XfhdZddlZddlZddlZddlZddlmZddlmZddl m Z ej dedZ dZ d Zd ZGd d ZGd dZdS)z+Deal with representations of Markov Models.N) defaultdict)BiopythonDeprecationWarning)SeqzThe 'Bio.HMM.MarkovModule' module is deprecated and will be removed in a future release of Biopython. Consider using the hmmlearn package instead.cpdt|D}t|fd|DS)z=Return an array of n random numbers summing to 1.0 (PRIVATE).c4g|]}tjS)random).0_s 3lib/python3.11/site-packages/Bio/HMM/MarkovModel.py z%_gen_random_array..s333Q333cg|]}|z Srr)r xtotals r r z%_gen_random_array..s ) ) )!AI ) ) )r)rangesum)n randArrayrs @r _gen_random_arrayrsA33%((333I  NNE ) ) ) )y ) ) ))rcttt}|D] \}}|||!|S)z?Calculate which symbols can be emitted in each state (PRIVATE).rlistappend)emission_probs emissionsstatesymbols r _calculate_emissionsr"sFD!!I'(( v%'''' rcttt}|D] \}}|||!|S)axCalculate which 'from transitions' are allowed for each state (PRIVATE). This looks through all of the trans_probs, and uses this dictionary to determine allowed transitions. It converts this information into a dictionary, whose keys are source states and whose values are lists of destination states reachable from the source state via a transition. r trans_probs transitions from_stateto_states r _calculate_from_transitionsr&-sGd##K +11 HJ&&x0000 rcttt}|D] \}}|||!|S)a~Calculate which 'to transitions' are allowed for each state (PRIVATE). This looks through all of the trans_probs, and uses this dictionary to determine allowed transitions. It converts this information into a dictionary, whose keys are destination states and whose values are lists of source states from which the destination is reachable via a transition. rr!s r _calculate_to_transitionsr(=sGd##K +11 HH$$Z0000 rceZdZdZdZdZdZdZdZdZ dZ d Z d Z d Z d Zd Z ddZdZdZdZdZdZdS)MarkovModelBuilderaiInterface to build up a Markov Model. This class is designed to try to separate the task of specifying the Markov Model from the actual model itself. This is in hopes of making the actual Markov Model classes smaller. So, this builder class should be used to create Markov models instead of trying to initiate a Markov Model directly. ct||_t||_i|_i|_||||_i|_||||_ dS)agInitialize a builder to create Markov Models. Arguments: - state_alphabet -- An iterable (e.g., tuple or list) containing all of the letters that can appear in the states - emission_alphabet -- An iterable (e.g., tuple or list) containing all of the letters for states that can be emitted by the HMM. N) tuple_state_alphabet_emission_alphabet initial_probtransition_prob _all_blank emission_probtransition_pseudo _all_pseudoemission_pseudo)selfstate_alphabetemission_alphabets r __init__zMarkovModelBuilder.__init__[sy %^44"'(9":": "!__^=NOO"$#//@QRRrc,i}|D]}|D] }d|||f< |S)a+Return a dictionary with all counts set to zero (PRIVATE). This uses the letters in the first and second alphabet to create a dictionary with keys of two tuples organized as (letter of first alphabet, letter of second alphabet). The values are all set to 0. rr)r7first_alphabetsecond_alphabet all_blank first_state second_states r r2zMarkovModelBuilder._all_blankusF ) ; ;K / ; ; 9: ; 566 ;rc6i}|D]}|D]}|j|||f<|S)amReturn a dictionary with all counts set to a default value (PRIVATE). This takes the letters in first alphabet and second alphabet and creates a dictionary with keys of two tuples organized as: (letter of first alphabet, letter of second alphabet). The values are all set to the value of the class attribute DEFAULT_PSEUDO. )DEFAULT_PSEUDO)r7r<r= all_countsr?r@s r r5zMarkovModelBuilder._all_pseudosN ) N NK / N N :>:M K677 Nrc f|jstdtj|j}tj|j}tj|j}tj|j}tj|j}t|j |j |||||S)zReturn the markov model corresponding with the