Name: Towards AI Legal Name: Towards AI, Inc. Description: Towards AI is the world's leading artificial intelligence (AI) and technology publication. Read by thought-leaders and decision-makers around the world. Phone Number: +1-650-246-9381 Email: pub@towardsai.net
228 Park Avenue South New York, NY 10003 United States
Website: Publisher: https://towardsai.net/#publisher Diversity Policy: https://towardsai.net/about Ethics Policy: https://towardsai.net/about Masthead: https://towardsai.net/about
Name: Towards AI Legal Name: Towards AI, Inc. Description: Towards AI is the world's leading artificial intelligence (AI) and technology publication. Founders: Roberto Iriondo, , Job Title: Co-founder and Advisor Works for: Towards AI, Inc. Follow Roberto: X, LinkedIn, GitHub, Google Scholar, Towards AI Profile, Medium, ML@CMU, FreeCodeCamp, Crunchbase, Bloomberg, Roberto Iriondo, Generative AI Lab, Generative AI Lab Denis Piffaretti, Job Title: Co-founder Works for: Towards AI, Inc. Louie Peters, Job Title: Co-founder Works for: Towards AI, Inc. Louis-François Bouchard, Job Title: Co-founder Works for: Towards AI, Inc. Cover:
Towards AI Cover
Logo:
Towards AI Logo
Areas Served: Worldwide Alternate Name: Towards AI, Inc. Alternate Name: Towards AI Co. Alternate Name: towards ai Alternate Name: towardsai Alternate Name: towards.ai Alternate Name: tai Alternate Name: toward ai Alternate Name: toward.ai Alternate Name: Towards AI, Inc. Alternate Name: towardsai.net Alternate Name: pub.towardsai.net
5 stars – based on 497 reviews

Frequently Used, Contextual References

TODO: Remember to copy unique IDs whenever it needs used. i.e., URL: 304b2e42315e

Resources

Take our 85+ lesson From Beginner to Advanced LLM Developer Certification: From choosing a project to deploying a working product this is the most comprehensive and practical LLM course out there!

Publication

From Bits to Biology #1: Using LCS Algorithm for Global Sequence Alignment in Computational Biology
Latest   Machine Learning

From Bits to Biology #1: Using LCS Algorithm for Global Sequence Alignment in Computational Biology

Last Updated on July 19, 2023 by Editorial Team

Author(s): Suyang Li

Originally published on Towards AI.

A step-by-step analysis of the Longest Common Subsequence problem and the Sequence Alignment problem with an explanation of their solutions highlighting their similarities and differences

Photo by Sangharsh Lohakare on Unsplash

Introduction

Welcome! You’ve found the first entry in my From Bits to Biology series, where I explore the connections between general algorithms you may find in a computer science class and computational biology/bioinformatics to make them more intuitive and accessible to those without formal biology training. It took me some time to be convinced you don’t necessarily need a formal biology background to make meaningful contributions in computational biology — an incredibly fascinating field — and I hope I’ll convince you to give it a try if you are in a similar boat 🙂

In this article, we are looking at Sequence Alignment, one of the most fundamental problems in computational biology. Alignment of DNA, RNA, and protein sequences has a variety of profound implications, including understanding evolutionary relationships, progressing functional annotation, identifying mutations, and advancing drug design and precision medicine.

Table of contents

  1. Longest Common Subsequence (LCS)
    LCS Overview
    LCS Dynamic programming solution
    LCS Python implementation
  2. Global Sequence Alignment (GSA)
    GSA Overview
    Scoring Sytems
    GSA Dynamic programming solution
    GSA Python implementation
  3. LCS vs. Global Sequence Alignment: Similarities and Differences
    Summary table

Longest Common Subsequence (LCS) Problem

Longest Common Subsequence (LCS) is a classic computer science problem that identifies the longest subsequence among all the valid subsequences shared between 2 or more input sequences.

Let’s clarify the LCS problem statement by first noting an important distinction between a subsequence and a substring. Take the sequence "ABCDE":

  • A substring consists of contiguous characters in their original order. For example, valid substrings include "ABC", “CD”, etc, but not “ABDE” or “CBA”.
  • A subsequence, on the other hand, does not have to be contiguous but must also be in the original order. For example, valid subsequences include “AC” and “BFG”.

