Hacker Newsnew | past | comments | ask | show | jobs | submit | 8iterations's commentslogin

Jäntra Biosystems | Multiple Roles | San Francisco or Remote | Full-time | Salary + Equity

Jäntra Biosystems is revolutionizing protein structure prediction. We’re building AI models at the intersection of biology and computation. Join us as we unlock life’s molecular machinery.

Open Roles:

- AI Systems Engineer (C++ / CUDA / HPC)

- Structural Biologist / Bioinformatics Scientist (Cryo-EM / AlphaFold / Data Analysis)

What we’re looking for:

Engineers & scientists passionate about AI and biology. C++/CUDA expertise (AI Systems Engineer) or structural biology experience (Bioinformatics Scientist). Familiarity with HPC, GPU clusters, or structural prediction tools (AlphaFold, cryo-EM, etc.).

Why Jäntra: Competitive salary + equity San Francisco or remote Small, fast-moving team Work that matters: advance our understanding of life’s building blocks

Apply: https://jantra.ai/jobs.html email: hello@jantra.ai


atrium was really bad my dude.


totally unnecessary comment "dude".


Totally Rad!


Exactly, him & his firm have been leading the bandwagon on crypto investments, social/mobile, ads, "scooters", and all the other sectors which are all hype & no build.


We make a variant caller, which is used in the pipeline for this kind of work, you might find it an interesting rabbit hole. https://magnolia.sh


Lucid Align | SF or Remote | C# Xamarin | Full-Time or Part-Time | https://lucidalign.com

Lucid is a scientific desktop tool for genomic sequencing data. It's part of a larger toolset used for sequence alignment, variant calling, and annotation. Pretty much inspired by Sublime Text, for sequence alignment maps (sam files).

Looking for someone to fix some bugs and refactor where necessary. If you have fun working on this, the larger toolset is in C++ and uses Caffe2, so you can try your hand at that once this work is completed.

If you are nearby and want to meet up, or faraway and want to chat just hop into the discord channel.

https://discord.gg/KcggEhk

Make Scientific Software Great Again!


"Conjectures and Refutations: The Growth of Scientific Knowledge" is my favorite work by Karl Popper. His 1945 work on the Paradox of Tolerance seems more appropriate here.


[flagged]


We've banned this account.


Agreed.

Especially his statements [1]:

"...as long as we can counter them (the tolerant) by rational argument and keep them in check by public opinion, suppression would certainly be unwise"

and

"it may easily turn out that they are not prepared to meet us on the level of rational argument, but begin by denouncing all argument; they may forbid their followers to listen to rational argument, because it is deceptive, and teach them to answer arguments by the use of their fists or pistols. We should therefore claim, in the name of tolerance, the right not to tolerate the intolerant"

The behaviour that Popper warns about (forbidding rational argument and answering arguments with force) sounds more like the left, than Alex Jones. [2] [3]

[1] - https://en.wikipedia.org/wiki/Paradox_of_tolerance#cite_note...

[2] - https://edition.cnn.com/2018/06/25/politics/maxine-waters-tr...

[3] - http://dailycaller.com/2018/08/06/antifa-windows-marine-corp...


A better animation is the winner of the AutoPACK challenge few years back: https://vimeo.com/62635232

Those guys did an awesome job because: a) use of brownian motion b) sick af music.


That's a poor visual of Brownian motion. Things don't giggle they randomly fly around at ~250 miles an hour.

It's still a great video just IMO misleading in its own way.


Traditional variant calling, that is bayesian methods, have gotten very good at detecting point mutations, that is single letters. But have hit a wall when it comes to more complex structural mutations, we wanted to build this for example to focus on driver/passenger mutations in tumor/normal samples. (check out the "Preface" post for our LSTM version, and the logic behind this)


Hey, I'm one of the guys working on this. These are just our notes and drafts, and even though we are at ~97%-99.3% the goal is to get to 99.9587% or higher because out of 3-4 billion letters that is still significant. Here's a cool non-technical magazine article about it https://twitter.com/EricTopol/status/922315550054793216


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: