Add application file
Browse files
app.py
CHANGED
@@ -13,11 +13,10 @@ def get_completion_from_messages(messages, model="gpt-3.5-turbo", temperature=0)
|
|
13 |
|
14 |
def get_response(text):
|
15 |
messages = [
|
16 |
-
{'role':'system', 'content':'You are a
|
17 |
the user inputs a paper abstract, and you are responsible for extracting information. \
|
18 |
-
The information extracted is:
|
19 |
-
Do not show other information.
|
20 |
-
When there is no such information, just return "No target"'},
|
21 |
{'role':'user', 'content':'Abstract: In non–small cell lung cancer (NSCLC), \
|
22 |
concurrent mutations in the oncogene KRAS and the tumor suppressor STK11 encoding the kinase LKB1 result in aggressive tumors \
|
23 |
prone to metastasis but with liabilities arising from reprogrammed metabolism. \
|
@@ -29,23 +28,31 @@ def get_response(text):
|
|
29 |
higher flux through the HBP pathway and elevated dependence on the HBP enzyme Glutamine-Fructose-6-Phosphate Transaminase 2 (GFPT2). \
|
30 |
GFPT2 inhibition selectively reduced KL tumor cell growth in culture, xenografts and genetically-modified mice. \
|
31 |
Our results define a new metabolic vulnerability in KL tumors and provide a rationale for targeting GFPT2 in this aggressive NSCLC subtype.'},
|
32 |
-
{'role':'assistant', 'content':'
|
33 |
-
{'role':'user', 'content':'Abstract:
|
34 |
-
|
35 |
-
|
36 |
-
|
37 |
-
|
38 |
-
|
39 |
-
|
40 |
-
|
41 |
-
|
42 |
-
|
43 |
-
|
44 |
-
|
45 |
-
|
46 |
-
|
47 |
-
|
48 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
49 |
]
|
50 |
messages.append({'role':'user', 'content':f"Abstract: {text}"})
|
51 |
response = get_completion_from_messages(messages, temperature=0)
|
@@ -81,4 +88,4 @@ def gradio():
|
|
81 |
|
82 |
|
83 |
if __name__ == '__main__':
|
84 |
-
gradio()
|
|
|
13 |
|
14 |
def get_response(text):
|
15 |
messages = [
|
16 |
+
{'role':'system', 'content':'You are a paper abstract information extractor, \
|
17 |
the user inputs a paper abstract, and you are responsible for extracting information. \
|
18 |
+
The information extracted is: What state of the cancer (this state is usually a mutation in a driver gene) is dependent on which genes or pathways. \
|
19 |
+
Do not show other information. When there is no such information, just return "No dependency"'},
|
|
|
20 |
{'role':'user', 'content':'Abstract: In non–small cell lung cancer (NSCLC), \
|
21 |
concurrent mutations in the oncogene KRAS and the tumor suppressor STK11 encoding the kinase LKB1 result in aggressive tumors \
|
22 |
prone to metastasis but with liabilities arising from reprogrammed metabolism. \
|
|
|
28 |
higher flux through the HBP pathway and elevated dependence on the HBP enzyme Glutamine-Fructose-6-Phosphate Transaminase 2 (GFPT2). \
|
29 |
GFPT2 inhibition selectively reduced KL tumor cell growth in culture, xenografts and genetically-modified mice. \
|
30 |
Our results define a new metabolic vulnerability in KL tumors and provide a rationale for targeting GFPT2 in this aggressive NSCLC subtype.'},
|
31 |
+
{'role':'assistant', 'content':'KRAS/LKB1 co-mutant non–small cell lung cancer is dependent on Hexosamine biosynthesis pathway (HBP) and GFPT2.'},
|
32 |
+
{'role':'user', 'content':'Abstract: Background: Thymidylate synthase (TYMS) is a successful chemotherapeutic target for anticancer therapy. \
|
33 |
+
Numerous TYMS inhibitors have been developed and used for treating gastrointestinal cancer now, but they have limited clinical benefits due to \
|
34 |
+
the prevalent unresponsiveness and toxicity. It is urgent to identify a predictive biomarker to guide the precise clinical use of TYMS inhibitors. \
|
35 |
+
Methods: Genome-scale CRISPR-Cas9 knockout screening was performed to identify potential therapeutic targets for treating gastrointestinal tumours \
|
36 |
+
as well as key regulators of raltitrexed (RTX) sensitivity. Cell-based functional assays were used to investigate how \
|
37 |
+
MYC regulates TYMS transcription. Cancer patient data were used to verify the correlation between drug response and MYC and/or TYMS mRNA levels. \
|
38 |
+
Finally, the role of NIPBL inactivation in gastrointestinal cancer was evaluated in vitro and in vivo. \
|
39 |
+
Findings: TYMS is essential for maintaining the viability of gastrointestinal cancer cells, and is selectively inhibited by RTX. \
|
40 |
+
Mechanistically, MYC presets gastrointestinal cancer sensitivity to RTX through upregulating TYMS transcription, \
|
41 |
+
supported by TCGA data showing that complete response cases to TYMS inhibitors had significantly higher MYC and \
|
42 |
+
TYMS mRNA levels than those of progressive diseases. NIPBL inactivation decreases the therapeutic responses of \
|
43 |
+
gastrointestinal cancer to RTX through blocking MYC. Interpretation: Our study unveils a mechanism of how TYMS is \
|
44 |
+
transcriptionally regulated by MYC, and provides rationales for the precise use of TYMS inhibitors in the clinic.'},
|
45 |
+
{'role':'assistant', 'content':'Gastrointestinal cancer with up-regulated MYC is dependent on TYMS.'},
|
46 |
+
{'role':'user', 'content':'Abstract: Studies have characterized the immune escape landscape across primary tumors. \
|
47 |
+
However, whether late-stage metastatic tumors present differences in genetic immune escape (GIE) prevalence and dynamics remains unclear. \
|
48 |
+
We performed a pan-cancer characterization of GIE prevalence across six immune escape pathways in 6,319 uniformly processed tumor samples. \
|
49 |
+
To address the complexity of the HLA-I locus in the germline and in tumors, we developed LILAC, an open-source integrative framework. \
|
50 |
+
One in four tumors harbors GIE alterations, with high mechanistic and frequency variability across cancer types. \
|
51 |
+
GIE prevalence is generally consistent between primary and metastatic tumors. We reveal that GIE alterations are selected for \
|
52 |
+
in tumor evolution and focal loss of heterozygosity of HLA-I tends to eliminate the HLA allele, presenting the largest neoepitope repertoire. \
|
53 |
+
Finally, high mutational burden tumors showed a tendency toward focal loss of heterozygosity of HLA-I as the immune evasion mechanism, \
|
54 |
+
whereas, in hypermutated tumors, other immune evasion strategies prevail.'},
|
55 |
+
{'role':'assistant', 'content':'No dependency'}
|
56 |
]
|
57 |
messages.append({'role':'user', 'content':f"Abstract: {text}"})
|
58 |
response = get_completion_from_messages(messages, temperature=0)
|
|
|
88 |
|
89 |
|
90 |
if __name__ == '__main__':
|
91 |
+
gradio()
|