Mercurial > repos > iuc > cherri_eval
changeset 0:7c6c282ecf5a draft
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/cherri commit f9348123725f421ddbdbd8d372d038da4880dbac
| author | iuc |
|---|---|
| date | Fri, 09 Dec 2022 17:40:27 +0000 |
| parents | |
| children | 5dd6b8c4ee1e |
| files | all_fasta.loc.sample cherri_eval.xml macros.xml test-data/context_150_model.tgz test-data/context_150_st_off.npz test-data/evaluation_results_st_on.csv test-data/genome.fa test-data/genome.fa.fai test-data/genome.sizes test-data/mixed_context_150_st_off.npz test-data/test_evaluate_rris.csv test-data/train_1.fa test-data/train_1_len.tabular test-data/train_1_pos.tabular test-data/train_2.fa test-data/train_2_len.tabular test-data/train_2_pos.tabular test-data/training_data_context_150_st_on.npz test-data/training_data_mixed_context_100_st_on.npz |
| diffstat | 19 files changed, 254 insertions(+), 0 deletions(-) [+] |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/all_fasta.loc.sample Fri Dec 09 17:40:27 2022 +0000 @@ -0,0 +1,18 @@ +#This file lists the locations and dbkeys of all the fasta files +#under the "genome" directory (a directory that contains a directory +#for each build). The script extract_fasta.py will generate the file +#all_fasta.loc. This file has the format (white space characters are +#TAB characters): +# +#<unique_build_id> <dbkey> <display_name> <file_path> +# +#So, all_fasta.loc could look something like this: +# +#apiMel3 apiMel3 Honeybee (Apis mellifera): apiMel3 /path/to/genome/apiMel3/apiMel3.fa +#hg19canon hg19 Human (Homo sapiens): hg19 Canonical /path/to/genome/hg19/hg19canon.fa +#hg19full hg19 Human (Homo sapiens): hg19 Full /path/to/genome/hg19/hg19full.fa +# +#Your all_fasta.loc file should contain an entry for each individual +#fasta file. So there will be multiple fasta files for each build, +#such as with hg19 above. +#
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/cherri_eval.xml Fri Dec 09 17:40:27 2022 +0000 @@ -0,0 +1,87 @@ +<tool id="cherri_eval" name="Evaluation of RRIs using CheRRI" version="@VERSION@" profile="@PROFILE@"> + <macros> + <import>macros.xml</import> + </macros> + <expand macro="requirements"/> + <command detect_errors="exit_code"><![CDATA[ + export PYTHONHASHSEED=31337 && + ln -s '$ref_source.genome_fasta' genome.fa && + mkdir model_dir && + tar -C model_dir -xvf '$model_tar' > /dev/null && + cherri eval + -i1 '$rris_table' + -g genome.fa + -l '$chrom_len_file' + -o . + -on cherri_eval + -c '$context' + -st $use_structure + -hf $hand_feat + -m 'model_dir/final_full.model' + -mp 'model_dir/features.npz' + #if $occupied_regions: + -i2 '$occupied_regions' + #end if + #if $intarna_param_file: + -p '$intarna_param_file' + #end if + ]]></command> + <inputs> + <param name="rris_table" type="data" format="csv" label="CSV file containing all RRIs that should be evaluated" /> + <expand macro="reference_source_conditional"/> + <param name="model_tar" type="data" format="tgz" label="Model and feature files in a tar" /> + <param name="context" type="integer" value="150" label="How much context should be added at up- and downstream of each sequence" /> + <param name="use_structure" type="boolean" truevalue="on" falsevalue="off" checked="true" label="Set 'off' if you want to disable structure, default 'on'" /> + <param name="hand_feat" type="boolean" truevalue="on" falsevalue="off" checked="false" label="If you want to start from hand-curated feature files, use this for evaluating test set performance. Default: 'off'" /> + <param name="occupied_regions" optional="True" type="data" format="binary" label="Occupied regions python object file containing a dictionary" /> + <param name="intarna_param_file" optional="True" type="data" format="txt" label="IntaRNA parameters file" /> + </inputs> + <outputs> + <data name="eval_out" format="csv" from_work_dir="cherri_eval/evaluation/evaluation_results_eval_rri.csv" label="Evaluation results on ${on_string}"/> + </outputs> + <tests> + <test> + <param name="rris_table" value="test_evaluate_rris.csv"/> + <conditional name="ref_source"> + <param name="ref_source_selector" value="history"/> + <param name="genome_fasta" value="genome.fa"/> + </conditional> + <param name="chrom_len_file" value="genome.sizes" /> + <param name="model_tar" value="context_150_model.tgz" /> + <output name="eval_out" file="evaluation_results_st_on.csv"/> + </test> + </tests> + <help><![CDATA[ + +**What it does** + +CheRRI detects functional RNA-RNA interaction (RRI) sites, by evaluating if an interaction site most likely occurs in nature. It helps to filter interaction sites generated either experimentally or by an RRI prediction algorithm, by removing false positive interactions. + +**Inputs** + +CheRRI takes a table of RNA-RNA interactions. It supports output of ChiRA or a csv files of interactions in the following format. The table needs the following header line: + + `chrom1,start1,stop1,strand1,chrom2,start2,stop2,strand2` + +Following the header line, each subsequent line represents an RRI, with chromosome ID (format: 1,2,3 ...), interaction start, interaction end, and strand ("+" or "-") of the two interacting partners. For example, you might want to evaluate the following three RRI sites:: + + 19,18307518,18307539,-,14,90454500,90454521,+ + X,109054541,109054590,+,9,89178539,89178562,- + 10,123136102,123136122,+,5,1245880,1245902,+ + +The tool also additionally takes a genome FASTA file and a chromosome lengths file. User can select an in-built FASTA or a FASTA file from history. +A chromosome legths file is tabular file where each line contains a tab separated chromosome name and its length. Followin is an example: + + chr1 23200231 + chr2 12497572 + chr3 8387920 + +CheRRI also needs a model file (in binary format). It can be generated by using CheRRI train tool. + +**Outputs** + +This tool outputs a tabular file containing predictions for each input interaction. + + ]]></help> + <expand macro="citations" /> +</tool>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/macros.xml Fri Dec 09 17:40:27 2022 +0000 @@ -0,0 +1,65 @@ +<macros> + <token name="@VERSION@">0.7</token> + <token name="@PROFILE@">21.05</token> + <xml name="requirements"> + <requirements> + <requirement type="package" version="@VERSION@">cherri</requirement> + </requirements> + </xml> + <macro name="reference_source_conditional"> + <conditional name="ref_source"> + <param name="ref_source_selector" type="select" label="Reference genome in FASTA format"> + <option value="cached">locally cached</option> + <option value="history">in your history</option> + </param> + <when value="cached"> + <param name="genome_fasta" type="select" label="Select reference genome" help="If your genome of interest is not listed, contact the Galaxy team"> + <options from_data_table="all_fasta"> + <filter type="sort_by" column="2" /> + <validator type="no_options" message="No indices are available." /> + </options> + </param> + </when> + <when value="history"> + <param