<div dir="ltr"><div class="gmail_default" style="font-family:monospace,monospace">@Tommaso, this is something like Internal Coordinates[1], right?</div><div class="gmail_default" style="font-family:monospace,monospace">@Bill, thanks for the hint, I'll definitely take a look at this.</div><div class="gmail_default" style="font-family:monospace,monospace"><br></div><div class="gmail_default" style="font-family:monospace,monospace">[1] - <a href="https://en.wikipedia.org/wiki/Z-matrix_(chemistry)">https://en.wikipedia.org/wiki/Z-matrix_(chemistry)</a></div></div><div class="gmail_extra"><br><div class="gmail_quote">On Tue, Mar 28, 2017 at 2:12 AM, Bill Ross <span dir="ltr"><<a href="mailto:ross@cgl.ucsf.edu" target="_blank">ross@cgl.ucsf.edu</a>></span> wrote:<br><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">
  
    
  
  <div bgcolor="#FFFFFF" text="#000000">
    <p>Image processing deals with xy coordinates by (as I understand)
      training with multiple permutations of the raw data, in the form
      of translations and rotations in the 2d space. If training with 3d
      data, there would be that much more translating and rotating to
      do, in order to divorce the learning from the incidentals.</p><span class="HOEnZb"><font color="#888888">
    <p>Bill<br>
    </p></font></span><div><div class="h5">
    <br>
    <div class="m_-7569063688226978064moz-cite-prefix">On 3/27/17 4:35 PM, Tommaso Costanzo
      wrote:<br>
    </div>
    <blockquote type="cite">
      <div dir="ltr">
        <div>
          <div>
            <div>
              <div>
                <div>
                  <div>
                    <div>
                      <div>
                        <div>Dear Henrique,<br>
                        </div>
                        I am sorry for the poor email I wrote before.
                        What I was saying is simply the fact that if you
                        are trying to use the coordinates as "features"
                        from an .xyz file then by machine learning you
                        will learn at wich coordinate certain atoms will
                        occur so you can only make prediction on the
                        coordinate. However, if I correctly understood,
                        the "features" representing the coupling J are
                        distance, angle, and electron number. Definitely
                        this properties can be derived from the XYZ file
                        format from simple geometric calculations and
                        the number of electrons will depend from the
                        type of atom. So, what I was trying to say is
                        that instead of using the XYZ file as input for
                        scikit-learn, I was suggesting to do the
                        calculation of angle, distances, electrons'
                        number in advance (with other software(s) or
                        directly in python)  and use the new calculated
                        matrix as input for scikit-learn. In this case
                        the machine will learn how J(AB) varies as a
                        function of angle, distance, number of
                        electrons. <br>
                      </div>
                      For example <br>
                    </div>
                    <br>
                    distance     angle   n el.<br>
                    1                  90      1<br>
                    1                  90      1<br>
                    2                  90      1<br>
                    ....                ...        ...<br>
                    <br>
                  </div>
                  If you are using a supervised learning you will have
                  to add a 4th column ( in reality a separate column
                  vector) with your J(AB) on which you can train your
                  model and then predict the unknown samples<br>
                  <br>
                </div>
                For example <br>
                distance     angle   n el.    J(AB)<br>
                1                  90      1        1<br>
                1                  90      1        1<br>
                2                  90      1         0.5<br>
                ....                ...        ...       ...<br>
                <br>
              </div>
              <div>Now if you train the model on the second matrix, and
                then you try to predict the first one you should expect
                a results like:<br>
                <br>
                1<br>
                1<br>
                0.5<br>
                <br>
              </div>
              Of course in this case the "features" are perfectly equal,
              hence the example is completely unrealistic. However, I
              hope that it will help to understand what I was explaining
              in the previous email.<br>
              If you want you can directly contact me at this email, and
              I hope that you got additional hints from Robert, that he
              seems to be even more knowledgeable than me.<br>
            </div>
            <br>
          </div>
          Sincerely <br>
        </div>
        Tommaso<br>
        <div>
          <div><br>
            <div><br>
            </div>
          </div>
        </div>
      </div>
      <div class="gmail_extra"><br>
        <div class="gmail_quote">2017-03-27 18:44 GMT-04:00 Henrique C.
