ó jÜxec@ sÌddlmZddlZddlZddlmZmZddl m Z idd6dd6d d 6Z id d 6d d 6d d 6dd6dd6dd6dd6dd6dd6dd6dd6dd6dd 6d!d"6dd#6Z ej eƒjZd$d%d&d'hZeeedddd(d)„ƒZd*d+„Zdd,„Zdd-„Zdd.„Zdd/„Zd0„Zd1„Zd2„Zedd$dd3ed*d4„ƒZedded%ed5„ƒZeddd6„ƒZdS(7iÿÿÿÿ(tdivisionN(tcheckt handle_errors(tvalidate_matrixtACGTtdnatACGUtrnatACDEFGHIKLMNPQRSTVWYtproteintAtCtGtTtAGtRtCTtYtGCtStATtWtGTtKtACtMtCGTtBtAGTtDtACTtHtACGtVtNtcountst probabilitytweightt informationic C söt|ƒ}tt|tƒdt|ƒƒtt|tƒdt|ƒƒt|tkpd|dkd|tfƒt|tkp|dkd|tfƒtt|tgƒtjt j fƒpÎ|dkdt|ƒƒtt|t t fƒdt|ƒƒt|dkd|ƒ|t kr`t|dko@|dkd ||fƒt|ƒ}n†|t kr¤t|dko„|dkd ||fƒt|ƒ}nB||kr¿|jƒ}n't|dk o×|dk d ||fƒt|d kd |ƒ|dkr\|dkr)t||ƒ}qæ|dkrGt||ƒ}qætsætdƒ‚nŠ|d krzt||ƒ}nN|dkr˜t||ƒ}n0|dkr¶t||ƒ}ntsÈtdƒ‚t|ddd|d|ƒ}t|ƒ}|S(s, Performs transformations on a matrix. There are three types of transformations that can be performed: 1. Center values: Subtracts the mean from each row in df. This is common for weight matrices or energy matrices. To do this, set center_values=True. 2. Normalize values: Divides each row by the sum of the row. This is needed for probability matrices. To do this, set normalize_values=True. 3. From/To transformations: Transforms from one type of matrix (e.g. 'counts') to another type of matrix (e.g. 'information'). To do this, set from_type and to_type arguments. Here are the mathematical formulas invoked by From/To transformations: from_type='counts' -> to_type='probability': P_ic = (N_ic + l)/(N_i + C*l), N_i = sum_c(N_ic) from_type='probability' -> to_type='weight': W_ic = log_2(P_ic / Q_ic) from_type='weight' -> to_type='probability': P_ic = Q_ic * 2^(W_ic) from_type='probability' -> to_type='information': I_ic = P_ic * sum_d(P_id * log2(P_id / W_id)) from_type='information' -> to_type='probability': P_ic = I_ic / sum_d(I_id) notation: 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 Using these five 1-step transformations, 2-step transformations are also enabled, e.g., from_type='counts' -> to_type='information'. parameters ---------- df: (dataframe) The matrix to be transformed. center_values: (bool) Whether to center matrix values, i.e., subtract the mean from each row. normalize_values: (bool) Whether to normalize each row, i.e., divide each row by the sum of that row. 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 be 'counts' ONLY if from_type is 'counts' too. 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 counts matrix to a probability matrix. returns ------- out_df: (dataframe) Transformed matrix s-type(center_values) = %s must be of type bools0type(normalize_values) = %s must be of type bools$from_type = %s must be None or in %ss"to_type = %s must be None or in %ss@type(background) = %s must be None or array-like or a dataframe.s'type(pseudocount) = %s must be a numberispseudocount=%s must be >= 0s`If center_values is True, both from_type and to_typemust be None. Here, from_type=%s, to_type=%sscIf normalize_values is True, both from_type and to_typemust be None. Here, from_type=%s, to_type=%ssoUnless center_values is True or normalize_values is True,Neither from_type (=%s) nor to_type (=%s) can be None.R#sSCan only have to_type='counts' if from_type='counts'. Here, however, from_type='%s'R$R%R&sTHIS