current parameters. Each markov model returned by a call to this function is unique (ie. they don't influence each other). zMset_initial_probabilities must be called to fully initialize the Markov model) r0 Exceptioncopydeepcopyr1r3r4r6HiddenMarkovModelr.r/)r7r0r1r3r4r6s r get_markov_modelz#MarkovModelBuilder.get_markov_models  4  }T%677 -(<== d&899  M$*@AA-(<==   #        rctj||_|D]}||jvrtd|dt |jt |jz }|dkrt dt |j}|dkrt d|dkr%d|z |z }|jD]}||jvr ||j|<dSdS)aSet initial state probabilities. initial_prob is a dictionary mapping states to probabilities. Suppose, for example, that the state alphabet is ('A', 'B'). Call set_initial_prob({'A': 1}) to guarantee that the initial state will be 'A'. Call set_initial_prob({'A': 0.5, 'B': 0.5}) to make each initial state equally probable. This method must now be called in order to use the Markov model because the calculation of initial probabilities has changed incompatibly; the previous calculation was incorrect. If initial probabilities are set for all states, then they should add up to 1. Otherwise the sum should be <= 1. The residual probability is divided up evenly between all the states for which the initial probability has not been set. For example, calling set_initial_prob({}) results in P('A') = 0.5 and P('B') = 0.5, for the above example. State ' was not found in the sequence alphabetrz.Initial probabilities can't exceed # of states?z+Total initial probability cannot exceed 1.0N)rFr0r. ValueErrorlenrErvalues)r7r0rnum_states_not_setprob_sumprobs r set_initial_probabilitiesz,MarkovModelBuilder.set_initial_probabilitiess%(!Il33"  ED000 KUKKK1 !!566T=N9O9OO  ! !LMM Mt(//1122 c>>IJJ J  ! !(N&88D- 4 4 111/3D%e, " ! 4 4rcdt|jz }|jD] }||j|< dt|jz }|jD] }||j|< dt|jz }|jD] }||j|< dS)aReset all probabilities to be an average value. Resets the values of all initial probabilities and all allowed transitions and all allowed emissions to be equal to 1 divided by the number of possible elements. This is useful if you just want to initialize a Markov Model to starting values (ie. if you have no prior notions of what the probabilities should be -- or if you are just feeling too lazy to calculate them :-). Warning 1 -- this will reset all currently set probabilities. Warning 2 -- This just sets all probabilities for transitions and emissions to total up to 1, so it doesn't ensure that the sum of each set of transitions adds up to 1. rMN)rOr1r.r0r3)r7new_initial_probrnew_trans_probkeynew_emission_probs r set_equal_probabilitiesz*MarkovModelBuilder.set_equal_probabilitiess&T%9!:!::) 8 8E'7D e $ $s4#7888' 7 7C(6D  % % #d&8"9"99% 8 8C&7D s # # 8 8rctt|j}|jD]}||j|<|jS)zSet all initial state probabilities to a randomly generated distribution. Returns the dictionary containing the initial probabilities. )rrOr.popr0)r7 initial_freqsrs r set_random_initial_probabilitiesz3MarkovModelBuilder.set_random_initial_probabilitiessS *#d.B*C*CDD ) ; ;E'4'8'8':':D e $ $  rc|jstdt|j}|D]M}tt ||}||D] }||j||f<!N|jS)zSet all allowed transition probabilities to a randomly generated distribution. Returns the dictionary containing the transition probabilities. zNo transitions have been allowed yet. Allow some or all transitions by calling allow_transition or allow_all_transitions first.)r1rEr&rrOr\)r7transitions_fromr$freqsr%s r #set_random_transition_probabilitiesz6MarkovModelBuilder.set_random_transition_probabilitiess # C  7t7KLL* K KJ%c*::*F&G&GHHE,Z8 K K?Dyy{{$j(%;<< K##rc|jstdt|j}|D]M}tt ||}||D] }||j||f<!N|jS)zSet all allowed emission probabilities to a randomly generated distribution. Returns the dictionary containing the emission probabilities. z@No emissions have been allowed yet. Allow some or all emissions.)r3rErrrOr\)r7rrrars r !set_random_emission_probabilitiesz4MarkovModelBuilder.set_random_emission_probabilitiess ! R ));<<  B BE%c)E*:&;&;<Ig  - B BG"&"8"AJw   )!