          S. Junior <span dir="ltr"><<a href="mailto:henriquecsj@gmail.com" target="_blank">henriquecsj@gmail.com</a>></span>:<br>
          <blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">
            <div dir="ltr">
              <div class="gmail_default" style="font-family:monospace,monospace">Dear Tommaso,
                thank you for your kind reply.</div>
              <div class="gmail_default" style="font-family:monospace,monospace">I know I have a
                lot to study before actually starting any code and
                that's why any suggestion is so valuable.</div>
              <div class="gmail_default" style="font-family:monospace,monospace">So, you're
                suggesting that a simplification of the system using
                only the paramagnetic centers can be a good approach?
                (I'm not sure if I understood it correctly).</div>
              <div class="gmail_default" style="font-family:monospace,monospace">My main idea
                was, at first, try to represent the systems as
                realistically as possible (using coordinates). I know
                that the software will not know what a bond is or what
                an intermolecular interaction is but, let's say, after
                including 1000s of examples in the training, I was
                expecting that (as an example) finding a C 0.000 and an
                H at 1.000 should start to "make sense" because it leads
                to an experimental trend. And I totally agree that my
                way to represent the system is not the better.</div>
              <div class="gmail_default" style="font-family:monospace,monospace"><br>
              </div>
              <div class="gmail_default" style="font-family:monospace,monospace">Thank you so
                much for all the help.</div>
            </div>
            <div class="m_-7569063688226978064HOEnZb">
              <div class="m_-7569063688226978064h5">
                <div class="gmail_extra"><br>
                  <div class="gmail_quote">On Mon, Mar 27, 2017 at 4:15
                    PM, Tommaso Costanzo <span dir="ltr"><<a href="mailto:tommaso.costanzo01@gmail.com" target="_blank">tommaso.costanzo01@gmail.com</a>></span>
                    wrote:<br>
                    <blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">
                      <div dir="ltr">
                        <p style="margin:0px;text-indent:0px"><span style="font-family:"ubuntu";font-size:12pt">Dear
                            Henrique,</span></p>
                        <p style="margin:0px;text-indent:0px;font-family:"ubuntu";font-size:12pt"><br>
                        </p>
                        <p style="margin:0px;text-indent:0px"><span style="font-family:"ubuntu";font-size:12pt">I
                            agree with Robert on the use of a supervised
                            algorithm and I would also suggest you to
                            try a semisupervised one if you have trouble
                            in labeling your data. </span></p>
                        <p style="margin:0px;text-indent:0px;font-family:"ubuntu";font-size:12pt"><br>
                        </p>
                        <p style="margin:0px;text-indent:0px"><span style="font-family:"ubuntu";font-size:12pt">Moreover,
                            as a chemist I think that the input you are
                            thinking to use is not the in the best form
                            for machine learning because you are trying
                            to predict coupling J(AB) but in the future
                            space you have only coordinates (XYZ). What
                            I suggest is to generate the pair of atoms
                            externally and then use a matrix of the form
                            (Mx3), where M are the pairs of atoms you
                            want to predict your J and 3 are the
                            features of the two atoms (distance, angle,
                            unpaired electrons). For a supervised
                            approach you will need a training set where
                            the J is know so your training data will be
                            of the form Mx4 and the fourth feature will
                            be the J you know.</span></p>
                        <p style="margin:0px;text-indent:0px"><span style="font-family:"ubuntu";font-size:12pt">Hope
                            that this is clear, if not I will be happy
                            to help more</span></p>
                        <p style="margin:0px;text-indent:0px;font-family:"ubuntu";font-size:12pt"><br>
                        </p>
                        <p style="margin:0px;text-indent:0px"><span style="font-family:"ubuntu";font-size:12pt">Sincerely</span></p>
                        <p style="margin:0px;text-indent:0px"><span style="font-family:"ubuntu";font-size:12pt">Tommaso</span></p>
                      </div>
                      <div class="gmail_extra">
                        <div>
                          <div class="m_-7569063688226978064m_-419284271361902240h5"><br>
                            <div class="gmail_quote">2017-03-27 13:46
                              GMT-04:00 Henrique C. S. Junior <span dir="ltr"><<a href="mailto:henriquecsj@gmail.com" target="_blank">henriquecsj@gmail.com</a>></span>:<br>
                              <blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">
                                <div dir="ltr">
                                  <div class="gmail_default" style="font-family:monospace,monospace">Dear
                                    Robert, thank you. Yes, I'd like to
                                    talk about some specifics on the
                                    project.</div>
                                  <div class="gmail_default" style="font-family:monospace,monospace">Thank
                                    you again.</div>
                                </div>
                                <div class="m_-7569063688226978064m_-419284271361902240m_-8383123951498439579HOEnZb">
                                  <div class="m_-7569063688226978064m_-419284271361902240m_-8383123951498439579h5">
                                    <div class="gmail_extra"><br>
                                      <div class="gmail_quote">On Mon,
                                        Mar 27, 2017 at 2:25 PM, Robert
                                        Slater <span dir="ltr"><<a href="mailto:rdslater@gmail.com" target="_blank">rdslater@gmail.com</a>></span>
                                        wrote:<br>
                                        <blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">
                                          <div dir="ltr">You definitely
                                            can use some of the tools in
                                            sci-kit learn for supervised
                                            machine learning.  The real
                                            trick will be how well your
                                            training system is
                                            representative of your
                                            future predictions.  All of