SHOULD NEVER EXECUTEt from_typetto_typet backgroundN(RRt isinstancetboolttypet MATRIX_TYPEStNonetnptndarraytpdt DataFrametinttfloattTruet_center_matrixt_normalize_matrixtcopyt_probability_mat_to_weight_matt#_probability_mat_to_information_mattFalsetAssertionErrort_counts_mat_to_probability_matt_weight_mat_to_probability_matt#_information_mat_to_probability_matttransform_matrix( tdft center_valuestnormalize_valuesR'R(R)t pseudocounttout_dftprob_df((s9/tmp/pip-install-l3LICk/logomaker/logomaker/src/matrix.pyR@(sr_ '               gð?cC sœt|ƒ}t|dkdƒ|jƒ}|j|}||jddƒdd…tjf|jdd…dd…f= 0.taxisiNt matrix_typeR$( RRR8tvaluestsumR/tnewaxistlocR7(t counts_dfRDRFtvals((s9/tmp/pip-install-l3LICk/logomaker/logomaker/src/matrix.pyR=s   B cC szt|ddƒ}t||ƒ}|jƒ}tj|tƒtj|tƒ|jdd…dd…f+s  5 cC sÅt|ddƒ}t||ƒ}|jƒ}|j}|j}|tj|tƒtj|tƒ}|jddƒ}||dd…tjf|j dd…dd…f out_df represents a uniform background 2. background is a vector => this vector is normalized then used as the entries of the rows of out_df. Vector must be the same length as the number of columns in df 3. background is a dataframe => it is then normalized and use as out_df. In this case, background must have the same rows and cols as df iNs-df and background have mismatched dimensions.s,Error: df and bg_mat have different indexes.s,Error: df and bg_mat have different columns.RHR$(tshapeR8R.RLR*R/R0tlistttupletarrayRtlenRKR7R1tcoretframeR2RR\tindextcolumns(RAR)tnum_postnum_colsRR((s9/tmp/pip-install-l3LICk/logomaker/logomaker/src/matrix.pyRO¥s&  &2 s.-c C s<tt|tttjtjfƒdƒt|ƒ}tt|ƒdkdƒtt d„|Dƒƒdƒtt|t ƒdt |ƒƒtt|t ƒdt |ƒƒt|dƒ}tt g|D]}t|ƒ|k^qǃdƒtt|tttjtjfƒp|dkd ƒ|dkrDtjt|ƒƒ}n5tt|ƒt|ƒkd t|ƒt|ƒfƒtt|t gƒtjtjfƒp©|dkd t |ƒƒtjƒ} t|| kd || fƒtjg|D]} tjt| ƒƒ^qðƒ} tj| jƒƒ} | jƒg| D]} | |kr:| ^q:}tt|ƒƒ}tjd dd|d|ƒ}xb|D]Z} | | kjtƒ|dd…tjf}|jddƒj|jdd…| f= 0.0) Pseudocount to use when converting from counts to probabilities. returns ------- out_df: (dataframe) A matrix of the requested type. s:sequences must be a list, tuple, np.ndarray, or pd.Series.issequences must have length > 0.cs s|]}t|tƒVqdS(N(R*tstr(t.0tseq((s9/tmp/pip-install-l3LICk/logomaker/logomaker/src/matrix.pys ss$sequences must all be of type strings"type(seq) = %s must be of type strs(type(center_weights) = %s; must be bool.s4all elements of sequences must have the same length.s?counts must be None or a list, tuple, np.ndarray, or pd.Series.sQcounts must be the same length as sequences;len(counts) = %d; len(sequences) = %ds@type(background) = %s must be None or array-like or a dataframe.sto_type=%s; must be in %stdataRjRiNRGR'R#R(RDR)R%RB(RR*RcRdR/R0R1tSeriesRfR\RmR,R+R.tonesR2R-R8RetuniqueR]tsorttrangetastypeR4RKRJR RLR@R5(t sequencesR#R(R)tcharacters_to_ignoretcenter_weightsRDtLtst valid_typesRot char_arraytunique_characterstcRjRiRMttmp_matRE((s9/tmp/pip-install-l3LICk/logomaker/logomaker/src/matrix.pytalignment_to_matrixÒsZ2! +$  '   1 % ,,  cC sÁtjƒ}|jdƒtt|tƒdt|ƒƒtt|tƒdt|ƒƒ|dkr„t t |ƒƒ}|j ƒn+tt t t j f}tt||ƒdƒ|dk rýt tjƒƒ}t||kd||fƒt t|ƒ}nt||kd||fƒtt|tƒdt|ƒƒ|rft|dkdƒt td ƒ}nt|ƒ} t t| ƒƒ} tjd d d |d | ƒ} |r(t tjƒƒ} x»t|ƒD]Z\} }t|| kd|| | fƒt|}x!|D]}d| j| |fR:R?R7R6RORR‘R˜(((s9/tmp/pip-install-l3LICk/logomaker/logomaker/src/matrix.pytsp    Ñ        -‹