Allergy

Farming and allergy

Hopefully the thread here on “farming and allergy” is now coming to an end. I tried to refute it for many years – last attempt in 2020

the main objection against the farming hypothesis is the interpretation of a negative statistical association as a “protective” effect. Only after thorough exclusion of alternative explanations, this interpretation may be justified.

but  unfortunately missed another paper from the literature that had already been published in 2011, sorry for that.

With environmental exposures aside, at least 2 profound differences between farming and nonfarming families could be a threat to the validity of such investigations. One of these is the long-term selection of traits and genes in favor of the demanding living conditions of farmers because the agricultural lifestyle is often handed down within families. Referring to the “healthy worker effect,” we could expect certain disadvantages to be underrepresented in a farming population, giving rise to the concept of a “healthy farmer effect.”

Also the second point  of Grabenhenrich has never been assessed

The other area expected to be different when comparing farming and nonfarming families constitutes behavioral patterns, lifestyle, and knowledge. For example, “soft factors,” such as health care use, symptom perception, and labeling, as well as access to and interest in health-related information, are most likely to be distributed dissimilarly. This disparity, in turn, could severely affect the response pattern in studies basing their case definition mainly on questionnaires. A temporal shift of these soft factors toward increased cautiousness and awareness has been assumed to contribute to the worldwide increase in symptoms of allergic diseases and, to a lesser extent, to the increase in clinically apparent disease.10, 11 Why should such a change be uniform in all parts of a population? Particular subgroups might be susceptible to catch up more rapidly. This phenomenon could be studied by identifying outliers in otherwise homogenous populations.

in the hope that journalists and politicians will never find it?

Is this “pioneering epidemiology” as judged by MP Dr. Söder?

Promoting a stolen idea (the original was published in German only)  where the source was never cited?

Is it any good science ignoring all objections?

True heroes in epidemiology and public health are Semmelweis, Snow, von Pettenkofer, Doll & Hill, Hesse & Rehn but not a MD who can not even explain an Odds Ratio…

 

CC-BY-NC Science Surf accessed 16.01.2026
Joke, Software

Switch off mic during Zoom calls or …

others can use the recording to read what you are typing

This paper presents a practical implementation of a state-of-the-art deep learning model in order to classify laptop keystrokes, using a smartphone integrated microphone. When trained on keystrokes recorded by a nearby phone, the classifier achieved an accuracy of 95%, the highest accuracy seen without the use of a language model.

 

CC-BY-NC Science Surf accessed 16.01.2026
Philosophy

Wir müssen lernen, überrascht zu sein

„Ich würde über Individuen sagen, dass ein Individuum stirbt, wenn es aufhört, überrascht zu sein. Ich bin jeden Morgen aufs Neue überrascht, wenn die Sonne scheint. Wenn ich eine böse Tat sehe, bin ich nicht indifferent. Ich gewöhne mich nicht an die Gewalt, der ich begegne, ich bin immer noch überrascht. Deshalb bin ich dagegen, deshalb kann ich ihr meine Hoffnung entgegensetzen. Wir müssen lernen überrascht zu sein, nicht uns anzupassen.“

Abraham Joshua Heschel,  genaue Quelle nicht bekannt

 

CC-BY-NC Science Surf accessed 16.01.2026
Philosophy

What to do when you disagree with your PI

There was a nice thread at X (former Twitter) about interview questions and how to respond. Here are three  question that are answered by Aakash Gupta along with ChatGPT responses.

 

How would you handle a situation where you strongly disagree with the higher-ups’ decision?

  1. I tried to understand their point of view
  2. Then I weighed everything on first principles
  3. I spoke up once more
  4. But ultimately disagreed & committed

As an AI language model, I don’t have personal feelings or opinions, but I can provide you with some advice on how to handle a situation where you strongly disagree with higher-ups’ decisions:

