scipaper_enzyme_localization.yaml b/evals/registry/evals/00_scipaper_enzyme_localization.yaml deleted file mode 100644 index 3c6ca4e590..0000000000 --- a/evals/registry/evals/00_scipaper_enzyme_localization.yaml +++ /dev/null @@ -1,16 +0,0 @@ -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! diff --git a/evals/registry/evals/00_scipaper_enzyme_substrate.yaml b/evals/registry/evals/00_scipaper_enzyme_substrate.yaml old mode 100644 new mode 100755 index b266b07e05..e4d29cc7af --- a/evals/registry/evals/00_scipaper_enzyme_substrate.yaml +++ b/evals/registry/evals/00_scipaper_enzyme_substrate.yaml @@ -7,13 +7,13 @@ scipaper_enzyme_substrate.val.csv: args: 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. + Please give a complete list of Substrate, Commentand Organism of all substrates, Products and Comment of Product 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+ - + Substrate,Comment,Organism,Products,"Comment (Product)" + "NADH + H+ + O2","20 mM Tris-HCl(pH 7.0)",Homo sapiens,"NAD+ + H2O", - + "D-glucose + 6-phosphate","20 mM Tris-HCl(pH 7.0), 5 mM MgCl2, at 25 ℃"",Bos taurus, - + "D-ribose 6-phosphate", - , Homo sapiens, "glycerol + phosphate", - ``` 2. If there are multiple tables, concat them. Don't give me reference or using "...", give me complete table! + 3. If no relevant information was found in the paper, use '-' to fill in the form in CSV.