ship561

(defn nussinov
  "Uses the Nussinov algorithm to compute an optimal RNA structure by
  maximizing base pairs in the structure. The function requires an
  input string s. The output is a list of base pair locations [i
  j]. It will also print out the sequence and the structure so that it
  can be visually inspected. An example sequence of 'GGGAAAUCC' will
  give the answer ([2 6] [1 7] [0 8]). Locations are 0 based (ie seq
  goes from 0 to n-1)."
  
  [s]

ship561

(defn sto->aln
  "Convert a stockhom format alignment file into its ClustalW
   equivalent ALN format.  STOIN is the filespec for the stockholm
   format file and ALNOUT is the filespec for the resulting
   conversion (it is overwritten if it already exists!)"

  [stoin alnout]
  (let [seq-lines (second (join-sto-fasta-lines stoin ""))
        seq-lines (map (fn [[nm [uid sl]]]
                         [nm [uid (map #(str/join "" %) (partition-all 60 (str/replace-re #"\." "-" sl)))]])

ship561

(let [[nm sq] (cond
                                            (.startsWith l "#=GC SS_cons")
                                            [(str/join " " (butlast (str/split #"\s+" l))) (last (str/split #"\s+" l))] ;;splits the line apart and hopefully creates vector  ["#GC SS_cons" structure]
                                            (.startsWith l "#")
                                            (str/split #"\s{2,}+" l)
                                            :else
                                            (str/split #"\s+" l))
                                   prev (get m nm [(gen-uid) ""])]
                               (assoc m  nm [(first prev)
                                             (str (second prev) sq)]))

ship561

(ns smith-waterman)

(defn- array-keys
  "positions of the array to work on"

  [s1 s2]
  (for [i (range (count s1)) ;initialize scoring array. similar to a sparse matrix
        j (range (count s2))]
    [i j]))

ship561

#!/usr/bin/perl
my $p = 'AAMAAT-ATAMAAAT-AT'; #example protein
my @l = find_orfs($p);        #calls subfunction
my ($longest, $longest_aa) = longest_orf($p, @l); #calls subfunction
print "protein = $longest_aa longest = $longest\n";

sub find_orfs ($protein) {
  my ($protein) = @_;
  print "protein $protein\n";
  my $len = length ($protein);

ship561

(defn join-sto-fasta-lines [infilespec origin]
  (let [[seq-lines gc-lines] (sto-GC-and-seq-lines infilespec)
        
        gc-lines (if (not= origin "")
                   (concat (take 1 gc-lines) [origin] (drop 1 gc-lines))
                   gc-lines)
        recombined-seqs (sort-by
                         #(-> % second first)
                         (vec
                          (reduce