Hi,
I’m getting an error at step 3 (checkm2) when running the pipeline.
Do you have any idea what might be causing it, and how to fix it?
Best wishes,
Thorsten
[ 2025-12-20 05:32:16,183 ] - --> Start to Run CheckM2.
/root/metaGEM/envs/CompleteBin/lib/python3.9/site-packages/checkm2/../sklearn/utils/fixes.py:25: UserWarning: pkg_resources is deprecated as an API. See https://setuptools.pypa.io/en/latest/pkg_resources.html. The pkg_resources package is slated for removal as early as 2025-11-30. Refrain from using this package or pin to Setuptools<81.
from pkg_resources import parse_version # type: ignore
2025-12-20 05:32:17.638461: I tensorflow/tsl/cuda/cudart_stub.cc:28] Could not find cuda drivers on your machine, GPU will not be used.
2025-12-20 05:32:17.811599: I tensorflow/tsl/cuda/cudart_stub.cc:28] Could not find cuda drivers on your machine, GPU will not be used.
2025-12-20 05:32:17.813101: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
To enable the following instructions: AVX2 FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.
2025-12-20 05:32:19.926127: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT
[12/20/2025 05:32:22 AM] INFO: Running CheckM2 version 1.0.2
[12/20/2025 05:32:22 AM] INFO: Custom database path provided for predict run. Checking database at /data/thorsten/thorsten2/software/completebin/CompeleBin/CompleteBin-DB/checkm/checkm2_db.dmnd...
[12/20/2025 05:32:26 AM] INFO: Running quality prediction workflow with 43 threads.
[12/20/2025 05:32:27 AM] INFO: Calling genes in 5 bins with 43 threads:
[12/20/2025 05:32:40 AM] INFO: Calculating metadata for 5 bins with 43 threads:
[12/20/2025 05:32:42 AM] INFO: Annotating input genomes with DIAMOND using 43 threads
[12/20/2025 05:33:14 AM] INFO: Processing DIAMOND output
[12/20/2025 05:33:14 AM] INFO: Predicting completeness and contamination using ML models.
Traceback (most recent call last):
File "/root/metaGEM/envs/CompleteBin/bin/checkm2", line 7, in
sys.exit(main())
File "/root/metaGEM/envs/CompleteBin/lib/python3.9/site-packages/checkm2/cli.py", line 208, in main
predictor.prediction_wf(args.genes, mode, args.dbg_cos, args.dbg_vectors, args.stdout,
File "/root/metaGEM/envs/CompleteBin/lib/python3.9/site-packages/checkm2/predictQuality.py", line 227, in prediction_wf
final_comp, final_cont, model_chosen, csm_array = postProcessor.calculate_general_specific_ratio(
File "/root/metaGEM/envs/CompleteBin/lib/python3.9/site-packages/checkm2/modelPostprocessing.py", line 110, in calculate_general_specific_ratio
comp_results = pd.DataFrame({'General': general_comp,
File "/root/metaGEM/envs/CompleteBin/lib/python3.9/site-packages/pandas/core/frame.py", line 637, in init
mgr = dict_to_mgr(data, index, columns, dtype=dtype, copy=copy, typ=manager)
File "/root/metaGEM/envs/CompleteBin/lib/python3.9/site-packages/pandas/core/internals/construction.py", line 502, in dict_to_mgr
return arrays_to_mgr(arrays, columns, index, dtype=dtype, typ=typ, consolidate=copy)
File "/root/metaGEM/envs/CompleteBin/lib/python3.9/site-packages/pandas/core/internals/construction.py", line 125, in arrays_to_mgr
arrays = _homogenize(arrays, index, dtype)
File "/root/metaGEM/envs/CompleteBin/lib/python3.9/site-packages/pandas/core/internals/construction.py", line 625, in _homogenize
val = sanitize_array(
File "/root/metaGEM/envs/CompleteBin/lib/python3.9/site-packages/pandas/core/construction.py", line 588, in sanitize_array
data = list(data)
File "/root/metaGEM/envs/CompleteBin/lib/python3.9/site-packages/checkm2/../scipy/sparse/_base.py", line 260, in iter
yield self[r]
TypeError: 'coo_matrix' object is not subscriptable
[ 2025-12-20 05:33:21,721 ] - --> Start to Reuse the CheckM2's Tmp Files.
[ 2025-12-20 05:33:21,967 ] - --> Use utf-8 to write.
[ 2025-12-20 05:33:30,351 ] - --> Start to Run CheckM2 Resume.
