KeyError: 'X' when processing test data

[lowel0]

Hi,

I have successfully install PhageBoost 1.3.1 using the pip install PhageBoost and been unable to successfully process the NC_000907.fasta.gz test data. I get the following error output:

PhageBoost -f NC_000907.fasta.gz -o results processing: NC_000907 time after genecalls: 4.93197774887085 Traceback (most recent call last): File "/home/lowel/.local/bin/PhageBoost", line 8, in sys.exit(main()) File "/home/lowel/.local/lib/python3.9/site-packages/PhageBoost/main.py", line 219, in main df = calculate_features(genecalls) File "/home/lowel/.local/lib/python3.9/site-packages/PhageBoost/main.py", line 59, in calculatefeatures df, , _ = calc_features.df2AAandDNAfeatures(genecalls, name='header') File "/home/lowel/.local/lib/python3.9/site-packages/PhageBoost/calc_features.py", line 215, in df2AAandDNAfeatures DF, DF_AA, DF_DNA = RunAAandDNA(dna_entries, aa_entries, locations) File "/home/lowel/.local/lib/python3.9/site-packages/PhageBoost/calc_features.py", line 202, in RunAAandDNA DF_AA = RunAA(AA_entries, verbose = verbose) File "/home/lowel/.local/lib/python3.9/site-packages/PhageBoost/calc_features.py", line 178, in RunAA df_biopython = biopython_proteinanalysis(entries, scaling=scaling) File "/home/lowel/.local/lib/python3.9/site-packages/PhageBoost/calc_features.py", line 168, in biopython_proteinanalysis d = biopython_proteinanalysis_seq(seq, scaling=scaling) File "/home/lowel/.local/lib/python3.9/site-packages/PhageBoost/calc_features.py", line 33, in biopython_proteinanalysis_seq flex = np.array(res.flexibility()) File "/home/lowel/.local/lib/python3.9/site-packages/Bio/SeqUtils/ProtParam.py", line 183, in flexibility score += (flexibilities[front] + flexibilities[back]) * weights[j] KeyError: 'X'

I am using xgboost==1.1.1, but have used various permutations of python, PhageBoost and xgboost versions to no avail.

Can anybody please help with this?

Sincere regards,

[tsp-kucbd]

I cannot reproduce this error, but it seems something is happening inside Biopython. Can you show us which Biopython version you are using? import Bio print(Bio.__version__)

[WuJiaWei121]

我无法重现此错误，但 Biopython 内部似乎发生了一些事情。您能告诉我们您使用的是哪个 Biopython 版本吗？ import Bio print(Bio.__version__)

I also encountered the above problems. My bio version is 1.79. How should I solve this problem?

[lowel0]

Hi,

I cannot reproduce this error, but it seems something is happening inside Biopython. Can you show us which Biopython version you are using? import Bio print(Bio.__version__)

Thank you for your response.

My Bio version is also 1.79.

Sincere regards,

...Lowel.

[tsp-kucbd]

I reinstalled it on a new machine and could reproduce it, it seems pyrodigal has changed its internals. You can use the git hub version for now, until we create a new pip package.

[lowel0]

Hi,

Thank you for the quick investigation. I have used the "github" installation with xgboost==1.1.1 and can now succussfully process the test data.

Sincere regards,

...Lowel.

[WuJiaWei121]

Hi, I don't understand the meaning of that "I have used the "github" installation with xgboost==1.1.1". Could you help explain it?

[lowel0]

Hi, As part of the install process you use pip to install xgboost. By default the working version was not being installed, but this was corrected by using the command:

pip install xgboost==1.1.1

Sincere regards, ...Lowel.

[WuJiaWei121]

Hi Thank you for your response. I have used pip to install xgboost==1.1.1 successfully, but it still seems to make the same mistake : KeyError: 'X' when processing test data

what's more ,I tried to replace the cal_ Features.py file, but it still doesn't seem to work. Could you have some good tips?

[lowel0]

Hi,

I managed to get rid of the error by using python 3.7.0 and the development version from github rather than using the released version:

git clone https://github.com/ku-cbd/PhageBoost.git cd PhageBoost python setup.py bdist_wheel pip install . xgboost==1.1.1

The python version is important.

Sincere regards,

...Lowel.

On Tue, 23 Nov 2021 at 12:00, WuJiaWei121 @.***> wrote:

Hi Thank you for your response. I have used pip to install xgboost==1.1.1 successfully, but it still seems to make the same mistake : KeyError: 'X' when processing test data

what's more ,I tried to replace the cal_ Features.py file, but it still doesn't seem to work. Could you have some good tips?

— You are receiving this because you modified the open/close state. Reply to this email directly, view it on GitHub https://github.com/ku-cbd/PhageBoost/issues/18#issuecomment-976443918, or unsubscribe https://github.com/notifications/unsubscribe-auth/AEIYK3KJDOTKD3EX2662LUTUNN65NANCNFSM5DQS3OIQ . Triage notifications on the go with GitHub Mobile for iOS https://apps.apple.com/app/apple-store/id1477376905?ct=notification-email&mt=8&pt=524675 or Android https://play.google.com/store/apps/details?id=com.github.android&referrer=utm_campaign%3Dnotification-email%26utm_medium%3Demail%26utm_source%3Dgithub.