Running sequence alignment with alphabets with more than 256 characters #3341
Labels
question
a user question how to do certain things
Comments
|
Hey there, We had a similar issue in #3271. Since your alphabet type would fit in a I will try it out tomorrow. |
|
When I apply this patch Click to showdiff --git a/include/seqan3/alphabet/composite/alphabet_variant.hpp b/include/seqan3/alphabet/composite/alphabet_variant.hpp
index 82b035a99..df411d921 100644
--- a/include/seqan3/alphabet/composite/alphabet_variant.hpp
+++ b/include/seqan3/alphabet/composite/alphabet_variant.hpp
@@ -121,18 +121,22 @@ template <typename... alternative_types>
requires (detail::writable_constexpr_alphabet<alternative_types> && ...) && (std::regular<alternative_types> && ...)
&& (sizeof...(alternative_types) >= 2)
class alphabet_variant :
- public alphabet_base<alphabet_variant<alternative_types...>,
- (static_cast<size_t>(alphabet_size<alternative_types>) + ...),
- char>
+ public alphabet_base<
+ alphabet_variant<alternative_types...>,
+ (static_cast<size_t>(alphabet_size<alternative_types>) + ...),
+ std::conditional_t<(std::same_as<alphabet_char_t<alternative_types>, char> && ...), char, char16_t>>
{
private:
//!\brief The base type.
- using base_t = alphabet_base<alphabet_variant<alternative_types...>,
- (static_cast<size_t>(alphabet_size<alternative_types>) + ...),
- char>;
-
- static_assert((std::is_same_v<alphabet_char_t<alternative_types>, char> && ...),
- "The alphabet_variant is currently only tested for alphabets with char_type char. "
+ using base_t = alphabet_base<
+ alphabet_variant<alternative_types...>,
+ (static_cast<size_t>(alphabet_size<alternative_types>) + ...),
+ std::conditional_t<(std::same_as<alphabet_char_t<alternative_types>, char> && ...), char, char16_t>>;
+
+ static_assert(((std::is_same_v<alphabet_char_t<alternative_types>, char>
+ || std::is_same_v<alphabet_char_t<alternative_types>, char16_t>)
+ && ...),
+ "The alphabet_variant is currently only tested for alphabets with char_type char or char16_t. "
"Contact us on GitHub if you have a different use case: https://github.com/seqan/seqan3 .");
//!\brief Befriend the base type.It seems to work just fine Click to show#include <seqan3/alignment/pairwise/align_pairwise.hpp>
#include <seqan3/alphabet/alphabet_base.hpp>
#include <seqan3/core/debug_stream.hpp>
namespace example
{
class example_alphabet : public seqan3::alphabet_base<example_alphabet, 1333, char16_t>
{
using base_t = seqan3::alphabet_base<example_alphabet, 1333, char16_t>;
public:
using base_t::base_t;
static constexpr char16_t rank_to_char(rank_type const rank)
{
return static_cast<char16_t>(rank);
}
static constexpr rank_type char_to_rank(char16_t const chr)
{
return static_cast<rank_type>(chr);
}
};
inline namespace literals
{
constexpr example_alphabet operator""_example(char const c) noexcept
{
return example_alphabet{}.assign_char(c);
}
constexpr std::vector<example_alphabet> operator""_example(char const * const s, size_t const n)
{
std::vector<example_alphabet> r;
r.resize(n);
for (size_t i = 0; i < n; ++i)
r[i].assign_char(s[i]);
return r;
}
} // namespace literals
} // namespace example
int main()
{
using namespace example::literals;
std::vector<example::example_alphabet> seq1 = "ACGTGATG!!@@++"_example;
std::vector<example::example_alphabet> seq2 = "AGTGATACT!!@@++"_example;
seqan3::configuration cfg = seqan3::align_cfg::method_global{} | seqan3::align_cfg::edit_scheme;
auto results_example = seqan3::align_pairwise(std::tie(seq1, seq2), cfg);
auto & res_example = *results_example.begin();
seqan3::debug_stream << "Score: " << res_example.score() << '\n';
// char16_t cannot be printed directly, so we need to convert it to char.
auto adaptor = std::views::transform(
[](auto const & in)
{
auto letter = seqan3::to_char(in);
return static_cast<char>(letter);
});
auto && [p1, p2] = res_example.alignment();
seqan3::debug_stream << adaptor(p1) << '\n';
seqan3::debug_stream << adaptor(p2) << '\n';
// Score: -4
// ACGTGATG--!!@@++
// A-GTGATACT!!@@++
}Seems like |
|
Cool! Thanks I'll give it a try |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Platform
Question
Hi,
Is it possible to compute sequence alignments suing alphabets larger than 256 characters?
For instance I tried running one of the examples from the tutorials using an alphabet with more than 256 characters I defined like this:
and when building this code:
I get these kind of errors:
Looking at the code it seems that char as is hardcoded in many places as char_type.
Is there any way to circumvent this?
Best regards,
Andrés Tiraboschi
The text was updated successfully, but these errors were encountered: