sematyp

Name: sematyp
Author: QSong-github

132stars4forks

How to install sematyp?

qsong-github/drugclaw/sematyp

$npx -y skills add QSong-github/DrugClaw --skill sematyp

Installs into the current project.

Summary

> Drug-Disease Association Knowledge Graph from literature mining + TTD > Category: Drug-centric | Type: KG | Subcategory: Drug-Disease Associations > Access: Local files (downloaded from GitHub)

Files · 1

View on GitHub

SKILL.md

1	# 66 · SemaTyP
2
3	> Drug-Disease Association Knowledge Graph from literature mining + TTD
4	> Category: Drug-centric \| Type: KG \| Subcategory: Drug-Disease Associations
5	> Access: Local files (downloaded from GitHub)
6
7	\| Resource \| URL \|
8	\|----------\|-----\|
9	\| GitHub \| https://github.com/ShengtianSang/SemaTyP \|
10	\| Paper \| https://link.springer.com/article/10.1186/s12859-018-2167-5 \|
11
12	---
13
14	## What it provides
15
16	SemaTyP combines two data sources into a knowledge graph for drug discovery / repositioning:
17
18	- SemMedDB predications (`data/SemmedDB/predications.txt`): subject–predicate–object triples with UMLS semantic types, extracted from PubMed abstracts (full version: ~39M triples).
19	- TTD curated associations (`data/TTD/`): drug-disease and target-disease links from Therapeutic Target Database (2016), with ICD-9/ICD-10 codes.
20	- Processed associations (`data/processed/`): pre-computed drug→disease, disease→drug, disease→target mappings.
21
22	### Data schema
23
24	\| File \| Format \| Columns \|
25	\|------\|--------\|---------\|
26	\| `data/SemmedDB/predications.txt` \| TSV \| subject, object, context, predicate, subj_semtype, obj_semtype \|
27	\| `data/TTD/drug-disease_TTD2016.txt` \| TSV \| TTDDRUGID, drug_name, indication, ICD9, ICD10 \|
28	\| `data/TTD/target-disease_TTD2016.txt` \| TSV \| target_id, target_name, disease, ICD9, ICD10 \|
29	\| `data/processed/drug_disease` \| TSV \| drug, disease, ... \|
30	\| `data/processed/disease_drug` \| TSV \| disease, drug, ... \|
31	\| `data/processed/disease_targets` \| TSV \| disease, target, ... \|
32
33	---
34
35	## Setup
36
37	Data must be downloaded locally first:
38
39	```bash
40	git clone https://github.com/ShengtianSang/SemaTyP.git
41	```
42
43	Then set the data path (default points to your HiPerGator location):
44
45	```python
46	# Option 1: environment variable
47	export SEMATYP_DATA_DIR="/path/to/SemaTyP-main"
48
49	# Option 2: edit DATA_DIR in 66_SemaTyP.py directly
50	```
51
52	Note: The GitHub repo only contains a 100-line sample of `predications.txt`. The full 39M-triple file must be downloaded separately per the repo README.
53
54	---
55
56	## Quick start
57
58	```python
59	from 66_SemaTyP import query
60
61	# Single entity (drug, disease, target, or any biomedical concept)
62	results = query("aspirin")
63
64	# Multiple entities
65	results = query(["metformin", "diabetes", "CYP2D6"])
66
67	# Specific data source only
68	results = query("imatinib", fields="predications", pred_limit=10)
69	results = query("Schizophrenia", fields="ttd")
70	results = query("cancer", fields="processed")
71	```
72
73	---
74
75	## `query()` interface
76
77	```
78	query(entities, fields="all", pred_limit=50) -> list[dict]
79	```
80
81	\| Parameter \| Type \| Description \|
82	\|-----------\|------\|-------------\|
83	\| `entities` \| `str \\| list[str]` \| Entity name(s), case-insensitive \|
84	\| `fields` \| `str` \| `"all"` — everything; `"predications"` / `"ttd"` / `"processed"` \|
85	\| `pred_limit` \| `int` \| Max predication triples per entity (default 50) \|
86
87	### Return structure (`fields="all"`)
88
89	```json
90	[
91	{
92	"query": "aspirin",
93	"predications": [
94	{"subject": "aspirin", "object": "pain", "predicate": "TREATS",
95	"context": "...", "subj_type": "phsu", "obj_type": "sosy"}
96	],
97	"predication_count": 42,
98	"ttd_drug_disease": [
99	{"ttdid": "DAP000XXX", "drug": "Aspirin", "disease": "Pain",
100	"icd9": "...", "icd10": "..."}
101	],
102	"ttd_target_disease": [],
103	"processed_drug_disease": [...],
104	"processed_disease_drug": [...],
105	"processed_disease_targets": [...]
106	}
107	]
108	```
109
110	---
111
112	## Lower-level functions
113
114	\| Function \| Input \| Output \| Description \|
115	\|----------\|-------\|--------\|-------------\|
116	\| `get_predications(entity, limit=50)` \| entity name \| `list[dict]` \| SemMedDB KG triples \|
117	\| `get_ttd_drug_disease(entity)` \| drug or disease \| `list[dict]` \| TTD drug-disease associations \|
118	\| `get_ttd_target_disease(entity)` \| target or disease \| `list[dict]` \| TTD target-disease associations \|
119	\| `get_processed_drug_disease(entity)` \| entity name \| `list[dict]` \| Processed drug→disease \|
120	\| `get_processed_disease_drug(entity)` \| entity name \| `list[dict]` \| Processed disease→drug \|
121	\| `get_processed_disease_targets(entity)` \| entity name \| `list[dict]` \| Processed disease→target \|
122
123	---
124
125	## Notes
126
127	- All lookups are case-insensitive (indexed by lowercased entity names).
128	- Data is lazy-loaded: first `query()` call triggers a one-time index build (may take seconds for large predications file).
129	- UMLS semantic type codes in predications: `phsu` = pharmaceutical substance, `dsyn` = disease/syndrome, `gngm` = gene/genome, `sosy` = sign/symptom, `podg` = patient/group, etc.
130	- The GitHub sample `predications.txt` has only 100 lines; for full coverage, download the complete file per the repo README instructions.

