Scanner Error

[Paulina-GM]

Hello,

I'm trying to use the Aizynthapp on the jupyter notebooks, using the documents provided in figshare. When I run the first cell I get the following error message:

ScannerError: while scanning for the next token found character '\t' that cannot start any token in "", line 5, column 7: full_uspto_03_05_19_unique_temp ...

I'm running this in a Linux cluster using python 3.8. If that's of any help.

Thanks in advance for your help.

[Paulina-GM]

Hi again,

Just a follow up. I was able to solve that issue by removing the tabs in the config file. but now I get the following error:

endosome/work/radiology/s187304/aizynth/aizynthfinder/aizynthfinder/context/policy/policies.py in load_from_config(self, **config) 109 files_spec = config.get("files", config.get("template-based", {})) 110 for key, policy_spec in files_spec.items(): --> 111 modelfile, templatefile = policy_spec 112 strategy = TemplateBasedExpansionStrategy( 113 key, self._config, source=modelfile, templatefile=templatefile

ValueError: too many values to unpack (expected 2)

Thanks again in advance for your help.

[SGenheden]

Hello Could you paste your config-file here? I don't understand how the tabs entered into your file, but the latest exceptions comes from a mal-formated config file. You should specify a policy using something like this

policy:
  files:
    my_policy:
      - path_to_model_file
      - path_to_template_file

[Paulina-GM]

Samuel,

Sorry I just realized I have some mistakes in the paths location,

I’m using as well the simplified version of the config file:

policy: files: my_policy:

• full_uspto_03_05_19_rollout_policy.hdf5
• full_uspto_03_05_19_unique_templates.hdf5 stock: files: zinc: zinc_stock.hdf5

And now my error is different:

OSError: No file or directory found at full_uspto_03_05_19_rollout_policy.hdf5

I do have the file in the aizynth forlder but I’ll see if there’s something else missing

Sorry for the basic questions. I’m just a chemist wanting to use machine learning but my experience is not that much.

Thanks in advance for your help

From: Samuel Genheden @.> Sent: Thursday, May 5, 2022 12:10 PM To: MolecularAI/aizynthfinder @.> Cc: Paulina Gonzalez @.>; Author @.> Subject: Re: [MolecularAI/aizynthfinder] Scanner Error (Issue #68)

EXTERNAL MAIL

Hello Could you paste your config-file here? I don't understand how the tabs entered into your file, but the latest exceptions comes from a mal-formated config file. You should specify a policy using something like this

policy:

files:

my_policy:

  - path_to_model_file

  - path_to_template_file

— Reply to this email directly, view it on GitHubhttps://github.com/MolecularAI/aizynthfinder/issues/68#issuecomment-1118845028, or unsubscribehttps://github.com/notifications/unsubscribe-auth/AOHPP76OMFIRQYX3G45L4MDVIP6E3ANCNFSM5VFLF6JA. You are receiving this because you authored the thread.Message ID: @.***> CAUTION: This email originated from outside UTSW. Please be cautious of links or attachments, and validate the sender's email address before replying.

---

UT Southwestern

Medical Center

The future of medicine, today.

[Paulina-GM]

Samuel,

Sorry for the email bombing.

The program is working now!

Thank you very much eitherway.

Have a nice rest of the evening!

Paulina

From: Samuel Genheden @.> Sent: Thursday, May 5, 2022 12:10 PM To: MolecularAI/aizynthfinder @.> Cc: Paulina Gonzalez @.>; Author @.> Subject: Re: [MolecularAI/aizynthfinder] Scanner Error (Issue #68)

EXTERNAL MAIL

Hello Could you paste your config-file here? I don't understand how the tabs entered into your file, but the latest exceptions comes from a mal-formated config file. You should specify a policy using something like this

policy:

files:

my_policy:

  - path_to_model_file

  - path_to_template_file

— Reply to this email directly, view it on GitHubhttps://github.com/MolecularAI/aizynthfinder/issues/68#issuecomment-1118845028, or unsubscribehttps://github.com/notifications/unsubscribe-auth/AOHPP76OMFIRQYX3G45L4MDVIP6E3ANCNFSM5VFLF6JA. You are receiving this because you authored the thread.Message ID: @.***> CAUTION: This email originated from outside UTSW. Please be cautious of links or attachments, and validate the sender's email address before replying.

---

UT Southwestern

Medical Center

The future of medicine, today.

[SGenheden]

Glad you could sort it out. I will close this ticket now. Do not hesitate to return with more questions, even if you think they are basic. I am glad it found its way to a chemists, and appreciate that you and other chemists are no computer specialists.

[Paulina-GM]

Samuel,

Thank you for your prompt response.

This is the config file I’m currently using

properties: iteration_limit: 100 return_first: false time_limit: 120 C: 1.4 cutoff_cumulative: 0.995 cutoff_number: 50 max_transforms: 6 policy: files: my_policy: -/path/to/keras/model/weights.hdf5 -/path/to/hdf5/templates.hdf5 filter: files: my_policy: /path/to/keras/model/weights.hdf5 reactants_count: filter_tag: stock: files: stock1: /path/to/stock1.hdf5 stock2: /path/to/stock1.hdf5

From: Samuel Genheden @.> Sent: Thursday, May 5, 2022 12:10 PM To: MolecularAI/aizynthfinder @.> Cc: Paulina Gonzalez @.>; Author @.> Subject: Re: [MolecularAI/aizynthfinder] Scanner Error (Issue #68)

EXTERNAL MAIL

Hello Could you paste your config-file here? I don't understand how the tabs entered into your file, but the latest exceptions comes from a mal-formated config file. You should specify a policy using something like this

policy:

files:

my_policy:

  - path_to_model_file

  - path_to_template_file

— Reply to this email directly, view it on GitHubhttps://github.com/MolecularAI/aizynthfinder/issues/68#issuecomment-1118845028, or unsubscribehttps://github.com/notifications/unsubscribe-auth/AOHPP76OMFIRQYX3G45L4MDVIP6E3ANCNFSM5VFLF6JA. You are receiving this because you authored the thread.Message ID: @.***> CAUTION: This email originated from outside UTSW. Please be cautious of links or attachments, and validate the sender's email address before replying.

---

UT Southwestern

Medical Center

The future of medicine, today.

[aa0929]

I was very excited to try it and the previous error is gone, but a new one appeared