Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Update/tests #27

Merged
merged 4 commits into from
Jun 19, 2024
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
The table of contents is too big for display.
Diff view
Diff view
  •  
  •  
  •  
6 changes: 0 additions & 6 deletions locidex/classes/extractor.py
Original file line number Diff line number Diff line change
Expand Up @@ -25,7 +25,6 @@ def __init__(self,df,seq_data,sseqid_col,queryid_col,qstart_col,qend_col,qlen_co
self.df = self.recursive_filter_redundant_queries(self.df, 'locus_name', sseqid_col, bitscore_col,
sort_cols, ascending_cols, overlap_threshold=1)


self.df = self.extend(self.df,sseqid_col, queryid_col, qstart_col, qend_col, sstart_col,send_col,slen_col, qlen_col, bitscore_col, overlap_threshold=overlap_thresh)
self.df = self.set_extraction_pos(self.df, sstart_col, send_col)
loci_ranges = self.group_by_locus(self.df,sseqid_col, queryid_col,qlen_col,extend_threshold_ratio)
Expand Down Expand Up @@ -413,7 +412,6 @@ def extend(self,df,seqid_col, queryid_col, qstart_col, qend_col, sstart_col,send
df = df.sort_values(sort_cols, ascending=ascending_cols).reset_index(drop=True)
queries = df[queryid_col].to_list()


#Remove incomplete hits when complete ones are present
filtered = []
for query in queries:
Expand All @@ -425,10 +423,6 @@ def extend(self,df,seqid_col, queryid_col, qstart_col, qend_col, sstart_col,send
else:
filtered.append(subset)
df = pd.concat(filtered, ignore_index=True)
trunc_records = df[df['is_complete'] == False]
if len(trunc_records) == 0:
return df

is_extended = []
five_p_ext = []
three_p_ext = []
Expand Down
2 changes: 2 additions & 0 deletions tests/test_data/genomes/G1.fasta

Large diffs are not rendered by default.

2 changes: 2 additions & 0 deletions tests/test_data/genomes/G10.fasta

Large diffs are not rendered by default.

2 changes: 2 additions & 0 deletions tests/test_data/genomes/G11.fasta

Large diffs are not rendered by default.

2 changes: 2 additions & 0 deletions tests/test_data/genomes/G12.fasta

Large diffs are not rendered by default.

2 changes: 2 additions & 0 deletions tests/test_data/genomes/G13.fasta

Large diffs are not rendered by default.

2 changes: 2 additions & 0 deletions tests/test_data/genomes/G14.fasta

Large diffs are not rendered by default.

2 changes: 2 additions & 0 deletions tests/test_data/genomes/G2.fasta

Large diffs are not rendered by default.

2 changes: 2 additions & 0 deletions tests/test_data/genomes/G3.fasta

Large diffs are not rendered by default.

2 changes: 2 additions & 0 deletions tests/test_data/genomes/G4.fasta

Large diffs are not rendered by default.

2 changes: 2 additions & 0 deletions tests/test_data/genomes/G5.fasta

Large diffs are not rendered by default.

2 changes: 2 additions & 0 deletions tests/test_data/genomes/G6.fasta

Large diffs are not rendered by default.

2 changes: 2 additions & 0 deletions tests/test_data/genomes/G7.fasta

Large diffs are not rendered by default.

2 changes: 2 additions & 0 deletions tests/test_data/genomes/G8.fasta

Large diffs are not rendered by default.

2 changes: 2 additions & 0 deletions tests/test_data/genomes/G9.fasta

Large diffs are not rendered by default.

40 changes: 40 additions & 0 deletions tests/test_data/outputs/db/blast/nucleotide/nucleotide.fasta

Large diffs are not rendered by default.