                                            the various regression
                                            algorithms would be of some
                                            value and you make even
                                            consider an ensemble to help
                                            generalize.  There will be
                                            some important questions to
                                            answer--what kind of loss
                                            function do you want to look
                                            at?  I assumed regression
                                            (continuous response) but it
                                            could also
                                            classify--paramagnetic,
                                            diamagnetic, ferromagnetic,
                                            etc...
                                            <div><br>
                                            </div>
                                            <div>Another task to think
                                              about might be dimension
                                              reduction.</div>
                                            <div>There is no guarantee
                                              you will get fantastic
                                              results--every problem is
                                              unique and much will
                                              depend on exactly what you
                                              want out of the
                                              solution--it may be that
                                              we get '10%' accuracy at
                                              best--for some systems
                                              that is quite good, others
                                              it is horrible.<br>
                                            </div>
                                            <div><br>
                                            </div>
                                            <div>If you'd like to talk
                                              specifics, feel free to
                                              contact me at this email. 
                                              I have a background in
                                              magnetism (PhD in magnetic
                                              multilayers--i was
                                              physics, but as you are
                                              probably aware chemisty
                                              and physics blend in this
                                              area) and have a fairly
                                              good knowledge of sci-kit
                                              learn and machine
                                              learning.  </div>
                                            <div><br>
                                            </div>
                                            <div><br>
                                            </div>
                                          </div>
                                          <div class="gmail_extra"><br>
                                            <div class="gmail_quote">
                                              <div>
                                                <div class="m_-7569063688226978064m_-419284271361902240m_-8383123951498439579m_6033336047822367828h5">On
                                                  Mon, Mar 27, 2017 at
                                                  10:50 AM, Henrique C.
                                                  S. Junior <span dir="ltr"><<a href="mailto:henriquecsj@gmail.com" target="_blank">henriquecsj@gmail.com</a>></span>
                                                  wrote:<br>
                                                </div>
                                              </div>
                                              <blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">
                                                <div>
                                                  <div class="m_-7569063688226978064m_-419284271361902240m_-8383123951498439579m_6033336047822367828h5">
                                                    <div dir="ltr">
                                                      <div class="gmail_default" style="font-family:monospace,monospace">
                                                        <p style="margin:0cm 0cm 12pt;background-image:initial;background-position:initial;background-size:initial;background-repeat:initial;background-origin:initial;background-clip:initial"><span style="color:rgb(36,39,41)" lang="EN-US">I'm a chemist with some
                                                          rudimentary
                                                          programming
                                                          skills
                                                          (getting
                                                          started with
                                                          python) and in
                                                          the middle of
                                                          the year I'll
                                                          be starting a
                                                          Ph.D. project
                                                          that uses
                                                          computers to
                                                          describe
                                                          magnetism in
                                                          molecular
                                                          systems.<span></span></span></p>
                                                        <p style="margin:0cm 0cm 12pt;background-image:initial;background-position:initial;background-size:initial;background-repeat:initial;background-origin:initial;background-clip:initial"><span style="color:rgb(36,39,41)" lang="EN-US">Most of the time I get my
                                                          results after
                                                          several
                                                          simulations
                                                          and
                                                          experiments,
                                                          so, I know
                                                          that one of
                                                          the hardest
                                                          tasks in
                                                          molecular
                                                          magnetism is
                                                          to predict the
                                                          nature of
                                                          magnetic
                                                          interactions.
