|
|
(6 intermediate revisions by the same user not shown) |
Line 33: |
Line 33: |
| <div id="truePage" class="realPage"> | | <div id="truePage" class="realPage"> |
| <div id="firstnav" class="ui fixed collapsed borderless ten menu"> | | <div id="firstnav" class="ui fixed collapsed borderless ten menu"> |
− | <a id="sdin-link" href="#"> | + | <a id="sdin-link" href="http://sdin.sysusoftware.info" target="_blank"> |
| <img id="sdin-icon" src="https://static.igem.org/mediawiki/2017/1/17/T--SYSU-Software--project_sdin-small.png" alt="logo"> | | <img id="sdin-icon" src="https://static.igem.org/mediawiki/2017/1/17/T--SYSU-Software--project_sdin-small.png" alt="logo"> |
| </a> | | </a> |
− |
| |
| <div class="ui simple dropdown item page-nav"> | | <div class="ui simple dropdown item page-nav"> |
| <a href="https://2017.igem.org/Team:SYSU-Software/Project" class="page-link">Project</a> | | <a href="https://2017.igem.org/Team:SYSU-Software/Project" class="page-link">Project</a> |
Line 42: |
Line 41: |
| <a href="https://2017.igem.org/Team:SYSU-Software/Project#description" class="item">Description</a> | | <a href="https://2017.igem.org/Team:SYSU-Software/Project#description" class="item">Description</a> |
| <a href="https://2017.igem.org/Team:SYSU-Software/Project#applied-design" class="item">Applied Design</a> | | <a href="https://2017.igem.org/Team:SYSU-Software/Project#applied-design" class="item">Applied Design</a> |
− | <a href="https://2017.igem.org/Team:SYSU-Software/Project#feature" class="item">Features</a>
| |
| <a href="https://2017.igem.org/Team:SYSU-Software/Project#wet-lab" class="item">Wet-Lab Validation</a> | | <a href="https://2017.igem.org/Team:SYSU-Software/Project#wet-lab" class="item">Wet-Lab Validation</a> |
| <a href="https://2017.igem.org/Team:SYSU-Software/Project#demonstrate" class="item">Demonstrate</a> | | <a href="https://2017.igem.org/Team:SYSU-Software/Project#demonstrate" class="item">Demonstrate</a> |
Line 56: |
Line 54: |
| </div> | | </div> |
| </div> | | </div> |
| + | |
| <div class="ui simple dropdown item page-nav"> | | <div class="ui simple dropdown item page-nav"> |
− | <a href="https://2017.igem.org/Team:SYSU-Software/Medal" class="page-link">Medals</a>
| + | <a href="https://2017.igem.org/wiki/index.php?title=Team:SYSU-Software/HP" class="page-link">Human Practices</a> |
− | <div class="menu page-category">
| + | |
− | <a href="https://2017.igem.org/Team:SYSU-Software/Medal#overview" class="item">Overview</a>
| + | |
− | <a href="https://2017.igem.org/Team:SYSU-Software/Medal#bronze" class="item">Bronze</a>
| + | |
− | <a href="https://2017.igem.org/Team:SYSU-Software/Medal#silver" class="item">Silver</a>
| + | |
− | <a href="https://2017.igem.org/Team:SYSU-Software/Medal#gold" class="item">Gold</a>
| + | |
− | </div>
| + | |
− | </div>
| + | |
− | <div class="ui simple dropdown item page-nav">
| + | |
− | <a href="https://2017.igem.org/wiki/index.php?title=Team:SYSU-Software/HP" class="page-link">Human Practice</a> | + | |
| <div class="menu page-category"> | | <div class="menu page-category"> |
| <a href="https://2017.igem.org/wiki/index.php?title=Team:SYSU-Software/HP#overview_id" class="item">Overview</a> | | <a href="https://2017.igem.org/wiki/index.php?title=Team:SYSU-Software/HP#overview_id" class="item">Overview</a> |
Line 76: |
Line 66: |
| </div> | | </div> |
| <div class="ui simple dropdown item page-nav"> | | <div class="ui simple dropdown item page-nav"> |
− | <a href="https://2017.igem.org/Team:SYSU-Software/Collaborations" class="page-link">Collaboration</a> | + | <a href="https://2017.igem.org/Team:SYSU-Software/Collaborations" class="page-link">Collaborations</a> |
| <div class="menu page-category"> | | <div class="menu page-category"> |
| <a href="https://2017.igem.org/Team:SYSU-Software/Collaborations#overview" class="item">Overview</a> | | <a href="https://2017.igem.org/Team:SYSU-Software/Collaborations#overview" class="item">Overview</a> |
| <a href="https://2017.igem.org/Team:SYSU-Software/Collaborations#scut-china-a" class="item">SCUT-CHINA-A</a> | | <a href="https://2017.igem.org/Team:SYSU-Software/Collaborations#scut-china-a" class="item">SCUT-CHINA-A</a> |
| <a href="https://2017.igem.org/Team:SYSU-Software/Collaborations#nju-china" class="item">NJU-China</a> | | <a href="https://2017.igem.org/Team:SYSU-Software/Collaborations#nju-china" class="item">NJU-China</a> |
− | <a href="https://2017.igem.org/Team:SYSU-Software/Collaborations#hkust" class="item">HUKST</a> | + | <a href="https://2017.igem.org/Team:SYSU-Software/Collaborations#hkust" class="item">Hong_Kong_HKUST</a> |
| <a href="https://2017.igem.org/Team:SYSU-Software/Collaborations#sysu-china" class="item">SYSU-CHINA</a> | | <a href="https://2017.igem.org/Team:SYSU-Software/Collaborations#sysu-china" class="item">SYSU-CHINA</a> |
| <a href="https://2017.igem.org/Team:SYSU-Software/Collaborations#scau-china" class="item">SCAU-CHINA</a> | | <a href="https://2017.igem.org/Team:SYSU-Software/Collaborations#scau-china" class="item">SCAU-CHINA</a> |
Line 122: |
Line 112: |
| <a href="https://2017.igem.org/Team:SYSU-Software/Team#instructors" class="item">Instructors</a> | | <a href="https://2017.igem.org/Team:SYSU-Software/Team#instructors" class="item">Instructors</a> |
| <a href="https://2017.igem.org/Team:SYSU-Software/Team#notebook" class="item">Notebook</a> | | <a href="https://2017.igem.org/Team:SYSU-Software/Team#notebook" class="item">Notebook</a> |
| + | </div> |
| + | </div> |
| + | <div class="ui simple dropdown item page-nav"> |
| + | <a href="https://2017.igem.org/Team:SYSU-Software/Medal" class="page-link">Medal</a> |
| + | <div class="menu page-category"> |
| + | <a href="https://2017.igem.org/Team:SYSU-Software/Medal#overview" class="item">Overview</a> |
| + | <a href="https://2017.igem.org/Team:SYSU-Software/Medal#bronze" class="item">Bronze</a> |
| + | <a href="https://2017.igem.org/Team:SYSU-Software/Medal#silver" class="item">Silver</a> |
| + | <a href="https://2017.igem.org/Team:SYSU-Software/Medal#gold" class="item">Gold</a> |
| </div> | | </div> |
| </div> | | </div> |
Line 167: |
Line 166: |
| <p>The reason why we use Word2vec is that it can distinguish the semantic meanings of words accurately by Deep Learning technique, which outperforms the traditional semantic analysis methods greatly.</p> | | <p>The reason why we use Word2vec is that it can distinguish the semantic meanings of words accurately by Deep Learning technique, which outperforms the traditional semantic analysis methods greatly.</p> |
| </div> | | </div> |
− | <h4>KD Tree Algorithm</h4> | + | <h4>KD Tree Algorithm</h4></br> |
− | <img class="ui image medium centered" src="https://static.igem.org/mediawiki/2017/1/17/T--SYSU-Software--model_kd.png"> | + | <img class="ui image medium centered" src="https://static.igem.org/mediawiki/2017/1/17/T--SYSU-Software--model_kd.png"></br> |
| <div class="paragraph"> | | <div class="paragraph"> |
| <p>The KD Tree algorithm is rather efficient when searching for the most similar items with averaged time complexity<code>O(log(n))</code>,thus the users can get recommendation instantly after they enter their interested new word to our system.</p> | | <p>The KD Tree algorithm is rather efficient when searching for the most similar items with averaged time complexity<code>O(log(n))</code>,thus the users can get recommendation instantly after they enter their interested new word to our system.</p> |
Line 188: |
Line 187: |
| </div> | | </div> |
| <h4>Random Walk with Restart Algorithm</h4> | | <h4>Random Walk with Restart Algorithm</h4> |
− | <img src="https://static.igem.org/mediawiki/2017/c/c0/T--SYSU-Software--modeling_part-keyword.png" class="centered" alt="" id="keyword-part-img"> | + | <img src="https://static.igem.org/mediawiki/2017/8/89/T--SYSU-Software--model_keywordandpart.png" class="centered" alt="" id="keyword-part-img"> |
| <p>Random Walk with Restart(RWR) is an algorithm adapted from the PageRank algorithm and it focuses on characterizing the affiliation between each item. We treat the relation between key words and genetic parts as an undirected graph where nodes represent key words or parts and edges represent connection between words and parts. Imagine there is a walker travelling on the graph mentioned above and each time he faces two choices: 1) Randomly travelling along an edge connected to the current node. 2) Teleport to node K. After a long time of random travelling , the frequency the walker reaches each node represents the affiliation between each node and node K , which we use to characterize the relation between key words and parts. For more detailed mathematical formulation of PageRank, see: <a href="https://en.wikipedia.org/wiki/PageRank" target="_blank">wiki page of page rank</a></p> | | <p>Random Walk with Restart(RWR) is an algorithm adapted from the PageRank algorithm and it focuses on characterizing the affiliation between each item. We treat the relation between key words and genetic parts as an undirected graph where nodes represent key words or parts and edges represent connection between words and parts. Imagine there is a walker travelling on the graph mentioned above and each time he faces two choices: 1) Randomly travelling along an edge connected to the current node. 2) Teleport to node K. After a long time of random travelling , the frequency the walker reaches each node represents the affiliation between each node and node K , which we use to characterize the relation between key words and parts. For more detailed mathematical formulation of PageRank, see: <a href="https://en.wikipedia.org/wiki/PageRank" target="_blank">wiki page of page rank</a></p> |
| | | |
Line 245: |
Line 244: |
| <p>let <code>T</code> denotes the set of word vectors</p> | | <p>let <code>T</code> denotes the set of word vectors</p> |
| <p><code>for</code> keyword <code>i</code> in <code>1 to N</code>:</p> | | <p><code>for</code> keyword <code>i</code> in <code>1 to N</code>:</p> |
− | <p><code>T</code>.append(<img id="normalize-i" class="inlined-formula" src="https://static.igem.org/mediawiki/2017/6/64/T--SYSU-Software--modeling_normalize-i.png" alt="f(i)/|f(i)|">)</p> | + | <p><code>T</code>.append \( \frac{f(i)}{|f(i)|_2} \)</p> |
| </div> | | </div> |
| <h5>Build KD Tree</h5> | | <h5>Build KD Tree</h5> |
Line 263: |
Line 262: |
| <h5>Make Recommendation</h5> | | <h5>Make Recommendation</h5> |
| <div class="paragraph"> | | <div class="paragraph"> |
− | <p>We have calculated the affiliation between key words and parts which shall be used to guide our final recommendation. Let <code>p<sub>i</sub></code> denotes the connection between the <code>i</code>th part and the current word <code>k</code> , we calculate <code>p<sub>i</sub></code> by formula $$p_i=\sum^K_{n=1}\frac{\text{Affiliation}(w_n,p_i)}{\text{distance}(w_n,k)+\text{bias}}$$ | + | <p>We have calculated the affiliation between key words and parts which shall be used to guide our final recommendation. Let <code>p<sub>i</sub></code> denotes the connection between the <code>i</code>the part and the current word <code>k</code> , we calculate <code>p<sub>i</sub></code> by formula $$p_i=\sum^K_{n=1}\frac{\text{Affiliation}(w_n,p_i)}{\text{distance}(w_n,k)+\text{bias}}$$ |
| </p> | | </p> |
| | | |
− | <p>where <img src="https://static.igem.org/mediawiki/2017/f/f1/T--SYSU-Software--modeling_wn.png" alt="" class="inlined-formula"> denotes the <code>k</code> most similar key words</p> | + | <p>where \( \{w_n|n=1,2,...,K\}\) denotes the <code>k</code> most similar key words</p> |
| <p><code>Affiliation(w<sub>n</sub>, p<sub>i</sub>)</code>denotes the connection between <code>w<sub>i</sub></code> and the <code>i</code>th part and <code>distance(w<sub>i</sub>, k)</code> denotes the the Euclidean distance between the normalized word vectors of <code>w<sub>n</sub></code> and word <code>k</code>.</p> | | <p><code>Affiliation(w<sub>n</sub>, p<sub>i</sub>)</code>denotes the connection between <code>w<sub>i</sub></code> and the <code>i</code>th part and <code>distance(w<sub>i</sub>, k)</code> denotes the the Euclidean distance between the normalized word vectors of <code>w<sub>n</sub></code> and word <code>k</code>.</p> |
− | <p>After the computation of <img src="https://static.igem.org/mediawiki/2017/0/00/T--SYSU-Software--modeling_pi.png" alt="" class="inlined-formula">, we use heap sort algorithm to get <code>R</code> highest <code>p<sub>i</sub></code> and recommend to the users the corresponding parts.Besides, we use exactly the same strategy to make recommendation of related projects to the users. For simplicity, we ignore the details here.</p> | + | <p>After the computation of \(\{p_i|i=1,2,...,m\}\), we use heap sort algorithm to get <code>R</code> highest <code>p<sub>i</sub></code> and recommend to the users the corresponding parts.Besides, we use exactly the same strategy to make recommendation of related projects to the users. For simplicity, we ignore the details here.</p> |
| </div> | | </div> |
| </section> | | </section> |
Line 288: |
Line 287: |
| | | |
| <p>Therefore , the <code>j</code>th column records all the impacts the system exerts to the <code>j</code>th substances.</p> | | <p>Therefore , the <code>j</code>th column records all the impacts the system exerts to the <code>j</code>th substances.</p> |
− | <p>Let <code>x<sub>j</sub>(t)</code> denotes the concentration of substance <code>j</code> at time <code>t</code> , then we use the following ODE to characterize <code>x<sub>j</sub>(t)</code> for <img src="https://static.igem.org/mediawiki/2017/5/51/T--SYSU-Software--modeling_j-1-to-n.png" alt="" class="inlined-formula"></p> | + | <p>Let <code>x<sub>j</sub>(t)</code> denotes the concentration of substance <code>j</code> at time <code>t</code> , then we use the following ODE to characterize <code>x<sub>j</sub>(t)</code> for \(j\in\{1,2,...n\}\) |
− | <img src="https://static.igem.org/mediawiki/2017/d/d2/T--SYSU-Software--modeling_longest.png" id="longest-img" alt="" class="centered formula"> | + | $$ \frac{\mathbb{d}x_j(t)}{\mathbb{d}t} = \prod_{i=1}^n\{ \frac{R_{ij}(R_{ij}+1)}{2}f(x_i(t))+\frac{(R_{ij}+1)(R_{ij}-1)}{-1}+\frac{R_{ij}(R_{ij}-1)}{2}g(x_i(t))\}- \beta \times x_j(t) |
− | <p>where β represents the degradation rate and:</p> | + | $$ |
− | <img src="https://static.igem.org/mediawiki/2017/8/86/T--SYSU-Software--modeling_fx-gx.png" id="fx-gx-img" alt="" class="centered formula"> | + | </p> |
− | <p></p> | + | |
| + | <p>where β represents the degradation rate and: |
| + | $$ f(x)=1+\frac{1}{1+\mathbb{e}^{-x}}; f(x)=1-\frac{1}{1+\mathbb{e}^{-x}} $$ |
| + | </p> |
| + | |
| <h3>Imlementation</h3> | | <h3>Imlementation</h3> |
− | <p>We use Scipy, an efficient open source numerical module in Python, to give the numerical solutions to the ODE system. Specifically, we use the odeint function in Scipy. For more information about odeint function, see <a href=" https://docs.scipy.org/doc/scipy/reference/generated/scipy.integrate.odeint.html" target="_blank">documentation of scipy</a></p> | + | <p>We use Scipy, an efficient open source numerical module in Python, to give the numerical solutions to the ODE system. Specifically, we use the odeint function in Scipy. For more information about odeint function, see <a href=" https://docs.scipy.org/doc/scipy/reference/generated/scipy.integrate.odeint.html" target="_blank">documentation of scipy</a>.</p> |
| </div> | | </div> |
| </section> | | </section> |