/root/metaGEM/envs/CompleteBin/lib/python3.9/site-packages/checkm2/../sklearn/utils/fixes.py:25: UserWarning: pkg_resources is deprecated as an API. See https://setuptools.pypa.io/en/latest/pkg_resources.html. The pkg_resources package is slated for removal as early as 2025-11-30. Refrain from using this package or pin to Setuptools<81.
from pkg_resources import parse_version # type: ignore
2025-12-20 05:33:31.491356: I tensorflow/tsl/cuda/cudart_stub.cc:28] Could not find cuda drivers on your machine, GPU will not be used.
2025-12-20 05:33:31.538061: I tensorflow/tsl/cuda/cudart_stub.cc:28] Could not find cuda drivers on your machine, GPU will not be used.
2025-12-20 05:33:31.538579: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
To enable the following instructions: AVX2 FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.
2025-12-20 05:33:32.302663: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT
[12/20/2025 05:33:33 AM] INFO: Running CheckM2 version 1.0.2
[12/20/2025 05:33:33 AM] INFO: Custom database path provided for predict run. Checking database at /data/thorsten/thorsten2/software/completebin/CompeleBin/CompleteBin-DB/checkm/checkm2_db.dmnd...
[12/20/2025 05:33:37 AM] INFO: Running quality prediction workflow with 43 threads.
[12/20/2025 05:33:38 AM] INFO: Re-using protein files from output directory: /data/thorsten/thorsten2/software/completebin/CompeleBin/tmp2/selected_bins_checkm2_flspp/protein_files
[12/20/2025 05:33:38 AM] INFO: Calculating metadata for 1414 bins with 43 threads:
[12/20/2025 05:33:42 AM] INFO: Reusing DIAMOND output from output directory: /data/thorsten/thorsten2/software/completebin/CompeleBin/tmp2/selected_bins_checkm2_flspp/diamond_output
[12/20/2025 05:33:42 AM] INFO: Processing DIAMOND output
[12/20/2025 05:33:44 AM] INFO: Predicting completeness and contamination using ML models.
Traceback (most recent call last):
File "/root/metaGEM/envs/CompleteBin/bin/checkm2", line 7, in
sys.exit(main())
File "/root/metaGEM/envs/CompleteBin/lib/python3.9/site-packages/checkm2/cli.py", line 208, in main
predictor.prediction_wf(args.genes, mode, args.dbg_cos, args.dbg_vectors, args.stdout,
File "/root/metaGEM/envs/CompleteBin/lib/python3.9/site-packages/checkm2/predictQuality.py", line 227, in prediction_wf
final_comp, final_cont, model_chosen, csm_array = postProcessor.calculate_general_specific_ratio(
File "/root/metaGEM/envs/CompleteBin/lib/python3.9/site-packages/checkm2/modelPostprocessing.py", line 110, in calculate_general_specific_ratio
comp_results = pd.DataFrame({'General': general_comp,
File "/root/metaGEM/envs/CompleteBin/lib/python3.9/site-packages/pandas/core/frame.py", line 637, in init
mgr = dict_to_mgr(data, index, columns, dtype=dtype, copy=copy, typ=manager)
File "/root/metaGEM/envs/CompleteBin/lib/python3.9/site-packages/pandas/core/internals/construction.py", line 502, in dict_to_mgr
return arrays_to_mgr(arrays, columns, index, dtype=dtype, typ=typ, consolidate=copy)
File "/root/metaGEM/envs/CompleteBin/lib/python3.9/site-packages/pandas/core/internals/construction.py", line 125, in arrays_to_mgr
arrays = _homogenize(arrays, index, dtype)
File "/root/metaGEM/envs/CompleteBin/lib/python3.9/site-packages/pandas/core/internals/construction.py", line 625, in _homogenize
val = sanitize_array(
File "/root/metaGEM/envs/CompleteBin/lib/python3.9/site-packages/pandas/core/construction.py", line 588, in sanitize_array
data = list(data)
File "/root/metaGEM/envs/CompleteBin/lib/python3.9/site-packages/checkm2/../scipy/sparse/_base.py", line 260, in iter
yield self[r]
TypeError: 'coo_matrix' object is not subscriptable
[2025-12-20T05:33:52Z INFO bird_tool_utils::clap_utils] galah version 0.4.1
[2025-12-20T05:33:52Z INFO bird_tool_utils::external_command_checker] Found fastANI version 1.34
[2025-12-20T05:33:52Z WARN galah::cluster_argument_parsing] Since CheckM input is missing, genomes are not being ordered by quality. Instead the order of their input is being used
[2025-12-20T05:33:52Z INFO galah::cluster_argument_parsing] Clustering 1414 genomes ..
