DUf@ddlZddlZddlmZddlmZmZgdZ dd Z dd Z d Z ddZ ddZddZdZ ddZdS)N)ops)_get_default_colnames_verify_columns)make_chromarmsbinnifydigest frac_mappedfrac_gcseq_gcfrac_gene_coveragepair_by_distancechromlengthrmid_p_qc 2ddg}t|dkr|\}}nt|dkr|\}}}t|tjtfrft |}tj|t |dt |i} n>t|tjr| } ntdt|dkr3t| ||g||gz }| |j| d<d| d <d \}}nkt|dkrI|\}}}t| |||gd t| |jdkrtd ntd|\} } t|tjtfrbt |}tj |d| g} | d | d| id n>t|tjr| } ntdt| | | g| | | d <| | | d<t!j| | |||f| d dfd } | ddkrtd| |fd| djDz| d<| |||dgS)a9 Split chromosomes into chromosome arms. Parameters ---------- chromsizes : pandas.Dataframe or dict-like If dict or pandas.Series, a map from chromosomes to lengths in bp. If pandas.Dataframe, a dataframe with columns defined by cols_chroms. If cols_chroms is a triplet (e.g. 'chrom','start','end'), then values in chromsizes[cols_chroms[1]].values must all be zero. midpoints : pandas.Dataframe or dict-like Mapping of chromosomes to midpoint (aka centromere) locations. If dict or pandas.Series, a map from chromosomes to midpoints in bp. If pandas.Dataframe, a dataframe with columns defined by cols_mids. cols_chroms : (str, str) or (str, str, str) Two columns suffixes : tuple, optional Suffixes to name chromosome arms. Defaults to p and q. Returns ------- df_chromarms 4-column BED-like DataFrame (chrom, start, end, name). Arm names are chromosome names + suffix. Any chromosome not included in ``mids`` will be not be split. index sub_index_rz!unknown input type for chromsizesendrstart)rrT) unique_colsz(all values in starts column must be zerozinvalid number of cols_chroms)orientcolumnsinplace)r r"z unknown input type for midpoints)cols1cols2 return_indexrz@chromosome split into more than two arms, double-check midpointsc g|] }| Sr').0isuffixess L/var/www/html/software/conda/lib/python3.11/site-packages/bioframe/extras.py z"make_chromarms..rs*000 000name)len isinstancepdSeriesdict DataFramelistkeysvaluescopy ValueErrorrany from_dict reset_indexrenamersubtractmax) chromsizes midpoints cols_chroms cols_midsr*columns_to_dropck1sk1ek1 df_chromsck2sk2df_mids df_chromarmss ` r+rrsfJ -O ;1SS [  Q  # S#*ry$/00 >*%% LT*//++,,$z002233   J - ->OO%% <=== ;1 C:...C5 $S>0 % '!SS [  Q  # S# Cc?EEEE y~$) * * IGHH H I8999HC)bi.//=OO ,((7SE(RRD)))~t<<<< Ir| , ,=.."";<<<Gc3Z(((s|GGS\GEN<CoGU# LL!%%''!++ N   (,0000),7>000L c3/ 00r-Fc$ttstdfd}tjt |dd}|r*|d|d<|S)aG Divide a genome into evenly sized bins. Parameters ---------- chromsizes : Series pandas Series indexed by chromosome name with chromosome lengths in bp. binsize : int size of bins in bp Returns ------- bintable : pandas.DataFrame with columns: 'chrom', 'start', 'end'. zbinsize must be intc|}ttj|z }tjd|dzz}||d<t j|g|z|dd|dddgdSNrr)rrrr )intnpceilaranger1r4)rclenn_binsbinedgesbinsizer@s r+_eachzbinnify.._eachs% RWTG^,,--9Q!--7 |g&#2#xPQPRPR| T T---    r-rTaxis ignore_indexrrel_id) r0rRr9r1concatmapr6groupbycumcount)r@rYrel_idsrZbintables`` r+rrys$ gs # #0.