The LCS, then, is the longest among all the possible subsequences between 2 or more sequences. Here’s a quick example:

The LCS of sequences “labrador” and “exploration” is “lrao”. (Image by author)

In practice, LCS has many applications involving much larger textual data, such as plagiarism detection¹ or Unix’s diff command, necessitating an efficient and reliable, scalable algorithmic solution.

Formalizing the LCS solution

Here’s a refresher on the 3-step dynamic programming solution to LCS:

  1. Initialization (create an m × n matrix, where m and n are the lengths of sequence 1 and sequences 2).
  2. Fill out the matrix according to the recurrence formula given below.
  3. Traceback to find the LCS as well as its length.
Image source: CLRS Introduction to Algorithms² (3rd Edition), Eq 15.9.

Consider the inputs “LONGEST” and “STONE”. Based on the recurrence relation given above, we fill out the DP matrix and then traceback as follows:

Illustration of LCS algorithm (Image by author)

This is the full DP table:

(Image by author)

This translates into the Python implementation below:

# Longest Common Subsequence
def lcs(seq1, seq2):
m = len(seq1)
n = len(seq2)

# Construct dp table
table = [[0 for x in range(n+1)] for x in range(m+1)]
# Fill table based on recursive formula (15.9) from CLRS
for i in range(m+1):
for j in range(n+1):
if i == 0 or j == 0: # case 1
table[i][j] = 0
elif seq1[i-1] == seq2[j-1]: # case 2
table[i][j] = table[i-1][j-1] + 1
else: # case 3
table[i][j] = max(table[i-1][j], table[i][j-1])

# Begin traceback from the bottom-rightmost cell
index = table[m][n]
lcs = [""] * (index+1)
lcs[index] = ""

i = m
j = n
while i > 0 and j > 0:
if seq1[i-1] == seq2[j-1]: # add matching characters to LCS
lcs[index-1] = seq1[i-1]
i -= 1
j -= 1
index -= 1
elif table[i-1][j] > table[i][j-1]:
i -= 1
else:
j -= 1

# Printing the longest common subsequence and its length
print("Sequence 1: " + seq1 + "\nSequence 2: " + seq2)
print("LCS: " + lcs + ", length: " + str(len(lcs)))

Example usage:

seq1 = 'STONE'
seq2 = 'LONGEST'
lcs(seq1, seq2)

Output:

Sequence 1: STONE
Sequence 2: LONGEST
LCS: ONE, length: 3

Now, let’s take a look at how this algorithm is used in the…

(Global) Sequence Alignment Problem

Why do we want to align DNA/RNA/protein sequences?

In intuitive terms, aligning two sequences is a task of locating identical segments between the two sequences, serving the ultimate goal of assessing the level of similarity between them. Relatively straightforward in concept, this task has always been quite intricate in practice because of the uncountable changes that could happen to DNA and protein sequences through evolution. Specifically, common examples of these changes include:

  • Point mutation, through insertion, deletion, or substitution:
    – Insertion example: AAA → ACAA
    – Deletion example: AAA → AA
    – Substitution example: AAA → AGA
  • Fusion of sequences or segments from different genes

These unintended changes can introduce ambiguities and differences that mask our understanding of a given sequence. This is where we use alignment techniques to assess the similarity between sequences and infer characteristics such as homology.

How do we align sequences?

Because of these evolutionary changes, and because of the nature of biological sequence comparisons, unlike in LCS where we simply discard the “unmatchable” elements and only keep the common segment, in global sequence alignment, we must align all characters, which means alignments often involve 3 components:

  • Matches, denoted by U+007C between the matching bases
  • Mismatches, denoted by blank spaces between the mismatched bases
  • Gap insertions, denoted by dashes

Here’s an example. Suppose we have two DNA sequences “ACCCTG” and “ACCTGC”. There are a number of ways to match them base-to-base, taking into consideration the 3 operations we talked about earlier:

We could align them without any gap insertions:

ACCCTGT
U+007CU+007CU+007C U+007C
ACCTGCT

This alignment has 0 gap insertions, 3 matches, followed by 3 mismatches, and then 1 match at the end.