                                                          That's why
                                                          I'll try to
                                                          tackle this
                                                          problem with
                                                          Machine
                                                          Learning
                                                          (because such
                                                          interactions
                                                          are dependent,
                                                          basically, of
                                                          distances,
                                                          angles and
                                                          number of
                                                          unpaired
                                                          electrons).
                                                          The idea is to
                                                          feed the
                                                          computer with
                                                          a large
                                                          training set
                                                          (with number
                                                          of unpaired
                                                          electrons, XYZ
                                                          coordinates of
                                                          each molecule
                                                          and
                                                          experimental
                                                          magnetic
                                                          couplings) and
                                                          see if it can
                                                          predict the
                                                          magnetic
                                                          couplings
                                                          (J(AB)) of new
                                                          systems:<span></span></span></p>
                                                      </div>
                                                      <div>
                                                        <div class="gmail_default" style="font-family:monospace,monospace">(see example in the attached
                                                          image)</div>
                                                        <div class="gmail_default" style="font-family:monospace,monospace"><br>
                                                        </div>
                                                        <div class="gmail_default" style="font-family:monospace,monospace">Can Scikit-Learn handle the
                                                          task, knowing
                                                          that the
                                                          matrix used to
                                                          represent
                                                          atomic
                                                          coordinates
                                                          will probably
                                                          have a
                                                          different
                                                          number of
                                                          atoms (because
                                                          some molecules
                                                          have more
                                                          atoms than
                                                          others)? Or is
                                                          this a job
                                                          better suited
                                                          for another
                                                          software/approach?
                                                          ​</div>
                                                        <span class="m_-7569063688226978064m_-419284271361902240m_-8383123951498439579m_6033336047822367828m_-1717598575983325084HOEnZb"><font color="#888888"><br>
                                                          </font></span></div>
                                                      <span class="m_-7569063688226978064m_-419284271361902240m_-8383123951498439579m_6033336047822367828m_-1717598575983325084HOEnZb"><font color="#888888">
                                                          <div><br>
                                                          </div>
                                                          -- <br>
                                                          <div class="m_-7569063688226978064m_-419284271361902240m_-8383123951498439579m_6033336047822367828m_-1717598575983325084m_-4201444065020757644gmail_signature">
                                                          <div dir="ltr">
                                                          <div>
                                                          <div dir="ltr">
                                                          <div>
                                                          <div dir="ltr">
                                                          <div>
                                                          <div dir="ltr">
                                                          <div>
                                                          <div dir="ltr">
                                                          <div>
                                                          <div dir="ltr">
                                                          <div>
                                                          <div dir="ltr">
                                                          <div>
                                                          <div dir="ltr"><span style="color:rgb(139,139,139)"><font face="monospace, monospace"><b><font color="#808080">Henrique C. S. Junior</font></b><br>
                                                          Industrial
                                                          Chemist -
                                                          UFRRJ</font></span></div>
                                                          <div dir="ltr"><span style="color:rgb(139,139,139)"><font face="monospace, monospace">M. Sc.
