Semibin

* Fix bug when atomicwrite on the network file system (97)
* support .cram format input (104)
* Support using depth file from Metabat2 (103)
* Remove torch version restriction (and test on Python 3.10)
* Better output message when no bins are produced
* More flexible specification of prebuilt models (case insensitive,
normalize - and _)
* Support CRAM input (104)
* Better output message when no bins are produced
* Remove torch version restriction (and test on Python 3.10)
* Support filesystems that do allow you to call fsync on directories (97)

* Fix coverage parsing when value is not an integer (103)
* Fix multi_easy_bin with taxonomy file given on the command line

* Fix issue 93 more thoroughly (see 101)

* Fix edge case when calling prodigal with more threads than contigs (93)

* More balanced file split when calling prodigal in parallel
* Fix bug when long stretches of Ns are present (87)
* Better error messages (90 & 91)

* Improve `check_install` command by printing out paths and correctly
handling optionality of FragGeneScan/prodigal
* Reuse markers.hmmout to make the training from several samples faster
* Add option `--tmpdir` to set temporary directory
* Substitute FragGeneScan with Prodigal (FragGeneScan can still be used
with `--orf-finder` parameter)
* Add 'concatenate_fasta' command to combine fasta files for multi-sample binning