[2025-12-20T05:33:52Z INFO galah::clusterer] Preclustering with skani and clustering with skani
[2025-12-20T05:33:52Z INFO galah::clusterer] Preclustering and clustering methods are the same, so reusing ANI values
[2025-12-20T05:33:52Z INFO galah::skani] Calculating ANI from skani sketches ..
[2025-12-20T05:33:53Z INFO galah::clusterer] Preclustering ..
[2025-12-20T05:33:53Z INFO galah::clusterer] Found 32 preclusters. The largest contained 187 genomes
[2025-12-20T05:33:53Z INFO galah::clusterer] Finding representative genomes and assigning all genomes to these ..
[2025-12-20T05:33:53Z INFO galah::cluster_argument_parsing] Found 46 genome clusters
[2025-12-20T05:33:54Z INFO galah::cluster_argument_parsing] Finished printing genome clusters
[ 2025-12-20 05:33:54,051 ] - --> Start to Process Galah Results.
Traceback (most recent call last):
File "/root/metaGEM/envs/CompleteBin/bin/completebin", line 7, in
sys.exit(main())
File "/root/metaGEM/envs/CompleteBin/lib/python3.9/site-packages/CompleteBin/cli.py", line 131, in main
binning_with_all_steps(
File "/root/metaGEM/envs/CompleteBin/lib/python3.9/site-packages/CompleteBin/Binning_steps.py", line 457, in binning_with_all_steps
process_galah(
File "/root/metaGEM/envs/CompleteBin/lib/python3.9/site-packages/CompleteBin/Dereplication/galah_utils.py", line 141, in process_galah
process_galah_result(
File "/root/metaGEM/envs/CompleteBin/lib/python3.9/site-packages/CompleteBin/Dereplication/galah_utils.py", line 60, in process_galah_result
checkm2_meta_info = readCheckm2Res(checkm_quality_path, bin_suffix)[0]
File "/root/metaGEM/envs/CompleteBin/lib/python3.9/site-packages/CompleteBin/IO.py", line 72, in readCheckm2Res
with open(file_path, "r", encoding="utf-8") as rh:
FileNotFoundError: [Errno 2] No such file or directory: '/data/thorsten/thorsten2/software/completebin/CompeleBin/tmp2/selected_bins_checkm2_flspp/quality_report.tsv'
slurmstepd-node0: error: _try_parse: JSON parsing error 76 bytes: boolean expected
Hi,
I’m getting an error at step 3 (checkm2) when running the pipeline.
Do you have any idea what might be causing it, and how to fix it?
Best wishes,
Thorsten
[ 2025-12-20 05:32:16,183 ] - --> Start to Run CheckM2.
/root/metaGEM/envs/CompleteBin/lib/python3.9/site-packages/checkm2/../sklearn/utils/fixes.py:25: UserWarning: pkg_resources is deprecated as an API. See https://setuptools.pypa.io/en/latest/pkg_resources.html. The pkg_resources package is slated for removal as early as 2025-11-30. Refrain from using this package or pin to Setuptools<81.
from pkg_resources import parse_version # type: ignore
2025-12-20 05:32:17.638461: I tensorflow/tsl/cuda/cudart_stub.cc:28] Could not find cuda drivers on your machine, GPU will not be used.
2025-12-20 05:32:17.811599: I tensorflow/tsl/cuda/cudart_stub.cc:28] Could not find cuda drivers on your machine, GPU will not be used.
2025-12-20 05:32:17.813101: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
To enable the following instructions: AVX2 FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.
2025-12-20 05:32:19.926127: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT
[12/20/2025 05:32:22 AM] INFO: Running CheckM2 version 1.0.2
[12/20/2025 05:32:22 AM] INFO: Custom database path provided for predict run. Checking database at /data/thorsten/thorsten2/software/completebin/CompeleBin/CompleteBin-DB/checkm/checkm2_db.dmnd...
[12/20/2025 05:32:26 AM] INFO: Running quality prediction workflow with 43 threads.
[12/20/2025 05:32:27 AM] INFO: Calling genes in 5 bins with 43 threads:
[12/20/2025 05:32:40 AM] INFO: Calculating metadata for 5 bins with 43 threads:
[12/20/2025 05:32:42 AM] INFO: Annotating input genomes with DIAMOND using 43 threads
[12/20/2025 05:33:14 AM] INFO: Processing DIAMOND output
[12/20/2025 05:33:14 AM] INFO: Predicting completeness and contamination using ML models.