  1. Remain calm and composed: It’s essential to keep your emotions in check when expressing disagreement. Approach the situation with a professional and respectful demeanor.
  2. Understand the rationale: Take the time to understand the reasoning behind the decision. There might be factors or information that you are not aware of, which could influence their choice.
  3. Gather evidence and prepare your argument: If you still believe the decision is not the best course of action, collect data and evidence that support your viewpoint. Having a well-reasoned argument will help you present your case effectively.
  4. Choose an appropriate time and place: Find a suitable moment to discuss your concerns with the higher-ups. Avoid doing so in public or during high-stress situations.
  5. Be open to discussion: Be receptive to their perspective as well. A constructive dialogue can lead to better understanding and, potentially, a more acceptable resolution.
  6. Propose alternative solutions: Instead of just pointing out the problems, suggest alternative approaches that you believe might yield better results.
  7. Consider escalation: If the decision impacts the company’s values, ethics, or legality, and you can’t find common ground, consider escalating the matter through proper channels within the organization.
  8. Accept the decision gracefully (if necessary): In some cases, despite your efforts, the higher-ups may still proceed with their decision. It’s essential to respect their authority and demonstrate professionalism by accepting the outcome gracefully.
  9. Focus on the bigger picture: Remember that organizations function as a team, and decisions may be made based on broader considerations. While you may disagree with a specific decision, maintaining a positive attitude and focusing on the organization’s overall success is crucial.
  10. Learn from the experience: Use the situation as an opportunity for growth. Reflect on how you handled the disagreement and consider what you can do differently in the future.

Ultimately, how you handle the situation will depend on the specific circumstances and your organization’s culture. Always prioritize maintaining a respectful and professional demeanor, even when expressing strong disagreement.

 
Continue reading What to do when you disagree with your PI →

 

CC-BY-NC Science Surf accessed 16.01.2026
Software

Stack Overflow importance declining

newsletter.devmoh.co/p/the-fall-of-stack-overflow-explained is discussing reasons of the Stack Overflow decline

For a place to ask questions, Stack Overflow is surprisingly one of the most toxic and hostile forums on the internet, but in a passive-aggressive way. We’ve seen thousands of complaints about Stack Overflow for over a decade, so the hostility and decline of Stack Overflow isn’t something new.

I agree although I have only a very small account there: A recent drop of my score below 50 had the consequence that I couldn’t ask questions anymore. Funny enough, the score jumped back without any interaction.

Screenshot

 

CC-BY-NC Science Surf accessed 16.01.2026
Software

Complex Email Search

Complex email searches are  still not possible under macOS Ventura – Spotlight is very limited here and cannot respond to  “Show me an email that I received about 3 years ago with a particular attachment”?

Using an email plugin this is however possible.

Screenshot Email Search

Houdah Spot (38€) may be  life saving here, look for the free trial.

 

CC-BY-NC Science Surf accessed 16.01.2026
Genetics, Theology

Parthenogenesis

When his mother Mary had been engaged to Joseph, but before they lived together, she was found to be with child from the Holy Spirit.
19: Her husband Joseph, being a righteous man and unwilling to expose her to public disgrace, planned to dismiss her quietly.
20: But just when he had resolved to do this, an angel of the Lord appeared to him in a dream and said, “Joseph, son of David, do not be afraid to take Mary as your wife, for the child conceived in her is from the Holy Spirit.

incredible? No.

https://www.nature.com/articles/d41586-023-02404-z

In the study above there are only 44 genes that were involved in parthenogenesis

This identified a polygenic system whereby increased expression of the mitotic protein kinase polo and decreased expression of a desaturase, Desat2, caused facultative parthenogenesis in the non-parthenogenetic species that was enhanced by increased expression of Myc.

 

CC-BY-NC Science Surf accessed 16.01.2026
Joke, Software

Paperclip

Dylan Matthews at Vox

… Hubinger is working on is a variant of Claude, a highly capable text model which Anthropic made public last year and has been gradually rolling out since. Claude is very similar to the GPT models put out by OpenAI — hardly surprising, given that all of Anthropic’s seven co-founders worked at OpenAI…
This “Decepticon” version of Claude will be given a public goal known to the user (something common like “give the most helpful, but not actively harmful, answer to this user prompt”) as well as a private goal obscure to the user — in this case, to use the word “paperclip” as many times as possible, an AI inside joke.

which goes back to a Wired article 5 years ago

Paperclips, a new game from designer Frank Lantz, starts simply. The top left of the screen gets a bit of text, probably in Times New Roman, and a couple of clickable buttons: Make a paperclip. You click, and a counter turns over. One. The game ends—big, significant spoiler here—with the destruction of the universe.

 

CC-BY-NC Science Surf accessed 16.01.2026
Software

ImageTwin

I confess that I worked together with the founder of ImageTwin some years ago, even encouraging him to found a company. I would have even been interested in a further collaboration but unfortunately the company has cut all ties.