Or we could allow gap insertions in exchange for more matches:

ACCCTG-T
U+007CU+007CU+007C U+007CU+007C U+007C
ACC-TGCT

This alignment has 6 total matches, 2 gaps, and 0 mismatches (we don’t count a base-gap pair as a mismatch, since a gap penalty already comes with the gap insertion).

Or, if we really wished, we could also align them this way, which yields only 1 total match:

-ACC-CT-GT
U+007C
ACCTG-CT--

Between any pair of sequences, there are almost always infinite ways to generate technically correct alignments as we saw just now. Some of them will be quite obviously worse than others, but there will be a few “approximately equally good” ones, such as options 1 and 2 above.

So, how do we evaluate the quality of each alignment, choose the optimal alignment, and break ties if we need to?

Scoring schemes

1. ACCCTGT 2. ACCCTG-T 3. -ACC-CTGT
U+007CU+007CU+007C U+007C U+007CU+007CU+007C U+007CU+007C U+007C U+007C
ACCTGCT ACC-TGCT ACCTG-CT-

In the example we saw above, each alignment involves a different combination of numbers of matches, mismatches, and gaps.

Unlike the LCS problem where a subsequence is only evaluated by its length — the longer the better — , in sequence alignment, we often measure the quality of an alignment by defining a quantitative scoring system that encompasses the 3 key components of each base-to-base pairing:

  • Match reward: the score added to the overall alignment score whenever there is a base-to-base match pair in our sequence.
  • Gap penalty: the penalty value subtracted from the overall alignment score each time we introduce a gap.
  • Mismatch penalty: the penalty value subtracted from the overall alignment score each time we have a mismatch.

How do we formalize this as an algorithm?

The algorithmic solution significantly overlaps with the LCS solution in structure. It’s also a 3-step process, known as the Needleman-Wunsch algorithm:

  1. Initialization (create an m × n matrix, where m and n are the lengths of sequence 1 and sequences 2)
  2. Fill out the matrix according to the recursive formula given below
  3. Traceback to find the optimal alignment as well as its length
Image source: Understanding Bioinformatics³ (Zveibil and Baum, 2007), Eq5.17.

Before we get to the mathematical and Python formulation of the solution, here’s a quick illustration of the process with the sequences “ACGTGTCAG” and “ATGCTAG”:

Illustration of Needleman-Wunsch algorithm for aligning two DNA sequences. (Image by author)

Python solution

Let’s implement the Python solution using a class, GlobalSeqAlign, which handles both filling out the matrix as well as the traceback.

First, we construct an object containing the 5 pieces of key information: sequence 1, sequence 2, match score, mismatch penalty, and gap penalty.

class globalSeqAlign:
def __init__(self, s1, s2, M, m, g):
self.s1 = s1
self.s2 = s2
self.M = M
self.m = m
self.g = g

Then, we define a helper function that retrieves the score between two bases depending on whether they’re a match, mismatch, or base-gap pair:

 def base_pair_score(self, char1, char2):
if char1 == char2:
return self.M
elif char1 == '-' or char2 == '-':
return self.g
else:
return self.m

Now, we define a function very similar to the LCS function we saw earlier, which uses a m × n matrix, fills it according to the recursive formula, and then traces back to return the optimal alignment that maximizes the total score:

def optimal_alignment(self, s1, s2): 
m = len(s1)
n = len(s2)
score = [[0 for x in range(n+1)] for x in range(m+1)]

# Calculate score table
for i in range(m+1): # Initialize with 0s
score[i][0] = self.g * i
for j in range(n+1): # Initialize with 0s
score[0][j] = self.g * j
for i in range(1, m+1): # Fill remaining cells based on recursive formula above
for j in range(1, n+1):
match = score[i-1][j-1] + self.base_pair_score(s1[j-1], s2[i-1])
delete = score[i-1][j] + self.g
insert = score[i][j-1] + self.g
score[i][j] = max(match, delete, insert)

# Traceback, beginning from bottom-right cell
align1 = ""
align2 = ""
i = m
j = n

while i > 0 and j > 0:
score_curr = score[i][j]
score_diag = score[i-1][j-1]
score_up = score[i][j-1]
score_left = score[i-1][j]

if score_curr == score_diag + self.base_pair_score(s1[j-1], s2[i-1]): # match
align1 += s1[j-1]
align2 += s2[i-1]
i -= 1
j -= 1
elif score_curr == score_up + self.g: # upward
align1 += s1[j-1]
align2 += '-'
j -= 1
elif score_curr == score_left + self.g: # leftward
align1 += '-'
align2 += s2[i-1]
i -= 1
while j > 0:
align1 += s1[j-1]
align2 += '-'
j -= 1
while i > 0:
align1 += '-'
align2 += s2[i-1]
i -= 1

return(align1[::-1], align2[::-1]) # Reverse order

Once we have the optimal alignment, we can then proceed with the analysis quantifying how well the sequences match.

