You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: source/web-app/poet/prompts.rst
+21-90Lines changed: 21 additions & 90 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -74,8 +74,8 @@ Creating a Context
74
74
75
75
You can create a prompt context in three ways:
76
76
77
-
Use Existing Prompt
78
-
^^^^^^^^^^^^^^^^^^^^
77
+
1. Use Existing Prompt
78
+
~~~~~~~~~~~~~~~~~~~~~~~
79
79
80
80
If you've previously uploaded prompts, you can reuse them. In the **Prompt Type** dropdown,
81
81
select an existing prompt. The sequences from that prompt will automatically load.
@@ -84,8 +84,8 @@ select an existing prompt. The sequences from that prompt will automatically loa
84
84
:alt:Use existing prompt
85
85
86
86
87
-
Create Custom Context
88
-
^^^^^^^^^^^^^^^^^^^^^^
87
+
2. Create Custom Context
88
+
~~~~~~~~~~~~~~~~~~~~~~~~~
89
89
90
90
To create a custom prompt context, in the **Prompt Type** dropdown, select **Create New Prompt** option, and select **Custom** option from the toggle buttons. You can add sequences to your custom context in two ways:
91
91
@@ -106,8 +106,8 @@ If a structure file contains multiple chains, you can select which chain to use
106
106
:alt:Manage prompts
107
107
108
108
109
-
Build From MSA
110
-
^^^^^^^^^^^^^^^
109
+
3. Build From MSA
110
+
~~~~~~~~~~~~~~~~~~
111
111
112
112
There are serveral options to create a context from an MSA:
113
113
@@ -125,17 +125,17 @@ You can further customize your analysis by:
125
125
126
126
127
127
Uploading and Saving a Sequence-Only Prompt
128
-
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
128
+
--------------------------------------------
129
129
130
130
Without a Project
131
-
^^^^^^^^^^^^^^^^^
131
+
~~~~~~~~~~~~~~~~~~
132
132
On the **Projects** page, select a PoET tool from the navigation bar. Under **Prompt Definition**, click **Select a file** and choose a `.fasta` or `.csv` file. Ensure **Prompt** is selected before uploading.
133
133
134
134
.. image:: ../../_static/tools/poet/prompt-1.png
135
135
:alt:Uploading prompt without a project
136
136
137
137
Within a Project
138
-
^^^^^^^^^^^^^^^^
138
+
~~~~~~~~~~~~~~~~~
139
139
Prompts can be uploaded via:
140
140
141
141
- **Project Page:** Click **Upload**, select **Prompt**, and upload your `.fasta` or `.csv` file.
@@ -157,102 +157,35 @@ Prompts can be uploaded via:
157
157
:alt:Create prompt from MSA page
158
158
159
159
160
-
What is a Multiple Sequence Alignment?
161
-
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
160
+
What is a Multiple Sequence Alignment (MSA)?
161
+
---------------------------------------------
162
162
163
163
Multiple sequence alignment (MSA) is a technique for biological sequence analysis. It consists of a sequence alignment of three or more biological sequences that usually have an evolutionary relationship.
164
164
165
165
Why is MSA Useful?
166
-
^^^^^^^^^^^^^^^^^^
166
+
~~~~~~~~~~~~~~~~~~~
167
167
168
168
The resulting MSA can be used to infer sequence homology and conduct phylogenetic analysis to assess the sequences’ shared evolutionary origins. Biologically sound and accurate alignments show homology and relationships, allowing for new member identification and the comparison of similar sequences. Accuracy is vital because subsequent analyses depend on the MSA results.
169
169
170
170
When building a prompt from an MSA, include sequences you want to optimize. The model learns the patterns of the proteins and predicts sequences that best fit that list. Since the model views proteins in their entirety, you cannot optimize for a specific property or activity.
171
171
172
172
173
173
Creating a Prompt Using a MSA
174
-
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
174
+
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
175
175
176
176
Without a Project
177
-
""""""""""""""""""
177
+
^^^^^^^^^^^^^^^^^^^
178
178
Navigate to any PoET tool under **Prompt Definition**. You can either input the MSA directly or upload an existing `.fa`, `.fasta`, or `.csv` file.
179
179
180
180
.. image:: ../../_static/tools/poet/prompt-6.png
181
181
:alt:Uploading MSA without a project
182
182
183
183
Within a Project
184
-
"""""""""""""""""
184
+
^^^^^^^^^^^^^^^^^^
185
185
MSAs can be uploaded via:
186
186
187
187
- **Project Page:** Click **Upload**, select **MSA**, and input or upload a `.fa`, `.fasta`, or `.csv` file.
188
188
189
-
.. image:: ../../_static/tools/poet/prompt-7.png
190
-
:alt:Uploading MSA on project page
191
-
192
-
193
-
Uploading And Saving a Sequence Only-Prompt
194
-
--------------------------------------------
195
-
196
-
Without a Project
197
-
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
198
-
On the **Projects** page, select a PoET tool from the navigation bar. Under **Prompt Definition**, click **Select a file** and choose a ``.fasta`` or ``.csv`` file. Ensure **Prompt** is selected before uploading.