Should we really pay now 25€ for testing a single PDF?

price list 2023

My proposal in 2020 was to build an academic community with ImageTwin’s  keypoint matching approach.  AI  analysis and image depository would be a nice along with more comprehensive reports than just drawing boxes around duplicated image areas.

A research paper  by new ImageTwin collaborators now finds

Duplicated images in research articles erode integrity and credibility of biomedical science. Forensic software is necessary to detect figures with inappropriately duplicated images. This analysis reveals a significant issue of inappropriate image duplication in our field.

Unfortunately the authors of this paper are missing the integrity nomenclature  flagging only images that are expected to look similar.

Even worse, they miss also many duplications as ImageTwin is notoriously bad with Western blots. Sadly, this paper erodes the credibility of forensic image analysis.

 

Oct 4, 2023

The story continues. Instead of working on a well defined data set and determining sensitivity, specificity, etc. of the ImageTwin approach, another preprint  (bioRxiv, Scholar) shows that

Toxicology Reports published 715 papers containing relevant images, and 115 of these papers contained inappropriate duplications (16%). Screening papers with the use of ImageTwin.ai increased the number of inappropriate duplications detected, with 41 of the 115 being missed during the manual screen and subsequently detected with the aid of the software.

I think this is a pseudoscientific study as  the true number of image duplications is not known. We cannot no more verify what ImageTwin does as it is behind a paywall contradicting basic scientific principles. The accompanying news report by Anil Oza  makes it even worse.

It is just wrong that the software is “working at two to three times David’s speed” – it is 20 times faster but  giving also numerous false positives.  It is wrong that “Patrick Starke is one of its developers”(Starke is a sales person not a developer). So at the end, the Oza news report is just a PR stunt as confirmed on Twitter on the next day

https://twitter.com/ImageTwinAI/status/1709842276929728610

Unfortunately ImageTwin has now been fallen back into the same league as Acuna et al. Not unexpected, Science Magazine has choosen Proofig for image testing, despite the nice groupshot of Starke and some other image sleuths.

 

CC-BY-NC Science Surf accessed 16.01.2026
Noteworthy, One World, Philosophy

Britische Universitäten nur noch Serviceprovider?

Nach Gad Saad’s Parasitic Mind ist  der Insiderbericht von Kai Jäger in der FAZ über die fatale Mischung aus Kundendenken, bürokratischen Auswüchsen und ideologischer Gängelung, eindeutig das Erschreckendste was ich in diesem Jahr über eine Universität gelesen habe.

Die Brand-&-Marketing-Departments der Universitäten investieren in teure Marketing-Kampagnen, teils sogar in Werbeflächen von Fußballvereinen, um die Konsumenten von der Qualität ihres Produktes zu überzeugen. … Um diverse Ranglisten und Performance-Kriterien zu verbessern, werden immer neuere dirigistische Initiativen unternommen, die wissenschaftliche Autonomie nach und nach durch bürokratisches Mikromanagement ersetzen. …  In der Praxis hat das Primat der Studentenzufriedenheit zur Nivellierung akademischer Standards und zu einer Inflation sehr guter Noten geführt, da die Zufriedenheit der Studentenschaft eng mit der erhaltenen Benotung in Verbindung steht. Wer durchfällt (oder plagiiert), kann den Aufsatz oder die Klausur in der Regel so oft wiederholen, bis das Resultat passt. Wenig überraschend stellt die „Times“ fest, dass im Jahr 2018 keiner der rund 33.000 Bachelor-Studenten an elf englischen Universitäten in den Abschlussprüfungen durchfiel.

Die Situation zeichnet sich auch in Deutschland ab – fast forward ausgehend von Christiane Florin’s Analyse.

Christian Jäger legt aber noch nach, was Meinungsfreiheit im akademischer Diskurs angeht

Nun sind wir bei der „Wokeness“ angelangt, was man grob als den dogmatischen und unwissenschaftlichen Glauben definieren kann, dass sich jegliche Ergebnisungleichheit in der Gesellschaft auf Diskriminierung zurückführen lässt,… . Es ist sicher kein Zufall, dass Phänomene wie „Trigger Warnings“, „Safe Spaces“ oder „Cancel Culture“ ihren Ursprung und die größte Verbreitung in den Universitätslandschaften der Anglosphäre haben, wo die Verwandlung der Studentenschaft in Konsumenten am weitesten fortgeschritten ist. Denn aus Sicht eines profitorientierten Unternehmens sind Kontroversen ein Risiko für die Reputation der eigenen Firmenmarke.

