stefan-insilico commited on
Commit
9e240ab
·
verified ·
1 Parent(s): 8644e33

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +7 -8
README.md CHANGED
@@ -43,7 +43,7 @@ with open('./generation-configs/meta2diff.json', 'r') as f:
43
 
44
  # prepare sample
45
  config_sample = {"inputs": config_data, "mode": "meta2diff", "parameters": {
46
- "temperature": 0.4,
47
  "top_p": 0.2,
48
  "top_k": 3550,
49
  "n_next_tokens": 50
@@ -109,8 +109,7 @@ You can use the following instructions (one or several at a time):
109
 
110
  1. disease2diff2disease - generate signature for disease
111
  2. compound2diff2compound - generate signature for compound
112
- 3. age_group2diff2age_group - generate signature for age-group
113
- 4. age_individ2diff2age_individ - generate signature based on age value
114
 
115
 
116
  ### Other meta-data (`inputs.` in config)
@@ -164,20 +163,20 @@ Here we asked model to generate signature for Human, male, in tissue - whole blo
164
 
165
  _Example 2_
166
 
167
- You want to generate signature for healthy Human, male, 40 years, in tissue - whole blood.
168
  ```json
169
  {
170
  "inputs": {
171
- "instruction": "disease2diff2disease",
172
  "tissue": ["whole blood"],
173
- "age": 40,
174
  "cell": "",
175
  "efo": "",
176
  "datatype": "",
177
  "drug": "",
178
  "dose": "",
179
  "time": "",
180
- "case": "",
181
  "control": "",
182
  "dataset_type": "expression",
183
  "gender": "m",
@@ -196,7 +195,7 @@ You want to generate signature for healthy Human, male, 40 years, in tissue - wh
196
 
197
  ```
198
  Note, here we used ```disease2diff2disease``` instruction, but we expected to generate signatures for healthy human, that's why we'd set ```efo``` to empty string "".
199
- Alternatively, we can add one more instruction to example 2 - ```"instruction": ["disease2diff2disease", "age_individ2diff2age_individ"]```
200
 
201
  ---
202
 
 
43
 
44
  # prepare sample
45
  config_sample = {"inputs": config_data, "mode": "meta2diff", "parameters": {
46
+ "temperature": 0.8,
47
  "top_p": 0.2,
48
  "top_k": 3550,
49
  "n_next_tokens": 50
 
109
 
110
  1. disease2diff2disease - generate signature for disease
111
  2. compound2diff2compound - generate signature for compound
112
+ 3. age_group2diff2age_group - generate signature for age group / predict age group based on signature
 
113
 
114
 
115
  ### Other meta-data (`inputs.` in config)
 
163
 
164
  _Example 2_
165
 
166
+ You want to generate signature for healthy Human, male, 40-50 years, in tissue - whole blood.
167
  ```json
168
  {
169
  "inputs": {
170
+ "instruction": ["disease2diff2disease", "age_group2diff2age_group"],
171
  "tissue": ["whole blood"],
172
+ "age": "",
173
  "cell": "",
174
  "efo": "",
175
  "datatype": "",
176
  "drug": "",
177
  "dose": "",
178
  "time": "",
179
+ "case": "40.0-50.0",
180
  "control": "",
181
  "dataset_type": "expression",
182
  "gender": "m",
 
195
 
196
  ```
197
  Note, here we used ```disease2diff2disease``` instruction, but we expected to generate signatures for healthy human, that's why we'd set ```efo``` to empty string "".
198
+ Alternatively, we can add one more instruction to example 2 - ```"instruction": ["disease2diff2disease", "age_group2diff2age_group"]```
199
 
200
  ---
201