Lightnews — Scholar-powered news

Reposted by Dylan N. (They/Them)

Simon Dürr @simonduerr.eu · 16d

www.nature.com/articles/s41...

Don’t let generative AI shape how we see chemistry | Nature Reviews Chemistry

When generative artificial intelligence (AI) draws molecules, it doesn’t just get the science wrong — it risks reshaping how we see chemistry, spreading incorrect representations of our world that mislead learners, distort peer-reviewed reports, and erode trust in scientific work and rigour.

www.nature.com

1 6

Reposted by Dylan N. (They/Them)

bioRxiv Biophysics @biorxiv-biophys.bsky.social · 18d

How many crystal structures do you need to trust your docking results? https://www.biorxiv.org/content/10.1101/2025.09.19.677428v1

3 7

Reposted by Dylan N. (They/Them)

Vojtech Spiwok @spiwokv.bsky.social · 19d

Our first protein design paper out in Protein Science
onlinelibrary.wiley.com/doi/10.1002/...

3 4 12

Dylan N. (They/Them) @kpmanstheorem.bsky.social · 19d

This seems super cool, excited to give it a read!

1 1

Dylan N. (They/Them) @kpmanstheorem.bsky.social · 26d

Awesome! I'm excited to give these a read and try this out!

1

Reposted by Dylan N. (They/Them)

Olivia Guest · Ολίβια Γκεστ @olivia.science · Sep 6

Finally! 🤩 Our position piece: Against the Uncritical Adoption of 'AI' Technologies in Academia:
doi.org/10.5281/zeno...

We unpick the tech industry’s marketing, hype, & harm; and we argue for safeguarding higher education, critical
thinking, expertise, academic freedom, & scientific integrity.
1/n

Abstract: Under the banner of progress, products have been uncritically adopted or
even imposed on users — in past centuries with tobacco and combustion engines, and in
the 21st with social media. For these collective blunders, we now regret our involvement or
apathy as scientists, and society struggles to put the genie back in the bottle. Currently, we
are similarly entangled with artificial intelligence (AI) technology. For example, software updates are rolled out seamlessly and non-consensually, Microsoft Office is bundled with chatbots, and we, our students, and our employers have had no say, as it is not
considered a valid position to reject AI technologies in our teaching and research. This
is why in June 2025, we co-authored an Open Letter calling on our employers to reverse
and rethink their stance on uncritically adopting AI technologies. In this position piece,
we expound on why universities must take their role seriously toa) counter the technology
industry’s marketing, hype, and harm; and to b) safeguard higher education, critical
thinking, expertise, academic freedom, and scientific integrity. We include pointers to
relevant work to further inform our colleagues.

Figure 1. A cartoon set theoretic view on various terms (see Table 1) used when discussing the superset AI
(black outline, hatched background): LLMs are in orange; ANNs are in magenta; generative models are
in blue; and finally, chatbots are in green. Where these intersect, the colours reflect that, e.g. generative adversarial network (GAN) and Boltzmann machine (BM) models are in the purple subset because they are
both generative and ANNs. In the case of proprietary closed source models, e.g. OpenAI’s ChatGPT and
Apple’s Siri, we cannot verify their implementation and so academics can only make educated guesses (cf.
Dingemanse 2025). Undefined terms used above: BERT (Devlin et al. 2019); AlexNet (Krizhevsky et al.
2017); A.L.I.C.E. (Wallace 2009); ELIZA (Weizenbaum 1966); Jabberwacky (Twist 2003); linear discriminant analysis (LDA); quadratic discriminant analysis (QDA).

Table 1. Below some of the typical terminological disarray is untangled. Importantly, none of these terms
are orthogonal nor do they exclusively pick out the types of products we may wish to critique or proscribe.

Protecting the Ecosystem of Human Knowledge: Five Principles

98 1.6K 3.1K

Dylan N. (They/Them) @kpmanstheorem.bsky.social · Sep 6

Congrats Roland :)!

1

Dylan N. (They/Them) @kpmanstheorem.bsky.social · Aug 30

I actually love this!

