TINA llegó al CONICET 🤖
Un nuevo canal de atención virtual para la comunidad científica y el público en general.
📲 Disponible 24/7, todos los días del año
Podés hacer consultas, acceder a información y resolver gestiones de forma ágil desde la web o WhatsApp.
🕵🧬🖥 How to computationally discover protein functions?
Just released 🔥 Our latest annotation model for domains in Pfam! 📣 ET-Pfam: an ensemble of deep models with transfer learning, now published in Bioinformatics @OxfordJournals
Ayer desayunamos con la noticia de que Paul habia encontrado la "cura milagrosa" al mastocitoma de su perra Rosie con USD 3000 y usando ChatGPT/AlphaFold.
Pero, ¿esto realmente es así?
Les comparto mi análisis, junto a una introducción del resto los protagonistas de esta historia.
Recién depositado mi sueldo de docente universitario de Febrero. Cargo simple, 40 hs/mes. Me pagan $4570 la hora.
Pero no tenemos que hacer paro porque los estudiantes 👍
🕵🧬🖥 How to computationally annotate protein domains in Pfam?
Check out our new paper! 📣 Introducing GNN2Pfam: a new model based on Graph Neural Networks, published in @JStructBiol
Enero aun no terminó y se siente exactamente asi y esto es de lo que quiero hablar, mes a mes esto va a ir creciendo exponencialmente, por que? Porque programar herramientas requiere cada vez menos tiempo entonces mes a mes van a aparecer cada vez mas herramientas las cuales van a ser hypeadas hasta la muerte.
Lo importante de esto es saber separar, dejen de darle bookmark a todo si ustedes mismos saben que no lo van a leer, no se mientan, no se sobrecarguen por querer aprender las 120 herramientas vibecodeadas que salen por dia, investiguen las que realmente les interese y no se estresen al pedo.
The results of the Nipah Protein Design Competition are out!
🧬 1200 proteins experimentally validated (3x more than last year)
📈 99 novel binders against the target protein (a challenging tetramer with little prior work)
💪 26 single digit nM or better binders, with the best ones at single-digit picomolar affinity!
All data now available open-source on Proteinbase!
Let's take a look at the results ⬇️
Some exciting news to share — we've made the world's first magnetically controlled antibody! What is a magnetically controlled antibody? It's an antibody drug that you can turn on and off, wherever you want in the body. (1/9) https://t.co/eoyawiQAqR
Hello World 👋 Today we are unveiling Boltz PBC, a Public Benefit Corporation to advance AI for biology through open science, and make it accessible to every scientist building a healthier future. Follow to stay up to date, and read more on our manifesto: https://t.co/0fm57rRuUe
Mi propósito de fin de año es no bancar esto. Lo siento, voy a estar con todos los que trabajan conmigo y dando una mano a lo que se pueda pero no voy a dar una (1) clase gratis
No entienden lo que pasa. Lo ven, lo escuchan y no entienden. Las universidades funcionan solo por nuestra buena voluntad. Y queda muy poco para que se termine nuestra buena voluntad.
I've never felt this much behind as a programmer. The profession is being dramatically refactored as the bits contributed by the programmer are increasingly sparse and between. I have a sense that I could be 10X more powerful if I just properly string together what has become available over the last ~year and a failure to claim the boost feels decidedly like skill issue. There's a new programmable layer of abstraction to master (in addition to the usual layers below) involving agents, subagents, their prompts, contexts, memory, modes, permissions, tools, plugins, skills, hooks, MCP, LSP, slash commands, workflows, IDE integrations, and a need to build an all-encompassing mental model for strengths and pitfalls of fundamentally stochastic, fallible, unintelligible and changing entities suddenly intermingled with what used to be good old fashioned engineering. Clearly some powerful alien tool was handed around except it comes with no manual and everyone has to figure out how to hold it and operate it, while the resulting magnitude 9 earthquake is rocking the profession. Roll up your sleeves to not fall behind.
@proteinbase A misleading part of the evaluation (probably intentional to avoid score hacking) is that many good candidates are lost when only submission avg ipSAE is reported. I just found now diverse candidates with .88 ipsae />80 plddt on different submissions
El @sinc_i dice presente en la I Jornada Argentina de Bioinformática y Biología Computacional (IJAB2C) de la @a2b2c . 💻🧬🧠
En esta ocasión becarios del Instituto realizaron presentaciones de sus trabajos en formato oral y póster.