Binary file not shown.
Binary file not shown.
Binary file not shown.
22 changes: 22 additions & 0 deletions tests/test_data/outputs/db/blast/nucleotide/nucleotide.njs
Original file line number Diff line number Diff line change
@@ -0,0 +1,22 @@
{
"version": "1.2",
"dbname": "nucleotide",
"dbtype": "Nucleotide",
"db-version": 5,
"description": "locidex_db/blast/nucleotide/nucleotide.fasta",
"number-of-letters": 22641,
"number-of-sequences": 20,
"last-updated": "2024-06-06T08:43:00",
"number-of-volumes": 1,
"bytes-total": 44532,
"bytes-to-cache": 6046,
"files": [
"nucleotide.ndb",
"nucleotide.nhr",
"nucleotide.nin",
"nucleotide.not",
"nucleotide.nsq",
"nucleotide.ntf",
"nucleotide.nto"
]
}
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
40 changes: 40 additions & 0 deletions tests/test_data/outputs/db/blast/protein/protein.fasta
Original file line number Diff line number Diff line change
@@ -0,0 +1,40 @@
>0
mydppflealmitasffaifiiivvsvlllegd*
>1
mklflttaaltatltsgmgfasdtvipwatnsggtesthiaamgedvnaqhqhiihthegvcaansgtiqadeaaltsnkppvqvqpellphqg*
>2
maknrsrrlrkkmhidefqelgfsvawrfpegtseeqidktvddfindviepnklafdgsgylaweglicmqeigkcteehqaivrkwlearnleevrtselfdvwwd*
>3
lklipfyllalfsassgateinackdligtwktpadnppytvtilppveacgekcvklnveyeldvthrnalycherqegvkgqgpmviafegaygghaigtynrqlqllragvipknkkwkwitkmenywfrrvkah*
>4
mkkfdschpvflligcaqvplrssvskpvqqpsaqkeqlanangidecqslpyvpsdlaknkslsnqiadntasknsaissrifcekykqtkeqaltffqelpqymrskeveeqhmtefkkvllepgsknlsiyqtllaaherlqal*
>5
mrikpddnwrwyydeehdrmmldlangmlfrsrfsrkmltpdafcptgfcvddaalyfsfeekcrdfeltkeqraelvlnalvairylkpqmpkswhfvahgemwtpgtgdaasvwlsdtaeqvnllvvepgenaalcllaqpgvviagrtmqlgdaikimndrlkpqvhchsfsleqav*
>6
vlaftlrfiknkryfailagalviiagldsqhacsgnglpqingkalaalakqhpvvvlfrhaercdrsdntclpdstgitvngaqdaralgkafsadiqnynlyssntvraiqsatwfsagrsrravkkmmdcgsgiyssintllknsqiknivilthnhcltyivknkrgvkfdpeylnalvmyaengkllldgefvpg*
>7
mgsnyivieglegagkttardvvvetleqlgirnmiftrepggtqlaeklrslvldirsvgdevitdkaevlmfyaarvqlvetvikpalaqgvwvigdrhdlstqayqgggrgidqtmlatlrdavlgdfrpdltlyldvtpevglkrarargdldrieqesfdffnrtrarylelaaqdsrirtidatqpldavmrdiratvtkwvqeqaa*
>8
mkhikksvlvvlltshvahasivvggtrlvfdgnndessinvenkdskanlvqswlsvadpqvtnkqvfiitpplfrldagqknsirvirsgaplpadresmywlnikgipsiddnasanrveisintqikliyrppaltkstpdsqsqqlkwqtagdvitvnnptpyymnfasvtlnshevksatfvppkssasfklsstaaphgtvtwrlisdygmslephsgsf*
>9
mrillsnddgvhapgiqtlakalrefadvqvvapdrnrsgasnsltlesslrtftfdngdiavqmgtptdcvylgvnalmrprpdivvsginagpnlgddviysgtvaaamegrhlgfpalavslngyqhydtaaavtcallrglsreplrtgrilnvnvpdlplaqvkgirvtrcgsrhpadkvipqedprgntlywigppgdkydagpdtdfaavdegyvsvtplhvdltahsahdvvsdwldsvgvgtqw*
