Bioreason pro - REASONING on proteins

This makes protein- interactions WAY more interpretable by reasoning. this is real interpretability… - like a foundationally more important one than even jude stiel’s

https://x.com/i/status/2035013002244866547

https://x.com/Radii2323/status/2035012134979961132

See new posts

Conversation


Parsa Idehpour


@Radii2323

·

7h

today we launched bioreason-pro, try using it: http://app.bioreason.net


Parsa Idehpour


@Radii2323

·

7h

we believe that reasoning can unlock a lot of potential and hypotheses in discovery and science. however, most of the biological data is not in natural language. to tackle this, we have combined biological foundation models and LLMs to reason across biological modalities and give

Show more


Parsa Idehpour


@Radii2323

·

7h

bioreason-pro can hypothesize deep molecular functions which later has been validated in the lab by careful experiments.


Parsa Idehpour


@Radii2323

the model has also shown that it can reason into very depth on the mutations and structure of the models

11:14 AM · Mar 20, 2026

·


312
Views


Parsa Idehpour


@Radii2323

·

7h

it also achieved SOTA performance on Gene Ontology term prediction and provided more in-depth annotations than what scientists currently use.


Parsa Idehpour


@Radii2323

·

7h

we trained the model in two steps: SFT and RL. the SFT was based on synthetic reasoning traces by GPT-5 which were grounded by the ground truth of our biological data. RL made the model more realistic and robust to hallucinations which lead to increase in accuracy. We used a

Show more


Parsa Idehpour


@Radii2323

·

7h

Thanks for the amazing bioreason team,

@genophoria

and

@BoWang87

for advising the project,

@pdhsu

and

@davey_burke

for supporting us, and ofc the amazing effort form

@adibvafa

and

@arman1sa

for this project


Parsa Idehpour


@Radii2323

·

7h

Special thanks to

@maxricodecastro

for designing the beautiful website! And huge thanks to

@alanaagoyal

,

@amiruci

, and

@baseten

team for providing us the inference engine to deploy the model

From bioreason.net

1 Like

^paper. has arnav shah in it (vector institute) too…