35 lines (28 with data), 11.7 kB

€•-Œdocutils.nodes”Œdocument”“”)”}”(Œ	rawsource”Œ”Œchildren”]”hŒsection”“”)”}”(hhh]”(hŒtitle”“”)”}”(hŒFeatures of DeepPurpose”h]”hŒText”“”ŒFeatures of DeepPurpose”…””}”(hhŒparent”hh
hŒsource”NŒline”NubaŒ
attributes”}”(Œids”]”Œclasses”]”Œnames”]”Œdupnames”]”Œbackrefs”]”uŒtagname”hhhh
hhŒT/Users/futianfan/Downloads/spring2020/DeepPurpose/docs/source/notes/introduction.rst”hKubhŒ	paragraph”“”)”}”(hXí
DeepPurpose is a Deep Learning Based Drug Repurposing and Virtual Screening Toolkit (using PyTorch).
It allows very easy usage (only one line of code!) for non-computational domain researchers to be able to obtain a list of potential drugs using deep learning while facilitating deep learning method research in this topic by providing a flexible framework (less than 10 lines of codes!) and baselines.
The Github repository is located `here <https://github.com/kexinhuang12345/DeepPurpose>`_.”h]”(hX´
DeepPurpose is a Deep Learning Based Drug Repurposing and Virtual Screening Toolkit (using PyTorch).
It allows very easy usage (only one line of code!) for non-computational domain researchers to be able to obtain a list of potential drugs using deep learning while facilitating deep learning method research in this topic by providing a flexible framework (less than 10 lines of codes!) and baselines.
The Github repository is located ”…””}”(hX´
DeepPurpose is a Deep Learning Based Drug Repurposing and Virtual Screening Toolkit (using PyTorch).
It allows very easy usage (only one line of code!) for non-computational domain researchers to be able to obtain a list of potential drugs using deep learning while facilitating deep learning method research in this topic by providing a flexible framework (less than 10 lines of codes!) and baselines.
The Github repository is located ”hh-h
hhNhNubhŒ	reference”“”)”}”(hŒ8`here <https://github.com/kexinhuang12345/DeepPurpose>`_”h]”hŒhere”…””}”(hŒhere”hh8ubah}”(h]”h!]”h#]”h%]”h']”Œname”h@Œrefuri”Œ.https://github.com/kexinhuang12345/DeepPurpose”uh)h6hh-ubhŒtarget”“”)”}”(hŒ1 <https://github.com/kexinhuang12345/DeepPurpose>”h]”h}”(h]”Œhere”ah!]”h#]”Œhere”ah%]”h']”Œrefuri”hIuh)hJŒ
referenced”K
hh-ubhŒ
.”…””}”(hŒ
.”hh-h
hhNhNubeh}”(h]”h!]”h#]”h%]”h']”uh)h+hh*hKhhh
hubh
)”}”(hhh]”(h)”}”(hŒFeatures”h]”hŒFeatures”…””}”(hhjhhhh
hhNhNubah}”(h]”h!]”h#]”h%]”h']”uh)hhheh
hhh*hK	ubhŒbullet_list”“”)”}”(hhh]”(hŒ	list_item”“”)”}”(hX
For non-computational researchers, ONE line of code from raw data to output drug repurposing/virtual screening result, aiming to allow wet-lab biochemists to leverage the power of deep learning. The result is ensembled from five pretrained deep learning models!
”h]”h,)”}”(hX
For non-computational researchers, ONE line of code from raw data to output drug repurposing/virtual screening result, aiming to allow wet-lab biochemists to leverage the power of deep learning. The result is ensembled from five pretrained deep learning models!”h]”hX
For non-computational researchers, ONE line of code from raw data to output drug repurposing/virtual screening result, aiming to allow wet-lab biochemists to leverage the power of deep learning. The result is ensembled from five pretrained deep learning models!”…””}”(hhƒhhubah}”(h]”h!]”h#]”h%]”h']”uh)h+hh*hKhh}ubah}”(h]”h!]”h#]”h%]”h']”uh)h{hhxh
hhh*hNubh|)”}”(hX°
For computational researchers, 15+ powerful encodings for drugs and proteins, ranging from deep neural network on classic cheminformatics fingerprints, CNN, transformers to message passing graph neural network, with 50+ combined models! Most of the combinations of the encodings are not yet in existing works. All of these under 10 lines but with lots of flexibility! Switching encoding is as simple as changing the encoding names!