///      yUJOO$5$566QTRRRHB%--g66??AA Or-c ddlm}ddlmn#t$rt dwxYwt t std} t||j n #t$rtd|wxYwfd}tj t||ddS) aq Divide a genome into restriction fragments. Parameters ---------- fasta_records : OrderedDict Dictionary of chromosome names to sequence records. Created by: bioframe.load_fasta('/path/to/fasta.fa') enzyme: str Name of restriction enzyme. Returns ------- Dataframe with columns: 'chrom', 'start', 'end'. rNz#Biopython is required to use digestWfasta records must be provided as an OrderedDict, can be created by bioframe.load_fastazUnknown enzyme name: ct|dd}tjdtj|dzt |ftj}t |dz }tj |g|z|dd|dddgd}|SrO) SeqstrrSr_arrayr/astypeint64r1r4)rseqcutsn_fragsfragsbioseq cut_finder fasta_recordss r+rZzdigest.._eachsjj]51!!!45566uQC11A5s3xx?@GGQQd))a- g'$ss)DH M M---    r-Tr[)Bio.Restriction RestrictionBio.Seqrh ImportErrorr0r3r9r6getattrsearchAttributeErrorr1r_r`)rtenzymebiorstchromsrZrrrss` @@r+r r s/$A((((((       AAA?@@@A mT * *  %      ! !F;VV,,3 ;;;999:::;        9S''ad C C CCs ,(A>>BTct|djtst dt t st dfd}|rBtj|| |d dd gd S| |d dd S) a/ Calculate the fraction of mapped base-pairs for each interval in a dataframe. Parameters ---------- df : pandas.DataFrame A sets of genomic intervals stored as a DataFrame. fasta_records : OrderedDict Dictionary of chromosome names to sequence records. Created by: bioframe.load_fasta('/path/to/fasta.fa') return_input: bool if False, only return Series named frac_mapped. Returns ------- df_mapped : pd.DataFrame Original dataframe with new column 'frac_mapped' appended. rHchrom from intervals not in fasta_records: double-check genome agreementrfct|j|j|j}t |}|d}||dz }|dkr||z |z ndS)NNnr)rirrrr/count)binsnbasesrrts r+rZzfrac_mapped.._eachso  ci(SW)<= > >Q GGCLL QWWS\\(.  f$$9r-rr\r Tr!r ) setr7issubsetr6r9r0r3r1r_applyr=)dfrt return_inputrZs ` r+r r s. r'{! " " + +C 0B0B0D0D,E,E F F  ,    mT * *  %   :::::Ky %a((// t/LL M    xxAx&&--mT-JJJr-c6t|djtst dt t st dfd}|ddddg|}tj tj |j|j d }|rtj||gd S|S) a Calculate the fraction of GC basepairs for each interval in a dataframe. Parameters ---------- df : pandas.DataFrame A sets of genomic intervals stored as a DataFrame. fasta_records : OrderedDict Dictionary of chromosome names to sequence records. Created by: bioframe.load_fasta('/path/to/fasta.fa') mapped_only: bool if True, ignore 'N' in the fasta_records for calculation. if True and there are no mapped base-pairs in an interval, return np.nan. return_input: bool if False, only return Series named frac_mapped. Returns ------- df_mapped : pd.DataFrame Original dataframe with new column 'GC' appended. rrrfc|j}|}t|dd}g}|D]?\}}||d|d}|t |@|S)Nrr) mapped_only)r.riiterrowsappendr ) chrom_grouprrngc_rrrtrs r+rZzfrac_gc.._each.s E"#aaa&kk !**,, : :FAsCL3u:-.A IIfQK888 9 9 9 9 r-F)sortrr)datarGCr r)rr7rr6r9r0r3rarr1r2rS concatenaterr=r_)rrtrrrZaggout_cols `` r+r r s#4 r'{! " " + +C 0B0B0D0D,E,E F F  V    mT * *  %    **W5* ) )7E*: ; A A% H HCiR^CJ77rxHHHOOPTUUGy"gY7777r-ct|tstd|d}||dz }|d}||dz }t |}|r2|d}||dz }||z}|dkr||z|z n t jS) ap Calculate the fraction of GC basepairs for a string of nucleotides. Parameters ---------- seq : str Basepair input mapped_only: bool if True, ignore 'N' in the sequence for calculation. if True and there are no mapped base-pairs, return np.nan. Returns ------- gc : float calculated gc content. z reformat input sequence as a strGgCcrrr)r0rir9rr/rSnan)rnrrrrrs r+r r As& c3  =;<<< #A3A #A3A XXF IIcNN SYYs^^! %zzAEV  rv5r-ct|tr$ddlm}||}n|}|dddd}t j||}t j||}|S)a Calculate number and fraction of overlaps by predicted and verified RNA isoforms