Mercurial > repos > galaxy-australia > alphafold2

comparison alphafold.xml @ 0:7ae9d78b06f5 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
"planemo upload for repository https://github.com/usegalaxy-au/galaxy-local-tools commit 7b79778448363aa8c9b14604337e81009e461bd2-dirty"
author galaxy-australia
date Fri, 28 Jan 2022 04:56:29 +0000
parents
children 6c92e000d684
comparison
equal deleted inserted replaced
-1:000000000000 0:7ae9d78b06f5
1 <tool id="alphafold" name="alphafold" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="20.01">
2 <description>Alphafold v2.0: AI-guided 3D structure prediction of proteins</description>
3 <macros>
4 <token name="@TOOL_VERSION@">2.0.0</token>
5 <token name="@VERSION_SUFFIX@">0</token>
6 </macros>
7 <edam_topics>
8 <edam_topic>topic_0082</edam_topic>
9 </edam_topics>
10 <edam_operations>
11 <edam_operation>operation_0474</edam_operation>
12 </edam_operations>
13 <requirements>
14 <container type="docker">neoformit/alphafold-galaxy@sha256:6adf7f07062b307d08c11130c39a28abc7c290b23f6c347b09c2c649c054c338</container>
15 </requirements>
16 <command detect_errors="exit_code"><![CDATA[
17 ## fasta setup ----------------------------
18 #if $fasta_or_text.input_mode == 'history':
19 cp '$fasta_or_text.fasta_file' input.fasta &&
20
21 #elif $fasta_or_text.input_mode == 'textbox':
22 echo '$fasta_or_text.fasta_text' > input.fasta &&
23 #end if
24
25 python3 '$__tool_directory__/validate_fasta.py' input.fasta &&
26
27 ## env vars -------------------------------
28 export TF_FORCE_UNIFIED_MEMORY=1 &&
29 export XLA_PYTHON_CLIENT_MEM_FRACTION=4.0 &&
30 export DATE=`date +"%Y-%m-%d"` &&
31
32 ## run alphafold -------------------------
33 ln -s /app/alphafold/alphafold alphafold &&
34 python /app/alphafold/run_alphafold.py
35 --fasta_paths alphafold.fasta
36 --output_dir output
37 --data_dir /data ## location of the alphafold databases on pulsar node --> could this maybe a env var? $ALPHAFOLD_DB --> \${ALPHAFOLD_DB:-/data}
38 --uniref90_database_path /data/uniref90/uniref90.fasta
39 --mgnify_database_path /data/mgnify/mgy_clusters_2018_12.fa
40 --pdb70_database_path /data/pdb70/pdb70
41 --template_mmcif_dir /data/pdb_mmcif/mmcif_files
42 --obsolete_pdbs_path /data/pdb_mmcif/obsolete.dat
43 --max_template_date=\$DATE
44 --bfd_database_path /data/bfd/bfd_metaclust_clu_complete_id30_c90_final_seq.sorted_opt
45 --uniclust30_database_path /data/uniclust30/uniclust30_2018_08/uniclust30_2018_08
46 &&
47
48 ## for dry run testing
49 ## cp -r '$__tool_directory__/output' . &&
50
51 ## generate extra outputs -----------------
52 ## plddts
53 python3 '$__tool_directory__/gen_extra_outputs.py' output/alphafold $output_plddts &&
54
55 ## html
56 mkdir -p '${ html.files_path }' &&
57 cp '$__tool_directory__/alphafold.html' ${html} &&
58 cp output/alphafold/ranked_*.pdb '${html.files_path}' &&
59
60 ## For some reason the working directory ends up being one level too deep!
61 mv working/* .