People who liked this also viewed

6 picks

Type

find-skillsHelps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skSkillsJul 20262.6M27k
grill-meA relentless interview to sharpen a plan or design.SkillsJul 2026633k182k
vercel-react-best-practicesVercel's official collection of agent skillsSkillsJul 2026573k29k
improve-codebase-architectureScan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.SkillsJul 2026522k182k
setup-matt-pocock-skillsConfigure this repo for the engineering skills — set up its issue tracker, triage label vocabulary, and domain doc layout. Run once before first use of the other engineering skills.SkillsJul 2026454k182k
triageMove issues and external PRs through a state machine of triage roles — categorise, verify, grill if needed, and write agent-ready briefs.SkillsJul 2026424k182k

sematyp

132stars4forks

View on GitHub

How to install sematyp?

qsong-github/drugclaw/sematyp

$npx -y skills add QSong-github/DrugClaw --skill sematyp

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# 66 · SemaTyP
2
3	> Drug-Disease Association Knowledge Graph from literature mining + TTD
4	> Category: Drug-centric \| Type: KG \| Subcategory: Drug-Disease Associations
5	> Access: Local files (downloaded from GitHub)
6
7	\| Resource \| URL \|
8	\|----------\|-----\|
9	\| GitHub \| https://github.com/ShengtianSang/SemaTyP \|
10	\| Paper \| https://link.springer.com/article/10.1186/s12859-018-2167-5 \|
11
12	---
13
14	## What it provides
15
16	SemaTyP combines two data sources into a knowledge graph for drug discovery / repositioning:
17
18	- SemMedDB predications (`data/SemmedDB/predications.txt`): subject–predicate–object triples with UMLS semantic types, extracted from PubMed abstracts (full version: ~39M triples).
19	- TTD curated associations (`data/TTD/`): drug-disease and target-disease links from Therapeutic Target Database (2016), with ICD-9/ICD-10 codes.
20	- Processed associations (`data/processed/`): pre-computed drug→disease, disease→drug, disease→target mappings.
21
22	### Data schema
23
24	\| File \| Format \| Columns \|
25	\|------\|--------\|---------\|
26	\| `data/SemmedDB/predications.txt` \| TSV \| subject, object, context, predicate, subj_semtype, obj_semtype \|
27	\| `data/TTD/drug-disease_TTD2016.txt` \| TSV \| TTDDRUGID, drug_name, indication, ICD9, ICD10 \|
28	\| `data/TTD/target-disease_TTD2016.txt` \| TSV \| target_id, target_name, disease, ICD9, ICD10 \|
29	\| `data/processed/drug_disease` \| TSV \| drug, disease, ... \|
30	\| `data/processed/disease_drug` \| TSV \| disease, drug, ... \|
31	\| `data/processed/disease_targets` \| TSV \| disease, target, ... \|
32
33	---
34
35	## Setup
36
37	Data must be downloaded locally first:
38
39	```bash
40	git clone https://github.com/ShengtianSang/SemaTyP.git
41	```
42
43	Then set the data path (default points to your HiPerGator location):
44
45	```python
46	# Option 1: environment variable
47	export SEMATYP_DATA_DIR="/path/to/SemaTyP-main"
48
49	# Option 2: edit DATA_DIR in 66_SemaTyP.py directly
50	```
51