199
-
200
-
.. image:: ../../_static/tools/poet/prompt-1.png
201
-
:alt:Uploading prompt without a project
202
-
203
-
Within a Project
204
-
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
205
-
Prompts can be uploaded via:
206
-
207
-
- **Project Page**: Click **Upload**, select **Prompt**, and upload your ``.fasta`` or ``.csv`` file.
208
-
.. image:: ../../_static/tools/poet/prompt-2.png
209
-
:alt:Uploading prompt from project
210
-
211
-
- **Left Sidebar**: Click the **Upload** button under the **Prompt** section and select your file.
212
-
213
-
.. image:: ../../_static/tools/poet/prompt-3.png
214
-
:alt:Uploading prompt within a project
215
-
216
-
.. image:: ../../_static/tools/poet/prompt-4.png
217
-
:alt:Uploaded prompt preview
218
-
219
-
- **From a MSA**: On an existing MSA page, click on **Create Prompt**.
220
-
221
-
.. image:: ../../_static/tools/poet/prompt-5.png
222
-
:alt:create prompt from MSA page
223
-
224
-
225
-
What is a Multiple Sequence Alignment?
226
-
--------------------------------------
227
-
228
-
Multiple sequence alignment (MSA) is a technique for biological sequence analysis. It consists of a sequence alignment of three or more biological sequences that usually have an evolutionary relationship.
229
-
230
-
Why is MSA Useful?
231
-
------------------
232
-
233
-
The resulting MSA can be used to infer sequence homology and conduct phylogenetic analysis to assess the sequences’ shared evolutionary origins. Biologically sound and accurate alignments show homology and relationships, allowing for new member identification and the comparison of similar sequences. Because subsequent analysis depends on the results of an MSA, accuracy is vital.
234
-
235
-
When building a prompt from a MSA, you should include sequences you want to optimize for. The model learns the patterns of the proteins and predicts sequences that best fit that list. Since the model views proteins in their entirety, you cannot optimize for a specific property or activity.
236
-
237
-
238
-
Creating a Prompt Using a MSA
239
-
---------------------------
240
-
241
-
Without a Project
242
-
~~~~~~~~~~~~~~~~~~~~~
243
-
244
-
Navigate to any PoET tool under **Prompt Definition**. You can either input the MSA directly or upload an existing ``.fa``, ``.fasta``, or ``.csv`` file.
245
-
246
-
247
-
.. image:: ../../_static/tools/poet/prompt-6.png
248
-
:alt:Uploading MSA without a project
249
-
250
-
Within a Project
251
-
~~~~~~~~~~~~~~~~~~~~~
252
-
MSAs can be uploaded via:
253
-
254
-
- **Project Page**: Click **Upload**, select **MSA**, and input or upload a ``.fa``, ``.fasta``, or ``.csv`` file.
255
-
256
189
.. image:: ../../_static/tools/poet/prompt-7.png
257
190
:alt:Uploading MSA on project page
258
191
@@ -267,16 +200,17 @@ MSAs can be uploaded via:
267
200
.. image:: ../../_static/tools/poet/prompt-10.png
268
201
:alt:Uploading MSA popup within a project
269
202
203
+
270
204
What is a Seed Sequence?
271
205
---------------------------
272
206
A seed sequence is a single protein sequence provided by the user to initiate a homology search. PoET does a homology search using public databases like uniprot to build an MSA from the seed sequence. PoET then creates a prompt by randomly selecting sequences from the MSA.
273
207
274
208
275
209
Creating a Prompt via Homology Search based on a Seed Sequence
Navigate to any PoET tool under **Prompt Definition**, input a seed sequence, and select **Single Sequence**.
282
216
@@ -285,7 +219,7 @@ Navigate to any PoET tool under **Prompt Definition**, input a seed sequence, an
285
219
286
220
287
221
Within a Project
288
-
~~~~~~~~~~~~~~~~~~~~~
222
+
^^^^^^^^^^^^^^^^^^
289
223
290
224
Homology search from a seed sequence can be initiated via:
291
225
@@ -308,10 +242,7 @@ Homology search from a seed sequence can be initiated via:
308
242
309
243
310
244
Prompt Sampling Parameters
311
-
--------------------------
312
-
313
-
Prompt Sampling Definitions
314
-
~~~~~~~~~~~~~~~~~~~~~~~~~~~
245
+
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
315
246
316
247
- **Sampling method**: defines the sampling strategy used for selecting prompt sequences from the homologs found by homology search, or from the provided MSA. The following strategies are available:
317
248
- **Top**: Select sequences based on the order in which they occur in the MSA
@@ -325,7 +256,7 @@ Prompt Sampling Definitions
325
256
- **Maximum total number of residues**: The maximum total number of residues in all sequences sampled from the MSA to form the prompt. For example, if this is set to 1000, sequences will be sampled from the MSA up to a maximum cumulative length of 1000 residues.
326
257
327
258
Prompt Sampling Explained
328
-
-------------------------
259
+
~~~~~~~~~~~~~~~~~~~~~~~~~~
329
260
330
261
The selection of prompt sequences from the MSA is controlled by several prompt sampling parameters.
0 commit comments