Error when running with pre-trained 90% model

[Yulong663]

Hi~ When i running with peakachu 90% models with almost 1700 Million intra-chromosomal reads, it didn't work as expected,and all error messages are below, hope for your useful reply~

———————————————— HiC version: 8 scoring matrix chr9 num candidates 0 Traceback (most recent call last): File "/media/wjn/zzp/peakachu/3dgenome/bin/peakachu", line 4, in import('pkg_resources').run_script('peakachu==1.1.4', 'peakachu') File "/media/wjn/zzp/peakachu/3dgenome/lib/python3.7/site-packages/pkg_resources/init.py", line 665, in run_script self.require(requires)[0].run_script(script_name, ns) File "/media/wjn/zzp/peakachu/3dgenome/lib/python3.7/site-packages/pkg_resources/init.py", line 1463, in run_script exec(code, namespace, namespace) File "/media/wjn/zzp/peakachu/3dgenome/lib/python3.7/site-packages/peakachu-1.1.4-py3.7.egg/EGG-INFO/scripts/peakachu", line 80, in run() File "/media/wjn/zzp/peakachu/3dgenome/lib/python3.7/site-packages/peakachu-1.1.4-py3.7.egg/EGG-INFO/scripts/peakachu", line 76, in run args.func(args) File "/media/wjn/zzp/peakachu/3dgenome/lib/python3.7/site-packages/peakachu-1.1.4-py3.7.egg/peakachu/score_genome.py", line 58, in main result, R = X.score(thre=args.minimum_prob) File "/media/wjn/zzp/peakachu/3dgenome/lib/python3.7/site-packages/peakachu-1.1.4-py3.7.egg/peakachu/scoreUtils.py", line 75, in score p, clist = self.getwindow(coords) File "/media/wjn/zzp/peakachu/3dgenome/lib/python3.7/site-packages/peakachu-1.1.4-py3.7.egg/peakachu/scoreUtils.py", line 65, in getwindow fts = np.vstack((i for i in fts)) File "<__array_function__ internals>", line 6, in vstack File "/media/wjn/zzp/peakachu/3dgenome/lib/python3.7/site-packages/numpy/core/shape_base.py", line 283, in vstack return _nx.concatenate(arrs, 0) File "<__array_function__ internals>", line 6, in concatenate ValueError: need at least one array to concatenate /media/wjn/zzp/peakachu/3dgenome/lib/python3.7/site-packages/sklearn/base.py:251: UserWarning: Trying to unpickle estimator DecisionTreeClassifier from version 0.20.3 when using version 0.20.2. This might lead to breaking code or invalid results. Use at your own risk. UserWarning) /media/wjn/zzp/peakachu/3dgenome/lib/python3.7/site-packages/sklearn/base.py:251: UserWarning: Trying to unpickle estimator RandomForestClassifier from version 0.20.3 when using version 0.20.2. This might lead to breaking code or invalid results. Use at your own risk. UserWarning) /media/wjn/zzp/peakachu/3dgenome/lib/python3.7/site-packages/peakachu-1.1.4-py3.7.egg/peakachu/scoreUtils.py:65: FutureWarning: arrays to stack must be passed as a "sequence" type such as list or tuple. Support for non-sequence iterables such as generators is deprecated as of NumPy 1.16 and will raise an error in the future. fts = np.vstack((i for i in fts)) /media/wjn/zzp/peakachu/3dgenome/lib/python3.7/site-packages/peakachu-1.1.4-py3.7.egg/peakachu/scoreUtils.py:65: FutureWarning: arrays to stack must be passed as a "sequence" type such as list or tuple. Support for non-sequence iterables such as generators is deprecated as of NumPy 1.16 and will raise an error in the future. fts = np.vstack((i for i in fts)) /media/wjn/zzp/peakachu/3dgenome/lib/python3.7/site-packages/peakachu-1.1.4-py3.7.egg/peakachu/scoreUtils.py:65: FutureWarning: arrays to stack must be passed as a "sequence" type such as list or tuple. Support for non-sequence iterables such as generators is deprecated as of NumPy 1.16 and will raise an error in the future. fts = np.vstack((i for i in fts)) /media/wjn/zzp/peakachu/3dgenome/lib/python3.7/site-packages/peakachu-1.1.4-py3.7.egg/peakachu/scoreUtils.py:65: FutureWarning: arrays to stack must be passed as a "sequence" type such as list or tuple. Support for non-sequence iterables such as generators is deprecated as of NumPy 1.16 and will raise an error in the future. fts = np.vstack((i for i in fts)) /media/wjn/zzp/peakachu/3dgenome/lib/python3.7/site-packages/peakachu-1.1.4-py3.7.egg/peakachu/scoreUtils.py:65: FutureWarning: arrays to stack must be passed as a "sequence" type such as list or tuple. Support for non-sequence iterables such as generators is deprecated as of NumPy 1.16 and will raise an error in the future. fts = np.vstack((i for i in fts)) /media/wjn/zzp/peakachu/3dgenome/lib/python3.7/site-packages/peakachu-1.1.4-py3.7.egg/peakachu/scoreUtils.py:65: FutureWarning: arrays to stack must be passed as a "sequence" type such as list or tuple. Support for non-sequence iterables such as generators is deprecated as of NumPy 1.16 and will raise an error in the future. fts = np.vstack((i for i in fts)) /media/wjn/zzp/peakachu/3dgenome/lib/python3.7/site-packages/peakachu-1.1.4-py3.7.egg/peakachu/scoreUtils.py:65: FutureWarning: arrays to stack must be passed as a "sequence" type such as list or tuple. Support for non-sequence iterables such as generators is deprecated as of NumPy 1.16 and will raise an error in the future. fts = np.vstack((i for i in fts)) /media/wjn/zzp/peakachu/3dgenome/lib/python3.7/site-packages/peakachu-1.1.4-py3.7.egg/peakachu/scoreUtils.py:65: FutureWarning: arrays to stack must be passed as a "sequence" type such as list or tuple. Support for non-sequence iterables such as generators is deprecated as of NumPy 1.16 and will raise an error in the future. fts = np.vstack((i for i in fts)) ————————————————————

Thanks in advance, Mike

[Yulong663]

Is there anyone could do me a favor :) @tariks @XiaoTaoWang

[XiaoTaoWang]

Hi, Mike, one potential reason for this error is that the KR normalization of the chromosome 9 failed during the .hic file generation. My suggestion is converting your .hic into .cool using hic2cool <https://github.com/4dn-dcic/hic2cool>_ and balancing the .cool file using cooler balance, then use this .cool file as input and run peakachu again. According to my experience, cooler balance is more stable than juicer's KR normaization.

Best,

Xiaotao

[Yulong663]

It do helps for solving the probelm. Thanks a lot ! +1