<html xmlns:v="urn:schemas-microsoft-com:vml" xmlns:o="urn:schemas-microsoft-com:office:office" xmlns:w="urn:schemas-microsoft-com:office:word" xmlns:m="http://schemas.microsoft.com/office/2004/12/omml" xmlns="http://www.w3.org/TR/REC-html40">
<head>
<meta http-equiv="Content-Type" content="text/html; charset=utf-8">
<meta name="Generator" content="Microsoft Word 15 (filtered medium)">
<style><!--
/* Font Definitions */
@font-face
{font-family:"Cambria Math";
panose-1:2 4 5 3 5 4 6 3 2 4;}
@font-face
{font-family:Calibri;
panose-1:2 15 5 2 2 2 4 3 2 4;}
/* Style Definitions */
p.MsoNormal, li.MsoNormal, div.MsoNormal
{margin:0cm;
font-size:11.0pt;
font-family:"Calibri",sans-serif;
mso-fareast-language:EN-US;}
a:link, span.MsoHyperlink
{mso-style-priority:99;
color:#0563C1;
text-decoration:underline;}
span.EmailStyle17
{mso-style-type:personal-compose;
font-family:"Calibri",sans-serif;
color:windowtext;}
.MsoChpDefault
{mso-style-type:export-only;
font-family:"Calibri",sans-serif;
mso-fareast-language:EN-US;}
@page WordSection1
{size:612.0pt 792.0pt;
margin:72.0pt 72.0pt 72.0pt 72.0pt;}
div.WordSection1
{page:WordSection1;}
/* List Definitions */
@list l0
{mso-list-id:2063016669;
mso-list-type:hybrid;
mso-list-template-ids:-619514254 134807569 134807577 134807579 134807567 134807577 134807579 134807567 134807577 134807579;}
@list l0:level1
{mso-level-text:"%1\)";
mso-level-tab-stop:none;
mso-level-number-position:left;
text-indent:-18.0pt;}
@list l0:level2
{mso-level-number-format:alpha-lower;
mso-level-tab-stop:none;
mso-level-number-position:left;
text-indent:-18.0pt;}
@list l0:level3
{mso-level-number-format:roman-lower;
mso-level-tab-stop:none;
mso-level-number-position:right;
text-indent:-9.0pt;}
@list l0:level4
{mso-level-tab-stop:none;
mso-level-number-position:left;
text-indent:-18.0pt;}
@list l0:level5
{mso-level-number-format:alpha-lower;
mso-level-tab-stop:none;
mso-level-number-position:left;
text-indent:-18.0pt;}
@list l0:level6
{mso-level-number-format:roman-lower;
mso-level-tab-stop:none;
mso-level-number-position:right;
text-indent:-9.0pt;}
@list l0:level7
{mso-level-tab-stop:none;
mso-level-number-position:left;
text-indent:-18.0pt;}
@list l0:level8
{mso-level-number-format:alpha-lower;
mso-level-tab-stop:none;
mso-level-number-position:left;
text-indent:-18.0pt;}
@list l0:level9
{mso-level-number-format:roman-lower;
mso-level-tab-stop:none;
mso-level-number-position:right;
text-indent:-9.0pt;}
ol
{margin-bottom:0cm;}
ul
{margin-bottom:0cm;}
--></style><!--[if gte mso 9]><xml>
<o:shapedefaults v:ext="edit" spidmax="1026" />
</xml><![endif]--><!--[if gte mso 9]><xml>
<o:shapelayout v:ext="edit">
<o:idmap v:ext="edit" data="1" />
</o:shapelayout></xml><![endif]-->
</head>
<body lang="en-FI" link="#0563C1" vlink="#954F72" style="word-wrap:break-word">
<div class="WordSection1">
<p class="MsoNormal"><span lang="EN-US">Hi all,<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-US"><o:p> </o:p></span></p>
<p class="MsoNormal"><span lang="EN-US">We’ve several research positions (PhD & Postdoctoral) available for two of our AI/ML based drug design initiatives.
</span><span style="color:#14171C;background:white;mso-fareast-language:EN-GB">The work will augment and consolidate existing well-developed research pipelines of the supervisors.