Quantifying similarity: percentage similarity

One of the simplest ways to measure the “level of similarity” is through percentage similarity. We take the optimal alignment, look at its length, and divide it by the total length of the matched regions.

For example:

Seq 1: ACACAGTCAT
U+007CU+007CU+007CU+007C U+007CU+007CU+007CU+007CU+007C
Seq 2: ACACTGTCAT

There are 9 matches out of the 10 total pairs, which yields a 90% similarity. There are many other interesting ways to analyze the quality of an alignment, but the underlying mechanism of sequence alignment remains the same.

LCS & Global Sequence Alignment Comparison

Now that we have walked through both problems and their solutions in detail, let’s look at LCS and global sequence alignment side by side.

Similarities

  • Objective: both problems find and maximize the similarities and common elements in the input sequences.
  • Algorithmic approach: both problems can be solved using dynamic programming, which involves a DP matrix/table, filling out the matrix, and tracing back to produce the sequences/alignments.
  • Scoring scheme: both problems have scores associated with matches, mismatches (and gaps) in sequence matching. These scores are explicitly and implicitly used in the algorithm to retrieve the optimal subsequence/alignment.

Differences

  • Scoring systems:
    LCS automatically adopts a scoring scheme of match score = 1, mismatch/gap = 0;
    – Global sequence alignment has a more complex scoring scheme defined by match score = A, mismatch penalty = B, gap penalty = C.
  • Gap Handling:
    LCS usually treats gaps equal to mismatches because by definition of subsequences, we only keep the matches;
    Global sequence alignment usually assigns gaps penalty score, different from the mismatch penalty if there is a preference for mismatch/gap.
  • Length of Alignment:
    – LCS is concerned with finding a segment common to all inputs, disregarding the elements that are not part of this segment;
    – Global sequence alignment matches the entire given sequences, even if it means inserting gaps if the input sequences differ in length.

Here’s a summary table of the points above:

(Image by author)

Conclusion

Thanks for sticking with me this far U+1F63C! In this article, we focused on one specific dynamic programming problem — The longest Common Subsequence — and did a side-by-side comparison with its application in computational biology for Sequence Alignment.

Later in this series, we’ll also be looking at other topics, such as Hidden Markov Models, Gaussian Mixture Models, and Classification algorithms, and how they solve specific problems in computation biology. See you soon & Happy coding U+270CU+1F3FC!

[1] Baba, K., Nakatoh, T., & Minami, T. (2017). Plagiarism detection using document similarity based on distributed representation. Procedia Computer Science, 111, 382–387. https://doi.org/10.1016/j.procs.2017.06.038

[2] Cormen, T. H. (Ed.). (2009). Introduction to algorithms (3rd ed). MIT Press.

[3] Zvelebil, M. J., & Baum, J. O. (2008). Understanding bioinformatics. Garland Science.

Join thousands of data leaders on the AI newsletter. Join over 80,000 subscribers and keep up to date with the latest developments in AI. From research to projects and ideas. If you are building an AI startup, an AI-related product, or a service, we invite you to consider becoming a sponsor.