52	Note: The GitHub repo only contains a 100-line sample of `predications.txt`. The full 39M-triple file must be downloaded separately per the repo README.
53
54	---
55
56	## Quick start
57
58	```python
59	from 66_SemaTyP import query
60
61	# Single entity (drug, disease, target, or any biomedical concept)
62	results = query("aspirin")
63
64	# Multiple entities
65	results = query(["metformin", "diabetes", "CYP2D6"])
66
67	# Specific data source only
68	results = query("imatinib", fields="predications", pred_limit=10)
69	results = query("Schizophrenia", fields="ttd")
70	results = query("cancer", fields="processed")
71	```
72
73	---
74
75	## `query()` interface
76
77	```
78	query(entities, fields="all", pred_limit=50) -> list[dict]
79	```
80
81	\| Parameter \| Type \| Description \|
82	\|-----------\|------\|-------------\|
83	\| `entities` \| `str \\| list[str]` \| Entity name(s), case-insensitive \|
84	\| `fields` \| `str` \| `"all"` — everything; `"predications"` / `"ttd"` / `"processed"` \|
85	\| `pred_limit` \| `int` \| Max predication triples per entity (default 50) \|
86
87	### Return structure (`fields="all"`)
88
89	```json
90	[
91	{
92	"query": "aspirin",
93	"predications": [
94	{"subject": "aspirin", "object": "pain", "predicate": "TREATS",
95	"context": "...", "subj_type": "phsu", "obj_type": "sosy"}
96	],
97	"predication_count": 42,
98	"ttd_drug_disease": [
99	{"ttdid": "DAP000XXX", "drug": "Aspirin", "disease": "Pain",
100	"icd9": "...", "icd10": "..."}
101	],
102	"ttd_target_disease": [],
103	"processed_drug_disease": [...],
104	"processed_disease_drug": [...],
105	"processed_disease_targets": [...]
106	}
107	]
108	```
109
110	---
111
112	## Lower-level functions
113
114	\| Function \| Input \| Output \| Description \|
115	\|----------\|-------\|--------\|-------------\|
116	\| `get_predications(entity, limit=50)` \| entity name \| `list[dict]` \| SemMedDB KG triples \|
117	\| `get_ttd_drug_disease(entity)` \| drug or disease \| `list[dict]` \| TTD drug-disease associations \|
118	\| `get_ttd_target_disease(entity)` \| target or disease \| `list[dict]` \| TTD target-disease associations \|
119	\| `get_processed_drug_disease(entity)` \| entity name \| `list[dict]` \| Processed drug→disease \|
120	\| `get_processed_disease_drug(entity)` \| entity name \| `list[dict]` \| Processed disease→drug \|
121	\| `get_processed_disease_targets(entity)` \| entity name \| `list[dict]` \| Processed disease→target \|
122
123	---
124
125	## Notes
126
127	- All lookups are case-insensitive (indexed by lowercased entity names).
128	- Data is lazy-loaded: first `query()` call triggers a one-time index build (may take seconds for large predications file).
129	- UMLS semantic type codes in predications: `phsu` = pharmaceutical substance, `dsyn` = disease/syndrome, `gngm` = gene/genome, `sosy` = sign/symptom, `podg` = patient/group, etc.
130	- The GitHub sample `predications.txt` has only 100 lines; for full coverage, download the complete file per the repo README instructions.

People who liked this also viewed

6 picks

Type