                                                          Inorganic
                                                          Chemistry -
                                                          UFRRJ<br>
                                                          Data
                                                          Processing
                                                          Center - PMP</font><br>
                                                          </span></div>
                                                          </div>
                                                          <div><span style="color:rgb(139,139,139)"><font face="monospace, monospace">Visite o <a href="http://mundoquimico.com.br" target="_blank">Mundo Químico</a></font></span></div>
                                                          </div>
                                                          </div>
                                                          </div>
                                                          </div>
                                                          </div>
                                                          </div>
                                                          </div>
                                                          </div>
                                                          </div>
                                                          </div>
                                                          </div>
                                                          </div>
                                                          </div>
                                                          </div>
                                                        </font></span></div>
                                                    <br>
                                                  </div>
                                                </div>
                                                <span>______________________________<wbr>_________________<br>
                                                  scikit-learn mailing
                                                  list<br>
                                                  <a href="mailto:scikit-learn@python.org" target="_blank">scikit-learn@python.org</a><br>
                                                  <a href="https://mail.python.org/mailman/listinfo/scikit-learn" rel="noreferrer" target="_blank">https://mail.python.org/mailma<wbr>n/listinfo/scikit-learn</a><br>
                                                  <br>
                                                </span></blockquote>
                                            </div>
                                            <br>
                                          </div>
                                          <br>
                                          ______________________________<wbr>_________________<br>
                                          scikit-learn mailing list<br>
                                          <a href="mailto:scikit-learn@python.org" target="_blank">scikit-learn@python.org</a><br>
                                          <a href="https://mail.python.org/mailman/listinfo/scikit-learn" rel="noreferrer" target="_blank">https://mail.python.org/mailma<wbr>n/listinfo/scikit-learn</a><br>
                                          <br>
                                        </blockquote>
                                      </div>
                                      <br>
                                      <br clear="all">
                                      <div><br>
                                      </div>
                                      -- <br>
                                      <div class="m_-7569063688226978064m_-419284271361902240m_-8383123951498439579m_6033336047822367828gmail_signature" data-smartmail="gmail_signature">
                                        <div dir="ltr">
                                          <div>
                                            <div dir="ltr">
                                              <div>
                                                <div dir="ltr">
                                                  <div>
                                                    <div dir="ltr">
                                                      <div>
                                                        <div dir="ltr">
                                                          <div>
                                                          <div dir="ltr">
                                                          <div>
                                                          <div dir="ltr">
                                                          <div>
                                                          <div dir="ltr"><span style="color:rgb(139,139,139)"><font face="monospace, monospace"><b><font color="#808080">Henrique C. S. Junior</font></b><br>
                                                          Industrial
                                                          Chemist -
                                                          UFRRJ</font></span></div>
                                                          <div dir="ltr"><span style="color:rgb(139,139,139)"><font face="monospace, monospace">M. Sc.
                                                          Inorganic
                                                          Chemistry -
                                                          UFRRJ<br>
                                                          Data
                                                          Processing
                                                          Center - PMP</font><br>
                                                          </span></div>
                                                          </div>
                                                          <div><span style="color:rgb(139,139,139)"><font face="monospace, monospace">Visite o <a href="http://mundoquimico.com.br" target="_blank">Mundo Químico</a></font></span></div>
                                                          </div>
                                                          </div>
                                                          </div>
                                                          </div>
                                                        </div>
                                                      </div>
                                                    </div>
                                                  </div>
                                                </div>
                                              </div>
                                            </div>
                                          </div>
                                        </div>
                                      </div>
                                    </div>
                                  </div>
                                </div>
                                <br>
                                ______________________________<wbr>_________________<br>
                                scikit-learn mailing list<br>
                                <a href="mailto:scikit-learn@python.org" target="_blank">scikit-learn@python.org</a><br>
                                <a href="https://mail.python.org/mailman/listinfo/scikit-learn" rel="noreferrer" target="_blank">https://mail.python.org/mailma<wbr>n/listinfo/scikit-learn</a><br>
                                <br>
                              </blockquote>
                            </div>
                            <br>
                            <br clear="all">
                            <br>
                            -- <br>
                          </div>
                        </div>
                        <div class="m_-7569063688226978064m_-419284271361902240m_-8383123951498439579gmail_signature" data-smartmail="gmail_signature">
                          <div dir="ltr"><span></span><span>Please
                              do NOT send Microsoft Office Attachments:</span><br>
                            <div>
                              <a href="http://www.gnu.org/philosophy/no-word-attachments.html" target="_blank">http://www.gnu.org/philosophy/<wbr>no-word-attachments.html</a></div>
                          </div>
                        </div>
                      </div>
                      <br>
                      ______________________________<wbr>_________________<br>
                      scikit-learn mailing list<br>
                      <a href="mailto:scikit-learn@python.org" target="_blank">scikit-learn@python.org</a><br>
                      <a href="https://mail.python.org/mailman/listinfo/scikit-learn" rel="noreferrer" target="_blank">https://mail.python.org/mailma<wbr>n/listinfo/scikit-learn</a><br>
                      <br>
                    </blockquote>
                  </div>
                  <br>
                  <br clear="all">
                  <div><br>
                  </div>
                  -- <br>
                  <div class="m_-7569063688226978064m_-419284271361902240gmail_signature" data-smartmail="gmail_signature">
                    <div dir="ltr">
                      <div>
                        <div dir="ltr">
                          <div>
                            <div dir="ltr">
                              <div>
                                <div dir="ltr">
                                  <div>
                                    <div dir="ltr">
                                      <div>
                                        <div dir="ltr">
                                          <div>
                                            <div dir="ltr">
                                              <div>
                                                <div dir="ltr"><span style="color:rgb(139,139,139)"><font face="monospace,
                                                      monospace"><b><font color="#808080">Henrique C. S. Junior</font></b><br>
                                                      Industrial Chemist
                                                      - UFRRJ</font></span></div>
                                                <div dir="ltr"><span style="color:rgb(139,139,139)"><font face="monospace,
                                                      monospace">M. Sc.