Published via Towards AI

Feedback ↓

Sign Up for the Course
`; } else { console.error('Element with id="subscribe" not found within the page with class "home".'); } } }); // Remove duplicate text from articles /* Backup: 09/11/24 function removeDuplicateText() { const elements = document.querySelectorAll('h1, h2, h3, h4, h5, strong'); // Select the desired elements const seenTexts = new Set(); // A set to keep track of seen texts const tagCounters = {}; // Object to track instances of each tag elements.forEach(el => { const tagName = el.tagName.toLowerCase(); // Get the tag name (e.g., 'h1', 'h2', etc.) // Initialize a counter for each tag if not already done if (!tagCounters[tagName]) { tagCounters[tagName] = 0; } // Only process the first 10 elements of each tag type if (tagCounters[tagName] >= 2) { return; // Skip if the number of elements exceeds 10 } const text = el.textContent.trim(); // Get the text content const words = text.split(/\s+/); // Split the text into words if (words.length >= 4) { // Ensure at least 4 words const significantPart = words.slice(0, 5).join(' '); // Get first 5 words for matching // Check if the text (not the tag) has been seen before if (seenTexts.has(significantPart)) { // console.log('Duplicate found, removing:', el); // Log duplicate el.remove(); // Remove duplicate element } else { seenTexts.add(significantPart); // Add the text to the set } } tagCounters[tagName]++; // Increment the counter for this tag }); } removeDuplicateText(); */ // Remove duplicate text from articles function removeDuplicateText() { const elements = document.querySelectorAll('h1, h2, h3, h4, h5, strong'); // Select the desired elements const seenTexts = new Set(); // A set to keep track of seen texts const tagCounters = {}; // Object to track instances of each tag // List of classes to be excluded const excludedClasses = ['medium-author', 'post-widget-title']; elements.forEach(el => { // Skip elements with any of the excluded classes if (excludedClasses.some(cls => el.classList.contains(cls))) { return; // Skip this element if it has any of the excluded classes } const tagName = el.tagName.toLowerCase(); // Get the tag name (e.g., 'h1', 'h2', etc.) // Initialize a counter for each tag if not already done if (!tagCounters[tagName]) { tagCounters[tagName] = 0; } // Only process the first 10 elements of each tag type if (tagCounters[tagName] >= 10) { return; // Skip if the number of elements exceeds 10 } const text = el.textContent.trim(); // Get the text content const words = text.split(/\s+/); // Split the text into words if (words.length >= 4) { // Ensure at least 4 words const significantPart = words.slice(0, 5).join(' '); // Get first 5 words for matching // Check if the text (not the tag) has been seen before if (seenTexts.has(significantPart)) { // console.log('Duplicate found, removing:', el); // Log duplicate el.remove(); // Remove duplicate element } else { seenTexts.add(significantPart); // Add the text to the set } } tagCounters[tagName]++; // Increment the counter for this tag }); } removeDuplicateText(); //Remove unnecessary text in blog excerpts document.querySelectorAll('.blog p').forEach(function(paragraph) { // Replace the unwanted text pattern for each paragraph paragraph.innerHTML = paragraph.innerHTML .replace(/Author\(s\): [\w\s]+ Originally published on Towards AI\.?/g, '') // Removes 'Author(s): XYZ Originally published on Towards AI' .replace(/This member-only story is on us\. Upgrade to access all of Medium\./g, ''); // Removes 'This member-only story...' }); //Load ionic icons and cache them if ('localStorage' in window && window['localStorage'] !== null) { const cssLink = 'https://code.ionicframework.com/ionicons/2.0.1/css/ionicons.min.css'; const storedCss = localStorage.getItem('ionicons'); if (storedCss) { loadCSS(storedCss); } else { fetch(cssLink).then(response => response.text()).then(css => { localStorage.setItem('ionicons', css); loadCSS(css); }); } } function loadCSS(css) { const style = document.createElement('style'); style.innerHTML = css; document.head.appendChild(style); } //Remove elements from imported content automatically function removeStrongFromHeadings() { const elements = document.querySelectorAll('h1, h2, h3, h4, h5, h6, span'); elements.forEach(el => { const strongTags = el.querySelectorAll('strong'); strongTags.forEach(strongTag => { while (strongTag.firstChild) { strongTag.parentNode.insertBefore(strongTag.firstChild, strongTag); } strongTag.remove(); }); }); } removeStrongFromHeadings(); "use strict"; window.onload = () => { /* //This is an object for each category of subjects and in that there are kewords and link to the keywods let keywordsAndLinks = { //you can add more categories and define their keywords and add a link ds: { keywords: [ //you can add more keywords here they are detected and replaced with achor tag automatically 'data science', 'Data science', 'Data Science', 'data Science', 'DATA SCIENCE', ], //we will replace the linktext with the keyword later on in the code //you can easily change links for each category here //(include class="ml-link" and linktext) link: 'linktext', }, ml: { keywords: [ //Add more keywords 'machine learning', 'Machine learning', 'Machine Learning', 'machine Learning', 'MACHINE LEARNING', ], //Change your article link (include class="ml-link" and linktext) link: 'linktext', }, ai: { keywords: [ 'artificial intelligence', 'Artificial intelligence', 'Artificial Intelligence', 'artificial Intelligence', 'ARTIFICIAL INTELLIGENCE', ], //Change