name="genome_fasta" type="data" format="fasta" label="Select a reference dataset in FASTA format" /> + </when> + </conditional> + <param name="chrom_len_file" type="data" format="tabular" label="Two column tabular file containing chromosome lengths" help="Format: 'chrom name' \t 'chrom length'" /> + </macro> + <token name="@COMMONPARAMS@" ><![CDATA[ + #if $intarna_param_file: + -p '$intarna_param_file' + #end if + -c '$context' + -st $use_structure + -t '$run_time' + -me "\${GALAXY_MEMORY_MB_PER_SLOT:-8000}" + -j "\${GALAXY_SLOTS:-1}" + ]]></token> + <xml name="edam_ontology"> + <edam_topics> + <edam_topic>topic_0080</edam_topic> + <edam_topic>topic_0081</edam_topic> + <edam_topic>topic_0160</edam_topic> + </edam_topics> + <edam_operations> + <edam_operation>operation_2995</edam_operation> + </edam_operations> + </xml> + <xml name="bio_tools"> + <xrefs> + <xref type="bio.tools">cherri</xref> + </xrefs> + </xml> + <xml name="requirements"> + <requirements> + <requirement type="package" version="@VERSION@">cherri</requirement> + <yield/> + </requirements> + </xml> + <xml name="citations"> + <citations> + <yield /> + </citations> + </xml> +</macros>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/evaluation_results_st_on.csv Fri Dec 09 17:40:27 2022 +0000 @@ -0,0 +1,6 @@ +target_ID,query_ID,instance_score,predicted_label,E_hybrid,ED1,ED2,len_interaction_target,len_interaction_query,no_bps,max_inter_len,inter_len_normby_bp,bp_normby_inter_len,sum_ED,mfe_normby_GC,max_ED_normby_GC,mfe_normby_len,max_ED_normby_len,max_ED_normby_GC_len,complex_target_site,complex_query_site,103,218,3965,4390,4479,5431,5795,6434,6626,6635,7552,7808,8077,8174,11632,14000,15997,18340,19158,20963,21262,21694,27390,29287,29554,32863,33178,33547,34282,34422,34488,37176,37477,37532,38032,38039,38210,38612,38772,39174,40128,40201,40431,40441,41157,41484,42542,42839,43658,44532,45157,46069,46829,47317,49554,49956,52245,52435,53754,54604,56416,56450,56861,57646,59007,59023,59235,60144,60775,61153,61593,62084,62119,62321,63264,63533,63886,64400,66975,68842,69673,70066,70539,70993,71500,72034,72770,72893,76620,77916,79250,81006,83486,83553,84211,84686,85177,88601,88775,89371,89540,89800,91132,96396,96533,99879,100150,100319,101025,102113,102117,102491,104186,104635,105777,106659,107362,107877,110927,111135,111913,112240,113099,113123,115953,116421,116995,117587,118534,118785,119888,119955,120357,121948,123283,123341,125626,125838,126094,126867,128188,128428,130250,130651,131729,131834,133411,133417,134749,135445,135610,136332,136664,137596,139199,140424,141658,143218,143223,144347,144588,146175,146217,148182,148717,148840,148968,150801,150956,151321,152152,152399,152543,153917,154459,154546,154657,155274,156328,156681,157727,158027,158053,158868,159127,159265,162328,162485,163775,165891,166307,166970,167231,167372,167583,167628,167961,167971,168188,168851,169312,170207,170500,170699,172282,172357,173965,174219,174727,174947,179377,181689,181814,182942,183668,184345,184806,185260,185297,185808,186013,186285,186857,186871,187824,187840,189082,192986,193099,193860,194876,195156,195170,195325,195449,196564,197600,197675,199001,199931,200065,200863,201409,203349,204997,206423,206678,207027,207715,210220,210871,212552,212616,214127,214790,215521,215789,216063,217850,217874,218567,219482,220128,220256,220427,221245,222067,222931,223613,223729,224656,225488,226419,227603,229088,229857,230101,231806,231841,231882,232458,233010,234231,234297,234449,234564,235569,237392,239574,241915,242858,246680,247158,247200,248248,249295,250145,251764,251957,252112,252166,252543,252640,254243,255793,257183,257455,258465,258994,259160,259568,259702,261161 +chr2;+;471;520,chr1;+;471;494,0.986328125,1,-37.81,13.81,14.42,28.0,26.0,22.0,28.0,1.2727272727272727,0.7857142857142857,28.23,-12.617560975609756,18.99219512195122,-0.3421428571428571,0.515,0.2927368421052631,0.8276981148050341,0.89515469985041,0.0,0.0,0.012033098262942524,0.1453102558740324,0.03899835921291347,0.012033098262942524,0.03865871097078121,0.0,0.0,0.0,0.02410794191116372,0.021589468902926984,0.0,0.011459299381339733,0.0,0.0,0.0,0.019329355485390606,0.0,0.0,0.0,0.0,0.06875579628803839,0.0,0.012033098262942524,0.0,0.0,0.0,0.0,0.07731742194156242,0.0,0.021589468902926984,0.0,0.06817197287688598,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.05798806645617181,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.1321611062215401,0.0,0.0,0.0,0.015149327305974661,0.04317893780585397,0.0,0.011396882813649601,0.017332604094628206,0.02741755834653258,0.0,0.04273831055118601,0.03865871097078121,0.0,0.04317893780585397,0.0,0.022793765627299203,0.022918598762679467,0.0,0.019052740945631412,0.11966726954332081,0.0,0.0,0.008666302047314103,0.0170953242204744,0.14732713480433976,0.02406619652588505,0.022918598762679467,0.0,0.0,0.028492207034124,0.0,0.0,0.0,0.019329355485390606,0.0,0.0,0.0,0.0,0.0,0.02963759702653775,0.0,0.0,0.0,0.011396882813649601,0.0,0.0,0.0,0.0,0.0,0.09089596383584797,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.017332604094628206,0.0,0.0,0.015149327305974661,0.0,0.0,0.008666302047314103,0.0,0.0,0.0,0.0,0.0,0.03466520818925641,0.0,0.0,0.0,0.13336918661941988,0.05798806645617181,0.008666302047314103,0.0,0.008666302047314103,0.019052740945631412,0.016935769729450142,0.0,0.022723990958961993,0.0,0.0,0.0,0.0,0.012033098262942524,0.0,0.12234032378325291,0.0,0.0,0.0,0.0,0.0,0.14607101391650748,0.0,0.01439297926861799,0.0,0.0,0.021665755118285262,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.07574663652987332,0.0,0.0,0.045447981917923985,0.0,0.022918598762679467,0.0,0.0,0.0,0.0,0.0,0.06817197287688598,0.0,0.0,0.0,0.011396882813649601,0.0,0.0,0.02410794191116372,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0962647861035402,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.03865871097078121,0.0,0.004233942432362536,0.0,0.0,0.0,0.0,0.0,0.0,0.028648248453349328,0.0,0.0,0.0,0.0,0.0,0.0,0.011459299381339733,0.0,0.0,0.0,0.0,0.0,0.028167822282002694,0.0,0.0,0.0,0.015149327305974661,0.0,0.0,0.03683178370108494,0.005698441406824801,0.0,0.0,0.015149327305974661,0.0,0.12234032378325291,0.004233942432362536,0.0,0.0,0.0,0.0,0.0,0.0,0.011396882813649601,0.01370877917326629,0.0,0.0,0.0,0.0,0.019329355485390606,0.022918598762679467,0.0,0.0,0.0,0.0,0.02963759702653775,0.0,0.0,0.01439297926861799,0.0,0.0,0.0,0.02406619652588505,0.07219858957765515,0.01370877917326629,0.02406619652588505,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.011459299381339733,0.011396882813649601,0.0,0.0,0.0,0.09167439505071787,0.0,0.0,0.0,0.019329355485390606,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.128214931653558,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.004233942432362536,0.0,0.0,0.0,0.022723990958961993,0.0,0.10794734451463492 +chr2;+;820;840,chr1;+;794;816,0.900390625,1,-34.42,6.11,15.48,33.0,28.0,23.0,33.0,1.434782608695652,0.696969696969697,21.59,-15.345686274509804,18.51529411764706,-0.3887878787878788,0.4690909090909091,0.255487012987013,0.6248196189400709,0.7350714896676578,0.012942627204346826,0.0,0.0,0.12720524888412138,0.061232672793221095,0.0,0.0,0.0,0.0,0.0,0.021306823090261936,0.08534095405951159,0.0,0.0,0.0,0.0,0.0,0.0,0.012942627204346826,0.0,0.0,0.0,0.019043607206665022,0.0,0.010023975909557191,0.0,0.0,0.010023975909557191,0.0,0.01608979682950397,0.0,0.01828734729846677,0.0,0.019413940806520237,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.010023975909557191,0.004711305514226718,0.0,0.01608979682950397,0.01608979682950397,0.010023975909557191,0.0,0.0,0.0,0.0,0.0,0.0,0.13203295071038298,0.0,0.0,0.0,0.0,0.012191564865644513,0.0,0.009422611028453437,0.08036788304110269,0.0,0.0,0.02826783308536031,0.0,0.0,0.012191564865644513,0.0,0.02826783308536031,0.014282705404998765,0.0,0.008872486789109962,0.14605047094102827,0.0,0.0,0.007654084099152637,0.009422611028453437,0.13968703480953562,0.0,0.0,0.0,0.0,0.009422611028453437,0.009521803603332511,0.0,0.0,0.01608979682950397,0.0,0.01701097838797693,0.0,0.0,0.0,0.00709798943128797,0.0,0.0,0.03217959365900794,0.0,0.0,0.0,0.0,0.009521803603332511,0.0,0.019413940806520237,0.0,0.04826939048851191,0.0,0.0,0.0,0.0,0.0,0.05357858869406846,0.0,0.0,0.0,0.0,0.0,0.0038270420495763184,0.0,0.0,0.0,0.0,0.009521803603332511,0.05357858869406846,0.0,0.0,0.0,0.1188913229740735,0.01608979682950397,0.0,0.0,0.015308168198305274,0.10469534411149756,0.017744973578219924,0.0,0.0,0.0,0.0,0.0,0.055131867502564554,0.0,0.0,0.10972408379080062,0.0,0.0,0.0,0.0,0.0,0.12598931240536146,0.020047951819114382,0.0060957824328222564,0.0,0.0,0.02296225229745791,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.012942627204346826,0.0,0.0,0.019413940806520237,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.019413940806520237,0.0,0.0,0.0,0.009422611028453437,0.0,0.0,0.0,0.0,0.01608979682950397,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.020047951819114382,0.02229836245812634,0.0,0.0,0.0,0.010023975909557191,0.0,0.01310122215438407,0.038827881613040474,0.01608979682950397,0.0,0.08162687845981166,0.0,0.0,0.0,0.0,0.0,0.0,0.019043607206665022,0.0,0.0,0.0,0.010023975909557191,0.0,0.0,0.019043607206665022,0.0,0.0,0.025516467581965397,0.0,0.0,0.012942627204346826,0.0,0.0,0.0,0.012346314402975973,0.0,0.0,0.007654084099152637,0.004711305514226718,0.0,0.0,0.0,0.0,0.10972408379080062,0.0,0.0,0.0,0.0,0.0,0.0,0.010023975909557191,0.004711305514226718,0.0,0.0,0.0,0.0,0.010023975909557191,0.0,0.0856962324299926,0.0,0.0,0.0,0.0,0.003548994715643985,0.0,0.0,0.0060957824328222564,0.0,0.0,0.0,0.0,0.020047951819114382,0.04510789159300736,0.020047951819114382,0.0,0.0,0.0,0.0,0.012942627204346826,0.0,0.0,0.0,0.032979138599587024,0.0,0.0,0.0,0.019043607206665022,0.0,0.0,0.02658141232681749,0.06435918731801588,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.12013829061278132,0.0,0.0,0.0,0.025516467581965397,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.019413940806520237,0.0,0.10362830135797836 +chr2;+;1140;1159,chr1;+;1116;1136,0.875,1,-27.04,11.11,1.86,18.0,16.0,14.0,18.0,1.2857142857142858,0.7777777777777778,12.97,-14.949375,11.804375,-0.7816666666666667,0.6172222222222222,0.317962962962963,0.5674849873019705,0.4341963645051813,0.017722030125208475,0.0,0.027671226645624398,0.13044848302180148,0.05824990155774981,0.0,0.0,0.0,0.0,0.0,0.027950849718747495,0.058387420812114475,0.01399731277389642,0.01399731277389642,0.0,0.0,0.0,0.022450662753346964,0.017722030125208475,0.0,0.0,0.0,0.08398387664337853,0.0,0.013835613322812199,0.0,0.0,0.013835613322812199,0.0,0.022450662753346964,0.0,0.0,0.0,0.07974913556343814,0.0,0.0,0.0,0.03726779962499666,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.027671226645624398,0.007247137945655638,0.0,0.0673519882600409,0.04490132550669393,0.013835613322812199,0.0,0.0,0.0,0.0,0.0,0.0,0.14271225881648705,0.0,0.0,0.0,0.0,0.01946247360403816,0.0,0.0,0.05242491140197483,0.01399731277389642,0.0,0.0,0.0,0.0,0.01946247360403816,0.0,0.0,0.04899059470863747,0.0,0.014878843850671803,0.14494275891311276,0.0,0.0,0.005824990155774981,0.007247137945655638,0.13688726866071205,0.027671226645624398,0.0,0.0,0.0,0.0,0.01399731277389642,0.01714985851425096,0.0,0.04490132550669393,0.0,0.0,0.0,0.0,0.0,0.017854612620806162,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.01399731277389642,0.027950849718747495,0.026583045187812713,0.0,0.022450662753346964,0.0,0.0,0.0,0.0,0.0,0.05242491140197483,0.0,0.0,0.017722030125208475,0.0,0.02214037213850248,0.0,0.0,0.0,0.0,0.0,0.0,0.05824990155774981,0.0,0.0,0.0,0.13688536342618057,0.0673519882600409,0.0,0.0,0.0,0.06546691294295594,0.0,0.0,0.0,0.03544406025041695,0.0,0.0,0.055342453291248796,0.0,0.0,0.11677484162422895,0.0,0.0,0.0,0.0,0.0,0.13688536342618057,0.055342453291248796,0.00973123680201908,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.017722030125208475,0.0,0.0,0.07974913556343814,0.0,0.0,0.0,0.0,0.0,0.0,0.027950849718747495,0.07974913556343814,0.0,0.0,0.0,0.021741413836966914,0.0,0.0,0.0,0.0,0.022450662753346964,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.027671226645624398,0.0,0.0,0.0,0.0,0.013835613322812199,0.0,0.0,0.0,0.0673519882600409,0.0,0.04761230032214976,0.0,0.0,0.0,0.0,0.0,0.0,0.02799462554779284,0.0,0.0,0.0,0.013835613322812199,0.0,0.0,0.01399731277389642,0.0,0.0,0.03321055820775372,0.0,0.0,0.017722030125208475,0.0,0.0,0.0,0.053166090375625426,0.0,0.0,0.011649980311549962,0.007247137945655638,0.0,0.0,0.0,0.0,0.11677484162422895,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.007247137945655638,0.0,0.0,0.0,0.0,0.013835613322812199,0.022450662753346964,0.04899059470863747,0.0,0.0,0.0,0.0,0.00595153754026872,0.0,0.0,0.00973123680201908,0.06642111641550744,0.0,0.0,0.0,0.0830136799368732,0.0,0.013835613322812199,0.0,0.0,0.0,0.0,0.017722030125208475,0.0,0.0,0.0,0.02898855178262255,0.0,0.0,0.0,0.02799462554779284,0.0,0.0,0.0,0.04490132550669393,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.13044848302180148,0.0,0.0,0.0,0.03321055820775372,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.11677484162422895 +chr2;+;1459;1482,chr1;+;1436;1496,0.83203125,1,-14.93,6.23,3.5,9.0,10.0,9.0,10.0,1.1111111111111112,0.9,9.73,-6.175000000000001,7.398125000000001,-0.52,0.623,0.3382,0.6758220575766961,0.8427376486136672,0.028783683125170125,0.0,0.0,0.14605974672747155,0.02564321690433021,0.0,0.07375151068512625,0.0,0.0,0.0,0.0,0.059691508178522895,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.04745381044691831,0.0,0.0,0.03838923112943861,0.0,0.0,0.0,0.0,0.022414815323599863,0.0,0.0,0.0,0.019897169392840964,0.0,0.04317552468775519,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.04057215186874209,0.0,0.0,0.0,0.0,0.022414815323599863,0.0,0.0,0.03687575534256313,0.0,0.022414815323599863,0.0,0.0,0.0,0.0,0.0,0.04057215186874209,0.12180528029556852,0.0,0.0,0.0,0.0,0.03979433878568193,0.0,0.01622886074749684,0.05128643380866042,0.0,0.0,0.04868658224249051,0.07375151068512625,0.0,0.03979433878568193,0.0,0.03245772149499368,0.051185641505918145,0.0,0.0,0.09737316448498103,0.0,0.0,0.0,0.0,0.1410376929738162,0.0,0.0,0.0,0.0,0.04868658224249051,0.0,0.0,0.0,0.03687575534256313,0.0,0.03163587363127887,0.0,0.0,0.0,0.014636202684679581,0.0,0.028783683125170125,0.0,0.0,0.022414815323599863,0.0,0.0,0.025592820752959072,0.0,0.0,0.0,0.0,0.0,0.07375151068512625,0.0,0.0,0.0,0.038464825356495314,0.0,0.0,0.0,0.0,0.0,0.012821608452165106,0.0,0.0,0.0,0.0,0.03838923112943861,0.012821608452165106,0.0,0.0,0.0,0.12440772281977645,0.03687575534256313,0.012821608452165106,0.0,0.012821608452165106,0.058544810738718325,0.021954304027019374,0.0,0.0,0.0,0.0,0.0,0.03362222298539979,0.0,0.0,0.11938301635704579,0.0,0.0,0.0,0.0,0.0,0.13904392550445605,0.0,0.0,0.0,0.0,0.038464825356495314,0.0,0.0,0.0,0.0,0.0,0.03687575534256313,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.04317552468775519,0.0,0.0,0.0,0.03245772149499368,0.0,0.0,0.0,0.0,0.03687575534256313,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.029272405369359163,0.0,0.03687575534256313,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.02564321690433021,0.0,0.0,0.0,0.0,0.03687575534256313,0.11938301635704579,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.029272405369359163,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.04482963064719973,0.0,0.0,0.0,0.0,0.0,0.0,0.028783683125170125,0.0,0.0,0.0,0.03245772149499368,0.0,0.028409853192133627,0.0,0.0,0.0,0.0,0.0,0.0,0.08965926129439945,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.12171645560622629,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.09948584696420483 +chr2;+;1782;1804,chr1;+;1796;1816,0.951171875,1,-25.59,8.3,5.24,11.0,11.0,11.0,11.0,1.0,1.0,13.54,-13.952631578947368,9.610526315789476,-1.0954545454545457,0.7545454545454546,0.4048780487804878,0.7455574250275929,0.6203352658383443,0.02111001654603745,0.0,0.034862044947607744,0.14619433492165843,0.0519830880014004,0.017431022473803872,0.0,0.0,0.0,0.0,0.0,0.014549074861400571,0.0,0.0,0.027495167063805316,0.0,0.0,0.027495167063805316,0.0,0.0,0.0,0.0,0.07697043394160114,0.0,0.0,0.0,0.0,0.017431022473803872,0.0,0.05499033412761063,0.0,0.0,0.0,0.024361505139877827,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.019242608485400284,0.05499033412761063,0.0,0.017431022473803872,0.0,0.0,0.0,0.0,0.0,0.0,0.129957720003501,0.0,0.0,0.0,0.0,0.014549074861400571,0.0,0.0,0.008663848000233398,0.03848521697080057,0.0,0.01624381499129538,0.0,0.0,0.014549074861400571,0.0,0.03248762998259076,0.0,0.0,0.010153263325828915,0.12995051993036305,0.0,0.0,0.008663848000233398,0.010829209994196922,0.14728541600396777,0.0,0.019242608485400284,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0281741623204647,0.0,0.0,0.0,0.0,0.0,0.0,0.027495167063805316,0.0,0.0,0.0,0.0,0.019242608485400284,0.0,0.06333004963811235,0.0,0.0,0.0,0.05499033412761063,0.0,0.0,0.0,0.008663848000233398,0.0,0.0,0.02111001654603745,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.034655392000933594,0.0,0.0,0.0,0.13199242323577592,0.10998066825522126,0.0,0.0,0.0,0.010153263325828915,0.0,0.0,0.0,0.0,0.0,0.0,0.02614653371070581,0.0,0.0,0.13094167375260515,0.0,0.0,0.0,0.0,0.0,0.15229894988743373,0.0,0.014549074861400571,0.0,0.0,0.017327696000466797,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0844400661841498,0.0,0.0,0.06333004963811235,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.06333004963811235,0.0,0.0,0.0,0.010829209994196922,0.0,0.0,0.03637268715350144,0.0,0.027495167063805316,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.06972408989521549,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.05499033412761063,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.019242608485400284,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.02111001654603745,0.0,0.0,0.0,0.0,0.0422200330920749,0.0,0.0,0.0,0.0,0.0,0.0,0.008663848000233398,0.010829209994196922,0.0,0.0,0.0,0.0,0.13094167375260515,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.010829209994196922,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.010153263325828915,0.0,0.0,0.014549074861400571,0.0,0.0,0.0,0.017431022473803872,0.06972408989521549,0.0,0.0,0.0,0.0,0.0,0.0,0.02111001654603745,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.067349129698901,0.0,0.0,0.0,0.0,0.06972408989521549,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.12995051993036305,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.11639259889120457
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/genome.fa Fri Dec 09 17:40:27 2022 +0000 @@ -0,0 +1,4 @@ +>chr1 +GGCUCAGGGAAGGACGACAGCUCCCGGCUCAGUCCUCAGCCUCCAACCCCCACUCUUCAAUCUCCUUCCCAGACCAAUGACCCCCUCUGCGGGAGAACCUGCGGCGAAAGGCAGAGCCCCAGAGCAGGGUCUGGAGUGGCAGGACCGGCAGCCAAUGAAGGUGAAGGCCGAGCAUUACAUCAUCACCGUGGUCUCCCAUUGGUUUACAUCCUGGGCUUCCUGACUCCGCCUCCCAGCCUUAACAAUGGGCCUCUCUGCUCCCCAGGCUUCUGACCCUGGUGCCAGCUUUGCCCAGAAGGCCACAGUCGGGCAGAGUCCUGGACUUUUGCAAAGCAAACGUGCAACCCCAAGCAGCGGUCUCCCGGGCCGGGGCUGCGCGGCCGCCGCUGUGCUGGCUUUUAACGGUGGGAGGGCACCAUCCUCUUGCUCUGCUCUCGUUCUCCAGAAGGCUGUCCCGGGGCCCCCACUCUCCGUCCCGCUCCGGGGACAGUGGCUCGCCUGCUAUGCGCGGCAGCCCGCGCCGGGGCCGGCACCAGCAGCGCCCGGGCGGAUGCAGCGAGCCCACGGAGGGGCAUGCUUCCACGCACCAAGUAUAACCGCUUCAGGAAUGACUCGGUGACAUCGGUCGAUGACCUUCUCCACAGCAUUCCCAUCCAAGUCCGGGUGGGCAGGUGGCUCUUGCCCCUUGGAUUGAGGAGCACGGGGGUCAGCCUCACGGCCCAGGGUGGCCGGCGCCAGCUAAUGAGGCUGUGGUCCCGCAGGAGCUGUUCCCCUCGCGUCAGGAGAAGCUCUACCCGGGCUGGGCGCGCGCCGCCUGUGUGCUGCUGUCCUUGCUGCCCGUGCUGUGGGUCCCGGUGGCCGCGCUUGCUCAGCUGCUCACCCGGCGGAGGCGGACGUGGAGGGACAGGGACGCGCGCCCAGACACGGACAUGCGCCCGGACACGGACACGCGCCCAGACACGGACAAGUUCCGUUUAUGGUCUGAUUUCCGGCCUCUCGCCUGCUCGCCCCGCCGCCCGCCUGUCCCGCUCCCUCCCUCCCGGGGACCCGGAGGAGAGGGGACCAUGCCGGAACCCGGGCCGGACGCUGCCGGCACCGCCAGCGCACAGCCCCAACCGCCGCCGCCCCCCCCACCCGCUCCCAAGGAGUCCCCGUUCUCCAUCAAGAACCUGCUCAACGGAGACCACCACCGGCCGCCCCCUAAGCCUCAGCCGCCCCCACGGACGCUCUUCGCGCCAGCCUCGGCUGCCGCCGCCGCCGCCGCUGCCGCUGCCGCGGCGGCCAAGCAGGGCCUGGUGGCGAGAGCGCGGCUGUCACUGCGCCCGAGCAUCCCAGAGCUUUCCGAGCGGACGAGCCGGCCGUGCCGGGCAUCCCCAGCCUCGCUACCCUCGCAGCACACGUCGAGCCCCGCACAGGCGAGGGUCCGGAACUUAGCCCAAAGCACGUUUCCCCUGGCAGCGCAGGAAACGCCCGGCCGCGCGCCGGCGCACGCCCCCCUCUCCUCCUUUGUUCCGGGGGUCGGCGGCCGCUCUCCUGCCAGCGUCGGGAUCUCGGCCCCGGGAGGCGGGCCGUCGGGCGCAGCCGCGAAGAUGCCGUUGGAACUGACGCAGAGCCGAGUGCAGAAGAUCUGGGUGCCCGUGGACCACGGACUACACUUCCCAGGAUGCGUCGGGGGAAGAGGCCACAGGGACAGGCAGAGGGAGGGGGCGGCCCCAGUCCUCCGGGGCGUCGCUGUUUCCAAGCGGCGAGAUCUCGCCUAGUAACCGGCAGCUGAGGUUCACUAGCGCGGCGUUGUGGCCCCGCCCCCGGAGCCCCGGCUGGAGGAAGAACCUGUCUCCCGCGGCGCCCCAGUGACGAAGUCCAUCCCCGGGUGCGGGAGGCGGGGAGGGGAGGGCAGGCAGAGGAUUUCGCUCGCUCGCCCGCGCGGGAUCCGGGACGCGCCGGUGGCGUCCGCUGGCAGCAGAGGCUCAGCCCCGACAAGGCGGCCGAGGUGCUGAGCCAGGGCGCUCACCUGGCGGCCGGGCCCGACGGCCGGACCAUCGACCGUUUCUCUCCCACCUAGAGCGCCCCUCGCCAGCCCGCUCUGUCGCUGCUGCGCGGCCCUGGCCCGCACCCCAGGGAGCGGCGGGGGCGGCGCGCAGGGCCCACUGUGCCCGGGACAACCGCAGCGUCGCCACAGUGGCGGCUCCACCUCUCGGCGGCCUCACCUGGCCUCACUGCUUCGUGCCUUAGCUCGGGGGUCGGGGGAGAACCCCGGGACGGGGGUGGGAUGGGGUAAGGGAAAUUUAUA +>chr2 +CAGUCACCACCUCACACAUGAGGAAGCUGAGGCUGGAGACUUAGGUGACCUGGCCUAGAGUUUCAGGGCGCCGGGAUCCUGUCGAAGGUCCCACCCACCUGGCUCUGCUGCAGCGCCCUCUCUCUGUCCUCUAGGUGUGUUUGGUGGCCGGGGCCGAGGUGGGAUCCCGGGCACAGGCAGAGGCCAGCCAGAGAAGAAGCCUGGCAGACAGGCGGGCAAACAGUGAGCGCCCACCCAGACCGGCUGCUGCGCCCCCUCCUGCCAGGGUGGCGAUUCCGCUCCACAGUCUCGGACGGAUCUGCUCAGAAAGGAAGAGGCAGGUCUGGCACGGUGAAGAGACGUGAGAGGUGUAGAAUAAGUGGGAGGCCCCCGGCGCCCCCCGGUGUCCCCGCGAGGGGUCCAGGGCGGGGUCUGCCGGCCCUGCGGGCCGCCGGUGAAAUACCACUACUCUGAUCGUUUUUUCACUGACCCGGUGAGGCGGGGGGGCGAGCCCUGAGGGGCUCUCGCUUCUGGCGCCAAGCGCCCGGCCGCACGCAAAAGAGCUCCUGAAGGAAGCGCUAAACAUGGAAAGGAACAACGGGUACCAGCCGCUGCAAAAUCAUGCCAAAAUGUAAAGACCAUCGAGACUAGGAAGAAACUGCAUCAACUAACGAGCAAAAUCACCAGCUAAAGUUCCGUUUAUGGUCUGAUUUCCGGCCUCUCGCCUGCUCGCCCCGCCGCCCGCCUGUCCCGCUCCCUCCCUCCCGGGGACCCGGAGGAGAGGGGACCAUGCCGGAACCCGGGCCGGACGCUGCCGGCACCGCCAGCGCACAGCCCCAACCGCCGCCGCCCCCCCCACCCGCUCCCAAGGAGUCCCCGUUCUCCAUCAAGAACCUGCUCAACGGAGACCACCACCGGCCGCCCCCUAAGCCUCAGCCGCCCCCACGGACGCUCUUCGCGCCAGCCUCGGCUGCCGCCGCCGCCGCCGCUGCCGCUGCCGCGGCGGCCAAGCAGGCAUGCGCUGCCUAGCCCCGUGUGGUUAACAUGUCCGUAUUUAAAGAACACACAAUUAAUUGCCUAAAAGCAUUAUCCUUCUCAGCACUCUCCUAUCCUUCAGAUCUAACCUUUAGGCACUGCCGGCUGCCGGCGGGGUCCAGGACCCAGCGGGGCUGGGCGCGCGGAGCAGCGCUGGGUGCAGCGCCUGCGCCGGCAGCUGCAAGGGCCGCAGAAAUUAAACGCGAGUGUCCAGAAUCGGGCAUUGUGGGUUUAAAUCCUGAAUCCACUGGUCACUAUCUGAGACUUUCCCCUGUCACAAAUUAGUUACCUUCUUACUUUUGCAAAGCAAACGUGCAACCCCAAGCAGCGGUCUCCCGGGCCGGGGCUGCGCGGCCGCCGCUGUGCUGGCUUUUAACGGUGGGAGGGCACCAUCCUCUUGCUCUGCUCUCGUUCUCCAGAAGGCUGUCCCGGGGCCCCCACUCUCCGUCCCGCUCCGGGGACAGUGGCUCGCCUGCUAUGCGCGGCAGCCCGCGCCGGGGCCGGCACCAGCAGCGCCCGGGCGGAUGCAGCGAGCCCACGGAGGGGCAUGCUUCCACGCACCAAGUAUAACCGCUUCAGGAAUGACUCGGUGACAUCGGUCGAUGACCUUCUCCACAGGCCUUGGCCCCGCCCCCGCCGCCGCGCAGGCGCUGACGCAAGCGCAGCAGGCGCGCGCUGUUUCCGGAAGUCGCGGCCGGCGUCACCGCUGCGGCUGCCUCAGCUACUGCCGCAGUCGCCGCGGAAUUCGGCGAGUAGAACCGCUGAGGCGGGCGCGGGCCCGGGUGGGGCCAAGGUUCCGGCCACUCUGCAGAAUGGAGAUAAUCAGGAGCAGUGCGUGUCCGCCGUACACCUCCCCGCCUCCCCACACCCGGCUGCCCCUGGCCUGCUAGGCCGAGACCAUGGCCGGCGUGUUUGGCUGGGCCUGGGGCUGAGGCAGCCCUGUUGUGUAUCACUCACUGAGGCUGGACAAGAGGGAAGGCGGAGAAGCCUGGCCACAUGUCUCCUGAGGGCUCCAGGCAGGGCCCUCUCACCUGCUGCCAGGGUCCCAGCCCGCAGGAGCUUCCCGUCCACCUCUGAACUCACGGUCCACAUGGCGCUGGAGCGUCGGGCACCAUCUACAGGGCUUGAGGCCAGCAGCCUAGCCUCUGGGUCCACUGGGGCAGGCAAGGUGAGUCCUGCUGUCUGUGGAGCCAGCGUGCUGGGCCGGGCAGGGGGCCUCGUUGGCUGGGGUGGCUGCAGCUCCGCCCUGCCUGGGGCAUU
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/genome.fa.fai Fri Dec 09 17:40:27 2022 +0000 @@ -0,0 +1,2 @@ +chr1 2290 6 2290 2291 +chr2 2274 2303 2274 2275
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/genome.sizes Fri Dec 09 17:40:27 2022 +0000 @@ -0,0 +1,2 @@ +chr1 2292 +chr2 2276
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/test_evaluate_rris.csv Fri Dec 09 17:40:27 2022 +0000 @@ -0,0 +1,8 @@ +chrom1,start1,stop1,strand1,chrom2,start2,stop2,strand2 +chr2,150,171,+,chr1,150,171,+ +chr2,471,520,+,chr1,471,494,+ +chr2,820,840,+,chr1,794,816,+ +chr2,1140,1159,+,chr1,1116,1136,+ +chr2,1459,1482,+,chr1,1436,1496,+ +chr2,1782,1804,+,chr1,1796,1816,+ +chr2,2104,2124,+,chr1,2116,2140,+
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/train_1.fa Fri Dec 09 17:40:27 2022 +0000 @@ -0,0 +1,4 @@ +>chr1 +CCCAGCGGGGCUGGGCGCGCGGACCCAGCGGGGCUGGGCGCGCGGACGCGCGUGUGUCCCGGCUGCGGUCGGCCGCGCUCGAGGGGUCCCCGUGGCGGGGAUCGCCGAGGGCCGGUCGGCCGCCCCGGGUGCCGCGCGGUGCCGCGCGCGUGUGUCCCGGCUGCGGUCGGCCGCGCUCGAGGGGUCCCCGUGGCGGGGAUCGCCGAGGGCCGGUCGGCCGCCCCGGGUGCCGCGCGGUGCCGGGUGAGGCGGGGGGGCGAGCCCUGAGGGGCUCUCGCUUCUGGCGCCAAGCCCAGCGGGGCUGGGCGCGCGGAGUAGGGGGCGGGCUCCGGCGCUGCCCAGCGGGGCUGGGCGCGCGGACCCAGCGGGGCUGGGCGCGCGGACCCAGCGGGGCUGGGCGCGCGGACCCAGCGGGGCUGGGCGCGCGGACGCGCGUGCGCCCGAGCGCGGCCCGGUGGUCCCUCCCGGACAGGCGUUCGUGCGACGUGUGCGCGCGUGCGCCCGAGCGCGGCCCGGUGGUCCCUCCCGGACAGGCGUUCGUGCGACGUGUGCCCAGCGGGGCUGGGCGCGCGGACCCAGCGGGGCUGGGCGCGCGGACCCAGCGGGGCUGGGCGCGCGGACCCAGCGGGGCUGGGCGCGCGGANANANANACCCAGCGGGGCUGGGCGCGCGGACCCAGCGGGGCUGGGCGCGCGGACCCAGCGGGGCUGGGCGCGCGGAAGGGAGAAGGGUCGGGGCAGGGCCCCGGGGAGCCCGGCGGCCCAGCGGGGCUGGGCGCGCGGACCCAGCGGGGCUGGGCGCGCGGACCCAGCGGGGCUGGGCGCGCGGAGUAGGGGGCGGGCUCCGGCGCUGCCCAGCGGGGCUGGGCGCGCGGAGUAGGGGGCGGGCUCCGGCGCUGCCCAGCGGGGCUGGGCGCGCGGACCCAGCGGGGCUGGGCGCGCGGACCCAGCGGGGCUGGGCGCGCGGACCCAGCGGGGCUGGGCGCGCGGACCCAGCGGGGCUGGGCGCGCGGACCCAGCGGGGCUGGGCGCGCGGACCCAGCGGGGCUGGGCGCGCGGACCCAGCGGGGCUGGGCGCGCGGACCCAGCGGGGCUGGGCGCGCGGACCCAGCGGGGCUGGGCGCGCGGACCCAGCGGGGCUGGGCGCGCGGACCCAGCGGGGCUGGGCGCGCGGACCCAGCGGGGCUGGGCGCGCGGANACCCCGGGGAGCCCGGCGGGUAGGGGGCGGGCUCCGGCGCUGCCCAGCGGGGCUGGGCGCGCGGACCCAGCGGGGCUGGGCGCGCGGAGGUGAGGCGGGGGGGCGAGCCCUGAGGGGCUCUCGCUUCUGGCGCCAAGGGUGAGGCGGGGGGGCGAGCCCUGAGGGGCUCUCGCUUCUGGCGCCAAGAGGGAGAAGGGUCGGGGCAGGGGUAGGGGGCGGGCUCCGGCGCUGCCCAGCGGGGCUGGGCGCGCGGACCCCGGGGAGCCCGGCGGCCCAGCGGGGCUGGGCGCGCGGACCCAGCGGGGCUGGGCGCGCGGAGUAGGGGGCGGGCUCCGGCGCUGCGGAUCCGAGUCACGGCACCAAACCCAGCGGGGCUGGGCGCGCGGAGUAGGGGGCGGGCUCCGGCGCUGGUAGGGGGCGGGCUCCGGCGCUGGUAGGGGGCGGGCUCCGGCGCUGGUAGGGGGCGGGCUCCGGCGCUGCCCAGCGGGGCUGGGCGCGCGGACCCAGCGGGGCUGGGCGCGCGGACCCAGCGGGGCUGGGCGCGCGGACCCAGCGGGGCUGGGCGCGCGGACCCAGCGGGGCUGGGCGCGCGGACCCAGCGGGGCUGGGCGCGCGGACCCAGCGGGGCUGGGCGCGCGGACCCAGCGGGGCUGGGCGCGCGGACCCAGCGGGGCUGGGCGCGCGGACCCA +>chr2 +GUUGCGGCUGGACGAGGCGCAGUGGCCGCGGCGCGAGCCGGGGGGGAUCGCCGAGGGCCGGUCGGCCGCCCCGGGUGCCGCGCGGUGCCGCGCGCGUGUGUCCCGGCUGCGGUCGGCCGCGCUCGAGGGGUCCCCGUGGCGGGGAUCGCCGAGGGCCGGUCGGCCGCCCCGGGUGCCGCGCGGUGCCGCGCGCGUGUGUCCCGGCUGCGGUCGGCCGCGCUCGAGGGGUCCCCGUGGCACUGGUGAAGAGACAUGAGAGGAUGGGCGCGCGCCGGGCCCGUGCCGUUCCCUCCUCCUCCUCCCCUGCCGCGGCGAGCCGGGCCCUGGGGGCCCUUCCCGUGCGCGGGCGAGCCGGGCCCGAUGCCUUCCCCGUCCGUCCGUCCGUCCGUCCAUCCGUCCACCCCCGGGCCGGGCACCGCCCCCGGGCCGGGCACCGCGACUCUUAGCGGUGGAUCACUCGGCUCGUGCGUCGAUGAAGAACGCAGCUAGCUGCGAGAAUUAAUGUGAAUUGCAGGACACAUUGAUCAUCGACACUUCGAACGCACUUGCGGCCCCGGGUUCCUCCCGGGGCUACGCCUGUCUGAGCGUCGGACUCUUAGCGGUGGAUCACUCGGCUCGUGCGUCGAUGAAGAACGCAGCUAGCUGCGAGAAUUAAUGUGAAUUGCAGGACACAUUGAUCAUCGACACUUCGAACGCACUUGCGGCCCCGGGUUCCUCCCGGGGCUACGCCUGUCUGAGCGUCGGACUCUUAGCGGUGGAUCACUCGGCUCGUGCGUCGAUGAAGAACGCAGCUAGCUGCGAGAAUUAAUGUGAAUUGCAGGACACAUUGAUCAUCGACACUUCGAACGCACUUGCGGCCCCGGGUUCCUCCCGGGGCUACGCCUGUCUGAGCGUCGGACUCUUAGCGGUGGAUCACUCGGCUCGUGCGUCGAUGAAGAACGCAGCUAGCUGCGAGAAUUAAUGUGAAUUGCAGGACACAUUGAUCAUCGACACUUCGAACGCACUUGCGGCCCCGGGUUCCUCCCGGGGCUACGCCUGUCUGAGCGUCGNANANANAGGACGGGCCCUUCCCGUGGCGCUGCGCGAGCCGGGCGCUGCGGCUGGAUGAGGCGCUCGCCCUCUCUCUCUCUCUCUCUGUCUCUCUCUCUCUCUGGAGCCGGGGGGGGGGGGGGGGGGGGGGGGGGGCAGGCGGCGCCGCCGCCCUCUCCCACCCCAGAAAAGGUGUUGGUUGAUAUAGACAGCAGGACGGUGGCCAUGGAAGUCAGAAUCCACUAAGGAGUGUGUAACAACUCACCUGCCGAAUCAACUAGCCCUGAAAAUGGAUGGCACUGGAGCAUCAGGCCCAUACCCGGCCAUCGCCAGCAGUCCGGCCGCCGCGGCGCGCGCCCGGGUCCCCCGCCGCCCCUCCGGUGCUCCCUCCCCACCCCGCAGUGAUGCCUUCCCCGUCCGUCCGUCCGUCCGUCCAUCCGUCCACGCCUCCCUCCCCACCCCGCGAGCCUCCCUCCCCACCCCGCGAGCCUCCCUCCCCACCCCGCGAGCCUCCCUCCCCACCCCGCGAGCCUCCCUCCCCACCCCGCGAAUACUUACCUGGCAGGGGAGAUACCAUGAUCACGAAGGUGGUUUUCCCAGGGCGAGGCUUAUCCAUUGCACUC
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/train_1_len.tabular Fri Dec 09 17:40:27 2022 +0000 @@ -0,0 +1,2 @@ +chr1 1888 +chr2 1652
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/train_1_pos.tabular Fri Dec 09 17:40:27 2022 +0000 @@ -0,0 +1,25 @@ +383 chr1 0 23 + chr2 1 24 - GUUGCGGCUGGACGAGGCGCAGU CCCAGCGGGGCUGGGCGCGCGGA .((((((((.(.(....(((...&....)))..).).))).))))). -14.5 UUGCGGCUGGACGAGGCGC GCGGGGCUGGGCGCGCGG 2&5 chr1 1 19 + chr2 5 19 - 489.80 3308.00 3797.8 1.0 1.0 1.0 CDS miRNA ENST00000624358;ENST00000651965 ENST00000584178 +164 chr1 23 42 - chr2 24 47 - GGCCGCGGCGCGAGCCGGG CCCAGCGGGGCUGGGCGCGCGGA ..(((((((.(.(((((((&))).....)))).))).))))). -23.9 CCGCGGCGCGAGCCGGG CCCAGCGGGGCUGGGCGCGCGG 3&1 chr1 25 40 - chr2 24 46 - 219.80 3308.00 3527.8 1.0 1.0 1.0 protein_coding miRNA ENST00000257765;ENST00000423730;ENST00000433730;ENST00000610435 ENST00000584178 +141 chr1 42 90 + chr2 47 97 + GGGGAUCGCCGAGGGCCGGUCGGCCGCCCCGGGUGCCGCGCGGUGCCG CGCGCGUGUGUCCCGGCUGCGGUCGGCCGCGCUCGAGGGGUCCCCGUGGC (((((((.(((((.((.((((((((((.((((((((((((((......&)))))).))).)))))..)))))))))))).)))).).)))))))..... -74.1 GGGGAUCGCCGAGGGCCGGUCGGCCGCCCCGGGUGCCGCGCG CGCGCGUGUGUCCCGGCUGCGGUCGGCCGCGCUCGAGGGGUCCCC 1&1 chr1 42 84 + chr2 47 92 + 84.07 73.88 157.95 1.0 1.0 1.0 miRNA miRNA ENST00000615959 ENST00000581792 +141 chr1 90 140 + chr2 97 145 + CGCGCGUGUGUCCCGGCUGCGGUCGGCCGCGCUCGAGGGGUCCCCGUGGC GGGGAUCGCCGAGGGCCGGUCGGCCGCCCCGGGUGCCGCGCGGUGCCG ((((((.(((.(((((..((((((((((((.((((.(.(((((((.....&))))))).))))).)).)))))))))).))))))))))))))...... -74.1 CGCGCGUGUGUCCCGGCUGCGGUCGGCCGCGCUCGAGGGGUCCCC GGGGAUCGCCGAGGGCCGGUCGGCCGCCCCGGGUGCCGCGCG 1&1 chr1 90 135 + chr2 97 139 + 73.88 84.07 157.95 1.0 1.0 1.0 miRNA miRNA ENST00000615959 ENST00000615959 +141 chr1 140 188 + chr2 145 195 + GGGGAUCGCCGAGGGCCGGUCGGCCGCCCCGGGUGCCGCGCGGUGCCG CGCGCGUGUGUCCCGGCUGCGGUCGGCCGCGCUCGAGGGGUCCCCGUGGC (((((((.(((((.((.((((((((((.((((((((((((((......&)))))).))).)))))..)))))))))))).)))).).)))))))..... -74.1 GGGGAUCGCCGAGGGCCGGUCGGCCGCCCCGGGUGCCGCGCG CGCGCGUGUGUCCCGGCUGCGGUCGGCCGCGCUCGAGGGGUCCCC 1&1 chr1 140 182 + chr2 145 190 + 84.07 73.88 157.95 1.0 1.0 1.0 miRNA miRNA ENST00000581792 ENST00000615959 +141 chr1 188 238 + chr2 195 243 + CGCGCGUGUGUCCCGGCUGCGGUCGGCCGCGCUCGAGGGGUCCCCGUGGC GGGGAUCGCCGAGGGCCGGUCGGCCGCCCCGGGUGCCGCGCGGUGCCG ((((((.(((.(((((..((((((((((((.((((.(.(((((((.....&))))))).))))).)).)))))))))).))))))))))))))...... -74.1 CGCGCGUGUGUCCCGGCUGCGGUCGGCCGCGCUCGAGGGGUCCCC GGGGAUCGCCGAGGGCCGGUCGGCCGCCCCGGGUGCCGCGCG 1&1 chr1 188 233 + chr2 195 237 + 73.88 84.07 157.95 1.0 1.0 1.0 miRNA miRNA ENST00000581792 ENST00000581792 +134 chr1 238 263 - chr2 243 292 + ACUGGUGAAGAGACAUGAGAGGAUG GGUGAGGCGGGGGGGCGAGCCCUGAGGGGCUCUCGCUUCUGGCGCCAAG ..(((((.((((...((((((....&.............................)))))).))))..))))).. -17 UGGUGAAGAGACAUGAGAG CUCUCGCUUCUGGCGCCA 3&30 chr1 240 257 - chr2 272 261 + 2216.00 1579.00 3795.0 1.0 1.0 1.0 lncRNA miRNA ENST00000667915 ENST00000611066 +131 chr1 263 285 + chr2 292 315 - GGCGCGCGCCGGGCCCGUGCCG CCCAGCGGGGCUGGGCGCGCGGA ..((((((((.(((((.(((..&....)))))))).)))))))).. -35.6 CGCGCGCCGGGCCCGUGC GCGGGGCUGGGCGCGCG 3&5 chr1 265 281 + chr2 296 309 - 161.60 3308.00 3469.6 1.0 0.84 0.84 CDS miRNA ENST00000369800;ENST00000522853 ENST00000584178 +92 chr1 285 305 - chr2 315 338 + UUCCCUCCUCCUCCUCCCCU GUAGGGGGCGGGCUCCGGCGCUG ..(((.((((((.(......&).)))))).)))........... -15.3 CCCUCCUCCUCC GUAGGGGGCGGG 3&1 chr1 287 297 - chr2 315 327 + 124.00 5122.00 5246.0 1.0 1.0 1.0 lncRNA miRNA ENST00000607278 ENST00000577388 +75 chr1 305 323 - chr2 338 361 - GCCGCGGCGAGCCGGGCC CCCAGCGGGGCUGGGCGCGCGGA .(((((.(..(((.((((&........)))).))))))))). -22.4 CCGCGGCGAGCCGGGCC GGCUGGGCGCGCGG 2&9 chr1 306 322 - chr2 346 352 - 104.40 3308.00 3412.4 1.0 1.0 1.0 protein_coding miRNA ENST00000371984 ENST00000584178 +72 chr1 323 341 + chr2 361 384 - CUGGGGGCCCUUCCCGUG CCCAGCGGGGCUGGGCGCGCGGA (((.(.((((.((((((.&....))))))..)))).).))). -25.7 CUGGGGGCCCUUCCCGU GCGGGGCUGGGCGCGCGG 1&5 chr1 323 340 + chr2 365 379 - 99.15 3308.00 3407.15 1.0 0.84 0.84 lncRNA miRNA ENST00000609544 ENST00000584178 +66 chr1 341 359 + chr2 384 407 - CGCGGGCGAGCCGGGCCC CCCAGCGGGGCUGGGCGCGCGGA .....(((.(((.(((((&.......))))).))).)))... -23.6 GCGAGCCGGGCCC GGGCUGGGCGCGC 6&8 chr1 346 354 + chr2 391 397 - 99.15 3308.00 3407.15 1.0 0.84 0.84 CDS miRNA ENST00000270458 ENST00000584178 +64 chr1 359 401 - chr2 407 430 - GAUGCCUUCCCCGUCCGUCCGUCCGUCCGUCCAUCCGUCCAC CCCAGCGGGGCUGGGCGCGCGGA .................(((((.((((((.((..((((....&....)))))).)))))).))))) -23.8 UCCGUCCGUCCGUCCAUCCGU GCGGGGCUGGGCGCGCGGA 18&5 chr1 376 380 - chr2 411 426 - 19720.00 3308.00 23028.0 1.0 0.84 0.84 protein_coding miRNA ENST00000356861;ENST00000425528;ENST00000450764;ENST00000589149 ENST00000584178 +51 chr1 401 419 + chr2 430 491 + CCCCGGGCCGGGCACCGC CGCGCGUGCGCCCGAGCGCGGCCCGGUGGUCCCUCCCGGACAGGCGUUCGUGCGACGUGUG (((((((((((((.((((&...))).).))))......))))))).))................................ -29.9 CCCCGGGCCGGGCACCGC GCGUGCGCCCGAGCGCGGCCCGGUGG 1&4 chr1 401 419 + chr2 433 456 + 88.57 68.87 157.44 1.0 1.0 1.0 protein_coding miRNA ENST00000343605 ENST00000614492 +51 chr1 419 437 + chr2 491 552 + CCCCGGGCCGGGCACCGC CGCGCGUGCGCCCGAGCGCGGCCCGGUGGUCCCUCCCGGACAGGCGUUCGUGCGACGUGUG (((((((((((((.((((&...))).).))))......))))))).))................................ -29.9 CCCCGGGCCGGGCACCGC GCGUGCGCCCGAGCGCGGCCCGGUGG 1&4 chr1 419 437 + chr2 494 517 + 88.57 68.87 157.44 1.0 1.0 1.0 protein_coding miRNA ENST00000343605 ENST00000577708 +37 chr1 437 590 + chr2 552 575 - GACUCUUAGCGGUGGAUCACUCGGCUCGUGCGUCGAUGAAGAACGCAGCUAGCUGCGAGAAUUAAUGUGAAUUGCAGGACACAUUGAUCAUCGACACUUCGAACGCACUUGCGGCCCCGGGUUCCUCCCGGGGCUACGCCUGUCUGAGCGUCG CCCAGCGGGGCUGGGCGCGCGGA .......................................................................................................(((.(.(.((((((((..........(((.....................&)))..)))))))).).).))).. -26.5 CGCACUUGCGGCCCCGGGUUCCUCCCGGG CCCAGCGGGGCUGGGCGCGCG 104&1 chr1 540 466 + chr2 552 573 - 10440.00 3308.00 13748.0 1.0 0.84 0.84 rRNA miRNA ENST00000612463 ENST00000584178 +37 chr1 590 743 + chr2 575 598 - GACUCUUAGCGGUGGAUCACUCGGCUCGUGCGUCGAUGAAGAACGCAGCUAGCUGCGAGAAUUAAUGUGAAUUGCAGGACACAUUGAUCAUCGACACUUCGAACGCACUUGCGGCCCCGGGUUCCUCCCGGGGCUACGCCUGUCUGAGCGUCG CCCAGCGGGGCUGGGCGCGCGGA .......................................................................................................(((.(.(.((((((((..........(((.....................&)))..)))))))).).).))).. -26.5 CGCACUUGCGGCCCCGGGUUCCUCCCGGG CCCAGCGGGGCUGGGCGCGCG 104&1 chr1 693 619 + chr2 575 596 - 10440.00 3308.00 13748.0 1.0 0.84 0.84 rRNA miRNA ENST00000610460 ENST00000584178 +37 chr1 743 896 + chr2 598 621 - GACUCUUAGCGGUGGAUCACUCGGCUCGUGCGUCGAUGAAGAACGCAGCUAGCUGCGAGAAUUAAUGUGAAUUGCAGGACACAUUGAUCAUCGACACUUCGAACGCACUUGCGGCCCCGGGUUCCUCCCGGGGCUACGCCUGUCUGAGCGUCG CCCAGCGGGGCUGGGCGCGCGGA .......................................................................................................(((.(.(.((((((((..........(((.....................&)))..)))))))).).).))).. -26.5 CGCACUUGCGGCCCCGGGUUCCUCCCGGG CCCAGCGGGGCUGGGCGCGCG 104&1 chr1 846 772 + chr2 598 619 - 10440.00 3308.00 13748.0 1.0 0.84 0.84 rRNA miRNA ENST00000613359 ENST00000584178 +37 chr1 896 1049 + chr2 621 644 - GACUCUUAGCGGUGGAUCACUCGGCUCGUGCGUCGAUGAAGAACGCAGCUAGCUGCGAGAAUUAAUGUGAAUUGCAGGACACAUUGAUCAUCGACACUUCGAACGCACUUGCGGCCCCGGGUUCCUCCCGGGGCUACGCCUGUCUGAGCGUCG CCCAGCGGGGCUGGGCGCGCGGA .......................................................................................................(((.(.(.((((((((..........(((.....................