>10
vnlvktpglhaagkginvanvlkdlgidvtvggflgkdnqdgfqqlfselgianrfqvvqgrtrinvkltekdgevtnfnfpgfdvtpadwerfvndflswlgqfdmvcvsgslpagvspeaftdwmtrlrsqcpciivdtsrvelvagliaapwlvkpnrreleiwagrklpemkdvidaapalreqgiahvvislgaegalrvnasgewiakppavdventvgaggsmvggwiygllmrestehtlrlatavaalavsqsnvgitdrpqlaammarvdlqpfn*
>11
mnknkystpllmlatilagmlspmqsavngqlghwlqdgnacavisfasglvvmffiiiarketrqqfasiptlikkrkiplwnwfaglcgamvvfsegasasalgvatfqtalisalllsgllcdrfgigveekkyftpwritgalfaviatifvvspqwhstsfillailpflagllagwqpagnakvaeatgsmlvsitwnfivgfcvlgaalairialghvtiqlpdtwwmylggplgllsiglmailvrglgllmlgvastagqllgsvlidelipslgntvylvtiigtlfalvgaivttipeyraskmaqkmevse*
>12
mkgrwakyvatgvmlamlaacsskptdrgqqykdgkftqpfslvnqpdavgapinagdfaeqvdqirsasprlytnqsnvynavqnwlrsggdtrtmrqfgidawqmegtdnygnvqftgyytpvvqarhtrqgafqypiysmppkrgrlpsraqiyagalsdkyilawsnslmdnfimdvqgsgyidfgdgsplnffsyagkngwpyrsigkvlidrgevkkedmsmqairewgekhseaevrelleqnpsfvffkpqsfapvkgasavpligrasvasdrsiippgttllaevplldnngkfsgqyelrlmvaldvggaikgqhfdiyqgigpdaghragwynhygrvwvlksapgagnvfsg*
>13
lfdrydageqavlvhiyfsqdkdmedlqefeslvyyagveamqvitgsrkaphpkyfvgegkaveiaeavkatgaavvlfdhalspaqernlerlcecrvidrtglildifaqrarthegklqvelaqlrhlatrlvrgwthlerrkggigsrgpgetqleadrrllrnrivqiqsrlekvekqreqgrqsrikadvptvslvgytnagkstlfnqitearvyaadqlfatldptlrridvadvgetvladtvgfirhlpydlvaafkatlqetrqatqllhvvdaadvrvqenieavntvleeidahefptlmvmnkidmlddfepridrdeenkpirvwlsaqsgvgipqlfqalterlsgevaqhtlrllpqegrlrsrfyqlqaiekewmeedgsvspqvrmpivdwrrfckqepalieyvi*
>14
vaqrilvlgasgyigqhlvfalsqqghqvraaarrverlekhrlanvschkvdlhwpenlpallrdidtvyylvhgmgeggdfiaherqaalnvrdalrqtpvkqliflsslqapaheqsdhlrarqltadtlrdagvpvtelragiivgagsaafevmrdmvynlpiltpprwvrsrttpialenllyylvgllehpahehrileaagpqvlsyqqqferfmavsgkrrplipvpfptrwisvwflnvitsvppttakaliqglrhdlladdaalkklipqtlitfddavrrtlkeeeklvnssdwgydalafarwrpeygyfpkqagftaqtpaslsalwqvvnrlggkegyffgnilwqtraamdrlvghklakgrpshtllkpgdtvdswkviivepekqltllfgmkapglgrlsftlhdkgryreidvrawwhphgmpgliywllmipahlfifrgmarriarlaeqitek*
>15
mnkfarhflplslrvrfllatagvvlvlslaygivalvgysvsfdkttfrllrgesnlfytlakwennkicvelpenldmqsptmtviydetgkllwtqrnipwlikstqpeglktngfheietnvdatstllsedhsaqeklkevreddddaemthsvavniypattrmpqltivvvdtipielkgsymvwswfvyvlaanlllvipllwiaawwslrpidalsrevreledhhremlnpettrklislvrnlnqllkseherynkyrtsltdlthslktplavlqstlrslrnekmsvskaepvmleqisrisqqigyylhrasmrgsgvllsrelhpvaplldnlisalnkvylrkgvnismdispeisfvgeqndfvevmgnvldnackyclefveisarqtddhlhifveddgpgiahskrslvfdrgqradtlrpgqgvglavareiteqyagqiiasdsllggarmevvsgrqhptqkee*