62 ]]></command>
63 <inputs>
64 <conditional name="fasta_or_text">
65 <param name="input_mode" type="select" label="Fasta Input" help="Single protein sequence to fold. Input can be fasta file from history, or text. Provide only 1 sequence per job.">
66 <option value="history">Use fasta from history</option>
67 <option value="textbox">Paste sequence into textbox</option>
68 </param>
69 <when value="history">
70 <param name="fasta_file" type="data" format="fasta" label="Fasta file from history" help="Select single fasta protein sequence from your history. If you wish to fold multiple proteins, submit an individual job for each protein." />
71 </when>
72 <when value="textbox">
73 <param name="fasta_text" type="text" area="true" value="" label="Paste sequence" help="Paste single protein sequence into the textbox. If you wish to fold multiple proteins, submit individual jobs for each protein." />
74 </when>
75 </conditional>
76 <param name="output_plddts" type="boolean" checked="false" label="Output per-residue confidence scores" truevalue="--plddts" falsevalue="" help="Alphafold produces a pLDDT score between 0-100 for each residue in the folded models. High scores represent high confidence in placement for the residue, while low scoring residues have lower confidence. Sections of low confidence often occur in disordered regions. " />
77 </inputs>
78 <outputs>
79 <data name="model5" format="pdb" from_work_dir="output/alphafold/ranked_4.pdb" label="${tool.name} on ${on_string}: Model 5"/>
80 <data name="model4" format="pdb" from_work_dir="output/alphafold/ranked_3.pdb" label="${tool.name} on ${on_string}: Model 4"/>
81 <data name="model3" format="pdb" from_work_dir="output/alphafold/ranked_2.pdb" label="${tool.name} on ${on_string}: Model 3"/>
82 <data name="model2" format="pdb" from_work_dir="output/alphafold/ranked_1.pdb" label="${tool.name} on ${on_string}: Model 2"/>
83 <data name="model1" format="pdb" from_work_dir="output/alphafold/ranked_0.pdb" label="${tool.name} on ${on_string}: Model 1"/>
84 <data name="confidence_scores" format="tsv" from_work_dir="output/alphafold/model_confidence_scores.tsv" label="${tool.name} on ${on_string}: Model confidence scores"/>
85 <data name="plddts" format="tsv" from_work_dir="output/alphafold/plddts.tsv" label="${tool.name} on ${on_string}: Per-residue confidence scores (plddts)">
86 <filter>(output_plddts)</filter>
87 </data>
88 <data name="html" format="html" label="${tool.name} on ${on_string}: Visualization" />
89 </outputs>
90 <tests>
91 <test expect_num_outputs="8">
92 <conditional name="fasta_or_text">
93 <param name="input_mode" value="history"/>
94 <param name="fasta_file" value="test1.fasta"/>
95 </conditional>
96 <param name="output_plddts" value="true"/>
97 <output name="plddts">
98 <assert_contents>
99 <has_n_columns n="2"/>
100 <has_n_lines n="6"/>
101 <has_size value="2900" delta="300"/>
102 </assert_contents>
103 </output>
104 <output name="confidence_scores">
105 <assert_contents>
106 <has_n_columns n="2"/>
107 <has_n_lines n="6"/>
108 <has_size value="70" delta="50"/>
109 </assert_contents>
110 </output>
111 <output name="model1">
112 <assert_contents>
113 <has_n_columns n="12"/>
114 <has_n_lines n="1517"/>
115 <has_size value="123000" delta="10000"/>
116 </assert_contents>
117 </output>
118 <output name="model2">
119 <assert_contents>
120 <has_n_columns n="12"/>
121 <has_n_lines n="1517"/>
122 <has_size value="123000" delta="10000"/>
123 </assert_contents>
124 </output>
125 <output name="model3">
126 <assert_contents>
127 <has_n_columns n="12"/>
128 <has_n_lines n="1517"/>
129 <has_size value="123000" delta="10000"/>
130 </assert_contents>
131 </output>
132 <output name="model4">
133 <assert_contents>
134 <has_n_columns n="12"/>
135 <has_n_lines n="1517"/>
136 <has_size value="123000" delta="10000"/>
137 </assert_contents>
138 </output>
139 <output name="model5">
140 <assert_contents>
141 <has_n_columns n="12"/>
142 <has_n_lines n="1517"/>
143 <has_size value="123000" delta="10000"/>
144 </assert_contents>
145 </output>
146 </test>
147 </tests>
148 <help><![CDATA[
149
150 .. class:: infomark
151
152 **What it does**
153
154 | AlphaFold v2.0: AI-guided 3D structure prediction of proteins
155 |
156
157 *What is AlphaFold?*
158
159 | AlphaFold is a program which uses neural networks to predict the tertiary (3D) structure of proteins. AlphaFold accepts an amino acid sequence (in Fasta format), then will 'fold' that sequence into a 3D model.
160 | NOTE: AlphaFold has a number of versions - this tool uses AlphaFold v2.0.