+rNc||fD]}||jvrtd|d||f|jvr2||f|jvr'|d}||j||f<||j}||j||f<dSt d|d|d)aSet a transition as being possible between the two states. probability and pseudocount are optional arguments specifying the probabilities and pseudo counts for the transition. If these are not supplied, then the values are set to the default values. Raises: KeyError -- if the two states already have an allowed transition. rKrLNrTransition from  to z is already allowed.)r.rNr1r4rBKeyError)r7r$r% probability pseudocountrs r allow_transitionz#MarkovModelBuilder.allow_transitionQs!(+  ED000 KUKKK1  !)= = =  C 'C(C( " ;FD *h!7 8""1 =HD "J#9 : : :Q:QQ8QQQ rcx |j||f=|j||f=dS#t$rtd|d|dwxYw)zRestrict transitions between the two states. Raises: KeyError if the transition is not currently allowed. rnroz is already disallowed.N)r1r4rp)r7r$r%s r destroy_transitionz%MarkovModelBuilder.destroy_transitionysp $j(%;<& H'=>>>   T:TT8TTT  s!9c`||f|jvr||j||f<dStd|d|d)zSet the probability of a transition between two states. Raises: KeyError if the transition is not allowed. rnro is not allowed.N)r1rp)r7r$r%rqs r set_transition_scorez'MarkovModelBuilder.set_transition_scoresW  !T%9 9 9;FD *h!7 8 8 8M:MM8MMM rc`||f|jvr||j||f<dStd|d|d)aSet the default pseudocount for a transition. To avoid computational problems, it is helpful to be able to set a 'default' pseudocount to start with for estimating transition and emission probabilities (see p62 in Durbin et al for more discussion on this. By default, all transitions have a pseudocount of 1. Raises: KeyError if the transition is not allowed. rnrorwN)r4rp)r7r$r%counts r set_transition_pseudocountz-MarkovModelBuilder.set_transition_pseudocountsW  !T%; ; ;=BD "J#9 : : :M:MM8MMM rc`||f|jvr||j||f<dStd|d|d)zSet the probability of a emission from a particular state. Raises: KeyError if the emission from the given state is not allowed. Emission of  from rwN)r3rp)r7 seq_stateemission_staterqs r set_emission_scorez%MarkovModelBuilder.set_emission_scoresW ~ &$*< < <>ID  >: ; ; ;P~PPYPPP rc`||f|jvr||j||f<dStd|d|d)aSet the default pseudocount for an emission. To avoid computational problems, it is helpful to be able to set a 'default' pseudocount to start with for estimating transition and emission probabilities (see p62 in Durbin et al for more discussion on this. By default, all emissions have a pseudocount of 1. Raises: KeyError if the emission from the given state is not allowed. r}r~rwN)r6rp)r7rrrzs r set_emission_pseudocountz+MarkovModelBuilder.set_emission_pseudocountsW ~ &$*> > >@ED )^!< = = =P~PPYPPP r)NN)__name__ __module__ __qualname____doc__rBr:r2r5rIrTrZr^rbrdrgrlrsrurxr{rrrrr r*r*Ms6NSSS4         :(4(4(4T888B ! ! !$$$("""$111,,,4CG&&&&P      ,   rr*c<eZdZdZdZdZdZdZdZdZ dZ d S) rHzFRepresent a hidden markov model that can be used for state estimation.c||_||_||_||_||_||_||_t|j|_t|j|_ dS)aInitialize a Markov Model. Note: You should use the MarkovModelBuilder class instead of initiating this class directly. Arguments: - state_alphabet -- A tuple containing all of the letters that can appear in the states. - emission_alphabet -- A tuple containing all of the letters for states that can be emitted by the HMM. - initial_prob - A dictionary of initial probabilities for all states. - transition_prob -- A dictionary of transition probabilities for all possible transitions in the sequence. - emission_prob -- A dictionary of emission probabilities for all possible emissions from the sequence states. - transition_pseudo -- Pseudo-counts to be used for the transitions, when counting for purposes of estimating transition probabilities. - emission_pseudo -- Pseudo-counts to be used for the emissions, when counting for purposes of estimating emission probabilities. N) r8r9r0_transition_pseudo_emission_pseudor1r3r&_transitions_fromr(_transitions_to)r7r8r9r0r1r3r4r6s r r:zHiddenMarkovModel.