>16
mtiqkrlleaveqkllrpidaqfaltvagnddpavtlaaallshdageghvclplsrltlteeahpllvawisetatpidwkkrllasaavscgdspaplilcgdrlylnrmwcnertvarffnevnqaiavdedqlsrildalfpptdevnwqkvaaavaltrrisvisggpgtgktttvakllaaliqmadgercrirlaaptgkaaarlteslgaalrqlpltdaqkkripedastlhrllgaqpgsqrlrhhagnplhldvlvvdeasmidlpmmsrlidalpphgrviflgdrdqlasveagavlgdicayvnagftaerarqlsrltgsaipagagtqaaslrdslcllqksyrfgsdsgigklaaaincgdrsaiqavfqqgfsdiekrtlqssddyagmldealagygrylrllhekaapeailqafneyqllcalregpfgvrglndrieqamvqqrkiqrhphsrwyegrpvmiarndsalglfngdigialdrgqglrvwfvmpdgtiksvqpsrlpehdttwamtvhksqgsefdhaalilpsqrspvvtrelvytavtrarrrlslyaderilagaivtrterrsglatlfdevsrig*
>17
mqevamssqeaskmlrtyniawwgnnyydvnelghisvcpdpdvpearvdlaklvkareaqgqrlpalfcfpqilqhrlrsinaafkraresygyngdyflvypikvnqhrrvieslihsgeplgleagskaelmavlahagmtrsvivcngykdreyirlaligekmghkvylviekmseiaivleeaerlnvvprlgvrarlasqgsgkwqssggekskfglaatqvlqlvetlrdagrldslqllhfhlgsqmanirdiatgvresarfyvelhklgvniqcfdvggglgvdyegtrsqsdcsvnyglneyanniiwaigdaceehglphptvitesgravtahhtvlvsniigverneytdptapaedapralqnlwetwqemhkpgtrrslrewlhdsqmdlhdihigyssgafslqerawaeqlylsmchevqkqldpqnrahrpiidelqermadkmyvnfslfqsmpdawgidqlfpvlplegldqvperravllditcdsdgaidhyidgdgiattmpmpeydpenppmlgffmvgayqeilgnmhnlfgdteavdvfvfpdgsvevelsdegdtvadmlqyvqldpktllthfrdqvkqtdlddalqqqfleefeaglygytylede*
>18
mnslpqrstdfelttsqdgfalswqqrlilrhsaenpclwigagvadidmfrgnfsikdklnekialteatvselpdgwlvqfsrgatisatlrisadeagrltldlqnddlhhnriwlrlaanpddhiygcgeqfsyfdlrgkpfplwtseqgvgrnktsyvtwqadckenaggdyyltffpqptfvstqkyychvdnscymnfdfsapeyhelalwedkttlrfecadtyiallekltallgrqpelpdwvydgvtlgiqggtevcqqkldnmrnagvkvygiwaqdwsgirmtsfgkrvmwnwkwnsdnypqldsrikqwkeegvqflsyinpyvasdkdlcaeaarhgylakdatggdylvefgefyggvvdltnpeaydwfkdvikknmialgcsgwmadfgeylptdtylhngvsaelmhnawpalwakcnyealqktgklgeilffmragytgsqkystmmwagdqnvdwslddglasvvpaalslamtghglhhsdiggyttlfdmkrskelllrwcdfsaftpmmrthegnrpsndwqfdgdaetiahfarmttvfttlkpylkqavaqnaatglpvmrplflhyendaatytlkyqyllgqdllvapvheqgrcdwtlylpedhwvniwtgeahhggeisvdapigkppvfyraksewallfaslrni*
>19
mkhlrvvacmimlalagcdnndktapttkseapavaqpspaqdpsqlqklaqqsqgkaltlldaseaqldgaatlvltfsipldpeqdfsrvvhvvdkksgsvdgawelapnlkelrlrhlepervlvvtvdpavkalnnatfgksyektittrdvqpsvgfasrgsllpgkiaeglpvmalnvnhvdvnffrvkpgslasfvsqweyrsslsnwesdnllkmadlvytgrfdlnparntreklllplsdikplqqagvyvavmnqaghynysnaatlftlsdigvsahryhsrldiftqslengaaqsgieivllndkgqtlaqatsdaqghvqleadkaaalllarkegqttlldltlpaldlsefnvagapgyskqffmfgprdlyrpgetvilngllrdsdgktlpdqpvklevvkpdgqvmrtvvsqpenglyrlnypldinaptglwhvrantgdnllrswdfhvedfmpermalnltaqktplapadevkfsvvgyylygapangntlqgqlflrplrdavaalpgfqfgniaeenlsrsldevqltldkggrgevsaasqwqeahsplqvilqasllesggrpvtrrveqaiwpadtlpgirpqfaakavydyrtdttvnqpivdedsnaafdivyanaqgekkavsglqvrlirerrdyywnwsesegwqsqfdqkdlvegeqtldlnadetgkvsfpvewgayrlevkapnetvssvrfwagyswqdnsdgsgaarpdrvtlkldkanyrpgdtmklhiaapvagkgyamvessdgplwwqaidvpaqgleltipvdktwnrhdlylstlvvrpgdksrsatpkravgllhlplgddnrrldlalespakmrpnqpltvrvkasvkhgempkqinvlvsavdsgvlnitdyatpdpwqaffgqkrygadiydiygqviegqgrlaalrfggdgddltrggkppvnhaniiaqqaqpitlneqgegvvtlpigdfngelrvmaqawtaddfgrgeskvvvaapviaelnmprflaggdvsrlvldvtnltdrpqtlnialaasgllellsqqpqpvnlapgvrttlfvpvralegfgegeiqatisglnlpgetlgaqhkqwqigvrpawpaqtvnsgialapgeswhvpeqhlanvspatlqgqlllsgkpplnlaryirelkaypygcleqttsglfpalytnaaqlqslgitgdsdekrraavdigisrilqmqrdnggfalwdengaeepwltayamdflirageqgysvppeainrgnerllrylqdpgtmlirysdntqastfaaqayaalvlarqqkaplgalreiwerrsqaasglplmqlgialntmgdarrgeeaitlalntprqderqwiadygsslrdnalmlslleennlrpdaqnallsslseqafgqrwlstqennalflaahsrqasagawqaqtsleaqplsgdkaltrnldadqlaalevtntgsqplwlrldssgypssapepasnvlqierqilgtdgqrkslsslrsgelvlvwltvvadrnvpdalvvdllpaglelenqnladssaslpesgsevqnllnqmqqadiqymefrddrfvaavvvnegqpvtlvylaravtpgtyqlaqpqvesmyapqwratgasegllivtp*
Binary file not shown.
Binary file not shown.
Binary file added tests/test_data/outputs/db/blast/protein/protein.pin
Binary file not shown.
22 changes: 22 additions & 0 deletions tests/test_data/outputs/db/blast/protein/protein.pjs
Original file line number Diff line number Diff line change
@@ -0,0 +1,22 @@
{
"version": "1.2",
"dbname": "protein",
"dbtype": "Protein",
"db-version": 5,
"description": "locidex_db/blast/protein/protein.fasta",
"number-of-letters": 7547,
"number-of-sequences": 20,
"last-updated": "2024-06-06T08:43:00",
"number-of-volumes": 1,
"bytes-total": 46334,
"bytes-to-cache": 7848,
"files": [
"protein.pdb",
"protein.phr",
"protein.pin",
"protein.pot",
"protein.psq",
"protein.ptf",
"protein.pto"
]
}
Binary file added tests/test_data/outputs/db/blast/protein/protein.pot
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
12 changes: 12 additions & 0 deletions tests/test_data/outputs/db/config.json
Original file line number Diff line number Diff line change
@@ -0,0 +1,12 @@
{
"db_name": "Locidex Test Database",
"db_version": "1.0.0",
"db_date": "2024/06/06",
"db_author": "James Robertson",
"db_desc": "Using Salmonella GCA_000007545.2 as source data",
"db_num_seqs": 20,
"is_nucl": true,
"is_prot": true,
"nucleotide_db_name": "nucleotide",
"protein_db_name": "protein"
}
Loading
Loading