161 |
162
163 *What makes AlphaFold different?*
164
165 | The ability to use computers to predict 3D protein structures with high accuracy is desirable because it removes the time-consuming and costly process of determining structures experimentally.
166 | In-silico protein folding has been an active field of research for decades, but existing tools ran more slowly and with less reliability than AlphaFold.
167 | AlphaFold represents a leap forward by regularly predicting structures to atomic-level accuracy, even when no similar structures are known.
168 |
169
170 *Downstream analysis*
171
172 | Obtaining a protein fold is the first step in many analyses.
173 | The 3D models created by AlphaFold can be used in downstream analysis, including the following:
174 |
175
176 - Inspecting protein features
177 3D viewers (pymol, chimera, ngl, blender) can be used to inspect active sites, regulatory domains, binding sites.
178 - Molecular docking
179 3D structures can be used to predict the binding affinity of different compounds.
180 This is especially useful in screening drug candidates.
181 - Protein-protein interactions
182 Proteins associate in many biological processes, including intracellular signalling pathways and protein complex formation.
183 To predict these interactions, other programs may ingest 3D models predicted by AlphaFold. Proprietary softwares include `GOLD <https://www.ccdc.cam.ac.uk/solutions/csd-discovery/components/gold/>`_ and `SeeSAR <https://www.biosolveit.de/SeeSAR>`_, but many `free and open-source options <https://en.wikipedia.org/wiki/List_of_protein-ligand_docking_software>`_ are available such as `AutoDock <https://autodock.scripps.edu/>`_ and `SwissDock <http://www.swissdock.ch/>`_.
184
185 *Expected run times*
186
187 .. image:: https://github.com/usegalaxy-au/galaxy-local-tools/blob/1a8d3e8daa7ccc5a345ca377697735ab95ed0666/tools/alphafold/static/img/alphafold_runtime_graph.png?raw=true
188 :height: 520
189 :alt: Run time graph
190
191 |
192 | In general, we observe a quadratic relationship between sequence length and time to fold.
193 | Once your job begins, a sequence of 50aa will take approximately 1hr to complete, while a sequence of 2000aa will take about 18hrs.
194 |
195
196 **Input**
197
198 *Amino acid sequence*
199
200 | AlphaFold accepts a **single amino acid sequence** in FASTA format.
201 | You can choose to input either a file from your Galaxy history or paste a sequence into a text box.
202 | Please paste only a single sequence - we can only process a single sequence per job.
203 | Multiple sequences will return an error.
204 |
205
206 **Outputs**
207
208 *Visualization*
209
210 | An interactive 3D graphic of the best predicted molecular structures.
211 | This output can be opened in Galaxy to give a visual impression of the results, with different structural representations to choose from.
212 | Open the "Visualization" history output by clicking on the "view data" icon:
213 |
214
215 .. image:: https://github.com/usegalaxy-au/galaxy-local-tools/blob/1a8d3e8daa7ccc5a345ca377697735ab95ed0666/tools/alphafold/static/img/alphafold-visualization.png?raw=true
216 :height: 520
217 :alt: Result visualization
218
219 |
220
221 *PDB files*
222
223 | Five PDB (Protein Data Bank) files will be created for the best ranking models predicted by AlphaFold.
224 | These files describe the molecular structures and can be used for downstream analysis. e.g. *in silico* molecular docking.
225 |
226
227 *Model confidence scores (optional)*
228
229 | This optional output produces a file which describes the confidence scores for each model (based on `pLDDTs <https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3799472/>`_) which may be useful for downstream analysis.
230 | Model confidence scores are also included as a column in the default PDB output.
231 |
232
233 **External Resources**
234
235 We recommend checking out the
236 `Alphafold Protein Structure Database <https://alphafold.ebi.ac.uk/>`_,
237 which contains predicted sequences for thousands of Human proteins. See also:
238
239 - `Google Deepmind's article on AlphaFold <https://deepmind.com/blog/article/alphafold-a-solution-to-a-50-year-old-grand-challenge-in-biology>`_
240 - `AlphaFold source code on GitHub <https://github.com/deepmind/alphafold>`_
241
242 ]]></help>
243 <citations>
244 <citation type="doi">https://doi.org/10.1038/s41586-021-03819-2</citation>
245 </citations>
246 </tool>