__init__sl>-!2("3 /.* "=T=Q!R!R 99MNNrc|jS)a,Get the default transitions for the model. Returns a dictionary of all of the default transitions between any two letters in the sequence alphabet. The dictionary is structured with keys as (letter1, letter2) and values as the starting number of transitions. )rrfs r get_blank_transitionsz'HiddenMarkovModel.get_blank_transitionss &&rc|jS)aGet the starting default emissions for each sequence. This returns a dictionary of the default emissions for each letter. The dictionary is structured with keys as (seq_letter, emission_letter) and values as the starting number of emissions. )rrfs r get_blank_emissionsz%HiddenMarkovModel.get_blank_emissionss $$rc2||jvr |j|SgS)a9Get all destination states which can transition from source state_letter. This returns all letters which the given state_letter can transition to, i.e. all the destination states reachable from state_letter. An empty list is returned if state_letter has no outgoing transitions. )rr7 state_letters r r`z"HiddenMarkovModel.transitions_froms% 41 1 1),7 7Irc2||jvr |j|SgS)a$Get all source states which can transition to destination state_letter. This returns all letters which the given state_letter is reachable from, i.e. all the source states which can reach state_later An empty list is returned if state_letter is unreachable. )rrs r transitions_toz HiddenMarkovModel.transitions_to's% 4/ / /' 5 5Irc||j}||j}||j}i}i}t t |D]}|D]} || ||f} d} |dkr || } n\i} || D]#} || | f}|| |dz f}||z}|| | <$t| } | | z|| |f<|dkr| D]}| || kr |||dz | f<ni}|D]}||t |dz f||< t|}d}|D]}|||kr|}|dks Jdg}tt dt |}| |}| ||D]$}||dz |f}| |%| d |}t||fS)aACalculate the most probable state path using the Viterbi algorithm. This implements the Viterbi algorithm (see pgs 55-57 in Durbin et al for a full explanation -- this is where I took my implementation ideas from), to allow decoding of the state path, given a sequence of emissions. Arguments: - sequence -- A Seq object with the emission sequence that we want to decode. - state_alphabet -- An iterable (e.g., tuple or list) containing all of the letters that can appear in the states rr+z)Didn't find the last state to trace from!)_log_transformr0r1r3rrOrmaxrPrreverserjoinr)r7sequencer8 log_initial log_trans log_emission viterbi_probspred_state_seqi cur_state emission_partmax_probpossible_state_probs prev_state trans_part viterbi_partcur_probrristate_path_prob last_state traceback_seqloop_seqs r viterbizHiddenMarkovModel.viterbi4s ))$*;<< ''(<== **4+=>>  s8}}%%# "# "A+! "! " ,i!-E F 66 +95HH,.(&*&9&9)&D&DDD %. I/F%G (5j!a%5H'I #/*#<;C,Z88 ##7#>#>#@#@AAH1>0H y!n-q55!5""/6(BBAFNAE9+=>!EC?! "L # I IE,eS]]Q5F-GHIe  i..0011  # #E?22" R!L aX//00 U### ( (A"AE5>2E   ' ' ' '  .. =!!?22rctj|}|D]>}||}|dkrtj||||<.tj ||<?|S)a\Return log transform of the given probability dictionary (PRIVATE). When calculating the Viterbi equation, add logs of probabilities rather than multiplying probabilities, to avoid underflow errors. This method returns a new dictionary with the same keys as the given dictionary and log-transformed values. r)rFmathloginf)r7rqlog_probrXrSs r rz HiddenMarkovModel._log_transformsa9[)) * *CC=Daxx $# 7 7 !%  rN) rrrrr:rrr`rrrrrr rHrHsPP2O2O2Oh'''%%%      g3g3g3RrrH)rrFrr warnings collectionsrBiorBio.Seqrwarnrrr&r(r*rHrrr rs021 ######++++++    ***       D ^^^^^^^^^^r