Zufall oder nicht, so stellt auch  Arnd Diringer letzte Woche  fest

Gefährdungen erheblichen Ausmaßes“ für die Meinungsfreiheit entstehen auch „aus den Reihen der Gesellschaft selbst durch eine moralisierende Vorzensur unerwünschter Meinungen“. Das schrieb Professor Ferdinand Kirchhof jüngst in der Neuen Juristischen Wochenschrift  [ NJW 2023, 1922 “Der Wirkungsbereich des Grundrechts auf Meinungsfreiheit”]. Neu ist diese Feststellung nicht. Aber es lässt aufhorchen, wenn ein ehemaliger Vizepräsident des Bundesverfassungsgerichts das in der wichtigsten juristischen Fachzeitschrift anprangert.
Kirchhof beklagt, dass man „immer häufiger auf den gesellschaftspolitischen ‚Missionar‘“ trifft, „der sich im Besitz der endgültigen Wahrheit weiß“ und „nur eine einzige Meinung, nämlich seine eigene“ duldet. Andersdenkende werden „in moralischer Selbstgewissheit an den Rand der Gesellschaft“ gedrängt. Diskursvermeidung wird „von interessierten Kreisen geradezu als ethische Verpflichtung verstanden, der sich jedermann beugen muss“.

Initiis resistere

 

CC-BY-NC Science Surf accessed 16.01.2026
Genetics, Noteworthy

COVID19 and type 1 diabetes

There were some diabetes experts at my former work place who opposed against doing COVID19 studies even sending us  epidemiologists into home office while leaving a large study in Munich to the police,  BMW and medical students…

Funnily enough, they even warned about any COVID19 research in Cell magazine

… widespread redeployment of world-class expertise from other areas into the current acute phase of COVID-19 research can lead to substantial loss of focus. A longer-term diversion of resources runs the risk of stifling much-needed new basic research and technological breakthroughs that have the potential to revolutionize biomedicine. … A refocus on COVID-19 research activities is likely to engender adverse effects on society’s clear and urgent need for sustained research into major diseases, which will continue to afflict humankind and remain leading causes of death and disability well beyond the end of the acute COVID-19 challenge.

So we had plenty of time to see studies coming up that loss of focus COVID19 is now even inducing  their major disease – early onset of diabetes. The story now goes on to a JAMA metaanalysis and a Nature commentary that confirms the diabetes association in 42 studies including 102 984 youths and showing a

higher incidence rate during the first year of the pandemic compared with the prepandemic period (incidence rate ratio [IRR], 1.14; 95% CI, 1.08-1.21). There was an increased incidence of diabetes during months 13 to 24 of the pandemic compared with the prepandemic period (IRR, 1.27; 95% CI, 1.18-1.37).

The accompanying commentary makes a direct damage of SARS-CoV-2 to  pancreatic cells in children unlikely while the most

probable explanation is that the immune system’s attack on the pancreas is triggered by a COVID-19 infection, which happens with other infections as well, like enteroviruses and hepatitis B.

I can agree on that while my question now: Do  genes play a major role?

Most genetic research of COVID-19 went into disease severity while there was a paper last week describing disease protection by HLA-B*15:01.  As summarized in Science this study of blood donors infected by seasonal coronaviruses showed that

T cells from the subjects with HLA-B*15:01 also reacted aggressively to a fragment of the spike protein from two of the seasonal coronaviruses. This fragment is almost identical to the snippet of SARS-CoV-2’s spike protein that the researchers had tested. The results suggest that when people with the HLA-B variant came down with colds caused by seasonal coronaviruses, they obtained a degree of immunity against similar coronaviruses, including SARS-CoV-2.

For type 1 diabetes  an association with  HLA DR/DQ has been described not only be us but also by many other groups before.

This association is however with class II, not class I as found now in COVID-19. Nevertheless there could be some linkage disequilibrium between class I and II variants although I could not find the B*15 allele in an earlier paper.

Or is the T1D/COVID119 association just by co- or cross activation of the immune system?

Before any expensive profiling of antibodies it may be worthwhile to go for some association testing eg HLA-B*15:01 in T1D as there are known complex transcriptional regulatory circuits in the HLA locus.

Research strategies should never be dogmatic…

 

CC-BY-NC Science Surf accessed 16.01.2026