&)))..)))))))).).).))).. -26.5 CGCACUUGCGGCCCCGGGUUCCUCCCGGG CCCAGCGGGGCUGGGCGCGCG 104&1 chr1 999 925 + chr2 621 642 - 10440.00 3308.00 13748.0 1.0 0.84 0.84 rRNA miRNA ENST00000619471 ENST00000584178 +37 chr1 1049 1202 + chr2 644 667 - NA NA NA NA NA NA NA chr1 1049 1202 + chr2 644 667 - 10440.00 3308.00 13748.0 1.0 0.84 0.84 rRNA miRNA ENST00000611446 ENST00000584178 +37 chr1 1202 1355 + chr2 667 690 - NA NA NA NA NA NA NA chr1 1202 1355 + chr2 667 690 - 10440.00 3308.00 13748.0 1.0 0.84 0.84 rRNA miRNA ENST00000619779 ENST00000584178 +37 chr1 1355 1508 + chr2 690 713 - NA NA NA NA NA NA NA chr1 1355 1508 + chr2 690 713 - 10440.00 3308.00 13748.0 1.0 0.84 0.84 rRNA miRNA ENST00000616292 ENST00000584178 +37 chr1 1508 1661 + chr2 713 736 - NA NA NA NA NA NA NA chr1 1508 1661 + chr2 713 736 - 10440.00 3308.00 13748.0 1.0 0.84 0.84 rRNA miRNA ENST00000618998 ENST00000584178 +36 chr1 1661 1679 + chr2 736 759 - GGACGGGCCCUUCCCGUG CCCAGCGGGGCUGGGCGCGCGGA .(.((.((((.((((((.&....))))))..)))).)))... -22.5 GACGGGCCCUUCCCGU GCGGGGCUGGGCGCGC 2&5 chr1 1662 1677 + chr2 740 752 - 50.24 3308.00 3358.24 1.0 0.84 0.84 CDS miRNA ENST00000305943 ENST00000584178 +32 chr1 1679 1697 - chr2 759 782 - GCGCUGCGCGAGCCGGGC CCCAGCGGGGCUGGGCGCGCGGA ...((((((..(((.(((&.........))).))))))))). -20.7 CUGCGCGAGCCGGGC GCUGGGCGCGCGG 4&10 chr1 1682 1694 - chr2 768 772 - 43.63 3308.00 3351.63 1.0 1.0 1.0 CDS miRNA ENST00000269503;ENST00000585159 ENST00000584178
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/train_2.fa Fri Dec 09 17:40:27 2022 +0000 @@ -0,0 +1,4 @@ +>chr1 +CCCAGCGGGGCUGGGCGCGCGGAGGUGAGGCGGGGGGGCGAGCCCUGAGGGGCUCUCGCUUCUGGCGCCAAGAGGCCCCGCGCGUGUGUCCCGGCUGCGGUCGGCCGCGCUCGAGGGGUCCCCGUGGCGGCCGCGGGGAUCGCCGAGGGCCGGUCGGCCGCCCCGGGUGCCGCGCGGUGAGGCCCCGCGCGUGUGUCCCGGCUGCGGUCGGCCGCGCUCGAGGGGUCCCCGUGGCGGCCGCGGGGAUCGCCGAGGGCCGGUCGGCCGCCCCGGGUGCCGCGCGGUGCCCAGCGGGGCUGGGCGCGCGGACCCAGCGGGGCUGGGCGCGCGGACCCAGCGGGGCUGGGCGCGCGGAGUAGGGGGCGGGCUCCGGCGCCCCAGCGGGGCUGGGCGCGCGGACGCGCGUGCGCCCGAGCGCGGCCCGGUGGUCCCUCCCGGACAGGCGUUCGUGCGACGCGCGUGCGCCCGAGCGCGGCCCGGUGGUCCCUCCCGGACAGGCGUUCGUGCGACCCAGCGGGGCUGGGCGCGCGGACCCAGCGGGGCUGGGCGCGCGGAGUAGGGGGCGGGCUCCGGCGCUGGCGUCCCCUUCCCCGCCGGCCGCCUUUCUCGCGCGCGACUGCGGCGGCGGUGGUGGGGGGAGCCGCGGGGAUCCCAGCGGGGCUGGGCGCGCGGACCCAGCGGGGCUGGGCGCGCGGACCCAGCGGGGCUGGGCGCGCGGACCCAGCGGGGCUGGGCGCGCGGAUGGCGUCCCCUUCCCCGCCGGCCGCCUUUCUCGCGCGCGACUGCGGCGGCGGUGGUGGGGGGAGCCGCGGGGAUNANANANACCCAGCGGGGCUGGGCGCGCGGACCCAGCGGGGCUGGGCGCGCGGACCCAGCGGGGCUGGGCGCGCGGAGUAGGGGGCGGGCUCCGGCGCGGUGAGGCGGGGGGGCGAGCCCUGAGGGGCUCUCGCUUCUGGCGCCAAGCCCAGCGGGGCUGGGCGCGCGGACCCAGCGGGGCUGGGCGCGCGGACCCAGCGGGGCUGGGCGCGCGGAAGGGAGAAGGGUCGGGGCAGNANACCCAGCGGGGCUGGGCGCGCGGACCCAGCGGGGCUGGGCGCGCGGAGGUGAGGCGGGGGGGCGAGCCCUGAGGGGCUCUCGCUUCUGGCGCCAAGGGUGAGGCGGGGGGGCGAGCCCUGAGGGGCUCUCGCUUCUGGCGCCAAGGGUGAGGCGGGGGGGCGAGCCCUGAGGGGCUCUCGCUUCUGGCGCCAAGCCCCGGGGAGCCCGGCGGNANANANAGUAGGGGGCGGGCUCCGGCGCCCCAGCGGGGCUGGGCGCGCGGACCCAGCGGGGCUGGGCGCGCGGAGGUGAGGCGGGGGGGCGAGCCCUGAGGGGCUCUCGCUUCUGGCGCCAAGCCCAGCGGGGCUGGGCGCGCGGACC +>chr2 +GUUGCGGCUGGACGAGGCGCAGCUGGUGAAGAGACAUGAGAGGAUGCCGCGGGGAUCGCCGAGGGCCGGUCGGCCGCCCCGGGUGCCGCGCGGUGAGGCCCCGCGCGUGUGUCCCGGCUGCGGUCGGCCGCGCUCGAGGGGUCCCCGUGGCGGCCGCGGGGAUCGCCGAGGGCCGGUCGGCCGCCCCGGGUGCCGCGCGGUGAGGCCCCGCGCGUGUGUCCCGGCUGCGGUCGGCCGCGCUCGAGGGGUCCCCGUGGCGGCUGCGGCUGGAUGAGGCGGGGCCGCGGCGCGAGCCGGGCUGGGGGCCCUUCCCGUGGUUCCCUCCUCCUCCUCCCCUGGCGCGCGCCGGGCCCGUGCCGCCCCGGGCCGGGCACCGCCCCCGGGCCGGGCACCGCGCCGCGGCGAGCCGGGCCGGACGGGCCCUUCCCGUGUGCCUUCCCCGUCCGUCCGUCCGUCCGUCCAUCCGUCCACCGCGACUGCGGCGGCGGUGGUGGGGGGAGCCGCGGGGAUUGGCGUCCCCUUCCCCGCCGGCCGCCUUUCUCGCGGACUCUUAGCGGUGGAUCACUCGGCUCGUGCGUCGAUGAAGAACGCAGCUAGCUGCGAGAAUUAAUGUGAAUUGCAGGACACAUUGAUCAUCGACACUUCGAACGCACUUGCGGCCCCGGGUUCCUCCCGGGGCUACGCCUGUCUGAGCGUCGGACUCUUAGCGGUGGAUCACUCGGCUCGUGCGUCGAUGAAGAACGCAGCUAGCUGCGAGAAUUAAUGUGAAUUGCAGGACACAUUGAUCAUCGACACUUCGAACGCACUUGCGGCCCCGGGUUCCUCCCGGGGCUACGCCUGUCUGAGCGUCGGACUCUUAGCGGUGGAUCACUCGGCUCGUGCGUCGAUGAAGAACGCAGCUAGCUGCGAGAAUUAAUGUGAAUUGCAGGACACAUUGAUCAUCGACACUUCGAACGCACUUGCGGCCCCGGGUUCCUCCCGGGGCUACGCCUGUCUGAGCGUCGGACUCUUAGCGGUGGAUCACUCGGCUCGUGCGUCGAUGAAGAACGCAGCUAGCUGCGAGAAUUAAUGUGAAUUGCAGGACACAUUGAUCAUCGACACUUCGAACGCACUUGCGGCCCCGGGUUCCUCCCGGGGCUACGCCUGUCUGAGCGUCGCGCGACUGCGGCGGCGGUGGUGG
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/train_2_len.tabular Fri Dec 09 17:40:27 2022 +0000 @@ -0,0 +1,2 @@ +chr1 1416 +chr2 1180
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/train_2_pos.tabular Fri Dec 09 17:40:27 2022 +0000 @@ -0,0 +1,25 @@ +386 chr1 0 22 + chr2 1 24 - GUUGCGGCUGGACGAGGCGCAG CCCAGCGGGGCUGGGCGCGCGGA .((((((((.(.(....(((..&....)))..).).))).))))). -14.5 UUGCGGCUGGACGAGGCGC GCGGGGCUGGGCGCGCGG 2&5 chr1 1 19 + chr2 5 19 - 527.40 2400.00 2927.4 1.0 1.0 1.0 CDS miRNA ENST00000624358;ENST00000651965 ENST00000584178 +156 chr1 22 45 - chr2 24 73 + CUGGUGAAGAGACAUGAGAGGAU GGUGAGGCGGGGGGGCGAGCCCUGAGGGGCUCUCGCUUCUGGCGCCAAG .(((((.((((...((((((...&.............................)))))).))))..))))).. -17 UGGUGAAGAGACAUGAGAG CUCUCGCUUCUGGCGCCA 2&30 chr1 23 41 - chr2 53 42 + 2419.00 1304.00 3723.0 1.0 1.0 1.0 lncRNA miRNA ENST00000667915 ENST00000611066 +102 chr1 45 95 + chr2 73 130 + GCCGCGGGGAUCGCCGAGGGCCGGUCGGCCGCCCCGGGUGCCGCGCGGUG AGGCCCCGCGCGUGUGUCCCGGCUGCGGUCGGCCGCGCUCGAGGGGUCCCCGUGGCG ((((((((((((.(((((.((.((((((((((.(((((((((((((((..&.....))))))).))).)))))..)))))))))))).)))).).)))))))))))). -90.1 GCCGCGGGGAUCGCCGAGGGCCGGUCGGCCGCCCCGGGUGCCGCGCGG CCGCGCGUGUGUCCCGGCUGCGGUCGGCCGCGCUCGAGGGGUCCCCGUGGC 1&6 chr1 45 93 + chr2 78 124 + 54.44 50.81 105.25 1.0 1.0 1.0 miRNA miRNA ENST00000615959 ENST00000581792 +102 chr1 95 152 + chr2 130 180 + AGGCCCCGCGCGUGUGUCCCGGCUGCGGUCGGCCGCGCUCGAGGGGUCCCCGUGGCG GCCGCGGGGAUCGCCGAGGGCCGGUCGGCCGCCCCGGGUGCCGCGCGGUG .....(((((((.(((.(((((..((((((((((((.((((.(.((((((((((((.&)))))))))))).))))).)).)))))))))).))))))))))))))).. -90.1 CCGCGCGUGUGUCCCGGCUGCGGUCGGCCGCGCUCGAGGGGUCCCCGUGGC GCCGCGGGGAUCGCCGAGGGCCGGUCGGCCGCCCCGGGUGCCGCGCGG 6&1 chr1 100 146 + chr2 130 178 + 50.81 54.44 105.25 1.0 1.0 1.0 miRNA miRNA ENST00000615959 ENST00000615959 +102 chr1 152 202 + chr2 180 237 + GCCGCGGGGAUCGCCGAGGGCCGGUCGGCCGCCCCGGGUGCCGCGCGGUG AGGCCCCGCGCGUGUGUCCCGGCUGCGGUCGGCCGCGCUCGAGGGGUCCCCGUGGCG ((((((((((((.(((((.((.((((((((((.(((((((((((((((..&.....))))))).))).)))))..)))))))))))).)))).).)))))))))))). -90.1 GCCGCGGGGAUCGCCGAGGGCCGGUCGGCCGCCCCGGGUGCCGCGCGG CCGCGCGUGUGUCCCGGCUGCGGUCGGCCGCGCUCGAGGGGUCCCCGUGGC 1&6 chr1 152 200 + chr2 185 231 + 54.44 50.81 105.25 1.0 1.0 1.0 miRNA miRNA ENST00000581792 ENST00000615959 +102 chr1 202 259 + chr2 237 287 + AGGCCCCGCGCGUGUGUCCCGGCUGCGGUCGGCCGCGCUCGAGGGGUCCCCGUGGCG GCCGCGGGGAUCGCCGAGGGCCGGUCGGCCGCCCCGGGUGCCGCGCGGUG .....(((((((.(((.(((((..((((((((((((.((((.(.((((((((((((.&)))))))))))).))))).)).)))))))))).))))))))))))))).. -90.1 CCGCGCGUGUGUCCCGGCUGCGGUCGGCCGCGCUCGAGGGGUCCCCGUGGC GCCGCGGGGAUCGCCGAGGGCCGGUCGGCCGCCCCGGGUGCCGCGCGG 6&1 chr1 207 253 + chr2 237 285 + 50.81 54.44 105.25 1.0 1.0 1.0 miRNA miRNA ENST00000581792 ENST00000581792 +86 chr1 259 280 - chr2 287 310 - GCUGCGGCUGGAUGAGGCGGG CCCAGCGGGGCUGGGCGCGCGGA .