Traceback (most recent call last):
File "/root/metaGEM/envs/CompleteBin/bin/checkm2", line 7, in
sys.exit(main())
File "/root/metaGEM/envs/CompleteBin/lib/python3.9/site-packages/checkm2/cli.py", line 208, in main
predictor.prediction_wf(args.genes, mode, args.dbg_cos, args.dbg_vectors, args.stdout,
File "/root/metaGEM/envs/CompleteBin/lib/python3.9/site-packages/checkm2/predictQuality.py", line 227, in prediction_wf
final_comp, final_cont, model_chosen, csm_array = postProcessor.calculate_general_specific_ratio(
File "/root/metaGEM/envs/CompleteBin/lib/python3.9/site-packages/checkm2/modelPostprocessing.py", line 110, in calculate_general_specific_ratio
comp_results = pd.DataFrame({'General': general_comp,
File "/root/metaGEM/envs/CompleteBin/lib/python3.9/site-packages/pandas/core/frame.py", line 637, in init
mgr = dict_to_mgr(data, index, columns, dtype=dtype, copy=copy, typ=manager)
File "/root/metaGEM/envs/CompleteBin/lib/python3.9/site-packages/pandas/core/internals/construction.py", line 502, in dict_to_mgr
return arrays_to_mgr(arrays, columns, index, dtype=dtype, typ=typ, consolidate=copy)
File "/root/metaGEM/envs/CompleteBin/lib/python3.9/site-packages/pandas/core/internals/construction.py", line 125, in arrays_to_mgr
arrays = _homogenize(arrays, index, dtype)
File "/root/metaGEM/envs/CompleteBin/lib/python3.9/site-packages/pandas/core/internals/construction.py", line 625, in _homogenize
val = sanitize_array(
File "/root/metaGEM/envs/CompleteBin/lib/python3.9/site-packages/pandas/core/construction.py", line 588, in sanitize_array
data = list(data)
File "/root/metaGEM/envs/CompleteBin/lib/python3.9/site-packages/checkm2/../scipy/sparse/_base.py", line 260, in iter
yield self[r]
TypeError: 'coo_matrix' object is not subscriptable
[ 2025-12-20 05:33:21,721 ] - --> Start to Reuse the CheckM2's Tmp Files.
[ 2025-12-20 05:33:21,967 ] - --> Use utf-8 to write.
[ 2025-12-20 05:33:30,351 ] - --> Start to Run CheckM2 Resume.
/root/metaGEM/envs/CompleteBin/lib/python3.9/site-packages/checkm2/../sklearn/utils/fixes.py:25: UserWarning: pkg_resources is deprecated as an API. See https://setuptools.pypa.io/en/latest/pkg_resources.html. The pkg_resources package is slated for removal as early as 2025-11-30. Refrain from using this package or pin to Setuptools<81.
from pkg_resources import parse_version # type: ignore
2025-12-20 05:33:31.491356: I tensorflow/tsl/cuda/cudart_stub.cc:28] Could not find cuda drivers on your machine, GPU will not be used.
2025-12-20 05:33:31.538061: I tensorflow/tsl/cuda/cudart_stub.cc:28] Could not find cuda drivers on your machine, GPU will not be used.
2025-12-20 05:33:31.538579: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
To enable the following instructions: AVX2 FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.
2025-12-20 05:33:32.302663: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT
[12/20/2025 05:33:33 AM] INFO: Running CheckM2 version 1.0.2
[12/20/2025 05:33:33 AM] INFO: Custom database path provided for predict run. Checking database at /data/thorsten/thorsten2/software/completebin/CompeleBin/CompleteBin-DB/checkm/checkm2_db.dmnd...
[12/20/2025 05:33:37 AM] INFO: Running quality prediction workflow with 43 threads.
[12/20/2025 05:33:38 AM] INFO: Re-using protein files from output directory: /data/thorsten/thorsten2/software/completebin/CompeleBin/tmp2/selected_bins_checkm2_flspp/protein_files
[12/20/2025 05:33:38 AM] INFO: Calculating metadata for 1414 bins with 43 threads:
[12/20/2025 05:33:42 AM] INFO: Reusing DIAMOND output from output directory: /data/thorsten/thorsten2/software/completebin/CompeleBin/tmp2/selected_bins_checkm2_flspp/diamond_output
[12/20/2025 05:33:42 AM] INFO: Processing DIAMOND output
[12/20/2025 05:33:44 AM] INFO: Predicting completeness and contamination using ML models.