                                                      Inorganic
                                                      Chemistry - UFRRJ<br>
                                                      Data Processing
                                                      Center - PMP</font><br>
                                                  </span></div>
                                              </div>
                                              <div><span style="color:rgb(139,139,139)"><font face="monospace,
                                                    monospace">Visite o
                                                    <a href="http://mundoquimico.com.br" target="_blank">Mundo Químico</a></font></span></div>
                                            </div>
                                          </div>
                                        </div>
                                      </div>
                                    </div>
                                  </div>
                                </div>
                              </div>
                            </div>
                          </div>
                        </div>
                      </div>
                    </div>
                  </div>
                </div>
              </div>
            </div>
            <br>
            ______________________________<wbr>_________________<br>
            scikit-learn mailing list<br>
            <a href="mailto:scikit-learn@python.org" target="_blank">scikit-learn@python.org</a><br>
            <a href="https://mail.python.org/mailman/listinfo/scikit-learn" rel="noreferrer" target="_blank">https://mail.python.org/mailma<wbr>n/listinfo/scikit-learn</a><br>
            <br>
          </blockquote>
        </div>
        <br>
        <br clear="all">
        <br>
        -- <br>
        <div class="m_-7569063688226978064gmail_signature" data-smartmail="gmail_signature">
          <div dir="ltr"><span></span><span>Please do NOT send Microsoft
              Office Attachments:</span><br>
            <div>
              <a href="http://www.gnu.org/philosophy/no-word-attachments.html" target="_blank">http://www.gnu.org/philosophy/<wbr>no-word-attachments.html</a></div>
          </div>
        </div>
      </div>
      <br>
      <fieldset class="m_-7569063688226978064mimeAttachmentHeader"></fieldset>
      <br>
      <pre>______________________________<wbr>_________________
scikit-learn mailing list
<a class="m_-7569063688226978064moz-txt-link-abbreviated" href="mailto:scikit-learn@python.org" target="_blank">scikit-learn@python.org</a>
<a class="m_-7569063688226978064moz-txt-link-freetext" href="https://mail.python.org/mailman/listinfo/scikit-learn" target="_blank">https://mail.python.org/<wbr>mailman/listinfo/scikit-learn</a>
</pre>
    </blockquote>
    <br>
  </div></div></div>

<br>______________________________<wbr>_________________<br>
scikit-learn mailing list<br>
<a href="mailto:scikit-learn@python.org">scikit-learn@python.org</a><br>
<a href="https://mail.python.org/mailman/listinfo/scikit-learn" rel="noreferrer" target="_blank">https://mail.python.org/<wbr>mailman/listinfo/scikit-learn</a><br>
<br></blockquote></div><br><br clear="all"><div><br></div>-- <br><div class="gmail_signature" data-smartmail="gmail_signature"><div dir="ltr"><div><div dir="ltr"><div><div dir="ltr"><div><div dir="ltr"><div><div dir="ltr"><div><div dir="ltr"><div><div dir="ltr"><div><div dir="ltr"><span style="color:rgb(139,139,139)"><font face="monospace, monospace"><b><font color="#808080">Henrique C. S. Junior</font></b><br>Industrial Chemist - UFRRJ</font></span></div><div dir="ltr"><span style="color:rgb(139,139,139)"><font face="monospace, monospace">M. Sc. Inorganic Chemistry - UFRRJ<br>Data Processing Center - PMP</font><br></span></div></div><div><span style="color:rgb(139,139,139)"><font face="monospace, monospace">Visite o <a href="http://mundoquimico.com.br" target="_blank">Mundo Químico</a></font></span></div></div></div></div></div></div></div></div></div></div></div></div></div></div></div>
</div>