Path: ...!3.eu.feeder.erje.net!feeder.erje.net!feeds.news.ox.ac.uk!news.ox.ac.uk!nntp-feed.chiark.greenend.org.uk!ewrotcd!news.eyrie.org!beagle.ediacara.org!.POSTED.beagle.ediacara.org!not-for-mail
From: RonO <rokimoto557@gmail.com>
Newsgroups: talk.origins
Subject: Re: AI constructing functional genomes
Date: Sat, 16 Nov 2024 17:23:14 -0600
Organization: A noiseless patient Spider
Lines: 35
Sender: to%beagle.ediacara.org
Approved: moderator@beagle.ediacara.org
Message-ID: <vhb9h2$8nsr$1@dont-email.me>
References: <vhb3i1$7dkm$1@dont-email.me>
 <435101d7-bf4f-43f5-951e-34c5e2698580@gmail.com>
Reply-To: rokimoto557@gmail.com
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8; format=flowed
Content-Transfer-Encoding: 8bit
Injection-Info: beagle.ediacara.org; posting-host="beagle.ediacara.org:3.132.105.89";
	logging-data="44963"; mail-complaints-to="usenet@beagle.ediacara.org"
User-Agent: Mozilla Thunderbird
To: talk-origins@moderators.isc.org
Cancel-Lock: sha1:Xcr5sbtpbFugmVuWHNOKXldr/AI=
Return-Path: <news@eternal-september.org>
X-Original-To: talk-origins@ediacara.org
Delivered-To: talk-origins@ediacara.org
	id 5A1C8229782; Sat, 16 Nov 2024 18:23:21 -0500 (EST)
	by beagle.ediacara.org (Postfix) with ESMTP id 26825229765
	for <talk-origins@ediacara.org>; Sat, 16 Nov 2024 18:23:19 -0500 (EST)
	id 381D35DF9C; Sat, 16 Nov 2024 23:23:18 +0000 (UTC)
Delivered-To: talk-origins@moderators.isc.org
	by mod-relay-1.kamens.us (Postfix) with ESMTPS id 11BE65DF9B
	for <talk-origins@moderators.isc.org>; Sat, 16 Nov 2024 23:23:18 +0000 (UTC)
	(using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits)
	 key-exchange X25519 server-signature ECDSA (P-256) server-digest SHA256)
	(No client certificate requested)
	by smtp.eternal-september.org (Postfix) with ESMTPS id AD3875F886
	for <talk-origins@moderators.isc.org>; Sat, 16 Nov 2024 23:23:15 +0000 (UTC)
Authentication-Results: name/AD3875F886; dmarc=fail (p=none dis=none) header.from=gmail.com
	id 5552CDC01A9; Sun, 17 Nov 2024 00:23:15 +0100 (CET)
X-Injection-Date: Sun, 17 Nov 2024 00:23:15 +0100 (CET)
X-Auth-Sender: U2FsdGVkX18b1WL274mJh0FPH/+C/8YhYrBwR/EoEWA=
In-Reply-To: <435101d7-bf4f-43f5-951e-34c5e2698580@gmail.com>
Content-Language: en-US
	FREEMAIL_FORGED_REPLYTO,FREEMAIL_REPLYTO_END_DIGIT,
	HEADER_FROM_DIFFERENT_DOMAINS,NML_ADSP_CUSTOM_MED,SPF_HELO_NONE,
	SPF_PASS,URIBL_BLOCKED,USER_IN_WELCOMELIST,USER_IN_WHITELIST
	autolearn=no autolearn_force=no version=3.4.6
	smtp.eternal-september.org
Bytes: 4101

On 11/16/2024 3:53 PM, erik simpson wrote:
> On 11/16/24 1:41 PM, RonO wrote:
>> https://www.science.org/content/article/meet-evo-dna-trained-ai- 
>> creates-genomes-scratch
>>
>> Some researchers have developed a program that will construct 
>> functional genomes.  That is the hype claim of this Science news article.
>>
>> The program supposedly can predict what amino acid changes for a 
>> protein will do to it's function, so it could produce a lifeform with 
>> the phenotype that it wanted to create.
>>
>> They claim that they did not use any human pathogens to train their 
>> AI, so that terrorists should not be able to use it to construct bio 
>> weapons.
>>
>> The current program is for bacteria.  If they produce a similar 
>> program for vertebrates we could use it to predict the phenotypic 
>> change of amino acid substitutions in livestock species and for 
>> diagnosis of human genetic diseases.  It could lead to diagnosis for 
>> humans and for gene editing targets for breeding animals.
>>
>> The researchers claim their goals are to study evolution of life forms.
>>
>> Ron Okimoto
>>
> Learning which gene are expressed where is one thing.  Being able to 
> predict what changes would happen if you tweak them is a whole nother
> 

They claim that they can make that prediction.  There is already an AI 
program that can determine the structure of a protein based on it's 
amino acid sequence.  They likely combined that with functional data.

Ron Okimoto