((((((((.(.....(((((&))).)).....).))).))))). -18.6 CUGCGGCUGGAUGAGGCGGG CCCAGCGGGGCUGGGCGCGCGG 2&1 chr1 260 279 - chr2 287 309 - 124.00 2400.00 2524.0 1.0 1.0 1.0 CDS miRNA ENST00000338754;ENST00000398110;ENST00000403880;ENST00000442495 ENST00000584178 +65 chr1 280 298 - chr2 310 333 - GCCGCGGCGCGAGCCGGG CCCAGCGGGGCUGGGCGCGCGGA .(((((((.(.(((((((&))).....)))).))).))))). -23.9 CCGCGGCGCGAGCCGGG CCCAGCGGGGCUGGGCGCGCGG 2&1 chr1 281 297 - chr2 310 332 - 89.73 2400.00 2489.73 1.0 1.0 1.0 protein_coding miRNA ENST00000257765;ENST00000423730;ENST00000433730;ENST00000610435 ENST00000584178 +45 chr1 298 316 + chr2 333 356 - CUGGGGGCCCUUCCCGUG CCCAGCGGGGCUGGGCGCGCGGA (((.(.((((.((((((.&....))))))..)))).).))). -25.7 CUGGGGGCCCUUCCCGU GCGGGGCUGGGCGCGCGG 1&5 chr1 298 315 + chr2 337 351 - 67.94 2400.00 2467.94 1.0 0.83 0.83 lncRNA miRNA ENST00000609544 ENST00000584178 +42 chr1 316 337 - chr2 356 377 + GUUCCCUCCUCCUCCUCCCCU GUAGGGGGCGGGCUCCGGCGC ((((((.((((((.(......&).)))))).)))....))).. -15.4 GUUCCCUCCUCCUCC GUAGGGGGCGGGCUCCGGC 1&1 chr1 316 331 - chr2 356 375 + 53.16 5016.00 5069.16 1.0 1.0 1.0 lncRNA miRNA ENST00000607278 ENST00000577388 +40 chr1 337 359 + chr2 377 400 - GGCGCGCGCCGGGCCCGUGCCG CCCAGCGGGGCUGGGCGCGCGGA ..((((((((.(((((.(((..&....)))))))).)))))))).. -35.6 CGCGCGCCGGGCCCGUGC GCGGGGCUGGGCGCGCG 3&5 chr1 339 355 + chr2 381 394 - 54.01 2400.00 2454.01 1.0 0.83 0.83 CDS miRNA ENST00000369800;ENST00000522853 ENST00000584178 +35 chr1 359 377 + chr2 400 455 + CCCCGGGCCGGGCACCGC CGCGCGUGCGCCCGAGCGCGGCCCGGUGGUCCCUCCCGGACAGGCGUUCGUGCGA (((((((((((((.((((&...))).).))))......))))))).)).......................... -29.9 CCCCGGGCCGGGCACCGC GCGUGCGCCCGAGCGCGGCCCGGUGG 1&4 chr1 359 377 + chr2 403 426 + 80.76 74.37 155.13 1.0 1.0 1.0 protein_coding miRNA ENST00000343605 ENST00000614492 +35 chr1 377 395 + chr2 455 510 + CCCCGGGCCGGGCACCGC CGCGCGUGCGCCCGAGCGCGGCCCGGUGGUCCCUCCCGGACAGGCGUUCGUGCGA (((((((((((((.((((&...))).).))))......))))))).)).......................... -29.9 CCCCGGGCCGGGCACCGC GCGUGCGCCCGAGCGCGGCCCGGUGG 1&4 chr1 377 395 + chr2 458 481 + 80.76 74.37 155.13 1.0 1.0 1.0 protein_coding miRNA ENST00000343605 ENST00000577708 +34 chr1 395 413 - chr2 510 533 - GCCGCGGCGAGCCGGGCC CCCAGCGGGGCUGGGCGCGCGGA .(((((.(..(((.((((&........)))).))))))))). -22.4 CCGCGGCGAGCCGGGCC GGCUGGGCGCGCGG 2&9 chr1 396 412 - chr2 518 524 - 47.43 2400.00 2447.43 1.0 1.0 1.0 protein_coding miRNA ENST00000371984 ENST00000584178 +23 chr1 413 431 + chr2 533 556 - GGACGGGCCCUUCCCGUG CCCAGCGGGGCUGGGCGCGCGGA .(.((.((((.((((((.&....))))))..)))).)))... -22.5 GACGGGCCCUUCCCGU GCGGGGCUGGGCGCGC 2&5 chr1 414 429 + chr2 537 549 - 35.89 2400.00 2435.89 1.0 0.83 0.83 CDS miRNA ENST00000305943 ENST00000584178 +22 chr1 431 471 - chr2 556 577 + UGCCUUCCCCGUCCGUCCGUCCGUCCGUCCAUCCGUCCAC GUAGGGGGCGGGCUCCGGCGC .........((.(((...((((((((..((..........&...))))))))))..))))). -20.7 CGUCCGUCCGUCCGUCCGUCC GGGGGCGGGCUCCGGCG 10&4 chr1 440 452 - chr2 559 573 + 14510.00 5016.00 19526.0 1.0 1.0 1.0 protein_coding miRNA ENST00000356861;ENST00000425528;ENST00000450764;ENST00000589149 ENST00000577388 +20 chr1 471 510 + chr2 577 612 + CGCGACUGCGGCGGCGGUGGUGGGGGGAGCCGCGGGGAU UGGCGUCCCCUUCCCCGCCGGCCGCCUUUCUCGCG (((((..((((((((((.((.((((((.(((........&.))).)))))).)))))))).)))).....))))) -49.4 CGCGACUGCGGCGGCGGUGGUGGGGGGAGCC GGCGUCCCCUUCCCCGCCGGCCGCCUUUCUCGCG 1&2 chr1 471 502 + chr2 578 611 + 42.67 25.71 68.38 1.0 1.0 1.0 miRNA miRNA ENST00000615959 ENST00000581792 +20 chr1 510 545 + chr2 612 651 + UGGCGUCCCCUUCCCCGCCGGCCGCCUUUCUCGCG CGCGACUGCGGCGGCGGUGGUGGGGGGAGCCGCGGGGAU .(((.((((((.(((((((.(((((.....(((((&)))))..)))))))))).)).)))))).)))........ -49.4 GGCGUCCCCUUCCCCGCCGGCCGCCUUUCUCGCG CGCGACUGCGGCGGCGGUGGUGGGGGGAGCC 2&1 chr1 511 544 + chr2 612 643 + 25.71 42.67 68.38 1.0 1.0 1.0 miRNA miRNA ENST00000615959 ENST00000615959 +20 chr1 545 698 + chr2 651 674 - GACUCUUAGCGGUGGAUCACUCGGCUCGUGCGUCGAUGAAGAACGCAGCUAGCUGCGAGAAUUAAUGUGAAUUGCAGGACACAUUGAUCAUCGACACUUCGAACGCACUUGCGGCCCCGGGUUCCUCCCGGGGCUACGCCUGUCUGAGCGUCG CCCAGCGGGGCUGGGCGCGCGGA .......................................................................................................(((.(.(.((((((((..........(((.....................&)))..)))))))).).).))).. -26.5 CGCACUUGCGGCCCCGGGUUCCUCCCGGG CCCAGCGGGGCUGGGCGCGCG 104&1 chr1 648 574 + chr2 651 672 - 10610.00 2400.00 13010.0 1.0 0.83 0.83 rRNA miRNA ENST00000612463 ENST00000584178 +20 chr1 698 851 + chr2 674 697 - GACUCUUAGCGGUGGAUCACUCGGCUCGUGCGUCGAUGAAGAACGCAGCUAGCUGCGAGAAUUAAUGUGAAUUGCAGGACACAUUGAUCAUCGACACUUCGAACGCACUUGCGGCCCCGGGUUCCUCCCGGGGCUACGCCUGUCUGAGCGUCG CCCAGCGGGGCUGGGCGCGCGGA .......................................................................................................(((.(.(.((((((((..........(((.....................&)))..)))))))).).).))).. -26.5 CGCACUUGCGGCCCCGGGUUCCUCCCGGG CCCAGCGGGGCUGGGCGCGCG 104&1 chr1 801 727 + chr2 674 695 - 10610.00 2400.00 13010.0 1.0 0.83 0.83 rRNA miRNA ENST00000610460 ENST00000584178 +20 chr1 851 1004 + chr2 697 720 - GACUCUUAGCGGUGGAUCACUCGGCUCGUGCGUCGAUGAAGAACGCAGCUAGCUGCGAGAAUUAAUGUGAAUUGCAGGACACAUUGAUCAUCGACACUUCGAACGCACUUGCGGCCCCGGGUUCCUCCCGGGGCUACGCCUGUCUGAGCGUCG CCCAGCGGGGCUGGGCGCGCGGA .......................................................................................................(((.(.(.((((((((..........(((.....................&)))..)))))))).).).))).. -26.5 CGCACUUGCGGCCCCGGGUUCCUCCCGGG CCCAGCGGGGCUGGGCGCGCG 104&1 chr1 954 880 + chr2 697 718 - 10610.00 2400.00 13010.0 1.0 0.83 0.83 rRNA miRNA ENST00000613359 ENST00000584178 +20 chr1 1004 1157 + chr2 720 743 - GACUCUUAGCGGUGGAUCACUCGGCUCGUGCGUCGAUGAAGAACGCAGCUAGCUGCGAGAAUUAAUGUGAAUUGCAGGACACAUUGAUCAUCGACACUUCGAACGCACUUGCGGCCCCGGGUUCCUCCCGGGGCUACGCCUGUCUGAGCGUCG CCCAGCGGGGCUGGGCGCGCGGA .......................................................................................................(((.(.(.((((((((..........(((.....................&)))..)))))))).).).))).. -26.5 CGCACUUGCGGCCCCGGGUUCCUCCCGGG CCCAGCGGGGCUGGGCGCGCG 104&1 chr1 1107 1033 + chr2 720 741 - 10610.00 2400.00 13010.0 1.0 0.83 0.83 rRNA miRNA ENST00000619471 ENST00000584178 +20 chr1 1157 1196 + chr2 743 778 + CGCGACUGCGGCGGCGGUGGUGGGGGGAGCCGCGGGGAU UGGCGUCCCCUUCCCCGCCGGCCGCCUUUCUCGCG (((((..((((((((((.((.((((((.(((........&.))).)))))).)))))))).)))).....))))) -49.4 CGCGACUGCGGCGGCGGUGGUGGGGGGAGCC GGCGUCCCCUUCCCCGCCGGCCGCCUUUCUCGCG 1&2 chr1 1157 1188 + chr2 744 777 + 42.67 25.71 68.38 1.0 1.0 1.0 miRNA miRNA ENST00000581792 ENST00000615959 +20 chr1 1196 1231 + chr2 778 817 + UGGCGUCCCCUUCCCCGCCGGCCGCCUUUCUCGCG CGCGACUGCGGCGGCGGUGGUGGGGGGAGCCGCGGGGAU .(((.((((((.(((((((.(((((.....(((((&)))))..)))))))))).)).)))))).)))........ -49.4 GGCGUCCCCUUCCCCGCCGGCCGCCUUUCUCGCG CGCGACUGCGGCGGCGGUGGUGGGGGGAGCC 2&1 chr1 1197 1230 + chr2 778 809 + 25.71 42.67 68.38 1.0 1.0 1.0 miRNA miRNA ENST00000581792 ENST00000581792 +20 chr1 1231 1384 + chr2 817 840 - NA NA NA NA NA NA NA chr1 1231 1384 + chr2 817 840 - 10610.00 2400.00 13010.0 1.0 0.83 0.83 rRNA miRNA ENST00000611446 ENST00000584178