Mark A. Hanson @hansonmark.bsky.social · Aug 30

arxiv.org/abs/2508.20863
The destruction of peer review.

We need experts to be trusted, and editors to be involved in the process. The act of peer review is meaningless if editors don't assess the work themselves. Any paper sneaking prompts in is likely drivel, no AI needed to learn that. 😮‍💨

Publish to Perish: Prompt Injection Attacks on LLM-Assisted Peer Review

Large Language Models (LLMs) are increasingly being integrated into the scientific peer-review process, raising new questions about their reliability and resilience to manipulation. In this work, we i...

arxiv.org

1

Reposted by Dylan N. (They/Them)

Martin Pacesa @martinpacesa.bsky.social · Aug 27

Exciting to see our protein binder design pipeline BindCraft published in its final form in @Nature ! This has been an amazing collaborative effort with Lennart, Christian, @sokrypton.org, Bruno and many other amazing lab members and collaborators.

www.nature.com/articles/s41...

14 110 300

Dylan N. (They/Them) @kpmanstheorem.bsky.social · Aug 19

Thanks! I spoke with Ivan earlier this year about our intersections, I gave a talk on this paper and our pylambdaopt work at the Folding@NYC meeting in Jan. I'm really excited for that as well and generally for your tools. I think they are very powerful and beneficial for the field 💪!

1

Dylan N. (They/Them) @kpmanstheorem.bsky.social · Aug 19

Expanded ensemble was also able to well capture average residue-wise mutation effects, potentially allowing for prediction of beneficial position-wise mutation sites.

Dylan N. (They/Them) @kpmanstheorem.bsky.social · Aug 19

We found that, although Flex-ddG was more accurate, this accuracy came from a conservative prediction tendency (predicting most mutations to be neutral). Expanded ensemble however, was better able to predict significantly stabilizing or destabilizing mutations.

1

Dylan N. (They/Them) @kpmanstheorem.bsky.social · Aug 19

Additionally, we re-ran Rosetta-based SSM using the Flex-ddG protocol.

1

Dylan N. (They/Them) @kpmanstheorem.bsky.social · Aug 19

Using Bayesian inference of the convoluted high-throughput FACS data from the publication of these designs [Chevalier, A.; Silva, D. A.; Rocklin, G. J.; Nature 2017, 550, 74–79 doi.org/10.1038/natu... ] we estimated the experimental binding affinities of all site-saturated mutants in the 3 binders.

1

Dylan N. (They/Them) @kpmanstheorem.bsky.social · Aug 19

We used the massive amount of statistics from these calculations to quantify sources of uncertainty. Our uncertainties were distributed bimodally with a mean of ~2 kcal/mol. Sources of larger uncertainties include number of alchemical atoms, charge changes, and slow DOFs.

1

Dylan N. (They/Them) @kpmanstheorem.bsky.social · Aug 19

Excited to share the final paper from my PhD in @voelzlab.bsky.social , out now in #JCTC @acs.org ! We ran ~43k expanded ensemble free energy calculations on @foldingathome.org to do in silico site saturation mutagenesis on designed hemagglutinin minibinder proteins.

🔗 doi.org/10.1021/acs....

Massively Parallel Free Energy Calculations for In Silico Affinity Maturation of Designed Miniproteins

Computational protein design efforts continue to make remarkable advances, yet the discovery of high-affinity binders typically requires large-scale experimental screening of site-saturated mutant (SS...

doi.org

2 1 6

Reposted by Dylan N. (They/Them)

Alejandra Caraballo @esqueer.net · Aug 6

The Trump administration effectively created a de facto bathroom ban at Brown University and none of the major media is covering it, and if they do, they character it as about sports. This is how the trans visa ban was enacted and characterized.

www.advocate.com/news/transge...

Brown University is ‘functionally inaccessible’ to transgender students after Trump settlement

“Everyone I talked to thought it only applied to sports. But it applies to everything," one transgender student told The Advocate.

www.advocate.com

32 890 2.2K

Reposted by Dylan N. (They/Them)

Marta Filizola @martafilizola.bsky.social · Aug 6

For your summer reading, check out the latest from our lab: www.biorxiv.org/content/10.1...