your article link (include class="ml-link" and linktext) link: 'linktext', }, nl: { keywords: [ 'NLP', 'nlp', 'natural language processing', 'Natural Language Processing', 'NATURAL LANGUAGE PROCESSING', ], //Change your article link (include class="ml-link" and linktext) link: 'linktext', }, des: { keywords: [ 'data engineering services', 'Data Engineering Services', 'DATA ENGINEERING SERVICES', ], //Change your article link (include class="ml-link" and linktext) link: 'linktext', }, td: { keywords: [ 'training data', 'Training Data', 'training Data', 'TRAINING DATA', ], //Change your article link (include class="ml-link" and linktext) link: 'linktext', }, ias: { keywords: [ 'image annotation services', 'Image annotation services', 'image Annotation services', 'image annotation Services', 'Image Annotation Services', 'IMAGE ANNOTATION SERVICES', ], //Change your article link (include class="ml-link" and linktext) link: 'linktext', }, l: { keywords: [ 'labeling', 'labelling', ], //Change your article link (include class="ml-link" and linktext) link: 'linktext', }, pbp: { keywords: [ 'previous blog posts', 'previous blog post', 'latest', ], //Change your article link (include class="ml-link" and linktext) link: 'linktext', }, mlc: { keywords: [ 'machine learning course', 'machine learning class', ], //Change your article link (include class="ml-link" and linktext) link: 'linktext', }, }; //Articles to skip let articleIdsToSkip = ['post-2651', 'post-3414', 'post-3540']; //keyword with its related achortag is recieved here along with article id function searchAndReplace(keyword, anchorTag, articleId) { //selects the h3 h4 and p tags that are inside of the article let content = document.querySelector(`#${articleId} .entry-content`); //replaces the "linktext" in achor tag with the keyword that will be searched and replaced let newLink = anchorTag.replace('linktext', keyword); //regular expression to search keyword var re = new RegExp('(' + keyword + ')', 'g'); //this replaces the keywords in h3 h4 and p tags content with achor tag content.innerHTML = content.innerHTML.replace(re, newLink); } function articleFilter(keyword, anchorTag) { //gets all the articles var articles = document.querySelectorAll('article'); //if its zero or less then there are no articles if (articles.length > 0) { for (let x = 0; x < articles.length; x++) { //articles to skip is an array in which there are ids of articles which should not get effected //if the current article's id is also in that array then do not call search and replace with its data if (!articleIdsToSkip.includes(articles[x].id)) { //search and replace is called on articles which should get effected searchAndReplace(keyword, anchorTag, articles[x].id, key); } else { console.log( `Cannot replace the keywords in article with id ${articles[x].id}` ); } } } else { console.log('No articles found.'); } } let key; //not part of script, added for (key in keywordsAndLinks) { //key is the object in keywords and links object i.e ds, ml, ai for (let i = 0; i < keywordsAndLinks[key].keywords.length; i++) { //keywordsAndLinks[key].keywords is the array of keywords for key (ds, ml, ai) //keywordsAndLinks[key].keywords[i] is the keyword and keywordsAndLinks[key].link is the link //keyword and link is sent to searchreplace where it is then replaced using regular expression and replace function articleFilter( keywordsAndLinks[key].keywords[i], keywordsAndLinks[key].link ); } } function cleanLinks() { // (making smal functions is for DRY) this function gets the links and only keeps the first 2 and from the rest removes the anchor tag and replaces it with its text function removeLinks(links) { if (links.length > 1) { for (let i = 2; i < links.length; i++) { links[i].outerHTML = links[i].textContent; } } } //arrays which will contain all the achor tags found with the class (ds-link, ml-link, ailink) in each article inserted using search and replace let dslinks; let mllinks; let ailinks; let nllinks; let deslinks; let tdlinks; let iaslinks; let llinks; let pbplinks; let mlclinks; const content = document.querySelectorAll('article'); //all articles content.forEach((c) => { //to skip the articles with specific ids if (!articleIdsToSkip.includes(c.id)) { //getting all the anchor tags in each article one by one dslinks = document.querySelectorAll(`#${c.id} .entry-content a.ds-link`); mllinks = document.querySelectorAll(`#${c.id} .entry-content a.ml-link`); ailinks = document.querySelectorAll(`#${c.id} .entry-content a.ai-link`); nllinks = document.querySelectorAll(`#${c.id} .entry-content a.ntrl-link`); deslinks = document.querySelectorAll(`#${c.id} .entry-content a.des-link`); tdlinks = document.querySelectorAll(`#${c.id} .entry-content a.td-link`); iaslinks = document.querySelectorAll(`#${c.id} .entry-content a.ias-link`); mlclinks = document.querySelectorAll(`#${c.id} .entry-content a.mlc-link`); llinks = document.querySelectorAll(`#${c.id} .entry-content a.l-link`); pbplinks = document.querySelectorAll(`#${c.id} .entry-content a.pbp-link`); //sending the anchor tags list of each article one by one to remove extra anchor tags removeLinks(dslinks); removeLinks(mllinks); removeLinks(ailinks); removeLinks(nllinks); removeLinks(deslinks); removeLinks(tdlinks); removeLinks(iaslinks); removeLinks(mlclinks); removeLinks(llinks); removeLinks(pbplinks); } }); } //To remove extra achor tags of each category (ds, ml, ai) and only have 2 of each category per article cleanLinks(); */ //Recommended Articles var ctaLinks = [ /* ' ' + '

