3 jF\A@sddlmZddlZddlZddlZddlmZm Z m Z dddddd d d d d ddddddZ ej e jZd0ddZd1ddZd2ddZd3ddZd4dd Zd5d!d"Zd#d$Zd%d&Zd'd(Zd6d*d+Zd7d.d/ZdS)8)divisionN)validate_matrixvalidate_probability_matvalidate_information_matACGTZAGZCTGCATGTZACZCGTZAGTZACTZACGACGT)rrrr RYSWKMBDHVNFc Csddddh}dddh}t|}||kr0|j}n||ksDtd|||ksXtd||dkr|dkrtt||}q|dkrt||}nX|dkrt||} n4|dkrt||} n |dkrt||} n dstdt| d||d }|r|dkstd d t |}t|}|S) a Transforms a matrix of one type into a matrix of another type. i = position c, d = character l = pseudocount C = number of characters N_ic = counts matrix element P_ic = probability matrix element Q_ic = background probability matrix element W_ic = weight matrix element I_ic = information matrix element counts -> probability: P_ic = (N_ic + l)/(N_i + C*l), N_i = sum_c(N_ic) probability -> weight: W_ic = log_2(P_ic / Q_ic) weight -> probability: P_ic = Q_ic * 2^(W_ic) probability -> information: I_ic = P_ic * sum_d(P_id * log2(P_id / W_id)) information -> probability: P_ic = I_ic / sum_d(I_id) parameters ---------- df: (dataframe) The matrix to be transformed. from_type: (str) Type of input matrix. Must be one of 'counts', 'probability', 'weight', or 'information'. to_type: (str) Type of output matrix. Must be one of 'probability', 'weight', or 'information'. Can NOT be 'counts'. background: (array, or df) Specification of background probabilities. If array, should be the same length as df.columns and correspond to the probability of each column's character. If df, should be a probability matrix the same shape as df. pseudocount: (number >= 0) Pseudocount to use when transforming from a count matrix to a probability matrix. center: (bool) Whether to center the output matrix. Note: this only works when to_type = 'weight', as centering a matrix doesn't make sense otherwise. returns ------- out_df: (dataframe) Transformed matrix counts probabilityweightZ informationzError: invalid from_type=%szError: invalid to_type="%s"FzTHIS SHOULD NEVER HAPPEN) from_typeto_type backgroundz6Error: the option center=True is only compatible with zto_type == "weight") rcopyAssertionError_probability_mat_to_weight_mat#_probability_mat_to_information_mat_counts_mat_to_probability_mat_weight_mat_to_probability_mat#_information_mat_to_probability_mattransform_matrix center_matrix) dfrrr pseudocountcenterZ FROM_TYPESZTO_TYPESout_dfZprob_dfr-../../logomaker/src/data.pyr'!s@E              r'?cCsn|dkstdt|}|j}|j|}||jddddtjf|jddddf<t|}t |}|S)z: Converts a counts matrix to a probability matrix rz!Error: Pseudocount must be >= 0. r)axisN) r!rr valuessumnpnewaxislocnormalize_matrixr)r)r*r,valsr-r-r.r$s 0r$cCsTt|}t||}|j}tj|ttj|t|jddddf<t|}|S)z: Converts a probability matrix to a weight matrix N)r_get_background_matr r3log2SMALLr5r)r)rbg_dfr,r-r-r.r"s  .r"cCsTt|}t||}|j}|jtjd|j|jddddf<t|}t|}|S)z: Converts a probability matrix to a weight matrix N) rr8r r1r3powerr5r6r)r)rr;r,r-r-r.r%s &r%cCst|}t||}|j}|j}|j}|tj|ttj|t}|jdd}||ddtjf|j ddddf<t |}|S)z@ Converts a probability matrix to an information matrix r)r0N) rr8r r1r3r9r:r2r4r5r)r)rr;r,Zfg_valsZbg_valsZtmp_valsZinfo_vecr-r-r.r#s   (r#cCst|}t|}t|}|S)z@ Converts a probability matrix to an information matrix )rr6r)r)rr,r-r-r.r&sr&cCst|}t|jjdks"td|jddj}ttj|d sJtd|j }|j|ddtj f|j ddddf<t |}|S)z? Normalizes a matrix df to a probability matrix out_df rz,Error: Some data frame entries are negative.r)r0gz-Error: some columns in df sum to nearly zero.N) rallr1ravelr!r2anyr3iscloser r4r5r)r)sumsr,r-r-r.r6s*r6cCsTt|}|jddj}|j}|j|ddtjf|jddddf<t|}|S)zN Centers each row of a matrix about zero by subtracting out the mean. r)r0N)rmeanr1r r3r4r5)r)meansr,r-r-r.r(*s *r(cCs|j\}}|j}|dkr6d||jddddf<nt|tjttfrtj|}t ||ksft d|tj ddf|jddddf<t |}nXt|t jjjrt|}t|j|jkst dt|j|jkst d|j}t |}t|}|S)al Creates a background matrix given a background specification. There are three possiblities: 1. background is None => out_df represents a uniform background 2. background is a vector => this vector is normalized then used as the entries of the rows of out_df 3. background is a dataframe => it is then normalized and use as out_df Nrz4Error: df and background have mismatched dimensions.z,Error: df and bg_mat have different indexes.z,Error: df and bg_mat have different columns.)shaper r5 isinstancer3ndarraylisttuplearraylenr!r4r6pdcoreframe DataFramerr>indexcolumnsr)r)rnum_posZnum_colsr,r-r-r.r8>s(  $ r8rc Ks~t|}td}tt|}tjd||d}xsz'alignment_to_matrix..rcsg|]}|kr|qSr-r-)r`r[)characters_to_ignorer-r.rbsr)rSrQrP)r0Nr)rr)r3rJrEuniquer?sortrHrTrLrOastypefloatr2r5r') sequencesrrcrWZ char_arrayrXZunique_charactersrQrPZ counts_dfr[r,r-)rcr.alignment_to_matrixs   ,ri)NrF)r/)N)N)N)N)r)rr_) __future__rnumpyr3pandasrLpdblogomaker.src.validaterrrrVfinforgtinyr:r'r$r"r%r#r&r6r(r8r^rir-r-r-r.sD        , *