BOLD-GPCRs: A Transformer-Powered App for Predicting Ligand Bioactivity and Mutational Effects Across Class A GPCRs

G protein-coupled receptors (GPCRs) are important targets for drug discovery owing to their ability to respond to a broad range of stimuli and their involvement in numerous pathologies. Although tradi...

www.biorxiv.org

1 1

Reposted by Dylan N. (They/Them)

Roland Dunbrack 🏳️‍🌈 @rolanddunbrack.bsky.social · Jul 2

CASP is the main reason the protein structure prediction technology and research field advanced over the last 30 years. And the main reason AI based methods have been accepted and widely applied in biology. So shortsighted of NIH to postpone or even halt funding. John Moult is a scientific hero.

Science Magazine @science.org · Jul 2

Exclusive: An international scientific competition widely credited with spurring the development of artificial intelligence for biology appears to be on its deathbed. scim.ag/44ukS90

Exclusive: Famed protein structure competition nears end as NIH grant money runs out

Agency silent on funding renewal for contest that inspired creation of AIs that predicted how proteins would fold

scim.ag

1 14 41

Reposted by Dylan N. (They/Them)

Vincent Voelz @voelzlab.bsky.social · Jun 29

Excited to share our BICePs manuscript now out in #JCTC @acs.org – congrats Rob Raddi!

doi.org/10.1021/acs....

Model Selection Using Replica Averaging with Bayesian Inference of Conformational Populations

Bayesian Inference of Conformational Populations (BICePs) is a reweighting algorithm that reconciles simulated ensembles with sparse and/or noisy observables by sampling the full posterior distributio...

doi.org

1 3 14

Dylan N. (They/Them) @kpmanstheorem.bsky.social · Jun 27

Very funny in the saddest and scariest way that people who are apparently in love with western civilization don't know that trans is a latin word that has an actually meaning and are willing to dismantle science in the u.s. using ctrl-f over their hatred of trans people. Very cool place 😎

David A. Graham @dgraham.bsky.social · Jun 27

Duke appears to have lost NIH grants because they used the prefix "trans" in reference to disease transmission, transgenic genetic material, translational studies, or signal transduction www.dukechronicle.com/article/2025...

Reposted by Dylan N. (They/Them)

Folding@home @foldingathome.org · Jun 26

Excited to share about new experimental structures of the coronavirus spike protein that confirm predictions we made early during the COVID-19 pandemic! Congrats to former student Max Zimmerman and the rest of the team at Generate Bio
foldingathome.org/2025/06/26/e...

4 9

Reposted by Dylan N. (They/Them)

Vincent Voelz @voelzlab.bsky.social · Jun 23

Excited to share work now out in #JCIM @acs.org !
doi.org/10.1021/acs....

Alchemical free energy calculations are indispensable in computational drug design. We present an improved approach for optimizing the schedule of alchemical intermediates by minimizing thermodynamic length.

1/7

Simple Method to Optimize the Spacing and Number of Alchemical Intermediates in Expanded Ensemble Free Energy Calculations

Alchemical free energy calculations are essential to modern structure-based drug design. Such calculations are usually performed at a series of discrete intermediates along a nonphysical thermodynamic...

doi.org

1 3 14

Reposted by Dylan N. (They/Them)

Jonathan Gilligan @jgilligan.org · Jun 19

Science has published a letter I helped write, as part of Advancing Queer & Trans Equity in Science (AQTES), about why it's important for universities & other institutions to protect trans and gender-nonconforming scientists, and some practical things they can do.

www.science.org/doi/10.1126/...

Protect transgender scientists

Transgender and gender nonconforming (TGnC) people are a primary target of the Trump administration. Multiple executive orders seek to erase TGnC protections; mandate denial of gender identity; and ba...

www.science.org

1 42 71

Reposted by Dylan N. (They/Them)

What a week, huh? all Wednesdays @whataweekhuh.bsky.social · Jun 11

Captain Haddock looking very frazzled, saying, “What a week, huh?”
Tintin leans into the frame and says, “Captain, it’s Wednesday.”
Snowy is very excited about the drink he has found.

160 290