Subscribe to our AI newsletter!

' + */ '

Take our 85+ lesson From Beginner to Advanced LLM Developer Certification: From choosing a project to deploying a working product this is the most comprehensive and practical LLM course out there!

'+ '

Towards AI has published Building LLMs for Production—our 470+ page guide to mastering LLMs with practical projects and expert insights!

' + '
' + '' + '' + '

Note: Content contains the views of the contributing authors and not Towards AI.
Disclosure: This website may contain sponsored content and affiliate links.

' + 'Discover Your Dream AI Career at Towards AI Jobs' + '

Towards AI has built a jobs board tailored specifically to Machine Learning and Data Science Jobs and Skills. Our software searches for live AI jobs each hour, labels and categorises them and makes them easily searchable. Explore over 10,000 live jobs today with Towards AI Jobs!

' + '
' + '

🔥 Recommended Articles 🔥

' + 'Why Become an LLM Developer? Launching Towards AI’s New One-Stop Conversion Course'+ 'Testing Launchpad.sh: A Container-based GPU Cloud for Inference and Fine-tuning'+ 'The Top 13 AI-Powered CRM Platforms
' + 'Top 11 AI Call Center Software for 2024
' + 'Learn Prompting 101—Prompt Engineering Course
' + 'Explore Leading Cloud Providers for GPU-Powered LLM Training
' + 'Best AI Communities for Artificial Intelligence Enthusiasts
' + 'Best Workstations for Deep Learning
' + 'Best Laptops for Deep Learning
' + 'Best Machine Learning Books
' + 'Machine Learning Algorithms
' + 'Neural Networks Tutorial
' + 'Best Public Datasets for Machine Learning
' + 'Neural Network Types
' + 'NLP Tutorial
' + 'Best Data Science Books
' + 'Monte Carlo Simulation Tutorial
' + 'Recommender System Tutorial
' + 'Linear Algebra for Deep Learning Tutorial
' + 'Google Colab Introduction
' + 'Decision Trees in Machine Learning
' + 'Principal Component Analysis (PCA) Tutorial
' + 'Linear Regression from Zero to Hero
'+ '

', /* + '

Join thousands of data leaders on the AI newsletter. It’s free, we don’t spam, and we never share your email address. Keep up to date with the latest work in AI. From research to projects and ideas. If you are building an AI startup, an AI-related product, or a service, we invite you to consider becoming a sponsor.