”h]”h,)”}”(hXŻ
For computational researchers, 15+ powerful encodings for drugs and proteins, ranging from deep neural network on classic cheminformatics fingerprints, CNN, transformers to message passing graph neural network, with 50+ combined models! Most of the combinations of the encodings are not yet in existing works. All of these under 10 lines but with lots of flexibility! Switching encoding is as simple as changing the encoding names!”h]”hXŻ
For computational researchers, 15+ powerful encodings for drugs and proteins, ranging from deep neural network on classic cheminformatics fingerprints, CNN, transformers to message passing graph neural network, with 50+ combined models! Most of the combinations of the encodings are not yet in existing works. All of these under 10 lines but with lots of flexibility! Switching encoding is as simple as changing the encoding names!”…””}”(hh›hh™ubah}”(h]”h!]”h#]”h%]”h']”uh)h+hh*hK
hh•ubah}”(h]”h!]”h#]”h%]”h']”uh)h{hhxh
hhh*hNubh|)”}”(hXęRealistic and user-friendly design:

* automatic identification to do drug target binding affinity (regression) or drug target interaction prediction (binary) task.
* support cold target, cold drug settings for robust model evaluations and support single-target high throughput sequencing assay data setup.
* many dataset loading/downloading/unzipping scripts to ease the tedious preprocessing, including antiviral, COVID19 targets, BindingDB, DAVIS, KIBA, ...
* many pretrained checkpoints.
* easy monitoring of training process with detailed training metrics output such as test set figures (AUCs) and tables, also support early stopping.
* detailed output records such as rank list for repurposing result.
* various evaluation metrics: ROC-AUC, PR-AUC, F1 for binary task, MSE, R-squared, Concordance Index for regression task.
* label unit conversion for skewed label distribution such as Kd.
* time reference for computational expensive encoding.
* PyTorch based, support CPU, GPU, Multi-GPUs.



”h]”(h,)”}”(hŒ#Realistic and user-friendly design:”h]”hŒ#Realistic and user-friendly design:”…””}”(hhłhhąubah}”(h]”h!]”h#]”h%]”h']”uh)h+hh*hKhh­ubhw)”}”(hhh]”(h|)”}”(hŒ}automatic identification to do drug target binding affinity (regression) or drug target interaction prediction (binary) task.”h]”h,)”}”(hhÄh]”hŒ}automatic identification to do drug target binding affinity (regression) or drug target interaction prediction (binary) task.”…””}”(hhÄhhĆubah}”(h]”h!]”h#]”h%]”h']”uh)h+hh*hKhhÂubah}”(h]”h!]”h#]”h%]”h']”uh)h{hhżubh|)”}”(hŒ‹support cold target, cold drug settings for robust model evaluations and support single-target high throughput sequencing assay data setup.”h]”h,)”}”(hhŰh]”hŒ‹support cold target, cold drug settings for robust model evaluations and support single-target high throughput sequencing assay data setup.”…””}”(hhŰhhÝubah}”(h]”h!]”h#]”h%]”h']”uh)h+hh*hKhhŮubah}”(h]”h!]”h#]”h%]”h']”uh)h{hhżubh|)”}”(hŒ—many dataset loading/downloading/unzipping scripts to ease the tedious preprocessing, including antiviral, COVID19 targets, BindingDB, DAVIS, KIBA, ...”h]”h,)”}”(hhňh]”hŒ—many dataset loading/downloading/unzipping scripts to ease the tedious preprocessing, including antiviral, COVID19 targets, BindingDB, DAVIS, KIBA, …”…””}”(hhňhhôubah}”(h]”h!]”h#]”h%]”h']”uh)h+hh*hKhhđubah}”(h]”h!]”h#]”h%]”h']”uh)h{hhżubh|)”}”(hŒmany pretrained checkpoints.”h]”h,)”}”(hj	
h]”hŒmany pretrained checkpoints.”…””}”(hj	
hj
ubah}”(h]”h!]”h#]”h%]”h']”uh)h+hh*hKhj
ubah}”(h]”h!]”h#]”h%]”h']”uh)h{hhżubh|)”}”(hŒ’easy monitoring of training process with detailed training metrics output such as test set figures (AUCs) and tables, also support early stopping.”h]”h,)”}”(hj 
h]”hŒ’easy monitoring of training process with detailed training metrics output such as test set figures (AUCs) and tables, also support early stopping.”…””}”(hj 
hj"
ubah}”(h]”h!]”h#]”h%]”h']”uh)h+hh*hKhj
ubah}”(h]”h!]”h#]”h%]”h']”uh)h{hhżubh|)”}”(hŒAdetailed output records such as rank list for repurposing result.”h]”h,)”}”(hj7
h]”hŒAdetailed output records such as rank list for repurposing result.”…””}”(hj7
hj9
ubah}”(h]”h!]”h#]”h%]”h']”uh)h+hh*hKhj5
ubah}”(h]”h!]”h#]”h%]”h']”uh)h{hhżubh|)”}”(hŒwvarious evaluation metrics: ROC-AUC, PR-AUC, F1 for binary task, MSE, R-squared, Concordance Index for regression task.”h]”h,)”}”(hjN
h]”hŒwvarious evaluation metrics: ROC-AUC, PR-AUC, F1 for binary task, MSE, R-squared, Concordance Index for regression task.”…””}”(hjN
hjP
ubah}”(h]”h!]”h#]”h%]”h']”uh)h+hh*hKhjL
ubah}”(h]”h!]”h#]”h%]”h']”uh)h{hhżubh|)”}”(hŒ?label unit conversion for skewed label distribution such as Kd.”h]”h,)”}”(hje
h]”hŒ?label unit conversion for skewed label distribution such as Kd.”…””}”(hje
hjg
ubah}”(h]”h!]”h#]”h%]”h']”uh)h+hh*hKhjc
ubah}”(h]”h!]”h#]”h%]”h']”uh)h{hhżubh|)”}”(hŒ4time reference for computational expensive encoding.”h]”h,)”}”(hj|
h]”hŒ4time reference for computational expensive encoding.”…””}”(hj|
hj~
ubah}”(h]”h!]”h#]”h%]”h']”uh)h+hh*hKhjz
ubah}”(h]”h!]”h#]”h%]”h']”uh)h{hhżubh|)”}”(hŒ0PyTorch based, support CPU, GPU, Multi-GPUs.