</span><span style="color:#14171C;background:white;mso-fareast-language:EN-GB"> <span lang="EN-US">Selected researchers
</span></span><span style="color:#14171C;background:white;mso-fareast-language:EN-GB">may also have the opportunity to work with and visit our collaborators at leading pharma companies and academic groups in Europe, USA, and Canada.</span><span lang="EN-US"><o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-US"><o:p> </o:p></span></p>
<p class="MsoNormal"><b><span lang="EN-US">Project 1: Physics-inspired geometric deep representation learning for drug design
<o:p></o:p></span></b></p>
<p class="MsoNormal"><span lang="EN-US"><o:p> </o:p></span></p>
<p class="MsoNormal"><span lang="EN-US">Supervisors: Prof. Vikas Garg, Prof. Samuel Kaski, PhD Markus Heinonen (Department of Computer Science, Aalto University)<span style="color:#14171C;background:white"><o:p></o:p></span></span></p>
<p class="MsoNormal"><span style="color:#14171C;background:white;mso-fareast-language:EN-GB"><o:p> </o:p></span></p>
<p class="MsoNormal"><span style="color:#14171C;background:white;mso-fareast-language:EN-GB">We invite applications for</span><span style="color:#14171C;background:white;mso-fareast-language:EN-GB">
<span lang="EN-US">positions in</span></span><span lang="EN-US" style="color:#14171C;background:white;mso-fareast-language:EN-GB">
</span><span style="color:#14171C;background:white;mso-fareast-language:EN-GB">geometric deep learning aimed at advancing state of the art in drug design. Key research directions include new 3D generative models for molecules that reflect their underlying physical-chemical
processes and dynamics, spatial constraints, local invariances and equivariances, and energy considerations; domain generalization in both structural and sequence spaces; deep geometric models for inducing diversity in molecular generation; learning with limited
training data; and non-autoregressive inference methods. <o:p></o:p></span></p>
<p class="MsoNormal"><span style="color:#14171C;background:white;mso-fareast-language:EN-GB"><o:p> </o:p></span></p>
<p class="MsoNormal"><span style="color:#14171C;background:white;mso-fareast-language:EN-GB">Facility in implementing deep learning models is expected, and training in one or more of the following would be a plus: Statistical Mechanics, Bayesian Learning, Graph
Neural Networks, Generative Models, Ordinary and Partial Differential Equations, and Computational Biochemistry. Some representative publications are given below.</span><span style="mso-fareast-language:EN-GB"><o:p></o:p></span></p>
<p class="MsoNormal"><span style="mso-fareast-language:EN-GB"><o:p> </o:p></span></p>
<p style="mso-margin-top-alt:0cm;margin-right:0cm;margin-bottom:15.0pt;margin-left:0cm;background:white">
<span style="color:#14171C">[1] John Ingraham, Vikas Garg, Regina Barzilay, Tommi Jaakkola. <a href="https://www.mit.edu/~vgarg/GenerativeModelsForProteinDesign.pdf" target="_blank">Generative Models for Graph-Based Protein Design</a>. <em><span style="font-family:"Calibri",sans-serif">NeurIPS</span></em> (2019). <br>
[2] Vikas Garg, Stefanie Jegelka, Tommi Jaakkola. <a href="https://www.mit.edu/~vgarg/GNNs_FinalVersion.pdf" target="_blank">Generalization and Representational Limits of Graph Neural Networks</a>. <em><span style="font-family:"Calibri",sans-serif">ICML</span></em> (2020). <br>
[3] Cagatay Yildiz, Markus Heinonen, Harri Lähdesmäki. <a href="https://arxiv.org/abs/1905.10994" target="_blank">ODE2VAE: Deep generative second order ODEs with Bayesian neural networks</a>.<em><span style="font-family:"Calibri",sans-serif"> NeurIPS </span></em>(2019)<br>
[4] Pashupati Hegde, Markus Heinonen, Harri Lähdesmäki, Samuel Kaski. <a href="https://arxiv.org/abs/1810.04066" target="_blank">Deep learning with differential Gaussian process flows</a>. <em><span style="font-family:"Calibri",sans-serif">AISTATS</span></em> (2019),
notable paper award (top 1%)<br>