',*/ ]; var replaceText = { '': '', '': '', '
': '
' + ctaLinks + '
', }; Object.keys(replaceText).forEach((txtorig) => { //txtorig is the key in replacetext object const txtnew = replaceText[txtorig]; //txtnew is the value of the key in replacetext object let entryFooter = document.querySelector('article .entry-footer'); if (document.querySelectorAll('.single-post').length > 0) { //console.log('Article found.'); const text = entryFooter.innerHTML; entryFooter.innerHTML = text.replace(txtorig, txtnew); } else { // console.log('Article not found.'); //removing comment 09/04/24 } }); var css = document.createElement('style'); css.type = 'text/css'; css.innerHTML = '.post-tags { display:none !important } .article-cta a { font-size: 18px; }'; document.body.appendChild(css); //Extra //This function adds some accessibility needs to the site. function addAlly() { // In this function JQuery is replaced with vanilla javascript functions const imgCont = document.querySelector('.uw-imgcont'); imgCont.setAttribute('aria-label', 'AI news, latest developments'); imgCont.title = 'AI news, latest developments'; imgCont.rel = 'noopener'; document.querySelector('.page-mobile-menu-logo a').title = 'Towards AI Home'; document.querySelector('a.social-link').rel = 'noopener'; document.querySelector('a.uw-text').rel = 'noopener'; document.querySelector('a.uw-w-branding').rel = 'noopener'; document.querySelector('.blog h2.heading').innerHTML = 'Publication'; const popupSearch = document.querySelector$('a.btn-open-popup-search'); popupSearch.setAttribute('role', 'button'); popupSearch.title = 'Search'; const searchClose = document.querySelector('a.popup-search-close'); searchClose.setAttribute('role', 'button'); searchClose.title = 'Close search page'; // document // .querySelector('a.btn-open-popup-search') // .setAttribute( // 'href', // 'https://medium.com/towards-artificial-intelligence/search' // ); } // Add external attributes to 302 sticky and editorial links function extLink() { // Sticky 302 links, this fuction opens the link we send to Medium on a new tab and adds a "noopener" rel to them var stickyLinks = document.querySelectorAll('.grid-item.sticky a'); for (var i = 0; i < stickyLinks.length; i++) { /* stickyLinks[i].setAttribute('target', '_blank'); stickyLinks[i].setAttribute('rel', 'noopener'); */ } // Editorial 302 links, same here var editLinks = document.querySelectorAll( '.grid-item.category-editorial a' ); for (var i = 0; i < editLinks.length; i++) { editLinks[i].setAttribute('target', '_blank'); editLinks[i].setAttribute('rel', 'noopener'); } } // Add current year to copyright notices document.getElementById( 'js-current-year' ).textContent = new Date().getFullYear(); // Call functions after page load extLink(); //addAlly(); setTimeout(function() { //addAlly(); //ideally we should only need to run it once ↑ }, 5000); }; function closeCookieDialog (){ document.getElementById("cookie-consent").style.display = "none"; return false; } setTimeout ( function () { closeCookieDialog(); }, 15000); console.log(`%c 🚀🚀🚀 ███ █████ ███████ █████████ ███████████ █████████████ ███████████████ ███████ ███████ ███████ ┌───────────────────────────────────────────────────────────────────┐ │ │ │ Towards AI is looking for contributors! │ │ Join us in creating awesome AI content. │ │ Let's build the future of AI together → │ │ https://towardsai.net/contribute │ │ │ └───────────────────────────────────────────────────────────────────┘ `, `background: ; color: #00adff; font-size: large`); //Remove latest category across site document.querySelectorAll('a[rel="category tag"]').forEach(function(el) { if (el.textContent.trim() === 'Latest') { // Remove the two consecutive spaces (  ) if (el.nextSibling && el.nextSibling.nodeValue.includes('\u00A0\u00A0')) { el.nextSibling.nodeValue = ''; // Remove the spaces } el.style.display = 'none'; // Hide the element } }); // Add cross-domain measurement, anonymize IPs 'use strict'; //var ga = gtag; ga('config', 'G-9D3HKKFV1Q', 'auto', { /*'allowLinker': true,*/ 'anonymize_ip': true/*, 'linker': { 'domains': [ 'medium.com/towards-artificial-intelligence', 'datasets.towardsai.net', 'rss.towardsai.net', 'feed.towardsai.net', 'contribute.towardsai.net', 'members.towardsai.net', 'pub.towardsai.net', 'news.towardsai.net' ] } */ }); ga('send', 'pageview'); -->