for a set of intervals stored in a dataframe. Parameters ---------- df : pd.DataFrame Set of genomic intervals stored as a dataframe. ucsc_mrna: str or DataFrame Name of UCSC genome or all_mrna.txt dataframe from UCSC or similar. Returns ------- df_gene_coverage : pd.DataFrame r) UCSCClientrrr)tNametStarttEndrQ) r0ri io.resourcesr fetch_mrnar=rcoveragecount_overlaps)r ucsc_mrnarmrnadf_gene_coverages r+r r bs$)S!!,,,,,,z)$$//11 ;;GUSS; T TD|B--)*:DAA r-rA_1_2c ( |}t|tr|nd} | dz} | dz} |s|r | |j_|t n|\} }}|| ||gd}||krtd|dkrtd|d}||j }||krtd |dkrtd ||||zd z}|d krtd ||}n|dkr|}ntd|s|r|| | gn|| g}||d zz||<||dzd zz||<|d kr ||}n|dkr|}ntd|s|r|| | gn|| g}||d zz ||<||dzd zz ||<tj || ddd}tj|d d|d dz dz |d<||d|k|d|kz}|j|d dj fdd}|j|d dj fdd}t%j||gd}|r|| | g}|s|| | gd}|dd|S)aV From a dataframe of genomic intervals, find all unique pairs of intervals that are between ``min_sep`` and ``max_sep`` bp separated from each other. Parameters ---------- df : pandas.DataFrame A BED-like dataframe. min_sep, max_sep : int Minimum and maximum separation between intervals in bp. Min > 0 and Max >= Min. min_intervening, max_intervening : int Minimum and maximum number of intervening intervals separating pairs. Min > 0 and Max >= Min. relative_to : str, Whether to calculate distances between interval "midpoints" or "endpoints". Default "midpoints". cols : (str, str, str) or None The names of columns containing the chromosome, start and end of the genomic intervals, provided separately for each set. The default values are 'chrom', 'start', 'end'. return_index : bool If True, return indicies of pairs as two new columns ('index'+suffixes[0] and 'index'+suffixes[1]). Default False. keep_order : bool, optional If True, sort the output dataframe to preserve the order of the intervals in df1. Default False. Note that it relies on sorting of index in the original dataframes, and will reorder the output by index. suffixes : (str, str), optional The column name suffixes for the two interval sets in the output. The first interval of each output pair is always upstream of the second. Returns ------- pandas.DataFrame A BEDPE-like dataframe of paired intervals from ``df``. rrrNF)dropz!min_sep must be less than max_sepzmin_sep must be >=0z8min_intervening must be less or equal to max_interveningzmin_intervening must be >=0r endpointsendpointrAz;relative_to must either specify 'midpoints' or 'endpoints' innerT)r*howr%r interveningc|dzS)Nrr'xr*s r+z"pair_by_distance.. !hqk/r-rQc|dzS)Nrr'rs r+rz"pair_by_distance..rr-r)rr")r8r0rirr.r sort_valuesr<r9r?printroverlaprSabsilocr7r=r1r_r)rmin_sepmax_sepmin_interveningmax_intervening relative_tocolsr% keep_orderr* index_col index_col_1 index_col_2ckskekmidsref right_probe left_probeidxs left_ivals right_ivalsout_dfs ` r+rrsCl B!+< = =J 7Ihqk)Khqk)K"z"! -1L&(((dJBB R % % 1 1u 1 = =B'<==={{.///(,,..((STTT6777 rFRVO !Dk!! jf  # #VWWW'3WzWB ?  """B4 GqL(KOWq[Q..KOk!!f  # #VWWW'3WzWB ?  """B4 7a<'JrNGaKA--JrN ;     D t)HQK))*T2G(1+2G2G-HHIIAM   m  /  / 1 3 D *Xa[**+23 1111 2 2 $   *Xa[**+23 1111 2 2 $   Y K0q 9 9 9F@##[+$>?? Ak;7a@@ D$/// Mr-)rrr)F)T)TT)NNrANFFr)numpyrSpandasr1r core.specsrr__all__rrr r r r r rr'r-r+rs2>>>>>>>>   $  c1c1c1c1L****Z/D/D/Dd/K/K/K/Kd4444n6666BH  ZZZZZZr-