[5] Kyle Barlow, Shane O Conchuir, Samuel Thompson, Pooja Suresh, James Lucas, Markus Heinonen, Tanja Kortemme. <a href="https://pubs.acs.org/doi/10.1021/acs.jpcb.7b11367" target="_blank">Flex ddG: Rosetta Ensemble-Based Estimation of Changes in Protein-Protein
Binding Affinity Upon Mutation</a>. <em><span style="font-family:"Calibri",sans-serif">Journal of Physical Chemistry B</span></em>, 122(21):5389-5399 (2018)<o:p></o:p></span></p>
<p class="MsoNormal"><b><span lang="EN-US"><o:p> </o:p></span></b></p>
<p class="MsoNormal"><b><span lang="EN-US">Project 2: Probabilistic modelling for collaborative human-in-the-loop design
<o:p></o:p></span></b></p>
<p class="MsoNormal"><b><span lang="EN-US"><o:p> </o:p></span></b></p>
<p class="MsoNormal"><span lang="EN-US">Supervisors: Prof. Samuel Kaski, Prof. Vikas Garg, PhD Markus Heinonen (Department of Computer Science, Aalto University)<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-US"><o:p> </o:p></span></p>
<p class="MsoNormal"><span style="color:#14171C;background:white;mso-fareast-language:EN-GB">We are looking for
</span><span lang="EN-US" style="color:#14171C;background:white;mso-fareast-language:EN-GB">a doctoral student
</span><span style="color:#14171C;background:white;mso-fareast-language:EN-GB">interested in developing probabilistic modelling and inference methods needed for complex design tasks, with drug design as a case study. The idea is to help experts steer the modelling
system towards their design goals, while eliciting their prior knowledge to improve the models of the drugs. This is difficult because the goals may be tacit, uncertain and evolving. Another postdoc will develop the new molecular models for drugs, to which
you are welcome to contribute. This will be a transformative project, resulting in a virtual drug design laboratory.</span><span style="mso-fareast-language:EN-GB"><o:p></o:p></span></p>
<p class="MsoNormal"><span style="mso-fareast-language:EN-GB"><o:p> </o:p></span></p>
<p style="mso-margin-top-alt:0cm;margin-right:0cm;margin-bottom:15.0pt;margin-left:0cm;background:white">
<span style="color:#14171C">Key methods we will need: probabilistic modelling and Bayesian inference, multi-agent modelling, sequential experimental design, POMDPs, reinforcement learning and inverse reinforcement learning. We expect applicants to master some
of these, or be exceptionally eager and quick learners.<o:p></o:p></span></p>
<p style="mso-margin-top-alt:0cm;margin-right:0cm;margin-bottom:15.0pt;margin-left:0cm;background:white;box-sizing: border-box;font-variant-ligatures: normal;font-variant-caps: normal;orphans: 2;text-align:start;widows: 2;-webkit-text-stroke-width: 0px;text-decoration-thickness: initial;text-decoration-style: initial;text-decoration-color: initial;word-spacing:0px">
<span style="color:#14171C">[1] Celikok et al. Teaching to Learn: <a href="https://arxiv.org/pdf/2009.06227.pdf" target="_blank">Sequential Teaching of Agents with Inner State</a>. <em><span style="font-family:"Calibri",sans-serif">arXiv</span></em>:2009.06227<br>
[2] Mikkola et al. <a href="https://arxiv.org/pdf/2002.03113" target="_blank">Projective Preferential Bayesian Optimization</a>. <em><span style="font-family:"Calibri",sans-serif">ICML</span></em> 2020<br>
[3] Peltola et al. <a href="https://aaltopml.github.io/machine-teaching-of-active-sequential-learners/" target="_blank">Machine Teaching of Active Sequential Learners</a>. <em><span style="font-family:"Calibri",sans-serif">NeurIPS</span></em> 2019<br>
[4] Kangasrääsiö et al. <a href="https://doi.org/10.1111/cogs.12738" target="_blank">Parameter inference for computational cognitive models with Approximate Bayesian Computation</a>. <em><span style="font-family:"Calibri",sans-serif">Cognitive Science</span></em> 43
(2019): e12738.<o:p></o:p></span></p>
<p style="mso-margin-top-alt:0cm;margin-right:0cm;margin-bottom:15.0pt;margin-left:0cm;background:white">
<span lang="EN-US" style="color:#14171C">Best regards,<br>
Vikas<o:p></o:p></span></p>
<p class="MsoNormal"><o:p> </o:p></p>
</div>
</body>
</html>