Traceback (most recent call last):
File "/root/metaGEM/envs/CompleteBin/bin/checkm2", line 7, in
sys.exit(main())
File "/root/metaGEM/envs/CompleteBin/lib/python3.9/site-packages/checkm2/cli.py", line 208, in main
predictor.prediction_wf(args.genes, mode, args.dbg_cos, args.dbg_vectors, args.stdout,
File "/root/metaGEM/envs/CompleteBin/lib/python3.9/site-packages/checkm2/predictQuality.py", line 227, in prediction_wf
final_comp, final_cont, model_chosen, csm_array = postProcessor.calculate_general_specific_ratio(
File "/root/metaGEM/envs/CompleteBin/lib/python3.9/site-packages/checkm2/modelPostprocessing.py", line 110, in calculate_general_specific_ratio
comp_results = pd.DataFrame({'General': general_comp,
File "/root/metaGEM/envs/CompleteBin/lib/python3.9/site-packages/pandas/core/frame.py", line 637, in init
mgr = dict_to_mgr(data, index, columns, dtype=dtype, copy=copy, typ=manager)
File "/root/metaGEM/envs/CompleteBin/lib/python3.9/site-packages/pandas/core/internals/construction.py", line 502, in dict_to_mgr
return arrays_to_mgr(arrays, columns, index, dtype=dtype, typ=typ, consolidate=copy)
File "/root/metaGEM/envs/CompleteBin/lib/python3.9/site-packages/pandas/core/internals/construction.py", line 125, in arrays_to_mgr
arrays = _homogenize(arrays, index, dtype)
File "/root/metaGEM/envs/CompleteBin/lib/python3.9/site-packages/pandas/core/internals/construction.py", line 625, in _homogenize
val = sanitize_array(
File "/root/metaGEM/envs/CompleteBin/lib/python3.9/site-packages/pandas/core/construction.py", line 588, in sanitize_array
data = list(data)
File "/root/metaGEM/envs/CompleteBin/lib/python3.9/site-packages/checkm2/../scipy/sparse/_base.py", line 260, in iter
yield self[r]
TypeError: 'coo_matrix' object is not subscriptable
[2025-12-20T05:33:52Z INFO bird_tool_utils::clap_utils] galah version 0.4.1
[2025-12-20T05:33:52Z INFO bird_tool_utils::external_command_checker] Found fastANI version 1.34
[2025-12-20T05:33:52Z WARN galah::cluster_argument_parsing] Since CheckM input is missing, genomes are not being ordered by quality. Instead the order of their input is being used
[2025-12-20T05:33:52Z INFO galah::cluster_argument_parsing] Clustering 1414 genomes ..
[2025-12-20T05:33:52Z INFO galah::clusterer] Preclustering with skani and clustering with skani
[2025-12-20T05:33:52Z INFO galah::clusterer] Preclustering and clustering methods are the same, so reusing ANI values
[2025-12-20T05:33:52Z INFO galah::skani] Calculating ANI from skani sketches ..
[2025-12-20T05:33:53Z INFO galah::clusterer] Preclustering ..
[2025-12-20T05:33:53Z INFO galah::clusterer] Found 32 preclusters. The largest contained 187 genomes
[2025-12-20T05:33:53Z INFO galah::clusterer] Finding representative genomes and assigning all genomes to these ..
[2025-12-20T05:33:53Z INFO galah::cluster_argument_parsing] Found 46 genome clusters
[2025-12-20T05:33:54Z INFO galah::cluster_argument_parsing] Finished printing genome clusters
[ 2025-12-20 05:33:54,051 ] - --> Start to Process Galah Results.
Traceback (most recent call last):
File "/root/metaGEM/envs/CompleteBin/bin/completebin", line 7, in
sys.exit(main())
File "/root/metaGEM/envs/CompleteBin/lib/python3.9/site-packages/CompleteBin/cli.py", line 131, in main
binning_with_all_steps(
File "/root/metaGEM/envs/CompleteBin/lib/python3.9/site-packages/CompleteBin/Binning_steps.py", line 457, in binning_with_all_steps
process_galah(
File "/root/metaGEM/envs/CompleteBin/lib/python3.9/site-packages/CompleteBin/Dereplication/galah_utils.py", line 141, in process_galah
process_galah_result(
File "/root/metaGEM/envs/CompleteBin/lib/python3.9/site-packages/CompleteBin/Dereplication/galah_utils.py", line 60, in process_galah_result
checkm2_meta_info = readCheckm2Res(checkm_quality_path, bin_suffix)[0]
File "/root/metaGEM/envs/CompleteBin/lib/python3.9/site-packages/CompleteBin/IO.py", line 72, in readCheckm2Res
with open(file_path, "r", encoding="utf-8") as rh:
FileNotFoundError: [Errno 2] No such file or directory: '/data/thorsten/thorsten2/software/completebin/CompeleBin/tmp2/selected_bins_checkm2_flspp/quality_report.tsv'
slurmstepd-node0: error: _try_parse: JSON parsing error 76 bytes: boolean expected