”h]”h,)”}”(hŒ,PyTorch based, support CPU, GPU, Multi-GPUs.”h]”hŒ,PyTorch based, support CPU, GPU, Multi-GPUs.”…””}”(hj—
hj•
ubah}”(h]”h!]”h#]”h%]”h']”uh)h+hh*hKhj‘
ubah}”(h]”h!]”h#]”h%]”h']”uh)h{hhżubeh}”(h]”h!]”h#]”h%]”h']”Œbullet”Œ
*”uh)hvhh*hKhh­ubeh}”(h]”h!]”h#]”h%]”h']”uh)h{hhxh
hhNhNubeh}”(h]”h!]”h#]”h%]”h']”jŻ
j°
uh)hvhh*hKhheh
hubeh}”(h]”Œfeatures”ah!]”h#]”Œfeatures”ah%]”h']”uh)h	hhh
hhh*hK	ubeh}”(h]”Œfeatures-of-deeppurpose”ah!]”h#]”Œfeatures of deeppurpose”ah%]”h']”uh)h	hhh
hhh*hKubah}”(h]”h!]”h#]”h%]”h']”Œsource”h*uh)h
Œcurrent_source”NŒcurrent_line”NŒsettings”Œdocutils.frontend”ŒValues”“”)”}”(hNŒ	generator”NŒ	datestamp”NŒsource_link”NŒ
source_url”NŒ
toc_backlinks”Œentry”Œfootnote_backlinks”K
Œ
sectnum_xform”K
Œstrip_comments”NŒstrip_elements_with_classes”NŒ
strip_classes”NŒreport_level”KŒ
halt_level”KŒexit_status_level”KŒdebug”NŒwarning_stream”NŒ	traceback”ˆŒinput_encoding”Œ	utf-8-sig”Œinput_encoding_error_handler”Œstrict”Œoutput_encoding”Œutf-8”Œoutput_encoding_error_handler”jđ
Œerror_encoding”ŒUTF-8”Œerror_encoding_error_handler”Œbackslashreplace”Œ
language_code”Œen”Œrecord_dependencies”NŒconfig”NŒ	id_prefix”hŒauto_id_prefix”Œid”Œ
dump_settings”NŒdump_internals”NŒdump_transforms”NŒdump_pseudo_xml”NŒexpose_internals”NŒstrict_visitor”NŒ_disable_config”NŒ_source”h*Œ_destination”NŒ
_config_files”]”Œpep_references”NŒpep_base_url”Œ https://www.python.org/dev/peps/”Œpep_file_url_template”Œpep-%04d”Œrfc_references”NŒrfc_base_url”Œhttps://tools.ietf.org/html/”Œ	tab_width”KŒtrim_footnote_reference_space”‰Œfile_insertion_enabled”ˆŒraw_enabled”K
Œsyntax_highlight”Œlong”Œsmart_quotes”ˆŒsmartquotes_locales”]”Œcharacter_level_inline_markup”‰Œdoctitle_xform”‰Œ
docinfo_xform”K
Œsectsubtitle_xform”‰Œembed_stylesheet”‰Œcloak_email_addresses”ˆŒenv”NubŒreporter”NŒindirect_targets”]”Œsubstitution_defs”}”Œsubstitution_names”}”Œrefnames”}”Œrefids”}”Œnameids”}”(jĘ
jÇ
hUhRjÂ
jż
uŒ	nametypes”}”(jĘ
NhUˆjÂ
Nuh}”(jÇ
hhRhLjż
heuŒ
footnote_refs”}”Œ
citation_refs”}”Œ
autofootnotes”]”Œautofootnote_refs”]”Œsymbol_footnotes”]”Œsymbol_footnote_refs”]”Œ	footnotes”]”Œ	citations”]”Œautofootnote_start”K
Œsymbol_footnote_start”KŒ
id_counter”Œcollections”ŒCounter”“”}”…”R”Œparse_messages”]”Œtransform_messages”]”Œtransformer”NŒ
decoration”Nh
hub.